Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (311 commits)
  perf tools: Add mode to build without newt support
  perf symbols: symbol inconsistency message should be done only at verbose=1
  perf tui: Add explicit -lslang option
  perf options: Type check all the remaining OPT_ variants
  perf options: Type check OPT_BOOLEAN and fix the offenders
  perf options: Check v type in OPT_U?INTEGER
  perf options: Introduce OPT_UINTEGER
  perf tui: Add workaround for slang < 2.1.4
  perf record: Fix bug mismatch with -c option definition
  perf options: Introduce OPT_U64
  perf tui: Add help window to show key associations
  perf tui: Make <- exit menus too
  perf newt: Add single key shortcuts for zoom into DSO and threads
  perf newt: Exit browser unconditionally when CTRL+C, q or Q is pressed
  perf newt: Fix the 'A'/'a' shortcut for annotate
  perf newt: Make <- exit the ui_browser
  x86, perf: P4 PMU - fix counters management logic
  perf newt: Make <- zoom out filters
  perf report: Report number of events, not samples
  perf hist: Clarify events_stats fields usage
  ...

Fix up trivial conflicts in kernel/fork.c and tools/perf/builtin-record.c

55 files changed, 6975 insertions, 1977 deletions

diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 54552a00a117..49ece7921914 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -1,6 +1,10 @@
 #!/bin/sh
 
-GVF=PERF-VERSION-FILE
+if [ $# -eq 1 ]  ; then
+	OUTPUT=$1
+fi
+
+GVF=${OUTPUT}PERF-VERSION-FILE
 DEF_VER=v0.0.2.PERF
 
 LF='
diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c
new file mode 100644
index 000000000000..5e230acae1e9
--- /dev/null
+++ b/tools/perf/util/bitmap.c
@@ -0,0 +1,21 @@
+/*
+ * From lib/bitmap.c
+ * Helper functions for bitmap.h.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+#include <linux/bitmap.h>
+
+int __bitmap_weight(const unsigned long *bitmap, int bits)
+{
+	int k, w = 0, lim = bits/BITS_PER_LONG;
+
+	for (k = 0; k < lim; k++)
+		w += hweight_long(bitmap[k]);
+
+	if (bits % BITS_PER_LONG)
+		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
+
+	return w;
+}
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 04904b35ba81..0f60a3906808 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -24,7 +24,7 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
 	}
 
 	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      event->ip.pid, event->ip.ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 918eb376abe3..4b9aab7f0405 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
+#include <stdbool.h>
 #include "util.h"
 #include "strbuf.h"
 #include "../perf.h"
@@ -69,6 +70,19 @@ extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
+extern bool use_browser;
+
+#ifdef NO_NEWT_SUPPORT
+static inline void setup_browser(void)
+{
+	setup_pager();
+}
+static inline void exit_browser(bool wait_for_ok __used) {}
+#else
+void setup_browser(void);
+void exit_browser(bool wait_for_ok);
+#endif
+
 extern const char *editor_program;
 extern const char *excludes_file;
 
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index b3b71258272a..21a52e0a4435 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Handle the callchains from the stream in an ad-hoc radix tree and then
  * sort them in an rbtree.
@@ -17,6 +17,13 @@
 
 #include "callchain.h"
 
+bool ip_callchain__valid(struct ip_callchain *chain, event_t *event)
+{
+	unsigned int chain_size = event->header.size;
+	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
+	return chain->nr * sizeof(u64) <= chain_size;
+}
+
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, brothers)
 
@@ -160,7 +167,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 {
 	struct callchain_node *new;
 
-	new = malloc(sizeof(*new));
+	new = zalloc(sizeof(*new));
 	if (!new) {
 		perror("not enough memory to create child for code path tree");
 		return NULL;
@@ -183,25 +190,36 @@ create_child(struct callchain_node *parent, bool inherit_children)
 	return new;
 }
 
+
+struct resolved_ip {
+	u64		  ip;
+	struct map_symbol ms;
+};
+
+struct resolved_chain {
+	u64			nr;
+	struct resolved_ip	ips[0];
+};
+
+
 /*
  * Fill the node with callchain values
  */
 static void
-fill_node(struct callchain_node *node, struct ip_callchain *chain,
-	  int start, struct symbol **syms)
+fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 {
 	unsigned int i;
 
 	for (i = start; i < chain->nr; i++) {
 		struct callchain_list *call;
 
-		call = malloc(sizeof(*call));
+		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
 			return;
 		}
-		call->ip = chain->ips[i];
-		call->sym = syms[i];
+		call->ip = chain->ips[i].ip;
+		call->ms = chain->ips[i].ms;
 		list_add_tail(&call->list, &node->val);
 	}
 	node->val_nr = chain->nr - start;
@@ -210,13 +228,13 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain,
 }
 
 static void
-add_child(struct callchain_node *parent, struct ip_callchain *chain,
-	  int start, struct symbol **syms)
+add_child(struct callchain_node *parent, struct resolved_chain *chain,
+	  int start)
 {
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, chain, start, syms);
+	fill_node(new, chain, start);
 
 	new->children_hit = 0;
 	new->hit = 1;
@@ -228,9 +246,8 @@ add_child(struct callchain_node *parent, struct ip_callchain *chain,
  * Then create another child to host the given callchain of new branch
  */
 static void
-split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local,
-		struct symbol **syms)
+split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
+		struct callchain_list *to_split, int idx_parents, int idx_local)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -257,7 +274,7 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
 	/* create a new child for the new branch if any */
 	if (idx_total < chain->nr) {
 		parent->hit = 0;
-		add_child(parent, chain, idx_total, syms);
+		add_child(parent, chain, idx_total);
 		parent->children_hit++;
 	} else {
 		parent->hit = 1;
@@ -265,32 +282,33 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain,
 }
 
 static int
-__append_chain(struct callchain_node *root, struct ip_callchain *chain,
-	       unsigned int start, struct symbol **syms);
+__append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	       unsigned int start);
 
 static void
-__append_chain_children(struct callchain_node *root, struct ip_callchain *chain,
-			struct symbol **syms, unsigned int start)
+__append_chain_children(struct callchain_node *root,
+			struct resolved_chain *chain,
+			unsigned int start)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start, syms);
+		unsigned int ret = __append_chain(rnode, chain, start);
 
 		if (!ret)
 			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start, syms);
+	add_child(root, chain, start);
 
 inc_children_hit:
 	root->children_hit++;
 }
 
 static int
-__append_chain(struct callchain_node *root, struct ip_callchain *chain,
-	       unsigned int start, struct symbol **syms)
+__append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	       unsigned int start)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -302,13 +320,19 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	 * anywhere inside a function.
 	 */
 	list_for_each_entry(cnode, &root->val, list) {
+		struct symbol *sym;
+
 		if (i == chain->nr)
 			break;
-		if (cnode->sym && syms[i]) {
-			if (cnode->sym->start != syms[i]->start)
+
+		sym = chain->ips[i].ms.sym;
+
+		if (cnode->ms.sym && sym) {
+			if (cnode->ms.sym->start != sym->start)
 				break;
-		} else if (cnode->ip != chain->ips[i])
+		} else if (cnode->ip != chain->ips[i].ip)
 			break;
+
 		if (!found)
 			found = true;
 		i++;
@@ -320,7 +344,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start, syms);
+		split_add_child(root, chain, cnode, start, i - start);
 		return 0;
 	}
 
@@ -331,15 +355,50 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, syms, i);
+	__append_chain_children(root, chain, i);
 
 	return 0;
 }
 
-void append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		  struct symbol **syms)
+static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
+			   struct map_symbol *syms)
 {
+	int i, j = 0;
+
+	for (i = 0; i < (int)old->nr; i++) {
+		if (old->ips[i] >= PERF_CONTEXT_MAX)
+			continue;
+
+		new->ips[j].ip = old->ips[i];
+		new->ips[j].ms = syms[i];
+		j++;
+	}
+
+	new->nr = j;
+}
+
+
+int append_chain(struct callchain_node *root, struct ip_callchain *chain,
+		 struct map_symbol *syms)
+{
+	struct resolved_chain *filtered;
+
 	if (!chain->nr)
-		return;
-	__append_chain_children(root, chain, syms, 0);
+		return 0;
+
+	filtered = zalloc(sizeof(*filtered) +
+			  chain->nr * sizeof(struct resolved_ip));
+	if (!filtered)
+		return -ENOMEM;
+
+	filter_context(chain, filtered, syms);
+
+	if (!filtered->nr)
+		goto end;
+
+	__append_chain_children(root, filtered, 0);
+end:
+	free(filtered);
+
+	return 0;
 }
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index ad4626de4c2b..1cba1f5504e7 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -4,6 +4,7 @@
 #include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include "event.h"
 #include "util.h"
 #include "symbol.h"
 
@@ -33,13 +34,14 @@ typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_node *,
 
 struct callchain_param {
 	enum chain_mode 	mode;
+	u32			print_limit;
 	double			min_percent;
 	sort_chain_func_t	sort;
 };
 
 struct callchain_list {
 	u64			ip;
-	struct symbol		*sym;
+	struct map_symbol	ms;
 	struct list_head	list;
 };
 
@@ -56,6 +58,8 @@ static inline u64 cumul_hits(struct callchain_node *node)
 }
 
 int register_callchain_param(struct callchain_param *param);
-void append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		  struct symbol **syms);
+int append_chain(struct callchain_node *root, struct ip_callchain *chain,
+		 struct map_symbol *syms);
+
+bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e88bca55a599..e191eb9a667f 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -166,6 +166,31 @@ int perf_color_default_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
+static int __color_vsnprintf(char *bf, size_t size, const char *color,
+			     const char *fmt, va_list args, const char *trail)
+{
+	int r = 0;
+
+	/*
+	 * Auto-detect:
+	 */
+	if (perf_use_color_default < 0) {
+		if (isatty(1) || pager_in_use())
+			perf_use_color_default = 1;
+		else
+			perf_use_color_default = 0;
+	}
+
+	if (perf_use_color_default && *color)
+		r += snprintf(bf, size, "%s", color);
+	r += vsnprintf(bf + r, size - r, fmt, args);
+	if (perf_use_color_default && *color)
+		r += snprintf(bf + r, size - r, "%s", PERF_COLOR_RESET);
+	if (trail)
+		r += snprintf(bf + r, size - r, "%s", trail);
+	return r;
+}
+
 static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 		va_list args, const char *trail)
 {
@@ -191,11 +216,28 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt,
 	return r;
 }
 
+int color_vsnprintf(char *bf, size_t size, const char *color,
+		    const char *fmt, va_list args)
+{
+	return __color_vsnprintf(bf, size, color, fmt, args, NULL);
+}
+
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args)
 {
 	return __color_vfprintf(fp, color, fmt, args, NULL);
 }
 
+int color_snprintf(char *bf, size_t size, const char *color,
+		   const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	va_start(args, fmt);
+	r = color_vsnprintf(bf, size, color, fmt, args);
+	va_end(args);
+	return r;
+}
 
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)
 {
@@ -274,3 +316,9 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
 
 	return r;
 }
+
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent)
+{
+	const char *color = get_percent_color(percent);
+	return color_snprintf(bf, size, color, fmt, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 24e8809210bb..dea082b79602 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -32,10 +32,14 @@ int perf_color_default_config(const char *var, const char *value, void *cb);
 int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty);
 void color_parse(const char *value, const char *var, char *dst);
 void color_parse_mem(const char *value, int len, const char *var, char *dst);
+int color_vsnprintf(char *bf, size_t size, const char *color,
+		    const char *fmt, va_list args);
 int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args);
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
+int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 0905600c3851..dd824cf3b628 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -6,13 +6,14 @@
 #include <stdarg.h>
 #include <stdio.h>
 
+#include "cache.h"
 #include "color.h"
 #include "event.h"
 #include "debug.h"
 #include "util.h"
 
 int verbose = 0;
-int dump_trace = 0;
+bool dump_trace = false;
 
 int eprintf(int level, const char *fmt, ...)
 {
@@ -21,7 +22,10 @@ int eprintf(int level, const char *fmt, ...)
 
 	if (verbose >= level) {
 		va_start(args, fmt);
-		ret = vfprintf(stderr, fmt, args);
+		if (use_browser)
+			ret = browser__show_help(fmt, args);
+		else
+			ret = vfprintf(stderr, fmt, args);
 		va_end(args);
 	}
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index c6c24c522dea..047ac3324ebe 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -2,14 +2,38 @@
 #ifndef __PERF_DEBUG_H
 #define __PERF_DEBUG_H
 
+#include <stdbool.h>
 #include "event.h"
 
 extern int verbose;
-extern int dump_trace;
+extern bool dump_trace;
 
-int eprintf(int level,
-	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(event_t *event);
 
+struct ui_progress;
+
+#ifdef NO_NEWT_SUPPORT
+static inline int browser__show_help(const char *format __used, va_list ap __used)
+{
+	return 0;
+}
+
+static inline struct ui_progress *ui_progress__new(const char *title __used,
+						   u64 total __used)
+{
+	return (struct ui_progress *)1;
+}
+
+static inline void ui_progress__update(struct ui_progress *self __used,
+				       u64 curr __used) {}
+
+static inline void ui_progress__delete(struct ui_progress *self __used) {}
+#else
+int browser__show_help(const char *format, va_list ap);
+struct ui_progress *ui_progress__new(const char *title, u64 total);
+void ui_progress__update(struct ui_progress *self, u64 curr);
+void ui_progress__delete(struct ui_progress *self);
+#endif
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 705ec63548b4..50771b5813ee 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,6 +7,23 @@
 #include "strlist.h"
 #include "thread.h"
 
+const char *event__name[] = {
+	[0]			 = "TOTAL",
+	[PERF_RECORD_MMAP]	 = "MMAP",
+	[PERF_RECORD_LOST]	 = "LOST",
+	[PERF_RECORD_COMM]	 = "COMM",
+	[PERF_RECORD_EXIT]	 = "EXIT",
+	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
+	[PERF_RECORD_FORK]	 = "FORK",
+	[PERF_RECORD_READ]	 = "READ",
+	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
+	[PERF_RECORD_HEADER_ATTR]	 = "ATTR",
+	[PERF_RECORD_HEADER_EVENT_TYPE]	 = "EVENT_TYPE",
+	[PERF_RECORD_HEADER_TRACING_DATA]	 = "TRACING_DATA",
+	[PERF_RECORD_HEADER_BUILD_ID]	 = "BUILD_ID",
+};
+
 static pid_t event__synthesize_comm(pid_t pid, int full,
 				    event__handler_t process,
 				    struct perf_session *session)
@@ -112,7 +129,11 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 		event_t ev = {
 			.header = {
 				.type = PERF_RECORD_MMAP,
-				.misc = 0, /* Just like the kernel, see kernel/perf_event.c __perf_event_mmap */
+				/*
+				 * Just like the kernel, see __perf_event_mmap
+				 * in kernel/perf_event.c
+				 */
+				.misc = PERF_RECORD_MISC_USER,
 			 },
 		};
 		int n;
@@ -130,6 +151,7 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 			continue;
 		pbf += n + 3;
 		if (*pbf == 'x') { /* vm_exec */
+			u64 vm_pgoff;
 			char *execname = strchr(bf, '/');
 
 			/* Catch VDSO */
@@ -139,6 +161,14 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 			if (execname == NULL)
 				continue;
 
+			pbf += 3;
+			n = hex2u64(pbf, &vm_pgoff);
+			/* pgoff is in bytes, not pages */
+			if (n >= 0)
+				ev.mmap.pgoff = vm_pgoff << getpagesize();
+			else
+				ev.mmap.pgoff = 0;
+
 			size = strlen(execname);
 			execname[size - 1] = '\0'; /* Remove \n */
 			memcpy(ev.mmap.filename, execname, size);
@@ -158,11 +188,23 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
 }
 
 int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session)
+			      struct perf_session *session,
+			      struct machine *machine)
 {
 	struct rb_node *nd;
+	struct map_groups *kmaps = &machine->kmaps;
+	u16 misc;
+
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(machine))
+		misc = PERF_RECORD_MISC_KERNEL;
+	else
+		misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-	for (nd = rb_first(&session->kmaps.maps[MAP__FUNCTION]);
+	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
 	     nd; nd = rb_next(nd)) {
 		event_t ev;
 		size_t size;
@@ -173,12 +215,13 @@ int event__synthesize_modules(event__handler_t process,
 
 		size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
 		memset(&ev, 0, sizeof(ev));
-		ev.mmap.header.misc = 1; /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
+		ev.mmap.header.misc = misc;
 		ev.mmap.header.type = PERF_RECORD_MMAP;
 		ev.mmap.header.size = (sizeof(ev.mmap) -
 				        (sizeof(ev.mmap.filename) - size));
 		ev.mmap.start = pos->start;
 		ev.mmap.len   = pos->end - pos->start;
+		ev.mmap.pid   = machine->pid;
 
 		memcpy(ev.mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
@@ -241,13 +284,18 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
 
 int event__synthesize_kernel_mmap(event__handler_t process,
 				  struct perf_session *session,
+				  struct machine *machine,
 				  const char *symbol_name)
 {
 	size_t size;
+	const char *filename, *mmap_name;
+	char path[PATH_MAX];
+	char name_buff[PATH_MAX];
+	struct map *map;
+
 	event_t ev = {
 		.header = {
 			.type = PERF_RECORD_MMAP,
-			.misc = 1, /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
 		},
 	};
 	/*
@@ -257,16 +305,37 @@ int event__synthesize_kernel_mmap(event__handler_t process,
 	 */
 	struct process_symbol_args args = { .name = symbol_name, };
 
-	if (kallsyms__parse("/proc/kallsyms", &args, find_symbol_cb) <= 0)
+	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
+	if (machine__is_host(machine)) {
+		/*
+		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
+		 * see kernel/perf_event.c __perf_event_mmap
+		 */
+		ev.header.misc = PERF_RECORD_MISC_KERNEL;
+		filename = "/proc/kallsyms";
+	} else {
+		ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+		if (machine__is_default_guest(machine))
+			filename = (char *) symbol_conf.default_guest_kallsyms;
+		else {
+			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+			filename = path;
+		}
+	}
+
+	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0)
 		return -ENOENT;
 
+	map = machine->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
-			"[kernel.kallsyms.%s]", symbol_name) + 1;
+			"%s%s", mmap_name, symbol_name) + 1;
 	size = ALIGN(size, sizeof(u64));
-	ev.mmap.header.size = (sizeof(ev.mmap) - (sizeof(ev.mmap.filename) - size));
+	ev.mmap.header.size = (sizeof(ev.mmap) -
+			(sizeof(ev.mmap.filename) - size));
 	ev.mmap.pgoff = args.start;
-	ev.mmap.start = session->vmlinux_maps[MAP__FUNCTION]->start;
-	ev.mmap.len   = session->vmlinux_maps[MAP__FUNCTION]->end - ev.mmap.start ;
+	ev.mmap.start = map->start;
+	ev.mmap.len   = map->end - ev.mmap.start;
+	ev.mmap.pid   = machine->pid;
 
 	return process(&ev, session);
 }
@@ -316,26 +385,54 @@ int event__process_comm(event_t *self, struct perf_session *session)
 int event__process_lost(event_t *self, struct perf_session *session)
 {
 	dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
-	session->events_stats.lost += self->lost.lost;
+	session->hists.stats.total_lost += self->lost.lost;
 	return 0;
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
+{
+	maps[MAP__FUNCTION]->start = self->mmap.start;
+	maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
+	/*
+	 * Be a bit paranoid here, some perf.data file came with
+	 * a zero sized synthesized MMAP event for the kernel.
+	 */
+	if (maps[MAP__FUNCTION]->end == 0)
+		maps[MAP__FUNCTION]->end = ~0UL;
+}
+
+static int event__process_kernel_mmap(event_t *self,
+			struct perf_session *session)
 {
-	struct thread *thread;
 	struct map *map;
+	char kmmap_prefix[PATH_MAX];
+	struct machine *machine;
+	enum dso_kernel_type kernel_type;
+	bool is_kernel_mmap;
+
+	machine = perf_session__findnew_machine(session, self->mmap.pid);
+	if (!machine) {
+		pr_err("Can't find id %d's machine\n", self->mmap.pid);
+		goto out_problem;
+	}
 
-	dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
-		    self->mmap.pid, self->mmap.tid, self->mmap.start,
-		    self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+	machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
+	if (machine__is_host(machine))
+		kernel_type = DSO_TYPE_KERNEL;
+	else
+		kernel_type = DSO_TYPE_GUEST_KERNEL;
 
-	if (self->mmap.pid == 0) {
-		static const char kmmap_prefix[] = "[kernel.kallsyms.";
+	is_kernel_mmap = memcmp(self->mmap.filename,
+				kmmap_prefix,
+				strlen(kmmap_prefix)) == 0;
+	if (self->mmap.filename[0] == '/' ||
+	    (!is_kernel_mmap && self->mmap.filename[0] == '[')) {
 
-		if (self->mmap.filename[0] == '/') {
-			char short_module_name[1024];
-			char *name = strrchr(self->mmap.filename, '/'), *dot;
+		char short_module_name[1024];
+		char *name, *dot;
 
+		if (self->mmap.filename[0] == '/') {
+			name = strrchr(self->mmap.filename, '/');
 			if (name == NULL)
 				goto out_problem;
 
@@ -343,58 +440,84 @@ int event__process_mmap(event_t *self, struct perf_session *session)
 			dot = strrchr(name, '.');
 			if (dot == NULL)
 				goto out_problem;
-
 			snprintf(short_module_name, sizeof(short_module_name),
-				 "[%.*s]", (int)(dot - name), name);
+					"[%.*s]", (int)(dot - name), name);
 			strxfrchar(short_module_name, '-', '_');
-
-			map = perf_session__new_module_map(session,
-							   self->mmap.start,
-							   self->mmap.filename);
-			if (map == NULL)
-				goto out_problem;
-
-			name = strdup(short_module_name);
-			if (name == NULL)
-				goto out_problem;
-
-			map->dso->short_name = name;
-			map->end = map->start + self->mmap.len;
-		} else if (memcmp(self->mmap.filename, kmmap_prefix,
-				sizeof(kmmap_prefix) - 1) == 0) {
-			const char *symbol_name = (self->mmap.filename +
-						   sizeof(kmmap_prefix) - 1);
+		} else
+			strcpy(short_module_name, self->mmap.filename);
+
+		map = machine__new_module(machine, self->mmap.start,
+					  self->mmap.filename);
+		if (map == NULL)
+			goto out_problem;
+
+		name = strdup(short_module_name);
+		if (name == NULL)
+			goto out_problem;
+
+		map->dso->short_name = name;
+		map->end = map->start + self->mmap.len;
+	} else if (is_kernel_mmap) {
+		const char *symbol_name = (self->mmap.filename +
+				strlen(kmmap_prefix));
+		/*
+		 * Should be there already, from the build-id table in
+		 * the header.
+		 */
+		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
+						     kmmap_prefix);
+		if (kernel == NULL)
+			goto out_problem;
+
+		kernel->kernel = kernel_type;
+		if (__machine__create_kernel_maps(machine, kernel) < 0)
+			goto out_problem;
+
+		event_set_kernel_mmap_len(machine->vmlinux_maps, self);
+		perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+							 symbol_name,
+							 self->mmap.pgoff);
+		if (machine__is_default_guest(machine)) {
 			/*
-			 * Should be there already, from the build-id table in
-			 * the header.
+			 * preload dso of guest kernel and modules
 			 */
-			struct dso *kernel = __dsos__findnew(&dsos__kernel,
-							     "[kernel.kallsyms]");
-			if (kernel == NULL)
-				goto out_problem;
-
-			kernel->kernel = 1;
-			if (__perf_session__create_kernel_maps(session, kernel) < 0)
-				goto out_problem;
+			dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION],
+				  NULL);
+		}
+	}
+	return 0;
+out_problem:
+	return -1;
+}
 
-			session->vmlinux_maps[MAP__FUNCTION]->start = self->mmap.start;
-			session->vmlinux_maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
-			/*
-			 * Be a bit paranoid here, some perf.data file came with
-			 * a zero sized synthesized MMAP event for the kernel.
-			 */
-			if (session->vmlinux_maps[MAP__FUNCTION]->end == 0)
-				session->vmlinux_maps[MAP__FUNCTION]->end = ~0UL;
+int event__process_mmap(event_t *self, struct perf_session *session)
+{
+	struct machine *machine;
+	struct thread *thread;
+	struct map *map;
+	u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	int ret = 0;
 
-			perf_session__set_kallsyms_ref_reloc_sym(session, symbol_name,
-								 self->mmap.pgoff);
-		}
+	dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
+			self->mmap.pid, self->mmap.tid, self->mmap.start,
+			self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+
+	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	    cpumode == PERF_RECORD_MISC_KERNEL) {
+		ret = event__process_kernel_mmap(self, session);
+		if (ret < 0)
+			goto out_problem;
 		return 0;
 	}
 
+	machine = perf_session__find_host_machine(session);
+	if (machine == NULL)
+		goto out_problem;
 	thread = perf_session__findnew(session, self->mmap.pid);
-	map = map__new(&self->mmap, MAP__FUNCTION,
-		       session->cwd, session->cwdlen);
+	map = map__new(&machine->user_dsos, self->mmap.start,
+			self->mmap.len, self->mmap.pgoff,
+			self->mmap.pid, self->mmap.filename,
+			MAP__FUNCTION, session->cwd, session->cwdlen);
 
 	if (thread == NULL || map == NULL)
 		goto out_problem;
@@ -434,22 +557,56 @@ int event__process_task(event_t *self, struct perf_session *session)
 
 void thread__find_addr_map(struct thread *self,
 			   struct perf_session *session, u8 cpumode,
-			   enum map_type type, u64 addr,
+			   enum map_type type, pid_t pid, u64 addr,
 			   struct addr_location *al)
 {
 	struct map_groups *mg = &self->mg;
+	struct machine *machine = NULL;
 
 	al->thread = self;
 	al->addr = addr;
+	al->cpumode = cpumode;
+	al->filtered = false;
 
-	if (cpumode == PERF_RECORD_MISC_KERNEL) {
+	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
-		mg = &session->kmaps;
-	} else if (cpumode == PERF_RECORD_MISC_USER)
+		machine = perf_session__find_host_machine(session);
+		if (machine == NULL) {
+			al->map = NULL;
+			return;
+		}
+		mg = &machine->kmaps;
+	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
-	else {
-		al->level = 'H';
+		machine = perf_session__find_host_machine(session);
+	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+		al->level = 'g';
+		machine = perf_session__find_machine(session, pid);
+		if (machine == NULL) {
+			al->map = NULL;
+			return;
+		}
+		mg = &machine->kmaps;
+	} else {
+		/*
+		 * 'u' means guest os user space.
+		 * TODO: We don't support guest user space. Might support late.
+		 */
+		if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest)
+			al->level = 'u';
+		else
+			al->level = 'H';
 		al->map = NULL;
+
+		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
+			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
+			!perf_guest)
+			al->filtered = true;
+		if ((cpumode == PERF_RECORD_MISC_USER ||
+			cpumode == PERF_RECORD_MISC_KERNEL) &&
+			!perf_host)
+			al->filtered = true;
+
 		return;
 	}
 try_again:
@@ -464,8 +621,10 @@ try_again:
 		 * "[vdso]" dso, but for now lets use the old trick of looking
 		 * in the whole kernel symbol list.
 		 */
-		if ((long long)al->addr < 0 && mg != &session->kmaps) {
-			mg = &session->kmaps;
+		if ((long long)al->addr < 0 &&
+		    cpumode == PERF_RECORD_MISC_KERNEL &&
+		    machine && mg != &machine->kmaps) {
+			mg = &machine->kmaps;
 			goto try_again;
 		}
 	} else
@@ -474,11 +633,11 @@ try_again:
 
 void thread__find_addr_location(struct thread *self,
 				struct perf_session *session, u8 cpumode,
-				enum map_type type, u64 addr,
+				enum map_type type, pid_t pid, u64 addr,
 				struct addr_location *al,
 				symbol_filter_t filter)
 {
-	thread__find_addr_map(self, session, cpumode, type, addr, al);
+	thread__find_addr_map(self, session, cpumode, type, pid, addr, al);
 	if (al->map != NULL)
 		al->sym = map__find_symbol(al->map, al->addr, filter);
 	else
@@ -490,8 +649,10 @@ static void dso__calc_col_width(struct dso *self)
 	if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
 	    (!symbol_conf.dso_list ||
 	     strlist__has_entry(symbol_conf.dso_list, self->name))) {
-		unsigned int slen = strlen(self->name);
-		if (slen > dsos__col_width)
+		u16 slen = self->short_name_len;
+		if (verbose)
+			slen = self->long_name_len;
+		if (dsos__col_width < slen)
 			dsos__col_width = slen;
 	}
 
@@ -512,31 +673,55 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 		goto out_filtered;
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	/*
+	 * Have we already created the kernel maps for the host machine?
+	 *
+	 * This should have happened earlier, when we processed the kernel MMAP
+	 * events, but for older perf.data files there was no such thing, so do
+	 * it now.
+	 */
+	if (cpumode == PERF_RECORD_MISC_KERNEL &&
+	    session->host_machine.vmlinux_maps[MAP__FUNCTION] == NULL)
+		machine__create_kernel_maps(&session->host_machine);
 
-	thread__find_addr_location(thread, session, cpumode, MAP__FUNCTION,
-				   self->ip.ip, al, filter);
+	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+			      self->ip.pid, self->ip.ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
-	/*
-	 * We have to do this here as we may have a dso with no symbol hit that
-	 * has a name longer than the ones with symbols sampled.
-	 */
-	if (al->map && !sort_dso.elide && !al->map->dso->slen_calculated)
-		dso__calc_col_width(al->map->dso);
-
-	if (symbol_conf.dso_list &&
-	    (!al->map || !al->map->dso ||
-	     !(strlist__has_entry(symbol_conf.dso_list, al->map->dso->short_name) ||
-	       (al->map->dso->short_name != al->map->dso->long_name &&
-		strlist__has_entry(symbol_conf.dso_list, al->map->dso->long_name)))))
-		goto out_filtered;
+	al->sym = NULL;
+
+	if (al->map) {
+		if (symbol_conf.dso_list &&
+		    (!al->map || !al->map->dso ||
+		     !(strlist__has_entry(symbol_conf.dso_list,
+					  al->map->dso->short_name) ||
+		       (al->map->dso->short_name != al->map->dso->long_name &&
+			strlist__has_entry(symbol_conf.dso_list,
+					   al->map->dso->long_name)))))
+			goto out_filtered;
+		/*
+		 * We have to do this here as we may have a dso with no symbol
+		 * hit that has a name longer than the ones with symbols
+		 * sampled.
+		 */
+		if (!sort_dso.elide && !al->map->dso->slen_calculated)
+			dso__calc_col_width(al->map->dso);
+
+		al->sym = map__find_symbol(al->map, al->addr, filter);
+	} else {
+		const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+		if (dsos__col_width < unresolved_col_width &&
+		    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+		    !symbol_conf.dso_list)
+			dsos__col_width = unresolved_col_width;
+	}
 
 	if (symbol_conf.sym_list && al->sym &&
 	    !strlist__has_entry(symbol_conf.sym_list, al->sym->name))
 		goto out_filtered;
 
-	al->filtered = false;
 	return 0;
 
 out_filtered:
@@ -570,6 +755,7 @@ int event__parse_sample(event_t *event, u64 type, struct sample_data *data)
 		array++;
 	}
 
+	data->id = -1ULL;
 	if (type & PERF_SAMPLE_ID) {
 		data->id = *array;
 		array++;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a33b94952e34..8577085db067 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -68,21 +68,54 @@ struct sample_data {
 	u64 addr;
 	u64 id;
 	u64 stream_id;
-	u32 cpu;
 	u64 period;
-	struct ip_callchain *callchain;
+	u32 cpu;
 	u32 raw_size;
 	void *raw_data;
+	struct ip_callchain *callchain;
 };
 
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
 	struct perf_event_header header;
+	pid_t			 pid;
 	u8			 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
 	char			 filename[];
 };
 
+enum perf_user_event_type { /* above any possible kernel type */
+	PERF_RECORD_HEADER_ATTR			= 64,
+	PERF_RECORD_HEADER_EVENT_TYPE		= 65,
+	PERF_RECORD_HEADER_TRACING_DATA		= 66,
+	PERF_RECORD_HEADER_BUILD_ID		= 67,
+	PERF_RECORD_FINISHED_ROUND		= 68,
+	PERF_RECORD_HEADER_MAX
+};
+
+struct attr_event {
+	struct perf_event_header header;
+	struct perf_event_attr attr;
+	u64 id[];
+};
+
+#define MAX_EVENT_NAME 64
+
+struct perf_trace_event_type {
+	u64	event_id;
+	char	name[MAX_EVENT_NAME];
+};
+
+struct event_type_event {
+	struct perf_event_header header;
+	struct perf_trace_event_type event_type;
+};
+
+struct tracing_data_event {
+	struct perf_event_header header;
+	u32 size;
+};
+
 typedef union event_union {
 	struct perf_event_header	header;
 	struct ip_event			ip;
@@ -92,22 +125,12 @@ typedef union event_union {
 	struct lost_event		lost;
 	struct read_event		read;
 	struct sample_event		sample;
+	struct attr_event		attr;
+	struct event_type_event		event_type;
+	struct tracing_data_event	tracing_data;
+	struct build_id_event		build_id;
 } event_t;
 
-struct events_stats {
-	u64 total;
-	u64 lost;
-};
-
-struct event_stat_id {
-	struct rb_node		rb_node;
-	struct rb_root		hists;
-	struct events_stats	stats;
-	u64			config;
-	u64			event_stream;
-	u32			type;
-};
-
 void event__print_totals(void);
 
 struct perf_session;
@@ -119,10 +142,13 @@ int event__synthesize_thread(pid_t pid, event__handler_t process,
 void event__synthesize_threads(event__handler_t process,
 			       struct perf_session *session);
 int event__synthesize_kernel_mmap(event__handler_t process,
-				  struct perf_session *session,
-				  const char *symbol_name);
+				struct perf_session *session,
+				struct machine *machine,
+				const char *symbol_name);
+
 int event__synthesize_modules(event__handler_t process,
-			      struct perf_session *session);
+			      struct perf_session *session,
+			      struct machine *machine);
 
 int event__process_comm(event_t *self, struct perf_session *session);
 int event__process_lost(event_t *self, struct perf_session *session);
@@ -134,4 +160,6 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
 			     struct addr_location *al, symbol_filter_t filter);
 int event__parse_sample(event_t *event, u64 type, struct sample_data *data);
 
+extern const char *event__name[];
+
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6c9aa16ee51f..8847bec64c54 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -99,13 +99,6 @@ int perf_header__add_attr(struct perf_header *self,
 	return 0;
 }
 
-#define MAX_EVENT_NAME 64
-
-struct perf_trace_event_type {
-	u64	event_id;
-	char	name[MAX_EVENT_NAME];
-};
-
 static int event_count;
 static struct perf_trace_event_type *events;
 
@@ -197,7 +190,8 @@ static int write_padded(int fd, const void *bf, size_t count,
 			continue;		\
 		else
 
-static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd)
+static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
+				u16 misc, int fd)
 {
 	struct dso *pos;
 
@@ -212,6 +206,7 @@ static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd)
 		len = ALIGN(len, NAME_ALIGN);
 		memset(&b, 0, sizeof(b));
 		memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
+		b.pid = pid;
 		b.header.misc = misc;
 		b.header.size = sizeof(b) + len;
 		err = do_write(fd, &b, sizeof(b));
@@ -226,13 +221,32 @@ static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd)
 	return 0;
 }
 
-static int dsos__write_buildid_table(int fd)
+static int dsos__write_buildid_table(struct perf_header *header, int fd)
 {
-	int err = __dsos__write_buildid_table(&dsos__kernel,
-					      PERF_RECORD_MISC_KERNEL, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&dsos__user,
-						  PERF_RECORD_MISC_USER, fd);
+	struct perf_session *session = container_of(header,
+			struct perf_session, header);
+	struct rb_node *nd;
+	int err = 0;
+	u16 kmisc, umisc;
+
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		if (machine__is_host(pos)) {
+			kmisc = PERF_RECORD_MISC_KERNEL;
+			umisc = PERF_RECORD_MISC_USER;
+		} else {
+			kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+			umisc = PERF_RECORD_MISC_GUEST_USER;
+		}
+
+		err = __dsos__write_buildid_table(&pos->kernel_dsos, pos->pid,
+						  kmisc, fd);
+		if (err == 0)
+			err = __dsos__write_buildid_table(&pos->user_dsos,
+							  pos->pid, umisc, fd);
+		if (err)
+			break;
+	}
 	return err;
 }
 
@@ -349,9 +363,12 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
 	return err;
 }
 
-static int dsos__cache_build_ids(void)
+static int dsos__cache_build_ids(struct perf_header *self)
 {
-	int err_kernel, err_user;
+	struct perf_session *session = container_of(self,
+			struct perf_session, header);
+	struct rb_node *nd;
+	int ret = 0;
 	char debugdir[PATH_MAX];
 
 	snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
@@ -360,9 +377,28 @@ static int dsos__cache_build_ids(void)
 	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	err_kernel = __dsos__cache_build_ids(&dsos__kernel, debugdir);
-	err_user   = __dsos__cache_build_ids(&dsos__user, debugdir);
-	return err_kernel || err_user ? -1 : 0;
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= __dsos__cache_build_ids(&pos->kernel_dsos, debugdir);
+		ret |= __dsos__cache_build_ids(&pos->user_dsos, debugdir);
+	}
+	return ret ? -1 : 0;
+}
+
+static bool dsos__read_build_ids(struct perf_header *self, bool with_hits)
+{
+	bool ret = false;
+	struct perf_session *session = container_of(self,
+			struct perf_session, header);
+	struct rb_node *nd;
+
+	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= __dsos__read_build_ids(&pos->kernel_dsos, with_hits);
+		ret |= __dsos__read_build_ids(&pos->user_dsos, with_hits);
+	}
+
+	return ret;
 }
 
 static int perf_header__adds_write(struct perf_header *self, int fd)
@@ -373,7 +409,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 	u64 sec_start;
 	int idx = 0, err;
 
-	if (dsos__read_build_ids(true))
+	if (dsos__read_build_ids(self, true))
 		perf_header__set_feat(self, HEADER_BUILD_ID);
 
 	nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
@@ -400,7 +436,6 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 		trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
 	}
 
-
 	if (perf_header__has_feat(self, HEADER_BUILD_ID)) {
 		struct perf_file_section *buildid_sec;
 
@@ -408,14 +443,14 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 
 		/* Write build-ids */
 		buildid_sec->offset = lseek(fd, 0, SEEK_CUR);
-		err = dsos__write_buildid_table(fd);
+		err = dsos__write_buildid_table(self, fd);
 		if (err < 0) {
 			pr_debug("failed to write buildid table\n");
 			goto out_free;
 		}
 		buildid_sec->size = lseek(fd, 0, SEEK_CUR) -
 					  buildid_sec->offset;
-		dsos__cache_build_ids();
+		dsos__cache_build_ids(self);
 	}
 
 	lseek(fd, sec_start, SEEK_SET);
@@ -427,6 +462,25 @@ out_free:
 	return err;
 }
 
+int perf_header__write_pipe(int fd)
+{
+	struct perf_pipe_file_header f_header;
+	int err;
+
+	f_header = (struct perf_pipe_file_header){
+		.magic	   = PERF_MAGIC,
+		.size	   = sizeof(f_header),
+	};
+
+	err = do_write(fd, &f_header, sizeof(f_header));
+	if (err < 0) {
+		pr_debug("failed to write perf pipe header\n");
+		return err;
+	}
+
+	return 0;
+}
+
 int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 {
 	struct perf_file_header f_header;
@@ -518,25 +572,10 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 	return 0;
 }
 
-static int do_read(int fd, void *buf, size_t size)
-{
-	while (size) {
-		int ret = read(fd, buf, size);
-
-		if (ret <= 0)
-			return -1;
-
-		size -= ret;
-		buf += ret;
-	}
-
-	return 0;
-}
-
 static int perf_header__getbuffer64(struct perf_header *self,
 				    int fd, void *buf, size_t size)
 {
-	if (do_read(fd, buf, size))
+	if (do_read(fd, buf, size) <= 0)
 		return -1;
 
 	if (self->needs_swap)
@@ -592,7 +631,7 @@ int perf_file_header__read(struct perf_file_header *self,
 {
 	lseek(fd, 0, SEEK_SET);
 
-	if (do_read(fd, self, sizeof(*self)) ||
+	if (do_read(fd, self, sizeof(*self)) <= 0 ||
 	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
 		return -1;
 
@@ -636,6 +675,93 @@ int perf_file_header__read(struct perf_file_header *self,
 	return 0;
 }
 
+static int __event_process_build_id(struct build_id_event *bev,
+				    char *filename,
+				    struct perf_session *session)
+{
+	int err = -1;
+	struct list_head *head;
+	struct machine *machine;
+	u16 misc;
+	struct dso *dso;
+	enum dso_kernel_type dso_type;
+
+	machine = perf_session__findnew_machine(session, bev->pid);
+	if (!machine)
+		goto out;
+
+	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	switch (misc) {
+	case PERF_RECORD_MISC_KERNEL:
+		dso_type = DSO_TYPE_KERNEL;
+		head = &machine->kernel_dsos;
+		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		dso_type = DSO_TYPE_GUEST_KERNEL;
+		head = &machine->kernel_dsos;
+		break;
+	case PERF_RECORD_MISC_USER:
+	case PERF_RECORD_MISC_GUEST_USER:
+		dso_type = DSO_TYPE_USER;
+		head = &machine->user_dsos;
+		break;
+	default:
+		goto out;
+	}
+
+	dso = __dsos__findnew(head, filename);
+	if (dso != NULL) {
+		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+		dso__set_build_id(dso, &bev->build_id);
+
+		if (filename[0] == '[')
+			dso->kernel = dso_type;
+
+		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
+				  sbuild_id);
+		pr_debug("build id event received for %s: %s\n",
+			 dso->long_name, sbuild_id);
+	}
+
+	err = 0;
+out:
+	return err;
+}
+
+static int perf_header__read_build_ids(struct perf_header *self,
+			int input, u64 offset, u64 size)
+{
+	struct perf_session *session = container_of(self,
+			struct perf_session, header);
+	struct build_id_event bev;
+	char filename[PATH_MAX];
+	u64 limit = offset + size;
+	int err = -1;
+
+	while (offset < limit) {
+		ssize_t len;
+
+		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+			goto out;
+
+		if (self->needs_swap)
+			perf_event_header__bswap(&bev.header);
+
+		len = bev.header.size - sizeof(bev);
+		if (read(input, filename, len) != len)
+			goto out;
+
+		__event_process_build_id(&bev, filename, session);
+
+		offset += bev.header.size;
+	}
+	err = 0;
+out:
+	return err;
+}
+
 static int perf_file_section__process(struct perf_file_section *self,
 				      struct perf_header *ph,
 				      int feat, int fd)
@@ -648,7 +774,7 @@ static int perf_file_section__process(struct perf_file_section *self,
 
 	switch (feat) {
 	case HEADER_TRACE_INFO:
-		trace_report(fd);
+		trace_report(fd, false);
 		break;
 
 	case HEADER_BUILD_ID:
@@ -662,13 +788,56 @@ static int perf_file_section__process(struct perf_file_section *self,
 	return 0;
 }
 
