Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 * Convert the trace builtins to use the growing evsel/evlist
   tracepoint infrastructure, removing several open coded constructs
   like switch like series of strcmp to dispatch events, etc.
   Basically what had already been showcased in 'perf sched'.

 * Add evsel constructor for tracepoints, that uses libtraceevent
   just to parse the /format events file, use it in a new 'perf test'
   to make sure the libtraceevent format parsing regressions can
   be more readily caught.

 * Some strange errors were happening in some builds, but not on the
   next, reported by several people, problem was some parser related
   files, generated during the build, didn't had proper make deps,
   fix from Eric Sandeen.

 * Fix some compiling errors on 32-bit, from Feng Tang.

 * Don't use sscanf extension %as, not available on bionic, reimplementation
   by Irina Tirdea.

 * Fix bfd.h/libbfd detection with recent binutils, from Markus Trippelsdorf.

 * Introduce struct and cache information about the environment where a
   perf.data file was captured, from Namhyung Kim.

 * Fix several error paths in libtraceevent, from Namhyung Kim.

   Print event causing perf_event_open() to fail in 'perf record',
   from Stephane Eranian.

 * New 'kvm' analysis tool, from Xiao Guangrong.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

21 files changed, 2048 insertions, 583 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 77ebeb8266f4..17c922145e88 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -31,6 +31,7 @@
 #include <ctype.h>
 #include <errno.h>
 #include <stdint.h>
+#include <limits.h>
 
 #include "event-parse.h"
 #include "event-utils.h"
@@ -117,14 +118,7 @@ void breakpoint(void)
 
 struct print_arg *alloc_arg(void)
 {
-	struct print_arg *arg;
-
-	arg = malloc_or_die(sizeof(*arg));
-	if (!arg)
-		return NULL;
-	memset(arg, 0, sizeof(*arg));
-
-	return arg;
+	return calloc(1, sizeof(struct print_arg));
 }
 
 struct cmdline {
@@ -158,7 +152,9 @@ static int cmdline_init(struct pevent *pevent)
 	struct cmdline *cmdlines;
 	int i;
 
-	cmdlines = malloc_or_die(sizeof(*cmdlines) * pevent->cmdline_count);
+	cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
+	if (!cmdlines)
+		return -1;
 
 	i = 0;
 	while (cmdlist) {
@@ -186,8 +182,8 @@ static char *find_cmdline(struct pevent *pevent, int pid)
 	if (!pid)
 		return "<idle>";
 
-	if (!pevent->cmdlines)
-		cmdline_init(pevent);
+	if (!pevent->cmdlines && cmdline_init(pevent))
+		return "<not enough memory for cmdlines!>";
 
 	key.pid = pid;
 
@@ -215,8 +211,8 @@ int pevent_pid_is_registered(struct pevent *pevent, int pid)
 	if (!pid)
 		return 1;
 
-	if (!pevent->cmdlines)
-		cmdline_init(pevent);
+	if (!pevent->cmdlines && cmdline_init(pevent))
+		return 0;
 
 	key.pid = pid;
 
@@ -258,10 +254,14 @@ static int add_new_comm(struct pevent *pevent, const char *comm, int pid)
 		return -1;
 	}
 
-	cmdlines[pevent->cmdline_count].pid = pid;
 	cmdlines[pevent->cmdline_count].comm = strdup(comm);
-	if (!cmdlines[pevent->cmdline_count].comm)
-		die("malloc comm");
+	if (!cmdlines[pevent->cmdline_count].comm) {
+		free(cmdlines);
+		errno = ENOMEM;
+		return -1;
+	}
+
+	cmdlines[pevent->cmdline_count].pid = pid;
 		
 	if (cmdlines[pevent->cmdline_count].comm)
 		pevent->cmdline_count++;
@@ -288,10 +288,15 @@ int pevent_register_comm(struct pevent *pevent, const char *comm, int pid)
 	if (pevent->cmdlines)
 		return add_new_comm(pevent, comm, pid);
 
-	item = malloc_or_die(sizeof(*item));
+	item = malloc(sizeof(*item));
+	if (!item)
+		return -1;
+
 	item->comm = strdup(comm);
-	if (!item->comm)
-		die("malloc comm");
+	if (!item->comm) {
+		free(item);
+		return -1;
+	}
 	item->pid = pid;
 	item->next = pevent->cmdlist;
 
@@ -355,7 +360,10 @@ static int func_map_init(struct pevent *pevent)
 	struct func_map *func_map;
 	int i;
 
-	func_map = malloc_or_die(sizeof(*func_map) * (pevent->func_count + 1));
+	func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1));
+	if (!func_map)
+		return -1;
+
 	funclist = pevent->funclist;
 
 	i = 0;
@@ -455,25 +463,36 @@ pevent_find_function_address(struct pevent *pevent, unsigned long long addr)
 int pevent_register_function(struct pevent *pevent, char *func,
 			     unsigned long long addr, char *mod)
 {
-	struct func_list *item;
+	struct func_list *item = malloc(sizeof(*item));
 
-	item = malloc_or_die(sizeof(*item));
+	if (!item)
+		return -1;
 
 	item->next = pevent->funclist;
 	item->func = strdup(func);
-	if (mod)
+	if (!item->func)
+		goto out_free;
+
+	if (mod) {
 		item->mod = strdup(mod);
-	else
+		if (!item->mod)
+			goto out_free_func;
+	} else
 		item->mod = NULL;
 	item->addr = addr;
 
-	if (!item->func || (mod && !item->mod))
-		die("malloc func");
-
 	pevent->funclist = item;
 	pevent->func_count++;
 
 	return 0;
+
+out_free_func:
+	free(item->func);
+	item->func = NULL;
+out_free:
+	free(item);
+	errno = ENOMEM;
+	return -1;
 }
 
 /**
@@ -524,14 +543,16 @@ static int printk_cmp(const void *a, const void *b)
 	return 0;
 }
 
-static void printk_map_init(struct pevent *pevent)
+static int printk_map_init(struct pevent *pevent)
 {
 	struct printk_list *printklist;
 	struct printk_list *item;
 	struct printk_map *printk_map;
 	int i;
 
-	printk_map = malloc_or_die(sizeof(*printk_map) * (pevent->printk_count + 1));
+	printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1));
+	if (!printk_map)
+		return -1;
 
 	printklist = pevent->printklist;
 
@@ -549,6 +570,8 @@ static void printk_map_init(struct pevent *pevent)
 
 	pevent->printk_map = printk_map;
 	pevent->printklist = NULL;
+
+	return 0;
 }
 
 static struct printk_map *
@@ -557,8 +580,8 @@ find_printk(struct pevent *pevent, unsigned long long addr)
 	struct printk_map *printk;
 	struct printk_map key;
 
-	if (!pevent->printk_map)
-		printk_map_init(pevent);
+	if (!pevent->printk_map && printk_map_init(pevent))
+		return NULL;
 
 	key.addr = addr;
 
@@ -580,21 +603,27 @@ find_printk(struct pevent *pevent, unsigned long long addr)
 int pevent_register_print_string(struct pevent *pevent, char *fmt,
 				 unsigned long long addr)
 {
-	struct printk_list *item;
+	struct printk_list *item = malloc(sizeof(*item));
 
-	item = malloc_or_die(sizeof(*item));
+	if (!item)
+		return -1;
 
 	item->next = pevent->printklist;
-	item->printk = strdup(fmt);
 	item->addr = addr;
 
+	item->printk = strdup(fmt);
 	if (!item->printk)
-		die("malloc fmt");
+		goto out_free;
 
 	pevent->printklist = item;
 	pevent->printk_count++;
 
 	return 0;
+
+out_free:
+	free(item);
+	errno = ENOMEM;
+	return -1;
 }
 
 /**
@@ -619,24 +648,18 @@ void pevent_print_printk(struct pevent *pevent)
 
 static struct event_format *alloc_event(void)
 {
-	struct event_format *event;
-
-	event = malloc(sizeof(*event));
-	if (!event)
-		return NULL;
-	memset(event, 0, sizeof(*event));
-
-	return event;
+	return calloc(1, sizeof(struct event_format));
 }
 
-static void add_event(struct pevent *pevent, struct event_format *event)
+static int add_event(struct pevent *pevent, struct event_format *event)
 {
 	int i;
+	struct event_format **events = realloc(pevent->events, sizeof(event) *
+					       (pevent->nr_events + 1));
+	if (!events)
+		return -1;
 
-	pevent->events = realloc(pevent->events, sizeof(event) *
-				 (pevent->nr_events + 1));
-	if (!pevent->events)
-		die("Can not allocate events");
+	pevent->events = events;
 
 	for (i = 0; i < pevent->nr_events; i++) {
 		if (pevent->events[i]->id > event->id)
@@ -651,6 +674,8 @@ static void add_event(struct pevent *pevent, struct event_format *event)
 	pevent->nr_events++;
 
 	event->pevent = pevent;
+
+	return 0;
 }
 
 static int event_item_type(enum event_type type)
@@ -827,9 +852,9 @@ static enum event_type __read_token(char **tok)
 	switch (type) {
 	case EVENT_NEWLINE:
 	case EVENT_DELIM:
-		*tok = malloc_or_die(2);
-		(*tok)[0] = ch;
-		(*tok)[1] = 0;
+		if (asprintf(tok, "%c", ch) < 0)
+			return EVENT_ERROR;
+
 		return type;
 
 	case EVENT_OP:
@@ -1240,8 +1265,10 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 
 		last_token = token;
 
-		field = malloc_or_die(sizeof(*field));
-		memset(field, 0, sizeof(*field));
+		field = calloc(1, sizeof(*field));
+		if (!field)
+			goto fail;
+
 		field->event = event;
 
 		/* read the rest of the type */
@@ -1282,7 +1309,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		}
 
 		if (!field->type) {
-			die("no type found");
+			do_warning("%s: no type found", __func__);
 			goto fail;
 		}
 		field->name = last_token;
@@ -1329,7 +1356,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				free_token(token);
 				type = read_token(&token);
 				if (type == EVENT_NONE) {
-					die("failed to find token");
+					do_warning("failed to find token");
 					goto fail;
 				}
 			}
@@ -1538,6 +1565,14 @@ process_cond(struct event_format *event, struct print_arg *top, char **tok)
 	left = alloc_arg();
 	right = alloc_arg();
 
+	if (!arg || !left || !right) {
+		do_warning("%s: not enough memory!", __func__);
+		/* arg will be freed at out_free */
+		free_arg(left);
+		free_arg(right);
+		goto out_free;
+	}
+
 	arg->type = PRINT_OP;
 	arg->op.left = left;
 	arg->op.right = right;
@@ -1580,6 +1615,12 @@ process_array(struct event_format *event, struct print_arg *top, char **tok)
 	char *token = NULL;
 
 	arg = alloc_arg();
+	if (!arg) {
+		do_warning("%s: not enough memory!", __func__);
+		/* '*tok' is set to top->op.op.  No need to free. */
+		*tok = NULL;
+		return EVENT_ERROR;
+	}
 
 	*tok = NULL;
 	type = process_arg(event, arg, &token);
@@ -1595,8 +1636,7 @@ process_array(struct event_format *event, struct print_arg *top, char **tok)
 	return type;
 
 out_free:
-	free_token(*tok);
-	*tok = NULL;
+	free_token(token);
 	free_arg(arg);
 	return EVENT_ERROR;
 }
@@ -1682,7 +1722,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 	if (arg->type == PRINT_OP && !arg->op.left) {
 		/* handle single op */
 		if (token[1]) {
-			die("bad op token %s", token);
+			do_warning("bad op token %s", token);
 			goto out_free;
 		}
 		switch (token[0]) {
@@ -1699,10 +1739,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 		/* make an empty left */
 		left = alloc_arg();
+		if (!left)
+			goto out_warn_free;
+
 		left->type = PRINT_NULL;
 		arg->op.left = left;
 
 		right = alloc_arg();
+		if (!right)
+			goto out_warn_free;
+
 		arg->op.right = right;
 
 		/* do not free the token, it belongs to an op */
@@ -1712,6 +1758,9 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 	} else if (strcmp(token, "?") == 0) {
 
 		left = alloc_arg();
+		if (!left)
+			goto out_warn_free;
+
 		/* copy the top arg to the left */
 		*left = *arg;
 
@@ -1720,6 +1769,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		arg->op.left = left;
 		arg->op.prio = 0;
 
+		/* it will set arg->op.right */
 		type = process_cond(event, arg, tok);
 
 	} else if (strcmp(token, ">>") == 0 ||
@@ -1739,6 +1789,8 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		   strcmp(token, "!=") == 0) {
 
 		left = alloc_arg();
+		if (!left)
+			goto out_warn_free;
 
 		/* copy the top arg to the left */
 		*left = *arg;
@@ -1746,6 +1798,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		arg->type = PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
+		arg->op.right = NULL;
 
 		if (set_op_prio(arg) == -1) {
 			event->flags |= EVENT_FL_FAILED;
@@ -1762,12 +1815,14 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		    type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
 			char *new_atom;
 
-			if (left->type != PRINT_ATOM)
-				die("bad pointer type");
+			if (left->type != PRINT_ATOM) {
+				do_warning("bad pointer type");
+				goto out_free;
+			}
 			new_atom = realloc(left->atom.atom,
 					    strlen(left->atom.atom) + 3);
 			if (!new_atom)
-				goto out_free;
+				goto out_warn_free;
 
 			left->atom.atom = new_atom;
 			strcat(left->atom.atom, " *");
@@ -1779,12 +1834,18 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		}
 
 		right = alloc_arg();
+		if (!right)
+			goto out_warn_free;
+
 		type = process_arg_token(event, right, tok, type);
 		arg->op.right = right;
 
 	} else if (strcmp(token, "[") == 0) {
 
 		left = alloc_arg();
+		if (!left)
+			goto out_warn_free;
+
 		*left = *arg;
 
 		arg->type = PRINT_OP;
@@ -1793,6 +1854,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 		arg->op.prio = 0;
 
+		/* it will set arg->op.right */
 		type = process_array(event, arg, tok);
 
 	} else {
@@ -1816,7 +1878,9 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 
 	return type;
 
- out_free:
+out_warn_free:
+	do_warning("%s: not enough memory!", __func__);
+out_free:
 	free_token(token);
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -1880,7 +1944,11 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 			return val;
 		}
 
-		ref = malloc_or_die(len);
+		ref = malloc(len);
+		if (!ref) {
+			do_warning("%s: not enough memory!", __func__);
+			return val;
+		}
 		memcpy(ref, type, len);
 
