Merge branch 'drm-core-next'HEADmaster

Conflicts:
	drivers/gpu/drm/tdfx/tdfx_drv.c

93 files changed, 5734 insertions, 1948 deletions

diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore
new file mode 100644
index 00000000000..35f56be5a4c
--- /dev/null
+++ b/tools/lib/traceevent/.gitignore
@@ -0,0 +1 @@
+TRACEEVENT-CFLAGS
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 3d69aa9ff51..14131cb0522 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -207,7 +207,7 @@ libtraceevent.so: $(PEVENT_LIB_OBJS)
 libtraceevent.a: $(PEVENT_LIB_OBJS)
 	$(Q)$(do_build_static_lib)
 
-$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
 	$(Q)$(do_fpic_compile)
 
 define make_version.h
@@ -250,8 +250,12 @@ endef
 all_objs := $(sort $(ALL_OBJS))
 all_deps := $(all_objs:%.o=.%.d)
 
+# let .d file also depends on the source and header files
 define check_deps
-		$(CC) -M $(CFLAGS) $< > $@;
+		@set -e; $(RM) $@; \
+		$(CC) -M $(CFLAGS) $< > $@.$$$$; \
+		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+		$(RM) $@.$$$$
 endef
 
 $(gui_deps): ks_version.h
@@ -268,13 +272,25 @@ ifneq ($(dep_includes),)
  include $(dep_includes)
 endif
 
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+TRACEEVENT-CFLAGS: force
+	@FLAGS='$(TRACK_CFLAGS)'; \
+	    if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \
+		echo 1>&2 "    * new build flags or cross compiler"; \
+		echo "$$FLAGS" >TRACEEVENT-CFLAGS; \
+            fi
+
 tags:	force
 	$(RM) tags
-	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px
+	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
 
 TAGS:	force
 	$(RM) TAGS
-	find . -name '*.[ch]' | xargs etags
+	find . -name '*.[ch]' | xargs etags \
+	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
 
 define do_install
 	$(print_install)				\
@@ -290,8 +306,8 @@ install_lib: all_cmd install_plugins install_python
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES).*.d
-	$(RM) tags TAGS
+	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 endif # skip-makefile
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 554828219c3..5f34aa371b5 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -467,8 +467,10 @@ int pevent_register_function(struct pevent *pevent, char *func,
 		item->mod = NULL;
 	item->addr = addr;
 
-	pevent->funclist = item;
+	if (!item->func || (mod && !item->mod))
+		die("malloc func");
 
+	pevent->funclist = item;
 	pevent->func_count++;
 
 	return 0;
@@ -511,12 +513,12 @@ struct printk_list {
 
 static int printk_cmp(const void *a, const void *b)
 {
-	const struct func_map *fa = a;
-	const struct func_map *fb = b;
+	const struct printk_map *pa = a;
+	const struct printk_map *pb = b;
 
-	if (fa->addr < fb->addr)
+	if (pa->addr < pb->addr)
 		return -1;
-	if (fa->addr > fb->addr)
+	if (pa->addr > pb->addr)
 		return 1;
 
 	return 0;
@@ -583,10 +585,13 @@ int pevent_register_print_string(struct pevent *pevent, char *fmt,
 	item = malloc_or_die(sizeof(*item));
 
 	item->next = pevent->printklist;
-	pevent->printklist = item;
 	item->printk = strdup(fmt);
 	item->addr = addr;
 
+	if (!item->printk)
+		die("malloc fmt");
+
+	pevent->printklist = item;
 	pevent->printk_count++;
 
 	return 0;
@@ -616,7 +621,9 @@ static struct event_format *alloc_event(void)
 {
 	struct event_format *event;
 
-	event = malloc_or_die(sizeof(*event));
+	event = malloc(sizeof(*event));
+	if (!event)
+		return NULL;
 	memset(event, 0, sizeof(*event));
 
 	return event;
@@ -626,12 +633,8 @@ static void add_event(struct pevent *pevent, struct event_format *event)
 {
 	int i;
 
-	if (!pevent->events)
-		pevent->events = malloc_or_die(sizeof(event));
-	else
-		pevent->events =
-			realloc(pevent->events, sizeof(event) *
-				(pevent->nr_events + 1));
+	pevent->events = realloc(pevent->events, sizeof(event) *
+				 (pevent->nr_events + 1));
 	if (!pevent->events)
 		die("Can not allocate events");
 
@@ -697,6 +700,10 @@ static void free_arg(struct print_arg *arg)
 		free_arg(arg->symbol.field);
 		free_flag_sym(arg->symbol.symbols);
 		break;
+	case PRINT_HEX:
+		free_arg(arg->hex.field);
+		free_arg(arg->hex.size);
+		break;
 	case PRINT_TYPE:
 		free(arg->typecast.type);
 		free_arg(arg->typecast.item);
@@ -775,6 +782,25 @@ int pevent_peek_char(void)
 	return __peek_char();
 }
 
+static int extend_token(char **tok, char *buf, int size)
+{
+	char *newtok = realloc(*tok, size);
+
+	if (!newtok) {
+		free(*tok);
+		*tok = NULL;
+		return -1;
+	}
+
+	if (!*tok)
+		strcpy(newtok, buf);
+	else
+		strcat(newtok, buf);
+	*tok = newtok;
+
+	return 0;
+}
+
 static enum event_type force_token(const char *str, char **tok);
 
 static enum event_type __read_token(char **tok)
@@ -859,17 +885,10 @@ static enum event_type __read_token(char **tok)
 		do {
 			if (i == (BUFSIZ - 1)) {
 				buf[i] = 0;
-				if (*tok) {
-					*tok = realloc(*tok, tok_size + BUFSIZ);
-					if (!*tok)
-						return EVENT_NONE;
-					strcat(*tok, buf);
-				} else
-					*tok = strdup(buf);
+				tok_size += BUFSIZ;
 
-				if (!*tok)
+				if (extend_token(tok, buf, tok_size) < 0)
 					return EVENT_NONE;
-				tok_size += BUFSIZ;
 				i = 0;
 			}
 			last_ch = ch;
@@ -908,17 +927,10 @@ static enum event_type __read_token(char **tok)
 	while (get_type(__peek_char()) == type) {
 		if (i == (BUFSIZ - 1)) {
 			buf[i] = 0;
-			if (*tok) {
-				*tok = realloc(*tok, tok_size + BUFSIZ);
-				if (!*tok)
-					return EVENT_NONE;
-				strcat(*tok, buf);
-			} else
-				*tok = strdup(buf);
+			tok_size += BUFSIZ;
 
-			if (!*tok)
+			if (extend_token(tok, buf, tok_size) < 0)
 				return EVENT_NONE;
-			tok_size += BUFSIZ;
 			i = 0;
 		}
 		ch = __read_char();
@@ -927,14 +939,7 @@ static enum event_type __read_token(char **tok)
 
  out:
 	buf[i] = 0;
-	if (*tok) {
-		*tok = realloc(*tok, tok_size + i);
-		if (!*tok)
-			return EVENT_NONE;
-		strcat(*tok, buf);
-	} else
-		*tok = strdup(buf);
-	if (!*tok)
+	if (extend_token(tok, buf, tok_size + i + 1) < 0)
 		return EVENT_NONE;
 
 	if (type == EVENT_ITEM) {
@@ -1255,9 +1260,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 					field->flags |= FIELD_IS_POINTER;
 
 				if (field->type) {
-					field->type = realloc(field->type,
-							      strlen(field->type) +
-							      strlen(last_token) + 2);
+					char *new_type;
+					new_type = realloc(field->type,
+							   strlen(field->type) +
+							   strlen(last_token) + 2);
+					if (!new_type) {
+						free(last_token);
+						goto fail;
+					}
+					field->type = new_type;
 					strcat(field->type, " ");
 					strcat(field->type, last_token);
 					free(last_token);
@@ -1282,6 +1293,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		if (strcmp(token, "[") == 0) {
 			enum event_type last_type = type;
 			char *brackets = token;
+			char *new_brackets;
 			int len;
 
 			field->flags |= FIELD_IS_ARRAY;
@@ -1301,9 +1313,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 					len = 1;
 				last_type = type;
 
-				brackets = realloc(brackets,
-						   strlen(brackets) +
-						   strlen(token) + len);
+				new_brackets = realloc(brackets,
+						       strlen(brackets) +
+						       strlen(token) + len);
+				if (!new_brackets) {
+					free(brackets);
+					goto fail;
+				}
+				brackets = new_brackets;
 				if (len == 2)
 					strcat(brackets, " ");
 				strcat(brackets, token);
@@ -1319,7 +1336,12 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 
 			free_token(token);
 
-			brackets = realloc(brackets, strlen(brackets) + 2);
+			new_brackets = realloc(brackets, strlen(brackets) + 2);
+			if (!new_brackets) {
+				free(brackets);
+				goto fail;
+			}
+			brackets = new_brackets;
 			strcat(brackets, "]");
 
 			/* add brackets to type */
@@ -1330,10 +1352,16 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 			 * the format: type [] item;
 			 */
 			if (type == EVENT_ITEM) {
-				field->type = realloc(field->type,
-						      strlen(field->type) +
-						      strlen(field->name) +
-						      strlen(brackets) + 2);
+				char *new_type;
+				new_type = realloc(field->type,
+						   strlen(field->type) +
+						   strlen(field->name) +
+						   strlen(brackets) + 2);
+				if (!new_type) {
+					free(brackets);
+					goto fail;
+				}
+				field->type = new_type;
 				strcat(field->type, " ");
 				strcat(field->type, field->name);
 				free_token(field->name);
@@ -1341,9 +1369,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				field->name = token;
 				type = read_token(&token);
 			} else {
-				field->type = realloc(field->type,
-						      strlen(field->type) +
-						      strlen(brackets) + 1);
+				char *new_type;
+				new_type = realloc(field->type,
+						   strlen(field->type) +
+						   strlen(brackets) + 1);
+				if (!new_type) {
+					free(brackets);
+					goto fail;
+				}
+				field->type = new_type;
 				strcat(field->type, brackets);
 			}
 			free(brackets);
@@ -1726,10 +1760,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		/* could just be a type pointer */
 		if ((strcmp(arg->op.op, "*") == 0) &&
 		    type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
+			char *new_atom;
+
 			if (left->type != PRINT_ATOM)
 				die("bad pointer type");
-			left->atom.atom = realloc(left->atom.atom,
+			new_atom = realloc(left->atom.atom,
 					    strlen(left->atom.atom) + 3);
+			if (!new_atom)
+				goto out_free;
+
+			left->atom.atom = new_atom;
 			strcat(left->atom.atom, " *");
 			free(arg->op.op);
 			*arg = *left;
@@ -2146,6 +2186,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 		if (value == NULL)
 			goto out_free;
 		field->value = strdup(value);
+		if (field->value == NULL)
+			goto out_free;
 
 		free_arg(arg);
 		arg = alloc_arg();
@@ -2159,6 +2201,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
 		if (value == NULL)
 			goto out_free;
 		field->str = strdup(value);
+		if (field->str == NULL)
+			goto out_free;
 		free_arg(arg);
 		arg = NULL;
 
@@ -2260,6 +2304,45 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 }
 
 static enum event_type
+process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+{
+	struct print_arg *field;
+	enum event_type type;
+	char *token;
+
+	memset(arg, 0, sizeof(*arg));
+	arg->type = PRINT_HEX;
+
+	field = alloc_arg();
+	type = process_arg(event, field, &token);
+
+	if (test_type_token(type, token, EVENT_DELIM, ","))
+		goto out_free;
+
+	arg->hex.field = field;
+
+	free_token(token);
+
+	field = alloc_arg();
+	type = process_arg(event, field, &token);
+
+	if (test_type_token(type, token, EVENT_DELIM, ")"))
+		goto out_free;
+
+	arg->hex.size = field;
+
+	free_token(token);
+	type = read_token_item(tok);
+	return type;
+
+ out_free:
+	free_arg(field);
+	free_token(token);
+	*tok = NULL;
+	return EVENT_ERROR;
+}
+
+static enum event_type
 process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct format_field *field;
@@ -2488,6 +2571,10 @@ process_function(struct event_format *event, struct print_arg *arg,
 		is_symbolic_field = 1;
 		return process_symbols(event, arg, tok);
 	}
+	if (strcmp(token, "__print_hex") == 0) {
+		free_token(token);
+		return process_hex(event, arg, tok);
+	}
 	if (strcmp(token, "__get_str") == 0) {
 		free_token(token);
 		return process_str(event, arg, tok);
@@ -2541,7 +2628,16 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 		}
 		/* atoms can be more than one token long */
 		while (type == EVENT_ITEM) {
-			atom = realloc(atom, strlen(atom) + strlen(token) + 2);
+			char *new_atom;
+			new_atom = realloc(atom,
+					   strlen(atom) + strlen(token) + 2);
+			if (!new_atom) {
+				free(atom);
+				*tok = NULL;
+				free_token(token);
+				return EVENT_ERROR;
+			}
+			atom = new_atom;
 			strcat(atom, " ");
 			strcat(atom, token);
 			free_token(token);
@@ -2835,7 +2931,7 @@ static int get_common_info(struct pevent *pevent,
 	event = pevent->events[0];
 	field = pevent_find_common_field(event, type);
 	if (!field)
-		die("field '%s' not found", type);
+		return -1;
 
 	*offset = field->offset;
 	*size = field->size;
@@ -2886,15 +2982,16 @@ static int parse_common_flags(struct pevent *pevent, void *data)
 
 static int parse_common_lock_depth(struct pevent *pevent, void *data)
 {
-	int ret;
-
-	ret = __parse_common(pevent, data,
-			     &pevent->ld_size, &pevent->ld_offset,
-			     "common_lock_depth");
-	if (ret < 0)
-		return -1;
+	return __parse_common(pevent, data,
+			      &pevent->ld_size, &pevent->ld_offset,
+			      "common_lock_depth");
+}
 