-int perf_header__read(struct perf_header *self, int fd)
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+				       struct perf_header *ph, int fd,
+				       bool repipe)
+{
+	if (do_read(fd, self, sizeof(*self)) <= 0 ||
+	    memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+		return -1;
+
+	if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0)
+		return -1;
+
+	if (self->size != sizeof(*self)) {
+		u64 size = bswap_64(self->size);
+
+		if (size != sizeof(*self))
+			return -1;
+
+		ph->needs_swap = true;
+	}
+
+	return 0;
+}
+
+static int perf_header__read_pipe(struct perf_session *session, int fd)
 {
+	struct perf_header *self = &session->header;
+	struct perf_pipe_file_header f_header;
+
+	if (perf_file_header__read_pipe(&f_header, self, fd,
+					session->repipe) < 0) {
+		pr_debug("incompatible file format\n");
+		return -EINVAL;
+	}
+
+	session->fd = fd;
+
+	return 0;
+}
+
+int perf_header__read(struct perf_session *session, int fd)
+{
+	struct perf_header *self = &session->header;
 	struct perf_file_header	f_header;
 	struct perf_file_attr	f_attr;
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
 
+	if (session->fd_pipe)
+		return perf_header__read_pipe(session, fd);
+
 	if (perf_file_header__read(&f_header, self, fd) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
@@ -753,6 +922,14 @@ perf_header__find_attr(u64 id, struct perf_header *header)
 {
 	int i;
 
+	/*
+	 * We set id to -1 if the data file doesn't contain sample
+	 * ids. Check for this and avoid walking through the entire
+	 * list of ids which may be large.
+	 */
+	if (id == -1ULL)
+		return NULL;
+
 	for (i = 0; i < header->attrs; i++) {
 		struct perf_header_attr *attr = header->attr[i];
 		int j;
@@ -765,3 +942,231 @@ perf_header__find_attr(u64 id, struct perf_header *header)
 
 	return NULL;
 }
+
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+			   event__handler_t process,
+			   struct perf_session *session)
+{
+	event_t *ev;
+	size_t size;
+	int err;
+
+	size = sizeof(struct perf_event_attr);
+	size = ALIGN(size, sizeof(u64));
+	size += sizeof(struct perf_event_header);
+	size += ids * sizeof(u64);
+
+	ev = malloc(size);
+
+	ev->attr.attr = *attr;
+	memcpy(ev->attr.id, id, ids * sizeof(u64));
+
+	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+	ev->attr.header.size = size;
+
+	err = process(ev, session);
+
+	free(ev);
+
+	return err;
+}
+
+int event__synthesize_attrs(struct perf_header *self,
+			    event__handler_t process,
+			    struct perf_session *session)
+{
+	struct perf_header_attr	*attr;
+	int i, err = 0;
+
+	for (i = 0; i < self->attrs; i++) {
+		attr = self->attr[i];
+
+		err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
+					     process, session);
+		if (err) {
+			pr_debug("failed to create perf header attribute\n");
+			return err;
+		}
+	}
+
+	return err;
+}
+
+int event__process_attr(event_t *self, struct perf_session *session)
+{
+	struct perf_header_attr *attr;
+	unsigned int i, ids, n_ids;
+
+	attr = perf_header_attr__new(&self->attr.attr);
+	if (attr == NULL)
+		return -ENOMEM;
+
+	ids = self->header.size;
+	ids -= (void *)&self->attr.id - (void *)self;
+	n_ids = ids / sizeof(u64);
+
+	for (i = 0; i < n_ids; i++) {
+		if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
+			perf_header_attr__delete(attr);
+			return -ENOMEM;
+		}
+	}
+
+	if (perf_header__add_attr(&session->header, attr) < 0) {
+		perf_header_attr__delete(attr);
+		return -ENOMEM;
+	}
+
+	perf_session__update_sample_type(session);
+
+	return 0;
+}
+
+int event__synthesize_event_type(u64 event_id, char *name,
+				 event__handler_t process,
+				 struct perf_session *session)
+{
+	event_t ev;
+	size_t size = 0;
+	int err = 0;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.event_type.event_type.event_id = event_id;
+	memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
+	strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
+
+	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
+	size = strlen(name);
+	size = ALIGN(size, sizeof(u64));
+	ev.event_type.header.size = sizeof(ev.event_type) -
+		(sizeof(ev.event_type.event_type.name) - size);
+
+	err = process(&ev, session);
+
+	return err;
+}
+
+int event__synthesize_event_types(event__handler_t process,
+				  struct perf_session *session)
+{
+	struct perf_trace_event_type *type;
+	int i, err = 0;
+
+	for (i = 0; i < event_count; i++) {
+		type = &events[i];
+
+		err = event__synthesize_event_type(type->event_id, type->name,
+						   process, session);
+		if (err) {
+			pr_debug("failed to create perf header event type\n");
+			return err;
+		}
+	}
+
+	return err;
+}
+
+int event__process_event_type(event_t *self,
+			      struct perf_session *session __unused)
+{
+	if (perf_header__push_event(self->event_type.event_type.event_id,
+				    self->event_type.event_type.name) < 0)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+				   int nb_events,
+				   event__handler_t process,
+				   struct perf_session *session __unused)
+{
+	event_t ev;
+	ssize_t size = 0, aligned_size = 0, padding;
+	int err = 0;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
+	size = read_tracing_data_size(fd, pattrs, nb_events);
+	if (size <= 0)
+		return size;
+	aligned_size = ALIGN(size, sizeof(u64));
+	padding = aligned_size - size;
+	ev.tracing_data.header.size = sizeof(ev.tracing_data);
+	ev.tracing_data.size = aligned_size;
+
+	process(&ev, session);
+
+	err = read_tracing_data(fd, pattrs, nb_events);
+	write_padded(fd, NULL, 0, padding);
+
+	return aligned_size;
+}
+
+int event__process_tracing_data(event_t *self,
+				struct perf_session *session)
+{
+	ssize_t size_read, padding, size = self->tracing_data.size;
+	off_t offset = lseek(session->fd, 0, SEEK_CUR);
+	char buf[BUFSIZ];
+
+	/* setup for reading amidst mmap */
+	lseek(session->fd, offset + sizeof(struct tracing_data_event),
+	      SEEK_SET);
+
+	size_read = trace_report(session->fd, session->repipe);
+
+	padding = ALIGN(size_read, sizeof(u64)) - size_read;
+
+	if (read(session->fd, buf, padding) < 0)
+		die("reading input file");
+	if (session->repipe) {
+		int retw = write(STDOUT_FILENO, buf, padding);
+		if (retw <= 0 || retw != padding)
+			die("repiping tracing data padding");
+	}
+
+	if (size_read + padding != size)
+		die("tracing data size mismatch");
+
+	return size_read + padding;
+}
+
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+			       event__handler_t process,
+			       struct machine *machine,
+			       struct perf_session *session)
+{
+	event_t ev;
+	size_t len;
+	int err = 0;
+
+	if (!pos->hit)
+		return err;
+
+	memset(&ev, 0, sizeof(ev));
+
+	len = pos->long_name_len + 1;
+	len = ALIGN(len, NAME_ALIGN);
+	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
+	ev.build_id.header.misc = misc;
+	ev.build_id.pid = machine->pid;
+	ev.build_id.header.size = sizeof(ev.build_id) + len;
+	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+
+	err = process(&ev, session);
+
+	return err;
+}
+
+int event__process_build_id(event_t *self,
+			    struct perf_session *session)
+{
+	__event_process_build_id(&self->build_id,
+				 self->build_id.filename,
+				 session);
+	return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 82a6af72d4cc..402ac2454cf8 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,11 @@ struct perf_file_header {
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
+struct perf_pipe_file_header {
+	u64				magic;
+	u64				size;
+};
+
 struct perf_header;
 
 int perf_file_header__read(struct perf_file_header *self,
@@ -47,21 +52,22 @@ int perf_file_header__read(struct perf_file_header *self,
 struct perf_header {
 	int			frozen;
 	int			attrs, size;
+	bool			needs_swap;
 	struct perf_header_attr **attr;
 	s64			attr_offset;
 	u64			data_offset;
 	u64			data_size;
 	u64			event_offset;
 	u64			event_size;
-	bool			needs_swap;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
 int perf_header__init(struct perf_header *self);
 void perf_header__exit(struct perf_header *self);
 
-int perf_header__read(struct perf_header *self, int fd);
+int perf_header__read(struct perf_session *session, int fd);
 int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_header__write_pipe(int fd);
 
 int perf_header__add_attr(struct perf_header *self,
 			  struct perf_header_attr *attr);
@@ -89,4 +95,33 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 			  const char *name, bool is_kallsyms);
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
 
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+			   event__handler_t process,
+			   struct perf_session *session);
+int event__synthesize_attrs(struct perf_header *self,
+			    event__handler_t process,
+			    struct perf_session *session);
+int event__process_attr(event_t *self, struct perf_session *session);
+
+int event__synthesize_event_type(u64 event_id, char *name,
+				 event__handler_t process,
+				 struct perf_session *session);
+int event__synthesize_event_types(event__handler_t process,
+				  struct perf_session *session);
+int event__process_event_type(event_t *self,
+			      struct perf_session *session);
+
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+				   int nb_events,
+				   event__handler_t process,
+				   struct perf_session *session);
+int event__process_tracing_data(event_t *self,
+				struct perf_session *session);
+
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+			       event__handler_t process,
+			       struct machine *machine,
+			       struct perf_session *session);
+int event__process_build_id(event_t *self, struct perf_session *session);
+
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2be33c7dbf03..9a71c94f057a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,3 +1,4 @@
+#include "util.h"
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
@@ -8,25 +9,69 @@ struct callchain_param	callchain_param = {
 	.min_percent = 0.5
 };
 
+static void hist_entry__add_cpumode_period(struct hist_entry *self,
+					   unsigned int cpumode, u64 period)
+{
+	switch (cpumode) {
+	case PERF_RECORD_MISC_KERNEL:
+		self->period_sys += period;
+		break;
+	case PERF_RECORD_MISC_USER:
+		self->period_us += period;
+		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+		self->period_guest_sys += period;
+		break;
+	case PERF_RECORD_MISC_GUEST_USER:
+		self->period_guest_us += period;
+		break;
+	default:
+		break;
+	}
+}
+
 /*
- * histogram, sorted on item, collects counts
+ * histogram, sorted on item, collects periods
  */
 
-struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
-						  struct addr_location *al,
-						  struct symbol *sym_parent,
-						  u64 count, bool *hit)
+static struct hist_entry *hist_entry__new(struct hist_entry *template)
+{
+	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
+	struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
+
+	if (self != NULL) {
+		*self = *template;
+		self->nr_events = 1;
+		if (symbol_conf.use_callchain)
+			callchain_init(self->callchain);
+	}
+
+	return self;
+}
+
+static void hists__inc_nr_entries(struct hists *self, struct hist_entry *entry)
 {
-	struct rb_node **p = &hists->rb_node;
+	if (entry->ms.sym && self->max_sym_namelen < entry->ms.sym->namelen)
+		self->max_sym_namelen = entry->ms.sym->namelen;
+	++self->nr_entries;
+}
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *sym_parent, u64 period)
+{
+	struct rb_node **p = &self->entries.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	struct hist_entry entry = {
 		.thread	= al->thread,
-		.map	= al->map,
-		.sym	= al->sym,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
 		.ip	= al->addr,
 		.level	= al->level,
-		.count	= count,
+		.period	= period,
 		.parent = sym_parent,
 	};
 	int cmp;
@@ -38,8 +83,9 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 		cmp = hist_entry__cmp(&entry, he);
 
 		if (!cmp) {
-			*hit = true;
-			return he;
+			he->period += period;
+			++he->nr_events;
+			goto out;
 		}
 
 		if (cmp < 0)
@@ -48,13 +94,14 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = malloc(sizeof(*he));
+	he = hist_entry__new(&entry);
 	if (!he)
 		return NULL;
-	*he = entry;
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, hists);
-	*hit = false;
+	rb_insert_color(&he->rb_node, &self->entries);
+	hists__inc_nr_entries(self, he);
+out:
+	hist_entry__add_cpumode_period(he, al->cpumode, period);
 	return he;
 }
 
@@ -65,7 +112,7 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 	int64_t cmp = 0;
 
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		cmp = se->cmp(left, right);
+		cmp = se->se_cmp(left, right);
 		if (cmp)
 			break;
 	}
@@ -82,7 +129,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 	list_for_each_entry(se, &hist_entry__sort_list, list) {
 		int64_t (*f)(struct hist_entry *, struct hist_entry *);
 
-		f = se->collapse ?: se->cmp;
+		f = se->se_collapse ?: se->se_cmp;
 
 		cmp = f(left, right);
 		if (cmp)
@@ -101,7 +148,7 @@ void hist_entry__free(struct hist_entry *he)
  * collapse the histogram
  */
 
-static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
+static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -115,9 +162,9 @@ static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
-			iter->count += he->count;
+			iter->period += he->period;
 			hist_entry__free(he);
-			return;
+			return false;
 		}
 
 		if (cmp < 0)
@@ -128,9 +175,10 @@ static void collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, root);
+	return true;
 }
 
-void perf_session__collapse_resort(struct rb_root *hists)
+void hists__collapse_resort(struct hists *self)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
@@ -140,72 +188,77 @@ void perf_session__collapse_resort(struct rb_root *hists)
 		return;
 
 	tmp = RB_ROOT;
-	next = rb_first(hists);
+	next = rb_first(&self->entries);
+	self->nr_entries = 0;
+	self->max_sym_namelen = 0;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, hists);
-		collapse__insert_entry(&tmp, n);
+		rb_erase(&n->rb_node, &self->entries);
+		if (collapse__insert_entry(&tmp, n))
+			hists__inc_nr_entries(self, n);
 	}
 
-	*hists = tmp;
+	self->entries = tmp;
 }
 
 /*
- * reverse the map, sort on count.
+ * reverse the map, sort on period.
  */
 
-static void perf_session__insert_output_hist_entry(struct rb_root *root,
-						   struct hist_entry *he,
-						   u64 min_callchain_hits)
+static void __hists__insert_output_entry(struct rb_root *entries,
+					 struct hist_entry *he,
+					 u64 min_callchain_hits)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 
 	if (symbol_conf.use_callchain)
-		callchain_param.sort(&he->sorted_chain, &he->callchain,
+		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
 
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-		if (he->count > iter->count)
+		if (he->period > iter->period)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	rb_insert_color(&he->rb_node, entries);
 }
 
-void perf_session__output_resort(struct rb_root *hists, u64 total_samples)
+void hists__output_resort(struct hists *self)
 {
 	struct rb_root tmp;
 	struct rb_node *next;
 	struct hist_entry *n;
 	u64 min_callchain_hits;
 
-	min_callchain_hits =
-		total_samples * (callchain_param.min_percent / 100);
+	min_callchain_hits = self->stats.total_period * (callchain_param.min_percent / 100);
 
 	tmp = RB_ROOT;
-	next = rb_first(hists);
+	next = rb_first(&self->entries);
+
+	self->nr_entries = 0;
+	self->max_sym_namelen = 0;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node);
 		next = rb_next(&n->rb_node);
 
-		rb_erase(&n->rb_node, hists);
-		perf_session__insert_output_hist_entry(&tmp, n,
-						       min_callchain_hits);
+		rb_erase(&n->rb_node, &self->entries);
+		__hists__insert_output_entry(&tmp, n, min_callchain_hits);
+		hists__inc_nr_entries(self, n);
 	}
 
-	*hists = tmp;
+	self->entries = tmp;
 }
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -237,7 +290,7 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 }
 
 static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
-				     int depth, int depth_mask, int count,
+				     int depth, int depth_mask, int period,
 				     u64 total_samples, int hits,
 				     int left_margin)
 {
@@ -250,7 +303,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 			ret += fprintf(fp, "|");
 		else
 			ret += fprintf(fp, " ");
-		if (!count && i == depth - 1) {
+		if (!period && i == depth - 1) {
 			double percent;
 
 			percent = hits * 100.0 / total_samples;
@@ -258,8 +311,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
-	if (chain->sym)
-		ret += fprintf(fp, "%s\n", chain->sym->name);
+	if (chain->ms.sym)
+		ret += fprintf(fp, "%s\n", chain->ms.sym->name);
 	else
 		ret += fprintf(fp, "%p\n", (void *)(long)chain->ip);
 
@@ -278,7 +331,7 @@ static void init_rem_hits(void)
 	}
 
 	strcpy(rem_sq_bracket->name, "[...]");
-	rem_hits.sym = rem_sq_bracket;
+	rem_hits.ms.sym = rem_sq_bracket;
 }
 
 static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
@@ -293,6 +346,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	u64 remaining;
 	size_t ret = 0;
 	int i;
+	uint entries_printed = 0;
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL)
 		new_total = self->children_hit;
@@ -328,8 +382,6 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 						   left_margin);
 		i = 0;
 		list_for_each_entry(chain, &child->val, list) {
-			if (chain->ip >= PERF_CONTEXT_MAX)
-				continue;
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
@@ -341,6 +393,8 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 						  new_depth_mask | (1 << depth),
 						  left_margin);
 		node = next;
+		if (++entries_printed == callchain_param.print_limit)
+			break;
 	}
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
@@ -366,11 +420,9 @@ static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	bool printed = false;
 	int i = 0;
 	int ret = 0;
+	u32 entries_printed = 0;
 
 	list_for_each_entry(chain, &self->val, list) {
-		if (chain->ip >= PERF_CONTEXT_MAX)
-			continue;
-
 		if (!i++ && sort__first_dimension == SORT_SYM)
 			continue;
 
@@ -385,10 +437,13 @@ static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		} else
 			ret += callchain__fprintf_left_margin(fp, left_margin);
 
-		if (chain->sym)
-			ret += fprintf(fp, " %s\n", chain->sym->name);
+		if (chain->ms.sym)
+			ret += fprintf(fp, " %s\n", chain->ms.sym->name);
 		else
 			ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+
+		if (++entries_printed == callchain_param.print_limit)
+			break;
 	}
 
 	ret += __callchain__fprintf_graph(fp, self, total_samples, 1, 1, left_margin);
@@ -411,8 +466,8 @@ static size_t callchain__fprintf_flat(FILE *fp, struct callchain_node *self,
 	list_for_each_entry(chain, &self->val, list) {
 		if (chain->ip >= PERF_CONTEXT_MAX)
 			continue;
-		if (chain->sym)
-			ret += fprintf(fp, "                %s\n", chain->sym->name);
+		if (chain->ms.sym)
+			ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
 		else
 			ret += fprintf(fp, "                %p\n",
 					(void *)(long)chain->ip);
@@ -427,6 +482,7 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 	struct rb_node *rb_node;
 	struct callchain_node *chain;
 	size_t ret = 0;
+	u32 entries_printed = 0;
 
 	rb_node = rb_first(&self->sorted_chain);
 	while (rb_node) {
@@ -449,55 +505,88 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self,
 			break;
 		}
 		ret += fprintf(fp, "\n");
+		if (++entries_printed == callchain_param.print_limit)
+			break;
 		rb_node = rb_next(rb_node);
 	}
 
 	return ret;
 }
 
-static size_t hist_entry__fprintf(struct hist_entry *self,
-				  struct perf_session *pair_session,
-				  bool show_displacement,
-				  long displacement, FILE *fp,
-				  u64 session_total)
+int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
+			 struct hists *pair_hists, bool show_displacement,
+			 long displacement, bool color, u64 session_total)
 {
 	struct sort_entry *se;
-	u64 count, total;
+	u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
 	const char *sep = symbol_conf.field_sep;
-	size_t ret;
+	int ret;
 
 	if (symbol_conf.exclude_other && !self->parent)
 		return 0;
 
-	if (pair_session) {
-		count = self->pair ? self->pair->count : 0;
-		total = pair_session->events_stats.total;
+	if (pair_hists) {
+		period = self->pair ? self->pair->period : 0;
+		total = pair_hists->stats.total_period;
+		period_sys = self->pair ? self->pair->period_sys : 0;
+		period_us = self->pair ? self->pair->period_us : 0;
+		period_guest_sys = self->pair ? self->pair->period_guest_sys : 0;
+		period_guest_us = self->pair ? self->pair->period_guest_us : 0;
 	} else {
-		count = self->count;
+		period = self->period;
 		total = session_total;
+		period_sys = self->period_sys;
+		period_us = self->period_us;
+		period_guest_sys = self->period_guest_sys;
+		period_guest_us = self->period_guest_us;
 	}
 
-	if (total)
-		ret = percent_color_fprintf(fp, sep ? "%.2f" : "   %6.2f%%",
-					    (count * 100.0) / total);
-	else
-		ret = fprintf(fp, sep ? "%lld" : "%12lld ", count);
+	if (total) {
+		if (color)
+			ret = percent_color_snprintf(s, size,
+						     sep ? "%.2f" : "   %6.2f%%",
+						     (period * 100.0) / total);
+		else
+			ret = snprintf(s, size, sep ? "%.2f" : "   %6.2f%%",
+				       (period * 100.0) / total);
+		if (symbol_conf.show_cpu_utilization) {
+			ret += percent_color_snprintf(s + ret, size - ret,
+					sep ? "%.2f" : "   %6.2f%%",
+					(period_sys * 100.0) / total);
+			ret += percent_color_snprintf(s + ret, size - ret,
+					sep ? "%.2f" : "   %6.2f%%",
+					(period_us * 100.0) / total);
+			if (perf_guest) {
+				ret += percent_color_snprintf(s + ret,
+						size - ret,
+						sep ? "%.2f" : "   %6.2f%%",
+						(period_guest_sys * 100.0) /
+								total);
+				ret += percent_color_snprintf(s + ret,
+						size - ret,
+						sep ? "%.2f" : "   %6.2f%%",
+						(period_guest_us * 100.0) /
+								total);
+			}
+		}
+	} else
+		ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period);
 
 	if (symbol_conf.show_nr_samples) {
 		if (sep)
-			fprintf(fp, "%c%lld", *sep, count);
+			ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period);
 		else
-			fprintf(fp, "%11lld", count);
+			ret += snprintf(s + ret, size - ret, "%11lld", period);
 	}
 
-	if (pair_session) {
+	if (pair_hists) {
 		char bf[32];
 		double old_percent = 0, new_percent = 0, diff;
 
 		if (total > 0)
-			old_percent = (count * 100.0) / total;
+			old_percent = (period * 100.0) / total;
 		if (session_total > 0)
-			new_percent = (self->count * 100.0) / session_total;
+			new_percent = (self->period * 100.0) / session_total;
 
 		diff = new_percent - old_percent;
 
@@ -507,9 +596,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 			snprintf(bf, sizeof(bf), " ");
 
 		if (sep)
-			ret += fprintf(fp, "%c%s", *sep, bf);
+			ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
 		else
-			ret += fprintf(fp, "%11.11s", bf);
+			ret += snprintf(s + ret, size - ret, "%11.11s", bf);
 
 		if (show_displacement) {
 			if (displacement)
@@ -518,9 +607,9 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 				snprintf(bf, sizeof(bf), " ");
 
 			if (sep)
-				fprintf(fp, "%c%s", *sep, bf);
+				ret += snprintf(s + ret, size - ret, "%c%s", *sep, bf);
 			else
-				fprintf(fp, "%6.6s", bf);
+				ret += snprintf(s + ret, size - ret, "%6.6s", bf);
 		}
 	}
 
@@ -528,33 +617,43 @@ static size_t hist_entry__fprintf(struct hist_entry *self,
 		if (se->elide)
 			continue;
 
-		fprintf(fp, "%s", sep ?: "  ");
-		ret += se->print(fp, self, se->width ? *se->width : 0);
+		ret += snprintf(s + ret, size - ret, "%s", sep ?: "  ");
+		ret += se->se_snprintf(self, s + ret, size - ret,
+				       se->se_width ? *se->se_width : 0);
 	}
 
-	ret += fprintf(fp, "\n");
+	return ret;
+}
 
-	if (symbol_conf.use_callchain) {
-		int left_margin = 0;
+int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
+			bool show_displacement, long displacement, FILE *fp,
+			u64 session_total)
+{
+	char bf[512];
+	hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
+			     show_displacement, displacement,
+			     true, session_total);
+	return fprintf(fp, "%s\n", bf);
+}
 
-		if (sort__first_dimension == SORT_COMM) {
-			se = list_first_entry(&hist_entry__sort_list, typeof(*se),
-						list);
-			left_margin = se->width ? *se->width : 0;
-			left_margin -= thread__comm_len(self->thread);
-		}
+static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp,
+					    u64 session_total)
+{
+	int left_margin = 0;
 
-		hist_entry_callchain__fprintf(fp, self, session_total,
-					      left_margin);
+	if (sort__first_dimension == SORT_COMM) {
+		struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
+							 typeof(*se), list);
+		left_margin = se->se_width ? *se->se_width : 0;
+		left_margin -= thread__comm_len(self->thread);
 	}
 
-	return ret;
+	return hist_entry_callchain__fprintf(fp, self, session_total,
+					     left_margin);
 }
 
-size_t perf_session__fprintf_hists(struct rb_root *hists,
-				   struct perf_session *pair,
-				   bool show_displacement, FILE *fp,
-				   u64 session_total)
+size_t hists__fprintf(struct hists *self, struct hists *pair,
+		      bool show_displacement, FILE *fp)
 {
 	struct sort_entry *se;
 	struct rb_node *nd;
@@ -563,7 +662,7 @@ size_t perf_session__fprintf_hists(struct rb_root *hists,
 	long displacement = 0;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
-	char *col_width = symbol_conf.col_width_list_str;
+	const char *col_width = symbol_conf.col_width_list_str;
 
 	init_rem_hits();
 
@@ -576,6 +675,24 @@ size_t perf_session__fprintf_hists(struct rb_root *hists,
 			fputs("  Samples  ", fp);
 	}
 
+	if (symbol_conf.show_cpu_utilization) {
+		if (sep) {
+			ret += fprintf(fp, "%csys", *sep);
+			ret += fprintf(fp, "%cus", *sep);
+			if (perf_guest) {
+				ret += fprintf(fp, "%cguest sys", *sep);
+				ret += fprintf(fp, "%cguest us", *sep);
+			}
+		} else {
+			ret += fprintf(fp, "  sys  ");
+			ret += fprintf(fp, "  us  ");
+			if (perf_guest) {
+				ret += fprintf(fp, "  guest sys  ");
+				ret += fprintf(fp, "  guest us  ");
+			}
+		}
+	}
+
 	if (pair) {
 		if (sep)
 			ret += fprintf(fp, "%cDelta", *sep);
@@ -594,22 +711,22 @@ size_t perf_session__fprintf_hists(struct rb_root *hists,
 		if (se->elide)
 			continue;
 		if (sep) {
-			fprintf(fp, "%c%s", *sep, se->header);
+			fprintf(fp, "%c%s", *sep, se->se_header);
 			continue;
 		}
-		width = strlen(se->header);
-		if (se->width) {
+		width = strlen(se->se_header);
+		if (se->se_width) {
 			if (symbol_conf.col_width_list_str) {
 				if (col_width) {
-					*se->width = atoi(col_width);
+					*se->se_width = atoi(col_width);
 					col_width = strchr(col_width, ',');
 					if (col_width)
 						++col_width;
 				}
 			}
-			width = *se->width = max(*se->width, width);
+			width = *se->se_width = max(*se->se_width, width);
 		}
-		fprintf(fp, "  %*s", width, se->header);
+		fprintf(fp, "  %*s", width, se->se_header);
 	}
 	fprintf(fp, "\n");
 
@@ -631,10 +748,10 @@ size_t perf_session__fprintf_hists(struct rb_root *hists,
 			continue;
 
 		fprintf(fp, "  ");
-		if (se->width)
-			width = *se->width;
+		if (se->se_width)
+			width = *se->se_width;
 		else
-			width = strlen(se->header);
+			width = strlen(se->se_header);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
@@ -642,7 +759,7 @@ size_t perf_session__fprintf_hists(struct rb_root *hists,
 	fprintf(fp, "\n#\n");
 
 print_entries:
-	for (nd = rb_first(hists); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (show_displacement) {
@@ -654,10 +771,14 @@ print_entries:
 			++position;
 		}
 		ret += hist_entry__fprintf(h, pair, show_displacement,
-					   displacement, fp, session_total);
-		if (h->map == NULL && verbose > 1) {
+					   displacement, fp, self->stats.total_period);
+
+		if (symbol_conf.use_callchain)
+			ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period);
+
+		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(&h->thread->mg,
-						   MAP__FUNCTION, fp);
+						   MAP__FUNCTION, verbose, fp);
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
@@ -666,3 +787,271 @@ print_entries:
 
 	return ret;
 }
+
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+};
+
+void hists__filter_by_dso(struct hists *self, const struct dso *dso)
+{
+	struct rb_node *nd;
+
+	self->nr_entries = self->stats.total_period = 0;
+	self->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	self->max_sym_namelen = 0;
+
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (symbol_conf.exclude_other && !h->parent)
+			continue;
+
+		if (dso != NULL && (h->ms.map == NULL || h->ms.map->dso != dso)) {
+			h->filtered |= (1 << HIST_FILTER__DSO);
+			continue;
+		}
+
+		h->filtered &= ~(1 << HIST_FILTER__DSO);
+		if (!h->filtered) {
+			++self->nr_entries;
+			self->stats.total_period += h->period;
+			self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events;
+			if (h->ms.sym &&
+			    self->max_sym_namelen < h->ms.sym->namelen)
+				self->max_sym_namelen = h->ms.sym->namelen;
+		}
+	}
+}
+
+void hists__filter_by_thread(struct hists *self, const struct thread *thread)
+{
+	struct rb_node *nd;
+
+	self->nr_entries = self->stats.total_period = 0;
+	self->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	self->max_sym_namelen = 0;
+
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (thread != NULL && h->thread != thread) {
+			h->filtered |= (1 << HIST_FILTER__THREAD);
+			continue;
+		}
+		h->filtered &= ~(1 << HIST_FILTER__THREAD);
+		if (!h->filtered) {
+			++self->nr_entries;
+			self->stats.total_period += h->period;
+			self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events;
+			if (h->ms.sym &&
+			    self->max_sym_namelen < h->ms.sym->namelen)
+				self->max_sym_namelen = h->ms.sym->namelen;
+		}
+	}
+}
+
+static int symbol__alloc_hist(struct symbol *self)
+{
+	struct sym_priv *priv = symbol__priv(self);
+	const int size = (sizeof(*priv->hist) +
+			  (self->end - self->start) * sizeof(u64));
+
+	priv->hist = zalloc(size);
+	return priv->hist == NULL ? -1 : 0;
+}
+
+int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
+{
+	unsigned int sym_size, offset;
+	struct symbol *sym = self->ms.sym;
+	struct sym_priv *priv;
+	struct sym_hist *h;
+
+	if (!sym || !self->ms.map)
+		return 0;
+
+	priv = symbol__priv(sym);
+	if (priv->hist == NULL && symbol__alloc_hist(sym) < 0)
+		return -ENOMEM;
+
+	sym_size = sym->end - sym->start;
+	offset = ip - sym->start;
+
+	pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
+
+	if (offset >= sym_size)
+		return 0;
+
+	h = priv->hist;
+	h->sum++;
+	h->ip[offset]++;
+
+	pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start,
+		  self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]);
+	return 0;
+}
+
+static struct objdump_line *objdump_line__new(s64 offset, char *line)
+{
+	struct objdump_line *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		self->offset = offset;
+		self->line = line;
+	}
+
+	return self;
+}
+
+void objdump_line__free(struct objdump_line *self)
+{
+	free(self->line);
+	free(self);
+}
+
+static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+{
+	list_add_tail(&line->node, head);
+}
+
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+					       struct objdump_line *pos)
+{
+	list_for_each_entry_continue(pos, head, node)
+		if (pos->offset >= 0)
+			return pos;
+
+	return NULL;
+}
+
+static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
+					  struct list_head *head)
+{
+	struct symbol *sym = self->ms.sym;
+	struct objdump_line *objdump_line;
+	char *line = NULL, *tmp, *tmp2, *c;
+	size_t line_len;
+	s64 line_ip, offset = -1;
+
+	if (getline(&line, &line_len, file) < 0)
+		return -1;
+
+	if (!line)
+		return -1;
+
+	while (line_len != 0 && isspace(line[line_len - 1]))
+		line[--line_len] = '\0';
+
+	c = strchr(line, '\n');
+	if (c)
+		*c = 0;
+
+	line_ip = -1;
+
+	/*
+	 * Strip leading spaces:
+	 */
+	tmp = line;
+	while (*tmp) {
+		if (*tmp != ' ')
+			break;
+		tmp++;
+	}
+
+	if (*tmp) {
+		/*
+		 * Parse hexa addresses followed by ':'
+		 */
+		line_ip = strtoull(tmp, &tmp2, 16);
+		if (*tmp2 != ':')
+			line_ip = -1;
+	}
+
+	if (line_ip != -1) {
+		u64 start = map__rip_2objdump(self->ms.map, sym->start);
+		offset = line_ip - start;
+	}
+
+	objdump_line = objdump_line__new(offset, line);
+	if (objdump_line == NULL) {
+		free(line);
+		return -1;
+	}
+	objdump__add_line(head, objdump_line);
+
+	return 0;
+}
+
+int hist_entry__annotate(struct hist_entry *self, struct list_head *head)
+{
+	struct symbol *sym = self->ms.sym;
+	struct map *map = self->ms.map;
+	struct dso *dso = map->dso;
+	const char *filename = dso->long_name;
+	char command[PATH_MAX * 2];
+	FILE *file;
+	u64 len;
+
+	if (!filename)
+		return -1;
+
+	if (dso->origin == DSO__ORIG_KERNEL) {
+		if (dso->annotate_warned)
+			return 0;
+		dso->annotate_warned = 1;
+		pr_err("Can't annotate %s: No vmlinux file was found in the "
+		       "path:\n", sym->name);
+		vmlinux_path__fprintf(stderr);
+		return -1;
+	}
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
+		 filename, sym->name, map->unmap_ip(map, sym->start),
+		 map->unmap_ip(map, sym->end));
+
+	len = sym->end - sym->start;
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n",
+		 dso, dso->long_name, sym, sym->name);
+
+	snprintf(command, sizeof(command),
+		 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s|expand",
+		 map__rip_2objdump(map, sym->start),
+		 map__rip_2objdump(map, sym->end),
+		 filename, filename);
+
+	pr_debug("Executing: %s\n", command);
+
+	file = popen(command, "r");
+	if (!file)
+		return -1;
+
+	while (!feof(file))
+		if (hist_entry__parse_objdump_line(self, file, head) < 0)
+			break;
+
+	pclose(file);
+	return 0;
+}
+
+void hists__inc_nr_events(struct hists *self, u32 type)
+{
+	++self->stats.nr_events[0];
+	++self->stats.nr_events[type];
+}
+
+size_t hists__fprintf_nr_events(struct hists *self, FILE *fp)
+{
+	int i;
+	size_t ret = 0;
+
+	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+		if (!event__name[i])
+			continue;
+		ret += fprintf(fp, "%10s events: %10d\n",
+			       event__name[i], self->stats.nr_events[i]);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 16f360cce5bf..6f17dcd8412c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -6,24 +6,104 @@
 
 extern struct callchain_param callchain_param;
 
-struct perf_session;
 struct hist_entry;
 struct addr_location;
 struct symbol;
 struct rb_root;
 
-struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
-						  struct addr_location *al,
-						  struct symbol *parent,
-						  u64 count, bool *hit);
+struct objdump_line {
+	struct list_head node;
+	s64		 offset;
+	char		 *line;
+};
+
+void objdump_line__free(struct objdump_line *self);
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+					       struct objdump_line *pos);
+
+struct sym_hist {
+	u64		sum;
+	u64		ip[0];
+};
+
+struct sym_ext {
+	struct rb_node	node;
+	double		percent;
+	char		*path;
+};
+
+struct sym_priv {
+	struct sym_hist	*hist;
+	struct sym_ext	*ext;
+};
+
+/*
+ * The kernel collects the number of events it couldn't send in a stretch and
+ * when possible sends this number in a PERF_RECORD_LOST event. The number of
+ * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
+ * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
+ * the sum of all struct lost_event.lost fields reported.
+ *
+ * The total_period is needed because by default auto-freq is used, so
+ * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
+ * the total number of low level events, it is necessary to to sum all struct
+ * sample_event.period and stash the result in total_period.
+ */
+struct events_stats {
+	u64 total_period;
+	u64 total_lost;
+	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_unknown_events;
+};
+
+struct hists {
+	struct rb_node		rb_node;
+	struct rb_root		entries;
+	u64			nr_entries;
+	struct events_stats	stats;
+	u64			config;
+	u64			event_stream;
+	u32			type;
+	u32			max_sym_namelen;
+};
+
+struct hist_entry *__hists__add_entry(struct hists *self,
+				      struct addr_location *al,
+				      struct symbol *parent, u64 period);
 extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *);
 extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *);
+int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
+			bool show_displacement, long displacement, FILE *fp,
+			u64 total);
+int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
+			 struct hists *pair_hists, bool show_displacement,
+			 long displacement, bool color, u64 total);
 void hist_entry__free(struct hist_entry *);
 
-void perf_session__output_resort(struct rb_root *hists, u64 total_samples);
-void perf_session__collapse_resort(struct rb_root *hists);
-size_t perf_session__fprintf_hists(struct rb_root *hists,
-				   struct perf_session *pair,
-				   bool show_displacement, FILE *fp,
-				   u64 session_total);
+void hists__output_resort(struct hists *self);
+void hists__collapse_resort(struct hists *self);
+
+void hists__inc_nr_events(struct hists *self, u32 type);
+size_t hists__fprintf_nr_events(struct hists *self, FILE *fp);
+
+size_t hists__fprintf(struct hists *self, struct hists *pair,
+		      bool show_displacement, FILE *fp);
+
+int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip);
+int hist_entry__annotate(struct hist_entry *self, struct list_head *head);
+
+void hists__filter_by_dso(struct hists *self, const struct dso *dso);
+void hists__filter_by_thread(struct hists *self, const struct thread *thread);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int hists__browse(struct hists *self __used,
+				const char *helpline __used,
+				const char *input_name __used)
+{
+	return 0;
+}
+#else
+int hists__browse(struct hists *self, const char *helpline,
+		  const char *input_name);
+#endif
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
new file mode 100644
index 000000000000..5c1d0d099f0d
--- /dev/null
+++ b/tools/perf/util/hweight.c
@@ -0,0 +1,31 @@
+#include <linux/bitops.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int hweight32(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+}
+
+unsigned long hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+}
diff --git a/tools/perf/util/include/asm/bitops.h b/tools/perf/util/include/asm/bitops.h
deleted file mode 100644
index 58e9817ffae0..000000000000
--- a/tools/perf/util/include/asm/bitops.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef _PERF_ASM_BITOPS_H_
-#define _PERF_ASM_BITOPS_H_
-
-#include <sys/types.h>
-#include "../../types.h"
-#include <linux/compiler.h>
-
-/* CHECKME: Not sure both always match */
-#define BITS_PER_LONG	__WORDSIZE
-
-#include "../../../../include/asm-generic/bitops/__fls.h"
-#include "../../../../include/asm-generic/bitops/fls.h"
-#include "../../../../include/asm-generic/bitops/fls64.h"
-#include "../../../../include/asm-generic/bitops/__ffs.h"
-#include "../../../../include/asm-generic/bitops/ffz.h"
-#include "../../../../include/asm-generic/bitops/hweight.h"
-
-#endif
diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
new file mode 100644
index 000000000000..36cf26d434a5
--- /dev/null
+++ b/tools/perf/util/include/asm/hweight.h
@@ -0,0 +1,8 @@
+#ifndef PERF_HWEIGHT_H
+#define PERF_HWEIGHT_H
+
+#include <linux/types.h>
+unsigned int hweight32(unsigned int w);
+unsigned long hweight64(__u64 w);
+
+#endif /* PERF_HWEIGHT_H */
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
new file mode 100644
index 000000000000..cf6727e99c44
--- /dev/null
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_DWARF_REGS_H_
+#define _PERF_DWARF_REGS_H_
+
+#ifdef DWARF_SUPPORT
+const char *get_arch_regstr(unsigned int n);
+#endif
+
+#endif
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index 94507639a8c4..eda4416efa0a 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -1,3 +1,35 @@
-#include "../../../../include/linux/bitmap.h"
-#include "../../../../include/asm-generic/bitops/find.h"
-#include <linux/errno.h>
+#ifndef _PERF_BITOPS_H
+#define _PERF_BITOPS_H
+
+#include <string.h>
+#include <linux/bitops.h>
+
+int __bitmap_weight(const unsigned long *bitmap, int bits);
+
+#define BITMAP_LAST_WORD_MASK(nbits)					\
+(									\
+	((nbits) % BITS_PER_LONG) ?					\
+		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
+)
+
+#define small_const_nbits(nbits) \
+	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
+
+static inline void bitmap_zero(unsigned long *dst, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = 0UL;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memset(dst, 0, len);
+	}
+}
+
+static inline int bitmap_weight(const unsigned long *src, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight(src, nbits);
+}
+
+#endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 8d63116e9435..bb4ac2e05385 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -1,13 +1,12 @@
 #ifndef _PERF_LINUX_BITOPS_H_
 #define _PERF_LINUX_BITOPS_H_
 
-#define __KERNEL__
+#include <linux/kernel.h>
+#include <asm/hweight.h>
 
-#define CONFIG_GENERIC_FIND_NEXT_BIT
-#define CONFIG_GENERIC_FIND_FIRST_BIT
-#include "../../../../include/linux/bitops.h"
-
-#undef __KERNEL__
+#define BITS_PER_LONG __WORDSIZE
+#define BITS_PER_BYTE           8
+#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 
 static inline void set_bit(int nr, unsigned long *addr)
 {
@@ -20,10 +19,9 @@ static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
 }
 
-unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, unsigned
-		long size, unsigned long offset);
-
-unsigned long generic_find_next_le_bit(const unsigned long *addr, unsigned
-		long size, unsigned long offset);
+static inline unsigned long hweight_long(unsigned long w)
+{
+	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
 
 #endif
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
index dfb0713ed47f..791f9dd27ebf 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/perf/util/include/linux/compiler.h
@@ -7,4 +7,6 @@
 #define __user
 #define __attribute_const__
 
+#define __used		__attribute__((__unused__))
+
 #endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index f2611655ab51..1eb804fd3fbf 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -28,6 +28,8 @@
 	(type *)((char *)__mptr - offsetof(type, member)); })
 #endif
 
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
 #ifndef max
 #define max(x, y) ({				\
 	typeof(x) _max1 = (x);			\
@@ -85,16 +87,19 @@ simple_strtoul(const char *nptr, char **endptr, int base)
 	return strtoul(nptr, endptr, base);
 }
 
+int eprintf(int level,
+	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
+
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
 #endif
 
 #define pr_err(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_warning(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_info(fmt, ...) \
-	do { fprintf(stderr, pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug(fmt, ...) \
 	eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debugN(n, fmt, ...) \
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e509cd59c67d..e672f2fef65b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,9 +1,11 @@
-#include "event.h"
 #include "symbol.h"
+#include <errno.h>
+#include <limits.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdio.h>
-#include "debug.h"
+#include <unistd.h>
+#include "map.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -36,15 +38,16 @@ void map__init(struct map *self, enum map_type type,
 	self->map_ip   = map__map_ip;
 	self->unmap_ip = map__unmap_ip;
 	RB_CLEAR_NODE(&self->rb_node);
+	self->groups   = NULL;
 }
 