 		/* chop off the " *" */
@@ -1957,8 +2025,10 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 static unsigned long long
 eval_type(unsigned long long val, struct print_arg *arg, int pointer)
 {
-	if (arg->type != PRINT_TYPE)
-		die("expected type argument");
+	if (arg->type != PRINT_TYPE) {
+		do_warning("expected type argument");
+		return 0;
+	}
 
 	return eval_type_str(val, arg->typecast.type, pointer);
 }
@@ -2143,7 +2213,7 @@ static char *arg_eval (struct print_arg *arg)
 	case PRINT_STRING:
 	case PRINT_BSTRING:
 	default:
-		die("invalid eval type %d", arg->type);
+		do_warning("invalid eval type %d", arg->type);
 		break;
 	}
 
@@ -2166,6 +2236,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 			break;
 
 		arg = alloc_arg();
+		if (!arg)
+			goto out_free;
 
 		free_token(token);
 		type = process_arg(event, arg, &token);
@@ -2179,30 +2251,33 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 		if (test_type_token(type, token, EVENT_DELIM, ","))
 			goto out_free;
 
-		field = malloc_or_die(sizeof(*field));
-		memset(field, 0, sizeof(*field));
+		field = calloc(1, sizeof(*field));
+		if (!field)
+			goto out_free;
 
 		value = arg_eval(arg);
 		if (value == NULL)
-			goto out_free;
+			goto out_free_field;
 		field->value = strdup(value);
 		if (field->value == NULL)
-			goto out_free;
+			goto out_free_field;
 
 		free_arg(arg);
 		arg = alloc_arg();
+		if (!arg)
+			goto out_free;
 
 		free_token(token);
 		type = process_arg(event, arg, &token);
 		if (test_type_token(type, token, EVENT_OP, "}"))
-			goto out_free;
+			goto out_free_field;
 
 		value = arg_eval(arg);
 		if (value == NULL)
-			goto out_free;
+			goto out_free_field;
 		field->str = strdup(value);
 		if (field->str == NULL)
-			goto out_free;
+			goto out_free_field;
 		free_arg(arg);
 		arg = NULL;
 
@@ -2216,6 +2291,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 	*tok = token;
 	return type;
 
+out_free_field:
+	free_flag_sym(field);
 out_free:
 	free_arg(arg);
 	free_token(token);
@@ -2235,6 +2312,10 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 	arg->type = PRINT_FLAGS;
 
 	field = alloc_arg();
+	if (!field) {
+		do_warning("%s: not enough memory!", __func__);
+		goto out_free;
+	}
 
 	type = process_arg(event, field, &token);
 
@@ -2243,7 +2324,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 		type = process_op(event, field, &token);
 
 	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto out_free;
+		goto out_free_field;
 	free_token(token);
 
 	arg->flags.field = field;
@@ -2265,7 +2346,9 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 	type = read_token_item(tok);
 	return type;
 
- out_free:
+out_free_field:
+	free_arg(field);
+out_free:
 	free_token(token);
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -2282,10 +2365,14 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 	arg->type = PRINT_SYMBOL;
 
 	field = alloc_arg();
+	if (!field) {
+		do_warning("%s: not enough memory!", __func__);
+		goto out_free;
+	}
 
 	type = process_arg(event, field, &token);
 	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto out_free;
+		goto out_free_field;
 
 	arg->symbol.field = field;
 
@@ -2297,7 +2384,9 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 	type = read_token_item(tok);
 	return type;
 
- out_free:
+out_free_field:
+	free_arg(field);
+out_free:
 	free_token(token);
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -2314,6 +2403,11 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 	arg->type = PRINT_HEX;
 
 	field = alloc_arg();
+	if (!field) {
+		do_warning("%s: not enough memory!", __func__);
+		goto out_free;
+	}
+
 	type = process_arg(event, field, &token);
 
 	if (test_type_token(type, token, EVENT_DELIM, ","))
@@ -2324,6 +2418,12 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 	free_token(token);
 
 	field = alloc_arg();
+	if (!field) {
+		do_warning("%s: not enough memory!", __func__);
+		*tok = NULL;
+		return EVENT_ERROR;
+	}
+
 	type = process_arg(event, field, &token);
 
 	if (test_type_token(type, token, EVENT_DELIM, ")"))
@@ -2381,6 +2481,12 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 
 	free_token(token);
 	arg = alloc_arg();
+	if (!field) {
+		do_warning("%s: not enough memory!", __func__);
+		*tok = NULL;
+		return EVENT_ERROR;
+	}
+
 	type = process_arg(event, arg, &token);
 	if (type == EVENT_ERROR)
 		goto out_free_arg;
@@ -2434,10 +2540,16 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
 		/* make this a typecast and contine */
 
 		/* prevous must be an atom */
-		if (arg->type != PRINT_ATOM)
-			die("previous needed to be PRINT_ATOM");
+		if (arg->type != PRINT_ATOM) {
+			do_warning("previous needed to be PRINT_ATOM");
+			goto out_free;
+		}
 
 		item_arg = alloc_arg();
+		if (!item_arg) {
+			do_warning("%s: not enough memory!", __func__);
+			goto out_free;
+		}
 
 		arg->type = PRINT_TYPE;
 		arg->typecast.type = arg->atom.atom;
@@ -2533,6 +2645,11 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	next_arg = &(arg->func.args);
 	for (i = 0; i < func->nr_args; i++) {
 		farg = alloc_arg();
+		if (!farg) {
+			do_warning("%s: not enough memory!", __func__);
+			return EVENT_ERROR;
+		}
+
 		type = process_arg(event, farg, &token);
 		if (i < (func->nr_args - 1))
 			test = ",";
@@ -2677,7 +2794,8 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 
 	case EVENT_ERROR ... EVENT_NEWLINE:
 	default:
-		die("unexpected type %d", type);
+		do_warning("unexpected type %d", type);
+		return EVENT_ERROR;
 	}
 	*tok = token;
 
@@ -2698,6 +2816,10 @@ static int event_read_print_args(struct event_format *event, struct print_arg **
 		}
 
 		arg = alloc_arg();
+		if (!arg) {
+			do_warning("%s: not enough memory!", __func__);
+			return -1;
+		}
 
 		type = process_arg(event, arg, &token);
 
@@ -2769,10 +2891,8 @@ static int event_read_print(struct event_format *event)
 	if (type == EVENT_DQUOTE) {
 		char *cat;
 
-		cat = malloc_or_die(strlen(event->print_fmt.format) +
-				    strlen(token) + 1);
-		strcpy(cat, event->print_fmt.format);
-		strcat(cat, token);
+		if (asprintf(&cat, "%s%s", event->print_fmt.format, token) < 0)
+			goto fail;
 		free_token(token);
 		free_token(event->print_fmt.format);
 		event->print_fmt.format = NULL;
@@ -2926,8 +3046,10 @@ static int get_common_info(struct pevent *pevent,
 	 * All events should have the same common elements.
 	 * Pick any event to find where the type is;
 	 */
-	if (!pevent->events)
-		die("no event_list!");
+	if (!pevent->events) {
+		do_warning("no event_list!");
+		return -1;
+	}
 
 	event = pevent->events[0];
 	field = pevent_find_common_field(event, type);
@@ -3085,7 +3207,8 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		if (!arg->field.field) {
 			arg->field.field = pevent_find_any_field(event, arg->field.name);
 			if (!arg->field.field)
-				die("field %s not found", arg->field.name);
+				goto out_warning_field;
+			
 		}
 		/* must be a number */
 		val = pevent_read_number(pevent, data + arg->field.field->offset,
@@ -3146,8 +3269,10 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 				if (!larg->field.field) {
 					larg->field.field =
 						pevent_find_any_field(event, larg->field.name);
-					if (!larg->field.field)
-						die("field %s not found", larg->field.name);
+					if (!larg->field.field) {
+						arg = larg;
+						goto out_warning_field;
+					}
 				}
 				field_size = larg->field.field->elementsize;
 				offset = larg->field.field->offset +
@@ -3183,7 +3308,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 				val = left != right;
 				break;
 			default:
-				die("unknown op '%s'", arg->op.op);
+				goto out_warning_op;
 			}
 			break;
 		case '~':
@@ -3213,7 +3338,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 				val = left <= right;
 				break;
 			default:
-				die("unknown op '%s'", arg->op.op);
+				goto out_warning_op;
 			}
 			break;
 		case '>':
@@ -3228,12 +3353,13 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 				val = left >= right;
 				break;
 			default:
-				die("unknown op '%s'", arg->op.op);
+				goto out_warning_op;
 			}
 			break;
 		case '=':
 			if (arg->op.op[1] != '=')
-				die("unknown op '%s'", arg->op.op);
+				goto out_warning_op;
+
 			val = left == right;
 			break;
 		case '-':
@@ -3249,13 +3375,21 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 			val = left * right;
 			break;
 		default:
-			die("unknown op '%s'", arg->op.op);
+			goto out_warning_op;
 		}
 		break;
 	default: /* not sure what to do there */
 		return 0;
 	}
 	return val;
+
+out_warning_op:
+	do_warning("%s: unknown op '%s'", __func__, arg->op.op);
+	return 0;
+
+out_warning_field:
+	do_warning("%s: field %s not found", __func__, arg->field.name);
+	return 0;
 }
 
 struct flag {
@@ -3332,8 +3466,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		field = arg->field.field;
 		if (!field) {
 			field = pevent_find_any_field(event, arg->field.name);
-			if (!field)
-				die("field %s not found", arg->field.name);
+			if (!field) {
+				str = arg->field.name;
+				goto out_warning_field;
+			}
 			arg->field.field = field;
 		}
 		/* Zero sized fields, mean the rest of the data */
@@ -3350,7 +3486,11 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			trace_seq_printf(s, "%lx", addr);
 			break;
 		}
-		str = malloc_or_die(len + 1);
+		str = malloc(len + 1);
+		if (!str) {
+			do_warning("%s: not enough memory!", __func__);
+			return;
+		}
 		memcpy(str, data + field->offset, len);
 		str[len] = 0;
 		print_str_to_seq(s, format, len_arg, str);
@@ -3390,7 +3530,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			str = arg->hex.field->field.name;
 			field = pevent_find_any_field(event, str);
 			if (!field)
-				die("field %s not found", str);
+				goto out_warning_field;
 			arg->hex.field->field.field = field;
 		}
 		hex = data + field->offset;
@@ -3442,6 +3582,11 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		/* well... */
 		break;
 	}
+
+	return;
+
+out_warning_field:
+	do_warning("%s: field %s not found", __func__, arg->field.name);
 }
 
 static unsigned long long
@@ -3468,7 +3613,11 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 	farg = arg->func.args;
 	param = func_handle->params;
 
-	args = malloc_or_die(sizeof(*args) * func_handle->nr_args);
+	ret = ULLONG_MAX;
+	args = malloc(sizeof(*args) * func_handle->nr_args);
+	if (!args)
+		goto out;
+
 	for (i = 0; i < func_handle->nr_args; i++) {
 		switch (param->type) {
 		case PEVENT_FUNC_ARG_INT:
@@ -3480,12 +3629,18 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 			trace_seq_init(&str);
 			print_str_arg(&str, data, size, event, "%s", -1, farg);
 			trace_seq_terminate(&str);
-			string = malloc_or_die(sizeof(*string));
+			string = malloc(sizeof(*string));
+			if (!string) {
+				do_warning("%s(%d): malloc str", __func__, __LINE__);
+				goto out_free;
+			}
 			string->next = strings;
 			string->str = strdup(str.buffer);
-			if (!string->str)
-				die("malloc str");
-
+			if (!string->str) {
+				free(string);
+				do_warning("%s(%d): malloc str", __func__, __LINE__);
+				goto out_free;
+			}
 			args[i] = (uintptr_t)string->str;
 			strings = string;
 			trace_seq_destroy(&str);
@@ -3495,14 +3650,15 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 			 * Something went totally wrong, this is not
 			 * an input error, something in this code broke.
 			 */
-			die("Unexpected end of arguments\n");
-			break;
+			do_warning("Unexpected end of arguments\n");
+			goto out_free;
 		}
 		farg = farg->next;
 		param = param->next;
 	}
 
 	ret = (*func_handle->func)(s, args);
+out_free:
 	free(args);
 	while (strings) {
 		string = strings;
@@ -3516,6 +3672,18 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 	return ret;
 }
 
+static void free_args(struct print_arg *args)
+{
+	struct print_arg *next;
+
+	while (args) {
+		next = args->next;
+
+		free_arg(args);
+		args = next;
+	}
+}
+
 static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event_format *event)
 {
 	struct pevent *pevent = event->pevent;
@@ -3531,11 +3699,15 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 
 	if (!field) {
 		field = pevent_find_field(event, "buf");
-		if (!field)
-			die("can't find buffer field for binary printk");
+		if (!field) {
+			do_warning("can't find buffer field for binary printk");
+			return NULL;
+		}
 		ip_field = pevent_find_field(event, "ip");
-		if (!ip_field)
-			die("can't find ip field for binary printk");
+		if (!ip_field) {
+			do_warning("can't find ip field for binary printk");
+			return NULL;
+		}
 		pevent->bprint_buf_field = field;
 		pevent->bprint_ip_field = ip_field;
 	}
@@ -3546,13 +3718,18 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	 * The first arg is the IP pointer.
 	 */
 	args = alloc_arg();
+	if (!args) {
+		do_warning("%s(%d): not enough memory!", __func__, __LINE__);
+		return NULL;
+	}
 	arg = args;
 	arg->next = NULL;
 	next = &arg->next;
 
 	arg->type = PRINT_ATOM;
-	arg->atom.atom = malloc_or_die(32);
-	sprintf(arg->atom.atom, "%lld", ip);
+		
+	if (asprintf(&arg->atom.atom, "%lld", ip) < 0)
+		goto out_free;
 
 	/* skip the first "%pf : " */
 	for (ptr = fmt + 6, bptr = data + field->offset;
@@ -3607,10 +3784,17 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				val = pevent_read_number(pevent, bptr, vsize);
 				bptr += vsize;
 				arg = alloc_arg();
+				if (!arg) {
+					do_warning("%s(%d): not enough memory!",
+						   __func__, __LINE__);
+					goto out_free;
+				}
 				arg->next = NULL;
 				arg->type = PRINT_ATOM;
-				arg->atom.atom = malloc_or_die(32);
-				sprintf(arg->atom.atom, "%lld", val);
+				if (asprintf(&arg->atom.atom, "%lld", val) < 0) {
+					free(arg);
+					goto out_free;
+				}
 				*next = arg;
 				next = &arg->next;
 				/*
@@ -3623,11 +3807,16 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				break;
 			case 's':
 				arg = alloc_arg();
+				if (!arg) {
+					do_warning("%s(%d): not enough memory!",
+						   __func__, __LINE__);
+					goto out_free;
+				}
 				arg->next = NULL;
 				arg->type = PRINT_BSTRING;
 				arg->string.string = strdup(bptr);
 				if (!arg->string.string)
-					break;
+					goto out_free;
 				bptr += strlen(bptr) + 1;
 				*next = arg;
 				next = &arg->next;
@@ -3638,18 +3827,10 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	}
 
 	return args;
-}
 
-static void free_args(struct print_arg *args)
-{
-	struct print_arg *next;
-
-	while (args) {
-		next = args->next;
-
-		free_arg(args);
-		args = next;
-	}
+out_free:
+	free_args(args);
+	return NULL;
 }
 
 static char *
@@ -3667,8 +3848,10 @@ get_bprint_format(void *data, int size __maybe_unused,
 
 	if (!field) {
 		field = pevent_find_field(event, "fmt");
-		if (!field)
-			die("can't find format field for binary printk");
+		if (!field) {
+			do_warning("can't find format field for binary printk");
+			return NULL;
+		}
 		pevent->bprint_fmt_field = field;
 	}
 