-	return ret;
+static int parse_common_migrate_disable(struct pevent *pevent, void *data)
+{
+	return __parse_common(pevent, data,
+			      &pevent->ld_size, &pevent->ld_offset,
+			      "common_migrate_disable");
 }
 
 static int events_id_cmp(const void *a, const void *b);
@@ -2995,6 +3092,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		break;
 	case PRINT_FLAGS:
 	case PRINT_SYMBOL:
+	case PRINT_HEX:
 		break;
 	case PRINT_TYPE:
 		val = eval_num_arg(data, size, event, arg->typecast.item);
@@ -3214,11 +3312,13 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 {
 	struct pevent *pevent = event->pevent;
 	struct print_flag_sym *flag;
+	struct format_field *field;
 	unsigned long long val, fval;
 	unsigned long addr;
 	char *str;
+	unsigned char *hex;
 	int print;
-	int len;
+	int i, len;
 
 	switch (arg->type) {
 	case PRINT_NULL:
@@ -3228,27 +3328,29 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		print_str_to_seq(s, format, len_arg, arg->atom.atom);
 		return;
 	case PRINT_FIELD:
-		if (!arg->field.field) {
-			arg->field.field = pevent_find_any_field(event, arg->field.name);
-			if (!arg->field.field)
+		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);
+			arg->field.field = field;
 		}
 		/* Zero sized fields, mean the rest of the data */
-		len = arg->field.field->size ? : size - arg->field.field->offset;
+		len = field->size ? : size - field->offset;
 
 		/*
 		 * Some events pass in pointers. If this is not an array
 		 * and the size is the same as long_size, assume that it
 		 * is a pointer.
 		 */
-		if (!(arg->field.field->flags & FIELD_IS_ARRAY) &&
-		    arg->field.field->size == pevent->long_size) {
-			addr = *(unsigned long *)(data + arg->field.field->offset);
+		if (!(field->flags & FIELD_IS_ARRAY) &&
+		    field->size == pevent->long_size) {
+			addr = *(unsigned long *)(data + field->offset);
 			trace_seq_printf(s, "%lx", addr);
 			break;
 		}
 		str = malloc_or_die(len + 1);
-		memcpy(str, data + arg->field.field->offset, len);
+		memcpy(str, data + field->offset, len);
 		str[len] = 0;
 		print_str_to_seq(s, format, len_arg, str);
 		free(str);
@@ -3281,6 +3383,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			}
 		}
 		break;
+	case PRINT_HEX:
+		field = arg->hex.field->field.field;
+		if (!field) {
+			str = arg->hex.field->field.name;
+			field = pevent_find_any_field(event, str);
+			if (!field)
+				die("field %s not found", str);
+			arg->hex.field->field.field = field;
+		}
+		hex = data + field->offset;
+		len = eval_num_arg(data, size, event, arg->hex.size);
+		for (i = 0; i < len; i++) {
+			if (i)
+				trace_seq_putc(s, ' ');
+			trace_seq_printf(s, "%02x", hex[i]);
+		}
+		break;
 
 	case PRINT_TYPE:
 		break;
@@ -3299,7 +3418,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		break;
 	}
 	case PRINT_BSTRING:
-		trace_seq_printf(s, format, arg->string.string);
+		print_str_to_seq(s, format, len_arg, arg->string.string);
 		break;
 	case PRINT_OP:
 		/*
@@ -3363,6 +3482,10 @@ process_defined_func(struct trace_seq *s, void *data, int size,
 			string = malloc_or_die(sizeof(*string));
 			string->next = strings;
 			string->str = strdup(str.buffer);
+			if (!string->str)
+				die("malloc str");
+
+			args[i] = (unsigned long long)string->str;
 			strings = string;
 			trace_seq_destroy(&str);
 			break;
@@ -3400,6 +3523,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	unsigned long long ip, val;
 	char *ptr;
 	void *bptr;
+	int vsize;
 
 	field = pevent->bprint_buf_field;
 	ip_field = pevent->bprint_ip_field;
@@ -3448,6 +3572,8 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				goto process_again;
 			case '0' ... '9':
 				goto process_again;
+			case '.':
+				goto process_again;
 			case 'p':
 				ls = 1;
 				/* fall through */
@@ -3455,23 +3581,30 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 			case 'u':
 			case 'x':
 			case 'i':
-				/* the pointers are always 4 bytes aligned */
-				bptr = (void *)(((unsigned long)bptr + 3) &
-						~3);
 				switch (ls) {
 				case 0:
-					ls = 4;
+					vsize = 4;
 					break;
 				case 1:
-					ls = pevent->long_size;
+					vsize = pevent->long_size;
 					break;
 				case 2:
-					ls = 8;
+					vsize = 8;
+					break;
 				default:
+					vsize = ls; /* ? */
 					break;
 				}
-				val = pevent_read_number(pevent, bptr, ls);
-				bptr += ls;
+			/* fall through */
+			case '*':
+				if (*ptr == '*')
+					vsize = 4;
+
+				/* the pointers are always 4 bytes aligned */
+				bptr = (void *)(((unsigned long)bptr + 3) &
+						~3);
+				val = pevent_read_number(pevent, bptr, vsize);
+				bptr += vsize;
 				arg = alloc_arg();
 				arg->next = NULL;
 				arg->type = PRINT_ATOM;
@@ -3479,12 +3612,21 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				sprintf(arg->atom.atom, "%lld", val);
 				*next = arg;
 				next = &arg->next;
+				/*
+				 * The '*' case means that an arg is used as the length.
+				 * We need to continue to figure out for what.
+				 */
+				if (*ptr == '*')
+					goto process_again;
+
 				break;
 			case 's':
 				arg = alloc_arg();
 				arg->next = NULL;
 				arg->type = PRINT_BSTRING;
 				arg->string.string = strdup(bptr);
+				if (!arg->string.string)
+					break;
 				bptr += strlen(bptr) + 1;
 				*next = arg;
 				next = &arg->next;
@@ -3589,6 +3731,16 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
 	trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]);
 }
 
+static int is_printable_array(char *p, unsigned int len)
+{
+	unsigned int i;
+
+	for (i = 0; i < len && p[i]; i++)
+		if (!isprint(p[i]))
+		    return 0;
+	return 1;
+}
+
 static void print_event_fields(struct trace_seq *s, void *data, int size,
 			       struct event_format *event)
 {
@@ -3608,7 +3760,8 @@ static void print_event_fields(struct trace_seq *s, void *data, int size,
 				len = offset >> 16;
 				offset &= 0xffff;
 			}
-			if (field->flags & FIELD_IS_STRING) {
+			if (field->flags & FIELD_IS_STRING &&
+			    is_printable_array(data + offset, len)) {
 				trace_seq_printf(s, "%s", (char *)data + offset);
 			} else {
 				trace_seq_puts(s, "ARRAY[");
@@ -3619,6 +3772,7 @@ static void print_event_fields(struct trace_seq *s, void *data, int size,
 							 *((unsigned char *)data + offset + i));
 				}
 				trace_seq_putc(s, ']');
+				field->flags &= ~FIELD_IS_STRING;
 			}
 		} else {
 			val = pevent_read_number(event->pevent, data + field->offset,
@@ -3758,6 +3912,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				} else if (*(ptr+1) == 'M' || *(ptr+1) == 'm') {
 					print_mac_arg(s, *(ptr+1), data, size, event, arg);
 					ptr++;
+					arg = arg->next;
 					break;
 				}
 
@@ -3794,14 +3949,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 						break;
 					}
 				}
-				if (pevent->long_size == 8 && ls) {
+				if (pevent->long_size == 8 && ls &&
+				    sizeof(long) != 8) {
 					char *p;
 
 					ls = 2;
 					/* make %l into %ll */
 					p = strchr(format, 'l');
 					if (p)
-						memmove(p, p+1, strlen(p)+1);
+						memmove(p+1, p, strlen(p)+1);
 					else if (strcmp(format, "%p") == 0)
 						strcpy(format, "0x%llx");
 				}
@@ -3878,8 +4034,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
  * pevent_data_lat_fmt - parse the data for the latency format
  * @pevent: a handle to the pevent
  * @s: the trace_seq to write to
- * @data: the raw data to read from
- * @size: currently unused.
+ * @record: the record to read from
  *
  * This parses out the Latency format (interrupts disabled,
  * need rescheduling, in hard/soft interrupt, preempt count
@@ -3889,10 +4044,13 @@ void pevent_data_lat_fmt(struct pevent *pevent,
 			 struct trace_seq *s, struct pevent_record *record)
 {
 	static int check_lock_depth = 1;
+	static int check_migrate_disable = 1;
 	static int lock_depth_exists;
+	static int migrate_disable_exists;
 	unsigned int lat_flags;
 	unsigned int pc;
 	int lock_depth;
+	int migrate_disable;
 	int hardirq;
 	int softirq;
 	void *data = record->data;
@@ -3900,18 +4058,26 @@ void pevent_data_lat_fmt(struct pevent *pevent,
 	lat_flags = parse_common_flags(pevent, data);
 	pc = parse_common_pc(pevent, data);
 	/* lock_depth may not always exist */
-	if (check_lock_depth) {
-		struct format_field *field;
-		struct event_format *event;
-
-		check_lock_depth = 0;
-		event = pevent->events[0];
-		field = pevent_find_common_field(event, "common_lock_depth");
-		if (field)
-			lock_depth_exists = 1;
-	}
 	if (lock_depth_exists)
 		lock_depth = parse_common_lock_depth(pevent, data);
+	else if (check_lock_depth) {
+		lock_depth = parse_common_lock_depth(pevent, data);
+		if (lock_depth < 0)
+			check_lock_depth = 0;
+		else
+			lock_depth_exists = 1;
+	}
+
+	/* migrate_disable may not always exist */
+	if (migrate_disable_exists)
+		migrate_disable = parse_common_migrate_disable(pevent, data);
+	else if (check_migrate_disable) {
+		migrate_disable = parse_common_migrate_disable(pevent, data);
+		if (migrate_disable < 0)
+			check_migrate_disable = 0;
+		else
+			migrate_disable_exists = 1;
+	}
 
 	hardirq = lat_flags & TRACE_FLAG_HARDIRQ;
 	softirq = lat_flags & TRACE_FLAG_SOFTIRQ;
@@ -3930,6 +4096,13 @@ void pevent_data_lat_fmt(struct pevent *pevent,
 	else
 		trace_seq_putc(s, '.');
 
+	if (migrate_disable_exists) {
+		if (migrate_disable < 0)
+			trace_seq_putc(s, '.');
+		else
+			trace_seq_printf(s, "%d", migrate_disable);
+	}
+
 	if (lock_depth_exists) {
 		if (lock_depth < 0)
 			trace_seq_putc(s, '.');
@@ -3996,10 +4169,7 @@ const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid)
  * pevent_data_comm_from_pid - parse the data into the print format
  * @s: the trace_seq to write to
  * @event: the handle to the event
- * @cpu: the cpu the event was recorded on
- * @data: the raw data
- * @size: the size of the raw data
- * @nsecs: the timestamp of the event
+ * @record: the record to read from
  *
  * This parses the raw @data using the given @event information and
  * writes the print format into the trace_seq.
@@ -4279,6 +4449,13 @@ static void print_args(struct print_arg *args)
 		trace_seq_destroy(&s);
 		printf(")");
 		break;
+	case PRINT_HEX:
+		printf("__print_hex(");
+		print_args(args->hex.field);
+		printf(", ");
+		print_args(args->hex.size);
+		printf(")");
+		break;
 	case PRINT_STRING:
 	case PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
@@ -4541,6 +4718,8 @@ int pevent_parse_event(struct pevent *pevent,
 		die("failed to read event id");
 
 	event->system = strdup(sys);
+	if (!event->system)
+		die("failed to allocate system");
 
 	/* Add pevent to event so that it can be referenced */
 	event->pevent = pevent;
@@ -4582,6 +4761,11 @@ int pevent_parse_event(struct pevent *pevent,
 			list = &arg->next;
 			arg->type = PRINT_FIELD;
 			arg->field.name = strdup(field->name);
+			if (!arg->field.name) {
+				do_warning("failed to allocate field name");
+				event->flags |= EVENT_FL_FAILED;
+				return -1;
+			}
 			arg->field.field = field;
 		}
 		return 0;
@@ -4753,7 +4937,7 @@ int pevent_get_any_field_val(struct trace_seq *s, struct event_format *event,
  * @record: The record with the field name.
  * @err: print default error if failed.
  *
- * Returns: 0 on success, -1 field not fould, or 1 if buffer is full.
+ * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
  */
 int pevent_print_num_field(struct trace_seq *s, const char *fmt,
 			   struct event_format *event, const char *name,
@@ -4795,11 +4979,12 @@ static void free_func_handle(struct pevent_function_handler *func)
  * pevent_register_print_function - register a helper function
  * @pevent: the handle to the pevent
  * @func: the function to process the helper function
+ * @ret_type: the return type of the helper function
  * @name: the name of the helper function
  * @parameters: A list of enum pevent_func_arg_type
  *
  * Some events may have helper functions in the print format arguments.
- * This allows a plugin to dynmically create a way to process one
+ * This allows a plugin to dynamically create a way to process one
  * of these functions.
  *
  * The @parameters is a variable list of pevent_func_arg_type enums that
@@ -4870,12 +5055,13 @@ int pevent_register_print_function(struct pevent *pevent,
 }
 
 /**
- * pevent_register_event_handle - register a way to parse an event
+ * pevent_register_event_handler - register a way to parse an event
  * @pevent: the handle to the pevent
  * @id: the id of the event to register
  * @sys_name: the system name the event belongs to
  * @event_name: the name of the event
  * @func: the function to call to parse the event information
+ * @context: the data to be passed to @func
  *
  * This function allows a developer to override the parsing of
  * a given event. If for some reason the default print format
@@ -4925,6 +5111,11 @@ int pevent_register_event_handler(struct pevent *pevent,
 	if (sys_name)
 		handle->sys_name = strdup(sys_name);
 