-struct map *map__new(struct mmap_event *event, enum map_type type,
-		     char *cwd, int cwdlen)
+struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+		     u64 pgoff, u32 pid, char *filename,
+		     enum map_type type, char *cwd, int cwdlen)
 {
 	struct map *self = malloc(sizeof(*self));
 
 	if (self != NULL) {
-		const char *filename = event->filename;
 		char newfilename[PATH_MAX];
 		struct dso *dso;
 		int anon;
@@ -62,16 +65,15 @@ struct map *map__new(struct mmap_event *event, enum map_type type,
 		anon = is_anon_memory(filename);
 
 		if (anon) {
-			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid);
+			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
 			filename = newfilename;
 		}
 
-		dso = dsos__findnew(filename);
+		dso = __dsos__findnew(dsos__list, filename);
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, event->start, event->start + event->len,
-			  event->pgoff, dso);
+		map__init(self, type, start, start + len, pgoff, dso);
 
 		if (anon) {
 set_identity:
@@ -235,3 +237,392 @@ u64 map__objdump_2ip(struct map *map, u64 addr)
 			map->unmap_ip(map, addr);	/* RIP -> IP */
 	return ip;
 }
+
+void map_groups__init(struct map_groups *self)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		self->maps[i] = RB_ROOT;
+		INIT_LIST_HEAD(&self->removed_maps[i]);
+	}
+	self->machine = NULL;
+}
+
+void map_groups__flush(struct map_groups *self)
+{
+	int type;
+
+	for (type = 0; type < MAP__NR_TYPES; type++) {
+		struct rb_root *root = &self->maps[type];
+		struct rb_node *next = rb_first(root);
+
+		while (next) {
+			struct map *pos = rb_entry(next, struct map, rb_node);
+			next = rb_next(&pos->rb_node);
+			rb_erase(&pos->rb_node, root);
+			/*
+			 * We may have references to this map, for
+			 * instance in some hist_entry instances, so
+			 * just move them to a separate list.
+			 */
+			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+		}
+	}
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *self,
+				       enum map_type type, u64 addr,
+				       struct map **mapp,
+				       symbol_filter_t filter)
+{
+	struct map *map = map_groups__find(self, type, addr);
+
+	if (map != NULL) {
+		if (mapp != NULL)
+			*mapp = map;
+		return map__find_symbol(map, map->map_ip(map, addr), filter);
+	}
+
+	return NULL;
+}
+
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+		if (sym == NULL)
+			continue;
+		if (mapp != NULL)
+			*mapp = pos;
+		return sym;
+	}
+
+	return NULL;
+}
+
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, int verbose, FILE *fp)
+{
+	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *pos = rb_entry(nd, struct map, rb_node);
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 2) {
+			printed += dso__fprintf(pos->dso, type, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+
+	return printed;
+}
+
+size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp)
+{
+	size_t printed = 0, i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		printed += __map_groups__fprintf_maps(self, i, verbose, fp);
+	return printed;
+}
+
+static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
+						 enum map_type type,
+						 int verbose, FILE *fp)
+{
+	struct map *pos;
+	size_t printed = 0;
+
+	list_for_each_entry(pos, &self->removed_maps[type], node) {
+		printed += fprintf(fp, "Map:");
+		printed += map__fprintf(pos, fp);
+		if (verbose > 1) {
+			printed += dso__fprintf(pos->dso, type, fp);
+			printed += fprintf(fp, "--\n");
+		}
+	}
+	return printed;
+}
+
+static size_t map_groups__fprintf_removed_maps(struct map_groups *self,
+					       int verbose, FILE *fp)
+{
+	size_t printed = 0, i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp);
+	return printed;
+}
+
+size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp)
+{
+	size_t printed = map_groups__fprintf_maps(self, verbose, fp);
+	printed += fprintf(fp, "Removed maps:\n");
+	return printed + map_groups__fprintf_removed_maps(self, verbose, fp);
+}
+
+int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+				   int verbose, FILE *fp)
+{
+	struct rb_root *root = &self->maps[map->type];
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node);
+		next = rb_next(&pos->rb_node);
+
+		if (!map__overlap(pos, map))
+			continue;
+
+		if (verbose >= 2) {
+			fputs("overlapping maps:\n", fp);
+			map__fprintf(map, fp);
+			map__fprintf(pos, fp);
+		}
+
+		rb_erase(&pos->rb_node, root);
+		/*
+		 * We may have references to this map, for instance in some
+		 * hist_entry instances, so just move them to a separate
+		 * list.
+		 */
+		list_add_tail(&pos->node, &self->removed_maps[map->type]);
+		/*
+		 * Now check if we need to create new maps for areas not
+		 * overlapped by the new map:
+		 */
+		if (map->start > pos->start) {
+			struct map *before = map__clone(pos);
+
+			if (before == NULL)
+				return -ENOMEM;
+
+			before->end = map->start - 1;
+			map_groups__insert(self, before);
+			if (verbose >= 2)
+				map__fprintf(before, fp);
+		}
+
+		if (map->end < pos->end) {
+			struct map *after = map__clone(pos);
+
+			if (after == NULL)
+				return -ENOMEM;
+
+			after->start = map->end + 1;
+			map_groups__insert(self, after);
+			if (verbose >= 2)
+				map__fprintf(after, fp);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * XXX This should not really _copy_ te maps, but refcount them.
+ */
+int map_groups__clone(struct map_groups *self,
+		      struct map_groups *parent, enum map_type type)
+{
+	struct rb_node *nd;
+	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
+		struct map *map = rb_entry(nd, struct map, rb_node);
+		struct map *new = map__clone(map);
+		if (new == NULL)
+			return -ENOMEM;
+		map_groups__insert(self, new);
+	}
+	return 0;
+}
+
+static u64 map__reloc_map_ip(struct map *map, u64 ip)
+{
+	return ip + (s64)map->pgoff;
+}
+
+static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
+{
+	return ip - (s64)map->pgoff;
+}
+
+void map__reloc_vmlinux(struct map *self)
+{
+	struct kmap *kmap = map__kmap(self);
+	s64 reloc;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
+		return;
+
+	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
+		 kmap->ref_reloc_sym->addr);
+
+	if (!reloc)
+		return;
+
+	self->map_ip   = map__reloc_map_ip;
+	self->unmap_ip = map__reloc_unmap_ip;
+	self->pgoff    = reloc;
+}
+
+void maps__insert(struct rb_root *maps, struct map *map)
+{
+	struct rb_node **p = &maps->rb_node;
+	struct rb_node *parent = NULL;
+	const u64 ip = map->start;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color(&map->rb_node, maps);
+}
+
+struct map *maps__find(struct rb_root *maps, u64 ip)
+{
+	struct rb_node **p = &maps->rb_node;
+	struct rb_node *parent = NULL;
+	struct map *m;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node);
+		if (ip < m->start)
+			p = &(*p)->rb_left;
+		else if (ip > m->end)
+			p = &(*p)->rb_right;
+		else
+			return m;
+	}
+
+	return NULL;
+}
+
+int machine__init(struct machine *self, const char *root_dir, pid_t pid)
+{
+	map_groups__init(&self->kmaps);
+	RB_CLEAR_NODE(&self->rb_node);
+	INIT_LIST_HEAD(&self->user_dsos);
+	INIT_LIST_HEAD(&self->kernel_dsos);
+
+	self->kmaps.machine = self;
+	self->pid	    = pid;
+	self->root_dir      = strdup(root_dir);
+	return self->root_dir == NULL ? -ENOMEM : 0;
+}
+
+struct machine *machines__add(struct rb_root *self, pid_t pid,
+			      const char *root_dir)
+{
+	struct rb_node **p = &self->rb_node;
+	struct rb_node *parent = NULL;
+	struct machine *pos, *machine = malloc(sizeof(*machine));
+
+	if (!machine)
+		return NULL;
+
+	if (machine__init(machine, root_dir, pid) != 0) {
+		free(machine);
+		return NULL;
+	}
+
+	while (*p != NULL) {
+		parent = *p;
+		pos = rb_entry(parent, struct machine, rb_node);
+		if (pid < pos->pid)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&machine->rb_node, parent, p);
+	rb_insert_color(&machine->rb_node, self);
+
+	return machine;
+}
+
+struct machine *machines__find(struct rb_root *self, pid_t pid)
+{
+	struct rb_node **p = &self->rb_node;
+	struct rb_node *parent = NULL;
+	struct machine *machine;
+	struct machine *default_machine = NULL;
+
+	while (*p != NULL) {
+		parent = *p;
+		machine = rb_entry(parent, struct machine, rb_node);
+		if (pid < machine->pid)
+			p = &(*p)->rb_left;
+		else if (pid > machine->pid)
+			p = &(*p)->rb_right;
+		else
+			return machine;
+		if (!machine->pid)
+			default_machine = machine;
+	}
+
+	return default_machine;
+}
+
+struct machine *machines__findnew(struct rb_root *self, pid_t pid)
+{
+	char path[PATH_MAX];
+	const char *root_dir;
+	struct machine *machine = machines__find(self, pid);
+
+	if (!machine || machine->pid != pid) {
+		if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID)
+			root_dir = "";
+		else {
+			if (!symbol_conf.guestmount)
+				goto out;
+			sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+			if (access(path, R_OK)) {
+				pr_err("Can't access file %s\n", path);
+				goto out;
+			}
+			root_dir = path;
+		}
+		machine = machines__add(self, pid, root_dir);
+	}
+
+out:
+	return machine;
+}
+
+void machines__process(struct rb_root *self, machine__process_t process, void *data)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		process(pos, data);
+	}
+}
+
+char *machine__mmap_name(struct machine *self, char *bf, size_t size)
+{
+	if (machine__is_host(self))
+		snprintf(bf, size, "[%s]", "kernel.kallsyms");
+	else if (machine__is_default_guest(self))
+		snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
+	else
+		snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", self->pid);
+
+	return bf;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b756368076c6..f39134512829 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -4,7 +4,9 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include <linux/types.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include "types.h"
 
 enum map_type {
 	MAP__FUNCTION = 0,
@@ -18,6 +20,7 @@ extern const char *map_type__name[MAP__NR_TYPES];
 struct dso;
 struct ref_reloc_sym;
 struct map_groups;
+struct machine;
 
 struct map {
 	union {
@@ -27,6 +30,7 @@ struct map {
 	u64			start;
 	u64			end;
 	enum map_type		type;
+	u32			priv;
 	u64			pgoff;
 
 	/* ip -> dso rip */
@@ -35,6 +39,7 @@ struct map {
 	u64			(*unmap_ip)(struct map *, u64);
 
 	struct dso		*dso;
+	struct map_groups	*groups;
 };
 
 struct kmap {
@@ -42,6 +47,32 @@ struct kmap {
 	struct map_groups	*kmaps;
 };
 
+struct map_groups {
+	struct rb_root	 maps[MAP__NR_TYPES];
+	struct list_head removed_maps[MAP__NR_TYPES];
+	struct machine	 *machine;
+};
+
+/* Native host kernel uses -1 as pid index in machine */
+#define	HOST_KERNEL_ID			(-1)
+#define	DEFAULT_GUEST_KERNEL_ID		(0)
+
+struct machine {
+	struct rb_node	  rb_node;
+	pid_t		  pid;
+	char		  *root_dir;
+	struct list_head  user_dsos;
+	struct list_head  kernel_dsos;
+	struct map_groups kmaps;
+	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+};
+
+static inline
+struct map *machine__kernel_map(struct machine *self, enum map_type type)
+{
+	return self->vmlinux_maps[type];
+}
+
 static inline struct kmap *map__kmap(struct map *self)
 {
 	return (struct kmap *)(self + 1);
@@ -68,14 +99,14 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
 u64 map__objdump_2ip(struct map *map, u64 addr);
 
 struct symbol;
-struct mmap_event;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *self, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
-struct map *map__new(struct mmap_event *event, enum map_type,
-		     char *cwd, int cwdlen);
+struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+		     u64 pgoff, u32 pid, char *filename,
+		     enum map_type type, char *cwd, int cwdlen);
 void map__delete(struct map *self);
 struct map *map__clone(struct map *self);
 int map__overlap(struct map *l, struct map *r);
@@ -91,4 +122,96 @@ void map__fixup_end(struct map *self);
 
 void map__reloc_vmlinux(struct map *self);
 
+size_t __map_groups__fprintf_maps(struct map_groups *self,
+				  enum map_type type, int verbose, FILE *fp);
+void maps__insert(struct rb_root *maps, struct map *map);
+struct map *maps__find(struct rb_root *maps, u64 addr);
+void map_groups__init(struct map_groups *self);
+int map_groups__clone(struct map_groups *self,
+		      struct map_groups *parent, enum map_type type);
+size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp);
+size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp);
+
+typedef void (*machine__process_t)(struct machine *self, void *data);
+
+void machines__process(struct rb_root *self, machine__process_t process, void *data);
+struct machine *machines__add(struct rb_root *self, pid_t pid,
+			      const char *root_dir);
+struct machine *machines__find_host(struct rb_root *self);
+struct machine *machines__find(struct rb_root *self, pid_t pid);
+struct machine *machines__findnew(struct rb_root *self, pid_t pid);
+char *machine__mmap_name(struct machine *self, char *bf, size_t size);
+int machine__init(struct machine *self, const char *root_dir, pid_t pid);
+
+/*
+ * Default guest kernel is defined by parameter --guestkallsyms
+ * and --guestmodules
+ */
+static inline bool machine__is_default_guest(struct machine *self)
+{
+	return self ? self->pid == DEFAULT_GUEST_KERNEL_ID : false;
+}
+
+static inline bool machine__is_host(struct machine *self)
+{
+	return self ? self->pid == HOST_KERNEL_ID : false;
+}
+
+static inline void map_groups__insert(struct map_groups *self, struct map *map)
+{
+	maps__insert(&self->maps[map->type], map);
+	map->groups = self;
+}
+
+static inline struct map *map_groups__find(struct map_groups *self,
+					   enum map_type type, u64 addr)
+{
+	return maps__find(&self->maps[type], addr);
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *self,
+				       enum map_type type, u64 addr,
+				       struct map **mapp,
+				       symbol_filter_t filter);
+
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+					       enum map_type type,
+					       const char *name,
+					       struct map **mapp,
+					       symbol_filter_t filter);
+
+static inline
+struct symbol *machine__find_kernel_symbol(struct machine *self,
+					   enum map_type type, u64 addr,
+					   struct map **mapp,
+					   symbol_filter_t filter)
+{
+	return map_groups__find_symbol(&self->kmaps, type, addr, mapp, filter);
+}
+
+static inline
+struct symbol *machine__find_kernel_function(struct machine *self, u64 addr,
+					     struct map **mapp,
+					     symbol_filter_t filter)
+{
+	return machine__find_kernel_symbol(self, MAP__FUNCTION, addr, mapp, filter);
+}
+
+static inline
+struct symbol *map_groups__find_function_by_name(struct map_groups *self,
+						 const char *name, struct map **mapp,
+						 symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
+}
+
+int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+				   int verbose, FILE *fp);
+
+struct map *map_groups__find_by_name(struct map_groups *self,
+				     enum map_type type, const char *name);
+struct map *machine__new_module(struct machine *self, u64 start, const char *filename);
+
+void map_groups__flush(struct map_groups *self);
+
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
new file mode 100644
index 000000000000..ccb7c5bb269e
--- /dev/null
+++ b/tools/perf/util/newt.c
@@ -0,0 +1,1084 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#undef _GNU_SOURCE
+
+#include <slang.h>
+#include <stdlib.h>
+#include <newt.h>
+#include <sys/ttydefaults.h>
+
+#include "cache.h"
+#include "hist.h"
+#include "pstack.h"
+#include "session.h"
+#include "sort.h"
+#include "symbol.h"
+
+#if SLANG_VERSION < 20104
+#define slsmg_printf(msg, args...) SLsmg_printf((char *)msg, ##args)
+#define slsmg_write_nstring(msg, len) SLsmg_write_nstring((char *)msg, len)
+#define sltt_set_color(obj, name, fg, bg) SLtt_set_color(obj,(char *)name,\
+							 (char *)fg, (char *)bg)
+#else
+#define slsmg_printf SLsmg_printf
+#define slsmg_write_nstring SLsmg_write_nstring
+#define sltt_set_color SLtt_set_color
+#endif
+
+struct ui_progress {
+	newtComponent form, scale;
+};
+
+struct ui_progress *ui_progress__new(const char *title, u64 total)
+{
+	struct ui_progress *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		int cols;
+		newtGetScreenSize(&cols, NULL);
+		cols -= 4;
+		newtCenteredWindow(cols, 1, title);
+		self->form  = newtForm(NULL, NULL, 0);
+		if (self->form == NULL)
+			goto out_free_self;
+		self->scale = newtScale(0, 0, cols, total);
+		if (self->scale == NULL)
+			goto out_free_form;
+		newtFormAddComponent(self->form, self->scale);
+		newtRefresh();
+	}
+
+	return self;
+
+out_free_form:
+	newtFormDestroy(self->form);
+out_free_self:
+	free(self);
+	return NULL;
+}
+
+void ui_progress__update(struct ui_progress *self, u64 curr)
+{
+	newtScaleSet(self->scale, curr);
+	newtRefresh();
+}
+
+void ui_progress__delete(struct ui_progress *self)
+{
+	newtFormDestroy(self->form);
+	newtPopWindow();
+	free(self);
+}
+
+static void ui_helpline__pop(void)
+{
+	newtPopHelpLine();
+}
+
+static void ui_helpline__push(const char *msg)
+{
+	newtPushHelpLine(msg);
+}
+
+static void ui_helpline__vpush(const char *fmt, va_list ap)
+{
+	char *s;
+
+	if (vasprintf(&s, fmt, ap) < 0)
+		vfprintf(stderr, fmt, ap);
+	else {
+		ui_helpline__push(s);
+		free(s);
+	}
+}
+
+static void ui_helpline__fpush(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	ui_helpline__vpush(fmt, ap);
+	va_end(ap);
+}
+
+static void ui_helpline__puts(const char *msg)
+{
+	ui_helpline__pop();
+	ui_helpline__push(msg);
+}
+
+static char browser__last_msg[1024];
+
+int browser__show_help(const char *format, va_list ap)
+{
+	int ret;
+	static int backlog;
+
+        ret = vsnprintf(browser__last_msg + backlog,
+			sizeof(browser__last_msg) - backlog, format, ap);
+	backlog += ret;
+
+	if (browser__last_msg[backlog - 1] == '\n') {
+		ui_helpline__puts(browser__last_msg);
+		newtRefresh();
+		backlog = 0;
+	}
+
+	return ret;
+}
+
+static void newt_form__set_exit_keys(newtComponent self)
+{
+	newtFormAddHotKey(self, NEWT_KEY_LEFT);
+	newtFormAddHotKey(self, NEWT_KEY_ESCAPE);
+	newtFormAddHotKey(self, 'Q');
+	newtFormAddHotKey(self, 'q');
+	newtFormAddHotKey(self, CTRL('c'));
+}
+
+static newtComponent newt_form__new(void)
+{
+	newtComponent self = newtForm(NULL, NULL, 0);
+	if (self)
+		newt_form__set_exit_keys(self);
+	return self;
+}
+
+static int popup_menu(int argc, char * const argv[])
+{
+	struct newtExitStruct es;
+	int i, rc = -1, max_len = 5;
+	newtComponent listbox, form = newt_form__new();
+
+	if (form == NULL)
+		return -1;
+
+	listbox = newtListbox(0, 0, argc, NEWT_FLAG_RETURNEXIT);
+	if (listbox == NULL)
+		goto out_destroy_form;
+
+	newtFormAddComponent(form, listbox);
+
+	for (i = 0; i < argc; ++i) {
+		int len = strlen(argv[i]);
+		if (len > max_len)
+			max_len = len;
+		if (newtListboxAddEntry(listbox, argv[i], (void *)(long)i))
+			goto out_destroy_form;
+	}
+
+	newtCenteredWindow(max_len, argc, NULL);
+	newtFormRun(form, &es);
+	rc = newtListboxGetCurrent(listbox) - NULL;
+	if (es.reason == NEWT_EXIT_HOTKEY)
+		rc = -1;
+	newtPopWindow();
+out_destroy_form:
+	newtFormDestroy(form);
+	return rc;
+}
+
+static int ui__help_window(const char *text)
+{
+	struct newtExitStruct es;
+	newtComponent tb, form = newt_form__new();
+	int rc = -1;
+	int max_len = 0, nr_lines = 0;
+	const char *t;
+
+	if (form == NULL)
+		return -1;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+		int len;
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	tb = newtTextbox(0, 0, max_len, nr_lines, 0);
+	if (tb == NULL)
+		goto out_destroy_form;
+
+	newtTextboxSetText(tb, text);
+	newtFormAddComponent(form, tb);
+	newtCenteredWindow(max_len, nr_lines, NULL);
+	newtFormRun(form, &es);
+	newtPopWindow();
+	rc = 0;
+out_destroy_form:
+	newtFormDestroy(form);
+	return rc;
+}
+
+static bool dialog_yesno(const char *msg)
+{
+	/* newtWinChoice should really be accepting const char pointers... */
+	char yes[] = "Yes", no[] = "No";
+	return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
+}
+
+#define HE_COLORSET_TOP		50
+#define HE_COLORSET_MEDIUM	51
+#define HE_COLORSET_NORMAL	52
+#define HE_COLORSET_SELECTED	53
+#define HE_COLORSET_CODE	54
+
+static int ui_browser__percent_color(double percent, bool current)
+{
+	if (current)
+		return HE_COLORSET_SELECTED;
+	if (percent >= MIN_RED)
+		return HE_COLORSET_TOP;
+	if (percent >= MIN_GREEN)
+		return HE_COLORSET_MEDIUM;
+	return HE_COLORSET_NORMAL;
+}
+
+struct ui_browser {
+	newtComponent	form, sb;
+	u64		index, first_visible_entry_idx;
+	void		*first_visible_entry, *entries;
+	u16		top, left, width, height;
+	void		*priv;
+	u32		nr_entries;
+};
+
+static void ui_browser__refresh_dimensions(struct ui_browser *self)
+{
+	int cols, rows;
+	newtGetScreenSize(&cols, &rows);
+
+	if (self->width > cols - 4)
+		self->width = cols - 4;
+	self->height = rows - 5;
+	if (self->height > self->nr_entries)
+		self->height = self->nr_entries;
+	self->top  = (rows - self->height) / 2;
+	self->left = (cols - self->width) / 2;
+}
+
+static void ui_browser__reset_index(struct ui_browser *self)
+{
+        self->index = self->first_visible_entry_idx = 0;
+        self->first_visible_entry = NULL;
+}
+
+static int objdump_line__show(struct objdump_line *self, struct list_head *head,
+			      int width, struct hist_entry *he, int len,
+			      bool current_entry)
+{
+	if (self->offset != -1) {
+		struct symbol *sym = he->ms.sym;
+		unsigned int hits = 0;
+		double percent = 0.0;
+		int color;
+		struct sym_priv *priv = symbol__priv(sym);
+		struct sym_ext *sym_ext = priv->ext;
+		struct sym_hist *h = priv->hist;
+		s64 offset = self->offset;
+		struct objdump_line *next = objdump__get_next_ip_line(head, self);
+
+		while (offset < (s64)len &&
+		       (next == NULL || offset < next->offset)) {
+			if (sym_ext) {
+				percent += sym_ext[offset].percent;
+			} else
+				hits += h->ip[offset];
+
+			++offset;
+		}
+
+		if (sym_ext == NULL && h->sum)
+			percent = 100.0 * hits / h->sum;
+
+		color = ui_browser__percent_color(percent, current_entry);
+		SLsmg_set_color(color);
+		slsmg_printf(" %7.2f ", percent);
+		if (!current_entry)
+			SLsmg_set_color(HE_COLORSET_CODE);
+	} else {
+		int color = ui_browser__percent_color(0, current_entry);
+		SLsmg_set_color(color);
+		slsmg_write_nstring(" ", 9);
+	}
+
+	SLsmg_write_char(':');
+	slsmg_write_nstring(" ", 8);
+	if (!*self->line)
+		slsmg_write_nstring(" ", width - 18);
+	else
+		slsmg_write_nstring(self->line, width - 18);
+
+	return 0;
+}
+
+static int ui_browser__refresh_entries(struct ui_browser *self)
+{
+	struct objdump_line *pos;
+	struct list_head *head = self->entries;
+	struct hist_entry *he = self->priv;
+	int row = 0;
+	int len = he->ms.sym->end - he->ms.sym->start;
+
+	if (self->first_visible_entry == NULL || self->first_visible_entry == self->entries)
+                self->first_visible_entry = head->next;
+
+	pos = list_entry(self->first_visible_entry, struct objdump_line, node);
+
+	list_for_each_entry_from(pos, head, node) {
+		bool current_entry = (self->first_visible_entry_idx + row) == self->index;
+		SLsmg_gotorc(self->top + row, self->left);
+		objdump_line__show(pos, head, self->width,
+				   he, len, current_entry);
+		if (++row == self->height)
+			break;
+	}
+
+	SLsmg_set_color(HE_COLORSET_NORMAL);
+	SLsmg_fill_region(self->top + row, self->left,
+			  self->height - row, self->width, ' ');
+
+	return 0;
+}
+
+static int ui_browser__run(struct ui_browser *self, const char *title,
+			   struct newtExitStruct *es)
+{
+	if (self->form) {
+		newtFormDestroy(self->form);
+		newtPopWindow();
+	}
+
+	ui_browser__refresh_dimensions(self);
+	newtCenteredWindow(self->width + 2, self->height, title);
+	self->form = newt_form__new();
+	if (self->form == NULL)
+		return -1;
+
+	self->sb = newtVerticalScrollbar(self->width + 1, 0, self->height,
+					 HE_COLORSET_NORMAL,
+					 HE_COLORSET_SELECTED);
+	if (self->sb == NULL)
+		return -1;
+
+	newtFormAddHotKey(self->form, NEWT_KEY_UP);
+	newtFormAddHotKey(self->form, NEWT_KEY_DOWN);
+	newtFormAddHotKey(self->form, NEWT_KEY_PGUP);
+	newtFormAddHotKey(self->form, NEWT_KEY_PGDN);
+	newtFormAddHotKey(self->form, NEWT_KEY_HOME);
+	newtFormAddHotKey(self->form, NEWT_KEY_END);
+
+	if (ui_browser__refresh_entries(self) < 0)
+		return -1;
+	newtFormAddComponent(self->form, self->sb);
+
+	while (1) {
+		unsigned int offset;
+
+		newtFormRun(self->form, es);
+
+		if (es->reason != NEWT_EXIT_HOTKEY)
+			break;
+		switch (es->u.key) {
+		case NEWT_KEY_DOWN:
+			if (self->index == self->nr_entries - 1)
+				break;
+			++self->index;
+			if (self->index == self->first_visible_entry_idx + self->height) {
+				struct list_head *pos = self->first_visible_entry;
+				++self->first_visible_entry_idx;
+				self->first_visible_entry = pos->next;
+			}
+			break;
+		case NEWT_KEY_UP:
+			if (self->index == 0)
+				break;
+			--self->index;
+			if (self->index < self->first_visible_entry_idx) {
+				struct list_head *pos = self->first_visible_entry;
+				--self->first_visible_entry_idx;
+				self->first_visible_entry = pos->prev;
+			}
+			break;
+		case NEWT_KEY_PGDN:
+			if (self->first_visible_entry_idx + self->height > self->nr_entries - 1)
+				break;
+
+			offset = self->height;
+			if (self->index + offset > self->nr_entries - 1)
+				offset = self->nr_entries - 1 - self->index;
+			self->index += offset;
+			self->first_visible_entry_idx += offset;
+
+			while (offset--) {
+				struct list_head *pos = self->first_visible_entry;
+				self->first_visible_entry = pos->next;
+			}
+
+			break;
+		case NEWT_KEY_PGUP:
+			if (self->first_visible_entry_idx == 0)
+				break;
+
+			if (self->first_visible_entry_idx < self->height)
+				offset = self->first_visible_entry_idx;
+			else
+				offset = self->height;
+
+			self->index -= offset;
+			self->first_visible_entry_idx -= offset;
+
+			while (offset--) {
+				struct list_head *pos = self->first_visible_entry;
+				self->first_visible_entry = pos->prev;
+			}
+			break;
+		case NEWT_KEY_HOME:
+			ui_browser__reset_index(self);
+			break;
+		case NEWT_KEY_END: {
+			struct list_head *head = self->entries;
+			offset = self->height - 1;
+
+			if (offset > self->nr_entries)
+				offset = self->nr_entries;
+
+			self->index = self->first_visible_entry_idx = self->nr_entries - 1 - offset;
+			self->first_visible_entry = head->prev;
+			while (offset-- != 0) {
+				struct list_head *pos = self->first_visible_entry;
+				self->first_visible_entry = pos->prev;
+			}
+		}
+			break;
+		case NEWT_KEY_ESCAPE:
+		case NEWT_KEY_LEFT:
+		case CTRL('c'):
+		case 'Q':
+		case 'q':
+			return 0;
+		default:
+			continue;
+		}
+		if (ui_browser__refresh_entries(self) < 0)
+			return -1;
+	}
+	return 0;
+}
+
+/*
+ * When debugging newt problems it was useful to be able to "unroll"
+ * the calls to newtCheckBoxTreeAdd{Array,Item}, so that we can generate
+ * a source file with the sequence of calls to these methods, to then
+ * tweak the arrays to get the intended results, so I'm keeping this code
+ * here, may be useful again in the future.
+ */
+#undef NEWT_DEBUG
+
+static void newt_checkbox_tree__add(newtComponent tree, const char *str,
+				    void *priv, int *indexes)
+{
+#ifdef NEWT_DEBUG
+	/* Print the newtCheckboxTreeAddArray to tinker with its index arrays */
+	int i = 0, len = 40 - strlen(str);
+
+	fprintf(stderr,
+		"\tnewtCheckboxTreeAddItem(tree, %*.*s\"%s\", (void *)%p, 0, ",
+		len, len, " ", str, priv);
+	while (indexes[i] != NEWT_ARG_LAST) {
+		if (indexes[i] != NEWT_ARG_APPEND)
+			fprintf(stderr, " %d,", indexes[i]);
+		else
+			fprintf(stderr, " %s,", "NEWT_ARG_APPEND");
+		++i;
+	}
+	fprintf(stderr, " %s", " NEWT_ARG_LAST);\n");
+	fflush(stderr);
+#endif
+	newtCheckboxTreeAddArray(tree, str, priv, 0, indexes);
+}
+
+static char *callchain_list__sym_name(struct callchain_list *self,
+				      char *bf, size_t bfsize)
+{
+	if (self->ms.sym)
+		return self->ms.sym->name;
+
+	snprintf(bf, bfsize, "%#Lx", self->ip);
+	return bf;
+}
+
+static void __callchain__append_graph_browser(struct callchain_node *self,
+					      newtComponent tree, u64 total,
+					      int *indexes, int depth)
+{
+	struct rb_node *node;
+	u64 new_total, remaining;
+	int idx = 0;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = self->children_hit;
+	else
+		new_total = total;
+
+	remaining = new_total;
+	node = rb_first(&self->rb_root);
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		u64 cumul = cumul_hits(child);
+		struct callchain_list *chain;
+		int first = true, printed = 0;
+		int chain_idx = -1;
+		remaining -= cumul;
+
+		indexes[depth] = NEWT_ARG_APPEND;
+		indexes[depth + 1] = NEWT_ARG_LAST;
+
+		list_for_each_entry(chain, &child->val, list) {
+			char ipstr[BITS_PER_LONG / 4 + 1],
+			     *alloc_str = NULL;
+			const char *str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+
+			if (first) {
+				double percent = cumul * 100.0 / new_total;
+
+				first = false;
+				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+					str = "Not enough memory!";
+				else
+					str = alloc_str;
+			} else {
+				indexes[depth] = idx;
+				indexes[depth + 1] = NEWT_ARG_APPEND;
+				indexes[depth + 2] = NEWT_ARG_LAST;
+				++chain_idx;
+			}
+			newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
+			free(alloc_str);
+			++printed;
+		}
+
+		indexes[depth] = idx;
+		if (chain_idx != -1)
+			indexes[depth + 1] = chain_idx;
+		if (printed != 0)
+			++idx;
+		__callchain__append_graph_browser(child, tree, new_total, indexes,
+						  depth + (chain_idx != -1 ? 2 : 1));
+		node = next;
+	}
+}
+
+static void callchain__append_graph_browser(struct callchain_node *self,
+					    newtComponent tree, u64 total,
+					    int *indexes, int parent_idx)
+{
+	struct callchain_list *chain;
+	int i = 0;
+
+	indexes[1] = NEWT_ARG_APPEND;
+	indexes[2] = NEWT_ARG_LAST;
+
+	list_for_each_entry(chain, &self->val, list) {
+		char ipstr[BITS_PER_LONG / 4 + 1], *str;
+
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+
+		if (!i++ && sort__first_dimension == SORT_SYM)
+			continue;
+
+		str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+		newt_checkbox_tree__add(tree, str, &chain->ms, indexes);
+	}
+
+	indexes[1] = parent_idx;
+	indexes[2] = NEWT_ARG_APPEND;
+	indexes[3] = NEWT_ARG_LAST;
+	__callchain__append_graph_browser(self, tree, total, indexes, 2);
+}
+
+static void hist_entry__append_callchain_browser(struct hist_entry *self,
+						 newtComponent tree, u64 total, int parent_idx)
+{
+	struct rb_node *rb_node;
+	int indexes[1024] = { [0] = parent_idx, };
+	int idx = 0;
+	struct callchain_node *chain;
+
+	rb_node = rb_first(&self->sorted_chain);
+	while (rb_node) {
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		switch (callchain_param.mode) {
+		case CHAIN_FLAT:
+			break;
+		case CHAIN_GRAPH_ABS: /* falldown */
+		case CHAIN_GRAPH_REL:
+			callchain__append_graph_browser(chain, tree, total, indexes, idx++);
+			break;
+		case CHAIN_NONE:
+		default:
+			break;
+		}
+		rb_node = rb_next(rb_node);
+	}
+}
+
+static size_t hist_entry__append_browser(struct hist_entry *self,
+					 newtComponent tree, u64 total)
+{
+	char s[256];
+	size_t ret;
+
+	if (symbol_conf.exclude_other && !self->parent)
+		return 0;
+
+	ret = hist_entry__snprintf(self, s, sizeof(s), NULL,
+				   false, 0, false, total);
+	if (symbol_conf.use_callchain) {
+		int indexes[2];
+
+		indexes[0] = NEWT_ARG_APPEND;
+		indexes[1] = NEWT_ARG_LAST;
+		newt_checkbox_tree__add(tree, s, &self->ms, indexes);
+	} else
+		newtListboxAppendEntry(tree, s, &self->ms);
+
+	return ret;
+}
+
+static void hist_entry__annotate_browser(struct hist_entry *self)
+{
+	struct ui_browser browser;
+	struct newtExitStruct es;
+	struct objdump_line *pos, *n;
+	LIST_HEAD(head);
+
+	if (self->ms.sym == NULL)
+		return;
+
+	if (hist_entry__annotate(self, &head) < 0)
+		return;
+
+	ui_helpline__push("Press <- or ESC to exit");
+
+	memset(&browser, 0, sizeof(browser));
+	browser.entries = &head;
+	browser.priv = self;
+	list_for_each_entry(pos, &head, node) {
+		size_t line_len = strlen(pos->line);
+		if (browser.width < line_len)
+			browser.width = line_len;
+		++browser.nr_entries;
+	}
+
+	browser.width += 18; /* Percentage */
+	ui_browser__run(&browser, self->ms.sym->name, &es);
+	newtFormDestroy(browser.form);
+	newtPopWindow();
+	list_for_each_entry_safe(pos, n, &head, node) {
+		list_del(&pos->node);
+		objdump_line__free(pos);
+	}
+	ui_helpline__pop();
+}
+
+static const void *newt__symbol_tree_get_current(newtComponent self)
+{
+	if (symbol_conf.use_callchain)
+		return newtCheckboxTreeGetCurrent(self);
+	return newtListboxGetCurrent(self);
+}
+
+static void hist_browser__selection(newtComponent self, void *data)
+{
+	const struct map_symbol **symbol_ptr = data;
+	*symbol_ptr = newt__symbol_tree_get_current(self);
+}
+
+struct hist_browser {
+	newtComponent		form, tree;
+	const struct map_symbol *selection;
+};
+
+static struct hist_browser *hist_browser__new(void)
+{
+	struct hist_browser *self = malloc(sizeof(*self));
+
+	if (self != NULL)
+		self->form = NULL;
+
+	return self;
+}
+
+static void hist_browser__delete(struct hist_browser *self)
+{
+	newtFormDestroy(self->form);
+	newtPopWindow();
+	free(self);
+}
+
+static int hist_browser__populate(struct hist_browser *self, struct hists *hists,
+				  const char *title)
+{
+	int max_len = 0, idx, cols, rows;
+	struct ui_progress *progress;
+	struct rb_node *nd;
+	u64 curr_hist = 0;
+	char seq[] = ".", unit;
+	char str[256];
+	unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+	if (self->form) {
+		newtFormDestroy(self->form);
+		newtPopWindow();
+	}
+
+	nr_events = convert_unit(nr_events, &unit);
+	snprintf(str, sizeof(str), "Events: %lu%c                            ",
+		 nr_events, unit);
+	newtDrawRootText(0, 0, str);
+
+	newtGetScreenSize(NULL, &rows);
+
+	if (symbol_conf.use_callchain)
+		self->tree = newtCheckboxTreeMulti(0, 0, rows - 5, seq,
+						   NEWT_FLAG_SCROLL);
+	else
+		self->tree = newtListbox(0, 0, rows - 5,
+					(NEWT_FLAG_SCROLL |
+					 NEWT_FLAG_RETURNEXIT));
+
+	newtComponentAddCallback(self->tree, hist_browser__selection,
+				 &self->selection);
+
+	progress = ui_progress__new("Adding entries to the browser...",
+				    hists->nr_entries);
+	if (progress == NULL)
+		return -1;
+
+	idx = 0;
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int len;
+
+		if (h->filtered)
+			continue;
+
+		len = hist_entry__append_browser(h, self->tree, hists->stats.total_period);
+		if (len > max_len)
+			max_len = len;
+		if (symbol_conf.use_callchain)
+			hist_entry__append_callchain_browser(h, self->tree,
+							     hists->stats.total_period, idx++);
+		++curr_hist;
+		if (curr_hist % 5)
+			ui_progress__update(progress, curr_hist);
+	}
+
+	ui_progress__delete(progress);
+
+	newtGetScreenSize(&cols, &rows);
+
+	if (max_len > cols)
+		max_len = cols - 3;
+
+	if (!symbol_conf.use_callchain)
+		newtListboxSetWidth(self->tree, max_len);
+
+	newtCenteredWindow(max_len + (symbol_conf.use_callchain ? 5 : 0),
+			   rows - 5, title);
+	self->form = newt_form__new();
+	if (self->form == NULL)
+		return -1;
+
+	newtFormAddHotKey(self->form, 'A');
+	newtFormAddHotKey(self->form, 'a');
+	newtFormAddHotKey(self->form, 'D');
+	newtFormAddHotKey(self->form, 'd');
+	newtFormAddHotKey(self->form, 'T');
+	newtFormAddHotKey(self->form, 't');
+	newtFormAddHotKey(self->form, '?');
+	newtFormAddHotKey(self->form, 'H');
+	newtFormAddHotKey(self->form, 'h');
+	newtFormAddHotKey(self->form, NEWT_KEY_F1);
+	newtFormAddHotKey(self->form, NEWT_KEY_RIGHT);
+	newtFormAddComponents(self->form, self->tree, NULL);
+	self->selection = newt__symbol_tree_get_current(self->tree);
+
+	return 0;
+}
+
+static struct hist_entry *hist_browser__selected_entry(struct hist_browser *self)
+{
+	int *indexes;
+
+	if (!symbol_conf.use_callchain)
+		goto out;
+
+	indexes = newtCheckboxTreeFindItem(self->tree, (void *)self->selection);
+	if (indexes) {
+		bool is_hist_entry = indexes[1] == NEWT_ARG_LAST;
+		free(indexes);
+		if (is_hist_entry)
+			goto out;
+	}
+	return NULL;
+out:
+	return container_of(self->selection, struct hist_entry, ms);
+}
+
+static struct thread *hist_browser__selected_thread(struct hist_browser *self)
+{
+	struct hist_entry *he = hist_browser__selected_entry(self);
+	return he ? he->thread : NULL;
+}
+
+static int hist_browser__title(char *bf, size_t size, const char *input_name,
+			       const struct dso *dso, const struct thread *thread)
+{
+	int printed = 0;
+
+	if (thread)
+		printed += snprintf(bf + printed, size - printed,
+				    "Thread: %s(%d)",
+				    (thread->comm_set ?  thread->comm : ""),
+				    thread->pid);
+	if (dso)
+		printed += snprintf(bf + printed, size - printed,
+				    "%sDSO: %s", thread ? " " : "",
+				    dso->short_name);
+	return printed ?: snprintf(bf, size, "Report: %s", input_name);
+}
+
+int hists__browse(struct hists *self, const char *helpline, const char *input_name)
+{
+	struct hist_browser *browser = hist_browser__new();
+	struct pstack *fstack = pstack__new(2);
+	const struct thread *thread_filter = NULL;
+	const struct dso *dso_filter = NULL;
+	struct newtExitStruct es;
+	char msg[160];
+	int err = -1;
+
+	if (browser == NULL)
+		return -1;
+
+	fstack = pstack__new(2);
+	if (fstack == NULL)
+		goto out;
+
+	ui_helpline__push(helpline);
+
+	hist_browser__title(msg, sizeof(msg), input_name,
+			    dso_filter, thread_filter);
+	if (hist_browser__populate(browser, self, msg) < 0)
+		goto out_free_stack;
+
+	while (1) {
+		const struct thread *thread;
+		const struct dso *dso;
+		char *options[16];
+		int nr_options = 0, choice = 0, i,
+		    annotate = -2, zoom_dso = -2, zoom_thread = -2;
+
+		newtFormRun(browser->form, &es);
+
+		thread = hist_browser__selected_thread(browser);
+		dso = browser->selection->map ? browser->selection->map->dso : NULL;
+
+		if (es.reason == NEWT_EXIT_HOTKEY) {
+			if (es.u.key == NEWT_KEY_F1)
+				goto do_help;
+
+			switch (toupper(es.u.key)) {
+			case 'A':
+				goto do_annotate;
+			case 'D':
+				goto zoom_dso;
+			case 'T':
+				goto zoom_thread;
+			case 'H':
+			case '?':
+do_help:
+				ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
+						"<-        Zoom out\n"
+						"a         Annotate current symbol\n"
+						"h/?/F1    Show this window\n"
+						"d         Zoom into current DSO\n"
+						"t         Zoom into current Thread\n"
+						"q/CTRL+C  Exit browser");
+				continue;
+			default:;
+			}
+			if (toupper(es.u.key) == 'Q' ||
+			    es.u.key == CTRL('c'))
+				break;
+			if (es.u.key == NEWT_KEY_ESCAPE) {
+				if (dialog_yesno("Do you really want to exit?"))
+					break;
+				else
+					continue;
+			}
+
+			if (es.u.key == NEWT_KEY_LEFT) {
+				const void *top;
+
+				if (pstack__empty(fstack))
+					continue;
+				top = pstack__pop(fstack);
+				if (top == &dso_filter)
+					goto zoom_out_dso;
+				if (top == &thread_filter)
+					goto zoom_out_thread;
+				continue;
+			}
+		}
+
+		if (browser->selection->sym != NULL &&
+		    asprintf(&options[nr_options], "Annotate %s",
+			     browser->selection->sym->name) > 0)
+			annotate = nr_options++;
+
+		if (thread != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
+			     (thread_filter ? "out of" : "into"),
+			     (thread->comm_set ? thread->comm : ""),
+			     thread->pid) > 0)
+			zoom_thread = nr_options++;
+
+		if (dso != NULL &&
+		    asprintf(&options[nr_options], "Zoom %s %s DSO",
+			     (dso_filter ? "out of" : "into"),
+			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
+			zoom_dso = nr_options++;
+
+		options[nr_options++] = (char *)"Exit";
+
+		choice = popup_menu(nr_options, options);
+
+		for (i = 0; i < nr_options - 1; ++i)
+			free(options[i]);
+
+		if (choice == nr_options - 1)
+			break;
+
+		if (choice == -1)
+			continue;
+
+		if (choice == annotate) {
+			struct hist_entry *he;
+do_annotate:
+			if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
+				ui_helpline__puts("No vmlinux file found, can't "
+						 "annotate with just a "
+						 "kallsyms file");
+				continue;
+			}
+
+			he = hist_browser__selected_entry(browser);
+			if (he == NULL)
+				continue;
+
+			hist_entry__annotate_browser(he);
+		} else if (choice == zoom_dso) {
+zoom_dso:
+			if (dso_filter) {
+				pstack__remove(fstack, &dso_filter);
+zoom_out_dso:
+				ui_helpline__pop();
+				dso_filter = NULL;
+			} else {
+				if (dso == NULL)
+					continue;
+				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+						   dso->kernel ? "the Kernel" : dso->short_name);
+				dso_filter = dso;
+				pstack__push(fstack, &dso_filter);
+			}
+			hists__filter_by_dso(self, dso_filter);
+			hist_browser__title(msg, sizeof(msg), input_name,
+					    dso_filter, thread_filter);
+			if (hist_browser__populate(browser, self, msg) < 0)
+				goto out;
+		} else if (choice == zoom_thread) {
+zoom_thread:
+			if (thread_filter) {
+				pstack__remove(fstack, &thread_filter);
+zoom_out_thread:
+				ui_helpline__pop();
+				thread_filter = NULL;
+			} else {
+				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+						   thread->comm_set ? thread->comm : "",
+						   thread->pid);
+				thread_filter = thread;
+				pstack__push(fstack, &thread_filter);
+			}
+			hists__filter_by_thread(self, thread_filter);
+			hist_browser__title(msg, sizeof(msg), input_name,
+					    dso_filter, thread_filter);
+			if (hist_browser__populate(browser, self, msg) < 0)
+				goto out;
+		}
+	}
+	err = 0;
+out_free_stack:
+	pstack__delete(fstack);
+out:
+	hist_browser__delete(browser);
+	return err;
+}
+
+static struct newtPercentTreeColors {
+	const char *topColorFg, *topColorBg;
+	const char *mediumColorFg, *mediumColorBg;
+	const char *normalColorFg, *normalColorBg;
+	const char *selColorFg, *selColorBg;
+	const char *codeColorFg, *codeColorBg;
+} defaultPercentTreeColors = {
+	"red",       "lightgray",
+	"green",     "lightgray",
+	"black",     "lightgray",
+	"lightgray", "magenta",
+	"blue",	     "lightgray",
+};
+
+void setup_browser(void)
+{
+	struct newtPercentTreeColors *c = &defaultPercentTreeColors;
+	if (!isatty(1))
+		return;
+
+	use_browser = true;
+	newtInit();
+	newtCls();
+	ui_helpline__puts(" ");
+	sltt_set_color(HE_COLORSET_TOP, NULL, c->topColorFg, c->topColorBg);
+	sltt_set_color(HE_COLORSET_MEDIUM, NULL, c->mediumColorFg, c->mediumColorBg);
+	sltt_set_color(HE_COLORSET_NORMAL, NULL, c->normalColorFg, c->normalColorBg);
+	sltt_set_color(HE_COLORSET_SELECTED, NULL, c->selColorFg, c->selColorBg);
+	sltt_set_color(HE_COLORSET_CODE, NULL, c->codeColorFg, c->codeColorBg);
+}
+
+void exit_browser(bool wait_for_ok)
+{
+	if (use_browser) {
+		if (wait_for_ok) {
+			char title[] = "Fatal Error", ok[] = "Ok";
+			newtWinMessage(title, ok, browser__last_msg);
+		}
+		newtFinished();
+	}
+}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 05d0c5c2030c..9bf0f402ca73 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -5,6 +5,7 @@
 #include "parse-events.h"
 #include "exec_cmd.h"
 #include "string.h"
+#include "symbol.h"
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
@@ -409,7 +410,6 @@ static enum event_result
 parse_single_tracepoint_event(char *sys_name,
 			      const char *evt_name,
 			      unsigned int evt_length,
-			      char *flags,
 			      struct perf_event_attr *attr,
 			      const char **strp)
 {
@@ -418,14 +418,6 @@ parse_single_tracepoint_event(char *sys_name,
 	u64 id;
 	int fd;
 