@@ -3676,9 +3859,8 @@ get_bprint_format(void *data, int size __maybe_unused,
 
 	printk = find_printk(pevent, addr);
 	if (!printk) {
-		format = malloc_or_die(45);
-		sprintf(format, "%%pf : (NO FORMAT FOUND at %llx)\n",
-			addr);
+		if (asprintf(&format, "%%pf : (NO FORMAT FOUND at %llx)\n", addr) < 0)
+			return NULL;
 		return format;
 	}
 
@@ -3686,8 +3868,8 @@ get_bprint_format(void *data, int size __maybe_unused,
 	/* Remove any quotes. */
 	if (*p == '"')
 		p++;
-	format = malloc_or_die(strlen(p) + 10);
-	sprintf(format, "%s : %s", "%pf", p);
+	if (asprintf(&format, "%s : %s", "%pf", p) < 0)
+		return NULL;
 	/* remove ending quotes and new line since we will add one too */
 	p = format + strlen(format) - 1;
 	if (*p == '"')
@@ -3722,8 +3904,11 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
 	if (!arg->field.field) {
 		arg->field.field =
 			pevent_find_any_field(event, arg->field.name);
-		if (!arg->field.field)
-			die("field %s not found", arg->field.name);
+		if (!arg->field.field) {
+			do_warning("%s: field %s not found",
+				   __func__, arg->field.name);
+			return;
+		}
 	}
 	if (arg->field.field->size != 6) {
 		trace_seq_printf(s, "INVALIDMAC");
@@ -4379,7 +4564,10 @@ get_event_fields(const char *type, const char *name,
 	struct format_field *field;
 	int i = 0;
 
-	fields = malloc_or_die(sizeof(*fields) * (count + 1));
+	fields = malloc(sizeof(*fields) * (count + 1));
+	if (!fields)
+		return NULL;
+
 	for (field = list; field; field = field->next) {
 		fields[i++] = field;
 		if (i == count + 1) {
@@ -4695,8 +4883,7 @@ static int find_event_handle(struct pevent *pevent, struct event_format *event)
 }
 
 /**
- * pevent_parse_event - parse the event format
- * @pevent: the handle to the pevent
+ * __pevent_parse_format - parse the event format
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
  * @sys: the system the event belongs to
@@ -4708,15 +4895,16 @@ static int find_event_handle(struct pevent *pevent, struct event_format *event)
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
-				     unsigned long size, const char *sys)
+enum pevent_errno __pevent_parse_format(struct event_format **eventp,
+					struct pevent *pevent, const char *buf,
+					unsigned long size, const char *sys)
 {
 	struct event_format *event;
 	int ret;
 
 	init_input_buf(buf, size);
 
-	event = alloc_event();
+	*eventp = event = alloc_event();
 	if (!event)
 		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 
@@ -4750,9 +4938,6 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 		goto event_alloc_failed;
 	}
 
-	/* Add pevent to event so that it can be referenced */
-	event->pevent = pevent;
-
 	ret = event_read_format(event);
 	if (ret < 0) {
 		ret = PEVENT_ERRNO__READ_FORMAT_FAILED;
@@ -4763,18 +4948,16 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 	 * If the event has an override, don't print warnings if the event
 	 * print format fails to parse.
 	 */
-	if (find_event_handle(pevent, event))
+	if (pevent && find_event_handle(pevent, event))
 		show_warning = 0;
 
 	ret = event_read_print(event);
+	show_warning = 1;
+
 	if (ret < 0) {
-		show_warning = 1;
 		ret = PEVENT_ERRNO__READ_PRINT_FAILED;
 		goto event_parse_failed;
 	}
-	show_warning = 1;
-
-	add_event(pevent, event);
 
 	if (!ret && (event->flags & EVENT_FL_ISFTRACE)) {
 		struct format_field *field;
@@ -4784,6 +4967,10 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 		list = &event->print_fmt.args;
 		for (field = event->format.fields; field; field = field->next) {
 			arg = alloc_arg();
+			if (!arg) {
+				event->flags |= EVENT_FL_FAILED;
+				return PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED;
+			}
 			arg->type = PRINT_FIELD;
 			arg->field.name = strdup(field->name);
 			if (!arg->field.name) {
@@ -4798,22 +4985,78 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 		return 0;
 	}
 
-#define PRINT_ARGS 0
-	if (PRINT_ARGS && event->print_fmt.args)
-		print_args(event->print_fmt.args);
-
 	return 0;
 
  event_parse_failed:
 	event->flags |= EVENT_FL_FAILED;
-	/* still add it even if it failed */
-	add_event(pevent, event);
 	return ret;
 
  event_alloc_failed:
 	free(event->system);
 	free(event->name);
 	free(event);
+	*eventp = NULL;
+	return ret;
+}
+
+/**
+ * pevent_parse_format - parse the event format
+ * @buf: the buffer storing the event format string
+ * @size: the size of @buf
+ * @sys: the system the event belongs to
+ *
+ * This parses the event format and creates an event structure
+ * to quickly parse raw data for a given event.
+ *
+ * These files currently come from:
+ *
+ * /sys/kernel/debug/tracing/events/.../.../format
+ */
+enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+				      unsigned long size, const char *sys)
+{
+	return __pevent_parse_format(eventp, NULL, buf, size, sys);
+}
+
+/**
+ * pevent_parse_event - parse the event format
+ * @pevent: the handle to the pevent
+ * @buf: the buffer storing the event format string
+ * @size: the size of @buf
+ * @sys: the system the event belongs to
+ *
+ * This parses the event format and creates an event structure
+ * to quickly parse raw data for a given event.
+ *
+ * These files currently come from:
+ *
+ * /sys/kernel/debug/tracing/events/.../.../format
+ */
+enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
+				     unsigned long size, const char *sys)
+{
+	struct event_format *event = NULL;
+	int ret = __pevent_parse_format(&event, pevent, buf, size, sys);
+
+	if (event == NULL)
+		return ret;
+
+	/* Add pevent to event so that it can be referenced */
+	event->pevent = pevent;
+
+	if (add_event(pevent, event))
+		goto event_add_failed;
+
+#define PRINT_ARGS 0
+	if (PRINT_ARGS && event->print_fmt.args)
+		print_args(event->print_fmt.args);
+
+	return 0;
+
+event_add_failed:
+	free(event->system);
+	free(event->name);
+	free(event);
 	return ret;
 }
 
@@ -5094,12 +5337,11 @@ int pevent_register_print_function(struct pevent *pevent,
 		remove_func_handler(pevent, name);
 	}
 
-	func_handle = malloc(sizeof(*func_handle));
+	func_handle = calloc(1, sizeof(*func_handle));
 	if (!func_handle) {
 		do_warning("Failed to allocate function handler");
 		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 	}
-	memset(func_handle, 0, sizeof(*func_handle));
 
 	func_handle->ret_type = ret_type;
 	func_handle->name = strdup(name);
@@ -5198,13 +5440,12 @@ int pevent_register_event_handler(struct pevent *pevent,
 
  not_found:
 	/* Save for later use. */
-	handle = malloc(sizeof(*handle));
+	handle = calloc(1, sizeof(*handle));
 	if (!handle) {
 		do_warning("Failed to allocate event handler");
 		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 	}
 
-	memset(handle, 0, sizeof(*handle));
 	handle->id = id;
 	if (event_name)
 		handle->event_name = strdup(event_name);
@@ -5233,13 +5474,10 @@ int pevent_register_event_handler(struct pevent *pevent,
  */
 struct pevent *pevent_alloc(void)
 {
-	struct pevent *pevent;
+	struct pevent *pevent = calloc(1, sizeof(*pevent));
 
-	pevent = malloc(sizeof(*pevent));
-	if (!pevent)
-		return NULL;
-	memset(pevent, 0, sizeof(*pevent));
-	pevent->ref_count = 1;
+	if (pevent)
+		pevent->ref_count = 1;
 
 	return pevent;
 }
@@ -5268,7 +5506,7 @@ static void free_formats(struct format *format)
 	free_format_fields(format->fields);
 }
 
-static void free_event(struct event_format *event)
+void pevent_free_format(struct event_format *event)
 {
 	free(event->name);
 	free(event->system);
@@ -5354,7 +5592,7 @@ void pevent_free(struct pevent *pevent)
 	}
 
 	for (i = 0; i < pevent->nr_events; i++)
-		free_event(pevent->events[i]);
+		pevent_free_format(pevent->events[i]);
 
 	while (pevent->handlers) {
 		handle = pevent->handlers;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index a4bbe2437925..24a4bbabc5d5 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -540,6 +540,9 @@ int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long siz
 
 enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys);
+enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+				      unsigned long size, const char *sys);
+void pevent_free_format(struct event_format *event);
 
 void *pevent_get_field_raw(struct trace_seq *s, struct event_format *event,
 			   const char *name, struct pevent_record *record,
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index dd84cb2f0a88..326f2cb333cb 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
 	{top|record|report|diff|buildid-list}
 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
-	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list}
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
 
 DESCRIPTION
 -----------
@@ -38,6 +38,18 @@ There are a couple of variants of perf kvm:
   so that other tools can be used to fetch packages with matching symbol tables
   for use by perf report.
 
+  'perf kvm stat <command>' to run a command and gather performance counter
+  statistics.
+  Especially, perf 'kvm stat record/report' generates a statistical analysis
+  of KVM events. Currently, vmexit, mmio and ioport events are supported.
+  'perf kvm stat record <command>' records kvm events and the events between
+  start and end <command>.
+  And this command produces a file which contains tracing results of kvm
+  events.
+
+  'perf kvm stat report' reports statistical data which includes events
+  handled time, samples, and so on.
+
 OPTIONS
 -------
 -i::
@@ -68,7 +80,21 @@ OPTIONS
 --guestvmlinux=<path>::
 	Guest os kernel vmlinux.
 
+STAT REPORT OPTIONS
+-------------------
+--vcpu=<value>::
+       analyze events which occures on this vcpu. (default: all vcpus)
+
+--events=<value>::
+       events to be analyzed. Possible values: vmexit, mmio, ioport.
+       (default: vmexit)
+-k::
+--key=<value>::
+       Sorting key. Possible values: sample (default, sort by samples
+       number), time (sort by average time).
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
-linkperf:perf-diff[1], linkperf:perf-buildid-list[1]
+linkperf:perf-diff[1], linkperf:perf-buildid-list[1],
+linkperf:perf-stat[1]
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 051807990938..80db3f4bcf7a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -16,3 +16,6 @@ arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/magic.h
 include/linux/hw_breakpoint.h
+arch/x86/include/asm/svm.h
+arch/x86/include/asm/vmx.h
+arch/x86/include/asm/kvm_host.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 5077f8e2ef72..251dcd7fb5ac 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -233,13 +233,13 @@ export PERL_PATH
 FLEX = flex
 BISON= bison
 
-$(OUTPUT)util/parse-events-flex.c: util/parse-events.l
+$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c
 
-$(OUTPUT)util/pmu-flex.c: util/pmu.l
+$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
@@ -715,7 +715,7 @@ else
 		EXTLIBS += -liberty
 		BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
         else
-		FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd
+		FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd
 		has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD))
 		ifeq ($(has_bfd),y)
 			EXTLIBS += -lbfd
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index f5f8a6b745a3..bc912c68f49a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1,6 +1,7 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/util.h"
 #include "util/cache.h"
@@ -212,36 +213,38 @@ static int insert_caller_stat(unsigned long call_site,
 }
 
 static int perf_evsel__process_alloc_event(struct perf_evsel *evsel,
-					   struct perf_sample *sample, int node)
+					   struct perf_sample *sample)
 {
-	struct event_format *event = evsel->tp_format;
-	void *data = sample->raw_data;
-	unsigned long call_site;
-	unsigned long ptr;
-	int bytes_req, cpu = sample->cpu;
-	int bytes_alloc;
-	int node1, node2;
-
-	ptr = raw_field_value(event, "ptr", data);
-	call_site = raw_field_value(event, "call_site", data);
-	bytes_req = raw_field_value(event, "bytes_req", data);
-	bytes_alloc = raw_field_value(event, "bytes_alloc", data);
-
-	if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu) ||
+	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"),
+		      call_site = perf_evsel__intval(evsel, sample, "call_site");
+	int bytes_req = perf_evsel__intval(evsel, sample, "bytes_req"),
+	    bytes_alloc = perf_evsel__intval(evsel, sample, "bytes_alloc");
+
+	if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, sample->cpu) ||
 	    insert_caller_stat(call_site, bytes_req, bytes_alloc))
 		return -1;
 
 	total_requested += bytes_req;
 	total_allocated += bytes_alloc;
 
-	if (node) {
-		node1 = cpunode_map[cpu];
-		node2 = raw_field_value(event, "node", data);
+	nr_allocs++;
+	return 0;
+}
+
+static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
+						struct perf_sample *sample)
+{
+	int ret = perf_evsel__process_alloc_event(evsel, sample);
+
+	if (!ret) {
+		int node1 = cpunode_map[sample->cpu],
+		    node2 = perf_evsel__intval(evsel, sample, "node");
+
 		if (node1 != node2)
 			nr_cross_allocs++;
 	}
-	nr_allocs++;
-	return 0;
+
+	return ret;
 }
 
 static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
@@ -275,8 +278,7 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 static int perf_evsel__process_free_event(struct perf_evsel *evsel,
 					  struct perf_sample *sample)
 {
-	unsigned long ptr = raw_field_value(evsel->tp_format, "ptr",
-					    sample->raw_data);
+	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr");
 	struct alloc_stat *s_alloc, *s_caller;
 
 	s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
@@ -297,28 +299,8 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
 	return 0;
 }
 