+	if ((event_name && !handle->event_name) ||
+	    (sys_name && !handle->sys_name)) {
+		die("Failed to allocate event/sys name");
+	}
+
 	handle->func = func;
 	handle->next = pevent->handlers;
 	pevent->handlers = handle;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index ac997bc7b59..5772ad8cb38 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -226,6 +226,11 @@ struct print_arg_symbol {
 	struct print_flag_sym	*symbols;
 };
 
+struct print_arg_hex {
+	struct print_arg	*field;
+	struct print_arg	*size;
+};
+
 struct print_arg_dynarray {
 	struct format_field	*field;
 	struct print_arg	*index;
@@ -253,6 +258,7 @@ enum print_arg_type {
 	PRINT_FIELD,
 	PRINT_FLAGS,
 	PRINT_SYMBOL,
+	PRINT_HEX,
 	PRINT_TYPE,
 	PRINT_STRING,
 	PRINT_BSTRING,
@@ -270,6 +276,7 @@ struct print_arg {
 		struct print_arg_typecast	typecast;
 		struct print_arg_flags		flags;
 		struct print_arg_symbol		symbol;
+		struct print_arg_hex		hex;
 		struct print_arg_func		func;
 		struct print_arg_string		string;
 		struct print_arg_op		op;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index dfcfe2c131d..ad17855528f 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -96,7 +96,7 @@ static enum event_type read_token(char **tok)
 	    (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) &&
 	    pevent_peek_char() == '~') {
 		/* append it */
-		*tok = malloc(3);
+		*tok = malloc_or_die(3);
 		sprintf(*tok, "%c%c", *token, '~');
 		free_token(token);
 		/* Now remove the '~' from the buffer */
@@ -148,17 +148,11 @@ add_filter_type(struct event_filter *filter, int id)
 	if (filter_type)
 		return filter_type;
 
-	if (!filter->filters)
-		filter->event_filters =
-			malloc_or_die(sizeof(*filter->event_filters));
-	else {
-		filter->event_filters =
-			realloc(filter->event_filters,
-				sizeof(*filter->event_filters) *
-				(filter->filters + 1));
-		if (!filter->event_filters)
-			die("Could not allocate filter");
-	}
+	filter->event_filters =	realloc(filter->event_filters,
+					sizeof(*filter->event_filters) *
+					(filter->filters + 1));
+	if (!filter->event_filters)
+		die("Could not allocate filter");
 
 	for (i = 0; i < filter->filters; i++) {
 		if (filter->event_filters[i].event_id > id)
@@ -1480,7 +1474,7 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 {
 	struct filter_type *filter_type;
 	int count = 0;
-	int *ids;
+	int *ids = NULL;
 	int i;
 
 	if (!filter->filters)
@@ -1504,10 +1498,8 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 		default:
 			break;
 		}
-		if (count)
-			ids = realloc(ids, sizeof(*ids) * (count + 1));
-		else
-			ids = malloc(sizeof(*ids));
+
+		ids = realloc(ids, sizeof(*ids) * (count + 1));
 		if (!ids)
 			die("Can't allocate ids");
 		ids[count++] = filter_type->event_id;
@@ -1710,18 +1702,43 @@ static int test_num(struct event_format *event,
 
 static const char *get_field_str(struct filter_arg *arg, struct pevent_record *record)
 {
-	const char *val = record->data + arg->str.field->offset;
+	struct event_format *event;
+	struct pevent *pevent;
+	unsigned long long addr;
+	const char *val = NULL;
+	char hex[64];
 
-	/*
-	 * We need to copy the data since we can't be sure the field
-	 * is null terminated.
-	 */
-	if (*(val + arg->str.field->size - 1)) {
-		/* copy it */
-		memcpy(arg->str.buffer, val, arg->str.field->size);
-		/* the buffer is already NULL terminated */
-		val = arg->str.buffer;
+	/* If the field is not a string convert it */
+	if (arg->str.field->flags & FIELD_IS_STRING) {
+		val = record->data + arg->str.field->offset;
+
+		/*
+		 * We need to copy the data since we can't be sure the field
+		 * is null terminated.
+		 */
+		if (*(val + arg->str.field->size - 1)) {
+			/* copy it */
+			memcpy(arg->str.buffer, val, arg->str.field->size);
+			/* the buffer is already NULL terminated */
+			val = arg->str.buffer;
+		}
+
+	} else {
+		event = arg->str.field->event;
+		pevent = event->pevent;
+		addr = get_value(event, arg->str.field, record);
+
+		if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG))
+			/* convert to a kernel symbol */
+			val = pevent_find_function(pevent, addr);
+
+		if (val == NULL) {
+			/* just use the hex of the string name */
+			snprintf(hex, 64, "0x%llx", addr);
+			val = hex;
+		}
 	}
+
 	return val;
 }
 
@@ -2001,11 +2018,13 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *lstr;
 	char *rstr;
 	char *op;
-	char *str;
+	char *str = NULL;
 	int len;
 
 	lstr = arg_to_str(filter, arg->exp.left);
 	rstr = arg_to_str(filter, arg->exp.right);
+	if (!lstr || !rstr)
+		goto out;
 
 	switch (arg->exp.type) {
 	case FILTER_EXP_ADD:
@@ -2045,6 +2064,7 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 	len = strlen(op) + strlen(lstr) + strlen(rstr) + 4;
 	str = malloc_or_die(len);
 	snprintf(str, len, "%s %s %s", lstr, op, rstr);
+out:
 	free(lstr);
 	free(rstr);
 
@@ -2061,6 +2081,8 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 	lstr = arg_to_str(filter, arg->num.left);
 	rstr = arg_to_str(filter, arg->num.right);
+	if (!lstr || !rstr)
+		goto out;
 
 	switch (arg->num.type) {
 	case FILTER_CMP_EQ:
@@ -2097,6 +2119,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 		break;
 	}
 
+out:
 	free(lstr);
 	free(rstr);
 	return str;
@@ -2247,7 +2270,12 @@ int pevent_filter_compare(struct event_filter *filter1, struct event_filter *fil
 		/* The best way to compare complex filters is with strings */
 		str1 = arg_to_str(filter1, filter_type1->filter);
 		str2 = arg_to_str(filter2, filter_type2->filter);
-		result = strcmp(str1, str2) != 0;
+		if (str1 && str2)
+			result = strcmp(str1, str2) != 0;
+		else
+			/* bail out if allocation fails */
+			result = 1;
+
 		free(str1);
 		free(str2);
 		if (result)
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index a3dbadb26ef..7065cd6fbdf 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This 'perf bench' command is general framework for benchmark suites.
+This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
@@ -45,14 +45,20 @@ SUBSYSTEM
 'sched'::
 	Scheduler and IPC mechanisms.
 