-	if (flags) {
-		if (!strncmp(flags, "record", strlen(flags))) {
-			attr->sample_type |= PERF_SAMPLE_RAW;
-			attr->sample_type |= PERF_SAMPLE_TIME;
-			attr->sample_type |= PERF_SAMPLE_CPU;
-		}
-	}
-
 	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
 		 sys_name, evt_name);
 
@@ -444,6 +436,13 @@ parse_single_tracepoint_event(char *sys_name,
 	attr->type = PERF_TYPE_TRACEPOINT;
 	*strp = evt_name + evt_length;
 
+	attr->sample_type |= PERF_SAMPLE_RAW;
+	attr->sample_type |= PERF_SAMPLE_TIME;
+	attr->sample_type |= PERF_SAMPLE_CPU;
+
+	attr->sample_period = 1;
+
+
 	return EVT_HANDLED;
 }
 
@@ -532,8 +531,7 @@ static enum event_result parse_tracepoint_event(const char **strp,
 						       flags);
 	} else
 		return parse_single_tracepoint_event(sys_name, evt_name,
-						     evt_length, flags,
-						     attr, strp);
+						     evt_length, attr, strp);
 }
 
 static enum event_result
@@ -690,19 +688,29 @@ static enum event_result
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
 	const char *str = *strp;
-	int eu = 1, ek = 1, eh = 1;
+	int exclude = 0;
+	int eu = 0, ek = 0, eh = 0, precise = 0;
 
 	if (*str++ != ':')
 		return 0;
 	while (*str) {
-		if (*str == 'u')
+		if (*str == 'u') {
+			if (!exclude)
+				exclude = eu = ek = eh = 1;
 			eu = 0;
-		else if (*str == 'k')
+		} else if (*str == 'k') {
+			if (!exclude)
+				exclude = eu = ek = eh = 1;
 			ek = 0;
-		else if (*str == 'h')
+		} else if (*str == 'h') {
+			if (!exclude)
+				exclude = eu = ek = eh = 1;
 			eh = 0;
-		else
+		} else if (*str == 'p') {
+			precise++;
+		} else
 			break;
+
 		++str;
 	}
 	if (str >= *strp + 2) {
@@ -710,6 +718,7 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 		attr->exclude_user   = eu;
 		attr->exclude_kernel = ek;
 		attr->exclude_hv     = eh;
+		attr->precise_ip     = precise;
 		return 1;
 	}
 	return 0;
@@ -934,7 +943,8 @@ void print_events(void)
 
 	printf("\n");
 	printf("  %-42s [%s]\n",
-		"rNNN", event_type_descriptors[PERF_TYPE_RAW]);
+		"rNNN (see 'perf list --help' on how to encode it)",
+	       event_type_descriptors[PERF_TYPE_RAW]);
 	printf("\n");
 
 	printf("  %-42s [%s]\n",
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b8c1f64bc935..fc4ab3fe877a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -13,6 +13,7 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
+extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events);
 
 extern int			nr_counters;
 
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index efebd5b476b3..99d02aa57dbf 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -49,8 +49,9 @@ static int get_value(struct parse_opt_ctx_t *p,
 				break;
 			/* FALLTHROUGH */
 		case OPTION_BOOLEAN:
+		case OPTION_INCR:
 		case OPTION_BIT:
-		case OPTION_SET_INT:
+		case OPTION_SET_UINT:
 		case OPTION_SET_PTR:
 			return opterror(opt, "takes no value", flags);
 		case OPTION_END:
@@ -58,7 +59,9 @@ static int get_value(struct parse_opt_ctx_t *p,
 		case OPTION_GROUP:
 		case OPTION_STRING:
 		case OPTION_INTEGER:
+		case OPTION_UINTEGER:
 		case OPTION_LONG:
+		case OPTION_U64:
 		default:
 			break;
 		}
@@ -73,11 +76,15 @@ static int get_value(struct parse_opt_ctx_t *p,
 		return 0;
 
 	case OPTION_BOOLEAN:
+		*(bool *)opt->value = unset ? false : true;
+		return 0;
+
+	case OPTION_INCR:
 		*(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
 		return 0;
 
-	case OPTION_SET_INT:
-		*(int *)opt->value = unset ? 0 : opt->defval;
+	case OPTION_SET_UINT:
+		*(unsigned int *)opt->value = unset ? 0 : opt->defval;
 		return 0;
 
 	case OPTION_SET_PTR:
@@ -120,6 +127,22 @@ static int get_value(struct parse_opt_ctx_t *p,
 			return opterror(opt, "expects a numerical value", flags);
 		return 0;
 
+	case OPTION_UINTEGER:
+		if (unset) {
+			*(unsigned int *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(unsigned int *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
 	case OPTION_LONG:
 		if (unset) {
 			*(long *)opt->value = 0;
@@ -136,6 +159,22 @@ static int get_value(struct parse_opt_ctx_t *p,
 			return opterror(opt, "expects a numerical value", flags);
 		return 0;
 
+	case OPTION_U64:
+		if (unset) {
+			*(u64 *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(u64 *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
 	case OPTION_END:
 	case OPTION_ARGUMENT:
 	case OPTION_GROUP:
@@ -441,7 +480,10 @@ int usage_with_options_internal(const char * const *usagestr,
 		switch (opts->type) {
 		case OPTION_ARGUMENT:
 			break;
+		case OPTION_LONG:
+		case OPTION_U64:
 		case OPTION_INTEGER:
+		case OPTION_UINTEGER:
 			if (opts->flags & PARSE_OPT_OPTARG)
 				if (opts->long_name)
 					pos += fprintf(stderr, "[=<n>]");
@@ -473,14 +515,14 @@ int usage_with_options_internal(const char * const *usagestr,
 					pos += fprintf(stderr, " ...");
 			}
 			break;
-		default: /* OPTION_{BIT,BOOLEAN,SET_INT,SET_PTR} */
+		default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
 		case OPTION_END:
 		case OPTION_GROUP:
 		case OPTION_BIT:
 		case OPTION_BOOLEAN:
-		case OPTION_SET_INT:
+		case OPTION_INCR:
+		case OPTION_SET_UINT:
 		case OPTION_SET_PTR:
-		case OPTION_LONG:
 			break;
 		}
 
@@ -500,6 +542,7 @@ int usage_with_options_internal(const char * const *usagestr,
 void usage_with_options(const char * const *usagestr,
 			const struct option *opts)
 {
+	exit_browser(false);
 	usage_with_options_internal(usagestr, opts, 0);
 	exit(129);
 }
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 948805af43c2..c7d72dce54b2 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -1,6 +1,9 @@
 #ifndef __PERF_PARSE_OPTIONS_H
 #define __PERF_PARSE_OPTIONS_H
 
+#include <linux/kernel.h>
+#include <stdbool.h>
+
 enum parse_opt_type {
 	/* special types */
 	OPTION_END,
@@ -8,14 +11,17 @@ enum parse_opt_type {
 	OPTION_GROUP,
 	/* options with no arguments */
 	OPTION_BIT,
-	OPTION_BOOLEAN, /* _INCR would have been a better name */
-	OPTION_SET_INT,
+	OPTION_BOOLEAN,
+	OPTION_INCR,
+	OPTION_SET_UINT,
 	OPTION_SET_PTR,
 	/* options with arguments (usually) */
 	OPTION_STRING,
 	OPTION_INTEGER,
 	OPTION_LONG,
 	OPTION_CALLBACK,
+	OPTION_U64,
+	OPTION_UINTEGER,
 };
 
 enum parse_opt_flags {
@@ -73,7 +79,7 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
  *
  * `defval`::
  *   default value to fill (*->value) with for PARSE_OPT_OPTARG.
- *   OPTION_{BIT,SET_INT,SET_PTR} store the {mask,integer,pointer} to put in
+ *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
  */
@@ -90,16 +96,21 @@ struct option {
 	intptr_t defval;
 };
 
+#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
+
 #define OPT_END()                   { .type = OPTION_END }
 #define OPT_ARGUMENT(l, h)          { .type = OPTION_ARGUMENT, .long_name = (l), .help = (h) }
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
-#define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (b) }
-#define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = (v), .help = (h) }
-#define OPT_SET_INT(s, l, v, h, i)  { .type = OPTION_SET_INT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (i) }
+#define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
+#define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
+#define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
-#define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = (v), .help = (h) }
-#define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = (v), .help = (h) }
-#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h) }
+#define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
+#define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
+#define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
+#define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
+#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
 #define OPT_CALLBACK(s, l, v, a, h, f) \
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 7c004b6ef24f..914c67095d96 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -33,20 +33,27 @@
 #include <limits.h>
 
 #undef _GNU_SOURCE
+#include "util.h"
 #include "event.h"
 #include "string.h"
 #include "strlist.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
-#include "parse-events.h"  /* For debugfs_path */
+#include "symbol.h"
+#include "thread.h"
+#include "debugfs.h"
+#include "trace-event.h"	/* For __unused */
 #include "probe-event.h"
+#include "probe-finder.h"
 
 #define MAX_CMDLEN 256
 #define MAX_PROBE_ARGS 128
 #define PERFPROBE_GROUP "probe"
 
-#define semantic_error(msg ...) die("Semantic error :" msg)
+bool probe_event_dry_run;	/* Dry run flag */
+
+#define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
 /* If there is no space to write, returns -E2BIG. */
 static int e_snprintf(char *str, size_t size, const char *format, ...)
@@ -64,7 +71,275 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 	return ret;
 }
 
-void parse_line_range_desc(const char *arg, struct line_range *lr)
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+static struct machine machine;
+
+/* Initialize symbol maps and path of vmlinux */
+static int init_vmlinux(void)
+{
+	struct dso *kernel;
+	int ret;
+
+	symbol_conf.sort_by_name = true;
+	if (symbol_conf.vmlinux_name == NULL)
+		symbol_conf.try_vmlinux_path = true;
+	else
+		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
+	ret = symbol__init();
+	if (ret < 0) {
+		pr_debug("Failed to init symbol map.\n");
+		goto out;
+	}
+
+	ret = machine__init(&machine, "/", 0);
+	if (ret < 0)
+		goto out;
+
+	kernel = dso__new_kernel(symbol_conf.vmlinux_name);
+	if (kernel == NULL)
+		die("Failed to create kernel dso.");
+
+	ret = __machine__create_kernel_maps(&machine, kernel);
+	if (ret < 0)
+		pr_debug("Failed to create kernel maps.\n");
+
+out:
+	if (ret < 0)
+		pr_warning("Failed to init vmlinux path.\n");
+	return ret;
+}
+
+#ifdef DWARF_SUPPORT
+static int open_vmlinux(void)
+{
+	if (map__load(machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
+		pr_debug("Failed to load kernel map.\n");
+		return -EINVAL;
+	}
+	pr_debug("Try to open %s\n", machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name);
+	return open(machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
+}
+
+/* Convert trace point to probe point with debuginfo */
+static int convert_to_perf_probe_point(struct kprobe_trace_point *tp,
+				       struct perf_probe_point *pp)
+{
+	struct symbol *sym;
+	int fd, ret = -ENOENT;
+
+	sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
+				       tp->symbol, NULL);
+	if (sym) {
+		fd = open_vmlinux();
+		if (fd >= 0) {
+			ret = find_perf_probe_point(fd,
+						 sym->start + tp->offset, pp);
+			close(fd);
+		}
+	}
+	if (ret <= 0) {
+		pr_debug("Failed to find corresponding probes from "
+			 "debuginfo. Use kprobe event information.\n");
+		pp->function = strdup(tp->symbol);
+		if (pp->function == NULL)
+			return -ENOMEM;
+		pp->offset = tp->offset;
+	}
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
+/* Try to find perf_probe_event with debuginfo */
+static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
+					   struct kprobe_trace_event **tevs,
+					   int max_tevs)
+{
+	bool need_dwarf = perf_probe_event_need_dwarf(pev);
+	int fd, ntevs;
+
+	fd = open_vmlinux();
+	if (fd < 0) {
+		if (need_dwarf) {
+			pr_warning("Failed to open debuginfo file.\n");
+			return fd;
+		}
+		pr_debug("Could not open vmlinux. Try to use symbols.\n");
+		return 0;
+	}
+
+	/* Searching trace events corresponding to probe event */
+	ntevs = find_kprobe_trace_events(fd, pev, tevs, max_tevs);
+	close(fd);
+
+	if (ntevs > 0) {	/* Succeeded to find trace events */
+		pr_debug("find %d kprobe_trace_events.\n", ntevs);
+		return ntevs;
+	}
+
+	if (ntevs == 0)	{	/* No error but failed to find probe point. */
+		pr_warning("Probe point '%s' not found.\n",
+			   synthesize_perf_probe_point(&pev->point));
+		return -ENOENT;
+	}
+	/* Error path : ntevs < 0 */
+	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
+	if (ntevs == -EBADF) {
+		pr_warning("Warning: No dwarf info found in the vmlinux - "
+			"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
+		if (!need_dwarf) {
+			pr_debug("Trying to use symbols.\nn");
+			return 0;
+		}
+	}
+	return ntevs;
+}
+
+#define LINEBUF_SIZE 256
+#define NR_ADDITIONAL_LINES 2
+
+static int show_one_line(FILE *fp, int l, bool skip, bool show_num)
+{
+	char buf[LINEBUF_SIZE];
+	const char *color = PERF_COLOR_BLUE;
+
+	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
+		goto error;
+	if (!skip) {
+		if (show_num)
+			fprintf(stdout, "%7d  %s", l, buf);
+		else
+			color_fprintf(stdout, color, "         %s", buf);
+	}
+
+	while (strlen(buf) == LINEBUF_SIZE - 1 &&
+	       buf[LINEBUF_SIZE - 2] != '\n') {
+		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
+			goto error;
+		if (!skip) {
+			if (show_num)
+				fprintf(stdout, "%s", buf);
+			else
+				color_fprintf(stdout, color, "%s", buf);
+		}
+	}
+
+	return 0;
+error:
+	if (feof(fp))
+		pr_warning("Source file is shorter than expected.\n");
+	else
+		pr_warning("File read error: %s\n", strerror(errno));
+
+	return -1;
+}
+
+/*
+ * Show line-range always requires debuginfo to find source file and
+ * line number.
+ */
+int show_line_range(struct line_range *lr)
+{
+	int l = 1;
+	struct line_node *ln;
+	FILE *fp;
+	int fd, ret;
+
+	/* Search a line range */
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
+
+	fd = open_vmlinux();
+	if (fd < 0) {
+		pr_warning("Failed to open debuginfo file.\n");
+		return fd;
+	}
+
+	ret = find_line_range(fd, lr);
+	close(fd);
+	if (ret == 0) {
+		pr_warning("Specified source line is not found.\n");
+		return -ENOENT;
+	} else if (ret < 0) {
+		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		return ret;
+	}
+
+	setup_pager();
+
+	if (lr->function)
+		fprintf(stdout, "<%s:%d>\n", lr->function,
+			lr->start - lr->offset);
+	else
+		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+
+	fp = fopen(lr->path, "r");
+	if (fp == NULL) {
+		pr_warning("Failed to open %s: %s\n", lr->path,
+			   strerror(errno));
+		return -errno;
+	}
+	/* Skip to starting line number */
+	while (l < lr->start && ret >= 0)
+		ret = show_one_line(fp, l++, true, false);
+	if (ret < 0)
+		goto end;
+
+	list_for_each_entry(ln, &lr->line_list, list) {
+		while (ln->line > l && ret >= 0)
+			ret = show_one_line(fp, (l++) - lr->offset,
+					    false, false);
+		if (ret >= 0)
+			ret = show_one_line(fp, (l++) - lr->offset,
+					    false, true);
+		if (ret < 0)
+			goto end;
+	}
+
+	if (lr->end == INT_MAX)
+		lr->end = l + NR_ADDITIONAL_LINES;
+	while (l <= lr->end && !feof(fp) && ret >= 0)
+		ret = show_one_line(fp, (l++) - lr->offset, false, false);
+end:
+	fclose(fp);
+	return ret;
+}
+
+#else	/* !DWARF_SUPPORT */
+
+static int convert_to_perf_probe_point(struct kprobe_trace_point *tp,
+					struct perf_probe_point *pp)
+{
+	pp->function = strdup(tp->symbol);
+	if (pp->function == NULL)
+		return -ENOMEM;
+	pp->offset = tp->offset;
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
+static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev,
+				struct kprobe_trace_event **tevs __unused,
+				int max_tevs __unused)
+{
+	if (perf_probe_event_need_dwarf(pev)) {
+		pr_warning("Debuginfo-analysis is not supported.\n");
+		return -ENOSYS;
+	}
+	return 0;
+}
+
+int show_line_range(struct line_range *lr __unused)
+{
+	pr_warning("Debuginfo-analysis is not supported.\n");
+	return -ENOSYS;
+}
+
+#endif
+
+int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
 	const char *ptr;
 	char *tmp;
@@ -75,29 +350,45 @@ void parse_line_range_desc(const char *arg, struct line_range *lr)
 	 */
 	ptr = strchr(arg, ':');
 	if (ptr) {
-		lr->start = (unsigned int)strtoul(ptr + 1, &tmp, 0);
-		if (*tmp == '+')
-			lr->end = lr->start + (unsigned int)strtoul(tmp + 1,
-								    &tmp, 0);
-		else if (*tmp == '-')
-			lr->end = (unsigned int)strtoul(tmp + 1, &tmp, 0);
+		lr->start = (int)strtoul(ptr + 1, &tmp, 0);
+		if (*tmp == '+') {
+			lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0);
+			lr->end--;	/*
+					 * Adjust the number of lines here.
+					 * If the number of lines == 1, the
+					 * the end of line should be equal to
+					 * the start of line.
+					 */
+		} else if (*tmp == '-')
+			lr->end = (int)strtoul(tmp + 1, &tmp, 0);
 		else
-			lr->end = 0;
-		pr_debug("Line range is %u to %u\n", lr->start, lr->end);
-		if (lr->end && lr->start > lr->end)
+			lr->end = INT_MAX;
+		pr_debug("Line range is %d to %d\n", lr->start, lr->end);
+		if (lr->start > lr->end) {
 			semantic_error("Start line must be smaller"
-				       " than end line.");
-		if (*tmp != '\0')
-			semantic_error("Tailing with invalid character '%d'.",
+				       " than end line.\n");
+			return -EINVAL;
+		}
+		if (*tmp != '\0') {
+			semantic_error("Tailing with invalid character '%d'.\n",
 				       *tmp);
+			return -EINVAL;
+		}
 		tmp = strndup(arg, (ptr - arg));
-	} else
+	} else {
 		tmp = strdup(arg);
+		lr->end = INT_MAX;
+	}
+
+	if (tmp == NULL)
+		return -ENOMEM;
 
 	if (strchr(tmp, '.'))
 		lr->file = tmp;
 	else
 		lr->function = tmp;
+
+	return 0;
 }
 
 /* Check the name is good for event/group */
@@ -113,8 +404,9 @@ static bool check_event_name(const char *name)
 }
 
 /* Parse probepoint definition. */
-static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
+static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
+	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
 	/*
@@ -129,13 +421,19 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 	if (ptr && *ptr == '=') {	/* Event name */
 		*ptr = '\0';
 		tmp = ptr + 1;
-		ptr = strchr(arg, ':');
-		if (ptr)	/* Group name is not supported yet. */
-			semantic_error("Group name is not supported yet.");
-		if (!check_event_name(arg))
+		if (strchr(arg, ':')) {
+			semantic_error("Group name is not supported yet.\n");
+			return -ENOTSUP;
+		}
+		if (!check_event_name(arg)) {
 			semantic_error("%s is bad for event name -it must "
-				       "follow C symbol-naming rule.", arg);
-		pp->event = strdup(arg);
+				       "follow C symbol-naming rule.\n", arg);
+			return -EINVAL;
+		}
+		pev->event = strdup(arg);
+		if (pev->event == NULL)
+			return -ENOMEM;
+		pev->group = NULL;
 		arg = tmp;
 	}
 
@@ -145,12 +443,15 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		*ptr++ = '\0';
 	}
 
+	tmp = strdup(arg);
+	if (tmp == NULL)
+		return -ENOMEM;
+
 	/* Check arg is function or file and copy it */
-	if (strchr(arg, '.'))	/* File */
-		pp->file = strdup(arg);
+	if (strchr(tmp, '.'))	/* File */
+		pp->file = tmp;
 	else			/* Function */
-		pp->function = strdup(arg);
-	DIE_IF(pp->file == NULL && pp->function == NULL);
+		pp->function = tmp;
 
 	/* Parse other options */
 	while (ptr) {
@@ -158,6 +459,8 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		c = nc;
 		if (c == ';') {	/* Lazy pattern must be the last part */
 			pp->lazy_line = strdup(arg);
+			if (pp->lazy_line == NULL)
+				return -ENOMEM;
 			break;
 		}
 		ptr = strpbrk(arg, ";:+@%");
@@ -168,266 +471,658 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
 		switch (c) {
 		case ':':	/* Line number */
 			pp->line = strtoul(arg, &tmp, 0);
-			if (*tmp != '\0')
+			if (*tmp != '\0') {
 				semantic_error("There is non-digit char"
-					       " in line number.");
+					       " in line number.\n");
+				return -EINVAL;
+			}
 			break;
 		case '+':	/* Byte offset from a symbol */
 			pp->offset = strtoul(arg, &tmp, 0);
-			if (*tmp != '\0')
+			if (*tmp != '\0') {
 				semantic_error("There is non-digit character"
-						" in offset.");
+						" in offset.\n");
+				return -EINVAL;
+			}
 			break;
 		case '@':	/* File name */
-			if (pp->file)
-				semantic_error("SRC@SRC is not allowed.");
+			if (pp->file) {
+				semantic_error("SRC@SRC is not allowed.\n");
+				return -EINVAL;
+			}
 			pp->file = strdup(arg);
-			DIE_IF(pp->file == NULL);
+			if (pp->file == NULL)
+				return -ENOMEM;
 			break;
 		case '%':	/* Probe places */
 			if (strcmp(arg, "return") == 0) {
 				pp->retprobe = 1;
-			} else	/* Others not supported yet */
-				semantic_error("%%%s is not supported.", arg);
+			} else {	/* Others not supported yet */
+				semantic_error("%%%s is not supported.\n", arg);
+				return -ENOTSUP;
+			}
 			break;
-		default:
-			DIE_IF("Program has a bug.");
+		default:	/* Buggy case */
+			pr_err("This program has a bug at %s:%d.\n",
+				__FILE__, __LINE__);
+			return -ENOTSUP;
 			break;
 		}
 	}
 
 	/* Exclusion check */
-	if (pp->lazy_line && pp->line)
+	if (pp->lazy_line && pp->line) {
 		semantic_error("Lazy pattern can't be used with line number.");
+		return -EINVAL;
+	}
 
-	if (pp->lazy_line && pp->offset)
+	if (pp->lazy_line && pp->offset) {
 		semantic_error("Lazy pattern can't be used with offset.");
+		return -EINVAL;
+	}
 
-	if (pp->line && pp->offset)
+	if (pp->line && pp->offset) {
 		semantic_error("Offset can't be used with line number.");
+		return -EINVAL;
+	}
 
-	if (!pp->line && !pp->lazy_line && pp->file && !pp->function)
+	if (!pp->line && !pp->lazy_line && pp->file && !pp->function) {
 		semantic_error("File always requires line number or "
 			       "lazy pattern.");
+		return -EINVAL;
+	}
 
-	if (pp->offset && !pp->function)
+	if (pp->offset && !pp->function) {
 		semantic_error("Offset requires an entry function.");
+		return -EINVAL;
+	}
 
-	if (pp->retprobe && !pp->function)
+	if (pp->retprobe && !pp->function) {
 		semantic_error("Return probe requires an entry function.");
+		return -EINVAL;
+	}
 
-	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe)
+	if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
 		semantic_error("Offset/Line/Lazy pattern can't be used with "
 			       "return probe.");
+		return -EINVAL;
+	}
 
-	pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n",
+	pr_debug("symbol:%s file:%s line:%d offset:%lu return:%d lazy:%s\n",
 		 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,
 		 pp->lazy_line);
+	return 0;
 }
 
-/* Parse perf-probe event definition */
-void parse_perf_probe_event(const char *str, struct probe_point *pp,
-			    bool *need_dwarf)
+/* Parse perf-probe event argument */
+static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 {
-	char **argv;
-	int argc, i;
+	char *tmp;
+	struct perf_probe_arg_field **fieldp;
+
+	pr_debug("parsing arg: %s into ", str);
 
-	*need_dwarf = false;
+	tmp = strchr(str, '=');
+	if (tmp) {
+		arg->name = strndup(str, tmp - str);
+		if (arg->name == NULL)
+			return -ENOMEM;
+		pr_debug("name:%s ", arg->name);
+		str = tmp + 1;
+	}
 
-	argv = argv_split(str, &argc);
-	if (!argv)
-		die("argv_split failed.");
-	if (argc > MAX_PROBE_ARGS + 1)
-		semantic_error("Too many arguments");
+	tmp = strchr(str, ':');
+	if (tmp) {	/* Type setting */
+		*tmp = '\0';
+		arg->type = strdup(tmp + 1);
+		if (arg->type == NULL)
+			return -ENOMEM;
+		pr_debug("type:%s ", arg->type);
+	}
 
+	tmp = strpbrk(str, "-.");
+	if (!is_c_varname(str) || !tmp) {
+		/* A variable, register, symbol or special value */
+		arg->var = strdup(str);
+		if (arg->var == NULL)
+			return -ENOMEM;
+		pr_debug("%s\n", arg->var);
+		return 0;
+	}
+
+	/* Structure fields */
+	arg->var = strndup(str, tmp - str);
+	if (arg->var == NULL)
+		return -ENOMEM;
+	pr_debug("%s, ", arg->var);
+	fieldp = &arg->field;
+
+	do {
+		*fieldp = zalloc(sizeof(struct perf_probe_arg_field));
+		if (*fieldp == NULL)
+			return -ENOMEM;
+		if (*tmp == '.') {
+			str = tmp + 1;
+			(*fieldp)->ref = false;
+		} else if (tmp[1] == '>') {
+			str = tmp + 2;
+			(*fieldp)->ref = true;
+		} else {
+			semantic_error("Argument parse error: %s\n", str);
+			return -EINVAL;
+		}
+
+		tmp = strpbrk(str, "-.");
+		if (tmp) {
+			(*fieldp)->name = strndup(str, tmp - str);
+			if ((*fieldp)->name == NULL)
+				return -ENOMEM;
+			pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref);
+			fieldp = &(*fieldp)->next;
+		}
+	} while (tmp);
+	(*fieldp)->name = strdup(str);
+	if ((*fieldp)->name == NULL)
+		return -ENOMEM;
+	pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref);
+
+	/* If no name is specified, set the last field name */
+	if (!arg->name) {
+		arg->name = strdup((*fieldp)->name);
+		if (arg->name == NULL)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+/* Parse perf-probe event command */
+int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev)
+{
+	char **argv;
+	int argc, i, ret = 0;
+
+	argv = argv_split(cmd, &argc);
+	if (!argv) {
+		pr_debug("Failed to split arguments.\n");
+		return -ENOMEM;
+	}
+	if (argc - 1 > MAX_PROBE_ARGS) {
+		semantic_error("Too many probe arguments (%d).\n", argc - 1);
+		ret = -ERANGE;
+		goto out;
+	}
 	/* Parse probe point */
-	parse_perf_probe_probepoint(argv[0], pp);
-	if (pp->file || pp->line || pp->lazy_line)
-		*need_dwarf = true;
+	ret = parse_perf_probe_point(argv[0], pev);
+	if (ret < 0)
+		goto out;
 
 	/* Copy arguments and ensure return probe has no C argument */
-	pp->nr_args = argc - 1;
-	pp->args = zalloc(sizeof(char *) * pp->nr_args);
-	for (i = 0; i < pp->nr_args; i++) {
-		pp->args[i] = strdup(argv[i + 1]);
-		if (!pp->args[i])
-			die("Failed to copy argument.");
-		if (is_c_varname(pp->args[i])) {
-			if (pp->retprobe)
-				semantic_error("You can't specify local"
-						" variable for kretprobe");
-			*need_dwarf = true;
+	pev->nargs = argc - 1;
+	pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs);
+	if (pev->args == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < pev->nargs && ret >= 0; i++) {
+		ret = parse_perf_probe_arg(argv[i + 1], &pev->args[i]);
+		if (ret >= 0 &&
+		    is_c_varname(pev->args[i].var) && pev->point.retprobe) {
+			semantic_error("You can't specify local variable for"
+				       " kretprobe.\n");
+			ret = -EINVAL;
 		}
 	}
-
+out:
 	argv_free(argv);
+
+	return ret;
+}
+
+/* Return true if this perf_probe_event requires debuginfo */
+bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
+{
+	int i;
+
+	if (pev->point.file || pev->point.line || pev->point.lazy_line)
+		return true;
+
+	for (i = 0; i < pev->nargs; i++)
+		if (is_c_varname(pev->args[i].var))
+			return true;
+
+	return false;
 }
 
 /* Parse kprobe_events event into struct probe_point */
-void parse_trace_kprobe_event(const char *str, struct probe_point *pp)
+int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev)
 {
+	struct kprobe_trace_point *tp = &tev->point;
 	char pr;
 	char *p;
 	int ret, i, argc;
 	char **argv;
 
-	pr_debug("Parsing kprobe_events: %s\n", str);
-	argv = argv_split(str, &argc);
-	if (!argv)
-		die("argv_split failed.");
-	if (argc < 2)
-		semantic_error("Too less arguments.");
+	pr_debug("Parsing kprobe_events: %s\n", cmd);
+	argv = argv_split(cmd, &argc);
+	if (!argv) {
+		pr_debug("Failed to split arguments.\n");
+		return -ENOMEM;
+	}
+	if (argc < 2) {
+		semantic_error("Too few probe arguments.\n");
+		ret = -ERANGE;
+		goto out;
+	}
 
 	/* Scan event and group name. */
 	ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]",
-		     &pr, (float *)(void *)&pp->group,
-		     (float *)(void *)&pp->event);
-	if (ret != 3)
-		semantic_error("Failed to parse event name: %s", argv[0]);
-	pr_debug("Group:%s Event:%s probe:%c\n", pp->group, pp->event, pr);
+		     &pr, (float *)(void *)&tev->group,
+		     (float *)(void *)&tev->event);
+	if (ret != 3) {
+		semantic_error("Failed to parse event name: %s\n", argv[0]);
+		ret = -EINVAL;
+		goto out;
+	}
+	pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr);
 
-	pp->retprobe = (pr == 'r');
+	tp->retprobe = (pr == 'r');
 
 	/* Scan function name and offset */
-	ret = sscanf(argv[1], "%a[^+]+%d", (float *)(void *)&pp->function,
-		     &pp->offset);
+	ret = sscanf(argv[1], "%a[^+]+%lu", (float *)(void *)&tp->symbol,
+		     &tp->offset);
 	if (ret == 1)
-		pp->offset = 0;
-
-	/* kprobe_events doesn't have this information */
-	pp->line = 0;
-	pp->file = NULL;
+		tp->offset = 0;
 
-	pp->nr_args = argc - 2;
-	pp->args = zalloc(sizeof(char *) * pp->nr_args);
-	for (i = 0; i < pp->nr_args; i++) {
+	tev->nargs = argc - 2;
+	tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	if (tev->args == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < tev->nargs; i++) {
 		p = strchr(argv[i + 2], '=');
 		if (p)	/* We don't need which register is assigned. */
-			*p = '\0';
-		pp->args[i] = strdup(argv[i + 2]);
-		if (!pp->args[i])
-			die("Failed to copy argument.");
+			*p++ = '\0';
+		else
+			p = argv[i + 2];
+		tev->args[i].name = strdup(argv[i + 2]);
+		/* TODO: parse regs and offset */
+		tev->args[i].value = strdup(p);
+		if (tev->args[i].name == NULL || tev->args[i].value == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
-
+	ret = 0;
+out:
 	argv_free(argv);
+	return ret;
 }
 
-/* Synthesize only probe point (not argument) */
-int synthesize_perf_probe_point(struct probe_point *pp)
+/* Compose only probe arg */
+int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 {
-	char *buf;
-	char offs[64] = "", line[64] = "";
+	struct perf_probe_arg_field *field = pa->field;
 	int ret;
+	char *tmp = buf;
 
-	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
-	pp->found = 1;
-	if (!buf)
-		die("Failed to allocate memory by zalloc.");
+	if (pa->name && pa->var)
+		ret = e_snprintf(tmp, len, "%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;
+
+	while (field) {
+		ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".",
+				 field->name);
+		if (ret <= 0)
+			goto error;
+		tmp += ret;
+		len -= ret;
+		field = field->next;
+	}
+
+	if (pa->type) {
+		ret = e_snprintf(tmp, len, ":%s", pa->type);
+		if (ret <= 0)
+			goto error;
+		tmp += ret;
+		len -= ret;
+	}
+
+	return tmp - buf;
+error:
+	pr_debug("Failed to synthesize perf probe argument: %s",
+		 strerror(-ret));
+	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;
+
+	buf = zalloc(MAX_CMDLEN);
+	if (buf == NULL) {
+		ret = -ENOMEM;
+		goto error;
+	}
 	if (pp->offset) {
-		ret = e_snprintf(offs, 64, "+%d", pp->offset);
+		ret = e_snprintf(offs, 32, "+%lu", pp->offset);
 		if (ret <= 0)
 			goto error;
 	}
 	if (pp->line) {
-		ret = e_snprintf(line, 64, ":%d", pp->line);
+		ret = e_snprintf(line, 32, ":%d", pp->line);
+		if (ret <= 0)
+			goto error;
+	}
+	if (pp->file) {
+		len = strlen(pp->file) - 31;
+		if (len < 0)
+			len = 0;
+		tmp = strchr(pp->file + len, '/');
+		if (!tmp)
+			tmp = pp->file + len;
+		ret = e_snprintf(file, 32, "@%s", tmp + 1);
 		if (ret <= 0)
 			goto error;
 	}
 
 	if (pp->function)
-		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s", pp->function,
-				 offs, pp->retprobe ? "%return" : "", line);
+		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", pp->file, line);
-	if (ret <= 0) {
+		ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line);
+	if (ret <= 0)
+		goto error;
+
+	return buf;
 error:
-		free(pp->probes[0]);
-		pp->probes[0] = NULL;
-		pp->found = 0;
-	}
-	return ret;
+	pr_debug("Failed to synthesize perf probe point: %s",
+		 strerror(-ret));
+	if (buf)
+		free(buf);
+	return NULL;
 }
 
-int synthesize_perf_probe_event(struct probe_point *pp)
+#if 0
+char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 {
 	char *buf;
 	int i, len, ret;
 
-	len = synthesize_perf_probe_point(pp);
-	if (len < 0)
-		return 0;
+	buf = synthesize_perf_probe_point(&pev->point);
+	if (!buf)
+		return NULL;
 
-	buf = pp->probes[0];
-	for (i = 0; i < pp->nr_args; i++) {
+	len = strlen(buf);
+	for (i = 0; i < pev->nargs; i++) {
 		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pp->args[i]);
-		if (ret <= 0)
-			goto error;
+				 pev->args[i].name);
+		if (ret <= 0) {
+			free(buf);
+			return NULL;
+		}
 		len += ret;
 	}
-	pp->found = 1;
 
-	return pp->found;
-error:
-	free(pp->probes[0]);
-	pp->probes[0] = NULL;
+	return buf;
+}
+#endif
+
+static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref,
+					     char **buf, size_t *buflen,
+					     int depth)
+{
+	int ret;
+	if (ref->next) {
+		depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf,
+							 buflen, 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;
+	}
+out:
+	return depth;
 
-	return ret;
 }
 
-int synthesize_trace_kprobe_event(struct probe_point *pp)
+static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg,
+				       char *buf, size_t buflen)
 {
+	int ret, depth = 0;
+	char *tmp = buf;
+
+	/* Argument name or separator */
+	if (arg->name)
+		ret = e_snprintf(buf, buflen, " %s=", arg->name);
+	else
+		ret = e_snprintf(buf, buflen, " ");
+	if (ret < 0)
+		return ret;
+	buf += ret;
+	buflen -= ret;
+
+	/* Dereferencing arguments */
+	if (arg->ref) {
+		depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf,
+							  &buflen, 1);
+		if (depth < 0)
+			return depth;
+	}
+
+	/* Print argument value */
+	ret = e_snprintf(buf, buflen, "%s", arg->value);
+	if (ret < 0)
+		return ret;
+	buf += ret;
+	buflen -= ret;
+
+	/* Closing */
+	while (depth--) {
+		ret = e_snprintf(buf, buflen, ")");
+		if (ret < 0)
+			return ret;
+		buf += ret;
+		buflen -= ret;
+	}
+	/* Print argument type */
+	if (arg->type) {
+		ret = e_snprintf(buf, buflen, ":%s", arg->type);
+		if (ret <= 0)
+			return ret;
+		buf += ret;
+	}
+
+	return buf - tmp;
+}
+
+char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev)
+{
+	struct kprobe_trace_point *tp = &tev->point;
 	char *buf;
 	int i, len, ret;
 
-	pp->probes[0] = buf = zalloc(MAX_CMDLEN);
-	if (!buf)
-		die("Failed to allocate memory by zalloc.");
-	ret = e_snprintf(buf, MAX_CMDLEN, "%s+%d", pp->function, pp->offset);
-	if (ret <= 0)
+	buf = zalloc(MAX_CMDLEN);
+	if (buf == NULL)
+		return NULL;
+
+	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s+%lu",
+			 tp->retprobe ? 'r' : 'p',
+			 tev->group, tev->event,
+			 tp->symbol, tp->offset);
+	if (len <= 0)
 		goto error;
-	len = ret;
 
-	for (i = 0; i < pp->nr_args; i++) {
-		ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-				 pp->args[i]);
+	for (i = 0; i < tev->nargs; i++) {
+		ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len,
+						  MAX_CMDLEN - len);
 		if (ret <= 0)
 			goto error;
 		len += ret;
 	}
-	pp->found = 1;
 