-static int perf_evsel__process_kmem_event(struct perf_evsel *evsel,
-					  struct perf_sample *sample)
-{
-	struct event_format *event = evsel->tp_format;
-
-	if (!strcmp(event->name, "kmalloc") ||
-	    !strcmp(event->name, "kmem_cache_alloc")) {
-		return perf_evsel__process_alloc_event(evsel, sample, 0);
-	}
-
-	if (!strcmp(event->name, "kmalloc_node") ||
-	    !strcmp(event->name, "kmem_cache_alloc_node")) {
-		return perf_evsel__process_alloc_event(evsel, sample, 1);
-	}
-
-	if (!strcmp(event->name, "kfree") ||
-	    !strcmp(event->name, "kmem_cache_free")) {
-		return perf_evsel__process_free_event(evsel, sample);
-	}
-
-	return 0;
-}
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+				  struct perf_sample *sample);
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
@@ -336,7 +318,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-	return perf_evsel__process_kmem_event(evsel, sample);
+	if (evsel->handler.func != NULL) {
+		tracepoint_handler f = evsel->handler.func;
+		return f(evsel, sample);
+	}
+
+	return 0;
 }
 
 static struct perf_tool perf_kmem = {
@@ -498,6 +485,14 @@ static int __cmd_kmem(void)
 {
 	int err = -EINVAL;
 	struct perf_session *session;
+	const struct perf_evsel_str_handler kmem_tracepoints[] = {
+		{ "kmem:kmalloc",		perf_evsel__process_alloc_event, },
+    		{ "kmem:kmem_cache_alloc",	perf_evsel__process_alloc_event, },
+		{ "kmem:kmalloc_node",		perf_evsel__process_alloc_node_event, },
+    		{ "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, },
+		{ "kmem:kfree",			perf_evsel__process_free_event, },
+    		{ "kmem:kmem_cache_free",	perf_evsel__process_free_event, },
+	};
 
 	session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_kmem);
 	if (session == NULL)
@@ -509,6 +504,11 @@ static int __cmd_kmem(void)
 	if (!perf_session__has_traces(session, "kmem record"))
 		goto out_delete;
 
+	if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
+		pr_err("Initializing perf session tracepoint handlers failed\n");
+		return -1;
+	}
+
 	setup_pager();
 	err = perf_session__process_events(session, &perf_kmem);
 	if (err != 0)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 4d2aa2cbeca8..a28c9cad9048 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1,6 +1,7 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evsel.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
@@ -10,8 +11,10 @@
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
-
 #include "util/debug.h"
+#include "util/debugfs.h"
+#include "util/tool.h"
+#include "util/stat.h"
 
 #include <sys/prctl.h>
 
@@ -19,11 +22,836 @@
 #include <pthread.h>
 #include <math.h>
 
-static const char		*file_name;
+#include "../../arch/x86/include/asm/svm.h"
+#include "../../arch/x86/include/asm/vmx.h"
+#include "../../arch/x86/include/asm/kvm.h"
+
+struct event_key {
+	#define INVALID_KEY     (~0ULL)
+	u64 key;
+	int info;
+};
+
+struct kvm_events_ops {
+	bool (*is_begin_event)(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key);
+	bool (*is_end_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key);
+	void (*decode_key)(struct event_key *key, char decode[20]);
+	const char *name;
+};
+
+static void exit_event_get_key(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->info = 0;
+	key->key = perf_evsel__intval(evsel, sample, "exit_reason");
+}
+
+static bool kvm_exit_event(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "kvm:kvm_exit");
+}
+
+static bool exit_event_begin(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key)
+{
+	if (kvm_exit_event(evsel)) {
+		exit_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool kvm_entry_event(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "kvm:kvm_entry");
+}
+
+static bool exit_event_end(struct perf_evsel *evsel,
+			   struct perf_sample *sample __maybe_unused,
+			   struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+struct exit_reasons_table {
+	unsigned long exit_code;
+	const char *reason;
+};
+
+struct exit_reasons_table vmx_exit_reasons[] = {
+	VMX_EXIT_REASONS
+};
+
+struct exit_reasons_table svm_exit_reasons[] = {
+	SVM_EXIT_REASONS
+};
+
+static int cpu_isa;
+
+static const char *get_exit_reason(u64 exit_code)
+{
+	int table_size = ARRAY_SIZE(svm_exit_reasons);
+	struct exit_reasons_table *table = svm_exit_reasons;
+
+	if (cpu_isa == 1) {
+		table = vmx_exit_reasons;
+		table_size = ARRAY_SIZE(vmx_exit_reasons);
+	}
+
+	while (table_size--) {
+		if (table->exit_code == exit_code)
+			return table->reason;
+		table++;
+	}
+
+	pr_err("unknown kvm exit code:%lld on %s\n",
+		(unsigned long long)exit_code, cpu_isa ? "VMX" : "SVM");
+	return "UNKNOWN";
+}
+
+static void exit_event_decode_key(struct event_key *key, char decode[20])
+{
+	const char *exit_reason = get_exit_reason(key->key);
+
+	scnprintf(decode, 20, "%s", exit_reason);
+}
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+    /*
+     * For the mmio events, we treat:
+     * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
+     * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
+     */
+static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "gpa");
+	key->info = perf_evsel__intval(evsel, sample, "type");
+}
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+static bool mmio_event_begin(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key)
+{
+	/* MMIO read begin event in kernel. */
+	if (kvm_exit_event(evsel))
+		return true;
+
+	/* MMIO write begin event in kernel. */
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
+			   struct event_key *key)
+{
+	/* MMIO write end event in kernel. */
+	if (kvm_entry_event(evsel))
+		return true;
+
+	/* MMIO read end event in kernel.*/
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static void mmio_event_decode_key(struct event_key *key, char decode[20])
+{
+	scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
+				key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+}
+
+static struct kvm_events_ops mmio_events = {
+	.is_begin_event = mmio_event_begin,
+	.is_end_event = mmio_event_end,
+	.decode_key = mmio_event_decode_key,
+	.name = "MMIO Access"
+};
+
+ /* The time of emulation pio access is from kvm_pio to kvm_entry. */
+static void ioport_event_get_key(struct perf_evsel *evsel,
+				 struct perf_sample *sample,
+				 struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "port");
+	key->info = perf_evsel__intval(evsel, sample, "rw");
+}
+
+static bool ioport_event_begin(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
+		ioport_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool ioport_event_end(struct perf_evsel *evsel,
+			     struct perf_sample *sample __maybe_unused,
+			     struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static void ioport_event_decode_key(struct event_key *key, char decode[20])
+{
+	scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
+				key->info ? "POUT" : "PIN");
+}
+
+static struct kvm_events_ops ioport_events = {
+	.is_begin_event = ioport_event_begin,
+	.is_end_event = ioport_event_end,
+	.decode_key = ioport_event_decode_key,
+	.name = "IO Port Access"
+};
+
+static const char *report_event = "vmexit";
+struct kvm_events_ops *events_ops;
+
+static bool register_kvm_events_ops(void)
+{
+	bool ret = true;
+
+	if (!strcmp(report_event, "vmexit"))
+		events_ops = &exit_events;
+	else if (!strcmp(report_event, "mmio"))
+		events_ops = &mmio_events;
+	else if (!strcmp(report_event, "ioport"))
+		events_ops = &ioport_events;
+	else {
+		pr_err("Unknown report event:%s\n", report_event);
+		ret = false;
+	}
+
+	return ret;
+}
+
+struct kvm_event_stats {
+	u64 time;
+	struct stats stats;
+};
+
+struct kvm_event {
+	struct list_head hash_entry;
+	struct rb_node rb;
+
+	struct event_key key;
+
+	struct kvm_event_stats total;
+
+	#define DEFAULT_VCPU_NUM 8
+	int max_vcpu;
+	struct kvm_event_stats *vcpu;
+};
+
+struct vcpu_event_record {
+	int vcpu_id;
+	u64 start_time;
+	struct kvm_event *last_event;
+};
+
+#define EVENTS_BITS			12
+#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
+
+static u64 total_time;
+static u64 total_count;
+static struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
+
+static void init_kvm_event_record(void)
+{
+	int i;
+
+	for (i = 0; i < (int)EVENTS_CACHE_SIZE; i++)
+		INIT_LIST_HEAD(&kvm_events_cache[i]);
+}
+
+static int kvm_events_hash_fn(u64 key)
+{
+	return key & (EVENTS_CACHE_SIZE - 1);
+}
+
+static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
+{
+	int old_max_vcpu = event->max_vcpu;
+
+	if (vcpu_id < event->max_vcpu)
+		return true;
+
+	while (event->max_vcpu <= vcpu_id)
+		event->max_vcpu += DEFAULT_VCPU_NUM;
+
+	event->vcpu = realloc(event->vcpu,
+			      event->max_vcpu * sizeof(*event->vcpu));
+	if (!event->vcpu) {
+		pr_err("Not enough memory\n");
+		return false;
+	}
+
+	memset(event->vcpu + old_max_vcpu, 0,
+	       (event->max_vcpu - old_max_vcpu) * sizeof(*event->vcpu));
+	return true;
+}
+
+static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
+{
+	struct kvm_event *event;
+
+	event = zalloc(sizeof(*event));
+	if (!event) {
+		pr_err("Not enough memory\n");
+		return NULL;
+	}
+
+	event->key = *key;
+	return event;
+}
+
+static struct kvm_event *find_create_kvm_event(struct event_key *key)
+{
+	struct kvm_event *event;
+	struct list_head *head;
+
+	BUG_ON(key->key == INVALID_KEY);
+
+	head = &kvm_events_cache[kvm_events_hash_fn(key->key)];
+	list_for_each_entry(event, head, hash_entry)
+		if (event->key.key == key->key && event->key.info == key->info)
+			return event;
+
+	event = kvm_alloc_init_event(key);
+	if (!event)
+		return NULL;
+
+	list_add(&event->hash_entry, head);
+	return event;
+}
+
+static bool handle_begin_event(struct vcpu_event_record *vcpu_record,
+			       struct event_key *key, u64 timestamp)
+{
+	struct kvm_event *event = NULL;
+
+	if (key->key != INVALID_KEY)
+		event = find_create_kvm_event(key);
+
+	vcpu_record->last_event = event;
+	vcpu_record->start_time = timestamp;
+	return true;
+}
+
+static void
+kvm_update_event_stats(struct kvm_event_stats *kvm_stats, u64 time_diff)
+{
+	kvm_stats->time += time_diff;
+	update_stats(&kvm_stats->stats, time_diff);
+}
+
+static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event)
+{
+	struct kvm_event_stats *kvm_stats = &event->total;
+
+	if (vcpu_id != -1)
+		kvm_stats = &event->vcpu[vcpu_id];
+
+	return rel_stddev_stats(stddev_stats(&kvm_stats->stats),
+				avg_stats(&kvm_stats->stats));
+}
+
+static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
+			     u64 time_diff)
+{
+	kvm_update_event_stats(&event->total, time_diff);
+
+	if (!kvm_event_expand(event, vcpu_id))
+		return false;
+
+	kvm_update_event_stats(&event->vcpu[vcpu_id], time_diff);
+	return true;
+}
+
+static bool handle_end_event(struct vcpu_event_record *vcpu_record,
+			     struct event_key *key, u64 timestamp)
+{
+	struct kvm_event *event;
+	u64 time_begin, time_diff;
+
+	event = vcpu_record->last_event;
+	time_begin = vcpu_record->start_time;
+
+	/* The begin event is not caught. */
+	if (!time_begin)
+		return true;
+
+	/*
+	 * In some case, the 'begin event' only records the start timestamp,
+	 * the actual event is recognized in the 'end event' (e.g. mmio-event).
+	 */
+
+	/* Both begin and end events did not get the key. */
+	if (!event && key->key == INVALID_KEY)
+		return true;
+
+	if (!event)
+		event = find_create_kvm_event(key);
+
+	if (!event)
+		return false;
+
+	vcpu_record->last_event = NULL;
+	vcpu_record->start_time = 0;
+
+	BUG_ON(timestamp < time_begin);
+
+	time_diff = timestamp - time_begin;
+	return update_kvm_event(event, vcpu_record->vcpu_id, time_diff);
+}
+
+static
+struct vcpu_event_record *per_vcpu_record(struct thread *thread,
+					  struct perf_evsel *evsel,
+					  struct perf_sample *sample)
+{
+	/* Only kvm_entry records vcpu id. */
+	if (!thread->priv && kvm_entry_event(evsel)) {
+		struct vcpu_event_record *vcpu_record;
+
+		vcpu_record = zalloc(sizeof(*vcpu_record));
+		if (!vcpu_record) {
+			pr_err("%s: Not enough memory\n", __func__);
+			return NULL;
+		}
+
+		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
+		thread->priv = vcpu_record;
+	}
+
+	return thread->priv;
+}
+
+static bool handle_kvm_event(struct thread *thread, struct perf_evsel *evsel,
+			     struct perf_sample *sample)
+{
+	struct vcpu_event_record *vcpu_record;
+	struct event_key key = {.key = INVALID_KEY};
+
+	vcpu_record = per_vcpu_record(thread, evsel, sample);
+	if (!vcpu_record)
+		return true;
+
+	if (events_ops->is_begin_event(evsel, sample, &key))
+		return handle_begin_event(vcpu_record, &key, sample->time);
+
+	if (events_ops->is_end_event(evsel, sample, &key))
+		return handle_end_event(vcpu_record, &key, sample->time);
+
+	return true;
+}
+
+typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
+struct kvm_event_key {
+	const char *name;
+	key_cmp_fun key;
+};
+
+static int trace_vcpu = -1;
+#define GET_EVENT_KEY(func, field)					\
+static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
+{									\
+	if (vcpu == -1)							\
+		return event->total.field;				\
+									\
+	if (vcpu >= event->max_vcpu)					\
+		return 0;						\
+									\
+	return event->vcpu[vcpu].field;					\
+}
+
+#define COMPARE_EVENT_KEY(func, field)					\
+GET_EVENT_KEY(func, field)						\
+static int compare_kvm_event_ ## func(struct kvm_event *one,		\
+					struct kvm_event *two, int vcpu)\
+{									\
+	return get_event_ ##func(one, vcpu) >				\
+				get_event_ ##func(two, vcpu);		\
+}
+
+GET_EVENT_KEY(time, time);
+COMPARE_EVENT_KEY(count, stats.n);
+COMPARE_EVENT_KEY(mean, stats.mean);
+
+#define DEF_SORT_NAME_KEY(name, compare_key)				\
+	{ #name, compare_kvm_event_ ## compare_key }
+
+static struct kvm_event_key keys[] = {
+	DEF_SORT_NAME_KEY(sample, count),
+	DEF_SORT_NAME_KEY(time, mean),
+	{ NULL, NULL }
+};
+
+static const char *sort_key = "sample";
+static key_cmp_fun compare;
+
+static bool select_key(void)
+{
+	int i;
+
+	for (i = 0; keys[i].name; i++) {
+		if (!strcmp(keys[i].name, sort_key)) {
+			compare = keys[i].key;
+			return true;
+		}
+	}
+
+	pr_err("Unknown compare key:%s\n", sort_key);
+	return false;
+}
+
+static struct rb_root result;
+static void insert_to_result(struct kvm_event *event, key_cmp_fun bigger,
+			     int vcpu)
+{
+	struct rb_node **rb = &result.rb_node;
+	struct rb_node *parent = NULL;
+	struct kvm_event *p;
+
+	while (*rb) {
+		p = container_of(*rb, struct kvm_event, rb);
+		parent = *rb;
+
+		if (bigger(event, p, vcpu))
+			rb = &(*rb)->rb_left;
+		else
+			rb = &(*rb)->rb_right;
+	}
+
+	rb_link_node(&event->rb, parent, rb);
+	rb_insert_color(&event->rb, &result);
+}
+
+static void update_total_count(struct kvm_event *event, int vcpu)
+{
+	total_count += get_event_count(event, vcpu);
+	total_time += get_event_time(event, vcpu);
+}
+
+static bool event_is_valid(struct kvm_event *event, int vcpu)
+{
+	return !!get_event_count(event, vcpu);
+}
+
+static void sort_result(int vcpu)
+{
+	unsigned int i;
+	struct kvm_event *event;
+
+	for (i = 0; i < EVENTS_CACHE_SIZE; i++)
+		list_for_each_entry(event, &kvm_events_cache[i], hash_entry)
+			if (event_is_valid(event, vcpu)) {
+				update_total_count(event, vcpu);
+				insert_to_result(event, compare, vcpu);
+			}
+}
+
+/* returns left most element of result, and erase it */
+static struct kvm_event *pop_from_result(void)
+{
+	struct rb_node *node = rb_first(&result);
+
+	if (!node)
+		return NULL;
+
+	rb_erase(node, &result);
+	return container_of(node, struct kvm_event, rb);
+}
+
+static void print_vcpu_info(int vcpu)
+{
+	pr_info("Analyze events for ");
+
+	if (vcpu == -1)
+		pr_info("all VCPUs:\n\n");
+	else
+		pr_info("VCPU %d:\n\n", vcpu);
+}
+
+static void print_result(int vcpu)
+{
+	char decode[20];
+	struct kvm_event *event;
+
+	pr_info("\n\n");
+	print_vcpu_info(vcpu);
+	pr_info("%20s ", events_ops->name);
+	pr_info("%10s ", "Samples");
+	pr_info("%9s ", "Samples%");
+
+	pr_info("%9s ", "Time%");
+	pr_info("%16s ", "Avg time");
+	pr_info("\n\n");
+
+	while ((event = pop_from_result())) {
+		u64 ecount, etime;
+
+		ecount = get_event_count(event, vcpu);
+		etime = get_event_time(event, vcpu);
+
+		events_ops->decode_key(&event->key, decode);
+		pr_info("%20s ", decode);
+		pr_info("%10llu ", (unsigned long long)ecount);
+		pr_info("%8.2f%% ", (double)ecount / total_count * 100);
+		pr_info("%8.2f%% ", (double)etime / total_time * 100);
+		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
+			kvm_event_rel_stddev(vcpu, event));
+		pr_info("\n");
+	}
+
+	pr_info("\nTotal Samples:%lld, Total events handled time:%.2fus.\n\n",
+		(unsigned long long)total_count, total_time / 1e3);
+}
+
+static int process_sample_event(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct thread *thread = machine__findnew_thread(machine, sample->tid);
+
+	if (thread == NULL) {
+		pr_debug("problem processing %d event, skipping it.\n",
+			event->header.type);
+		return -1;
+	}
+
+	if (!handle_kvm_event(thread, evsel, sample))
+		return -1;
+
+	return 0;
+}
+
+static struct perf_tool eops = {
+	.sample			= process_sample_event,
+	.comm			= perf_event__process_comm,
+	.ordered_samples	= true,
+};
+
+static int get_cpu_isa(struct perf_session *session)
+{
+	char *cpuid = session->header.env.cpuid;
+	int isa;
+
+	if (strstr(cpuid, "Intel"))
+		isa = 1;
+	else if (strstr(cpuid, "AMD"))
+		isa = 0;
+	else {
+		pr_err("CPU %s is not supported.\n", cpuid);
+		isa = -ENOTSUP;
+	}
+
+	return isa;
+}
+
+static const char *file_name;
+
+static int read_events(void)
+{
+	struct perf_session *kvm_session;
+	int ret;
+
+	kvm_session = perf_session__new(file_name, O_RDONLY, 0, false, &eops);
+	if (!kvm_session) {
+		pr_err("Initializing perf session failed\n");
+		return -EINVAL;
+	}
+
+	if (!perf_session__has_traces(kvm_session, "kvm record"))
+		return -EINVAL;
+
+	/*
+	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
+	 * traced in the old kernel.
+	 */
+	ret = get_cpu_isa(kvm_session);
+
+	if (ret < 0)
+		return ret;
+
+	cpu_isa = ret;
+
+	return perf_session__process_events(kvm_session, &eops);
+}
+
+static bool verify_vcpu(int vcpu)
+{
+	if (vcpu != -1 && vcpu < 0) {
+		pr_err("Invalid vcpu:%d.\n", vcpu);
+		return false;
+	}
+
+	return true;
+}
+
+static int kvm_events_report_vcpu(int vcpu)
+{
+	int ret = -EINVAL;
+
+	if (!verify_vcpu(vcpu))
+		goto exit;
+
+	if (!select_key())
+		goto exit;
+
+	if (!register_kvm_events_ops())
+		goto exit;
+
+	init_kvm_event_record();
+	setup_pager();
+
+	ret = read_events();
+	if (ret)
+		goto exit;
+
+	sort_result(vcpu);
+	print_result(vcpu);
+exit:
+	return ret;
+}
+
+static const char * const record_args[] = {
+	"record",
+	"-R",
+	"-f",
+	"-m", "1024",
+	"-c", "1",
+	"-e", "kvm:kvm_entry",
+	"-e", "kvm:kvm_exit",
+	"-e", "kvm:kvm_mmio",
+	"-e", "kvm:kvm_pio",
+};
+
+#define STRDUP_FAIL_EXIT(s)		\
+	({	char *_p;		\
+	_p = strdup(s);		\
+		if (!_p)		\
+			return -ENOMEM;	\
+		_p;			\
+	})
+
+static int kvm_events_record(int argc, const char **argv)
+{
+	unsigned int rec_argc, i, j;
+	const char **rec_argv;
+
+	rec_argc = ARRAY_SIZE(record_args) + argc + 2;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(record_args); i++)
+		rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);
+
+	rec_argv[i++] = STRDUP_FAIL_EXIT("-o");
+	rec_argv[i++] = STRDUP_FAIL_EXIT(file_name);
+
+	for (j = 1; j < (unsigned int)argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	return cmd_record(i, rec_argv, NULL);
+}
+
+static const char * const kvm_events_report_usage[] = {
+	"perf kvm stat report [<options>]",
+	NULL
+};
+
+static const struct option kvm_events_report_options[] = {
+	OPT_STRING(0, "event", &report_event, "report event",
+		    "event for reporting: vmexit, mmio, ioport"),
+	OPT_INTEGER(0, "vcpu", &trace_vcpu,
+		    "vcpu id to report"),
+	OPT_STRING('k', "key", &sort_key, "sort-key",
+		    "key for sorting: sample(sort by samples number)"
+		    " time (sort by avg time)"),
+	OPT_END()
+};
+
+static int kvm_events_report(int argc, const char **argv)
+{
+	symbol__init();
+
+	if (argc) {
+		argc = parse_options(argc, argv,
+				     kvm_events_report_options,
+				     kvm_events_report_usage, 0);
+		if (argc)
+			usage_with_options(kvm_events_report_usage,
+					   kvm_events_report_options);
+	}
+
+	return kvm_events_report_vcpu(trace_vcpu);
+}
+
+static void print_kvm_stat_usage(void)
+{
+	printf("Usage: perf kvm stat <command>\n\n");
+
+	printf("# Available commands:\n");
+	printf("\trecord: record kvm events\n");
+	printf("\treport: report statistical data of kvm events\n");
+
+	printf("\nOtherwise, it is the alias of 'perf stat':\n");
+}
+
+static int kvm_cmd_stat(int argc, const char **argv)
+{
+	if (argc == 1) {
+		print_kvm_stat_usage();
+		goto perf_stat;
+	}
+
+	if (!strncmp(argv[1], "rec", 3))
+		return kvm_events_record(argc - 1, argv + 1);
+
+	if (!strncmp(argv[1], "rep", 3))
+		return kvm_events_report(argc - 1 , argv + 1);
+
+perf_stat:
+	return cmd_stat(argc, argv, NULL);
+}
+
 static char			name_buffer[256];
 