+'mem'::
+	Memory access performance.
+
+'all'::
+	All benchmark subsystems.
+
 SUITES FOR 'sched'
 ~~~~~~~~~~~~~~~~~~
 *messaging*::
 Suite for evaluating performance of scheduler and IPC mechanisms.
 Based on hackbench by Rusty Russell.
 
-Options of *pipe*
-^^^^^^^^^^^^^^^^^
+Options of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
 -p::
 --pipe::
 Use pipe() instead of socketpair()
@@ -115,6 +121,72 @@ Example of *pipe*
                 59004 ops/sec
 ---------------------
 
+SUITES FOR 'mem'
+~~~~~~~~~~~~~~~~
+*memcpy*::
+Suite for evaluating performance of simple memory copy in various ways.
+
+Options of *memcpy*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to copy (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to copy (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
+
+-i::
+--iterations::
+Repeat memcpy invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memcpy.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memcpy.
+
+*memset*::
+Suite for evaluating performance of simple memory set in various ways.
+
+Options of *memset*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to set (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to set (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
+
+-i::
+--iterations::
+Repeat memset invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memset.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memset.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2d89f02719b..495210a612c 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -57,7 +57,7 @@ OPTIONS
 
 -s::
 --sort=::
-	Sort by key(s): pid, comm, dso, symbol, parent.
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline.
 
 -p::
 --parent=<regex>::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 4a5680cb242..5b80d84d6b4 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -112,7 +112,7 @@ Default is to monitor all CPUS.
 
 -s::
 --sort::
-	Sort by key(s): pid, comm, dso, symbol, parent
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline.
 
 -n::
 --show-nr-samples::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0eee64cfe9a..35655c3a7b7 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -155,7 +155,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -319,6 +319,8 @@ LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
 LIB_H += $(TRACE_EVENT_DIR)event-parse.h
 LIB_H += util/target.h
+LIB_H += util/rblist.h
+LIB_H += util/intlist.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -354,6 +356,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
 LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/dso-test-data.o
 LIB_OBJS += $(OUTPUT)util/color.o
 LIB_OBJS += $(OUTPUT)util/pager.o
 LIB_OBJS += $(OUTPUT)util/header.o
@@ -382,6 +385,8 @@ LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
 LIB_OBJS += $(OUTPUT)util/cgroup.o
 LIB_OBJS += $(OUTPUT)util/target.o
+LIB_OBJS += $(OUTPUT)util/rblist.o
+LIB_OBJS += $(OUTPUT)util/intlist.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
@@ -503,6 +508,7 @@ else
 		LIB_OBJS += $(OUTPUT)ui/progress.o
 		LIB_OBJS += $(OUTPUT)ui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/setup.o
+		LIB_OBJS += $(OUTPUT)ui/tui/util.o
 		LIB_H += ui/browser.h
 		LIB_H += ui/browsers/map.h
 		LIB_H += ui/helpline.h
@@ -522,13 +528,18 @@ else
 		msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
 		BASIC_CFLAGS += -DNO_GTK2_SUPPORT
 	else
+		ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y)
+			BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR
+		endif
 		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
 		EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
 		LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
+		LIB_OBJS += $(OUTPUT)ui/gtk/util.o
 		# Make sure that it'd be included only once.
 		ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),)
 			LIB_OBJS += $(OUTPUT)ui/setup.o
+			LIB_OBJS += $(OUTPUT)ui/util.o
 		endif
 	endif
 endif
@@ -797,6 +808,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $<
+
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
@@ -973,7 +987,8 @@ clean:
 	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
 	$(MAKE) -C Documentation/ clean
 	$(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
-	$(RM) $(OUTPUT)util/*-{bison,flex}*
+	$(RM) $(OUTPUT)util/*-bison*
+	$(RM) $(OUTPUT)util/*-flex*
 	$(python-clean)
 
 .PHONY: all install clean strip $(LIBTRACEEVENT)
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 71557225bf9..02dad5d3359 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -24,21 +24,21 @@
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
 static int		iterations	= 1;
-static bool		use_clock;
-static int		clock_fd;
+static bool		use_cycle;
+static int		cycle_fd;
 static bool		only_prefault;
 static bool		no_prefault;
 
 static const struct option options[] = {
 	OPT_STRING('l', "length", &length_str, "1MB",
 		    "Specify length of memory to copy. "
-		    "available unit: B, MB, GB (upper and lower)"),
+		    "Available units: B, KB, MB, GB and TB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
 	OPT_INTEGER('i', "iterations", &iterations,
 		    "repeat memcpy() invocation this number of times"),
-	OPT_BOOLEAN('c', "clock", &use_clock,
-		    "Use CPU clock for measuring"),
+	OPT_BOOLEAN('c', "cycle", &use_cycle,
+		    "Use cycles event instead of gettimeofday() for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
 		    "Show only the result with page faults before memcpy()"),
 	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -76,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = {
 	NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-	if (clock_fd < 0 && errno == ENOSYS)
+	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 	else
-		BUG_ON(clock_fd < 0);
+		BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
 	int ret;
 	u64 clk;
 
-	ret = read(clock_fd, &clk, sizeof(u64));
+	ret = read(cycle_fd, &clk, sizeof(u64));
 	BUG_ON(ret != sizeof(u64));
 
 	return clk;
@@ -119,9 +119,9 @@ static void alloc_mem(void **dst, void **src, size_t length)
 		die("memory allocation failed - maybe length is too large?\n");
 }
 
-static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
 {
-	u64 clock_start = 0ULL, clock_end = 0ULL;
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
 	void *src = NULL, *dst = NULL;
 	int i;
 
@@ -130,14 +130,14 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
 	if (prefault)
 		fn(dst, src, len);
 
-	clock_start = get_clock();
+	cycle_start = get_cycle();
 	for (i = 0; i < iterations; ++i)
 		fn(dst, src, len);
-	clock_end = get_clock();
+	cycle_end = get_cycle();
 
 	free(src);
 	free(dst);
-	return clock_end - clock_start;
+	return cycle_end - cycle_start;
 }
 
 static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
@@ -182,17 +182,17 @@ int bench_mem_memcpy(int argc, const char **argv,
 	int i;
 	size_t len;
 	double result_bps[2];
-	u64 result_clock[2];
+	u64 result_cycle[2];
 
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memcpy_usage, 0);
 
-	if (use_clock)
-		init_clock();
+	if (use_cycle)
+		init_cycle();
 
 	len = (size_t)perf_atoll((char *)length_str);
 
-	result_clock[0] = result_clock[1] = 0ULL;
+	result_cycle[0] = result_cycle[1] = 0ULL;
 	result_bps[0] = result_bps[1] = 0.0;
 
 	if ((s64)len <= 0) {
@@ -223,11 +223,11 @@ int bench_mem_memcpy(int argc, const char **argv,
 
 	if (!only_prefault && !no_prefault) {
 		/* show both of results */
-		if (use_clock) {
-			result_clock[0] =
-				do_memcpy_clock(routines[i].fn, len, false);
-			result_clock[1] =
-				do_memcpy_clock(routines[i].fn, len, true);
+		if (use_cycle) {
+			result_cycle[0] =
+				do_memcpy_cycle(routines[i].fn, len, false);
+			result_cycle[1] =
+				do_memcpy_cycle(routines[i].fn, len, true);
 		} else {
 			result_bps[0] =
 				do_memcpy_gettimeofday(routines[i].fn,
@@ -237,9 +237,9 @@ int bench_mem_memcpy(int argc, const char **argv,
 						len, true);
 		}
 	} else {
-		if (use_clock) {
-			result_clock[pf] =
-				do_memcpy_clock(routines[i].fn,
+		if (use_cycle) {
+			result_cycle[pf] =
+				do_memcpy_cycle(routines[i].fn,
 						len, only_prefault);
 		} else {
 			result_bps[pf] =
@@ -251,12 +251,12 @@ int bench_mem_memcpy(int argc, const char **argv,
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte\n",
-					(double)result_clock[0]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte\n",
+					(double)result_cycle[0]
 					/ (double)len);
-				printf(" %14lf Clock/Byte (with prefault)\n",
-					(double)result_clock[1]
+				printf(" %14lf Cycle/Byte (with prefault)\n",
+					(double)result_cycle[1]
 					/ (double)len);
 			} else {
 				print_bps(result_bps[0]);
@@ -265,9 +265,9 @@ int bench_mem_memcpy(int argc, const char **argv,
 				printf(" (with prefault)\n");
 			}
 		} else {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte",
-					(double)result_clock[pf]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte",
+					(double)result_cycle[pf]
 					/ (double)len);
 			} else
 				print_bps(result_bps[pf]);
@@ -277,17 +277,17 @@ int bench_mem_memcpy(int argc, const char **argv,
 		break;
 	case BENCH_FORMAT_SIMPLE:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
+			if (use_cycle) {
 				printf("%lf %lf\n",
-					(double)result_clock[0] / (double)len,
-					(double)result_clock[1] / (double)len);
+					(double)result_cycle[0] / (double)len,
+					(double)result_cycle[1] / (double)len);
 			} else {
 				printf("%lf %lf\n",
 					result_bps[0], result_bps[1]);
 			}
 		} else {
-			if (use_clock) {
-				printf("%lf\n", (double)result_clock[pf]
+			if (use_cycle) {
+				printf("%lf\n", (double)result_cycle[pf]
 					/ (double)len);
 			} else
 				printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index e9079185bd7..350cc955726 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -24,21 +24,21 @@
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
 static int		iterations	= 1;
-static bool		use_clock;
-static int		clock_fd;
+static bool		use_cycle;
+static int		cycle_fd;
 static bool		only_prefault;
 static bool		no_prefault;
 
 static const struct option options[] = {
 	OPT_STRING('l', "length", &length_str, "1MB",
-		    "Specify length of memory to copy. "
-		    "available unit: B, MB, GB (upper and lower)"),
+		    "Specify length of memory to set. "
+		    "Available units: B, KB, MB, GB and TB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
-		    "Specify routine to copy"),
+		    "Specify routine to set"),
 	OPT_INTEGER('i', "iterations", &iterations,
 		    "repeat memset() invocation this number of times"),
-	OPT_BOOLEAN('c', "clock", &use_clock,
-		    "Use CPU clock for measuring"),
+	OPT_BOOLEAN('c', "cycle", &use_cycle,
+		    "Use cycles event instead of gettimeofday() for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
 		    "Show only the result with page faults before memset()"),
 	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -76,27 +76,27 @@ static const char * const bench_mem_memset_usage[] = {
 	NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-	if (clock_fd < 0 && errno == ENOSYS)
+	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 	else
-		BUG_ON(clock_fd < 0);
+		BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
 	int ret;
 	u64 clk;
 
-	ret = read(clock_fd, &clk, sizeof(u64));
+	ret = read(cycle_fd, &clk, sizeof(u64));
 	BUG_ON(ret != sizeof(u64));
 
 	return clk;
@@ -115,9 +115,9 @@ static void alloc_mem(void **dst, size_t length)
 		die("memory allocation failed - maybe length is too large?\n");
 }
 
-static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
 {
-	u64 clock_start = 0ULL, clock_end = 0ULL;
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
 	void *dst = NULL;
 	int i;
 
@@ -126,13 +126,13 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
 	if (prefault)
 		fn(dst, -1, len);
 
-	clock_start = get_clock();
+	cycle_start = get_cycle();
 	for (i = 0; i < iterations; ++i)
 		fn(dst, i, len);
-	clock_end = get_clock();
+	cycle_end = get_cycle();
 
 	free(dst);
-	return clock_end - clock_start;
+	return cycle_end - cycle_start;
 }
 
 static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
@@ -176,17 +176,17 @@ int bench_mem_memset(int argc, const char **argv,
 	int i;
 	size_t len;
 	double result_bps[2];
-	u64 result_clock[2];
+	u64 result_cycle[2];
 
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memset_usage, 0);
 
-	if (use_clock)
-		init_clock();
+	if (use_cycle)
+		init_cycle();
 
 	len = (size_t)perf_atoll((char *)length_str);
 
-	result_clock[0] = result_clock[1] = 0ULL;
+	result_cycle[0] = result_cycle[1] = 0ULL;
 	result_bps[0] = result_bps[1] = 0.0;
 
 	if ((s64)len <= 0) {
@@ -217,11 +217,11 @@ int bench_mem_memset(int argc, const char **argv,
 
 	if (!only_prefault && !no_prefault) {
 		/* show both of results */
-		if (use_clock) {
-			result_clock[0] =
-				do_memset_clock(routines[i].fn, len, false);
-			result_clock[1] =
-				do_memset_clock(routines[i].fn, len, true);
+		if (use_cycle) {
+			result_cycle[0] =
+				do_memset_cycle(routines[i].fn, len, false);
+			result_cycle[1] =
+				do_memset_cycle(routines[i].fn, len, true);
 		} else {
 			result_bps[0] =
 				do_memset_gettimeofday(routines[i].fn,
@@ -231,9 +231,9 @@ int bench_mem_memset(int argc, const char **argv,
 						len, true);
 		}
 	} else {
-		if (use_clock) {
-			result_clock[pf] =
-				do_memset_clock(routines[i].fn,
+		if (use_cycle) {
+			result_cycle[pf] =
+				do_memset_cycle(routines[i].fn,
 						len, only_prefault);
 		} else {
 			result_bps[pf] =
@@ -245,12 +245,12 @@ int bench_mem_memset(int argc, const char **argv,
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte\n",
-					(double)result_clock[0]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte\n",
+					(double)result_cycle[0]
 					/ (double)len);
-				printf(" %14lf Clock/Byte (with prefault)\n ",
-					(double)result_clock[1]
+				printf(" %14lf Cycle/Byte (with prefault)\n ",
+					(double)result_cycle[1]
 					/ (double)len);
 			} else {
 				print_bps(result_bps[0]);
@@ -259,9 +259,9 @@ int bench_mem_memset(int argc, const char **argv,
 				printf(" (with prefault)\n");
 			}
 		} else {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte",
-					(double)result_clock[pf]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte",
+					(double)result_cycle[pf]
 					/ (double)len);
 			} else
 				print_bps(result_bps[pf]);
@@ -271,17 +271,17 @@ int bench_mem_memset(int argc, const char **argv,
 		break;
 	case BENCH_FORMAT_SIMPLE:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
+			if (use_cycle) {
 				printf("%lf %lf\n",
-					(double)result_clock[0] / (double)len,
-					(double)result_clock[1] / (double)len);
+					(double)result_cycle[0] / (double)len,
+					(double)result_cycle[1] / (double)len);
 			} else {
 				printf("%lf %lf\n",
 					result_bps[0], result_bps[1]);
 			}
 		} else {
-			if (use_clock) {
-				printf("%lf\n", (double)result_clock[pf]
+			if (use_cycle) {