-	return pp->found;
+	return buf;
 error:
-	free(pp->probes[0]);
-	pp->probes[0] = NULL;
+	free(buf);
+	return NULL;
+}
+
+int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
+				struct perf_probe_event *pev)
+{
+	char buf[64] = "";
+	int i, ret;
+
+	/* Convert event/group name */
+	pev->event = strdup(tev->event);
+	pev->group = strdup(tev->group);
+	if (pev->event == NULL || pev->group == NULL)
+		return -ENOMEM;
+
+	/* Convert trace_point to probe_point */
+	ret = convert_to_perf_probe_point(&tev->point, &pev->point);
+	if (ret < 0)
+		return ret;
+
+	/* Convert trace_arg to probe_arg */
+	pev->nargs = tev->nargs;
+	pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs);
+	if (pev->args == NULL)
+		return -ENOMEM;
+	for (i = 0; i < tev->nargs && ret >= 0; i++) {
+		if (tev->args[i].name)
+			pev->args[i].name = strdup(tev->args[i].name);
+		else {
+			ret = synthesize_kprobe_trace_arg(&tev->args[i],
+							  buf, 64);
+			pev->args[i].name = strdup(buf);
+		}
+		if (pev->args[i].name == NULL && ret >= 0)
+			ret = -ENOMEM;
+	}
+
+	if (ret < 0)
+		clear_perf_probe_event(pev);
 
 	return ret;
 }
 
-static int open_kprobe_events(int flags, int mode)
+void clear_perf_probe_event(struct perf_probe_event *pev)
+{
+	struct perf_probe_point *pp = &pev->point;
+	struct perf_probe_arg_field *field, *next;
+	int i;
+
+	if (pev->event)
+		free(pev->event);
+	if (pev->group)
+		free(pev->group);
+	if (pp->file)
+		free(pp->file);
+	if (pp->function)
+		free(pp->function);
+	if (pp->lazy_line)
+		free(pp->lazy_line);
+	for (i = 0; i < pev->nargs; i++) {
+		if (pev->args[i].name)
+			free(pev->args[i].name);
+		if (pev->args[i].var)
+			free(pev->args[i].var);
+		if (pev->args[i].type)
+			free(pev->args[i].type);
+		field = pev->args[i].field;
+		while (field) {
+			next = field->next;
+			if (field->name)
+				free(field->name);
+			free(field);
+			field = next;
+		}
+	}
+	if (pev->args)
+		free(pev->args);
+	memset(pev, 0, sizeof(*pev));
+}
+
+void clear_kprobe_trace_event(struct kprobe_trace_event *tev)
+{
+	struct kprobe_trace_arg_ref *ref, *next;
+	int i;
+
+	if (tev->event)
+		free(tev->event);
+	if (tev->group)
+		free(tev->group);
+	if (tev->point.symbol)
+		free(tev->point.symbol);
+	for (i = 0; i < tev->nargs; i++) {
+		if (tev->args[i].name)
+			free(tev->args[i].name);
+		if (tev->args[i].value)
+			free(tev->args[i].value);
+		if (tev->args[i].type)
+			free(tev->args[i].type);
+		ref = tev->args[i].ref;
+		while (ref) {
+			next = ref->next;
+			free(ref);
+			ref = next;
+		}
+	}
+	if (tev->args)
+		free(tev->args);
+	memset(tev, 0, sizeof(*tev));
+}
+
+static int open_kprobe_events(bool readwrite)
 {
 	char buf[PATH_MAX];
+	const char *__debugfs;
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/../kprobe_events", debugfs_path);
-	if (ret < 0)
-		die("Failed to make kprobe_events path.");
+	__debugfs = debugfs_find_mountpoint();
+	if (__debugfs == NULL) {
+		pr_warning("Debugfs is not mounted.\n");
+		return -ENOENT;
+	}
+
+	ret = e_snprintf(buf, PATH_MAX, "%stracing/kprobe_events", __debugfs);
+	if (ret >= 0) {
+		pr_debug("Opening %s write=%d\n", buf, readwrite);
+		if (readwrite && !probe_event_dry_run)
+			ret = open(buf, O_RDWR, O_APPEND);
+		else
+			ret = open(buf, O_RDONLY, 0);
+	}
 
-	ret = open(buf, flags, mode);
 	if (ret < 0) {
 		if (errno == ENOENT)
-			die("kprobe_events file does not exist -"
-			    " please rebuild with CONFIG_KPROBE_EVENT.");
+			pr_warning("kprobe_events file does not exist - please"
+				 " rebuild kernel with CONFIG_KPROBE_EVENT.\n");
 		else
-			die("Could not open kprobe_events file: %s",
-			    strerror(errno));
+			pr_warning("Failed to open kprobe_events file: %s\n",
+				   strerror(errno));
 	}
 	return ret;
 }
 
 /* Get raw string list of current kprobe_events */
-static struct strlist *get_trace_kprobe_event_rawlist(int fd)
+static struct strlist *get_kprobe_trace_command_rawlist(int fd)
 {
 	int ret, idx;
 	FILE *fp;
@@ -447,271 +1142,486 @@ static struct strlist *get_trace_kprobe_event_rawlist(int fd)
 		if (p[idx] == '\n')
 			p[idx] = '\0';
 		ret = strlist__add(sl, buf);
-		if (ret < 0)
-			die("strlist__add failed: %s", strerror(-ret));
+		if (ret < 0) {
+			pr_debug("strlist__add failed: %s\n", strerror(-ret));
+			strlist__delete(sl);
+			return NULL;
+		}
 	}
 	fclose(fp);
 
 	return sl;
 }
 
-/* Free and zero clear probe_point */
-static void clear_probe_point(struct probe_point *pp)
-{
-	int i;
-
-	if (pp->event)
-		free(pp->event);
-	if (pp->group)
-		free(pp->group);
-	if (pp->function)
-		free(pp->function);
-	if (pp->file)
-		free(pp->file);
-	if (pp->lazy_line)
-		free(pp->lazy_line);
-	for (i = 0; i < pp->nr_args; i++)
-		free(pp->args[i]);
-	if (pp->args)
-		free(pp->args);
-	for (i = 0; i < pp->found; i++)
-		free(pp->probes[i]);
-	memset(pp, 0, sizeof(*pp));
-}
-
 /* Show an event */
-static void show_perf_probe_event(const char *event, const char *place,
-				  struct probe_point *pp)
+static int show_perf_probe_event(struct perf_probe_event *pev)
 {
 	int i, ret;
 	char buf[128];
+	char *place;
+
+	/* Synthesize only event probe point */
+	place = synthesize_perf_probe_point(&pev->point);
+	if (!place)
+		return -EINVAL;
 
-	ret = e_snprintf(buf, 128, "%s:%s", pp->group, event);
+	ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
 	if (ret < 0)
-		die("Failed to copy event: %s", strerror(-ret));
-	printf("  %-40s (on %s", buf, place);
+		return ret;
+
+	printf("  %-20s (on %s", buf, place);
 
-	if (pp->nr_args > 0) {
+	if (pev->nargs > 0) {
 		printf(" with");
-		for (i = 0; i < pp->nr_args; i++)
-			printf(" %s", pp->args[i]);
+		for (i = 0; i < pev->nargs; i++) {
+			ret = synthesize_perf_probe_arg(&pev->args[i],
+							buf, 128);
+			if (ret < 0)
+				break;
+			printf(" %s", buf);
+		}
 	}
 	printf(")\n");
+	free(place);
+	return ret;
 }
 
 /* List up current perf-probe events */
-void show_perf_probe_events(void)
+int show_perf_probe_events(void)
 {
-	int fd;
-	struct probe_point pp;
+	int fd, ret;
+	struct kprobe_trace_event tev;
+	struct perf_probe_event pev;
 	struct strlist *rawlist;
 	struct str_node *ent;
 
 	setup_pager();
-	memset(&pp, 0, sizeof(pp));
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
+
+	memset(&tev, 0, sizeof(tev));
+	memset(&pev, 0, sizeof(pev));
 
-	fd = open_kprobe_events(O_RDONLY, 0);
-	rawlist = get_trace_kprobe_event_rawlist(fd);
+	fd = open_kprobe_events(false);
+	if (fd < 0)
+		return fd;
+
+	rawlist = get_kprobe_trace_command_rawlist(fd);
 	close(fd);
+	if (!rawlist)
+		return -ENOENT;
 
 	strlist__for_each(ent, rawlist) {
-		parse_trace_kprobe_event(ent->s, &pp);
-		/* Synthesize only event probe point */
-		synthesize_perf_probe_point(&pp);
-		/* Show an event */
-		show_perf_probe_event(pp.event, pp.probes[0], &pp);
-		clear_probe_point(&pp);
+		ret = parse_kprobe_trace_command(ent->s, &tev);
+		if (ret >= 0) {
+			ret = convert_to_perf_probe_event(&tev, &pev);
+			if (ret >= 0)
+				ret = show_perf_probe_event(&pev);
+		}
+		clear_perf_probe_event(&pev);
+		clear_kprobe_trace_event(&tev);
+		if (ret < 0)
+			break;
 	}
-
 	strlist__delete(rawlist);
+
+	return ret;
 }
 
 /* Get current perf-probe event names */
-static struct strlist *get_perf_event_names(int fd, bool include_group)
+static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group)
 {
 	char buf[128];
 	struct strlist *sl, *rawlist;
 	struct str_node *ent;
-	struct probe_point pp;
+	struct kprobe_trace_event tev;
+	int ret = 0;
 
-	memset(&pp, 0, sizeof(pp));
-	rawlist = get_trace_kprobe_event_rawlist(fd);
+	memset(&tev, 0, sizeof(tev));
 
+	rawlist = get_kprobe_trace_command_rawlist(fd);
 	sl = strlist__new(true, NULL);
 	strlist__for_each(ent, rawlist) {
-		parse_trace_kprobe_event(ent->s, &pp);
+		ret = parse_kprobe_trace_command(ent->s, &tev);
+		if (ret < 0)
+			break;
 		if (include_group) {
-			if (e_snprintf(buf, 128, "%s:%s", pp.group,
-				       pp.event) < 0)
-				die("Failed to copy group:event name.");
-			strlist__add(sl, buf);
+			ret = e_snprintf(buf, 128, "%s:%s", tev.group,
+					tev.event);
+			if (ret >= 0)
+				ret = strlist__add(sl, buf);
 		} else
-			strlist__add(sl, pp.event);
-		clear_probe_point(&pp);
+			ret = strlist__add(sl, tev.event);
+		clear_kprobe_trace_event(&tev);
+		if (ret < 0)
+			break;
 	}
-
 	strlist__delete(rawlist);
 
+	if (ret < 0) {
+		strlist__delete(sl);
+		return NULL;
+	}
 	return sl;
 }
 
-static void write_trace_kprobe_event(int fd, const char *buf)
+static int write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev)
 {
-	int ret;
+	int ret = 0;
+	char *buf = synthesize_kprobe_trace_command(tev);
+
+	if (!buf) {
+		pr_debug("Failed to synthesize kprobe trace event.\n");
+		return -EINVAL;
+	}
 
 	pr_debug("Writing event: %s\n", buf);
-	ret = write(fd, buf, strlen(buf));
-	if (ret <= 0)
-		die("Failed to write event: %s", strerror(errno));
+	if (!probe_event_dry_run) {
+		ret = write(fd, buf, strlen(buf));
+		if (ret <= 0)
+			pr_warning("Failed to write event: %s\n",
+				   strerror(errno));
+	}
+	free(buf);
+	return ret;
 }
 
-static void get_new_event_name(char *buf, size_t len, const char *base,
-			       struct strlist *namelist, bool allow_suffix)
+static int get_new_event_name(char *buf, size_t len, const char *base,
+			      struct strlist *namelist, bool allow_suffix)
 {
 	int i, ret;
 
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
-	if (ret < 0)
-		die("snprintf() failed: %s", strerror(-ret));
+	if (ret < 0) {
+		pr_debug("snprintf() failed: %s\n", strerror(-ret));
+		return ret;
+	}
 	if (!strlist__has_entry(namelist, buf))
-		return;
+		return 0;
 
 	if (!allow_suffix) {
 		pr_warning("Error: event \"%s\" already exists. "
 			   "(Use -f to force duplicates.)\n", base);
-		die("Can't add new event.");
+		return -EEXIST;
 	}
 
 	/* Try to add suffix */
 	for (i = 1; i < MAX_EVENT_INDEX; i++) {
 		ret = e_snprintf(buf, len, "%s_%d", base, i);
-		if (ret < 0)
-			die("snprintf() failed: %s", strerror(-ret));
+		if (ret < 0) {
+			pr_debug("snprintf() failed: %s\n", strerror(-ret));
+			return ret;
+		}
 		if (!strlist__has_entry(namelist, buf))
 			break;
 	}
-	if (i == MAX_EVENT_INDEX)
-		die("Too many events are on the same function.");
+	if (i == MAX_EVENT_INDEX) {
+		pr_warning("Too many events are on the same function.\n");
+		ret = -ERANGE;
+	}
+
+	return ret;
 }
 
-void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
-			     bool force_add)
+static int __add_kprobe_trace_events(struct perf_probe_event *pev,
+				     struct kprobe_trace_event *tevs,
+				     int ntevs, bool allow_suffix)
 {
-	int i, j, fd;
-	struct probe_point *pp;
-	char buf[MAX_CMDLEN];
-	char event[64];
+	int i, fd, ret;
+	struct kprobe_trace_event *tev = NULL;
+	char buf[64];
+	const char *event, *group;
 	struct strlist *namelist;
-	bool allow_suffix;
 
-	fd = open_kprobe_events(O_RDWR, O_APPEND);
+	fd = open_kprobe_events(true);
+	if (fd < 0)
+		return fd;
 	/* Get current event names */
-	namelist = get_perf_event_names(fd, false);
-
-	for (j = 0; j < nr_probes; j++) {
-		pp = probes + j;
-		if (!pp->event)
-			pp->event = strdup(pp->function);
-		if (!pp->group)
-			pp->group = strdup(PERFPROBE_GROUP);
-		DIE_IF(!pp->event || !pp->group);
-		/* If force_add is true, suffix search is allowed */
-		allow_suffix = force_add;
-		for (i = 0; i < pp->found; i++) {
-			/* Get an unused new event name */
-			get_new_event_name(event, 64, pp->event, namelist,
-					   allow_suffix);
-			snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s\n",
-				 pp->retprobe ? 'r' : 'p',
-				 pp->group, event,
-				 pp->probes[i]);
-			write_trace_kprobe_event(fd, buf);
-			printf("Added new event:\n");
-			/* Get the first parameter (probe-point) */
-			sscanf(pp->probes[i], "%s", buf);
-			show_perf_probe_event(event, buf, pp);
-			/* Add added event name to namelist */
-			strlist__add(namelist, event);
-			/*
-			 * Probes after the first probe which comes from same
-			 * user input are always allowed to add suffix, because
-			 * there might be several addresses corresponding to
-			 * one code line.
-			 */
-			allow_suffix = true;
+	namelist = get_kprobe_trace_event_names(fd, false);
+	if (!namelist) {
+		pr_debug("Failed to get current event list.\n");
+		return -EIO;
+	}
+
+	ret = 0;
+	printf("Add new event%s\n", (ntevs > 1) ? "s:" : ":");
+	for (i = 0; i < ntevs; i++) {
+		tev = &tevs[i];
+		if (pev->event)
+			event = pev->event;
+		else
+			if (pev->point.function)
+				event = pev->point.function;
+			else
+				event = tev->point.symbol;
+		if (pev->group)
+			group = pev->group;
+		else
+			group = PERFPROBE_GROUP;
+
+		/* Get an unused new event name */
+		ret = get_new_event_name(buf, 64, event,
+					 namelist, allow_suffix);
+		if (ret < 0)
+			break;
+		event = buf;
+
+		tev->event = strdup(event);
+		tev->group = strdup(group);
+		if (tev->event == NULL || tev->group == NULL) {
+			ret = -ENOMEM;
+			break;
 		}
+		ret = write_kprobe_trace_event(fd, tev);
+		if (ret < 0)
+			break;
+		/* Add added event name to namelist */
+		strlist__add(namelist, event);
+
+		/* Trick here - save current event/group */
+		event = pev->event;
+		group = pev->group;
+		pev->event = tev->event;
+		pev->group = tev->group;
+		show_perf_probe_event(pev);
+		/* Trick here - restore current event/group */
+		pev->event = (char *)event;
+		pev->group = (char *)group;
+
+		/*
+		 * Probes after the first probe which comes from same
+		 * user input are always allowed to add suffix, because
+		 * there might be several addresses corresponding to
+		 * one code line.
+		 */
+		allow_suffix = true;
+	}
+
+	if (ret >= 0) {
+		/* Show how to use the event. */
+		printf("\nYou can now use it on all perf tools, such as:\n\n");
+		printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
+			 tev->event);
 	}
-	/* Show how to use the event. */
-	printf("\nYou can now use it on all perf tools, such as:\n\n");
-	printf("\tperf record -e %s:%s -a sleep 1\n\n", PERFPROBE_GROUP, event);
 
 	strlist__delete(namelist);
 	close(fd);
+	return ret;
+}
+
+static int convert_to_kprobe_trace_events(struct perf_probe_event *pev,
+					  struct kprobe_trace_event **tevs,
+					  int max_tevs)
+{
+	struct symbol *sym;
+	int ret = 0, i;
+	struct kprobe_trace_event *tev;
+
+	/* Convert perf_probe_event with debuginfo */
+	ret = try_to_find_kprobe_trace_events(pev, tevs, max_tevs);
+	if (ret != 0)
+		return ret;
+
+	/* Allocate trace event buffer */
+	tev = *tevs = zalloc(sizeof(struct kprobe_trace_event));
+	if (tev == NULL)
+		return -ENOMEM;
+
+	/* Copy parameters */
+	tev->point.symbol = strdup(pev->point.function);
+	if (tev->point.symbol == NULL) {
+		ret = -ENOMEM;
+		goto error;
+	}
+	tev->point.offset = pev->point.offset;
+	tev->nargs = pev->nargs;
+	if (tev->nargs) {
+		tev->args = zalloc(sizeof(struct kprobe_trace_arg)
+				   * tev->nargs);
+		if (tev->args == NULL) {
+			ret = -ENOMEM;
+			goto error;
+		}
+		for (i = 0; i < tev->nargs; i++) {
+			if (pev->args[i].name) {
+				tev->args[i].name = strdup(pev->args[i].name);
+				if (tev->args[i].name == NULL) {
+					ret = -ENOMEM;
+					goto error;
+				}
+			}
+			tev->args[i].value = strdup(pev->args[i].var);
+			if (tev->args[i].value == NULL) {
+				ret = -ENOMEM;
+				goto error;
+			}
+			if (pev->args[i].type) {
+				tev->args[i].type = strdup(pev->args[i].type);
+				if (tev->args[i].type == NULL) {
+					ret = -ENOMEM;
+					goto error;
+				}
+			}
+		}
+	}
+
+	/* Currently just checking function name from symbol map */
+	sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
+				       tev->point.symbol, NULL);
+	if (!sym) {
+		pr_warning("Kernel symbol \'%s\' not found.\n",
+			   tev->point.symbol);
+		ret = -ENOENT;
+		goto error;
+	}
+
+	return 1;
+error:
+	clear_kprobe_trace_event(tev);
+	free(tev);
+	*tevs = NULL;
+	return ret;
+}
+
+struct __event_package {
+	struct perf_probe_event		*pev;
+	struct kprobe_trace_event	*tevs;
+	int				ntevs;
+};
+
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
+			  bool force_add, int max_tevs)
+{
+	int i, j, ret;
+	struct __event_package *pkgs;
+
+	pkgs = zalloc(sizeof(struct __event_package) * npevs);
+	if (pkgs == NULL)
+		return -ENOMEM;
+
+	/* Init vmlinux path */
+	ret = init_vmlinux();
+	if (ret < 0)
+		return ret;
+
+	/* Loop 1: convert all events */
+	for (i = 0; i < npevs; i++) {
+		pkgs[i].pev = &pevs[i];
+		/* Convert with or without debuginfo */
+		ret  = convert_to_kprobe_trace_events(pkgs[i].pev,
+						      &pkgs[i].tevs, max_tevs);
+		if (ret < 0)
+			goto end;
+		pkgs[i].ntevs = ret;
+	}
+
+	/* Loop 2: add all events */
+	for (i = 0; i < npevs && ret >= 0; i++)
+		ret = __add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs,
+						pkgs[i].ntevs, force_add);
+end:
+	/* Loop 3: cleanup trace events  */
+	for (i = 0; i < npevs; i++)
+		for (j = 0; j < pkgs[i].ntevs; j++)
+			clear_kprobe_trace_event(&pkgs[i].tevs[j]);
+
+	return ret;
 }
 
-static void __del_trace_kprobe_event(int fd, struct str_node *ent)
+static int __del_trace_kprobe_event(int fd, struct str_node *ent)
 {
 	char *p;
 	char buf[128];
+	int ret;
 
 	/* Convert from perf-probe event to trace-kprobe event */
-	if (e_snprintf(buf, 128, "-:%s", ent->s) < 0)
-		die("Failed to copy event.");
+	ret = e_snprintf(buf, 128, "-:%s", ent->s);
+	if (ret < 0)
+		goto error;
+
 	p = strchr(buf + 2, ':');
-	if (!p)
-		die("Internal error: %s should have ':' but not.", ent->s);
+	if (!p) {
+		pr_debug("Internal error: %s should have ':' but not.\n",
+			 ent->s);
+		ret = -ENOTSUP;
+		goto error;
+	}
 	*p = '/';
 
-	write_trace_kprobe_event(fd, buf);
+	pr_debug("Writing event: %s\n", buf);
+	ret = write(fd, buf, strlen(buf));
+	if (ret < 0)
+		goto error;
+
 	printf("Remove event: %s\n", ent->s);
+	return 0;
+error:
+	pr_warning("Failed to delete event: %s\n", strerror(-ret));
+	return ret;
 }
 
-static void del_trace_kprobe_event(int fd, const char *group,
-				   const char *event, struct strlist *namelist)
+static int del_trace_kprobe_event(int fd, const char *group,
+				  const char *event, struct strlist *namelist)
 {
 	char buf[128];
 	struct str_node *ent, *n;
-	int found = 0;
+	int found = 0, ret = 0;
 
-	if (e_snprintf(buf, 128, "%s:%s", group, event) < 0)
-		die("Failed to copy event.");
+	ret = e_snprintf(buf, 128, "%s:%s", group, event);
+	if (ret < 0) {
+		pr_err("Failed to copy event.");
+		return ret;
+	}
 
 	if (strpbrk(buf, "*?")) { /* Glob-exp */
 		strlist__for_each_safe(ent, n, namelist)
 			if (strglobmatch(ent->s, buf)) {
 				found++;
-				__del_trace_kprobe_event(fd, ent);
+				ret = __del_trace_kprobe_event(fd, ent);
+				if (ret < 0)
+					break;
 				strlist__remove(namelist, ent);
 			}
 	} else {
 		ent = strlist__find(namelist, buf);
 		if (ent) {
 			found++;
-			__del_trace_kprobe_event(fd, ent);
-			strlist__remove(namelist, ent);
+			ret = __del_trace_kprobe_event(fd, ent);
+			if (ret >= 0)
+				strlist__remove(namelist, ent);
 		}
 	}
-	if (found == 0)
-		pr_info("Info: event \"%s\" does not exist, could not remove it.\n", buf);
+	if (found == 0 && ret >= 0)
+		pr_info("Info: Event \"%s\" does not exist.\n", buf);
+
+	return ret;
 }
 
-void del_trace_kprobe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strlist *dellist)
 {
-	int fd;
+	int fd, ret = 0;
 	const char *group, *event;
 	char *p, *str;
 	struct str_node *ent;
 	struct strlist *namelist;
 
-	fd = open_kprobe_events(O_RDWR, O_APPEND);
+	fd = open_kprobe_events(true);
+	if (fd < 0)
+		return fd;
+
 	/* Get current event names */
-	namelist = get_perf_event_names(fd, true);
+	namelist = get_kprobe_trace_event_names(fd, true);
+	if (namelist == NULL)
+		return -EINVAL;
 
 	strlist__for_each(ent, dellist) {
 		str = strdup(ent->s);
-		if (!str)
-			die("Failed to copy event.");
+		if (str == NULL) {
+			ret = -ENOMEM;
+			break;
+		}
 		pr_debug("Parsing: %s\n", str);
 		p = strchr(str, ':');
 		if (p) {
@@ -723,80 +1633,14 @@ void del_trace_kprobe_events(struct strlist *dellist)
 			event = str;
 		}
 		pr_debug("Group: %s, Event: %s\n", group, event);
-		del_trace_kprobe_event(fd, group, event, namelist);
+		ret = del_trace_kprobe_event(fd, group, event, namelist);
 		free(str);
+		if (ret < 0)
+			break;
 	}
 	strlist__delete(namelist);
 	close(fd);
-}
 
-#define LINEBUF_SIZE 256
-#define NR_ADDITIONAL_LINES 2
-
-static void show_one_line(FILE *fp, unsigned int l, bool skip, bool show_num)
-{
-	char buf[LINEBUF_SIZE];
-	const char *color = PERF_COLOR_BLUE;
-
-	if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-		goto error;
-	if (!skip) {
-		if (show_num)
-			fprintf(stdout, "%7u  %s", l, buf);
-		else
-			color_fprintf(stdout, color, "         %s", buf);
-	}
-
-	while (strlen(buf) == LINEBUF_SIZE - 1 &&
-	       buf[LINEBUF_SIZE - 2] != '\n') {
-		if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-			goto error;
-		if (!skip) {
-			if (show_num)
-				fprintf(stdout, "%s", buf);
-			else
-				color_fprintf(stdout, color, "%s", buf);
-		}
-	}
-	return;
-error:
-	if (feof(fp))
-		die("Source file is shorter than expected.");
-	else
-		die("File read error: %s", strerror(errno));
+	return ret;
 }
 
-void show_line_range(struct line_range *lr)
-{
-	unsigned int l = 1;
-	struct line_node *ln;
-	FILE *fp;
-
-	setup_pager();
-
-	if (lr->function)
-		fprintf(stdout, "<%s:%d>\n", lr->function,
-			lr->start - lr->offset);
-	else
-		fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
-
-	fp = fopen(lr->path, "r");
-	if (fp == NULL)
-		die("Failed to open %s: %s", lr->path, strerror(errno));
-	/* Skip to starting line number */
-	while (l < lr->start)
-		show_one_line(fp, l++, true, false);
-
-	list_for_each_entry(ln, &lr->line_list, list) {
-		while (ln->line > l)
-			show_one_line(fp, (l++) - lr->offset, false, false);
-		show_one_line(fp, (l++) - lr->offset, false, true);
-	}
-
-	if (lr->end == INT_MAX)
-		lr->end = l + NR_ADDITIONAL_LINES;
-	while (l < lr->end && !feof(fp))
-		show_one_line(fp, (l++) - lr->offset, false, false);
-
-	fclose(fp);
-}
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 711287d4baea..e9db1a214ca4 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,21 +2,125 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
-#include "probe-finder.h"
 #include "strlist.h"
 
-extern void parse_line_range_desc(const char *arg, struct line_range *lr);
-extern void parse_perf_probe_event(const char *str, struct probe_point *pp,
-				   bool *need_dwarf);
-extern int synthesize_perf_probe_point(struct probe_point *pp);
-extern int synthesize_perf_probe_event(struct probe_point *pp);
-extern void parse_trace_kprobe_event(const char *str, struct probe_point *pp);
-extern int synthesize_trace_kprobe_event(struct probe_point *pp);
-extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
-				    bool force_add);
-extern void del_trace_kprobe_events(struct strlist *dellist);
-extern void show_perf_probe_events(void);
-extern void show_line_range(struct line_range *lr);
+extern bool probe_event_dry_run;
+
+/* kprobe-tracer tracing point */
+struct kprobe_trace_point {
+	char		*symbol;	/* Base symbol */
+	unsigned long	offset;		/* Offset from symbol */
+	bool		retprobe;	/* Return probe flag */
+};
+
+/* kprobe-tracer tracing argument referencing offset */
+struct kprobe_trace_arg_ref {
+	struct kprobe_trace_arg_ref	*next;	/* Next reference */
+	long				offset;	/* Offset value */
+};
+
+/* kprobe-tracer tracing argument */
+struct kprobe_trace_arg {
+	char				*name;	/* Argument name */
+	char				*value;	/* Base value */
+	char				*type;	/* Type name */
+	struct kprobe_trace_arg_ref	*ref;	/* Referencing offset */
+};
+
+/* kprobe-tracer tracing event (point + arg) */
+struct kprobe_trace_event {
+	char				*event;	/* Event name */
+	char				*group;	/* Group name */
+	struct kprobe_trace_point	point;	/* Trace point */
+	int				nargs;	/* Number of args */
+	struct kprobe_trace_arg		*args;	/* Arguments */
+};
+
+/* Perf probe probing point */
+struct perf_probe_point {
+	char		*file;		/* File path */
+	char		*function;	/* Function name */
+	int		line;		/* Line number */
+	bool		retprobe;	/* Return probe flag */
+	char		*lazy_line;	/* Lazy matching pattern */
+	unsigned long	offset;		/* Offset from function entry */
+};
+
+/* Perf probe probing argument field chain */
+struct perf_probe_arg_field {
+	struct perf_probe_arg_field	*next;	/* Next field */
+	char				*name;	/* Name of the field */
+	bool				ref;	/* Referencing flag */
+};
+
+/* Perf probe probing argument */
+struct perf_probe_arg {
+	char				*name;	/* Argument name */
+	char				*var;	/* Variable name */
+	char				*type;	/* Type name */
+	struct perf_probe_arg_field	*field;	/* Structure fields */
+};
+
+/* Perf probe probing event (point + arg) */
+struct perf_probe_event {
+	char			*event;	/* Event name */
+	char			*group;	/* Group name */
+	struct perf_probe_point	point;	/* Probe point */
+	int			nargs;	/* Number of arguments */
+	struct perf_probe_arg	*args;	/* Arguments */
+};
+
+
+/* Line number container */
+struct line_node {
+	struct list_head	list;
+	int			line;
+};
+
+/* Line range */
+struct line_range {
+	char			*file;		/* File name */
+	char			*function;	/* Function name */
+	int			start;		/* Start line number */
+	int			end;		/* End line number */
+	int			offset;		/* Start line offset */
+	char			*path;		/* Real path name */
+	struct list_head	line_list;	/* Visible lines */
+};
+
+/* Command string to events */
+extern int parse_perf_probe_command(const char *cmd,
+				    struct perf_probe_event *pev);
+extern int parse_kprobe_trace_command(const char *cmd,
+				      struct kprobe_trace_event *tev);
+
+/* Events to command string */
+extern char *synthesize_perf_probe_command(struct perf_probe_event *pev);
+extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev);
+extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf,
+				     size_t len);
+
+/* Check the perf_probe_event needs debuginfo */
+extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
+
+/* Convert from kprobe_trace_event to perf_probe_event */
+extern int convert_to_perf_probe_event(struct kprobe_trace_event *tev,
+				       struct perf_probe_event *pev);
+
+/* Release event contents */
+extern void clear_perf_probe_event(struct perf_probe_event *pev);
+extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev);
+
+/* Command string to line-range */
+extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
+
+
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
+				 bool force_add, int max_probe_points);
+extern int del_perf_probe_events(struct strlist *dellist);
+extern int show_perf_probe_events(void);
+extern int show_line_range(struct line_range *lr);
+
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c171a243d05b..562b1443e785 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -31,6 +31,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <ctype.h>
+#include <dwarf-regs.h>
 
 #include "string.h"
 #include "event.h"
@@ -38,57 +39,8 @@
 #include "util.h"
 #include "probe-finder.h"
 
-
-/*
- * Generic dwarf analysis helpers
- */
-
-#define X86_32_MAX_REGS 8
-const char *x86_32_regs_table[X86_32_MAX_REGS] = {
-	"%ax",
-	"%cx",
-	"%dx",
-	"%bx",
-	"$stack",	/* Stack address instead of %sp */
-	"%bp",
-	"%si",
-	"%di",
-};
-
-#define X86_64_MAX_REGS 16
-const char *x86_64_regs_table[X86_64_MAX_REGS] = {
-	"%ax",
-	"%dx",
-	"%cx",
-	"%bx",
-	"%si",
-	"%di",
-	"%bp",
-	"%sp",
-	"%r8",
-	"%r9",
-	"%r10",
-	"%r11",
-	"%r12",
-	"%r13",
-	"%r14",
-	"%r15",
-};
-
-/* TODO: switching by dwarf address size */
-#ifdef __x86_64__
-#define ARCH_MAX_REGS X86_64_MAX_REGS
-#define arch_regs_table x86_64_regs_table
-#else
-#define ARCH_MAX_REGS X86_32_MAX_REGS
-#define arch_regs_table x86_32_regs_table
-#endif
-
-/* Return architecture dependent register string (for kprobe-tracer) */
-static const char *get_arch_regstr(unsigned int n)
-{
-	return (n <= ARCH_MAX_REGS) ? arch_regs_table[n] : NULL;
-}
+/* Kprobe tracer basic type is up to u64 */
+#define MAX_BASIC_TYPE_BITS	64
 
 /*
  * Compare the tail of two strings.
@@ -108,7 +60,7 @@ static int strtailcmp(const char *s1, const char *s2)
 /* Line number list operations */
 
 /* Add a line to line number list */
-static void line_list__add_line(struct list_head *head, unsigned int line)
+static int line_list__add_line(struct list_head *head, int line)
 {
 	struct line_node *ln;
 	struct list_head *p;
@@ -119,21 +71,23 @@ static void line_list__add_line(struct list_head *head, unsigned int line)
 			p = &ln->list;
 			goto found;
 		} else if (ln->line == line)	/* Already exist */
-			return ;
+			return 1;
 	}
 	/* List is empty, or the smallest entry */
 	p = head;
 found:
 	pr_debug("line list: add a line %u\n", line);
 	ln = zalloc(sizeof(struct line_node));
-	DIE_IF(ln == NULL);
+	if (ln == NULL)
+		return -ENOMEM;
 	ln->line = line;
 	INIT_LIST_HEAD(&ln->list);
 	list_add(&ln->list, p);
+	return 0;
 }
 
 /* Check if the line in line number list */
-static int line_list__has_line(struct list_head *head, unsigned int line)
+static int line_list__has_line(struct list_head *head, int line)
 {
 	struct line_node *ln;
 
@@ -184,9 +138,129 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 		if (strtailcmp(src, fname) == 0)
 			break;
 	}
+	if (i == nfiles)
+		return NULL;
 	return src;
 }
 
+/* Compare diename and tname */
+static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+{
+	const char *name;
+	name = dwarf_diename(dw_die);
+	return name ? strcmp(tname, name) : -1;
+}
+
+/* Get type die, but skip qualifiers and typedef */
+static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+	Dwarf_Attribute attr;
+	int tag;
+
+	do {
+		if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL ||
+		    dwarf_formref_die(&attr, die_mem) == NULL)
+			return NULL;
+
+		tag = dwarf_tag(die_mem);
+		vr_die = die_mem;
+	} while (tag == DW_TAG_const_type ||
+		 tag == DW_TAG_restrict_type ||
+		 tag == DW_TAG_volatile_type ||
+		 tag == DW_TAG_shared_type ||
+		 tag == DW_TAG_typedef);
+
+	return die_mem;
+}
+
+static bool die_is_signed_type(Dwarf_Die *tp_die)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Word ret;
+
+	if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL ||
+	    dwarf_formudata(&attr, &ret) != 0)
+		return false;
+
+	return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
+		ret == DW_ATE_signed_fixed);
+}
+
+static int die_get_byte_size(Dwarf_Die *tp_die)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Word ret;
+
+	if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL ||
+	    dwarf_formudata(&attr, &ret) != 0)
+		return 0;
+
+	return (int)ret;
+}
+
+/* Get data_member_location offset */
+static int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs)
+{
+	Dwarf_Attribute attr;
+	Dwarf_Op *expr;
+	size_t nexpr;
+	int ret;
+
+	if (dwarf_attr(mb_die, DW_AT_data_member_location, &attr) == NULL)
+		return -ENOENT;
+
+	if (dwarf_formudata(&attr, offs) != 0) {
+		/* DW_AT_data_member_location should be DW_OP_plus_uconst */
+		ret = dwarf_getlocation(&attr, &expr, &nexpr);
+		if (ret < 0 || nexpr == 0)
+			return -ENOENT;
+
+		if (expr[0].atom != DW_OP_plus_uconst || nexpr != 1) {
+			pr_debug("Unable to get offset:Unexpected OP %x (%zd)\n",
+				 expr[0].atom, nexpr);
+			return -ENOTSUP;
+		}
+		*offs = (Dwarf_Word)expr[0].number;
+	}
+	return 0;
+}
+
+/* Return values for die_find callbacks */
+enum {
+	DIE_FIND_CB_FOUND = 0,		/* End of Search */
+	DIE_FIND_CB_CHILD = 1,		/* Search only children */
+	DIE_FIND_CB_SIBLING = 2,	/* Search only siblings */
+	DIE_FIND_CB_CONTINUE = 3,	/* Search children and siblings */
+};
+
+/* Search a child die */
+static Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
+				 int (*callback)(Dwarf_Die *, void *),
+				 void *data, Dwarf_Die *die_mem)
+{
+	Dwarf_Die child_die;
+	int ret;
+
+	ret = dwarf_child(rt_die, die_mem);
+	if (ret != 0)
+		return NULL;
+
+	do {
+		ret = callback(die_mem, data);
+		if (ret == DIE_FIND_CB_FOUND)
+			return die_mem;
+
+		if ((ret & DIE_FIND_CB_CHILD) &&
+		    die_find_child(die_mem, callback, data, &child_die)) {
+			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+			return die_mem;
+		}
+	} while ((ret & DIE_FIND_CB_SIBLING) &&
+		 dwarf_siblingof(die_mem, die_mem) == 0);
+
+	return NULL;
+}
+
 struct __addr_die_search_param {
 	Dwarf_Addr	addr;
 	Dwarf_Die	*die_mem;
@@ -205,8 +279,8 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 }
 
 /* Search a real subprogram including this line, */
-static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
-					  Dwarf_Die *die_mem)
+static Dwarf_Die *die_find_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
+					   Dwarf_Die *die_mem)
 {
 	struct __addr_die_search_param ad;
 	ad.addr = addr;
@@ -218,77 +292,64 @@ static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
 		return die_mem;
 }
 
-/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
-static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
-				     Dwarf_Die *die_mem)
+/* die_find callback for inline function search */
+static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 {
-	Dwarf_Die child_die;
-	int ret;
+	Dwarf_Addr *addr = data;
 
-	ret = dwarf_child(sp_die, die_mem);
-	if (ret != 0)
-		return NULL;
+	if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
+	    dwarf_haspc(die_mem, *addr))
+		return DIE_FIND_CB_FOUND;
 
-	do {
-		if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
-		    dwarf_haspc(die_mem, addr))
-			return die_mem;
-
-		if (die_get_inlinefunc(die_mem, addr, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while (dwarf_siblingof(die_mem, die_mem) == 0);
-
-	return NULL;
+	return DIE_FIND_CB_CONTINUE;
 }
 
-/* Compare diename and tname */
-static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
+/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
+static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+				      Dwarf_Die *die_mem)
 {
-	const char *name;
-	name = dwarf_diename(dw_die);
-	DIE_IF(name == NULL);
-	return strcmp(tname, name);
+	return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
 }
 
-/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
-static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die)
+static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
 {
-	Dwarf_Addr epc;
-	int ret;
+	const char *name = data;
+	int tag;
 
-	ret = dwarf_entrypc(dw_die, &epc);
-	DIE_IF(ret == -1);
-	return epc;
+	tag = dwarf_tag(die_mem);
+	if ((tag == DW_TAG_formal_parameter ||
+	     tag == DW_TAG_variable) &&
+	    (die_compare_name(die_mem, name) == 0))
+		return DIE_FIND_CB_FOUND;
+
+	return DIE_FIND_CB_CONTINUE;
 }
 
-/* Get a variable die */
+/* Find a variable called 'name' */
 static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
 				    Dwarf_Die *die_mem)
 {
-	Dwarf_Die child_die;
-	int tag;
-	int ret;
+	return die_find_child(sp_die, __die_find_variable_cb, (void *)name,
+			      die_mem);
+}
 
-	ret = dwarf_child(sp_die, die_mem);
-	if (ret != 0)
-		return NULL;
+static int __die_find_member_cb(Dwarf_Die *die_mem, void *data)
+{
+	const char *name = data;
 
-	do {
-		tag = dwarf_tag(die_mem);
-		if ((tag == DW_TAG_formal_parameter ||
-		     tag == DW_TAG_variable) &&
-		    (die_compare_name(die_mem, name) == 0))
-			return die_mem;
+	if ((dwarf_tag(die_mem) == DW_TAG_member) &&
+	    (die_compare_name(die_mem, name) == 0))
+		return DIE_FIND_CB_FOUND;
 
-		if (die_find_variable(die_mem, name, &child_die)) {
-			memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
-			return die_mem;
-		}
-	} while (dwarf_siblingof(die_mem, die_mem) == 0);
+	return DIE_FIND_CB_SIBLING;
+}
 
-	return NULL;
+/* Find a member called 'name' */
+static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
+				  Dwarf_Die *die_mem)
+{
+	return die_find_child(st_die, __die_find_member_cb, (void *)name,
+			      die_mem);
 }
 
 /*
@@ -296,19 +357,22 @@ static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
  */
 
 /* Show a location */
-static void show_location(Dwarf_Op *op, struct probe_finder *pf)
+static int convert_location(Dwarf_Op *op, struct probe_finder *pf)
 {
 	unsigned int regn;
 	Dwarf_Word offs = 0;
-	int deref = 0, ret;
+	bool ref = false;
 	const char *regs;
+	struct kprobe_trace_arg *tvar = pf->tvar;
 