 static const char * const kvm_usage[] = {
-	"perf kvm [<options>] {top|record|report|diff|buildid-list}",
+	"perf kvm [<options>] {top|record|report|diff|buildid-list|stat}",
 	NULL
 };
 
@@ -135,6 +963,8 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 		return cmd_top(argc, argv, NULL);
 	else if (!strncmp(argv[0], "buildid-list", 12))
 		return __cmd_buildid_list(argc, argv);
+	else if (!strncmp(argv[0], "stat", 4))
+		return kvm_cmd_stat(argc, argv);
 	else
 		usage_with_options(kvm_usage, kvm_options);
 
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index a8035207a3dd..7d6e09949880 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1,6 +1,7 @@
 #include "builtin.h"
 #include "perf.h"
 
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/util.h"
 #include "util/cache.h"
@@ -41,7 +42,7 @@ struct lock_stat {
 	struct rb_node		rb;		/* used for sorting */
 
 	/*
-	 * FIXME: raw_field_value() returns unsigned long long,
+	 * FIXME: perf_evsel__intval() returns u64,
 	 * so address of lockdep_map should be dealed as 64bit.
 	 * Is there more better solution?
 	 */
@@ -336,44 +337,18 @@ alloc_failed:
 
 static const char *input_name;
 
-struct raw_event_sample {
-	u32			size;
-	char			data[0];
-};
-
-struct trace_acquire_event {
-	void			*addr;
-	const char		*name;
-	int			flag;
-};
-
-struct trace_acquired_event {
-	void			*addr;
-	const char		*name;
-};
-
-struct trace_contended_event {
-	void			*addr;
-	const char		*name;
-};
-
-struct trace_release_event {
-	void			*addr;
-	const char		*name;
-};
-
 struct trace_lock_handler {
-	int (*acquire_event)(struct trace_acquire_event *,
-			      const struct perf_sample *sample);
+	int (*acquire_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample);
 
-	int (*acquired_event)(struct trace_acquired_event *,
-			       const struct perf_sample *sample);
+	int (*acquired_event)(struct perf_evsel *evsel,
+			      struct perf_sample *sample);
 
-	int (*contended_event)(struct trace_contended_event *,
-				const struct perf_sample *sample);
+	int (*contended_event)(struct perf_evsel *evsel,
+			       struct perf_sample *sample);
 
-	int (*release_event)(struct trace_release_event *,
-			      const struct perf_sample *sample);
+	int (*release_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample);
 };
 
 static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr)
@@ -412,15 +387,20 @@ enum acquire_flags {
 	READ_LOCK = 2,
 };
 
-static int
-report_lock_acquire_event(struct trace_acquire_event *acquire_event,
-			  const struct perf_sample *sample)
+static int report_lock_acquire_event(struct perf_evsel *evsel,
+				     struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+	int flag = perf_evsel__intval(evsel, sample, "flag");
 
-	ls = lock_stat_findnew(acquire_event->addr, acquire_event->name);
+	memcpy(&addr, &tmp, sizeof(void *));
+
+	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -1;
 	if (ls->discard)
@@ -430,19 +410,19 @@ report_lock_acquire_event(struct trace_acquire_event *acquire_event,
 	if (!ts)
 		return -1;
 
-	seq = get_seq(ts, acquire_event->addr);
+	seq = get_seq(ts, addr);
 	if (!seq)
 		return -1;
 
 	switch (seq->state) {
 	case SEQ_STATE_UNINITIALIZED:
 	case SEQ_STATE_RELEASED:
-		if (!acquire_event->flag) {
+		if (!flag) {
 			seq->state = SEQ_STATE_ACQUIRING;
 		} else {
-			if (acquire_event->flag & TRY_LOCK)
+			if (flag & TRY_LOCK)
 				ls->nr_trylock++;
-			if (acquire_event->flag & READ_LOCK)
+			if (flag & READ_LOCK)
 				ls->nr_readlock++;
 			seq->state = SEQ_STATE_READ_ACQUIRED;
 			seq->read_count = 1;
@@ -450,7 +430,7 @@ report_lock_acquire_event(struct trace_acquire_event *acquire_event,
 		}
 		break;
 	case SEQ_STATE_READ_ACQUIRED:
-		if (acquire_event->flag & READ_LOCK) {
+		if (flag & READ_LOCK) {
 			seq->read_count++;
 			ls->nr_acquired++;
 			goto end;
@@ -480,17 +460,20 @@ end:
 	return 0;
 }
 
-static int
-report_lock_acquired_event(struct trace_acquired_event *acquired_event,
-			   const struct perf_sample *sample)
+static int report_lock_acquired_event(struct perf_evsel *evsel,
+				      struct perf_sample *sample)
 {
-	u64 timestamp = sample->time;
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
 	u64 contended_term;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+
+	memcpy(&addr, &tmp, sizeof(void *));
 
-	ls = lock_stat_findnew(acquired_event->addr, acquired_event->name);
+	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -1;
 	if (ls->discard)
@@ -500,7 +483,7 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event,
 	if (!ts)
 		return -1;
 
-	seq = get_seq(ts, acquired_event->addr);
+	seq = get_seq(ts, addr);
 	if (!seq)
 		return -1;
 
@@ -511,7 +494,7 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event,
 	case SEQ_STATE_ACQUIRING:
 		break;
 	case SEQ_STATE_CONTENDED:
-		contended_term = timestamp - seq->prev_event_time;
+		contended_term = sample->time - seq->prev_event_time;
 		ls->wait_time_total += contended_term;
 		if (contended_term < ls->wait_time_min)
 			ls->wait_time_min = contended_term;
@@ -536,20 +519,24 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event,
 
 	seq->state = SEQ_STATE_ACQUIRED;
 	ls->nr_acquired++;
-	seq->prev_event_time = timestamp;
+	seq->prev_event_time = sample->time;
 end:
 	return 0;
 }
 
-static int
-report_lock_contended_event(struct trace_contended_event *contended_event,
-			    const struct perf_sample *sample)
+static int report_lock_contended_event(struct perf_evsel *evsel,
+				       struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+
+	memcpy(&addr, &tmp, sizeof(void *));
 
-	ls = lock_stat_findnew(contended_event->addr, contended_event->name);
+	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -1;
 	if (ls->discard)
@@ -559,7 +546,7 @@ report_lock_contended_event(struct trace_contended_event *contended_event,
 	if (!ts)
 		return -1;
 
-	seq = get_seq(ts, contended_event->addr);
+	seq = get_seq(ts, addr);
 	if (!seq)
 		return -1;
 