+				printf("%lf\n", (double)result_cycle[pf]
 					/ (double)len);
 			} else
 				printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b0e74ab2d7a..1f310021644 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -33,7 +33,7 @@ struct bench_suite {
 };
 						\
 /* sentinel: easy for help */
-#define suite_all { "all", "test all suite (pseudo suite)", NULL }
+#define suite_all { "all", "Test all benchmark suites", NULL }
 
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
@@ -75,7 +75,7 @@ static struct bench_subsys subsystems[] = {
 	  "memory access performance",
 	  mem_suites },
 	{ "all",		/* sentinel: easy for help */
-	  "test all subsystem (pseudo subsystem)",
+	  "all benchmark subsystem",
 	  NULL },
 	{ NULL,
 	  NULL,
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index acd78dc2834..0dd5a058f76 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -60,7 +60,7 @@ static int __cmd_evlist(const char *input_name, struct perf_attr_details *detail
 	list_for_each_entry(pos, &session->evlist->entries, node) {
 		bool first = true;
 
-		printf("%s", event_name(pos));
+		printf("%s", perf_evsel__name(pos));
 
 		if (details->verbose || details->freq) {
 			comma_printf(&first, " sample_freq=%" PRIu64,
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 547af48deb4..ce35015f2dc 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -57,6 +57,11 @@ static unsigned long nr_allocs, nr_cross_allocs;
 
 #define PATH_SYS_NODE	"/sys/devices/system/node"
 
+struct perf_kmem {
+	struct perf_tool    tool;
+	struct perf_session *session;
+};
+
 static void init_cpunode_map(void)
 {
 	FILE *fp;
@@ -278,14 +283,16 @@ static void process_free_event(void *data,
 	s_alloc->alloc_cpu = -1;
 }
 
-static void process_raw_event(union perf_event *raw_event __used, void *data,
+static void process_raw_event(struct perf_tool *tool,
+			      union perf_event *raw_event __used, void *data,
 			      int cpu, u64 timestamp, struct thread *thread)
 {
+	struct perf_kmem *kmem = container_of(tool, struct perf_kmem, tool);
 	struct event_format *event;
 	int type;
 
-	type = trace_parse_common_type(data);
-	event = trace_find_event(type);
+	type = trace_parse_common_type(kmem->session->pevent, data);
+	event = pevent_find_event(kmem->session->pevent, type);
 
 	if (!strcmp(event->name, "kmalloc") ||
 	    !strcmp(event->name, "kmem_cache_alloc")) {
@@ -306,7 +313,7 @@ static void process_raw_event(union perf_event *raw_event __used, void *data,
 	}
 }
 
-static int process_sample_event(struct perf_tool *tool __used,
+static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel __used,
@@ -322,16 +329,18 @@ static int process_sample_event(struct perf_tool *tool __used,
 
 	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-	process_raw_event(event, sample->raw_data, sample->cpu,
+	process_raw_event(tool, event, sample->raw_data, sample->cpu,
 			  sample->time, thread);
 
 	return 0;
 }
 
-static struct perf_tool perf_kmem = {
-	.sample			= process_sample_event,
-	.comm			= perf_event__process_comm,
-	.ordered_samples	= true,
+static struct perf_kmem perf_kmem = {
+	.tool = {
+		.sample			= process_sample_event,
+		.comm			= perf_event__process_comm,
+		.ordered_samples	= true,
+	},
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -486,11 +495,15 @@ static void sort_result(void)
 static int __cmd_kmem(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
-							 0, false, &perf_kmem);
+	struct perf_session *session;
+
+	session = perf_session__new(input_name, O_RDONLY, 0, false,
+				    &perf_kmem.tool);
 	if (session == NULL)
 		return -ENOMEM;
 
+	perf_kmem.session = session;
+
 	if (perf_session__create_kernel_maps(session) < 0)
 		goto out_delete;
 
@@ -498,7 +511,7 @@ static int __cmd_kmem(void)
 		goto out_delete;
 
 	setup_pager();
-	err = perf_session__process_events(session, &perf_kmem);
+	err = perf_session__process_events(session, &perf_kmem.tool);
 	if (err != 0)
 		goto out_delete;
 	sort_result();
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index fd53319de20..b3c42854886 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -724,8 +724,8 @@ process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread)
 	struct event_format *event;
 	int type;
 
-	type = trace_parse_common_type(data);
-	event = trace_find_event(type);
+	type = trace_parse_common_type(session->pevent, data);
+	event = pevent_find_event(session->pevent, type);
 
 	if (!strcmp(event->name, "lock_acquire"))
 		process_lock_acquire_event(data, event, cpu, timestamp, thread);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f95840d04e4..4db6e1ba54e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -265,7 +265,7 @@ try_again:
 
 			if (err == ENOENT) {
 				ui__error("The %s event is not supported.\n",
-					    event_name(pos));
+					  perf_evsel__name(pos));
 				exit(EXIT_FAILURE);
 			}
 
@@ -313,7 +313,7 @@ try_again:
 		}
  	}
 
-	perf_session__update_sample_type(session);
+	perf_session__set_id_hdr_size(session);
 }
 
 static int process_buildids(struct perf_record *rec)
@@ -844,8 +844,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	struct perf_record *rec = &record;
 	char errbuf[BUFSIZ];
 
-	perf_header__set_cmdline(argc, argv);
-
 	evsel_list = perf_evlist__new(NULL, NULL);
 	if (evsel_list == NULL)
 		return -ENOMEM;
@@ -916,7 +914,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 		usage_with_options(record_usage, record_options);
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {
-		if (perf_header__push_event(pos->attr.config, event_name(pos)))
+		if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos)))
 			goto out_free_fd;
 	}
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 25249f76329..7c88a243b5d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -69,7 +69,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 
 	if ((sort__has_parent || symbol_conf.use_callchain)
 	    && sample->callchain) {
-		err = machine__resolve_callchain(machine, evsel, al->thread,
+		err = machine__resolve_callchain(machine, al->thread,
 						 sample->callchain, &parent);
 		if (err)
 			return err;
@@ -140,7 +140,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	struct hist_entry *he;
 
 	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
-		err = machine__resolve_callchain(machine, evsel, al->thread,
+		err = machine__resolve_callchain(machine, al->thread,
 						 sample->callchain, &parent);
 		if (err)
 			return err;
@@ -230,7 +230,7 @@ static int process_read_event(struct perf_tool *tool,
 	struct perf_report *rep = container_of(tool, struct perf_report, tool);
 
 	if (rep->show_threads) {
-		const char *name = evsel ? event_name(evsel) : "unknown";
+		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
 		perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
 					   event->read.id,
@@ -239,17 +239,19 @@ static int process_read_event(struct perf_tool *tool,
 	}
 
 	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-		    evsel ? event_name(evsel) : "FAIL",
+		    evsel ? perf_evsel__name(evsel) : "FAIL",
 		    event->read.value);
 
 	return 0;
 }
 
+/* For pipe mode, sample_type is not currently set */
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
+	u64 sample_type = perf_evlist__sample_type(self->evlist);
 
-	if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
 			ui__error("Selected --sort parent, but no "
 				    "callchain data. Did you call "
@@ -272,7 +274,8 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 	}
 
 	if (sort__branch_mode == 1) {
-		if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+		if (!self->fd_pipe &&
+		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
 			ui__error("Selected -b but no branch data. "
 				  "Did you call perf record without -b?\n");
 			return -1;
@@ -314,7 +317,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct hists *hists = &pos->hists;
-		const char *evname = event_name(pos);
+		const char *evname = perf_evsel__name(pos);
 
 		hists__fprintf_nr_sample_events(hists, evname, stdout);
 		hists__fprintf(hists, NULL, false, true, 0, 0, stdout);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b125e07eb39..7a9ad2b1ee7 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -43,6 +43,11 @@ static u64			sleep_measurement_overhead;
 
 static unsigned long		nr_tasks;
 
+struct perf_sched {
+	struct perf_tool    tool;
+	struct perf_session *session;
+};
+
 struct sched_atom;
 
 struct task_desc {
@@ -1597,11 +1602,13 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
 						 struct perf_evsel *evsel,
 						 struct machine *machine)
 {
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	struct pevent *pevent = sched->session->pevent;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %s event, skipping it.\n",
-			 evsel->name);
+			 perf_evsel__name(evsel));
 		return -1;
 	}
 
@@ -1612,7 +1619,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
 		tracepoint_handler f = evsel->handler.func;
 
 		if (evsel->handler.data == NULL)
-			evsel->handler.data = trace_find_event(evsel->attr.config);
+			evsel->handler.data = pevent_find_event(pevent,
+							  evsel->attr.config);
 
 		f(tool, evsel->handler.data, sample, machine, thread);
 	}
@@ -1620,12 +1628,14 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
 	return 0;
 }
 
-static struct perf_tool perf_sched = {
-	.sample			= perf_sched__process_tracepoint_sample,
-	.comm			= perf_event__process_comm,
-	.lost			= perf_event__process_lost,
-	.fork			= perf_event__process_task,
-	.ordered_samples	= true,
+static struct perf_sched perf_sched = {
+	.tool = {
+		.sample		 = perf_sched__process_tracepoint_sample,
+		.comm		 = perf_event__process_comm,
+		.lost		 = perf_event__process_lost,
+		.fork		 = perf_event__process_task,
+		.ordered_samples = true,
+	},
 };
 
 static void read_events(bool destroy, struct perf_session **psession)
@@ -1640,16 +1650,20 @@ static void read_events(bool destroy, struct perf_session **psession)
 		{ "sched:sched_process_exit", process_sched_exit_event, },
 		{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
 	};
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
-							 0, false, &perf_sched);
+	struct perf_session *session;
+
+	session = perf_session__new(input_name, O_RDONLY, 0, false,
+				    &perf_sched.tool);
 	if (session == NULL)
 		die("No Memory");
 
-	err = perf_evlist__set_tracepoints_handlers_array(session->evlist, handlers);
+	perf_sched.session = session;
+
+	err = perf_session__set_tracepoints_handlers(session, handlers);
 	assert(err == 0);
 
 	if (perf_session__has_traces(session, "record -R")) {
-		err = perf_session__process_events(session, &perf_sched);
+		err = perf_session__process_events(session, &perf_sched.tool);
 		if (err)
 			die("Failed to process events, error %d", err);
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8e395a538eb..1e60ab70b2b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -28,6 +28,11 @@ static bool			system_wide;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
+struct perf_script {
+	struct perf_tool    tool;
+	struct perf_session *session;
+};
+
 enum perf_output_field {
 	PERF_OUTPUT_COMM            = 1U << 0,
 	PERF_OUTPUT_TID             = 1U << 1,
@@ -137,10 +142,11 @@ static const char *output_field2str(enum perf_output_field field)
 
 #define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_event_attr__check_stype(struct perf_event_attr *attr,
-				  u64 sample_type, const char *sample_msg,
-				  enum perf_output_field field)
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg,
+				   enum perf_output_field field)
 {
+	struct perf_event_attr *attr = &evsel->attr;
 	int type = attr->type;
 	const char *evname;
 
@@ -148,7 +154,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr,
 		return 0;
 
 	if (output[type].user_set) {
-		evname = __event_name(attr->type, attr->config);
+		evname = perf_evsel__name(evsel);
 		pr_err("Samples for '%s' event do not have %s attribute set. "
 		       "Cannot print '%s' field.\n",
 		       evname, sample_msg, output_field2str(field));
@@ -157,7 +163,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr,
 
 	/* user did not ask for it explicitly so remove from the default list */
 	output[type].fields &= ~field;
-	evname = __event_name(attr->type, attr->config);
+	evname = perf_evsel__name(evsel);
 	pr_debug("Samples for '%s' event do not have %s attribute set. "
 		 "Skipping '%s' field.\n",
 		 evname, sample_msg, output_field2str(field));
@@ -175,8 +181,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		return -EINVAL;
 
 	if (PRINT_FIELD(IP)) {
-		if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP",
-					   PERF_OUTPUT_IP))
+		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
+					    PERF_OUTPUT_IP))
 			return -EINVAL;
 
 		if (!no_callchain &&
@@ -185,8 +191,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	}
 
 	if (PRINT_FIELD(ADDR) &&
-		perf_event_attr__check_stype(attr, PERF_SAMPLE_ADDR, "ADDR",
-				       PERF_OUTPUT_ADDR))
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+					PERF_OUTPUT_ADDR))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
@@ -208,18 +214,18 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	}
 
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
-		perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID",
-				       PERF_OUTPUT_TID|PERF_OUTPUT_PID))
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
+					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
 		return -EINVAL;
 
 	if (PRINT_FIELD(TIME) &&
-		perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME",
-				       PERF_OUTPUT_TIME))
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME",
+					PERF_OUTPUT_TIME))
 		return -EINVAL;
 
 	if (PRINT_FIELD(CPU) &&
-		perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU",
-				       PERF_OUTPUT_CPU))
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+					PERF_OUTPUT_CPU))
 		return -EINVAL;
 
 	return 0;
@@ -256,11 +262,13 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	return 0;
 }
 
-static void print_sample_start(struct perf_sample *sample,
+static void print_sample_start(struct pevent *pevent,
+			       struct perf_sample *sample,
 			       struct thread *thread,
-			       struct perf_event_attr *attr)
+			       struct perf_evsel *evsel)
 {
 	int type;
+	struct perf_event_attr *attr = &evsel->attr;
 	struct event_format *event;
 	const char *evname = NULL;
 	unsigned long secs;
@@ -300,12 +308,18 @@ static void print_sample_start(struct perf_sample *sample,
 
 	if (PRINT_FIELD(EVNAME)) {
 		if (attr->type == PERF_TYPE_TRACEPOINT) {
-			type = trace_parse_common_type(sample->raw_data);
-			event = trace_find_event(type);
+			/*
+			 * XXX Do we really need this here?
+			 * perf_evlist__set_tracepoint_names should have done
+			 * this already
+			 */
+			type = trace_parse_common_type(pevent,
+						       sample->raw_data);
+			event = pevent_find_event(pevent, type);
 			if (event)
 				evname = event->name;