-	/* TODO: support CFA */
 	/* If this is based on frame buffer, set the offset */
 	if (op->atom == DW_OP_fbreg) {
-		if (pf->fb_ops == NULL)
-			die("The attribute of frame base is not supported.\n");
-		deref = 1;
+		if (pf->fb_ops == NULL) {
+			pr_warning("The attribute of frame base is not "
+				   "supported.\n");
+			return -ENOTSUP;
+		}
+		ref = true;
 		offs = op->number;
 		op = &pf->fb_ops[0];
 	}
@@ -316,35 +380,164 @@ static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 	if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
 		regn = op->atom - DW_OP_breg0;
 		offs += op->number;
-		deref = 1;
+		ref = true;
 	} else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) {
 		regn = op->atom - DW_OP_reg0;
 	} else if (op->atom == DW_OP_bregx) {
 		regn = op->number;
 		offs += op->number2;
-		deref = 1;
+		ref = true;
 	} else if (op->atom == DW_OP_regx) {
 		regn = op->number;
-	} else
-		die("DW_OP %d is not supported.", op->atom);
+	} else {
+		pr_warning("DW_OP %x is not supported.\n", op->atom);
+		return -ENOTSUP;
+	}
 
 	regs = get_arch_regstr(regn);
-	if (!regs)
-		die("%u exceeds max register number.", regn);
+	if (!regs) {
+		pr_warning("Mapping for DWARF register number %u missing on this architecture.", regn);
+		return -ERANGE;
+	}
+
+	tvar->value = strdup(regs);
+	if (tvar->value == NULL)
+		return -ENOMEM;
+
+	if (ref) {
+		tvar->ref = zalloc(sizeof(struct kprobe_trace_arg_ref));
+		if (tvar->ref == NULL)
+			return -ENOMEM;
+		tvar->ref->offset = (long)offs;
+	}
+	return 0;
+}
+
+static int convert_variable_type(Dwarf_Die *vr_die,
+				 struct kprobe_trace_arg *targ)
+{
+	Dwarf_Die type;
+	char buf[16];
+	int ret;
+
+	if (die_get_real_type(vr_die, &type) == NULL) {
+		pr_warning("Failed to get a type information of %s.\n",
+			   dwarf_diename(vr_die));
+		return -ENOENT;
+	}
+
+	ret = die_get_byte_size(&type) * 8;
+	if (ret) {
+		/* Check the bitwidth */
+		if (ret > MAX_BASIC_TYPE_BITS) {
+			pr_info("%s exceeds max-bitwidth."
+				" Cut down to %d bits.\n",
+				dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+			ret = MAX_BASIC_TYPE_BITS;
+		}
+
+		ret = snprintf(buf, 16, "%c%d",
+			       die_is_signed_type(&type) ? 's' : 'u', ret);
+		if (ret < 0 || ret >= 16) {
+			if (ret >= 16)
+				ret = -E2BIG;
+			pr_warning("Failed to convert variable type: %s\n",
+				   strerror(-ret));
+			return ret;
+		}
+		targ->type = strdup(buf);
+		if (targ->type == NULL)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
+				    struct perf_probe_arg_field *field,
+				    struct kprobe_trace_arg_ref **ref_ptr,
+				    Dwarf_Die *die_mem)
+{
+	struct kprobe_trace_arg_ref *ref = *ref_ptr;
+	Dwarf_Die type;
+	Dwarf_Word offs;
+	int ret;
+
+	pr_debug("converting %s in %s\n", field->name, varname);
+	if (die_get_real_type(vr_die, &type) == NULL) {
+		pr_warning("Failed to get the type of %s.\n", varname);
+		return -ENOENT;
+	}
+
+	/* Check the pointer and dereference */
+	if (dwarf_tag(&type) == DW_TAG_pointer_type) {
+		if (!field->ref) {
+			pr_err("Semantic error: %s must be referred by '->'\n",
+			       field->name);
+			return -EINVAL;
+		}
+		/* Get the type pointed by this pointer */
+		if (die_get_real_type(&type, &type) == NULL) {
+			pr_warning("Failed to get the type of %s.\n", varname);
+			return -ENOENT;
+		}
+		/* Verify it is a data structure  */
+		if (dwarf_tag(&type) != DW_TAG_structure_type) {
+			pr_warning("%s is not a data structure.\n", varname);
+			return -EINVAL;
+		}
+
+		ref = zalloc(sizeof(struct kprobe_trace_arg_ref));
+		if (ref == NULL)
+			return -ENOMEM;
+		if (*ref_ptr)
+			(*ref_ptr)->next = ref;
+		else
+			*ref_ptr = ref;
+	} else {
+		/* Verify it is a data structure  */
+		if (dwarf_tag(&type) != DW_TAG_structure_type) {
+			pr_warning("%s is not a data structure.\n", varname);
+			return -EINVAL;
+		}
+		if (field->ref) {
+			pr_err("Semantic error: %s must be referred by '.'\n",
+			       field->name);
+			return -EINVAL;
+		}
+		if (!ref) {
+			pr_warning("Structure on a register is not "
+				   "supported yet.\n");
+			return -ENOTSUP;
+		}
+	}
+
+	if (die_find_member(&type, field->name, die_mem) == NULL) {
+		pr_warning("%s(tyep:%s) has no member %s.\n", varname,
+			   dwarf_diename(&type), field->name);
+		return -EINVAL;
+	}
 
-	if (deref)
-		ret = snprintf(pf->buf, pf->len, " %s=%+jd(%s)",
-			       pf->var, (intmax_t)offs, regs);
+	/* Get the offset of the field */
+	ret = die_get_data_member_location(die_mem, &offs);
+	if (ret < 0) {
+		pr_warning("Failed to get the offset of %s.\n", field->name);
+		return ret;
+	}
+	ref->offset += (long)offs;
+
+	/* Converting next field */
+	if (field->next)
+		return convert_variable_fields(die_mem, field->name,
+					field->next, &ref, die_mem);
 	else
-		ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
-	DIE_IF(ret < 0);
-	DIE_IF(ret >= pf->len);
+		return 0;
 }
 
 /* Show a variables in kprobe event format */
-static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
+static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 {
 	Dwarf_Attribute attr;
+	Dwarf_Die die_mem;
 	Dwarf_Op *expr;
 	size_t nexpr;
 	int ret;
@@ -356,142 +549,191 @@ static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	if (ret <= 0 || nexpr == 0)
 		goto error;
 
-	show_location(expr, pf);
+	ret = convert_location(expr, pf);
+	if (ret == 0 && pf->pvar->field) {
+		ret = convert_variable_fields(vr_die, pf->pvar->var,
+					      pf->pvar->field, &pf->tvar->ref,
+					      &die_mem);
+		vr_die = &die_mem;
+	}
+	if (ret == 0) {
+		if (pf->pvar->type) {
+			pf->tvar->type = strdup(pf->pvar->type);
+			if (pf->tvar->type == NULL)
+				ret = -ENOMEM;
+		} else
+			ret = convert_variable_type(vr_die, pf->tvar);
+	}
 	/* *expr will be cached in libdw. Don't free it. */
-	return ;
+	return ret;
 error:
 	/* TODO: Support const_value */
-	die("Failed to find the location of %s at this address.\n"
-	    " Perhaps, it has been optimized out.", pf->var);
+	pr_err("Failed to find the location of %s at this address.\n"
+	       " Perhaps, it has been optimized out.\n", pf->pvar->var);
+	return -ENOENT;
 }
 
 /* Find a variable in a subprogram die */
-static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	int ret;
 	Dwarf_Die vr_die;
+	char buf[32], *ptr;
+	int ret;
 
-	/* TODO: Support struct members and arrays */
-	if (!is_c_varname(pf->var)) {
-		/* Output raw parameters */
-		ret = snprintf(pf->buf, pf->len, " %s", pf->var);
-		DIE_IF(ret < 0);
-		DIE_IF(ret >= pf->len);
-		return ;
+	/* TODO: Support arrays */
+	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;
+		ptr = strchr(buf, ':');	/* Change type separator to _ */
+		if (ptr)
+			*ptr = '_';
+		pf->tvar->name = strdup(buf);
+	}
+	if (pf->tvar->name == NULL)
+		return -ENOMEM;
+
+	if (!is_c_varname(pf->pvar->var)) {
+		/* Copy raw parameters */
+		pf->tvar->value = strdup(pf->pvar->var);
+		if (pf->tvar->value == NULL)
+			return -ENOMEM;
+		else
+			return 0;
 	}
 
-	pr_debug("Searching '%s' variable in context.\n", pf->var);
+	pr_debug("Searching '%s' variable in context.\n",
+		 pf->pvar->var);
 	/* Search child die for local variables and parameters. */
-	if (!die_find_variable(sp_die, pf->var, &vr_die))
-		die("Failed to find '%s' in this function.", pf->var);
-
-	show_variable(&vr_die, pf);
+	if (!die_find_variable(sp_die, pf->pvar->var, &vr_die)) {
+		pr_warning("Failed to find '%s' in this function.\n",
+			   pf->pvar->var);
+		return -ENOENT;
+	}
+	return convert_variable(&vr_die, pf);
 }
 
 /* Show a probe point to output buffer */
-static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-	struct probe_point *pp = pf->pp;
+	struct kprobe_trace_event *tev;
 	Dwarf_Addr eaddr;
 	Dwarf_Die die_mem;
 	const char *name;
-	char tmp[MAX_PROBE_BUFFER];
-	int ret, i, len;
+	int ret, i;
 	Dwarf_Attribute fb_attr;
 	size_t nops;
 
+	if (pf->ntevs == pf->max_tevs) {
+		pr_warning("Too many( > %d) probe point found.\n",
+			   pf->max_tevs);
+		return -ERANGE;
+	}
+	tev = &pf->tevs[pf->ntevs++];
+
 	/* If no real subprogram, find a real one */
 	if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
-		sp_die = die_get_real_subprogram(&pf->cu_die,
+		sp_die = die_find_real_subprogram(&pf->cu_die,
 						 pf->addr, &die_mem);
-		if (!sp_die)
-			die("Probe point is not found in subprograms.");
+		if (!sp_die) {
+			pr_warning("Failed to find probe point in any "
+				   "functions.\n");
+			return -ENOENT;
+		}
 	}
 
-	/* Output name of probe point */
+	/* Copy the name of probe point */
 	name = dwarf_diename(sp_die);
 	if (name) {
-		dwarf_entrypc(sp_die, &eaddr);
-		ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name,
-				(unsigned long)(pf->addr - eaddr));
-		/* Copy the function name if possible */
-		if (!pp->function) {
-			pp->function = strdup(name);
-			pp->offset = (size_t)(pf->addr - eaddr);
+		if (dwarf_entrypc(sp_die, &eaddr) != 0) {
+			pr_warning("Failed to get entry pc of %s\n",
+				   dwarf_diename(sp_die));
+			return -ENOENT;
 		}
-	} else {
+		tev->point.symbol = strdup(name);
+		if (tev->point.symbol == NULL)
+			return -ENOMEM;
+		tev->point.offset = (unsigned long)(pf->addr - eaddr);
+	} else
 		/* This function has no name. */
-		ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx",
-			       (uintmax_t)pf->addr);
-		if (!pp->function) {
-			/* TODO: Use _stext */
-			pp->function = strdup("");
-			pp->offset = (size_t)pf->addr;
-		}
-	}
-	DIE_IF(ret < 0);
-	DIE_IF(ret >= MAX_PROBE_BUFFER);
-	len = ret;
-	pr_debug("Probe point found: %s\n", tmp);
+		tev->point.offset = (unsigned long)pf->addr;
+
+	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
+		 tev->point.offset);
 
 	/* Get the frame base attribute/ops */
 	dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
-	if (ret <= 0 || nops == 0)
+	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
+	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
+		   pf->cfi != NULL) {
+		Dwarf_Frame *frame;
+		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
+		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
+			pr_warning("Failed to get CFA on 0x%jx\n",
+				   (uintmax_t)pf->addr);
+			return -ENOENT;
+		}
+	}
 
 	/* Find each argument */
-	/* TODO: use dwarf_cfi_addrframe */
-	for (i = 0; i < pp->nr_args; i++) {
-		pf->var = pp->args[i];
-		pf->buf = &tmp[len];
-		pf->len = MAX_PROBE_BUFFER - len;
-		find_variable(sp_die, pf);
-		len += strlen(pf->buf);
+	tev->nargs = pf->pev->nargs;
+	tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs);
+	if (tev->args == NULL)
+		return -ENOMEM;
+	for (i = 0; i < pf->pev->nargs; i++) {
+		pf->pvar = &pf->pev->args[i];
+		pf->tvar = &tev->args[i];
+		ret = find_variable(sp_die, pf);
+		if (ret != 0)
+			return ret;
 	}
 
 	/* *pf->fb_ops will be cached in libdw. Don't free it. */
 	pf->fb_ops = NULL;
-
-	if (pp->found == MAX_PROBES)
-		die("Too many( > %d) probe point found.\n", MAX_PROBES);
-
-	pp->probes[pp->found] = strdup(tmp);
-	pp->found++;
+	return 0;
 }
 
 /* Find probe point from its line number */
-static void find_probe_point_by_line(struct probe_finder *pf)
+static int find_probe_point_by_line(struct probe_finder *pf)
 {
 	Dwarf_Lines *lines;
 	Dwarf_Line *line;
 	size_t nlines, i;
 	Dwarf_Addr addr;
 	int lineno;
-	int ret;
+	int ret = 0;
 
-	ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
-	DIE_IF(ret != 0);
+	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
+		pr_warning("No source lines found in this CU.\n");
+		return -ENOENT;
+	}
 
-	for (i = 0; i < nlines; i++) {
+	for (i = 0; i < nlines && ret == 0; i++) {
 		line = dwarf_onesrcline(lines, i);
-		dwarf_lineno(line, &lineno);
-		if (lineno != pf->lno)
+		if (dwarf_lineno(line, &lineno) != 0 ||
+		    lineno != pf->lno)
 			continue;
 
 		/* TODO: Get fileno from line, but how? */
 		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
 			continue;
 
-		ret = dwarf_lineaddr(line, &addr);
-		DIE_IF(ret != 0);
+		if (dwarf_lineaddr(line, &addr) != 0) {
+			pr_warning("Failed to get the address of the line.\n");
+			return -ENOENT;
+		}
 		pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
 			 (int)i, lineno, (uintmax_t)addr);
 		pf->addr = addr;
 
-		show_probe_point(NULL, pf);
+		ret = convert_probe_point(NULL, pf);
 		/* Continuing, because target line might be inlined. */
 	}
+	return ret;
 }
 
 /* Find lines which match lazy pattern */
@@ -499,16 +741,27 @@ static int find_lazy_match_lines(struct list_head *head,
 				 const char *fname, const char *pat)
 {
 	char *fbuf, *p1, *p2;
-	int fd, line, nlines = 0;
+	int fd, ret, line, nlines = 0;
 	struct stat st;
 
 	fd = open(fname, O_RDONLY);
-	if (fd < 0)
-		die("failed to open %s", fname);
-	DIE_IF(fstat(fd, &st) < 0);
-	fbuf = malloc(st.st_size + 2);
-	DIE_IF(fbuf == NULL);
-	DIE_IF(read(fd, fbuf, st.st_size) < 0);
+	if (fd < 0) {
+		pr_warning("Failed to open %s: %s\n", fname, strerror(-fd));
+		return fd;
+	}
+
+	ret = fstat(fd, &st);
+	if (ret < 0) {
+		pr_warning("Failed to get the size of %s: %s\n",
+			   fname, strerror(errno));
+		return ret;
+	}
+	fbuf = xmalloc(st.st_size + 2);
+	ret = read(fd, fbuf, st.st_size);
+	if (ret < 0) {
+		pr_warning("Failed to read %s: %s\n", fname, strerror(errno));
+		return ret;
+	}
 	close(fd);
 	fbuf[st.st_size] = '\n';	/* Dummy line */
 	fbuf[st.st_size + 1] = '\0';
@@ -528,7 +781,7 @@ static int find_lazy_match_lines(struct list_head *head,
 }
 
 /* Find probe points from lazy pattern  */
-static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
+static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
 	Dwarf_Lines *lines;
 	Dwarf_Line *line;
@@ -536,37 +789,46 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 	Dwarf_Addr addr;
 	Dwarf_Die die_mem;
 	int lineno;
-	int ret;
+	int ret = 0;
 
 	if (list_empty(&pf->lcache)) {
 		/* Matching lazy line pattern */
 		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
-					    pf->pp->lazy_line);
-		if (ret <= 0)
-			die("No matched lines found in %s.", pf->fname);
+					    pf->pev->point.lazy_line);
+		if (ret == 0) {
+			pr_debug("No matched lines found in %s.\n", pf->fname);
+			return 0;
+		} else if (ret < 0)
+			return ret;
 	}
 
-	ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
-	DIE_IF(ret != 0);
-	for (i = 0; i < nlines; i++) {
+	if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
+		pr_warning("No source lines found in this CU.\n");
+		return -ENOENT;
+	}
+
+	for (i = 0; i < nlines && ret >= 0; i++) {
 		line = dwarf_onesrcline(lines, i);
 
-		dwarf_lineno(line, &lineno);
-		if (!line_list__has_line(&pf->lcache, lineno))
+		if (dwarf_lineno(line, &lineno) != 0 ||
+		    !line_list__has_line(&pf->lcache, lineno))
 			continue;
 
 		/* TODO: Get fileno from line, but how? */
 		if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
 			continue;
 
-		ret = dwarf_lineaddr(line, &addr);
-		DIE_IF(ret != 0);
+		if (dwarf_lineaddr(line, &addr) != 0) {
+			pr_debug("Failed to get the address of line %d.\n",
+				 lineno);
+			continue;
+		}
 		if (sp_die) {
 			/* Address filtering 1: does sp_die include addr? */
 			if (!dwarf_haspc(sp_die, addr))
 				continue;
 			/* Address filtering 2: No child include addr? */
-			if (die_get_inlinefunc(sp_die, addr, &die_mem))
+			if (die_find_inlinefunc(sp_die, addr, &die_mem))
 				continue;
 		}
 
@@ -574,27 +836,44 @@ static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 			 (int)i, lineno, (unsigned long long)addr);
 		pf->addr = addr;
 
-		show_probe_point(sp_die, pf);
+		ret = convert_probe_point(sp_die, pf);
 		/* Continuing, because target line might be inlined. */
 	}
 	/* TODO: deallocate lines, but how? */
+	return ret;
 }
 
+/* Callback parameter with return value */
+struct dwarf_callback_param {
+	void *data;
+	int retval;
+};
+
 static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	struct probe_finder *pf = (struct probe_finder *)data;
-	struct probe_point *pp = pf->pp;
+	struct dwarf_callback_param *param = data;
+	struct probe_finder *pf = param->data;
+	struct perf_probe_point *pp = &pf->pev->point;
+	Dwarf_Addr addr;
 
 	if (pp->lazy_line)
-		find_probe_point_lazy(in_die, pf);
+		param->retval = find_probe_point_lazy(in_die, pf);
 	else {
 		/* Get probe address */
-		pf->addr = die_get_entrypc(in_die);
+		if (dwarf_entrypc(in_die, &addr) != 0) {
+			pr_warning("Failed to get entry pc of %s.\n",
+				   dwarf_diename(in_die));
+			param->retval = -ENOENT;
+			return DWARF_CB_ABORT;
+		}
+		pf->addr = addr;
 		pf->addr += pp->offset;
 		pr_debug("found inline addr: 0x%jx\n",
 			 (uintmax_t)pf->addr);
 
-		show_probe_point(in_die, pf);
+		param->retval = convert_probe_point(in_die, pf);
+		if (param->retval < 0)
+			return DWARF_CB_ABORT;
 	}
 
 	return DWARF_CB_OK;
@@ -603,59 +882,88 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
 /* Search function from function name */
 static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 {
-	struct probe_finder *pf = (struct probe_finder *)data;
-	struct probe_point *pp = pf->pp;
+	struct dwarf_callback_param *param = data;
+	struct probe_finder *pf = param->data;
+	struct perf_probe_point *pp = &pf->pev->point;
 
 	/* Check tag and diename */
 	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
 	    die_compare_name(sp_die, pp->function) != 0)
-		return 0;
+		return DWARF_CB_OK;
 
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
 		pf->lno += pp->line;
-		find_probe_point_by_line(pf);
+		param->retval = find_probe_point_by_line(pf);
 	} else if (!dwarf_func_inline(sp_die)) {
 		/* Real function */
 		if (pp->lazy_line)
-			find_probe_point_lazy(sp_die, pf);
+			param->retval = find_probe_point_lazy(sp_die, pf);
 		else {
-			pf->addr = die_get_entrypc(sp_die);
+			if (dwarf_entrypc(sp_die, &pf->addr) != 0) {
+				pr_warning("Failed to get entry pc of %s.\n",
+					   dwarf_diename(sp_die));
+				param->retval = -ENOENT;
+				return DWARF_CB_ABORT;
+			}
 			pf->addr += pp->offset;
 			/* TODO: Check the address in this function */
-			show_probe_point(sp_die, pf);
+			param->retval = convert_probe_point(sp_die, pf);
 		}
-	} else
+	} else {
+		struct dwarf_callback_param _param = {.data = (void *)pf,
+						      .retval = 0};
 		/* Inlined function: search instances */
-		dwarf_func_inline_instances(sp_die, probe_point_inline_cb, pf);
+		dwarf_func_inline_instances(sp_die, probe_point_inline_cb,
+					    &_param);
+		param->retval = _param.retval;
+	}
 
-	return 1; /* Exit; no same symbol in this CU. */
+	return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
 }
 
-static void find_probe_point_by_func(struct probe_finder *pf)
+static int find_probe_point_by_func(struct probe_finder *pf)
 {
-	dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0);
+	struct dwarf_callback_param _param = {.data = (void *)pf,
+					      .retval = 0};
+	dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, &_param, 0);
+	return _param.retval;
 }
 
-/* Find a probe point */
-int find_probe_point(int fd, struct probe_point *pp)
+/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
+int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
+			     struct kprobe_trace_event **tevs, int max_tevs)
 {
-	struct probe_finder pf = {.pp = pp};
+	struct probe_finder pf = {.pev = pev, .max_tevs = max_tevs};
+	struct perf_probe_point *pp = &pev->point;
 	Dwarf_Off off, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
 	Dwarf *dbg;
+	int ret = 0;
+
+	pf.tevs = zalloc(sizeof(struct kprobe_trace_event) * max_tevs);
+	if (pf.tevs == NULL)
+		return -ENOMEM;
+	*tevs = pf.tevs;
+	pf.ntevs = 0;
 
 	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg)
-		return -ENOENT;
+	if (!dbg) {
+		pr_warning("No dwarf info found in the vmlinux - "
+			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		return -EBADF;
+	}
+
+	/* Get the call frame information from this dwarf */
+	pf.cfi = dwarf_getcfi(dbg);
 
-	pp->found = 0;
 	off = 0;
 	line_list__init(&pf.lcache);
 	/* Loop on CUs (Compilation Unit) */
-	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
+	while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) &&
+	       ret >= 0) {
 		/* Get the DIE(Debugging Information Entry) of this CU */
 		diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die);
 		if (!diep)
@@ -669,12 +977,12 @@ int find_probe_point(int fd, struct probe_point *pp)
 
 		if (!pp->file || pf.fname) {
 			if (pp->function)
-				find_probe_point_by_func(&pf);
+				ret = find_probe_point_by_func(&pf);
 			else if (pp->lazy_line)
-				find_probe_point_lazy(NULL, &pf);
+				ret = find_probe_point_lazy(NULL, &pf);
 			else {
 				pf.lno = pp->line;
-				find_probe_point_by_line(&pf);
+				ret = find_probe_point_by_line(&pf);
 			}
 		}
 		off = noff;
@@ -682,41 +990,169 @@ int find_probe_point(int fd, struct probe_point *pp)
 	line_list__free(&pf.lcache);
 	dwarf_end(dbg);
 
-	return pp->found;
+	return (ret < 0) ? ret : pf.ntevs;
+}
+
+/* Reverse search */
+int find_perf_probe_point(int fd, unsigned long addr,
+			  struct perf_probe_point *ppt)
+{
+	Dwarf_Die cudie, spdie, indie;
+	Dwarf *dbg;
+	Dwarf_Line *line;
+	Dwarf_Addr laddr, eaddr;
+	const char *tmp;
+	int lineno, ret = 0;
+	bool found = false;
+
+	dbg = dwarf_begin(fd, DWARF_C_READ);
+	if (!dbg)
+		return -EBADF;
+
+	/* Find cu die */
+	if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	/* Find a corresponding line */
+	line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
+	if (line) {
+		if (dwarf_lineaddr(line, &laddr) == 0 &&
+		    (Dwarf_Addr)addr == laddr &&
+		    dwarf_lineno(line, &lineno) == 0) {
+			tmp = dwarf_linesrc(line, NULL, NULL);
+			if (tmp) {
+				ppt->line = lineno;
+				ppt->file = strdup(tmp);
+				if (ppt->file == NULL) {
+					ret = -ENOMEM;
+					goto end;
+				}
+				found = true;
+			}
+		}
+	}
+
+	/* Find a corresponding function */
+	if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+		tmp = dwarf_diename(&spdie);
+		if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
+			goto end;
+
+		if (ppt->line) {
+			if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+						&indie)) {
+				/* addr in an inline function */
+				tmp = dwarf_diename(&indie);
+				if (!tmp)
+					goto end;
+				ret = dwarf_decl_line(&indie, &lineno);
+			} else {
+				if (eaddr == addr) {	/* Function entry */
+					lineno = ppt->line;
+					ret = 0;
+				} else
+					ret = dwarf_decl_line(&spdie, &lineno);
+			}
+			if (ret == 0) {
+				/* Make a relative line number */
+				ppt->line -= lineno;
+				goto found;
+			}
+		}
+		/* We don't have a line number, let's use offset */
+		ppt->offset = addr - (unsigned long)eaddr;
+found:
+		ppt->function = strdup(tmp);
+		if (ppt->function == NULL) {
+			ret = -ENOMEM;
+			goto end;
+		}
+		found = true;
+	}
+
+end:
+	dwarf_end(dbg);
+	if (ret >= 0)
+		ret = found ? 1 : 0;
+	return ret;
+}
+
+/* Add a line and store the src path */
+static int line_range_add_line(const char *src, unsigned int lineno,
+			       struct line_range *lr)
+{
+	/* Copy real path */
+	if (!lr->path) {
+		lr->path = strdup(src);
+		if (lr->path == NULL)
+			return -ENOMEM;
+	}
+	return line_list__add_line(&lr->line_list, lineno);
+}
+
+/* Search function declaration lines */
+static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data)
+{
+	struct dwarf_callback_param *param = data;
+	struct line_finder *lf = param->data;
+	const char *src;
+	int lineno;
+
+	src = dwarf_decl_file(sp_die);
+	if (src && strtailcmp(src, lf->fname) != 0)
+		return DWARF_CB_OK;
+
+	if (dwarf_decl_line(sp_die, &lineno) != 0 ||
+	    (lf->lno_s > lineno || lf->lno_e < lineno))
+		return DWARF_CB_OK;
+
+	param->retval = line_range_add_line(src, lineno, lf->lr);
+	if (param->retval < 0)
+		return DWARF_CB_ABORT;
+	return DWARF_CB_OK;
+}
+
+static int find_line_range_func_decl_lines(struct line_finder *lf)
+{
+	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
+	dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, &param, 0);
+	return param.retval;
 }
 
 /* Find line range from its line number */
-static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
+static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
 	Dwarf_Lines *lines;
 	Dwarf_Line *line;
 	size_t nlines, i;
 	Dwarf_Addr addr;
-	int lineno;
-	int ret;
+	int lineno, ret = 0;
 	const char *src;
 	Dwarf_Die die_mem;
 
 	line_list__init(&lf->lr->line_list);
-	ret = dwarf_getsrclines(&lf->cu_die, &lines, &nlines);
-	DIE_IF(ret != 0);
+	if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
+		pr_warning("No source lines found in this CU.\n");
+		return -ENOENT;
+	}
 
+	/* Search probable lines on lines list */
 	for (i = 0; i < nlines; i++) {
 		line = dwarf_onesrcline(lines, i);
-		ret = dwarf_lineno(line, &lineno);
-		DIE_IF(ret != 0);
-		if (lf->lno_s > lineno || lf->lno_e < lineno)
+		if (dwarf_lineno(line, &lineno) != 0 ||
+		    (lf->lno_s > lineno || lf->lno_e < lineno))
 			continue;
 
 		if (sp_die) {
 			/* Address filtering 1: does sp_die include addr? */
-			ret = dwarf_lineaddr(line, &addr);
-			DIE_IF(ret != 0);
-			if (!dwarf_haspc(sp_die, addr))
+			if (dwarf_lineaddr(line, &addr) != 0 ||
+			    !dwarf_haspc(sp_die, addr))
 				continue;
 
 			/* Address filtering 2: No child include addr? */
-			if (die_get_inlinefunc(sp_die, addr, &die_mem))
+			if (die_find_inlinefunc(sp_die, addr, &die_mem))
 				continue;
 		}
 
@@ -725,30 +1161,49 @@ static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 		if (strtailcmp(src, lf->fname) != 0)
 			continue;
 
-		/* Copy real path */
-		if (!lf->lr->path)
-			lf->lr->path = strdup(src);
-		line_list__add_line(&lf->lr->line_list, (unsigned int)lineno);
+		ret = line_range_add_line(src, lineno, lf->lr);
+		if (ret < 0)
+			return ret;
 	}
+
+	/*
+	 * Dwarf lines doesn't include function declarations. We have to
+	 * check functions list or given function.
+	 */
+	if (sp_die) {
+		src = dwarf_decl_file(sp_die);
+		if (src && dwarf_decl_line(sp_die, &lineno) == 0 &&
+		    (lf->lno_s <= lineno && lf->lno_e >= lineno))
+			ret = line_range_add_line(src, lineno, lf->lr);
+	} else
+		ret = find_line_range_func_decl_lines(lf);
+
 	/* Update status */
-	if (!list_empty(&lf->lr->line_list))
-		lf->found = 1;
+	if (ret >= 0)
+		if (!list_empty(&lf->lr->line_list))
+			ret = lf->found = 1;
+		else
+			ret = 0;	/* Lines are not found */
 	else {
 		free(lf->lr->path);
 		lf->lr->path = NULL;
 	}
+	return ret;
 }
 
 static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 {
-	find_line_range_by_line(in_die, (struct line_finder *)data);
+	struct dwarf_callback_param *param = data;
+
+	param->retval = find_line_range_by_line(in_die, param->data);
 	return DWARF_CB_ABORT;	/* No need to find other instances */
 }
 
 /* Search function from function name */
 static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
-	struct line_finder *lf = (struct line_finder *)data;
+	struct dwarf_callback_param *param = data;
+	struct line_finder *lf = param->data;
 	struct line_range *lr = lf->lr;
 
 	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
@@ -757,44 +1212,55 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
 		lf->lno_s = lr->offset + lr->start;
-		if (!lr->end)
+		if (lf->lno_s < 0)	/* Overflow */
+			lf->lno_s = INT_MAX;
+		lf->lno_e = lr->offset + lr->end;
+		if (lf->lno_e < 0)	/* Overflow */
 			lf->lno_e = INT_MAX;
-		else
-			lf->lno_e = lr->offset + lr->end;
+		pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e);
 		lr->start = lf->lno_s;
 		lr->end = lf->lno_e;
-		if (dwarf_func_inline(sp_die))
+		if (dwarf_func_inline(sp_die)) {
+			struct dwarf_callback_param _param;
+			_param.data = (void *)lf;
+			_param.retval = 0;
 			dwarf_func_inline_instances(sp_die,
-						    line_range_inline_cb, lf);
-		else
-			find_line_range_by_line(sp_die, lf);
-		return 1;
+						    line_range_inline_cb,
+						    &_param);
+			param->retval = _param.retval;
+		} else
+			param->retval = find_line_range_by_line(sp_die, lf);
+		return DWARF_CB_ABORT;
 	}
-	return 0;
+	return DWARF_CB_OK;
 }
 
-static void find_line_range_by_func(struct line_finder *lf)
+static int find_line_range_by_func(struct line_finder *lf)
 {
-	dwarf_getfuncs(&lf->cu_die, line_range_search_cb, lf, 0);
+	struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
+	dwarf_getfuncs(&lf->cu_die, line_range_search_cb, &param, 0);
+	return param.retval;
 }
 
 int find_line_range(int fd, struct line_range *lr)
 {
 	struct line_finder lf = {.lr = lr, .found = 0};
-	int ret;
+	int ret = 0;
 	Dwarf_Off off = 0, noff;
 	size_t cuhl;
 	Dwarf_Die *diep;
 	Dwarf *dbg;
 
 	dbg = dwarf_begin(fd, DWARF_C_READ);
-	if (!dbg)
-		return -ENOENT;
+	if (!dbg) {
+		pr_warning("No dwarf info found in the vmlinux - "
+			"please rebuild with CONFIG_DEBUG_INFO=y.\n");
+		return -EBADF;
+	}
 
 	/* Loop on CUs (Compilation Unit) */
-	while (!lf.found) {
-		ret = dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL);
-		if (ret != 0)
+	while (!lf.found && ret >= 0) {
+		if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
 			break;
 
 		/* Get the DIE(Debugging Information Entry) of this CU */
@@ -810,20 +1276,18 @@ int find_line_range(int fd, struct line_range *lr)
 
 		if (!lr->file || lf.fname) {
 			if (lr->function)
-				find_line_range_by_func(&lf);
+				ret = find_line_range_by_func(&lf);
 			else {
 				lf.lno_s = lr->start;
-				if (!lr->end)
-					lf.lno_e = INT_MAX;
-				else
-					lf.lno_e = lr->end;
-				find_line_range_by_line(NULL, &lf);
+				lf.lno_e = lr->end;
+				ret = find_line_range_by_line(NULL, &lf);
 			}
 		}
 		off = noff;
 	}
 	pr_debug("path: %lx\n", (unsigned long)lr->path);
 	dwarf_end(dbg);
-	return lf.found;
+
+	return (ret < 0) ? ret : lf.found;
 }
 
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 21f7354397b4..66f1980e3855 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "util.h"
+#include "probe-event.h"
 
 #define MAX_PATH_LEN		 256
 #define MAX_PROBE_BUFFER	1024
@@ -14,67 +15,39 @@ static inline int is_c_varname(const char *name)
 	return isalpha(name[0]) || name[0] == '_';
 }
 
-struct probe_point {
-	char			*event;			/* Event name */
-	char			*group;			/* Event group */
+#ifdef DWARF_SUPPORT
+/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */
+extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev,
+				    struct kprobe_trace_event **tevs,
+				    int max_tevs);
 
-	/* Inputs */
-	char			*file;			/* File name */
-	int			line;			/* Line number */
-	char			*lazy_line;		/* Lazy line pattern */
+/* Find a perf_probe_point from debuginfo */
+extern int find_perf_probe_point(int fd, unsigned long addr,
+				 struct perf_probe_point *ppt);
 
-	char			*function;		/* Function name */
-	int			offset;			/* Offset bytes */
-
-	int			nr_args;		/* Number of arguments */
-	char			**args;			/* Arguments */
-
-	int			retprobe;		/* Return probe */
-
-	/* Output */
-	int			found;			/* Number of found probe points */
-	char			*probes[MAX_PROBES];	/* Output buffers (will be allocated)*/
-};
-
-/* Line number container */
-struct line_node {
-	struct list_head	list;
-	unsigned int		line;
-};
-
-/* Line range */
-struct line_range {
-	char			*file;			/* File name */
-	char			*function;		/* Function name */
-	unsigned int		start;			/* Start line number */
-	unsigned int		end;			/* End line number */
-	int			offset;			/* Start line offset */
-	char			*path;			/* Real path name */
-	struct list_head	line_list;		/* Visible lines */
-};
-
-#ifndef NO_DWARF_SUPPORT
-extern int find_probe_point(int fd, struct probe_point *pp);
 extern int find_line_range(int fd, struct line_range *lr);
 
 #include <dwarf.h>
 #include <libdw.h>
 
 struct probe_finder {
-	struct probe_point	*pp;		/* Target probe point */
+	struct perf_probe_event	*pev;		/* Target probe event */
+	struct kprobe_trace_event *tevs;	/* Result trace events */
+	int			ntevs;		/* Number of trace events */
+	int			max_tevs;	/* Max number of trace events */
 
 	/* For function searching */
-	Dwarf_Addr		addr;		/* Address */
-	const char		*fname;		/* File name */
 	int			lno;		/* Line number */
+	Dwarf_Addr		addr;		/* Address */
+	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
+	struct list_head	lcache;		/* Line cache for lazy match */
 
 	/* For variable searching */
+	Dwarf_CFI		*cfi;		/* Call Frame Information */
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
-	const char		*var;		/* Current variable name */
-	char			*buf;		/* Current output buffer */
-	int			len;		/* Length of output buffer */
-	struct list_head	lcache;		/* Line cache for lazy match */
+	struct perf_probe_arg	*pvar;		/* Current target variable */
+	struct kprobe_trace_arg	*tvar;		/* Current result variable */
 };
 
 struct line_finder {
@@ -87,6 +60,6 @@ struct line_finder {
 	int			found;
 };
 
-#endif /* NO_DWARF_SUPPORT */
+#endif /* DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
new file mode 100644
index 000000000000..13d36faf64eb
--- /dev/null
+++ b/tools/perf/util/pstack.c
@@ -0,0 +1,75 @@
+/*
+ * Simple pointer stack
+ *
+ * (c) 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "util.h"
+#include "pstack.h"
+#include <linux/kernel.h>
+#include <stdlib.h>
+
+struct pstack {
+	unsigned short	top;
+	unsigned short	max_nr_entries;
+	void		*entries[0];
+};
+
+struct pstack *pstack__new(unsigned short max_nr_entries)
+{
+	struct pstack *self = zalloc((sizeof(*self) +
+				     max_nr_entries * sizeof(void *)));
+	if (self != NULL)
+		self->max_nr_entries = max_nr_entries;
+	return self;
+}
+
+void pstack__delete(struct pstack *self)
+{
+	free(self);
+}
+
+bool pstack__empty(const struct pstack *self)
+{
+	return self->top == 0;
+}
+
+void pstack__remove(struct pstack *self, void *key)
+{
+	unsigned short i = self->top, last_index = self->top - 1;
+
+	while (i-- != 0) {
+		if (self->entries[i] == key) {
+			if (i < last_index)
+				memmove(self->entries + i,
+					self->entries + i + 1,
+					(last_index - i) * sizeof(void *));
+			--self->top;
+			return;
+		}
+	}
+	pr_err("%s: %p not on the pstack!\n", __func__, key);
+}
+
+void pstack__push(struct pstack *self, void *key)
+{
+	if (self->top == self->max_nr_entries) {
+		pr_err("%s: top=%d, overflow!\n", __func__, self->top);
+		return;
+	}
+	self->entries[self->top++] = key;
+}
+
+void *pstack__pop(struct pstack *self)
+{
+	void *ret;
+
+	if (self->top == 0) {
+		pr_err("%s: underflow!\n", __func__);
+		return NULL;
+	}
+
+	ret = self->entries[--self->top];
+	self->entries[self->top] = NULL;
+	return ret;
+}
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
new file mode 100644
index 000000000000..5ad07023504b
--- /dev/null
+++ b/tools/perf/util/pstack.h
@@ -0,0 +1,12 @@
+#ifndef _PERF_PSTACK_
+#define _PERF_PSTACK_
+
+struct pstack;
+struct pstack *pstack__new(unsigned short max_nr_entries);
+void pstack__delete(struct pstack *self);
+bool pstack__empty(const struct pstack *self);
+void pstack__remove(struct pstack *self, void *key);
+void pstack__push(struct pstack *self, void *key);
+void *pstack__pop(struct pstack *self);
+
+#endif /* _PERF_PSTACK_ */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 5376378e0cfc..b059dc50cc2d 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -371,7 +371,6 @@ static int perl_start_script(const char *script, int argc, const char **argv)
 	run_start_sub();
 
 	free(command_line);
-	fprintf(stderr, "perf trace started with Perl script %s\n\n", script);
 	return 0;
 error:
 	perl_free(my_perl);
@@ -394,8 +393,6 @@ static int perl_stop_script(void)
 	perl_destruct(my_perl);
 	perl_free(my_perl);
 
-	fprintf(stderr, "\nperf trace Perl script stopped\n");
-
 	return 0;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 6a72f14c5986..81f39cab3aaa 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -374,8 +374,6 @@ static int python_start_script(const char *script, int argc, const char **argv)
 	}
 
 	free(command_line);
-	fprintf(stderr, "perf trace started with Python script %s\n\n",
-		script);
 
 	return err;
 error:
@@ -407,8 +405,6 @@ out:
 	Py_XDECREF(main_module);
 	Py_Finalize();
 
-	fprintf(stderr, "\nperf trace Python script stopped\n");
-
 	return err;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index eed1cb889008..25bfca4f10f0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,16 @@ static int perf_session__open(struct perf_session *self, bool force)
 {
 	struct stat input_stat;
 
+	if (!strcmp(self->filename, "-")) {
+		self->fd_pipe = true;
+		self->fd = STDIN_FILENO;
+
+		if (perf_header__read(self, self->fd) < 0)
+			pr_err("incompatible file format");
+
+		return 0;
+	}
+
 	self->fd = open(self->filename, O_RDONLY);
 	if (self->fd < 0) {
 		pr_err("failed to open file: %s", self->filename);
@@ -38,7 +48,7 @@ static int perf_session__open(struct perf_session *self, bool force)
 		goto out_close;
 	}
 
-	if (perf_header__read(&self->header, self->fd) < 0) {
+	if (perf_header__read(self, self->fd) < 0) {
 		pr_err("incompatible file format");
 		goto out_close;
 	}
@@ -52,12 +62,21 @@ out_close:
 	return -1;
 }
 
-static inline int perf_session__create_kernel_maps(struct perf_session *self)
+void perf_session__update_sample_type(struct perf_session *self)
+{
+	self->sample_type = perf_header__sample_type(&self->header);
+}
+
+int perf_session__create_kernel_maps(struct perf_session *self)
 {
-	return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
+	int ret = machine__create_kernel_maps(&self->host_machine);
+
+	if (ret >= 0)
+		ret = machines__create_guest_kernel_maps(&self->machines);
+	return ret;
 }
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force)
+struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe)
 {
 	size_t len = filename ? strlen(filename) + 1 : 0;
 	struct perf_session *self = zalloc(sizeof(*self) + len);
@@ -70,13 +89,15 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 
 	memcpy(self->filename, filename, len);
 	self->threads = RB_ROOT;
-	self->stats_by_id = RB_ROOT;
+	self->hists_tree = RB_ROOT;
 	self->last_match = NULL;
 	self->mmap_window = 32;
 	self->cwd = NULL;
 	self->cwdlen = 0;
-	self->unknown_events = 0;
-	map_groups__init(&self->kmaps);
+	self->machines = RB_ROOT;
+	self->repipe = repipe;
+	INIT_LIST_HEAD(&self->ordered_samples.samples_head);
+	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
 
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
@@ -90,7 +111,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 			goto out_delete;
 	}
 
-	self->sample_type = perf_header__sample_type(&self->header);
+	perf_session__update_sample_type(self);
 out:
 	return self;
 out_free:
@@ -117,22 +138,17 @@ static bool symbol__match_parent_regex(struct symbol *sym)
 	return 0;
 }
 
-struct symbol **perf_session__resolve_callchain(struct perf_session *self,
-						struct thread *thread,
-						struct ip_callchain *chain,
-						struct symbol **parent)
+struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
+						   struct thread *thread,
+						   struct ip_callchain *chain,
+						   struct symbol **parent)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	struct symbol **syms = NULL;
 	unsigned int i;
+	struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
 
-	if (symbol_conf.use_callchain) {
-		syms = calloc(chain->nr, sizeof(*syms));
-		if (!syms) {
-			fprintf(stderr, "Can't allocate memory for symbols\n");
-			exit(-1);
-		}
-	}
+	if (!syms)
+		return NULL;
 
 	for (i = 0; i < chain->nr; i++) {
 		u64 ip = chain->ips[i];
@@ -152,15 +168,17 @@ struct symbol **perf_session__resolve_callchain(struct perf_session *self,
 			continue;
 		}
 
+		al.filtered = false;
 		thread__find_addr_location(thread, self, cpumode,
-					   MAP__FUNCTION, ip, &al, NULL);
+				MAP__FUNCTION, thread->pid, ip, &al, NULL);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
 			    symbol__match_parent_regex(al.sym))
 				*parent = al.sym;
 			if (!symbol_conf.use_callchain)
 				break;
-			syms[i] = al.sym;
+			syms[i].map = al.map;
+			syms[i].sym = al.sym;
 		}
 	}
 
@@ -174,6 +192,18 @@ static int process_event_stub(event_t *event __used,
 	return 0;
 }
 