@@ -592,15 +579,19 @@ end:
 	return 0;
 }
 
-static int
-report_lock_release_event(struct trace_release_event *release_event,
-			  const struct perf_sample *sample)
+static int report_lock_release_event(struct perf_evsel *evsel,
+				     struct perf_sample *sample)
 {
+	void *addr;
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
+	const char *name = perf_evsel__strval(evsel, sample, "name");
+	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
 
-	ls = lock_stat_findnew(release_event->addr, release_event->name);
+	memcpy(&addr, &tmp, sizeof(void *));
+
+	ls = lock_stat_findnew(addr, name);
 	if (!ls)
 		return -1;
 	if (ls->discard)
@@ -610,7 +601,7 @@ report_lock_release_event(struct trace_release_event *release_event,
 	if (!ts)
 		return -1;
 
-	seq = get_seq(ts, release_event->addr);
+	seq = get_seq(ts, addr);
 	if (!seq)
 		return -1;
 
@@ -663,96 +654,33 @@ static struct trace_lock_handler *trace_handler;
 static int perf_evsel__process_lock_acquire(struct perf_evsel *evsel,
 					     struct perf_sample *sample)
 {
-	struct trace_acquire_event acquire_event;
-	struct event_format *event = evsel->tp_format;
-	void *data = sample->raw_data;
-	u64 tmp;		/* this is required for casting... */
-	int rc = 0;
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&acquire_event.addr, &tmp, sizeof(void *));
-	acquire_event.name = (char *)raw_field_ptr(event, "name", data);
-	acquire_event.flag = (int)raw_field_value(event, "flag", data);
-
 	if (trace_handler->acquire_event)
-		rc = trace_handler->acquire_event(&acquire_event, sample);
-
-	return rc;
+		return trace_handler->acquire_event(evsel, sample);
+	return 0;
 }
 
 static int perf_evsel__process_lock_acquired(struct perf_evsel *evsel,
 					      struct perf_sample *sample)
 {
-	struct trace_acquired_event acquired_event;
-	struct event_format *event = evsel->tp_format;
-	void *data = sample->raw_data;
-	u64 tmp;		/* this is required for casting... */
-	int rc = 0;
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&acquired_event.addr, &tmp, sizeof(void *));
-	acquired_event.name = (char *)raw_field_ptr(event, "name", data);
-
 	if (trace_handler->acquired_event)
-		rc = trace_handler->acquired_event(&acquired_event, sample);
-
-	return rc;
+		return trace_handler->acquired_event(evsel, sample);
+	return 0;
 }
 
 static int perf_evsel__process_lock_contended(struct perf_evsel *evsel,
-					       struct perf_sample *sample)
+					      struct perf_sample *sample)
 {
-	struct trace_contended_event contended_event;
-	struct event_format *event = evsel->tp_format;
-	void *data = sample->raw_data;
-	u64 tmp;		/* this is required for casting... */
-	int rc = 0;
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&contended_event.addr, &tmp, sizeof(void *));
-	contended_event.name = (char *)raw_field_ptr(event, "name", data);
-
 	if (trace_handler->contended_event)
-		rc = trace_handler->contended_event(&contended_event, sample);
-
-	return rc;
+		return trace_handler->contended_event(evsel, sample);
+	return 0;
 }
 
 static int perf_evsel__process_lock_release(struct perf_evsel *evsel,
-					     struct perf_sample *sample)
+					    struct perf_sample *sample)
 {
-	struct trace_release_event release_event;
-	struct event_format *event = evsel->tp_format;
-	void *data = sample->raw_data;
-	u64 tmp;		/* this is required for casting... */
-	int rc = 0;
-
-	tmp = raw_field_value(event, "lockdep_addr", data);
-	memcpy(&release_event.addr, &tmp, sizeof(void *));
-	release_event.name = (char *)raw_field_ptr(event, "name", data);
-
 	if (trace_handler->release_event)
-		rc = trace_handler->release_event(&release_event, sample);
-
-	return rc;
-}
-
-static int perf_evsel__process_lock_event(struct perf_evsel *evsel,
-					   struct perf_sample *sample)
-{
-	struct event_format *event = evsel->tp_format;
-	int rc = 0;
-
-	if (!strcmp(event->name, "lock_acquire"))
-		rc = perf_evsel__process_lock_acquire(evsel, sample);
-	if (!strcmp(event->name, "lock_acquired"))
-		rc = perf_evsel__process_lock_acquired(evsel, sample);
-	if (!strcmp(event->name, "lock_contended"))
-		rc = perf_evsel__process_lock_contended(evsel, sample);
-	if (!strcmp(event->name, "lock_release"))
-		rc = perf_evsel__process_lock_release(evsel, sample);
-
-	return rc;
+		return trace_handler->release_event(evsel, sample);
+	return 0;
 }
 
 static void print_bad_events(int bad, int total)
@@ -870,6 +798,9 @@ static int dump_info(void)
 	return rc;
 }
 
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+				  struct perf_sample *sample);
+
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -884,7 +815,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	return perf_evsel__process_lock_event(evsel, sample);
+	if (evsel->handler.func != NULL) {
+		tracepoint_handler f = evsel->handler.func;
+		return f(evsel, sample);
+	}
+
+	return 0;
 }
 
 static struct perf_tool eops = {
@@ -893,6 +829,13 @@ static struct perf_tool eops = {
 	.ordered_samples	= true,
 };
 
+static const struct perf_evsel_str_handler lock_tracepoints[] = {
+	{ "lock:lock_acquire",	 perf_evsel__process_lock_acquire,   }, /* CONFIG_LOCKDEP */
+	{ "lock:lock_acquired",	 perf_evsel__process_lock_acquired,  }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+	{ "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+	{ "lock:lock_release",	 perf_evsel__process_lock_release,   }, /* CONFIG_LOCKDEP */
+};
+
 static int read_events(void)
 {
 	session = perf_session__new(input_name, O_RDONLY, 0, false, &eops);
@@ -901,6 +844,11 @@ static int read_events(void)
 		return -1;
 	}
 
+	if (perf_session__set_tracepoints_handlers(session, lock_tracepoints)) {
+		pr_err("Initializing perf session tracepoint handlers failed\n");
+		return -1;
+	}
+
 	return perf_session__process_events(session, &eops);
 }
 
@@ -967,13 +915,6 @@ static const struct option lock_options[] = {
 	OPT_END()
 };
 
-static const char * const lock_tracepoints[] = {
-	"lock:lock_acquire",    /* CONFIG_LOCKDEP */
-	"lock:lock_acquired",   /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
-	"lock:lock_contended",  /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
-	"lock:lock_release",    /* CONFIG_LOCKDEP */
-};
-
 static const char *record_args[] = {
 	"record",
 	"-R",
@@ -988,10 +929,10 @@ static int __cmd_record(int argc, const char **argv)
 	const char **rec_argv;
 
 	for (i = 0; i < ARRAY_SIZE(lock_tracepoints); i++) {
-		if (!is_valid_tracepoint(lock_tracepoints[i])) {
+		if (!is_valid_tracepoint(lock_tracepoints[i].name)) {
 				pr_err("tracepoint %s is not enabled. "
 				       "Are CONFIG_LOCKDEP and CONFIG_LOCK_STAT enabled?\n",
-				       lock_tracepoints[i]);
+				       lock_tracepoints[i].name);
 				return 1;
 		}
 	}
@@ -1009,7 +950,7 @@ static int __cmd_record(int argc, const char **argv)
 
 	for (j = 0; j < ARRAY_SIZE(lock_tracepoints); j++) {
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = strdup(lock_tracepoints[j]);
+		rec_argv[i++] = strdup(lock_tracepoints[j].name);
 	}
 
 	for (j = 1; j < (unsigned int)argc; j++, i++)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c643ed669ef9..2cb74343de3e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -297,8 +297,10 @@ try_again:
 			}
 
 			printf("\n");
-			error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
-			      err, strerror(err));
+			error("sys_perf_event_open() syscall returned with %d "
+			      "(%s) for event %s. /bin/dmesg may provide "
+			      "additional information.\n",
+			      err, strerror(err), perf_evsel__name(pos));
 
 #if defined(__i386__) || defined(__x86_64__)
 			if (attr->type == PERF_TYPE_HARDWARE &&
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 4aed1553db56..32caf13cfe01 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -14,6 +14,7 @@
 #include "util/symbol.h"
 #include "util/thread_map.h"
 #include "util/pmu.h"
+#include "event-parse.h"
 #include "../../include/linux/hw_breakpoint.h"
 
 #include <sys/mman.h>
@@ -1207,6 +1208,87 @@ static int perf_evsel__roundtrip_name_test(void)
 	return ret;
 }
 
+static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
+				  int size, bool should_be_signed)
+{
+	struct format_field *field = perf_evsel__field(evsel, name);
+	int is_signed;
+	int ret = 0;
+
+	if (field == NULL) {
+		pr_debug("%s: \"%s\" field not found!\n", evsel->name, name);
+		return -1;
+	}
+
+	is_signed = !!(field->flags | FIELD_IS_SIGNED);
+	if (should_be_signed && !is_signed) {
+		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
+			 evsel->name, name, is_signed, should_be_signed);
+		ret = -1;
+	}
+
+	if (field->size != size) {
+		pr_debug("%s: \"%s\" size (%d) should be %d!\n",
+			 evsel->name, name, field->size, size);
+		ret = -1;
+	}
+
+	return 0;
+}
+
+static int perf_evsel__tp_sched_test(void)
+{
+	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch", 0);
+	int ret = 0;
+
+	if (evsel == NULL) {
+		pr_debug("perf_evsel__new\n");
+		return -1;
+	}
+
+	if (perf_evsel__test_field(evsel, "prev_comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_prio", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prev_state", 8, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "next_prio", 4, true))
+		ret = -1;
+
+	perf_evsel__delete(evsel);
+
+	evsel = perf_evsel__newtp("sched", "sched_wakeup", 0);
+
+	if (perf_evsel__test_field(evsel, "comm", 16, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "pid", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "prio", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "success", 4, true))
+		ret = -1;
+
+	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
+		ret = -1;
+
+	return 0;
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -1254,6 +1336,10 @@ static struct test {
 		.func = perf_evsel__roundtrip_name_test,
 	},
 	{
+		.desc = "Check parsing of sched tracepoints fields",
+		.func = perf_evsel__tp_sched_test,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 55a3a6c6b9e7..b1a8a3b841cc 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -168,9 +168,8 @@ static struct per_pid *find_create_pid(int pid)
 			return cursor;
 		cursor = cursor->next;
 	}
-	cursor = malloc(sizeof(struct per_pid));
+	cursor = zalloc(sizeof(*cursor));
 	assert(cursor != NULL);
-	memset(cursor, 0, sizeof(struct per_pid));
 	cursor->pid = pid;
 	cursor->next = all_data;
 	all_data = cursor;
@@ -195,9 +194,8 @@ static void pid_set_comm(int pid, char *comm)
 		}
 		c = c->next;
 	}
-	c = malloc(sizeof(struct per_pidcomm));
+	c = zalloc(sizeof(*c));
 	assert(c != NULL);
-	memset(c, 0, sizeof(struct per_pidcomm));
 	c->comm = strdup(comm);
 	p->current = c;
 	c->next = p->all;
@@ -239,17 +237,15 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
 	p = find_create_pid(pid);
 	c = p->current;
 	if (!c) {
-		c = malloc(sizeof(struct per_pidcomm));
+		c = zalloc(sizeof(*c));
 		assert(c != NULL);
-		memset(c, 0, sizeof(struct per_pidcomm));
 		p->current = c;
 		c->next = p->all;
 		p->all = c;
 	}
 
-	sample = malloc(sizeof(struct cpu_sample));
+	sample = zalloc(sizeof(*sample));
 	assert(sample != NULL);
-	memset(sample, 0, sizeof(struct cpu_sample));
 	sample->start_time = start;
 	sample->end_time = end;
 	sample->type = type;
@@ -373,11 +369,10 @@ static void c_state_start(int cpu, u64 timestamp, int state)
 
 static void c_state_end(int cpu, u64 timestamp)
 {
-	struct power_event *pwr;
-	pwr = malloc(sizeof(struct power_event));
+	struct power_event *pwr = zalloc(sizeof(*pwr));
+
 	if (!pwr)
 		return;
-	memset(pwr, 0, sizeof(struct power_event));
 
 	pwr->state = cpus_cstate_state[cpu];
 	pwr->start_time = cpus_cstate_start_times[cpu];
@@ -392,14 +387,13 @@ static void c_state_end(int cpu, u64 timestamp)
 static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 {
 	struct power_event *pwr;
-	pwr = malloc(sizeof(struct power_event));
 
 	if (new_freq > 8000000) /* detect invalid data */
 		return;
 
+	pwr = zalloc(sizeof(*pwr));
 	if (!pwr)
 		return;
-	memset(pwr, 0, sizeof(struct power_event));
 
 	pwr->state = cpus_pstate_state[cpu];
 	pwr->start_time = cpus_pstate_start_times[cpu];
@@ -429,15 +423,13 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 static void
 sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
 {
-	struct wake_event *we;
 	struct per_pid *p;
 	struct wakeup_entry *wake = (void *)te;
+	struct wake_event *we = zalloc(sizeof(*we));
 
-	we = malloc(sizeof(struct wake_event));
 	if (!we)
 		return;
 
-	memset(we, 0, sizeof(struct wake_event));
 	we->time = timestamp;
 	we->waker = pid;
 
@@ -579,13 +571,12 @@ static void end_sample_processing(void)
 	struct power_event *pwr;
 
 	for (cpu = 0; cpu <= numcpus; cpu++) {
-		pwr = malloc(sizeof(struct power_event));
+		/* C state */
+#if 0
+		pwr = zalloc(sizeof(*pwr));
 		if (!pwr)
 			return;
-		memset(pwr, 0, sizeof(struct power_event));
 
-		/* C state */
-#if 0
 		pwr->state = cpus_cstate_state[cpu];
 		pwr->start_time = cpus_cstate_start_times[cpu];
 		pwr->end_time = last_time;
@@ -597,10 +588,9 @@ static void end_sample_processing(void)
 #endif
 		/* P state */
 
-		pwr = malloc(sizeof(struct power_event));
+		pwr = zalloc(sizeof(*pwr));
 		if (!pwr)
 			return;
-		memset(pwr, 0, sizeof(struct power_event));
 
 		pwr->state = cpus_pstate_state[cpu];
 		pwr->start_time = cpus_pstate_start_times[cpu];
@@ -830,11 +820,9 @@ static void draw_process_bars(void)
 
 static void add_process_filter(const char *string)
 {
-	struct process_filter *filt;
-	int pid;
+	int pid = strtoull(string, NULL, 10);
+	struct process_filter *filt = malloc(sizeof(*filt));
 