 		} else
-			evname = __event_name(attr->type, attr->config);
+			evname = perf_evsel__name(evsel);
 
 		printf("%s: ", evname ? evname : "[unknown]");
 	}
@@ -387,7 +401,7 @@ static void print_sample_bts(union perf_event *event,
 			printf(" ");
 		else
 			printf("\n");
-		perf_event__print_ip(event, sample, machine, evsel,
+		perf_event__print_ip(event, sample, machine,
 				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
 				     PRINT_FIELD(SYMOFFSET));
 	}
@@ -402,6 +416,7 @@ static void print_sample_bts(union perf_event *event,
 }
 
 static void process_event(union perf_event *event __unused,
+			  struct pevent *pevent,
 			  struct perf_sample *sample,
 			  struct perf_evsel *evsel,
 			  struct machine *machine,
@@ -412,7 +427,7 @@ static void process_event(union perf_event *event __unused,
 	if (output[attr->type].fields == 0)
 		return;
 
-	print_sample_start(sample, thread, attr);
+	print_sample_start(pevent, sample, thread, evsel);
 
 	if (is_bts_event(attr)) {
 		print_sample_bts(event, sample, evsel, machine, thread);
@@ -420,7 +435,7 @@ static void process_event(union perf_event *event __unused,
 	}
 
 	if (PRINT_FIELD(TRACE))
-		print_trace_event(sample->cpu, sample->raw_data,
+		print_trace_event(pevent, sample->cpu, sample->raw_data,
 				  sample->raw_size);
 
 	if (PRINT_FIELD(ADDR))
@@ -431,7 +446,7 @@ static void process_event(union perf_event *event __unused,
 			printf(" ");
 		else
 			printf("\n");
-		perf_event__print_ip(event, sample, machine, evsel,
+		perf_event__print_ip(event, sample, machine,
 				     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
 				     PRINT_FIELD(SYMOFFSET));
 	}
@@ -451,7 +466,8 @@ static int default_stop_script(void)
 	return 0;
 }
 
-static int default_generate_script(const char *outfile __unused)
+static int default_generate_script(struct pevent *pevent __unused,
+				   const char *outfile __unused)
 {
 	return 0;
 }
@@ -489,6 +505,7 @@ static int process_sample_event(struct perf_tool *tool __used,
 				struct machine *machine)
 {
 	struct addr_location al;
+	struct perf_script *scr = container_of(tool, struct perf_script, tool);
 	struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
 
 	if (thread == NULL) {
@@ -520,24 +537,27 @@ static int process_sample_event(struct perf_tool *tool __used,
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
 		return 0;
 
-	scripting_ops->process_event(event, sample, evsel, machine, thread);
+	scripting_ops->process_event(event, scr->session->pevent,
+				     sample, evsel, machine, thread);
 
 	evsel->hists.stats.total_period += sample->period;
 	return 0;
 }
 
-static struct perf_tool perf_script = {
-	.sample		 = process_sample_event,
-	.mmap		 = perf_event__process_mmap,
-	.comm		 = perf_event__process_comm,
-	.exit		 = perf_event__process_task,
-	.fork		 = perf_event__process_task,
-	.attr		 = perf_event__process_attr,
-	.event_type	 = perf_event__process_event_type,
-	.tracing_data	 = perf_event__process_tracing_data,
-	.build_id	 = perf_event__process_build_id,
-	.ordered_samples = true,
-	.ordering_requires_timestamps = true,
+static struct perf_script perf_script = {
+	.tool = {
+		.sample		 = process_sample_event,
+		.mmap		 = perf_event__process_mmap,
+		.comm		 = perf_event__process_comm,
+		.exit		 = perf_event__process_task,
+		.fork		 = perf_event__process_task,
+		.attr		 = perf_event__process_attr,
+		.event_type	 = perf_event__process_event_type,
+		.tracing_data	 = perf_event__process_tracing_data,
+		.build_id	 = perf_event__process_build_id,
+		.ordered_samples = true,
+		.ordering_requires_timestamps = true,
+	},
 };
 
 extern volatile int session_done;
@@ -553,7 +573,7 @@ static int __cmd_script(struct perf_session *session)
 
 	signal(SIGINT, sig_handler);
 
-	ret = perf_session__process_events(session, &perf_script);
+	ret = perf_session__process_events(session, &perf_script.tool);
 
 	if (debug_mode)
 		pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
@@ -1335,10 +1355,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 	if (!script_name)
 		setup_pager();
 
-	session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_script);
+	session = perf_session__new(input_name, O_RDONLY, 0, false,
+				    &perf_script.tool);
 	if (session == NULL)
 		return -ENOMEM;
 
+	perf_script.session = session;
+
 	if (cpu_list) {
 		if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
 			return -1;
@@ -1384,7 +1407,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 			return -1;
 		}
 
-		err = scripting_ops->generate_script("perf-script");
+		err = scripting_ops->generate_script(session->pevent,
+						     "perf-script");
 		goto out;
 	}
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 07b5c7703dd..861f0aec77a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -391,7 +391,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 
 	if (verbose) {
 		fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
-			event_name(counter), count[0], count[1], count[2]);
+			perf_evsel__name(counter), count[0], count[1], count[2]);
 	}
 
 	/*
@@ -496,7 +496,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 			    errno == ENXIO) {
 				if (verbose)
 					ui__warning("%s event is not supported by the kernel.\n",
-						    event_name(counter));
+						    perf_evsel__name(counter));
 				counter->supported = false;
 				continue;
 			}
@@ -594,7 +594,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 			csv_output ? 0 : -4,
 			evsel_list->cpus->map[cpu], csv_sep);
 
-	fprintf(output, fmt, cpustr, msecs, csv_sep, event_name(evsel));
+	fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -792,7 +792,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	else
 		cpu = 0;
 
-	fprintf(output, fmt, cpustr, avg, csv_sep, event_name(evsel));
+	fprintf(output, fmt, cpustr, avg, csv_sep, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -908,7 +908,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep,
 			csv_output ? 0 : -24,
-			event_name(counter));
+			perf_evsel__name(counter));
 
 		if (counter->cgrp)
 			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
@@ -961,7 +961,7 @@ static void print_counter(struct perf_evsel *counter)
 				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 				csv_sep,
 				csv_output ? 0 : -24,
-				event_name(counter));
+				perf_evsel__name(counter));
 
 			if (counter->cgrp)
 				fprintf(output, "%s%s",
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 5a8727c0875..1d592f5cbea 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -478,7 +478,6 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
@@ -563,8 +562,7 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
@@ -583,7 +581,7 @@ static int test__basic_mmap(void)
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],
-				 event_name(evsel), nr_events[evsel->idx]);
+				 perf_evsel__name(evsel), nr_events[evsel->idx]);
 			goto out_munmap;
 		}
 	}
@@ -661,12 +659,12 @@ static int test__PERF_RECORD(void)
 	const char *cmd = "sleep";
 	const char *argv[] = { cmd, "1", NULL, };
 	char *bname;
-	u64 sample_type, prev_time = 0;
+	u64 prev_time = 0;
 	bool found_cmd_mmap = false,
 	     found_libc_mmap = false,
 	     found_vdso_mmap = false,
 	     found_ld_mmap = false;
-	int err = -1, errs = 0, i, wakeups = 0, sample_size;
+	int err = -1, errs = 0, i, wakeups = 0;
 	u32 cpu;
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
 
@@ -757,13 +755,6 @@ static int test__PERF_RECORD(void)
 	}
 
 	/*
-	 * We'll need these two to parse the PERF_SAMPLE_* fields in each
-	 * event.
-	 */
-	sample_type = perf_evlist__sample_type(evlist);
-	sample_size = __perf_evsel__sample_size(sample_type);
-
-	/*
 	 * Now that all is properly set up, enable the events, they will
 	 * count just on workload.pid, which will start...
 	 */
@@ -788,9 +779,7 @@ static int test__PERF_RECORD(void)
 				if (type < PERF_RECORD_MAX)
 					nr_events[type]++;
 
-				err = perf_event__parse_sample(event, sample_type,
-							       sample_size, true,
-							       &sample, false);
+				err = perf_evlist__parse_sample(evlist, event, &sample, false);
 				if (err < 0) {
 					if (verbose)
 						perf_event__fprintf(event, stderr);
@@ -1142,6 +1131,10 @@ static struct test {
 		.func = test__perf_pmu,
 	},
 	{
+		.desc = "Test dso data interface",
+		.func = dso__test_data,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6bb0277b7df..68cd61ef6ac 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -38,6 +38,7 @@
 #include "util/cpumap.h"
 #include "util/xyarray.h"
 #include "util/sort.h"
+#include "util/intlist.h"
 
 #include "util/debug.h"
 
@@ -125,7 +126,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		pr_err("Can't annotate %s: No vmlinux file was found in the "
 		       "path\n", sym->name);
 		sleep(1);
@@ -245,7 +246,7 @@ static void perf_top__show_details(struct perf_top *top)
 	if (notes->src == NULL)
 		goto out_unlock;
 
-	printf("Showing %s for %s\n", event_name(top->sym_evsel), symbol->name);
+	printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name);
 	printf("  Events  Pcnt (>=%d%%)\n", top->sym_pcnt_filter);
 
 	more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx,
@@ -408,7 +409,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
 	fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", top->print_entries);
 
 	if (top->evlist->nr_entries > 1)
-		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(top->sym_evsel));
+		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", perf_evsel__name(top->sym_evsel));
 
 	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top->count_filter);
 
@@ -503,13 +504,13 @@ static void perf_top__handle_keypress(struct perf_top *top, int c)
 				fprintf(stderr, "\nAvailable events:");
 
 				list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
-					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, event_name(top->sym_evsel));
+					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
 				prompt_integer(&counter, "Enter details event counter");
 
 				if (counter >= top->evlist->nr_entries) {
 					top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node);
-					fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top->sym_evsel));
+					fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
 					sleep(1);
 					break;
 				}
@@ -706,8 +707,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	int err;
 
 	if (!machine && perf_guest) {
-		pr_err("Can't find guest [%d]'s kernel information\n",
-			event->ip.pid);
+		static struct intlist *seen;
+
+		if (!seen)
+			seen = intlist__new();
+
+		if (!intlist__has_entry(seen, event->ip.pid)) {
+			pr_err("Can't find guest [%d]'s kernel information\n",
+				event->ip.pid);
+			intlist__add(seen, event->ip.pid);
+		}
 		return;
 	}
 
@@ -774,7 +783,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 		if ((sort__has_parent || symbol_conf.use_callchain) &&
 		    sample->callchain) {
-			err = machine__resolve_callchain(machine, evsel, al.thread,
+			err = machine__resolve_callchain(machine, al.thread,
 							 sample->callchain, &parent);
 			if (err)
 				return;
@@ -811,7 +820,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	int ret;
 
 	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-		ret = perf_session__parse_sample(session, event, &sample);
+		ret = perf_evlist__parse_sample(top->evlist, event, &sample, false);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
 			continue;
@@ -943,8 +952,10 @@ try_again:
 			 * based cpu-clock-tick sw counter, which
 			 * is always available even if no PMU support:
 			 */
-			if (attr->type == PERF_TYPE_HARDWARE &&
-			    attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+			if ((err == ENOENT || err == ENXIO) &&
+			    (attr->type == PERF_TYPE_HARDWARE) &&
+			    (attr->config == PERF_COUNT_HW_CPU_CYCLES)) {
+
 				if (verbose)
 					ui__warning("Cycles event not supported,\n"
 						    "trying to fall back to cpu-clock-ticks\n");
@@ -960,7 +971,7 @@ try_again:
 
 			if (err == ENOENT) {
 				ui__error("The %s event is not supported.\n",
-					    event_name(counter));
+					  perf_evsel__name(counter));
 				goto out_err;
 			} else if (err == EMFILE) {
 				ui__error("Too many events are opened.\n"
@@ -1032,7 +1043,7 @@ static int __cmd_top(struct perf_top *top)
 					       &top->session->host_machine);
 	perf_top__start_counters(top);
 	top->session->evlist = top->evlist;
-	perf_session__update_sample_type(top->session);
+	perf_session__set_id_hdr_size(top->session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index d9084e03ce5..6c18785a641 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -78,6 +78,19 @@ int main(int argc, char *argv[])
         return 0;
 }
 endef
+
+define SOURCE_GTK2_INFOBAR
+#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error \"-Wstrict-prototypes\"
+
+int main(void)
+{
+	gtk_info_bar_new();
+
+	return 0;
+}
+endef
 endif
 
 ifndef NO_LIBPERL
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 34b1c46eaf4..67a2703e666 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -814,7 +814,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 {
 	struct disasm_line *pos, *n;
 	struct annotation *notes;
-	const size_t size = symbol__size(sym);
+	size_t size;
 	struct map_symbol ms = {
 		.map = map,
 		.sym = sym,
@@ -834,6 +834,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 	if (sym == NULL)
 		return -1;
 
+	size = symbol__size(sym);
+
 	if (map->dso->annotate_warned)
 		return -1;
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 53f6697d014..413bd62eedb 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -23,6 +23,7 @@ struct hist_browser {
 	struct hists	    *hists;
 	struct hist_entry   *he_selection;
 	struct map_symbol   *selection;
+	int		     print_seq;
 	bool		     has_symbols;
 };
 
@@ -800,6 +801,196 @@ do_offset:
 	}
 }
 
+static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
+							struct callchain_node *chain_node,
+							u64 total, int level,
+							FILE *fp)
+{
+	struct rb_node *node;
+	int offset = level * LEVEL_OFFSET_STEP;
+	u64 new_total, remaining;
+	int printed = 0;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		new_total = chain_node->children_hit;
+	else
+		new_total = total;
+
+	remaining = new_total;
+	node = rb_first(&chain_node->rb_root);
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		u64 cumul = callchain_cumul_hits(child);
+		struct callchain_list *chain;
+		char folded_sign = ' ';
+		int first = true;
+		int extra_offset = 0;
+
+		remaining -= cumul;
+
+		list_for_each_entry(chain, &child->val, list) {
+			char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str;
+			const char *str;
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+
+			alloc_str = NULL;
+			str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+			if (was_first) {
+				double percent = cumul * 100.0 / new_total;
+
+				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+					str = "Not enough memory!";
+				else
+					str = alloc_str;