+static int process_finished_round_stub(event_t *event __used,
+				       struct perf_session *session __used,
+				       struct perf_event_ops *ops __used)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int process_finished_round(event_t *event,
+				  struct perf_session *session,
+				  struct perf_event_ops *ops);
+
 static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 {
 	if (handler->sample == NULL)
@@ -194,29 +224,20 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 		handler->throttle = process_event_stub;
 	if (handler->unthrottle == NULL)
 		handler->unthrottle = process_event_stub;
-}
-
-static const char *event__name[] = {
-	[0]			 = "TOTAL",
-	[PERF_RECORD_MMAP]	 = "MMAP",
-	[PERF_RECORD_LOST]	 = "LOST",
-	[PERF_RECORD_COMM]	 = "COMM",
-	[PERF_RECORD_EXIT]	 = "EXIT",
-	[PERF_RECORD_THROTTLE]	 = "THROTTLE",
-	[PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-	[PERF_RECORD_FORK]	 = "FORK",
-	[PERF_RECORD_READ]	 = "READ",
-	[PERF_RECORD_SAMPLE]	 = "SAMPLE",
-};
-
-unsigned long event__total[PERF_RECORD_MAX];
-
-void event__print_totals(void)
-{
-	int i;
-	for (i = 0; i < PERF_RECORD_MAX; ++i)
-		pr_info("%10s events: %10ld\n",
-			event__name[i], event__total[i]);
+	if (handler->attr == NULL)
+		handler->attr = process_event_stub;
+	if (handler->event_type == NULL)
+		handler->event_type = process_event_stub;
+	if (handler->tracing_data == NULL)
+		handler->tracing_data = process_event_stub;
+	if (handler->build_id == NULL)
+		handler->build_id = process_event_stub;
+	if (handler->finished_round == NULL) {
+		if (handler->ordered_samples)
+			handler->finished_round = process_finished_round;
+		else
+			handler->finished_round = process_finished_round_stub;
+	}
 }
 
 void mem_bswap_64(void *src, int byte_size)
@@ -270,6 +291,37 @@ static void event__read_swap(event_t *self)
 	self->read.id		= bswap_64(self->read.id);
 }
 
+static void event__attr_swap(event_t *self)
+{
+	size_t size;
+
+	self->attr.attr.type		= bswap_32(self->attr.attr.type);
+	self->attr.attr.size		= bswap_32(self->attr.attr.size);
+	self->attr.attr.config		= bswap_64(self->attr.attr.config);
+	self->attr.attr.sample_period	= bswap_64(self->attr.attr.sample_period);
+	self->attr.attr.sample_type	= bswap_64(self->attr.attr.sample_type);
+	self->attr.attr.read_format	= bswap_64(self->attr.attr.read_format);
+	self->attr.attr.wakeup_events	= bswap_32(self->attr.attr.wakeup_events);
+	self->attr.attr.bp_type		= bswap_32(self->attr.attr.bp_type);
+	self->attr.attr.bp_addr		= bswap_64(self->attr.attr.bp_addr);
+	self->attr.attr.bp_len		= bswap_64(self->attr.attr.bp_len);
+
+	size = self->header.size;
+	size -= (void *)&self->attr.id - (void *)self;
+	mem_bswap_64(self->attr.id, size);
+}
+
+static void event__event_type_swap(event_t *self)
+{
+	self->event_type.event_type.event_id =
+		bswap_64(self->event_type.event_type.event_id);
+}
+
+static void event__tracing_data_swap(event_t *self)
+{
+	self->tracing_data.size = bswap_32(self->tracing_data.size);
+}
+
 typedef void (*event__swap_op)(event_t *self);
 
 static event__swap_op event__swap_ops[] = {
@@ -280,9 +332,212 @@ static event__swap_op event__swap_ops[] = {
 	[PERF_RECORD_LOST]   = event__all64_swap,
 	[PERF_RECORD_READ]   = event__read_swap,
 	[PERF_RECORD_SAMPLE] = event__all64_swap,
-	[PERF_RECORD_MAX]    = NULL,
+	[PERF_RECORD_HEADER_ATTR]   = event__attr_swap,
+	[PERF_RECORD_HEADER_EVENT_TYPE]   = event__event_type_swap,
+	[PERF_RECORD_HEADER_TRACING_DATA]   = event__tracing_data_swap,
+	[PERF_RECORD_HEADER_BUILD_ID]   = NULL,
+	[PERF_RECORD_HEADER_MAX]    = NULL,
 };
 
+struct sample_queue {
+	u64			timestamp;
+	struct sample_event	*event;
+	struct list_head	list;
+};
+
+static void flush_sample_queue(struct perf_session *s,
+			       struct perf_event_ops *ops)
+{
+	struct list_head *head = &s->ordered_samples.samples_head;
+	u64 limit = s->ordered_samples.next_flush;
+	struct sample_queue *tmp, *iter;
+
+	if (!ops->ordered_samples || !limit)
+		return;
+
+	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (iter->timestamp > limit)
+			return;
+
+		if (iter == s->ordered_samples.last_inserted)
+			s->ordered_samples.last_inserted = NULL;
+
+		ops->sample((event_t *)iter->event, s);
+
+		s->ordered_samples.last_flush = iter->timestamp;
+		list_del(&iter->list);
+		free(iter->event);
+		free(iter);
+	}
+}
+
+/*
+ * When perf record finishes a pass on every buffers, it records this pseudo
+ * event.
+ * We record the max timestamp t found in the pass n.
+ * Assuming these timestamps are monotonic across cpus, we know that if
+ * a buffer still has events with timestamps below t, they will be all
+ * available and then read in the pass n + 1.
+ * Hence when we start to read the pass n + 2, we can safely flush every
+ * events with timestamps below t.
+ *
+ *    ============ PASS n =================
+ *       CPU 0         |   CPU 1
+ *                     |
+ *    cnt1 timestamps  |   cnt2 timestamps
+ *          1          |         2
+ *          2          |         3
+ *          -          |         4  <--- max recorded
+ *
+ *    ============ PASS n + 1 ==============
+ *       CPU 0         |   CPU 1
+ *                     |
+ *    cnt1 timestamps  |   cnt2 timestamps
+ *          3          |         5
+ *          4          |         6
+ *          5          |         7 <---- max recorded
+ *
+ *      Flush every events below timestamp 4
+ *
+ *    ============ PASS n + 2 ==============
+ *       CPU 0         |   CPU 1
+ *                     |
+ *    cnt1 timestamps  |   cnt2 timestamps
+ *          6          |         8
+ *          7          |         9
+ *          -          |         10
+ *
+ *      Flush every events below timestamp 7
+ *      etc...
+ */
+static int process_finished_round(event_t *event __used,
+				  struct perf_session *session,
+				  struct perf_event_ops *ops)
+{
+	flush_sample_queue(session, ops);
+	session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
+
+	return 0;
+}
+
+static void __queue_sample_end(struct sample_queue *new, struct list_head *head)
+{
+	struct sample_queue *iter;
+
+	list_for_each_entry_reverse(iter, head, list) {
+		if (iter->timestamp < new->timestamp) {
+			list_add(&new->list, &iter->list);
+			return;
+		}
+	}
+
+	list_add(&new->list, head);
+}
+
+static void __queue_sample_before(struct sample_queue *new,
+				  struct sample_queue *iter,
+				  struct list_head *head)
+{
+	list_for_each_entry_continue_reverse(iter, head, list) {
+		if (iter->timestamp < new->timestamp) {
+			list_add(&new->list, &iter->list);
+			return;
+		}
+	}
+
+	list_add(&new->list, head);
+}
+
+static void __queue_sample_after(struct sample_queue *new,
+				 struct sample_queue *iter,
+				 struct list_head *head)
+{
+	list_for_each_entry_continue(iter, head, list) {
+		if (iter->timestamp > new->timestamp) {
+			list_add_tail(&new->list, &iter->list);
+			return;
+		}
+	}
+	list_add_tail(&new->list, head);
+}
+
+/* The queue is ordered by time */
+static void __queue_sample_event(struct sample_queue *new,
+				 struct perf_session *s)
+{
+	struct sample_queue *last_inserted = s->ordered_samples.last_inserted;
+	struct list_head *head = &s->ordered_samples.samples_head;
+
+
+	if (!last_inserted) {
+		__queue_sample_end(new, head);
+		return;
+	}
+
+	/*
+	 * Most of the time the current event has a timestamp
+	 * very close to the last event inserted, unless we just switched
+	 * to another event buffer. Having a sorting based on a list and
+	 * on the last inserted event that is close to the current one is
+	 * probably more efficient than an rbtree based sorting.
+	 */
+	if (last_inserted->timestamp >= new->timestamp)
+		__queue_sample_before(new, last_inserted, head);
+	else
+		__queue_sample_after(new, last_inserted, head);
+}
+
+static int queue_sample_event(event_t *event, struct sample_data *data,
+			      struct perf_session *s)
+{
+	u64 timestamp = data->time;
+	struct sample_queue *new;
+
+
+	if (timestamp < s->ordered_samples.last_flush) {
+		printf("Warning: Timestamp below last timeslice flush\n");
+		return -EINVAL;
+	}
+
+	new = malloc(sizeof(*new));
+	if (!new)
+		return -ENOMEM;
+
+	new->timestamp = timestamp;
+
+	new->event = malloc(event->header.size);
+	if (!new->event) {
+		free(new);
+		return -ENOMEM;
+	}
+
+	memcpy(new->event, event, event->header.size);
+
+	__queue_sample_event(new, s);
+	s->ordered_samples.last_inserted = new;
+
+	if (new->timestamp > s->ordered_samples.max_timestamp)
+		s->ordered_samples.max_timestamp = new->timestamp;
+
+	return 0;
+}
+
+static int perf_session__process_sample(event_t *event, struct perf_session *s,
+					struct perf_event_ops *ops)
+{
+	struct sample_data data;
+
+	if (!ops->ordered_samples)
+		return ops->sample(event, s);
+
+	bzero(&data, sizeof(struct sample_data));
+	event__parse_sample(event, s->sample_type, &data);
+
+	queue_sample_event(event, &data, s);
+
+	return 0;
+}
+
 static int perf_session__process_event(struct perf_session *self,
 				       event_t *event,
 				       struct perf_event_ops *ops,
@@ -290,12 +545,11 @@ static int perf_session__process_event(struct perf_session *self,
 {
 	trace_event(event);
 
-	if (event->header.type < PERF_RECORD_MAX) {
+	if (event->header.type < PERF_RECORD_HEADER_MAX) {
 		dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
 			    offset + head, event->header.size,
 			    event__name[event->header.type]);
-		++event__total[0];
-		++event__total[event->header.type];
+		hists__inc_nr_events(&self->hists, event->header.type);
 	}
 
 	if (self->header.needs_swap && event__swap_ops[event->header.type])
@@ -303,7 +557,7 @@ static int perf_session__process_event(struct perf_session *self,
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		return ops->sample(event, self);
+		return perf_session__process_sample(event, self, ops);
 	case PERF_RECORD_MMAP:
 		return ops->mmap(event, self);
 	case PERF_RECORD_COMM:
@@ -320,8 +574,20 @@ static int perf_session__process_event(struct perf_session *self,
 		return ops->throttle(event, self);
 	case PERF_RECORD_UNTHROTTLE:
 		return ops->unthrottle(event, self);
+	case PERF_RECORD_HEADER_ATTR:
+		return ops->attr(event, self);
+	case PERF_RECORD_HEADER_EVENT_TYPE:
+		return ops->event_type(event, self);
+	case PERF_RECORD_HEADER_TRACING_DATA:
+		/* setup for reading amidst mmap */
+		lseek(self->fd, offset + head, SEEK_SET);
+		return ops->tracing_data(event, self);
+	case PERF_RECORD_HEADER_BUILD_ID:
+		return ops->build_id(event, self);
+	case PERF_RECORD_FINISHED_ROUND:
+		return ops->finished_round(event, self, ops);
 	default:
-		self->unknown_events++;
+		++self->hists.stats.nr_unknown_events;
 		return -1;
 	}
 }
@@ -333,56 +599,114 @@ void perf_event_header__bswap(struct perf_event_header *self)
 	self->size = bswap_16(self->size);
 }
 
-int perf_header__read_build_ids(struct perf_header *self,
-				int input, u64 offset, u64 size)
+static struct thread *perf_session__register_idle_thread(struct perf_session *self)
 {
-	struct build_id_event bev;
-	char filename[PATH_MAX];
-	u64 limit = offset + size;
-	int err = -1;
-
-	while (offset < limit) {
-		struct dso *dso;
-		ssize_t len;
-		struct list_head *head = &dsos__user;
+	struct thread *thread = perf_session__findnew(self, 0);
 
-		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
-			goto out;
+	if (thread == NULL || thread__set_comm(thread, "swapper")) {
+		pr_err("problem inserting idle task.\n");
+		thread = NULL;
+	}
 
-		if (self->needs_swap)
-			perf_event_header__bswap(&bev.header);
+	return thread;
+}
 
-		len = bev.header.size - sizeof(bev);
-		if (read(input, filename, len) != len)
-			goto out;
+int do_read(int fd, void *buf, size_t size)
+{
+	void *buf_start = buf;
 
-		if (bev.header.misc & PERF_RECORD_MISC_KERNEL)
-			head = &dsos__kernel;
+	while (size) {
+		int ret = read(fd, buf, size);
 
-		dso = __dsos__findnew(head, filename);
-		if (dso != NULL) {
-			dso__set_build_id(dso, &bev.build_id);
-			if (head == &dsos__kernel && filename[0] == '[')
-				dso->kernel = 1;
-		}
+		if (ret <= 0)
+			return ret;
 
-		offset += bev.header.size;
+		size -= ret;
+		buf += ret;
 	}
-	err = 0;
-out:
-	return err;
+
+	return buf - buf_start;
 }
 
-static struct thread *perf_session__register_idle_thread(struct perf_session *self)
+#define session_done()	(*(volatile int *)(&session_done))
+volatile int session_done;
+
+static int __perf_session__process_pipe_events(struct perf_session *self,
+					       struct perf_event_ops *ops)
 {
-	struct thread *thread = perf_session__findnew(self, 0);
+	event_t event;
+	uint32_t size;
+	int skip = 0;
+	u64 head;
+	int err;
+	void *p;
 
-	if (thread == NULL || thread__set_comm(thread, "swapper")) {
-		pr_err("problem inserting idle task.\n");
-		thread = NULL;
+	perf_event_ops__fill_defaults(ops);
+
+	head = 0;
+more:
+	err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+	if (err <= 0) {
+		if (err == 0)
+			goto done;
+
+		pr_err("failed to read event header\n");
+		goto out_err;
 	}
 
-	return thread;
+	if (self->header.needs_swap)
+		perf_event_header__bswap(&event.header);
+
+	size = event.header.size;
+	if (size == 0)
+		size = 8;
+
+	p = &event;
+	p += sizeof(struct perf_event_header);
+
+	if (size - sizeof(struct perf_event_header)) {
+		err = do_read(self->fd, p,
+			      size - sizeof(struct perf_event_header));
+		if (err <= 0) {
+			if (err == 0) {
+				pr_err("unexpected end of event stream\n");
+				goto done;
+			}
+
+			pr_err("failed to read event data\n");
+			goto out_err;
+		}
+	}
+
+	if (size == 0 ||
+	    (skip = perf_session__process_event(self, &event, ops,
+						0, head)) < 0) {
+		dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+			    head, event.header.size, event.header.type);
+		/*
+		 * assume we lost track of the stream, check alignment, and
+		 * increment a single u64 in the hope to catch on again 'soon'.
+		 */
+		if (unlikely(head & 7))
+			head &= ~7ULL;
+
+		size = 8;
+	}
+
+	head += size;
+
+	dump_printf("\n%#Lx [%#x]: event: %d\n",
+		    head, event.header.size, event.header.type);
+
+	if (skip > 0)
+		head += skip;
+
+	if (!session_done())
+		goto more;
+done:
+	err = 0;
+out_err:
+	return err;
 }
 
 int __perf_session__process_events(struct perf_session *self,
@@ -396,6 +720,10 @@ int __perf_session__process_events(struct perf_session *self,
 	event_t *event;
 	uint32_t size;
 	char *buf;
+	struct ui_progress *progress = ui_progress__new("Processing events...",
+							self->size);
+	if (progress == NULL)
+		return -1;
 
 	perf_event_ops__fill_defaults(ops);
 
@@ -424,6 +752,7 @@ remap:
 
 more:
 	event = (event_t *)(buf + head);
+	ui_progress__update(progress, offset);
 
 	if (self->header.needs_swap)
 		perf_event_header__bswap(&event->header);
@@ -473,7 +802,11 @@ more:
 		goto more;
 done:
 	err = 0;
+	/* do the final flush for ordered samples */
+	self->ordered_samples.next_flush = ULLONG_MAX;
+	flush_sample_queue(self, ops);
 out_err:
+	ui_progress__delete(progress);
 	return err;
 }
 
@@ -502,9 +835,13 @@ out_getcwd_err:
 		self->cwdlen = strlen(self->cwd);
 	}
 
-	err = __perf_session__process_events(self, self->header.data_offset,
-					     self->header.data_size,
-					     self->size, ops);
+	if (!self->fd_pipe)
+		err = __perf_session__process_events(self,
+						     self->header.data_offset,
+						     self->header.data_size,
+						     self->size, ops);
+	else
+		err = __perf_session__process_pipe_events(self, ops);
 out_err:
 	return err;
 }
@@ -519,56 +856,41 @@ bool perf_session__has_traces(struct perf_session *self, const char *msg)
 	return true;
 }
 
-int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
+int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
 					     const char *symbol_name,
 					     u64 addr)
 {
 	char *bracket;
 	enum map_type i;
+	struct ref_reloc_sym *ref;
 
-	self->ref_reloc_sym.name = strdup(symbol_name);
-	if (self->ref_reloc_sym.name == NULL)
+	ref = zalloc(sizeof(struct ref_reloc_sym));
+	if (ref == NULL)
 		return -ENOMEM;
 
-	bracket = strchr(self->ref_reloc_sym.name, ']');
+	ref->name = strdup(symbol_name);
+	if (ref->name == NULL) {
+		free(ref);
+		return -ENOMEM;
+	}
+
+	bracket = strchr(ref->name, ']');
 	if (bracket)
 		*bracket = '\0';
 
-	self->ref_reloc_sym.addr = addr;
+	ref->addr = addr;
 
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		struct kmap *kmap = map__kmap(self->vmlinux_maps[i]);
-		kmap->ref_reloc_sym = &self->ref_reloc_sym;
+		struct kmap *kmap = map__kmap(maps[i]);
+		kmap->ref_reloc_sym = ref;
 	}
 
 	return 0;
 }
 
-static u64 map__reloc_map_ip(struct map *map, u64 ip)
-{
-	return ip + (s64)map->pgoff;
-}
-
-static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
-{
-	return ip - (s64)map->pgoff;
-}
-
-void map__reloc_vmlinux(struct map *self)
+size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp)
 {
-	struct kmap *kmap = map__kmap(self);
-	s64 reloc;
-
-	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
-		return;
-
-	reloc = (kmap->ref_reloc_sym->unrelocated_addr -
-		 kmap->ref_reloc_sym->addr);
-
-	if (!reloc)
-		return;
-
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
+	return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) +
+	       __dsos__fprintf(&self->host_machine.user_dsos, fp) +
+	       machines__fprintf_dsos(&self->machines, fp);
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5c33417eebb3..e7fce486ebe2 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
+#include "hist.h"
 #include "event.h"
 #include "header.h"
 #include "symbol.h"
@@ -8,45 +9,69 @@
 #include <linux/rbtree.h>
 #include "../../../include/linux/perf_event.h"
 
+struct sample_queue;
 struct ip_callchain;
 struct thread;
 
+struct ordered_samples {
+	u64			last_flush;
+	u64			next_flush;
+	u64			max_timestamp;
+	struct list_head	samples_head;
+	struct sample_queue	*last_inserted;
+};
+
 struct perf_session {
 	struct perf_header	header;
 	unsigned long		size;
 	unsigned long		mmap_window;
-	struct map_groups	kmaps;
 	struct rb_root		threads;
 	struct thread		*last_match;
-	struct map		*vmlinux_maps[MAP__NR_TYPES];
-	struct events_stats	events_stats;
-	struct rb_root		stats_by_id;
-	unsigned long		event_total[PERF_RECORD_MAX];
-	unsigned long		unknown_events;
-	struct rb_root		hists;
+	struct machine		host_machine;
+	struct rb_root		machines;
+	struct rb_root		hists_tree;
+	/*
+	 * FIXME: should point to the first entry in hists_tree and
+	 *        be a hists instance. Right now its only 'report'
+	 *        that is using ->hists_tree while all the rest use
+	 *        ->hists.
+	 */
+	struct hists		hists;
 	u64			sample_type;
-	struct ref_reloc_sym	ref_reloc_sym;
 	int			fd;
+	bool			fd_pipe;
+	bool			repipe;
 	int			cwdlen;
 	char			*cwd;
+	struct ordered_samples	ordered_samples;
 	char filename[0];
 };
 
+struct perf_event_ops;
+
 typedef int (*event_op)(event_t *self, struct perf_session *session);
+typedef int (*event_op2)(event_t *self, struct perf_session *session,
+			 struct perf_event_ops *ops);
 
 struct perf_event_ops {
-	event_op sample,
-		 mmap,
-		 comm,
-		 fork,
-		 exit,
-		 lost,
-		 read,
-		 throttle,
-		 unthrottle;
+	event_op	sample,
+			mmap,
+			comm,
+			fork,
+			exit,
+			lost,
+			read,
+			throttle,
+			unthrottle,
+			attr,
+			event_type,
+			tracing_data,
+			build_id;
+	event_op2	finished_round;
+	bool		ordered_samples;
 };
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force);
+struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe);
 void perf_session__delete(struct perf_session *self);
 
 void perf_event_header__bswap(struct perf_event_header *self);
@@ -57,33 +82,66 @@ int __perf_session__process_events(struct perf_session *self,
 int perf_session__process_events(struct perf_session *self,
 				 struct perf_event_ops *event_ops);
 
-struct symbol **perf_session__resolve_callchain(struct perf_session *self,
-						struct thread *thread,
-						struct ip_callchain *chain,
-						struct symbol **parent);
+struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
+						   struct thread *thread,
+						   struct ip_callchain *chain,
+						   struct symbol **parent);
 
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
-int perf_header__read_build_ids(struct perf_header *self, int input,
-				u64 offset, u64 file_size);
-
-int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
+int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
 					     const char *symbol_name,
 					     u64 addr);
 
 void mem_bswap_64(void *src, int byte_size);
 
-static inline int __perf_session__create_kernel_maps(struct perf_session *self,
-						struct dso *kernel)
+int perf_session__create_kernel_maps(struct perf_session *self);
+
+int do_read(int fd, void *buf, size_t size);
+void perf_session__update_sample_type(struct perf_session *self);
+
+static inline
+struct machine *perf_session__find_host_machine(struct perf_session *self)
+{
+	return &self->host_machine;
+}
+
+static inline
+struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
+{
+	if (pid == HOST_KERNEL_ID)
+		return &self->host_machine;
+	return machines__find(&self->machines, pid);
+}
+
+static inline
+struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid)
+{
+	if (pid == HOST_KERNEL_ID)
+		return &self->host_machine;
+	return machines__findnew(&self->machines, pid);
+}
+
+static inline
+void perf_session__process_machines(struct perf_session *self,
+				    machine__process_t process)
+{
+	process(&self->host_machine, self);
+	return machines__process(&self->machines, process, self);
+}
+
+size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
+
+static inline
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
+					  bool with_hits)
 {
-	return __map_groups__create_kernel_maps(&self->kmaps,
-						self->vmlinux_maps, kernel);
+	return machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
 }
 
-static inline struct map *
-	perf_session__new_module_map(struct perf_session *self,
-				     u64 start, const char *filename)
+static inline
+size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp)
 {
-	return map_groups__new_module(&self->kmaps, start, filename);
+	return hists__fprintf_nr_events(&self->hists, fp);
 }
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index cb0f327de9e8..2316cb5a4116 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,10 +1,10 @@
 #include "sort.h"
 
 regex_t		parent_regex;
-char		default_parent_pattern[] = "^sys_|^do_page_fault";
-char		*parent_pattern = default_parent_pattern;
-char		default_sort_order[] = "comm,dso,symbol";
-char		*sort_order = default_sort_order;
+const char	default_parent_pattern[] = "^sys_|^do_page_fault";
+const char	*parent_pattern = default_parent_pattern;
+const char	default_sort_order[] = "comm,dso,symbol";
+const char	*sort_order = default_sort_order;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
 
@@ -18,39 +18,50 @@ char * field_sep;
 
 LIST_HEAD(hist_entry__sort_list);
 
+static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width);
+static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+				     size_t size, unsigned int width);
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width);
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width);
+static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width);
+
 struct sort_entry sort_thread = {
-	.header = "Command:  Pid",
-	.cmp	= sort__thread_cmp,
-	.print	= sort__thread_print,
-	.width	= &threads__col_width,
+	.se_header	= "Command:  Pid",
+	.se_cmp		= sort__thread_cmp,
+	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_width	= &threads__col_width,
 };
 
 struct sort_entry sort_comm = {
-	.header		= "Command",
-	.cmp		= sort__comm_cmp,
-	.collapse	= sort__comm_collapse,
-	.print		= sort__comm_print,
-	.width		= &comms__col_width,
+	.se_header	= "Command",
+	.se_cmp		= sort__comm_cmp,
+	.se_collapse	= sort__comm_collapse,
+	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_width	= &comms__col_width,
 };
 
 struct sort_entry sort_dso = {
-	.header = "Shared Object",
-	.cmp	= sort__dso_cmp,
-	.print	= sort__dso_print,
-	.width	= &dsos__col_width,
+	.se_header	= "Shared Object",
+	.se_cmp		= sort__dso_cmp,
+	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_width	= &dsos__col_width,
 };
 
 struct sort_entry sort_sym = {
-	.header = "Symbol",
-	.cmp	= sort__sym_cmp,
-	.print	= sort__sym_print,
+	.se_header	= "Symbol",
+	.se_cmp		= sort__sym_cmp,
+	.se_snprintf	= hist_entry__sym_snprintf,
 };
 
 struct sort_entry sort_parent = {
-	.header = "Parent symbol",
-	.cmp	= sort__parent_cmp,
-	.print	= sort__parent_print,
-	.width	= &parent_symbol__col_width,
+	.se_header	= "Parent symbol",
+	.se_cmp		= sort__parent_cmp,
+	.se_snprintf	= hist_entry__parent_snprintf,
+	.se_width	= &parent_symbol__col_width,
 };
 
 struct sort_dimension {
@@ -85,45 +96,38 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 	return right->thread->pid - left->thread->pid;
 }
 
-int repsep_fprintf(FILE *fp, const char *fmt, ...)
+static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
 	va_list ap;
 
 	va_start(ap, fmt);
-	if (!field_sep)
-		n = vfprintf(fp, fmt, ap);
-	else {
-		char *bf = NULL;
-		n = vasprintf(&bf, fmt, ap);
-		if (n > 0) {
-			char *sep = bf;
-
-			while (1) {
-				sep = strchr(sep, *field_sep);
-				if (sep == NULL)
-					break;
-				*sep = '.';
-			}
+	n = vsnprintf(bf, size, fmt, ap);
+	if (field_sep && n > 0) {
+		char *sep = bf;
+
+		while (1) {
+			sep = strchr(sep, *field_sep);
+			if (sep == NULL)
+				break;
+			*sep = '.';
 		}
-		fputs(bf, fp);
-		free(bf);
 	}
 	va_end(ap);
 	return n;
 }
 
-size_t
-sort__thread_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%*s:%5d", width - 6,
+	return repsep_snprintf(bf, size, "%*s:%5d", width,
 			      self->thread->comm ?: "", self->thread->pid);
 }
 
-size_t
-sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
+				     size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%*s", width, self->thread->comm);
+	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
 /* --sort dso */
@@ -131,8 +135,8 @@ sort__comm_print(FILE *fp, struct hist_entry *self, unsigned int width)
 int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct dso *dso_l = left->map ? left->map->dso : NULL;
-	struct dso *dso_r = right->map ? right->map->dso : NULL;
+	struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
+	struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
 	const char *dso_name_l, *dso_name_r;
 
 	if (!dso_l || !dso_r)
@@ -149,16 +153,16 @@ sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 	return strcmp(dso_name_l, dso_name_r);
 }
 
-size_t
-sort__dso_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
 {
-	if (self->map && self->map->dso) {
-		const char *dso_name = !verbose ? self->map->dso->short_name :
-						  self->map->dso->long_name;
-		return repsep_fprintf(fp, "%-*s", width, dso_name);
+	if (self->ms.map && self->ms.map->dso) {
+		const char *dso_name = !verbose ? self->ms.map->dso->short_name :
+						  self->ms.map->dso->long_name;
+		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
 	}
 
-	return repsep_fprintf(fp, "%*llx", width, (u64)self->ip);
+	return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
 }
 
 /* --sort symbol */
@@ -168,31 +172,31 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 ip_l, ip_r;
 
-	if (left->sym == right->sym)
+	if (left->ms.sym == right->ms.sym)
 		return 0;
 
-	ip_l = left->sym ? left->sym->start : left->ip;
-	ip_r = right->sym ? right->sym->start : right->ip;
+	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
+	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
 
 	return (int64_t)(ip_r - ip_l);
 }
 
-
-size_t
-sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used)
+static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width __used)
 {
 	size_t ret = 0;
 
 	if (verbose) {
-		char o = self->map ? dso__symtab_origin(self->map->dso) : '!';
-		ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, o);
+		char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
+		ret += repsep_snprintf(bf, size, "%#018llx %c ", self->ip, o);
 	}
 
-	ret += repsep_fprintf(fp, "[%c] ", self->level);
-	if (self->sym)
-		ret += repsep_fprintf(fp, "%s", self->sym->name);
+	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
+	if (self->ms.sym)
+		ret += repsep_snprintf(bf + ret, size - ret, "%s",
+				       self->ms.sym->name);
 	else
-		ret += repsep_fprintf(fp, "%#016llx", (u64)self->ip);
+		ret += repsep_snprintf(bf + ret, size - ret, "%#016llx", self->ip);
 
 	return ret;
 }
@@ -231,10 +235,10 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 	return strcmp(sym_l->name, sym_r->name);
 }
 
-size_t
-sort__parent_print(FILE *fp, struct hist_entry *self, unsigned int width)
+static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
+				       size_t size, unsigned int width)
 {
-	return repsep_fprintf(fp, "%-*s", width,
+	return repsep_snprintf(bf, size, "%-*s", width,
 			      self->parent ? self->parent->name : "[other]");
 }
 
@@ -251,7 +255,7 @@ int sort_dimension__add(const char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		if (sd->entry->collapse)
+		if (sd->entry->se_collapse)
 			sort__need_collapse = 1;
 
 		if (sd->entry == &sort_parent) {
@@ -260,9 +264,8 @@ int sort_dimension__add(const char *tok)
 				char err[BUFSIZ];
 
 				regerror(ret, &parent_regex, err, sizeof(err));
-				fprintf(stderr, "Invalid regex: %s\n%s",
-					parent_pattern, err);
-				exit(-1);
+				pr_err("Invalid regex: %s\n%s", parent_pattern, err);
+				return -EINVAL;
 			}
 			sort__has_parent = 1;
 		}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 753f9ea99fb0..0d61c4082f43 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -25,10 +25,10 @@
 #include "sort.h"
 
 extern regex_t parent_regex;
-extern char *sort_order;
-extern char default_parent_pattern[];
-extern char *parent_pattern;
-extern char default_sort_order[];
+extern const char *sort_order;
+extern const char default_parent_pattern[];
+extern const char *parent_pattern;
+extern const char default_sort_order[];
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern char *field_sep;
@@ -43,19 +43,24 @@ extern enum sort_type sort__first_dimension;
 
 struct hist_entry {
 	struct rb_node		rb_node;
-	u64			count;
+	u64			period;
+	u64			period_sys;
+	u64			period_us;
+	u64			period_guest_sys;
+	u64			period_guest_us;
+	struct map_symbol	ms;
 	struct thread		*thread;
-	struct map		*map;
-	struct symbol		*sym;
 	u64			ip;
+	u32			nr_events;
 	char			level;
-	struct symbol	  *parent;
-	struct callchain_node	callchain;
+	u8			filtered;
+	struct symbol		*parent;
 	union {
 		unsigned long	  position;
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
+	struct callchain_node	callchain[0];
 };
 
 enum sort_type {
@@ -73,12 +78,13 @@ enum sort_type {
 struct sort_entry {
 	struct list_head list;
 
-	const char *header;
+	const char *se_header;
 
-	int64_t (*cmp)(struct hist_entry *, struct hist_entry *);
-	int64_t (*collapse)(struct hist_entry *, struct hist_entry *);
-	size_t	(*print)(FILE *fp, struct hist_entry *, unsigned int width);
-	unsigned int *width;
+	int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
+	int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
+	int	(*se_snprintf)(struct hist_entry *self, char *bf, size_t size,
+			       unsigned int width);
+	unsigned int *se_width;
 	bool	elide;
 };
 
@@ -87,7 +93,6 @@ extern struct list_head hist_entry__sort_list;
 
 void setup_sorting(const char * const usagestr[], const struct option *opts);
 
-extern int repsep_fprintf(FILE *fp, const char *fmt, ...);
 extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
 extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
 extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index a175949ed216..0409fc7c0058 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -1,48 +1,5 @@
-#include "string.h"
 #include "util.h"
-
-static int hex(char ch)
-{
-	if ((ch >= '0') && (ch <= '9'))
-		return ch - '0';
-	if ((ch >= 'a') && (ch <= 'f'))
-		return ch - 'a' + 10;
-	if ((ch >= 'A') && (ch <= 'F'))
-		return ch - 'A' + 10;
-	return -1;
-}
-
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
-{
-	const char *p = ptr;
-	*long_val = 0;
-
-	while (*p) {
-		const int hex_val = hex(*p);
-
-		if (hex_val < 0)
-			break;
-
-		*long_val = (*long_val << 4) | hex_val;
-		p++;
-	}
-
-	return p - ptr;
-}
-
-char *strxfrchar(char *s, char from, char to)
-{
-	char *p = s;
-
-	while ((p = strchr(p, from)) != NULL)
-		*p++ = to;
-
-	return s;
-}
+#include "string.h"
 
 #define K 1024LL
 /*
diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h
deleted file mode 100644
index 542e44de3719..000000000000
--- a/tools/perf/util/string.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef __PERF_STRING_H_
-#define __PERF_STRING_H_
-
-#include <stdbool.h>
-#include "types.h"
-
-int hex2u64(const char *ptr, u64 *val);
-char *strxfrchar(char *s, char from, char to);
-s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
-bool strglobmatch(const char *str, const char *pat);
-bool strlazymatch(const char *str, const char *pat);
-
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
-#endif /* __PERF_STRING_H */
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c458c4a371d1..a06131f6259a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,13 +1,19 @@
-#include "util.h"
-#include "../perf.h"
-#include "sort.h"
-#include "string.h"
+#define _GNU_SOURCE
+#include <ctype.h>
+#include <dirent.h>
+#include <errno.h>
+#include <libgen.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/param.h>
+#include <fcntl.h>
+#include <unistd.h>
 #include "symbol.h"
-#include "thread.h"
+#include "strlist.h"
 
-#include "debug.h"
-
-#include <asm/bug.h>
 #include <libelf.h>
 #include <gelf.h>
 #include <elf.h>
@@ -18,22 +24,12 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
-enum dso_origin {
-	DSO__ORIG_KERNEL = 0,
-	DSO__ORIG_JAVA_JIT,
-	DSO__ORIG_BUILD_ID_CACHE,
-	DSO__ORIG_FEDORA,
-	DSO__ORIG_UBUNTU,
-	DSO__ORIG_BUILDID,
-	DSO__ORIG_DSO,
-	DSO__ORIG_KMODULE,
-	DSO__ORIG_NOT_FOUND,
-};
-
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 static int dso__load_kernel_sym(struct dso *self, struct map *map,
 				symbol_filter_t filter);
+static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+			symbol_filter_t filter);
 static int vmlinux_path__nr_entries;
 static char **vmlinux_path;
 
@@ -126,16 +122,17 @@ static void map_groups__fixup_end(struct map_groups *self)
 static struct symbol *symbol__new(u64 start, u64 len, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
-	struct symbol *self = zalloc(symbol_conf.priv_size +
-				     sizeof(*self) + namelen);
+	struct symbol *self = calloc(1, (symbol_conf.priv_size +
+					 sizeof(*self) + namelen));
 	if (self == NULL)
 		return NULL;
 
 	if (symbol_conf.priv_size)
 		self = ((void *)self) + symbol_conf.priv_size;
 
-	self->start = start;
-	self->end   = len ? start + len - 1 : start;
+	self->start   = start;
+	self->end     = len ? start + len - 1 : start;
+	self->namelen = namelen - 1;
 
 	pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
 
@@ -178,7 +175,7 @@ static void dso__set_basename(struct dso *self)
 
 struct dso *dso__new(const char *name)
 {
-	struct dso *self = zalloc(sizeof(*self) + strlen(name) + 1);
+	struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
 
 	if (self != NULL) {
 		int i;
@@ -192,6 +189,8 @@ struct dso *dso__new(const char *name)
 		self->loaded = 0;
 		self->sorted_by_name = 0;
 		self->has_build_id = 0;
+		self->kernel = DSO_TYPE_USER;
+		INIT_LIST_HEAD(&self->node);
 	}
 
 	return self;
@@ -408,12 +407,9 @@ int kallsyms__parse(const char *filename, void *arg,
 		char *symbol_name;
 
 		line_len = getline(&line, &n, file);
-		if (line_len < 0)
+		if (line_len < 0 || !line)
 			break;
 
-		if (!line)
-			goto out_failure;
-
 		line[--line_len] = '\0'; /* \n */
 
 		len = hex2u64(line, &start);
@@ -465,6 +461,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	 * map__split_kallsyms, when we have split the maps per module
 	 */
 	symbols__insert(root, sym);
+
 	return 0;
 }
 
@@ -489,6 +486,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
+	struct machine *machine = kmaps->machine;
 	struct map *curr_map = map;
 	struct symbol *pos;
 	int count = 0;
@@ -510,15 +508,33 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			*module++ = '\0';
 
 			if (strcmp(curr_map->dso->short_name, module)) {
-				curr_map = map_groups__find_by_name(kmaps, map->type, module);
+				if (curr_map != map &&
+				    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+				    machine__is_default_guest(machine)) {
+					/*
+					 * We assume all symbols of a module are
+					 * continuous in * kallsyms, so curr_map
+					 * points to a module and all its
+					 * symbols are in its kmap. Mark it as
+					 * loaded.
+					 */
+					dso__set_loaded(curr_map->dso,
+							curr_map->type);
+				}
+
+				curr_map = map_groups__find_by_name(kmaps,
+							map->type, module);
 				if (curr_map == NULL) {
-					pr_debug("/proc/{kallsyms,modules} "
+					pr_debug("%s/proc/{kallsyms,modules} "
 					         "inconsistency while looking "
-						 "for \"%s\" module!\n", module);
-					return -1;
+						 "for \"%s\" module!\n",
+						 machine->root_dir, module);
+					curr_map = map;
+					goto discard_symbol;
 				}
 
-				if (curr_map->dso->loaded)
+				if (curr_map->dso->loaded &&
+				    !machine__is_default_guest(machine))
 					goto discard_symbol;
 			}
 			/*
@@ -531,13 +547,21 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 			char dso_name[PATH_MAX];
 			struct dso *dso;
 
-			snprintf(dso_name, sizeof(dso_name), "[kernel].%d",
-				 kernel_range++);
+			if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+				snprintf(dso_name, sizeof(dso_name),
+					"[guest.kernel].%d",
+					kernel_range++);
+			else
+				snprintf(dso_name, sizeof(dso_name),
+					"[kernel].%d",
+					kernel_range++);
 
 			dso = dso__new(dso_name);
 			if (dso == NULL)
 				return -1;
 
+			dso->kernel = self->kernel;
+
 			curr_map = map__new2(pos->start, dso, map->type);
 			if (curr_map == NULL) {
 				dso__delete(dso);
@@ -561,6 +585,12 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
 		}
 	}
 
+	if (curr_map != map &&
+	    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+	    machine__is_default_guest(kmaps->machine)) {
+		dso__set_loaded(curr_map->dso, curr_map->type);
+	}
+
 	return count;
 }
 
@@ -571,7 +601,10 @@ int dso__load_kallsyms(struct dso *self, const char *filename,
 		return -1;
 
 	symbols__fixup_end(&self->symbols[map->type]);
-	self->origin = DSO__ORIG_KERNEL;
+	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+		self->origin = DSO__ORIG_GUEST_KERNEL;
+	else
+		self->origin = DSO__ORIG_KERNEL;
 
 	return dso__split_kallsyms(self, map, filter);
 }
@@ -870,8 +903,8 @@ out_close:
 	if (err == 0)
 		return nr;
 out:
-	pr_warning("%s: problems reading %s PLT info.\n",
-		   __func__, self->long_name);
+	pr_debug("%s: problems reading %s PLT info.\n",
+		 __func__, self->long_name);
 	return 0;
 }
 
@@ -958,7 +991,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 	nr_syms = shdr.sh_size / shdr.sh_entsize;
 
 	memset(&sym, 0, sizeof(sym));
-	if (!self->kernel) {
+	if (self->kernel == DSO_TYPE_USER) {
 		self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
@@ -990,7 +1023,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 
 		section_name = elf_sec__name(&shdr, secstrs);
 
-		if (self->kernel || kmodule) {
+		if (self->kernel != DSO_TYPE_USER || kmodule) {
 			char dso_name[PATH_MAX];
 
 			if (strcmp(section_name,
@@ -1017,6 +1050,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				curr_dso = dso__new(dso_name);
 				if (curr_dso == NULL)
 					goto out_elf_end;
+				curr_dso->kernel = self->kernel;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
@@ -1025,9 +1059,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				}
 				curr_map->map_ip = identity__map_ip;
 				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->origin = DSO__ORIG_KERNEL;
+				curr_dso->origin = self->origin;
 				map_groups__insert(kmap->kmaps, curr_map);
-				dsos__add(&dsos__kernel, curr_dso);
+				dsos__add(&self->node, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
@@ -1089,7 +1123,7 @@ static bool dso__build_id_equal(const struct dso *self, u8 *build_id)
 	return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
 }
 
-static bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 {
 	bool have_build_id = false;
 	struct dso *pos;
@@ -1107,13 +1141,6 @@ static bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	return have_build_id;
 }
 
-bool dsos__read_build_ids(bool with_hits)
-{
-	bool kbuildids = __dsos__read_build_ids(&dsos__kernel, with_hits),
-	     ubuildids = __dsos__read_build_ids(&dsos__user, with_hits);
-	return kbuildids || ubuildids;
-}
-
 /*
  * Align offset to 4 bytes as needed for note name and descriptor data.
  */
@@ -1248,6 +1275,8 @@ char dso__symtab_origin(const struct dso *self)
 		[DSO__ORIG_BUILDID] =  'b',
 		[DSO__ORIG_DSO] =      'd',
 		[DSO__ORIG_KMODULE] =  'K',
+		[DSO__ORIG_GUEST_KERNEL] =  'g',
+		[DSO__ORIG_GUEST_KMODULE] =  'G',
 	};
 
 	if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
@@ -1263,11 +1292,20 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = -1;
 	int fd;
+	struct machine *machine;
+	const char *root_dir;
 
 	dso__set_loaded(self, map->type);
 
-	if (self->kernel)
+	if (self->kernel == DSO_TYPE_KERNEL)
 		return dso__load_kernel_sym(self, map, filter);
+	else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+		return dso__load_guest_kernel_sym(self, map, filter);
+
+	if (map->groups && map->groups->machine)
+		machine = map->groups->machine;
+	else
+		machine = NULL;
 
 	name = malloc(size);
 	if (!name)
@@ -1321,6 +1359,13 @@ more:
 		case DSO__ORIG_DSO:
 			snprintf(name, size, "%s", self->long_name);
 			break;
+		case DSO__ORIG_GUEST_KMODULE:
+			if (map->groups && map->groups->machine)
+				root_dir = map->groups->machine->root_dir;
+			else
+				root_dir = "";
+			snprintf(name, size, "%s%s", root_dir, self->long_name);
+			break;
 
 		default:
 			goto out;
@@ -1374,7 +1419,8 @@ struct map *map_groups__find_by_name(struct map_groups *self,
 	return NULL;
 }
 