-	pid = strtoull(string, NULL, 10);
-	filt = malloc(sizeof(struct process_filter));
 	if (!filt)
 		return;
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1506ba0453f1..00936ad29ff2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -10,6 +10,7 @@
 #include <byteswap.h>
 #include <linux/bitops.h>
 #include "asm/bug.h"
+#include "debugfs.h"
 #include "event-parse.h"
 #include "evsel.h"
 #include "evlist.h"
@@ -69,6 +70,72 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
+static struct event_format *event_format__new(const char *sys, const char *name)
+{
+	int fd, n;
+	char *filename;
+	void *bf = NULL, *nbf;
+	size_t size = 0, alloc_size = 0;
+	struct event_format *format = NULL;
+
+	if (asprintf(&filename, "%s/%s/%s/format", tracing_events_path, sys, name) < 0)
+		goto out;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		goto out_free_filename;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (nbf == NULL)
+				goto out_free_bf;
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, BUFSIZ);
+		if (n < 0)
+			goto out_free_bf;
+		size += n;
+	} while (n > 0);
+
+	pevent_parse_format(&format, bf, size, sys);
+
+out_free_bf:
+	free(bf);
+	close(fd);
+out_free_filename:
+	free(filename);
+out:
+	return format;
+}
+
+struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx)
+{
+	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+
+	if (evsel != NULL) {
+		struct perf_event_attr attr = {
+			.type = PERF_TYPE_TRACEPOINT,
+		};
+
+		evsel->tp_format = event_format__new(sys, name);
+		if (evsel->tp_format == NULL)
+			goto out_free;
+
+		attr.config = evsel->tp_format->id;
+		perf_evsel__init(evsel, &attr, idx);
+		evsel->name = evsel->tp_format->name;
+	}
+
+	return evsel;
+
+out_free:
+	free(evsel);
+	return NULL;
+}
+
 const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
 	"cycles",
 	"instructions",
@@ -495,6 +562,10 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	perf_evsel__exit(evsel);
 	close_cgroup(evsel->cgrp);
 	free(evsel->group_name);
+	if (evsel->tp_format && evsel->name == evsel->tp_format->name) {
+		evsel->name = NULL;
+		pevent_free_format(evsel->tp_format);
+	}
 	free(evsel->name);
 	free(evsel);
 }
@@ -1002,14 +1073,19 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	return 0;
 }
 
+struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+{
+	return pevent_find_field(evsel->tp_format, name);
+}
+
 char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name)
 {
-	struct format_field *field = pevent_find_field(evsel->tp_format, name);
+	struct format_field *field = perf_evsel__field(evsel, name);
 	int offset;
 
-        if (!field)
-                return NULL;
+	if (!field)
+		return NULL;
 
 	offset = field->offset;
 
@@ -1024,11 +1100,11 @@ char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name)
 {
-	struct format_field *field = pevent_find_field(evsel->tp_format, name);
+	struct format_field *field = perf_evsel__field(evsel, name);
 	u64 val;
 
-        if (!field)
-                return 0;
+	if (!field)
+		return 0;
 
 	val = pevent_read_number(evsel->tp_format->pevent,
 				 sample->raw_data + field->offset, field->size);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 93876bad2e52..bb445d1cbc7b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,6 +81,7 @@ struct perf_evlist;
 struct perf_record_opts;
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
+struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx);
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx);
 void perf_evsel__exit(struct perf_evsel *evsel);
@@ -128,6 +129,10 @@ char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name);
 
+struct format_field;
+
+struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
+
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
 	 evsel->attr.config == PERF_COUNT_##c)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index acbf6336199e..6aae3290358e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -22,6 +22,7 @@
 #include "cpumap.h"
 #include "pmu.h"
 #include "vdso.h"
+#include "strbuf.h"
 
 static bool no_buildid_cache = false;
 
@@ -1102,118 +1103,80 @@ static int write_branch_stack(int fd __maybe_unused,
 	return 0;
 }
 
-static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
+static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
+			   FILE *fp)
 {
-	char *str = do_read_string(fd, ph);
-	fprintf(fp, "# hostname : %s\n", str);
-	free(str);
+	fprintf(fp, "# hostname : %s\n", ph->env.hostname);
 }
 
-static void print_osrelease(struct perf_header *ph, int fd, FILE *fp)
+static void print_osrelease(struct perf_header *ph, int fd __maybe_unused,
+			    FILE *fp)
 {
-	char *str = do_read_string(fd, ph);
-	fprintf(fp, "# os release : %s\n", str);
-	free(str);
+	fprintf(fp, "# os release : %s\n", ph->env.os_release);
 }
 
-static void print_arch(struct perf_header *ph, int fd, FILE *fp)
+static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
 {
-	char *str = do_read_string(fd, ph);
-	fprintf(fp, "# arch : %s\n", str);
-	free(str);
+	fprintf(fp, "# arch : %s\n", ph->env.arch);
 }
 
-static void print_cpudesc(struct perf_header *ph, int fd, FILE *fp)
+static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused,
+			  FILE *fp)
 {
-	char *str = do_read_string(fd, ph);
-	fprintf(fp, "# cpudesc : %s\n", str);
-	free(str);
+	fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc);
 }
 
-static void print_nrcpus(struct perf_header *ph, int fd, FILE *fp)
+static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused,
+			 FILE *fp)
 {
-	ssize_t ret;
-	u32 nr;
-
-	ret = read(fd, &nr, sizeof(nr));
-	if (ret != (ssize_t)sizeof(nr))
-		nr = -1; /* interpreted as error */
-
-	if (ph->needs_swap)
-		nr = bswap_32(nr);
-
-	fprintf(fp, "# nrcpus online : %u\n", nr);
-
-	ret = read(fd, &nr, sizeof(nr));
-	if (ret != (ssize_t)sizeof(nr))
-		nr = -1; /* interpreted as error */
-
-	if (ph->needs_swap)
-		nr = bswap_32(nr);
-
-	fprintf(fp, "# nrcpus avail : %u\n", nr);
+	fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online);
+	fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail);
 }
 
-static void print_version(struct perf_header *ph, int fd, FILE *fp)
+static void print_version(struct perf_header *ph, int fd __maybe_unused,
+			  FILE *fp)
 {
-	char *str = do_read_string(fd, ph);
-	fprintf(fp, "# perf version : %s\n", str);
-	free(str);
+	fprintf(fp, "# perf version : %s\n", ph->env.version);
 }
 
-static void print_cmdline(struct perf_header *ph, int fd, FILE *fp)
+static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
+			  FILE *fp)
 {
-	ssize_t ret;
+	int nr, i;
 	char *str;
-	u32 nr, i;
-
-	ret = read(fd, &nr, sizeof(nr));
-	if (ret != (ssize_t)sizeof(nr))
-		return;
 
-	if (ph->needs_swap)
-		nr = bswap_32(nr);
+	nr = ph->env.nr_cmdline;
+	str = ph->env.cmdline;
 
 	fprintf(fp, "# cmdline : ");
 
 	for (i = 0; i < nr; i++) {
-		str = do_read_string(fd, ph);
 		fprintf(fp, "%s ", str);
-		free(str);
+		str += strlen(str) + 1;
 	}
 	fputc('\n', fp);
 }
 
-static void print_cpu_topology(struct perf_header *ph, int fd, FILE *fp)
+static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
+			       FILE *fp)
 {
-	ssize_t ret;
-	u32 nr, i;
+	int nr, i;
 	char *str;
 
-	ret = read(fd, &nr, sizeof(nr));
-	if (ret != (ssize_t)sizeof(nr))
-		return;
-
-	if (ph->needs_swap)
-		nr = bswap_32(nr);
+	nr = ph->env.nr_sibling_cores;
+	str = ph->env.sibling_cores;
 
 	for (i = 0; i < nr; i++) {
-		str = do_read_string(fd, ph);
 		fprintf(fp, "# sibling cores   : %s\n", str);
-		free(str);
+		str += strlen(str) + 1;
 	}
 
-	ret = read(fd, &nr, sizeof(nr));
-	if (ret != (ssize_t)sizeof(nr))
-		return;
-
-	if (ph->needs_swap)
-		nr = bswap_32(nr);
+	nr = ph->env.nr_sibling_threads;
+	str = ph->env.sibling_threads;
 
 	for (i = 0; i < nr; i++) {
-		str = do_read_string(fd, ph);
 		fprintf(fp, "# sibling threads : %s\n", str);
-		free(str);
+		str += strlen(str) + 1;
 	}
 }
 
@@ -1374,126 +1337,89 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 	free_event_desc(events);
 }
 
-static void print_total_mem(struct perf_header *h __maybe_unused, int fd,
+static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
 			    FILE *fp)
 {
-	uint64_t mem;
-	ssize_t ret;
-
-	ret = read(fd, &mem, sizeof(mem));
-	if (ret != sizeof(mem))
-		goto error;
-
-	if (h->needs_swap)
-		mem = bswap_64(mem);
-
-	fprintf(fp, "# total memory : %"PRIu64" kB\n", mem);
-	return;
-error:
-	fprintf(fp, "# total memory : unknown\n");
+	fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem);
 }
 
-static void print_numa_topology(struct perf_header *h __maybe_unused, int fd,
+static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
 				FILE *fp)
 {
-	ssize_t ret;
 	u32 nr, c, i;
-	char *str;
+	char *str, *tmp;
 	uint64_t mem_total, mem_free;
 
 	/* nr nodes */
-	ret = read(fd, &nr, sizeof(nr));
-	if (ret != (ssize_t)sizeof(nr))
-		goto error;
-
-	if (h->needs_swap)
-		nr = bswap_32(nr);
+	nr = ph->env.nr_numa_nodes;
+	str = ph->env.numa_nodes;
 
 	for (i = 0; i < nr; i++) {
-
 		/* node number */
-		ret = read(fd, &c, sizeof(c));
-		if (ret != (ssize_t)sizeof(c))
+		c = strtoul(str, &tmp, 0);
+		if (*tmp != ':')
 			goto error;
 
-		if (h->needs_swap)
-			c = bswap_32(c);
-
-		ret = read(fd, &mem_total, sizeof(u64));
-		if (ret != sizeof(u64))
+		str = tmp + 1;
+		mem_total = strtoull(str, &tmp, 0);
+		if (*tmp != ':')
 			goto error;
 
-		ret = read(fd, &mem_free, sizeof(u64));
-		if (ret != sizeof(u64))
+		str = tmp + 1;
+		mem_free = strtoull(str, &tmp, 0);
+		if (*tmp != ':')
 			goto error;
 
-		if (h->needs_swap) {
-			mem_total = bswap_64(mem_total);
-			mem_free = bswap_64(mem_free);
-		}
-
 		fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
 			    " free = %"PRIu64" kB\n",
-			c,
-			mem_total,
-			mem_free);
+			c, mem_total, mem_free);
 
-		str = do_read_string(fd, h);
+		str = tmp + 1;
 		fprintf(fp, "# node%u cpu list : %s\n", c, str);
-		free(str);
 	}
 	return;
 error:
 	fprintf(fp, "# numa topology : not available\n");
 }
 
-static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
+static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
 {
-	char *str = do_read_string(fd, ph);
-	fprintf(fp, "# cpuid : %s\n", str);
-	free(str);
+	fprintf(fp, "# cpuid : %s\n", ph->env.cpuid);
 }
 
 static void print_branch_stack(struct perf_header *ph __maybe_unused,
-			       int fd __maybe_unused,
-			       FILE *fp)
+			       int fd __maybe_unused, FILE *fp)
 {
 	fprintf(fp, "# contains samples with branch stack\n");
 }
 
-static void print_pmu_mappings(struct perf_header *ph, int fd, FILE *fp)
+static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
+			       FILE *fp)
 {
 	const char *delimiter = "# pmu mappings: ";
-	char *name;
-	int ret;
+	char *str, *tmp;
 	u32 pmu_num;
 	u32 type;
 
-	ret = read(fd, &pmu_num, sizeof(pmu_num));
-	if (ret != sizeof(pmu_num))
-		goto error;
-
-	if (ph->needs_swap)
-		pmu_num = bswap_32(pmu_num);
-
+	pmu_num = ph->env.nr_pmu_mappings;
 	if (!pmu_num) {
 		fprintf(fp, "# pmu mappings: not available\n");
 		return;
 	}
 
+	str = ph->env.pmu_mappings;
+
 	while (pmu_num) {
-		if (read(fd, &type, sizeof(type)) != sizeof(type))
-			break;
-		if (ph->needs_swap)
-			type = bswap_32(type);
+		type = strtoul(str, &tmp, 0);
+		if (*tmp != ':')
+			goto error;
+
+		str = tmp + 1;
+		fprintf(fp, "%s%s = %" PRIu32, delimiter, str, type);
 
-		name = do_read_string(fd, ph);
-		if (!name)
-			break;
-		pmu_num--;
-		fprintf(fp, "%s%s = %" PRIu32, delimiter, name, type);
-		free(name);
 		delimiter = ", ";
+		str += strlen(str) + 1;
+		pmu_num--;
 	}
 
 	fprintf(fp, "\n");
@@ -1654,18 +1580,16 @@ out:
 	return err;
 }
 
-static int process_tracing_data(struct perf_file_section *section
-				__maybe_unused,
-			      struct perf_header *ph __maybe_unused,
-			      int feat __maybe_unused, int fd, void *data)
+static int process_tracing_data(struct perf_file_section *section __maybe_unused,
+				struct perf_header *ph __maybe_unused,
+				int fd, void *data)
 {
 	trace_report(fd, data, false);
 	return 0;
 }
 
 static int process_build_id(struct perf_file_section *section,
-			    struct perf_header *ph,
-			    int feat __maybe_unused, int fd,
+			    struct perf_header *ph, int fd,
 			    void *data __maybe_unused)
 {
 	if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
@@ -1673,6 +1597,99 @@ static int process_build_id(struct perf_file_section *section,
 	return 0;
 }
 