+			}
+
+			printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
+			free(alloc_str);
+			if (folded_sign == '+')
+				break;
+		}
+
+		if (folded_sign == '-') {
+			const int new_level = level + (extra_offset ? 2 : 1);
+			printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
+										new_level, fp);
+		}
+
+		node = next;
+	}
+
+	return printed;
+}
+
+static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
+						struct callchain_node *node,
+						int level, FILE *fp)
+{
+	struct callchain_list *chain;
+	int offset = level * LEVEL_OFFSET_STEP;
+	char folded_sign = ' ';
+	int printed = 0;
+
+	list_for_each_entry(chain, &node->val, list) {
+		char ipstr[BITS_PER_LONG / 4 + 1], *s;
+
+		folded_sign = callchain_list__folded(chain);
+		s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+		printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
+	}
+
+	if (folded_sign == '-')
+		printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
+									browser->hists->stats.total_period,
+									level + 1,  fp);
+	return printed;
+}
+
+static int hist_browser__fprintf_callchain(struct hist_browser *browser,
+					   struct rb_root *chain, int level, FILE *fp)
+{
+	struct rb_node *nd;
+	int printed = 0;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+
+		printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
+	}
+
+	return printed;
+}
+
+static int hist_browser__fprintf_entry(struct hist_browser *browser,
+				       struct hist_entry *he, FILE *fp)
+{
+	char s[8192];
+	double percent;
+	int printed = 0;
+	char folded_sign = ' ';
+
+	if (symbol_conf.use_callchain)
+		folded_sign = hist_entry__folded(he);
+
+	hist_entry__snprintf(he, s, sizeof(s), browser->hists);
+	percent = (he->period * 100.0) / browser->hists->stats.total_period;
+
+	if (symbol_conf.use_callchain)
+		printed += fprintf(fp, "%c ", folded_sign);
+
+	printed += fprintf(fp, " %5.2f%%", percent);
+
+	if (symbol_conf.show_nr_samples)
+		printed += fprintf(fp, " %11u", he->nr_events);
+
+	if (symbol_conf.show_total_period)
+		printed += fprintf(fp, " %12" PRIu64, he->period);
+
+	printed += fprintf(fp, "%s\n", rtrim(s));
+
+	if (folded_sign == '-')
+		printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+
+	return printed;
+}
+
+static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
+{
+	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries));
+	int printed = 0;
+
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		printed += hist_browser__fprintf_entry(browser, h, fp);
+		nd = hists__filter_entries(rb_next(nd));
+	}
+
+	return printed;
+}
+
+static int hist_browser__dump(struct hist_browser *browser)
+{
+	char filename[64];
+	FILE *fp;
+
+	while (1) {
+		scnprintf(filename, sizeof(filename), "perf.hist.%d", browser->print_seq);
+		if (access(filename, F_OK))
+			break;
+		/*
+ 		 * XXX: Just an arbitrary lazy upper limit
+ 		 */
+		if (++browser->print_seq == 8192) {
+			ui_helpline__fpush("Too many perf.hist.N files, nothing written!");
+			return -1;
+		}
+	}
+
+	fp = fopen(filename, "w");
+	if (fp == NULL) {
+		char bf[64];
+		const char *err = strerror_r(errno, bf, sizeof(bf));
+		ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
+		return -1;
+	}
+
+	++browser->print_seq;
+	hist_browser__fprintf(browser, fp);
+	fclose(fp);
+	ui_helpline__fpush("%s written!", filename);
+
+	return 0;
+}
+
 static struct hist_browser *hist_browser__new(struct hists *hists)
 {
 	struct hist_browser *browser = zalloc(sizeof(*browser));
@@ -937,6 +1128,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			    browser->selection->map->dso->annotate_warned)
 				continue;
 			goto do_annotate;
+		case 'P':
+			hist_browser__dump(browser);
+			continue;
 		case 'd':
 			goto zoom_dso;
 		case 't':
@@ -969,6 +1163,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					"E             Expand all callchains\n"
 					"d             Zoom into current DSO\n"
 					"t             Zoom into current Thread\n"
+					"P             Print histograms to perf.hist.N\n"
 					"/             Filter symbol by name");
 			continue;
 		case K_ENTER:
@@ -1172,7 +1367,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
 	bool current_entry = ui_browser__is_current_entry(browser, row);
 	unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
-	const char *ev_name = event_name(evsel);
+	const char *ev_name = perf_evsel__name(evsel);
 	char bf[256], unit;
 	const char *warn = " ";
 	size_t printed;
@@ -1240,7 +1435,7 @@ browse_hists:
 			 */
 			if (timer)
 				timer(arg);
-			ev_name = event_name(pos);
+			ev_name = perf_evsel__name(pos);
 			key = perf_evsel__hists_browse(pos, nr_events, help,
 						       ev_name, true, timer,
 						       arg, delay_secs);
@@ -1309,17 +1504,11 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 	ui_helpline__push("Press ESC to exit");
 
 	list_for_each_entry(pos, &evlist->entries, node) {
-		const char *ev_name = event_name(pos);
+		const char *ev_name = perf_evsel__name(pos);
 		size_t line_len = strlen(ev_name) + 7;
 
 		if (menu.b.width < line_len)
 			menu.b.width = line_len;
-		/*
-		 * Cache the evsel name, tracepoints have a _high_ cost per
-		 * event_name() call.
-		 */
-		if (pos->name == NULL)
-			pos->name = strdup(ev_name);
 	}
 
 	return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer,
@@ -1330,11 +1519,10 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  void(*timer)(void *arg), void *arg,
 				  int delay_secs)
 {
-
 	if (evlist->nr_entries == 1) {
 		struct perf_evsel *first = list_entry(evlist->entries.next,
 						      struct perf_evsel, node);
-		const char *ev_name = event_name(first);
+		const char *ev_name = perf_evsel__name(first);
 		return perf_evsel__hists_browse(first, evlist->nr_entries, help,
 						ev_name, false, timer, arg,
 						delay_secs);
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 0656c381a89..ec12e0b4ded 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -11,8 +11,8 @@
 
 static void perf_gtk__signal(int sig)
 {
+	perf_gtk__exit(false);
 	psignal(sig, "perf");
-	gtk_main_quit();
 }
 
 static void perf_gtk__resize_window(GtkWidget *window)
@@ -122,13 +122,59 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 	gtk_container_add(GTK_CONTAINER(window), view);
 }
 
+#ifdef HAVE_GTK_INFO_BAR
+static GtkWidget *perf_gtk__setup_info_bar(void)
+{
+	GtkWidget *info_bar;
+	GtkWidget *label;
+	GtkWidget *content_area;
+
+	info_bar = gtk_info_bar_new();
+	gtk_widget_set_no_show_all(info_bar, TRUE);
+
+	label = gtk_label_new("");
+	gtk_widget_show(label);
+
+	content_area = gtk_info_bar_get_content_area(GTK_INFO_BAR(info_bar));
+	gtk_container_add(GTK_CONTAINER(content_area), label);
+
+	gtk_info_bar_add_button(GTK_INFO_BAR(info_bar), GTK_STOCK_OK,
+				GTK_RESPONSE_OK);
+	g_signal_connect(info_bar, "response",
+			 G_CALLBACK(gtk_widget_hide), NULL);
+
+	pgctx->info_bar = info_bar;
+	pgctx->message_label = label;
+
+	return info_bar;
+}
+#endif
+
+static GtkWidget *perf_gtk__setup_statusbar(void)
+{
+	GtkWidget *stbar;
+	unsigned ctxid;
+
+	stbar = gtk_statusbar_new();
+
+	ctxid = gtk_statusbar_get_context_id(GTK_STATUSBAR(stbar),
+					     "perf report");
+	pgctx->statbar = stbar;
+	pgctx->statbar_ctx_id = ctxid;
+
+	return stbar;
+}
+
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 				  const char *help __used,
 				  void (*timer) (void *arg)__used,
 				  void *arg __used, int delay_secs __used)
 {
 	struct perf_evsel *pos;
+	GtkWidget *vbox;
 	GtkWidget *notebook;
+	GtkWidget *info_bar;
+	GtkWidget *statbar;
 	GtkWidget *window;
 
 	signal(SIGSEGV, perf_gtk__signal);
@@ -143,11 +189,17 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
 	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
 
+	pgctx = perf_gtk__activate_context(window);
+	if (!pgctx)
+		return -1;
+
+	vbox = gtk_vbox_new(FALSE, 0);
+
 	notebook = gtk_notebook_new();
 
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct hists *hists = &pos->hists;
-		const char *evname = event_name(pos);
+		const char *evname = perf_evsel__name(pos);
 		GtkWidget *scrolled_window;
 		GtkWidget *tab_label;
 
@@ -164,7 +216,16 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
 	}
 
-	gtk_container_add(GTK_CONTAINER(window), notebook);
+	gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
+
+	info_bar = perf_gtk__setup_info_bar();
+	if (info_bar)
+		gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0);
+
+	statbar = perf_gtk__setup_statusbar();
+	gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
+
+	gtk_container_add(GTK_CONTAINER(window), vbox);
 
 	gtk_widget_show_all(window);
 
@@ -174,5 +235,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
 	gtk_main();
 
+	perf_gtk__deactivate_context(&pgctx);
+
 	return 0;
 }
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 75177ee0403..a4d0f2b4a2d 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -1,8 +1,39 @@
 #ifndef _PERF_GTK_H_
 #define _PERF_GTK_H_ 1
 
+#include <stdbool.h>
+
 #pragma GCC diagnostic ignored "-Wstrict-prototypes"
 #include <gtk/gtk.h>
 #pragma GCC diagnostic error "-Wstrict-prototypes"
 
+
+struct perf_gtk_context {
+	GtkWidget *main_window;
+
+#ifdef HAVE_GTK_INFO_BAR
+	GtkWidget *info_bar;
+	GtkWidget *message_label;
+#endif
+	GtkWidget *statbar;
+	guint statbar_ctx_id;
+};
+
+extern struct perf_gtk_context *pgctx;
+
+static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx)
+{
+	return ctx && ctx->main_window;
+}
+
+struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window);
+int perf_gtk__deactivate_context(struct perf_gtk_context **ctx);
+
+#ifndef HAVE_GTK_INFO_BAR
+static inline GtkWidget *perf_gtk__setup_info_bar(void)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 82952995776..92879ce61e2 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -1,12 +1,17 @@
 #include "gtk.h"
 #include "../../util/cache.h"
+#include "../../util/debug.h"
+
+extern struct perf_error_ops perf_gtk_eops;
 
 int perf_gtk__init(void)
 {
+	perf_error__register(&perf_gtk_eops);
 	return gtk_init_check(NULL, NULL) ? 0 : -1;
 }
 
 void perf_gtk__exit(bool wait_for_ok __used)
 {
+	perf_error__unregister(&perf_gtk_eops);
 	gtk_main_quit();
 }
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
new file mode 100644
index 00000000000..0ead373c0df
--- /dev/null
+++ b/tools/perf/ui/gtk/util.c
@@ -0,0 +1,129 @@
+#include "../util.h"
+#include "../../util/debug.h"
+#include "gtk.h"
+
+#include <string.h>
+
+
+struct perf_gtk_context *pgctx;
+
+struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window)
+{
+	struct perf_gtk_context *ctx;
+
+	ctx = malloc(sizeof(*pgctx));
+	if (ctx)
+		ctx->main_window = window;
+
+	return ctx;
+}
+
+int perf_gtk__deactivate_context(struct perf_gtk_context **ctx)
+{
+	if (!perf_gtk__is_active_context(*ctx))
+		return -1;
+
+	free(*ctx);
+	*ctx = NULL;
+	return 0;
+}
+
+static int perf_gtk__error(const char *format, va_list args)
+{
+	char *msg;
+	GtkWidget *dialog;
+
+	if (!perf_gtk__is_active_context(pgctx) ||
+	    vasprintf(&msg, format, args) < 0) {
+		fprintf(stderr, "Error:\n");
+		vfprintf(stderr, format, args);
+		fprintf(stderr, "\n");
+		return -1;
+	}
+
+	dialog = gtk_message_dialog_new_with_markup(GTK_WINDOW(pgctx->main_window),
+					GTK_DIALOG_DESTROY_WITH_PARENT,
+					GTK_MESSAGE_ERROR,
+					GTK_BUTTONS_CLOSE,
+					"<b>Error</b>\n\n%s", msg);
+	gtk_dialog_run(GTK_DIALOG(dialog));
+
+	gtk_widget_destroy(dialog);
+	free(msg);
+	return 0;
+}
+
+#ifdef HAVE_GTK_INFO_BAR
+static int perf_gtk__warning_info_bar(const char *format, va_list args)
+{
+	char *msg;
+
+	if (!perf_gtk__is_active_context(pgctx) ||
+	    vasprintf(&msg, format, args) < 0) {
+		fprintf(stderr, "Warning:\n");
+		vfprintf(stderr, format, args);
+		fprintf(stderr, "\n");
+		return -1;
+	}
+
+	gtk_label_set_text(GTK_LABEL(pgctx->message_label), msg);
+	gtk_info_bar_set_message_type(GTK_INFO_BAR(pgctx->info_bar),
+				      GTK_MESSAGE_WARNING);
+	gtk_widget_show(pgctx->info_bar);
+
+	free(msg);
+	return 0;
+}
+#else
+static int perf_gtk__warning_statusbar(const char *format, va_list args)
+{
+	char *msg, *p;
+
+	if (!perf_gtk__is_active_context(pgctx) ||
+	    vasprintf(&msg, format, args) < 0) {
+		fprintf(stderr, "Warning:\n");
+		vfprintf(stderr, format, args);
+		fprintf(stderr, "\n");
+		return -1;
+	}
+
+	gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar),
+			  pgctx->statbar_ctx_id);
+
+	/* Only first line can be displayed */
+	p = strchr(msg, '\n');
+	if (p)
+		*p = '\0';
+
+	gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar),
+			   pgctx->statbar_ctx_id, msg);
+
+	free(msg);
+	return 0;
+}
+#endif
+
+struct perf_error_ops perf_gtk_eops = {
+	.error		= perf_gtk__error,
+#ifdef HAVE_GTK_INFO_BAR
+	.warning	= perf_gtk__warning_info_bar,
+#else
+	.warning	= perf_gtk__warning_statusbar,
+#endif
+};
+
+/*
+ * FIXME: Functions below should be implemented properly.
+ *        For now, just add stubs for NO_NEWT=1 build.
+ */
+#ifdef NO_NEWT_SUPPORT
+int ui_helpline__show_help(const char *format __used, va_list ap __used)
+{
+	return 0;
+}
+
+void ui_progress__update(u64 curr __used, u64 total __used,
+			 const char *title __used)
+{
+}
+#endif
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index d33e943ac43..e813c1d1734 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -15,6 +15,8 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 
 static volatile int ui__need_resize;
 
+extern struct perf_error_ops perf_tui_eops;
+
 void ui__refresh_dimensions(bool force)
 {
 	if (force || ui__need_resize) {
@@ -122,6 +124,8 @@ int ui__init(void)
 	signal(SIGINT, ui__signal);
 	signal(SIGQUIT, ui__signal);
 	signal(SIGTERM, ui__signal);
+
+	perf_error__register(&perf_tui_eops);
 out:
 	return err;
 }
@@ -137,4 +141,6 @@ void ui__exit(bool wait_for_ok)
 	SLsmg_refresh();
 	SLsmg_reset_smg();
 	SLang_reset_tty();
+
+	perf_error__unregister(&perf_tui_eops);
 }
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
new file mode 100644
index 00000000000..092902e30ce
--- /dev/null
+++ b/tools/perf/ui/tui/util.c
@@ -0,0 +1,243 @@
+#include "../../util/util.h"
+#include <signal.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/ttydefaults.h>
+
+#include "../../util/cache.h"
+#include "../../util/debug.h"
+#include "../browser.h"
+#include "../keysyms.h"
+#include "../helpline.h"
+#include "../ui.h"
+#include "../util.h"
+#include "../libslang.h"
+
+static void ui_browser__argv_write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	char **arg = entry;
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+	slsmg_write_nstring(*arg, browser->width);
+}
+
+static int popup_menu__run(struct ui_browser *menu)
+{
+	int key;
+
+	if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(menu, 0);
+
+		switch (key) {
+		case K_RIGHT:
+		case K_ENTER:
+			key = menu->index;
+			break;
+		case K_LEFT:
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			key = -1;
+			break;
+		default:
+			continue;
+		}
+
+		break;
+	}
+
+	ui_browser__hide(menu);
+	return key;
+}
+
+int ui__popup_menu(int argc, char * const argv[])