-static int dso__kernel_module_get_build_id(struct dso *self)
+static int dso__kernel_module_get_build_id(struct dso *self,
+				const char *root_dir)
 {
 	char filename[PATH_MAX];
 	/*
@@ -1384,8 +1430,8 @@ static int dso__kernel_module_get_build_id(struct dso *self)
 	const char *name = self->short_name + 1;
 
 	snprintf(filename, sizeof(filename),
-		 "/sys/module/%.*s/notes/.note.gnu.build-id",
-		 (int)strlen(name - 1), name);
+		 "%s/sys/module/%.*s/notes/.note.gnu.build-id",
+		 root_dir, (int)strlen(name) - 1, name);
 
 	if (sysfs__read_build_id(filename, self->build_id,
 				 sizeof(self->build_id)) == 0)
@@ -1394,26 +1440,33 @@ static int dso__kernel_module_get_build_id(struct dso *self)
 	return 0;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirname)
+static int map_groups__set_modules_path_dir(struct map_groups *self,
+				const char *dir_name)
 {
 	struct dirent *dent;
-	DIR *dir = opendir(dirname);
+	DIR *dir = opendir(dir_name);
 
 	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dirname);
+		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
 		return -1;
 	}
 
 	while ((dent = readdir(dir)) != NULL) {
 		char path[PATH_MAX];
+		struct stat st;
 
-		if (dent->d_type == DT_DIR) {
+		/*sshfs might return bad dent->d_type, so we have to stat*/
+		sprintf(path, "%s/%s", dir_name, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (S_ISDIR(st.st_mode)) {
 			if (!strcmp(dent->d_name, ".") ||
 			    !strcmp(dent->d_name, ".."))
 				continue;
 
 			snprintf(path, sizeof(path), "%s/%s",
-				 dirname, dent->d_name);
+				 dir_name, dent->d_name);
 			if (map_groups__set_modules_path_dir(self, path) < 0)
 				goto failure;
 		} else {
@@ -1433,13 +1486,13 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirna
 				continue;
 
 			snprintf(path, sizeof(path), "%s/%s",
-				 dirname, dent->d_name);
+				 dir_name, dent->d_name);
 
 			long_name = strdup(path);
 			if (long_name == NULL)
 				goto failure;
 			dso__set_long_name(map->dso, long_name);
-			dso__kernel_module_get_build_id(map->dso);
+			dso__kernel_module_get_build_id(map->dso, "");
 		}
 	}
 
@@ -1449,18 +1502,47 @@ failure:
 	return -1;
 }
 
-static int map_groups__set_modules_path(struct map_groups *self)
+static char *get_kernel_version(const char *root_dir)
 {
-	struct utsname uts;
+	char version[PATH_MAX];
+	FILE *file;
+	char *name, *tmp;
+	const char *prefix = "Linux version ";
+
+	sprintf(version, "%s/proc/version", root_dir);
+	file = fopen(version, "r");
+	if (!file)
+		return NULL;
+
+	version[0] = '\0';
+	tmp = fgets(version, sizeof(version), file);
+	fclose(file);
+
+	name = strstr(version, prefix);
+	if (!name)
+		return NULL;
+	name += strlen(prefix);
+	tmp = strchr(name, ' ');
+	if (tmp)
+		*tmp = '\0';
+
+	return strdup(name);
+}
+
+static int machine__set_modules_path(struct machine *self)
+{
+	char *version;
 	char modules_path[PATH_MAX];
 
-	if (uname(&uts) < 0)
+	version = get_kernel_version(self->root_dir);
+	if (!version)
 		return -1;
 
-	snprintf(modules_path, sizeof(modules_path), "/lib/modules/%s/kernel",
-		 uts.release);
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+		 self->root_dir, version);
+	free(version);
 
-	return map_groups__set_modules_path_dir(self, modules_path);
+	return map_groups__set_modules_path_dir(&self->kmaps, modules_path);
 }
 
 /*
@@ -1470,8 +1552,8 @@ static int map_groups__set_modules_path(struct map_groups *self)
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-	struct map *self = zalloc(sizeof(*self) +
-				  (dso->kernel ? sizeof(struct kmap) : 0));
+	struct map *self = calloc(1, (sizeof(*self) +
+				      (dso->kernel ? sizeof(struct kmap) : 0)));
 	if (self != NULL) {
 		/*
 		 * ->end will be filled after we load all the symbols
@@ -1482,11 +1564,11 @@ static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return self;
 }
 
-struct map *map_groups__new_module(struct map_groups *self, u64 start,
-				   const char *filename)
+struct map *machine__new_module(struct machine *self, u64 start,
+				const char *filename)
 {
 	struct map *map;
-	struct dso *dso = __dsos__findnew(&dsos__kernel, filename);
+	struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename);
 
 	if (dso == NULL)
 		return NULL;
@@ -1495,18 +1577,31 @@ struct map *map_groups__new_module(struct map_groups *self, u64 start,
 	if (map == NULL)
 		return NULL;
 
-	dso->origin = DSO__ORIG_KMODULE;
-	map_groups__insert(self, map);
+	if (machine__is_host(self))
+		dso->origin = DSO__ORIG_KMODULE;
+	else
+		dso->origin = DSO__ORIG_GUEST_KMODULE;
+	map_groups__insert(&self->kmaps, map);
 	return map;
 }
 
-static int map_groups__create_modules(struct map_groups *self)
+static int machine__create_modules(struct machine *self)
 {
 	char *line = NULL;
 	size_t n;
-	FILE *file = fopen("/proc/modules", "r");
+	FILE *file;
 	struct map *map;
+	const char *modules;
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(self))
+		modules = symbol_conf.default_guest_modules;
+	else {
+		sprintf(path, "%s/proc/modules", self->root_dir);
+		modules = path;
+	}
 
+	file = fopen(modules, "r");
 	if (file == NULL)
 		return -1;
 
@@ -1538,16 +1633,16 @@ static int map_groups__create_modules(struct map_groups *self)
 		*sep = '\0';
 
 		snprintf(name, sizeof(name), "[%s]", line);
-		map = map_groups__new_module(self, start, name);
+		map = machine__new_module(self, start, name);
 		if (map == NULL)
 			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso);
+		dso__kernel_module_get_build_id(map->dso, self->root_dir);
 	}
 
 	free(line);
 	fclose(file);
 
-	return map_groups__set_modules_path(self);
+	return machine__set_modules_path(self);
 
 out_delete_line:
 	free(line);
@@ -1714,8 +1809,56 @@ out_fixup:
 	return err;
 }
 
-LIST_HEAD(dsos__user);
-LIST_HEAD(dsos__kernel);
+static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+				symbol_filter_t filter)
+{
+	int err;
+	const char *kallsyms_filename = NULL;
+	struct machine *machine;
+	char path[PATH_MAX];
+
+	if (!map->groups) {
+		pr_debug("Guest kernel map hasn't the point to groups\n");
+		return -1;
+	}
+	machine = map->groups->machine;
+
+	if (machine__is_default_guest(machine)) {
+		/*
+		 * if the user specified a vmlinux filename, use it and only
+		 * it, reporting errors to the user if it cannot be used.
+		 * Or use file guest_kallsyms inputted by user on commandline
+		 */
+		if (symbol_conf.default_guest_vmlinux_name != NULL) {
+			err = dso__load_vmlinux(self, map,
+				symbol_conf.default_guest_vmlinux_name, filter);
+			goto out_try_fixup;
+		}
+
+		kallsyms_filename = symbol_conf.default_guest_kallsyms;
+		if (!kallsyms_filename)
+			return -1;
+	} else {
+		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+		kallsyms_filename = path;
+	}
+
+	err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+	if (err > 0)
+		pr_debug("Using %s for symbols\n", kallsyms_filename);
+
+out_try_fixup:
+	if (err > 0) {
+		if (kallsyms_filename != NULL) {
+			machine__mmap_name(machine, path, sizeof(path));
+			dso__set_long_name(self, strdup(path));
+		}
+		map__fixup_start(map);
+		map__fixup_end(map);
+	}
+
+	return err;
+}
 
 static void dsos__add(struct list_head *head, struct dso *dso)
 {
@@ -1747,21 +1890,32 @@ struct dso *__dsos__findnew(struct list_head *head, const char *name)
 	return dso;
 }
 
-static void __dsos__fprintf(struct list_head *head, FILE *fp)
+size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 {
 	struct dso *pos;
+	size_t ret = 0;
 
 	list_for_each_entry(pos, head, node) {
 		int i;
 		for (i = 0; i < MAP__NR_TYPES; ++i)
-			dso__fprintf(pos, i, fp);
+			ret += dso__fprintf(pos, i, fp);
 	}
+
+	return ret;
 }
 
-void dsos__fprintf(FILE *fp)
+size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp)
 {
-	__dsos__fprintf(&dsos__kernel, fp);
-	__dsos__fprintf(&dsos__user, fp);
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
+		ret += __dsos__fprintf(&pos->user_dsos, fp);
+	}
+
+	return ret;
 }
 
 static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -1779,10 +1933,17 @@ static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
 	return ret;
 }
 
-size_t dsos__fprintf_buildid(FILE *fp, bool with_hits)
+size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits)
 {
-	return (__dsos__fprintf_buildid(&dsos__kernel, fp, with_hits) +
-		__dsos__fprintf_buildid(&dsos__user, fp, with_hits));
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf_buildid(&pos->kernel_dsos, fp, with_hits);
+		ret += __dsos__fprintf_buildid(&pos->user_dsos, fp, with_hits);
+	}
+	return ret;
 }
 
 struct dso *dso__new_kernel(const char *name)
@@ -1791,55 +1952,98 @@ struct dso *dso__new_kernel(const char *name)
 
 	if (self != NULL) {
 		dso__set_short_name(self, "[kernel]");
-		self->kernel	 = 1;
+		self->kernel = DSO_TYPE_KERNEL;
 	}
 
 	return self;
 }
 
-void dso__read_running_kernel_build_id(struct dso *self)
+static struct dso *dso__new_guest_kernel(struct machine *machine,
+					const char *name)
 {
-	if (sysfs__read_build_id("/sys/kernel/notes", self->build_id,
+	char bf[PATH_MAX];
+	struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf)));
+
+	if (self != NULL) {
+		dso__set_short_name(self, "[guest.kernel]");
+		self->kernel = DSO_TYPE_GUEST_KERNEL;
+	}
+
+	return self;
+}
+
+void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine)
+{
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(machine))
+		return;
+	sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
+	if (sysfs__read_build_id(path, self->build_id,
 				 sizeof(self->build_id)) == 0)
 		self->has_build_id = true;
 }
 
-static struct dso *dsos__create_kernel(const char *vmlinux)
+static struct dso *machine__create_kernel(struct machine *self)
 {
-	struct dso *kernel = dso__new_kernel(vmlinux);
+	const char *vmlinux_name = NULL;
+	struct dso *kernel;
 
-	if (kernel != NULL) {
-		dso__read_running_kernel_build_id(kernel);
-		dsos__add(&dsos__kernel, kernel);
+	if (machine__is_host(self)) {
+		vmlinux_name = symbol_conf.vmlinux_name;
+		kernel = dso__new_kernel(vmlinux_name);
+	} else {
+		if (machine__is_default_guest(self))
+			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
+		kernel = dso__new_guest_kernel(self, vmlinux_name);
 	}
 
+	if (kernel != NULL) {
+		dso__read_running_kernel_build_id(kernel, self);
+		dsos__add(&self->kernel_dsos, kernel);
+	}
 	return kernel;
 }
 
-int __map_groups__create_kernel_maps(struct map_groups *self,
-				     struct map *vmlinux_maps[MAP__NR_TYPES],
-				     struct dso *kernel)
+int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
 {
 	enum map_type type;
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 
-		vmlinux_maps[type] = map__new2(0, kernel, type);
-		if (vmlinux_maps[type] == NULL)
+		self->vmlinux_maps[type] = map__new2(0, kernel, type);
+		if (self->vmlinux_maps[type] == NULL)
 			return -1;
 
-		vmlinux_maps[type]->map_ip =
-			vmlinux_maps[type]->unmap_ip = identity__map_ip;
+		self->vmlinux_maps[type]->map_ip =
+			self->vmlinux_maps[type]->unmap_ip = identity__map_ip;
 
-		kmap = map__kmap(vmlinux_maps[type]);
-		kmap->kmaps = self;
-		map_groups__insert(self, vmlinux_maps[type]);
+		kmap = map__kmap(self->vmlinux_maps[type]);
+		kmap->kmaps = &self->kmaps;
+		map_groups__insert(&self->kmaps, self->vmlinux_maps[type]);
 	}
 
 	return 0;
 }
 
+int machine__create_kernel_maps(struct machine *self)
+{
+	struct dso *kernel = machine__create_kernel(self);
+
+	if (kernel == NULL ||
+	    __machine__create_kernel_maps(self, kernel) < 0)
+		return -1;
+
+	if (symbol_conf.use_modules && machine__create_modules(self) < 0)
+		pr_debug("Problems creating module maps, continuing anyway...\n");
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&self->kmaps);
+	return 0;
+}
+
 static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0) {
@@ -1895,6 +2099,17 @@ out_fail:
 	return -1;
 }
 
+size_t vmlinux_path__fprintf(FILE *fp)
+{
+	int i;
+	size_t printed = 0;
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i)
+		printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]);
+
+	return printed;
+}
+
 static int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
@@ -1945,22 +2160,129 @@ out_free_comm_list:
 	return -1;
 }
 
-int map_groups__create_kernel_maps(struct map_groups *self,
-				   struct map *vmlinux_maps[MAP__NR_TYPES])
+int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
 {
-	struct dso *kernel = dsos__create_kernel(symbol_conf.vmlinux_name);
+	struct machine *machine = machines__findnew(self, pid);
 
-	if (kernel == NULL)
+	if (machine == NULL)
 		return -1;
 
-	if (__map_groups__create_kernel_maps(self, vmlinux_maps, kernel) < 0)
-		return -1;
+	return machine__create_kernel_maps(machine);
+}
 
-	if (symbol_conf.use_modules && map_groups__create_modules(self) < 0)
-		pr_debug("Problems creating module maps, continuing anyway...\n");
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(self);
-	return 0;
+static int hex(char ch)
+{
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	if ((ch >= 'A') && (ch <= 'F'))
+		return ch - 'A' + 10;
+	return -1;
+}
+
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, u64 *long_val)
+{
+	const char *p = ptr;
+	*long_val = 0;
+
+	while (*p) {
+		const int hex_val = hex(*p);
+
+		if (hex_val < 0)
+			break;
+
+		*long_val = (*long_val << 4) | hex_val;
+		p++;
+	}
+
+	return p - ptr;
+}
+
+char *strxfrchar(char *s, char from, char to)
+{
+	char *p = s;
+
+	while ((p = strchr(p, from)) != NULL)
+		*p++ = to;
+
+	return s;
+}
+
+int machines__create_guest_kernel_maps(struct rb_root *self)
+{
+	int ret = 0;
+	struct dirent **namelist = NULL;
+	int i, items = 0;
+	char path[PATH_MAX];
+	pid_t pid;
+
+	if (symbol_conf.default_guest_vmlinux_name ||
+	    symbol_conf.default_guest_modules ||
+	    symbol_conf.default_guest_kallsyms) {
+		machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID);
+	}
+
+	if (symbol_conf.guestmount) {
+		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
+		if (items <= 0)
+			return -ENOENT;
+		for (i = 0; i < items; i++) {
+			if (!isdigit(namelist[i]->d_name[0])) {
+				/* Filter out . and .. */
+				continue;
+			}
+			pid = atoi(namelist[i]->d_name);
+			sprintf(path, "%s/%s/proc/kallsyms",
+				symbol_conf.guestmount,
+				namelist[i]->d_name);
+			ret = access(path, R_OK);
+			if (ret) {
+				pr_debug("Can't access file %s\n", path);
+				goto failure;
+			}
+			machines__create_kernel_maps(self, pid);
+		}
+failure:
+		free(namelist);
+	}
+
+	return ret;
+}
+
+int machine__load_kallsyms(struct machine *self, const char *filename,
+			   enum map_type type, symbol_filter_t filter)
+{
+	struct map *map = self->vmlinux_maps[type];
+	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		/*
+		 * Since /proc/kallsyms will have multiple sessions for the
+		 * kernel, with modules between them, fixup the end of all
+		 * sections.
+		 */
+		__map_groups__fixup_end(&self->kmaps, type);
+	}
+
+	return ret;
+}
+
+int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+			       symbol_filter_t filter)
+{
+	struct map *map = self->vmlinux_maps[type];
+	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		map__reloc_vmlinux(map);
+	}
+
+	return ret;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f30a37428919..032469e41876 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -3,10 +3,11 @@
 
 #include <linux/types.h>
 #include <stdbool.h>
-#include "types.h"
+#include <stdint.h>
+#include "map.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include "event.h"
+#include <stdio.h>
 
 #define DEBUG_CACHE_DIR ".debug"
 
@@ -29,6 +30,9 @@ static inline char *bfd_demangle(void __used *v, const char __used *c,
 #endif
 #endif
 
+int hex2u64(const char *ptr, u64 *val);
+char *strxfrchar(char *s, char from, char to);
+
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
@@ -44,10 +48,13 @@ static inline char *bfd_demangle(void __used *v, const char __used *c,
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define BUILD_ID_SIZE 20
+
 struct symbol {
 	struct rb_node	rb_node;
 	u64		start;
 	u64		end;
+	u16		namelen;
 	char		name[0];
 };
 
@@ -63,10 +70,15 @@ struct symbol_conf {
 			show_nr_samples,
 			use_callchain,
 			exclude_other,
-			full_paths;
+			full_paths,
+			show_cpu_utilization;
 	const char	*vmlinux_name,
 			*field_sep;
-	char            *dso_list_str,
+	const char	*default_guest_vmlinux_name,
+			*default_guest_kallsyms,
+			*default_guest_modules;
+	const char	*guestmount;
+	const char	*dso_list_str,
 			*comm_list_str,
 			*sym_list_str,
 			*col_width_list_str;
@@ -88,6 +100,11 @@ struct ref_reloc_sym {
 	u64		unrelocated_addr;
 };
 
+struct map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;
@@ -95,6 +112,13 @@ struct addr_location {
 	u64	      addr;
 	char	      level;
 	bool	      filtered;
+	unsigned int  cpumode;
+};
+
+enum dso_kernel_type {
+	DSO_TYPE_USER = 0,
+	DSO_TYPE_KERNEL,
+	DSO_TYPE_GUEST_KERNEL
 };
 
 struct dso {
@@ -104,8 +128,9 @@ struct dso {
 	u8		 adjust_symbols:1;
 	u8		 slen_calculated:1;
 	u8		 has_build_id:1;
-	u8		 kernel:1;
+	enum dso_kernel_type	kernel;
 	u8		 hit:1;
+	u8		 annotate_warned:1;
 	unsigned char	 origin;
 	u8		 sorted_by_name;
 	u8		 loaded;
@@ -131,42 +156,65 @@ static inline void dso__set_loaded(struct dso *self, enum map_type type)
 
 void dso__sort_by_name(struct dso *self, enum map_type type);
 
-extern struct list_head dsos__user, dsos__kernel;
-
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
-static inline struct dso *dsos__findnew(const char *name)
-{
-	return __dsos__findnew(&dsos__user, name);
-}
-
 int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *self, struct map *map,
 			   symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
 		       symbol_filter_t filter);
-void dsos__fprintf(FILE *fp);
-size_t dsos__fprintf_buildid(FILE *fp, bool with_hits);
+int machine__load_kallsyms(struct machine *self, const char *filename,
+			   enum map_type type, symbol_filter_t filter);
+int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+			       symbol_filter_t filter);
+
+size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+
+size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
 
 size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
+
+enum dso_origin {
+	DSO__ORIG_KERNEL = 0,
+	DSO__ORIG_GUEST_KERNEL,
+	DSO__ORIG_JAVA_JIT,
+	DSO__ORIG_BUILD_ID_CACHE,
+	DSO__ORIG_FEDORA,
+	DSO__ORIG_UBUNTU,
+	DSO__ORIG_BUILDID,
+	DSO__ORIG_DSO,
+	DSO__ORIG_GUEST_KMODULE,
+	DSO__ORIG_KMODULE,
+	DSO__ORIG_NOT_FOUND,
+};
+
 char dso__symtab_origin(const struct dso *self);
 void dso__set_long_name(struct dso *self, char *name);
 void dso__set_build_id(struct dso *self, void *build_id);
-void dso__read_running_kernel_build_id(struct dso *self);
+void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine);
 struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
 					const char *name);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
-bool dsos__read_build_ids(bool with_hits);
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 int build_id__sprintf(const u8 *self, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start));
 
+int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *self);
+
+int machines__create_kernel_maps(struct rb_root *self, pid_t pid);
+int machines__create_guest_kernel_maps(struct rb_root *self);
+
 int symbol__init(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
+size_t vmlinux_path__fprintf(FILE *fp);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fa968312ee7d..1f7ecd47f499 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,13 +7,35 @@
 #include "util.h"
 #include "debug.h"
 
-void map_groups__init(struct map_groups *self)
+int find_all_tid(int pid, pid_t ** all_tid)
 {
+	char name[256];
+	int items;
+	struct dirent **namelist = NULL;
+	int ret = 0;
 	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		self->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&self->removed_maps[i]);
+
+	sprintf(name, "/proc/%d/task", pid);
+	items = scandir(name, &namelist, NULL, NULL);
+	if (items <= 0)
+                return -ENOENT;
+	*all_tid = malloc(sizeof(pid_t) * items);
+	if (!*all_tid) {
+		ret = -ENOMEM;
+		goto failure;
 	}
+
+	for (i = 0; i < items; i++)
+		(*all_tid)[i] = atoi(namelist[i]->d_name);
+
+	ret = items;
+
+failure:
+	for (i=0; i<items; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return ret;
 }
 
 static struct thread *thread__new(pid_t pid)
@@ -31,28 +53,6 @@ static struct thread *thread__new(pid_t pid)
 	return self;
 }
 
-static void map_groups__flush(struct map_groups *self)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &self->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
-		}
-	}
-}
-
 int thread__set_comm(struct thread *self, const char *comm)
 {
 	int err;
@@ -79,69 +79,10 @@ int thread__comm_len(struct thread *self)
 	return self->comm_len;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
-				  enum map_type type, FILE *fp)
-{
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
-	struct rb_node *nd;
-
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-
-	return printed;
-}
-
-size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(self, i, fp);
-	return printed;
-}
-
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
-						 enum map_type type, FILE *fp)
-{
-	struct map *pos;
-	size_t printed = 0;
-
-	list_for_each_entry(pos, &self->removed_maps[type], node) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-	return printed;
-}
-
-static size_t map_groups__fprintf_removed_maps(struct map_groups *self, FILE *fp)
-{
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(self, i, fp);
-	return printed;
-}
-
-static size_t map_groups__fprintf(struct map_groups *self, FILE *fp)
-{
-	size_t printed = map_groups__fprintf_maps(self, fp);
-	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(self, fp);
-}
-
 static size_t thread__fprintf(struct thread *self, FILE *fp)
 {
 	return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) +
-	       map_groups__fprintf(&self->mg, fp);
+	       map_groups__fprintf(&self->mg, verbose, fp);
 }
 
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
@@ -183,127 +124,12 @@ struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
 	return th;
 }
 
-static int map_groups__fixup_overlappings(struct map_groups *self,
-					  struct map *map)
-{
-	struct rb_root *root = &self->maps[map->type];
-	struct rb_node *next = rb_first(root);
-
-	while (next) {
-		struct map *pos = rb_entry(next, struct map, rb_node);
-		next = rb_next(&pos->rb_node);
-
-		if (!map__overlap(pos, map))
-			continue;
-
-		if (verbose >= 2) {
-			fputs("overlapping maps:\n", stderr);
-			map__fprintf(map, stderr);
-			map__fprintf(pos, stderr);
-		}
-
-		rb_erase(&pos->rb_node, root);
-		/*
-		 * We may have references to this map, for instance in some
-		 * hist_entry instances, so just move them to a separate
-		 * list.
-		 */
-		list_add_tail(&pos->node, &self->removed_maps[map->type]);
-		/*
-		 * Now check if we need to create new maps for areas not
-		 * overlapped by the new map:
-		 */
-		if (map->start > pos->start) {
-			struct map *before = map__clone(pos);
-
-			if (before == NULL)
-				return -ENOMEM;
-
-			before->end = map->start - 1;
-			map_groups__insert(self, before);
-			if (verbose >= 2)
-				map__fprintf(before, stderr);
-		}
-
-		if (map->end < pos->end) {
-			struct map *after = map__clone(pos);
-
-			if (after == NULL)
-				return -ENOMEM;
-
-			after->start = map->end + 1;
-			map_groups__insert(self, after);
-			if (verbose >= 2)
-				map__fprintf(after, stderr);
-		}
-	}
-
-	return 0;
-}
-
-void maps__insert(struct rb_root *maps, struct map *map)
-{
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
-	const u64 ip = map->start;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, maps);
-}
-
-struct map *maps__find(struct rb_root *maps, u64 ip)
-{
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
-	struct map *m;
-
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
-		if (ip < m->start)
-			p = &(*p)->rb_left;
-		else if (ip > m->end)
-			p = &(*p)->rb_right;
-		else
-			return m;
-	}
-
-	return NULL;
-}
-
 void thread__insert_map(struct thread *self, struct map *map)
 {
-	map_groups__fixup_overlappings(&self->mg, map);
+	map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
 	map_groups__insert(&self->mg, map);
 }
 
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-static int map_groups__clone(struct map_groups *self,
-			     struct map_groups *parent, enum map_type type)
-{
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
-		struct map *new = map__clone(map);
-		if (new == NULL)
-			return -ENOMEM;
-		map_groups__insert(self, new);
-	}
-	return 0;
-}
-
 int thread__fork(struct thread *self, struct thread *parent)
 {
 	int i;
@@ -336,15 +162,3 @@ size_t perf_session__fprintf(struct perf_session *self, FILE *fp)
 
 	return ret;
 }
-
-struct symbol *map_groups__find_symbol(struct map_groups *self,
-				       enum map_type type, u64 addr,
-				       symbol_filter_t filter)
-{
-	struct map *map = map_groups__find(self, type, addr);
-
-	if (map != NULL)
-		return map__find_symbol(map, map->map_ip(map, addr), filter);
-
-	return NULL;
-}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index dcf70303e58e..1dfd9ff8bdcd 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,14 +5,6 @@
 #include <unistd.h>
 #include "symbol.h"
 
-struct map_groups {
-	struct rb_root		maps[MAP__NR_TYPES];
-	struct list_head	removed_maps[MAP__NR_TYPES];
-};
-
-size_t __map_groups__fprintf_maps(struct map_groups *self,
-				  enum map_type type, FILE *fp);
-
 struct thread {
 	struct rb_node		rb_node;
 	struct map_groups	mg;
@@ -23,29 +15,16 @@ struct thread {
 	int			comm_len;
 };
 
-void map_groups__init(struct map_groups *self);
+struct perf_session;
+
+int find_all_tid(int pid, pid_t ** all_tid);
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
 void thread__insert_map(struct thread *self, struct map *map);
 int thread__fork(struct thread *self, struct thread *parent);
-size_t map_groups__fprintf_maps(struct map_groups *self, FILE *fp);
 size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
 
-void maps__insert(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-
-static inline void map_groups__insert(struct map_groups *self, struct map *map)
-{
-	 maps__insert(&self->maps[map->type], map);
-}
-
-static inline struct map *map_groups__find(struct map_groups *self,
-					   enum map_type type, u64 addr)
-{
-	return maps__find(&self->maps[type], addr);
-}
-
 static inline struct map *thread__find_map(struct thread *self,
 					   enum map_type type, u64 addr)
 {
@@ -54,34 +33,12 @@ static inline struct map *thread__find_map(struct thread *self,
 
 void thread__find_addr_map(struct thread *self,
 			   struct perf_session *session, u8 cpumode,
-			   enum map_type type, u64 addr,
+			   enum map_type type, pid_t pid, u64 addr,
 			   struct addr_location *al);
 
 void thread__find_addr_location(struct thread *self,
 				struct perf_session *session, u8 cpumode,
-				enum map_type type, u64 addr,
+				enum map_type type, pid_t pid, u64 addr,
 				struct addr_location *al,
 				symbol_filter_t filter);
-struct symbol *map_groups__find_symbol(struct map_groups *self,
-				       enum map_type type, u64 addr,
-				       symbol_filter_t filter);
-
-static inline struct symbol *map_groups__find_function(struct map_groups *self,
-						       u64 addr,
-						       symbol_filter_t filter)
-{
-	return map_groups__find_symbol(self, MAP__FUNCTION, addr, filter);
-}
-
-struct map *map_groups__find_by_name(struct map_groups *self,
-				     enum map_type type, const char *name);
-
-int __map_groups__create_kernel_maps(struct map_groups *self,
-				     struct map *vmlinux_maps[MAP__NR_TYPES],
-				     struct dso *kernel);
-int map_groups__create_kernel_maps(struct map_groups *self,
-				   struct map *vmlinux_maps[MAP__NR_TYPES]);
-
-struct map *map_groups__new_module(struct map_groups *self, u64 start,
-				   const char *filename);
 #endif	/* __PERF_THREAD_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 5ea8973ad331..b1572601286c 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -154,10 +154,17 @@ static void put_tracing_file(char *file)
 	free(file);
 }
 
+static ssize_t calc_data_size;
+
 static ssize_t write_or_die(const void *buf, size_t len)
 {
 	int ret;
 
+	if (calc_data_size) {
+		calc_data_size += len;
+		return len;
+	}
+
 	ret = write(output_fd, buf, len);
 	if (ret < 0)
 		die("writing to '%s'", output_file);
@@ -480,6 +487,17 @@ get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events)
 	return nr_tracepoints > 0 ? path.next : NULL;
 }
 
+bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events)
+{
+	int i;
+
+	for (i = 0; i < nb_events; i++)
+		if (pattrs[i].type == PERF_TYPE_TRACEPOINT)
+			return true;
+
+	return false;
+}
+
 int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
 {
 	char buf[BUFSIZ];
@@ -526,3 +544,20 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
 
 	return 0;
 }
+
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+			       int nb_events)
+{
+	ssize_t size;
+	int err = 0;
+
+	calc_data_size = 1;
+	err = read_tracing_data(fd, pattrs, nb_events);
+	size = calc_data_size - 1;
+	calc_data_size = 0;
+
+	if (err < 0)
+		return err;
+
+	return size;
+}
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 613c9cc90570..73a02223c629 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -37,10 +37,12 @@ int header_page_ts_offset;
 int header_page_ts_size;
 int header_page_size_offset;
 int header_page_size_size;
+int header_page_overwrite_offset;
+int header_page_overwrite_size;
 int header_page_data_offset;
 int header_page_data_size;
 
-int latency_format;
+bool latency_format;
 
 static char *input_buf;
 static unsigned long long input_buf_ptr;
@@ -628,23 +630,32 @@ static int test_type(enum event_type type, enum event_type expect)
 	return 0;
 }
 
-static int test_type_token(enum event_type type, char *token,
-		    enum event_type expect, const char *expect_tok)
+static int __test_type_token(enum event_type type, char *token,
+			     enum event_type expect, const char *expect_tok,
+			     bool warn)
 {
 	if (type != expect) {
-		warning("Error: expected type %d but read %d",
-		    expect, type);
+		if (warn)
+			warning("Error: expected type %d but read %d",
+				expect, type);
 		return -1;
 	}
 
 	if (strcmp(token, expect_tok) != 0) {
-		warning("Error: expected '%s' but read '%s'",
-		    expect_tok, token);
+		if (warn)
+			warning("Error: expected '%s' but read '%s'",
+				expect_tok, token);
 		return -1;
 	}
 	return 0;
 }
 
+static int test_type_token(enum event_type type, char *token,
+			   enum event_type expect, const char *expect_tok)
+{
+	return __test_type_token(type, token, expect, expect_tok, true);
+}
+
 static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
 {
 	enum event_type type;
@@ -661,7 +672,8 @@ static int read_expect_type(enum event_type expect, char **tok)
 	return __read_expect_type(expect, tok, 1);
 }
 
-static int __read_expected(enum event_type expect, const char *str, int newline_ok)
+static int __read_expected(enum event_type expect, const char *str,
+			   int newline_ok, bool warn)
 {
 	enum event_type type;
 	char *token;
@@ -672,7 +684,7 @@ static int __read_expected(enum event_type expect, const char *str, int newline_
 	else
 		type = read_token_item(&token);
 
-	ret = test_type_token(type, token, expect, str);
+	ret = __test_type_token(type, token, expect, str, warn);
 
 	free_token(token);
 
@@ -681,12 +693,12 @@ static int __read_expected(enum event_type expect, const char *str, int newline_
 
 static int read_expected(enum event_type expect, const char *str)
 {
-	return __read_expected(expect, str, 1);
+	return __read_expected(expect, str, 1, true);
 }
 
 static int read_expected_item(enum event_type expect, const char *str)
 {
-	return __read_expected(expect, str, 0);
+	return __read_expected(expect, str, 0, true);
 }
 
 static char *event_read_name(void)
@@ -744,7 +756,7 @@ static int field_is_string(struct format_field *field)
 
 static int field_is_dynamic(struct format_field *field)
 {
-	if (!strcmp(field->type, "__data_loc"))
+	if (!strncmp(field->type, "__data_loc", 10))
 		return 1;
 
 	return 0;
@@ -3087,88 +3099,6 @@ static void print_args(struct print_arg *args)
 	}
 }
 
-static void parse_header_field(const char *field,
-			       int *offset, int *size)
-{
-	char *token;
-	int type;
-
-	if (read_expected(EVENT_ITEM, "field") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-
-	/* type */
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	free_token(token);
-
-	if (read_expected(EVENT_ITEM, field) < 0)
-		return;
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	if (read_expected(EVENT_ITEM, "offset") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	*offset = atoi(token);
-	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	if (read_expected(EVENT_ITEM, "size") < 0)
-		return;
-	if (read_expected(EVENT_OP, ":") < 0)
-		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
-		goto fail;
-	*size = atoi(token);
-	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
-		return;
-	type = read_token(&token);
-	if (type != EVENT_NEWLINE) {
-		/* newer versions of the kernel have a "signed" type */
-		if (type != EVENT_ITEM)
-			goto fail;
-
-		if (strcmp(token, "signed") != 0)
-			goto fail;
-
-		free_token(token);
-
-		if (read_expected(EVENT_OP, ":") < 0)
-			return;
-
-		if (read_expect_type(EVENT_ITEM, &token))
-			goto fail;
-
-		free_token(token);
-		if (read_expected(EVENT_OP, ";") < 0)
-			return;
-
-		if (read_expect_type(EVENT_NEWLINE, &token))
-			goto fail;
-	}
- fail:
-	free_token(token);
-}
-
-int parse_header_page(char *buf, unsigned long size)
-{
-	init_input_buf(buf, size);
-
-	parse_header_field("timestamp", &header_page_ts_offset,
-			   &header_page_ts_size);
-	parse_header_field("commit", &header_page_size_offset,
-			   &header_page_size_size);
-	parse_header_field("data", &header_page_data_offset,
-			   &header_page_data_size);
-
-	return 0;
-}
-
 int parse_ftrace_file(char *buf, unsigned long size)
 {
 	struct format_field *field;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 7cd1193918c7..cb54cd002f49 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -50,14 +50,51 @@ static int long_size;
 
 static unsigned long	page_size;
 
+static ssize_t calc_data_size;
+static bool repipe;
+
+/* If it fails, the next read will report it */
+static void skip(int size)
+{
+	lseek(input_fd, size, SEEK_CUR);
+}
+
+static int do_read(int fd, void *buf, int size)
+{
+	int rsize = size;
+
+	while (size) {
+		int ret = read(fd, buf, size);
+
+		if (ret <= 0)
+			return -1;
+
+		if (repipe) {
+			int retw = write(STDOUT_FILENO, buf, ret);
+
+			if (retw <= 0 || retw != ret)
+				die("repiping input file");
+		}
+
+		size -= ret;
+		buf += ret;
+	}
+
+	return rsize;
+}
+
 static int read_or_die(void *data, int size)
 {
 	int r;
 
-	r = read(input_fd, data, size);
-	if (r != size)
+	r = do_read(input_fd, data, size);
+	if (r <= 0)
 		die("reading input file (size expected=%d received=%d)",
 		    size, r);
+
+	if (calc_data_size)
+		calc_data_size += r;
+
 	return r;
 }
 
@@ -82,57 +119,36 @@ static char *read_string(void)
 	char buf[BUFSIZ];
 	char *str = NULL;
 	int size = 0;
-	int i;
 	off_t r;
+	char c;
 
 	for (;;) {
-		r = read(input_fd, buf, BUFSIZ);
+		r = read(input_fd, &c, 1);
 		if (r < 0)
 			die("reading input file");
 
 		if (!r)
 			die("no data");
 
-		for (i = 0; i < r; i++) {
-			if (!buf[i])
-				break;
-		}
-		if (i < r)
-			break;
+		if (repipe) {
+			int retw = write(STDOUT_FILENO, &c, 1);
 
-		if (str) {
-			size += BUFSIZ;
-			str = realloc(str, size);
-			if (!str)
-				die("malloc of size %d", size);
-			memcpy(str + (size - BUFSIZ), buf, BUFSIZ);
-		} else {
-			size = BUFSIZ;
-			str = malloc_or_die(size);
-			memcpy(str, buf, size);
+			if (retw <= 0 || retw != r)
+				die("repiping input file string");
 		}
-	}
 
-	/* trailing \0: */
-	i++;
-
-	/* move the file descriptor to the end of the string */
-	r = lseek(input_fd, -(r - i), SEEK_CUR);
-	if (r == (off_t)-1)
-		die("lseek");
-
-	if (str) {
-		size += i;
-		str = realloc(str, size);
-		if (!str)
-			die("malloc of size %d", size);
-		memcpy(str + (size - i), buf, i);
-	} else {
-		size = i;
-		str = malloc_or_die(i);
-		memcpy(str, buf, i);
+		buf[size++] = c;
+
+		if (!c)
+			break;
 	}
 
+	if (calc_data_size)
+		calc_data_size += size;
+
+	str = malloc_or_die(size);
+	memcpy(str, buf, size);
+
 	return str;
 }
 
@@ -174,7 +190,6 @@ static void read_ftrace_printk(void)
 static void read_header_files(void)
 {
 	unsigned long long size;
-	char *header_page;
 	char *header_event;
 	char buf[BUFSIZ];
 
@@ -184,10 +199,7 @@ static void read_header_files(void)
 		die("did not read header page");
 
 	size = read8();
-	header_page = malloc_or_die(size);
-	read_or_die(header_page, size);
-	parse_header_page(header_page, size);
-	free(header_page);
+	skip(size);
 
 	/*
 	 * The size field in the page is of type long,
@@ -459,7 +471,7 @@ struct record *trace_read_data(int cpu)
 	return data;
 }
 
-void trace_report(int fd)
+ssize_t trace_report(int fd, bool __repipe)
 {
 	char buf[BUFSIZ];
 	char test[] = { 23, 8, 68 };
@@ -467,6 +479,10 @@ void trace_report(int fd)
 	int show_version = 0;
 	int show_funcs = 0;
 	int show_printk = 0;
+	ssize_t size;
+
+	calc_data_size = 1;
+	repipe = __repipe;
 
 	input_fd = fd;
 
@@ -499,14 +515,18 @@ void trace_report(int fd)
 	read_proc_kallsyms();
 	read_ftrace_printk();
 
+	size = calc_data_size - 1;
+	calc_data_size = 0;
+	repipe = false;
+
 	if (show_funcs) {
 		print_funcs();
-		return;
+		return size;
 	}
 	if (show_printk) {
 		print_printk();
-		return;
+		return size;
 	}
 
-	return;
+	return size;
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index c3269b937db4..406d452956db 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_TRACE_EVENTS_H
 #define __PERF_TRACE_EVENTS_H
 
+#include <stdbool.h>
 #include "parse-events.h"
 
 #define __unused __attribute__((unused))
@@ -162,7 +163,7 @@ struct record *trace_read_data(int cpu);
 
 void parse_set_info(int nr_cpus, int long_sz);
 
-void trace_report(int fd);
+ssize_t trace_report(int fd, bool repipe);
 
 void *malloc_or_die(unsigned int size);
 
@@ -241,9 +242,8 @@ extern int header_page_size_size;
 extern int header_page_data_offset;
 extern int header_page_data_size;
 
-extern int latency_format;
+extern bool latency_format;
 
-int parse_header_page(char *buf, unsigned long size);
 int trace_parse_common_type(void *data);
 int trace_parse_common_pid(void *data);
 int parse_common_pc(void *data);
@@ -258,6 +258,8 @@ void *raw_field_ptr(struct event *event, const char *name, void *data);
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+			       int nb_events);
 
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index f9b890fde681..214265674ddd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -92,3 +92,25 @@ out_close_from:
 out:
 	return err;
 }
+
+unsigned long convert_unit(unsigned long value, char *unit)
+{
+	*unit = ' ';
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'K';
+	}
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'M';
+	}
+
+	if (value > 1000) {
+		value /= 1000;
+		*unit = 'G';
+	}
+
+	return value;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0f5b2a6f1080..0795bf304b19 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -42,12 +42,14 @@
 #define _ALL_SOURCE 1
 #define _GNU_SOURCE 1
 #define _BSD_SOURCE 1
+#define HAS_BOOL
 
 #include <unistd.h>
 #include <stdio.h>
 #include <sys/stat.h>
 #include <sys/statfs.h>
 #include <fcntl.h>
+#include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
 #include <stdarg.h>
@@ -78,6 +80,7 @@
 #include <pwd.h>
 #include <inttypes.h>
 #include "../../../include/linux/magic.h"
+#include "types.h"
 
 
 #ifndef NO_ICONV
@@ -295,6 +298,13 @@ extern void *xmemdupz(const void *data, size_t len);
 extern char *xstrndup(const char *str, size_t len);
 extern void *xrealloc(void *ptr, size_t size) __attribute__((weak));
 
+static inline void *xzalloc(size_t size)
+{
+	void *buf = xmalloc(size);
+
+	return memset(buf, 0, size);
+}
+
 static inline void *zalloc(size_t size)
 {
 	return calloc(1, size);
@@ -309,6 +319,7 @@ static inline int has_extension(const char *filename, const char *ext)
 {
 	size_t len = strlen(filename);
 	size_t extlen = strlen(ext);
+
 	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
 }
 
@@ -322,6 +333,7 @@ static inline int has_extension(const char *filename, const char *ext)
 #undef isalnum
 #undef tolower
 #undef toupper
+
 extern unsigned char sane_ctype[256];
 #define GIT_SPACE		0x01
 #define GIT_DIGIT		0x02
@@ -406,4 +418,14 @@ void git_qsort(void *base, size_t nmemb, size_t size,
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
 
+s64 perf_atoll(const char *str);
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+bool strglobmatch(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
+unsigned long convert_unit(unsigned long value, char *unit);
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
 #endif