+static int process_hostname(struct perf_file_section *section __maybe_unused,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	ph->env.hostname = do_read_string(fd, ph);
+	return ph->env.hostname ? 0 : -ENOMEM;
+}
+
+static int process_osrelease(struct perf_file_section *section __maybe_unused,
+			     struct perf_header *ph, int fd,
+			     void *data __maybe_unused)
+{
+	ph->env.os_release = do_read_string(fd, ph);
+	return ph->env.os_release ? 0 : -ENOMEM;
+}
+
+static int process_version(struct perf_file_section *section __maybe_unused,
+			   struct perf_header *ph, int fd,
+			   void *data __maybe_unused)
+{
+	ph->env.version = do_read_string(fd, ph);
+	return ph->env.version ? 0 : -ENOMEM;
+}
+
+static int process_arch(struct perf_file_section *section __maybe_unused,
+			struct perf_header *ph,	int fd,
+			void *data __maybe_unused)
+{
+	ph->env.arch = do_read_string(fd, ph);
+	return ph->env.arch ? 0 : -ENOMEM;
+}
+
+static int process_nrcpus(struct perf_file_section *section __maybe_unused,
+			  struct perf_header *ph, int fd,
+			  void *data __maybe_unused)
+{
+	size_t ret;
+	u32 nr;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_cpus_online = nr;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_cpus_avail = nr;
+	return 0;
+}
+
+static int process_cpudesc(struct perf_file_section *section __maybe_unused,
+			   struct perf_header *ph, int fd,
+			   void *data __maybe_unused)
+{
+	ph->env.cpu_desc = do_read_string(fd, ph);
+	return ph->env.cpu_desc ? 0 : -ENOMEM;
+}
+
+static int process_cpuid(struct perf_file_section *section __maybe_unused,
+			 struct perf_header *ph,  int fd,
+			 void *data __maybe_unused)
+{
+	ph->env.cpuid = do_read_string(fd, ph);
+	return ph->env.cpuid ? 0 : -ENOMEM;
+}
+
+static int process_total_mem(struct perf_file_section *section __maybe_unused,
+			     struct perf_header *ph, int fd,
+			     void *data __maybe_unused)
+{
+	uint64_t mem;
+	size_t ret;
+
+	ret = read(fd, &mem, sizeof(mem));
+	if (ret != sizeof(mem))
+		return -1;
+
+	if (ph->needs_swap)
+		mem = bswap_64(mem);
+
+	ph->env.total_mem = mem;
+	return 0;
+}
+
 static struct perf_evsel *
 perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
@@ -1687,7 +1704,8 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 }
 
 static void
-perf_evlist__set_event_name(struct perf_evlist *evlist, struct perf_evsel *event)
+perf_evlist__set_event_name(struct perf_evlist *evlist,
+			    struct perf_evsel *event)
 {
 	struct perf_evsel *evsel;
 
@@ -1706,15 +1724,16 @@ perf_evlist__set_event_name(struct perf_evlist *evlist, struct perf_evsel *event
 
 static int
 process_event_desc(struct perf_file_section *section __maybe_unused,
-		   struct perf_header *header, int feat __maybe_unused, int fd,
+		   struct perf_header *header, int fd,
 		   void *data __maybe_unused)
 {
-	struct perf_session *session = container_of(header, struct perf_session, header);
+	struct perf_session *session;
 	struct perf_evsel *evsel, *events = read_event_desc(header, fd);
 
 	if (!events)
 		return 0;
 
+	session = container_of(header, struct perf_session, header);
 	for (evsel = events; evsel->attr.size; evsel++)
 		perf_evlist__set_event_name(session->evlist, evsel);
 
@@ -1723,11 +1742,213 @@ process_event_desc(struct perf_file_section *section __maybe_unused,
 	return 0;
 }
 
+static int process_cmdline(struct perf_file_section *section __maybe_unused,
+			   struct perf_header *ph, int fd,
+			   void *data __maybe_unused)
+{
+	size_t ret;
+	char *str;
+	u32 nr, i;
+	struct strbuf sb;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_cmdline = nr;
+	strbuf_init(&sb, 128);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
+	}
+	ph->env.cmdline = strbuf_detach(&sb, NULL);
+	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
+static int process_cpu_topology(struct perf_file_section *section __maybe_unused,
+				struct perf_header *ph, int fd,
+				void *data __maybe_unused)
+{
+	size_t ret;
+	u32 nr, i;
+	char *str;
+	struct strbuf sb;
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_sibling_cores = nr;
+	strbuf_init(&sb, 128);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
+	}
+	ph->env.sibling_cores = strbuf_detach(&sb, NULL);
+
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		return -1;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_sibling_threads = nr;
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
+	}
+	ph->env.sibling_threads = strbuf_detach(&sb, NULL);
+	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
+static int process_numa_topology(struct perf_file_section *section __maybe_unused,
+				 struct perf_header *ph, int fd,
+				 void *data __maybe_unused)
+{
+	size_t ret;
+	u32 nr, node, i;
+	char *str;
+	uint64_t mem_total, mem_free;
+	struct strbuf sb;
+
+	/* nr nodes */
+	ret = read(fd, &nr, sizeof(nr));
+	if (ret != sizeof(nr))
+		goto error;
+
+	if (ph->needs_swap)
+		nr = bswap_32(nr);
+
+	ph->env.nr_numa_nodes = nr;
+	strbuf_init(&sb, 256);
+
+	for (i = 0; i < nr; i++) {
+		/* node number */
+		ret = read(fd, &node, sizeof(node));
+		if (ret != sizeof(node))
+			goto error;
+
+		ret = read(fd, &mem_total, sizeof(u64));
+		if (ret != sizeof(u64))
+			goto error;
+
+		ret = read(fd, &mem_free, sizeof(u64));
+		if (ret != sizeof(u64))
+			goto error;
+
+		if (ph->needs_swap) {
+			node = bswap_32(node);
+			mem_total = bswap_64(mem_total);
+			mem_free = bswap_64(mem_free);
+		}
+
+		strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
+			    node, mem_total, mem_free);
+
+		str = do_read_string(fd, ph);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		strbuf_add(&sb, str, strlen(str) + 1);
+		free(str);
+	}
+	ph->env.numa_nodes = strbuf_detach(&sb, NULL);
+	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
+static int process_pmu_mappings(struct perf_file_section *section __maybe_unused,
+				struct perf_header *ph, int fd,
+				void *data __maybe_unused)
+{
+	size_t ret;
+	char *name;
+	u32 pmu_num;
+	u32 type;
+	struct strbuf sb;
+
+	ret = read(fd, &pmu_num, sizeof(pmu_num));
+	if (ret != sizeof(pmu_num))
+		return -1;
+
+	if (ph->needs_swap)
+		pmu_num = bswap_32(pmu_num);
+
+	if (!pmu_num) {
+		pr_debug("pmu mappings not available\n");
+		return 0;
+	}
+
+	ph->env.nr_pmu_mappings = pmu_num;
+	strbuf_init(&sb, 128);
+
+	while (pmu_num) {
+		if (read(fd, &type, sizeof(type)) != sizeof(type))
+			goto error;
+		if (ph->needs_swap)
+			type = bswap_32(type);
+
+		name = do_read_string(fd, ph);
+		if (!name)
+			goto error;
+
+		strbuf_addf(&sb, "%u:%s", type, name);
+		/* include a NULL character at the end */
+		strbuf_add(&sb, "", 1);
+
+		free(name);
+		pmu_num--;
+	}
+	ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
+	return 0;
+
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
 	int (*process)(struct perf_file_section *section,
-		       struct perf_header *h, int feat, int fd, void *data);
+		       struct perf_header *h, int fd, void *data);
 	const char *name;
 	bool full_only;
 };
@@ -1739,7 +1960,7 @@ struct feature_ops {
 		.process = process_##func }
 #define FEAT_OPF(n, func) \
 	[n] = { .name = #n, .write = write_##func, .print = print_##func, \
-		.full_only = true }
+		.process = process_##func, .full_only = true }
 
 /* feature_ops not implemented: */
 #define print_tracing_data	NULL
@@ -1748,20 +1969,20 @@ struct feature_ops {
 static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPP(HEADER_TRACING_DATA,	tracing_data),
 	FEAT_OPP(HEADER_BUILD_ID,	build_id),
-	FEAT_OPA(HEADER_HOSTNAME,	hostname),
-	FEAT_OPA(HEADER_OSRELEASE,	osrelease),
-	FEAT_OPA(HEADER_VERSION,	version),
-	FEAT_OPA(HEADER_ARCH,		arch),
-	FEAT_OPA(HEADER_NRCPUS,		nrcpus),
-	FEAT_OPA(HEADER_CPUDESC,	cpudesc),
-	FEAT_OPA(HEADER_CPUID,		cpuid),
-	FEAT_OPA(HEADER_TOTAL_MEM,	total_mem),
+	FEAT_OPP(HEADER_HOSTNAME,	hostname),
+	FEAT_OPP(HEADER_OSRELEASE,	osrelease),
+	FEAT_OPP(HEADER_VERSION,	version),
+	FEAT_OPP(HEADER_ARCH,		arch),
+	FEAT_OPP(HEADER_NRCPUS,		nrcpus),
+	FEAT_OPP(HEADER_CPUDESC,	cpudesc),
+	FEAT_OPP(HEADER_CPUID,		cpuid),
+	FEAT_OPP(HEADER_TOTAL_MEM,	total_mem),
 	FEAT_OPP(HEADER_EVENT_DESC,	event_desc),
-	FEAT_OPA(HEADER_CMDLINE,	cmdline),
+	FEAT_OPP(HEADER_CMDLINE,	cmdline),
 	FEAT_OPF(HEADER_CPU_TOPOLOGY,	cpu_topology),
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
-	FEAT_OPA(HEADER_PMU_MAPPINGS,	pmu_mappings),
+	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 };
 
 struct header_print_data {
@@ -2241,7 +2462,7 @@ static int perf_file_section__process(struct perf_file_section *section,
 	if (!feat_ops[feat].process)
 		return 0;
 
-	return feat_ops[feat].process(section, ph, feat, fd, data);
+	return feat_ops[feat].process(section, ph, fd, data);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 209dad4fee2b..99bdd3abce59 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -58,6 +58,29 @@ struct perf_header;
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
+struct perf_session_env {
+	char			*hostname;
+	char			*os_release;
+	char			*version;
+	char			*arch;
+	int			nr_cpus_online;
+	int			nr_cpus_avail;
+	char			*cpu_desc;
+	char			*cpuid;
+	unsigned long long	total_mem;
+
+	int			nr_cmdline;
+	char			*cmdline;
+	int			nr_sibling_cores;
+	char			*sibling_cores;
+	int			nr_sibling_threads;
+	char			*sibling_threads;
+	int			nr_numa_nodes;
+	char			*numa_nodes;
+	int			nr_pmu_mappings;
+	char			*pmu_mappings;
+};
+
 struct perf_header {
 	int			frozen;
 	bool			needs_swap;
@@ -67,6 +90,7 @@ struct perf_header {
 	u64			event_offset;
 	u64			event_size;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
+	struct perf_session_env env;
 };
 
 struct perf_evlist;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b442ee49452b..ead5316b3f89 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -243,15 +243,14 @@ size_t map__fprintf(struct map *self, FILE *fp)
 
 size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 {
-	const char *dsoname;
+	const char *dsoname = "[unknown]";
 
 	if (map && map->dso && (map->dso->name || map->dso->long_name)) {
 		if (symbol_conf.show_kernel_path && map->dso->long_name)
 			dsoname = map->dso->long_name;
 		else if (map->dso->name)
 			dsoname = map->dso->name;
-	} else
-		dsoname = "[unknown]";
+	}
 
 	return fprintf(fp, "%s", dsoname);
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 4ce04c2281d3..49a256e6e0a2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1100,6 +1100,7 @@ static int parse_probe_trace_command(const char *cmd,
 	struct probe_trace_point *tp = &tev->point;
 	char pr;
 	char *p;
+	char *argv0_str = NULL, *fmt, *fmt1_str, *fmt2_str, *fmt3_str;
 	int ret, i, argc;
 	char **argv;
 
@@ -1116,14 +1117,27 @@ static int parse_probe_trace_command(const char *cmd,
 	}
 
 	/* Scan event and group name. */
-	ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]",
-		     &pr, (float *)(void *)&tev->group,
-		     (float *)(void *)&tev->event);
-	if (ret != 3) {
+	argv0_str = strdup(argv[0]);
+	if (argv0_str == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	fmt1_str = strtok_r(argv0_str, ":", &fmt);
+	fmt2_str = strtok_r(NULL, "/", &fmt);
+	fmt3_str = strtok_r(NULL, " \t", &fmt);
+	if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL
+	    || fmt3_str == NULL) {
 		semantic_error("Failed to parse event name: %s\n", argv[0]);
 		ret = -EINVAL;
 		goto out;
 	}
+	pr = fmt1_str[0];
+	tev->group = strdup(fmt2_str);
+	tev->event = strdup(fmt3_str);
+	if (tev->group == NULL || tev->event == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr);
 
 	tp->retprobe = (pr == 'r');
@@ -1135,10 +1149,17 @@ static int parse_probe_trace_command(const char *cmd,
 		p++;
 	} else
 		p = argv[1];
-	ret = sscanf(p, "%a[^+]+%lu", (float *)(void *)&tp->symbol,
-		     &tp->offset);
-	if (ret == 1)
+	fmt1_str = strtok_r(p, "+", &fmt);
+	tp->symbol = strdup(fmt1_str);
+	if (tp->symbol == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	fmt2_str = strtok_r(NULL, "", &fmt);
+	if (fmt2_str == NULL)
 		tp->offset = 0;
+	else
+		tp->offset = strtoul(fmt2_str, NULL, 10);
 
 	tev->nargs = argc - 2;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
@@ -1162,6 +1183,7 @@ static int parse_probe_trace_command(const char *cmd,
 	}
 	ret = 0;
 out:
+	free(argv0_str);
 	argv_free(argv);
 	return ret;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index ffde3e4e34aa..f80605eb1855 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 
 	event = find_cache_event(evsel);
 	if (!event)
-		die("ug! no event found for type %d", evsel->attr.config);
+		die("ug! no event found for type %" PRIu64, evsel->attr.config);
 
 	pid = raw_field_value(event, "common_pid", data);
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 4ff45e30c726..b441b07172b7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -34,6 +34,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 	return NULL;
 }
 #else
+#define PACKAGE 'perf'
 #include <bfd.h>
 #endif
 #endif
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 70c2c13ff679..f66610b7bacf 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -16,6 +16,8 @@ struct thread {
 	bool			comm_set;
 	char			*comm;
 	int			comm_len;
+
+	void			*priv;
 };
 
 struct machine;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index aa4c860a21d1..3aabcd687cd5 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -229,24 +229,22 @@ void parse_proc_kallsyms(struct pevent *pevent,
 	char *next = NULL;
 	char *addr_str;
 	char *mod;
-	char ch;
+	char *fmt;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
 		mod = NULL;
-		sscanf(line, "%as %c %as\t[%as",
-		       (float *)(void *)&addr_str, /* workaround gcc warning */
-		       &ch, (float *)(void *)&func, (float *)(void *)&mod);
+		addr_str = strtok_r(line, " ", &fmt);
 		addr = strtoull(addr_str, NULL, 16);
-		free(addr_str);
-
-		/* truncate the extra ']' */
+		/* skip character */
+		strtok_r(NULL, " ", &fmt);
+		func = strtok_r(NULL, "\t", &fmt);
+		mod = strtok_r(NULL, "]", &fmt);
+		/* truncate the extra '[' */
 		if (mod)
-			mod[strlen(mod) - 1] = 0;
+			mod = mod + 1;
 
 		pevent_register_function(pevent, func, addr, mod);
-		free(func);
-		free(mod);
 
 		line = strtok_r(NULL, "\n", &next);
 	}