+{
+	struct ui_browser menu = {
+		.entries    = (void *)argv,
+		.refresh    = ui_browser__argv_refresh,
+		.seek	    = ui_browser__argv_seek,
+		.write	    = ui_browser__argv_write,
+		.nr_entries = argc,
+	};
+
+	return popup_menu__run(&menu);
+}
+
+int ui_browser__input_window(const char *title, const char *text, char *input,
+			     const char *exit_msg, int delay_secs)
+{
+	int x, y, len, key;
+	int max_len = 60, nr_lines = 0;
+	static char buf[50];
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	max_len += 2;
+	nr_lines += 8;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 7;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	y += nr_lines;
+	len = 5;
+	while (len--) {
+		SLsmg_gotorc(y + len - 1, x);
+		SLsmg_write_nstring((char *)" ", max_len);
+	}
+	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
+
+	SLsmg_gotorc(y + 3, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+
+	x += 2;
+	len = 0;
+	key = ui__getch(delay_secs);
+	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+		if (key == K_BKSPC) {
+			if (len == 0)
+				goto next_key;
+			SLsmg_gotorc(y, x + --len);
+			SLsmg_write_char(' ');
+		} else {
+			buf[len] = key;
+			SLsmg_gotorc(y, x + len++);
+			SLsmg_write_char(key);
+		}
+		SLsmg_refresh();
+
+		/* XXX more graceful overflow handling needed */
+		if (len == sizeof(buf) - 1) {
+			ui_helpline__push("maximum size of symbol name reached!");
+			key = K_ENTER;
+			break;
+		}
+next_key:
+		key = ui__getch(delay_secs);
+	}
+
+	buf[len] = '\0';
+	strncpy(input, buf, len+1);
+	return key;
+}
+
+int ui__question_window(const char *title, const char *text,
+			const char *exit_msg, int delay_secs)
+{
+	int x, y;
+	int max_len = 0, nr_lines = 0;
+	const char *t;
+
+	t = text;
+	while (1) {
+		const char *sep = strchr(t, '\n');
+		int len;
+
+		if (sep == NULL)
+			sep = strchr(t, '\0');
+		len = sep - t;
+		if (max_len < len)
+			max_len = len;
+		++nr_lines;
+		if (*sep == '\0')
+			break;
+		t = sep + 1;
+	}
+
+	max_len += 2;
+	nr_lines += 4;
+	y = SLtt_Screen_Rows / 2 - nr_lines / 2,
+	x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+	SLsmg_set_color(0);
+	SLsmg_draw_box(y, x++, nr_lines, max_len);
+	if (title) {
+		SLsmg_gotorc(y, x + 1);
+		SLsmg_write_string((char *)title);
+	}
+	SLsmg_gotorc(++y, x);
+	nr_lines -= 2;
+	max_len -= 2;
+	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+				   nr_lines, max_len, 1);
+	SLsmg_gotorc(y + nr_lines - 2, x);
+	SLsmg_write_nstring((char *)" ", max_len);
+	SLsmg_gotorc(y + nr_lines - 1, x);
+	SLsmg_write_nstring((char *)exit_msg, max_len);
+	SLsmg_refresh();
+	return ui__getch(delay_secs);
+}
+
+int ui__help_window(const char *text)
+{
+	return ui__question_window("Help", text, "Press any key...", 0);
+}
+
+int ui__dialog_yesno(const char *msg)
+{
+	return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0);
+}
+
+static int __ui__warning(const char *title, const char *format, va_list args)
+{
+	char *s;
+
+	if (vasprintf(&s, format, args) > 0) {
+		int key;
+
+		pthread_mutex_lock(&ui__lock);
+		key = ui__question_window(title, s, "Press any key...", 0);
+		pthread_mutex_unlock(&ui__lock);
+		free(s);
+		return key;
+	}
+
+	fprintf(stderr, "%s\n", title);
+	vfprintf(stderr, format, args);
+	return K_ESC;
+}
+
+static int perf_tui__error(const char *format, va_list args)
+{
+	return __ui__warning("Error:", format, args);
+}
+
+static int perf_tui__warning(const char *format, va_list args)
+{
+	return __ui__warning("Warning:", format, args);
+}
+
+struct perf_error_ops perf_tui_eops = {
+	.error		= perf_tui__error,
+	.warning	= perf_tui__warning,
+};
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
index ad4374a16bb..4f989774c8c 100644
--- a/tools/perf/ui/util.c
+++ b/tools/perf/ui/util.c
@@ -1,250 +1,85 @@
-#include "../util.h"
-#include <signal.h>
-#include <stdbool.h>
-#include <string.h>
-#include <sys/ttydefaults.h>
-
-#include "../cache.h"
-#include "../debug.h"
-#include "browser.h"
-#include "keysyms.h"
-#include "helpline.h"
-#include "ui.h"
 #include "util.h"
-#include "libslang.h"
-
-static void ui_browser__argv_write(struct ui_browser *browser,
-				   void *entry, int row)
-{
-	char **arg = entry;
-	bool current_entry = ui_browser__is_current_entry(browser, row);
-
-	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
-						       HE_COLORSET_NORMAL);
-	slsmg_write_nstring(*arg, browser->width);
-}
-
-static int popup_menu__run(struct ui_browser *menu)
-{
-	int key;
-
-	if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0)
-		return -1;
+#include "../debug.h"
 
-	while (1) {
-		key = ui_browser__run(menu, 0);
-
-		switch (key) {
-		case K_RIGHT:
-		case K_ENTER:
-			key = menu->index;
-			break;
-		case K_LEFT:
-		case K_ESC:
-		case 'q':
-		case CTRL('c'):
-			key = -1;
-			break;
-		default:
-			continue;
-		}
-
-		break;
-	}
-
-	ui_browser__hide(menu);
-	return key;
-}
 
-int ui__popup_menu(int argc, char * const argv[])
+/*
+ * Default error logging functions
+ */
+static int perf_stdio__error(const char *format, va_list args)
 {
-	struct ui_browser menu = {
-		.entries    = (void *)argv,
-		.refresh    = ui_browser__argv_refresh,
-		.seek	    = ui_browser__argv_seek,
-		.write	    = ui_browser__argv_write,
-		.nr_entries = argc,
-	};
-
-	return popup_menu__run(&menu);
+	fprintf(stderr, "Error:\n");
+	vfprintf(stderr, format, args);
+	return 0;
 }
 
-int ui_browser__input_window(const char *title, const char *text, char *input,
-			     const char *exit_msg, int delay_secs)
+static int perf_stdio__warning(const char *format, va_list args)
 {
-	int x, y, len, key;
-	int max_len = 60, nr_lines = 0;
-	static char buf[50];
-	const char *t;
-
-	t = text;
-	while (1) {
-		const char *sep = strchr(t, '\n');
-
-		if (sep == NULL)
-			sep = strchr(t, '\0');
-		len = sep - t;
-		if (max_len < len)
-			max_len = len;
-		++nr_lines;
-		if (*sep == '\0')
-			break;
-		t = sep + 1;
-	}
-
-	max_len += 2;
-	nr_lines += 8;
-	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
-	x = SLtt_Screen_Cols / 2 - max_len / 2;
-
-	SLsmg_set_color(0);
-	SLsmg_draw_box(y, x++, nr_lines, max_len);
-	if (title) {
-		SLsmg_gotorc(y, x + 1);
-		SLsmg_write_string((char *)title);
-	}
-	SLsmg_gotorc(++y, x);
-	nr_lines -= 7;
-	max_len -= 2;
-	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
-				   nr_lines, max_len, 1);
-	y += nr_lines;
-	len = 5;
-	while (len--) {
-		SLsmg_gotorc(y + len - 1, x);
-		SLsmg_write_nstring((char *)" ", max_len);
-	}
-	SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
-
-	SLsmg_gotorc(y + 3, x);
-	SLsmg_write_nstring((char *)exit_msg, max_len);
-	SLsmg_refresh();
-
-	x += 2;
-	len = 0;
-	key = ui__getch(delay_secs);
-	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
-		if (key == K_BKSPC) {
-			if (len == 0)
-				goto next_key;
-			SLsmg_gotorc(y, x + --len);
-			SLsmg_write_char(' ');
-		} else {
-			buf[len] = key;
-			SLsmg_gotorc(y, x + len++);
-			SLsmg_write_char(key);
-		}
-		SLsmg_refresh();
-
-		/* XXX more graceful overflow handling needed */
-		if (len == sizeof(buf) - 1) {
-			ui_helpline__push("maximum size of symbol name reached!");
-			key = K_ENTER;
-			break;
-		}
-next_key:
-		key = ui__getch(delay_secs);
-	}
-
-	buf[len] = '\0';
-	strncpy(input, buf, len+1);
-	return key;
+	fprintf(stderr, "Warning:\n");
+	vfprintf(stderr, format, args);
+	return 0;
 }
 
-int ui__question_window(const char *title, const char *text,
-			const char *exit_msg, int delay_secs)
+static struct perf_error_ops default_eops =
 {
-	int x, y;
-	int max_len = 0, nr_lines = 0;
-	const char *t;
-
-	t = text;
-	while (1) {
-		const char *sep = strchr(t, '\n');
-		int len;
-
-		if (sep == NULL)
-			sep = strchr(t, '\0');
-		len = sep - t;
-		if (max_len < len)
-			max_len = len;
-		++nr_lines;
-		if (*sep == '\0')
-			break;
-		t = sep + 1;
-	}
-
-	max_len += 2;
-	nr_lines += 4;
-	y = SLtt_Screen_Rows / 2 - nr_lines / 2,
-	x = SLtt_Screen_Cols / 2 - max_len / 2;
-
-	SLsmg_set_color(0);
-	SLsmg_draw_box(y, x++, nr_lines, max_len);
-	if (title) {
-		SLsmg_gotorc(y, x + 1);
-		SLsmg_write_string((char *)title);
-	}
-	SLsmg_gotorc(++y, x);
-	nr_lines -= 2;
-	max_len -= 2;
-	SLsmg_write_wrapped_string((unsigned char *)text, y, x,
-				   nr_lines, max_len, 1);
-	SLsmg_gotorc(y + nr_lines - 2, x);
-	SLsmg_write_nstring((char *)" ", max_len);
-	SLsmg_gotorc(y + nr_lines - 1, x);
-	SLsmg_write_nstring((char *)exit_msg, max_len);
-	SLsmg_refresh();
-	return ui__getch(delay_secs);
-}
+	.error		= perf_stdio__error,
+	.warning	= perf_stdio__warning,
+};
 
-int ui__help_window(const char *text)
-{
-	return ui__question_window("Help", text, "Press any key...", 0);
-}
+static struct perf_error_ops *perf_eops = &default_eops;
 
-int ui__dialog_yesno(const char *msg)
-{
-	return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0);
-}
 
-int __ui__warning(const char *title, const char *format, va_list args)
+int ui__error(const char *format, ...)
 {
-	char *s;
-
-	if (use_browser > 0 && vasprintf(&s, format, args) > 0) {
-		int key;
+	int ret;
+	va_list args;
 
-		pthread_mutex_lock(&ui__lock);
-		key = ui__question_window(title, s, "Press any key...", 0);
-		pthread_mutex_unlock(&ui__lock);
-		free(s);
-		return key;
-	}
+	va_start(args, format);
+	ret = perf_eops->error(format, args);
+	va_end(args);
 
-	fprintf(stderr, "%s:\n", title);
-	vfprintf(stderr, format, args);
-	return K_ESC;
+	return ret;
 }
 
 int ui__warning(const char *format, ...)
 {
-	int key;
+	int ret;
 	va_list args;
 
 	va_start(args, format);
-	key = __ui__warning("Warning", format, args);
+	ret = perf_eops->warning(format, args);
 	va_end(args);
-	return key;
+
+	return ret;
 }
 
-int ui__error(const char *format, ...)
+
+/**
+ * perf_error__register - Register error logging functions
+ * @eops: The pointer to error logging function struct
+ *
+ * Register UI-specific error logging functions. Before calling this,
+ * other logging functions should be unregistered, if any.
+ */
+int perf_error__register(struct perf_error_ops *eops)
 {
-	int key;
-	va_list args;
+	if (perf_eops != &default_eops)
+		return -1;
 
-	va_start(args, format);
-	key = __ui__warning("Error", format, args);
-	va_end(args);
-	return key;
+	perf_eops = eops;
+	return 0;
+}
+
+/**
+ * perf_error__unregister - Unregister error logging functions
+ * @eops: The pointer to error logging function struct
+ *
+ * Unregister already registered error logging functions.
+ */
+int perf_error__unregister(struct perf_error_ops *eops)
+{
+	if (perf_eops != eops)
+		return -1;
+
+	perf_eops = &default_eops;
+	return 0;
 }
diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h
index 2d1738bd71c..361f08c52d3 100644
--- a/tools/perf/ui/util.h
+++ b/tools/perf/ui/util.h
@@ -9,6 +9,13 @@ int ui__help_window(const char *text);
 int ui__dialog_yesno(const char *msg);
 int ui__question_window(const char *title, const char *text,
 			const char *exit_msg, int delay_secs);
-int __ui__warning(const char *title, const char *format, va_list args);
+
+struct perf_error_ops {
+	int (*error)(const char *format, va_list args);
+	int (*warning)(const char *format, va_list args);
+};
+
+int perf_error__register(struct perf_error_ops *eops);
+int perf_error__unregister(struct perf_error_ops *eops);
 
 #endif /* _PERF_UI_UTIL_H_ */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8069dfb5ba7..3a282c0057d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -426,7 +426,18 @@ int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	const size_t size = symbol__size(sym);
-	size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+	size_t sizeof_sym_hist;
+
+	/* Check for overflow when calculating sizeof_sym_hist */
+	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64))
+		return -1;
+
+	sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+
+	/* Check for overflow in zalloc argument */
+	if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
+				/ symbol_conf.nr_events)
+		return -1;
 
 	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
 	if (notes->src == NULL)
@@ -777,7 +788,7 @@ fallback:
 		free_filename = false;
 	}
 
-	if (dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
 		char *build_id_msg = NULL;
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index efb1fce259a..4dfe0bb3c32 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -47,7 +47,7 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
-#ifdef NO_NEWT_SUPPORT
+#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT)
 int ui__warning(const char *format, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 6bebe7f0a20..015c91dbc09 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -12,8 +12,9 @@ int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
 struct ui_progress;
+struct perf_error_ops;
 
-#ifdef NO_NEWT_SUPPORT
+#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT)
 static inline int ui_helpline__show_help(const char *format __used, va_list ap __used)
 {
 	return 0;
@@ -23,12 +24,28 @@ static inline void ui_progress__update(u64 curr __used, u64 total __used,
 				       const char *title __used) {}
 
 #define ui__error(format, arg...) ui__warning(format, ##arg)
-#else
+
+static inline int
+perf_error__register(struct perf_error_ops *eops __used)
+{
+	return 0;
+}
+
+static inline int
+perf_error__unregister(struct perf_error_ops *eops __used)
+{
+	return 0;
+}
+
+#else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */
+
 extern char ui_helpline__last_msg[];
 int ui_helpline__show_help(const char *format, va_list ap);
 #include "../ui/progress.h"
 int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
-#endif
+#include "../ui/util.h"
+
+#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */
 
 int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 int ui__error_paranoid(void);
diff --git a/tools/perf/util/dso-test-data.c b/tools/perf/util/dso-test-data.c
new file mode 100644
index 00000000000..541cdc72c7d
--- /dev/null
+++ b/tools/perf/util/dso-test-data.c
@@ -0,0 +1,153 @@
+#include "util.h"
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "symbol.h"
+
+#define TEST_ASSERT_VAL(text, cond) \
+do { \
+	if (!(cond)) { \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1; \
+	} \
+} while (0)
+
+static char *test_file(int size)
+{
+	static char buf_templ[] = "/tmp/test-XXXXXX";
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC);
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data_offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data_offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+int dso__test_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	size_t i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		struct test_data_offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < (size_t)size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1b197280c62..d84870b0642 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -197,9 +197,6 @@ int perf_event__preprocess_sample(const union perf_event *self,
 
 const char *perf_event__name(unsigned int id);
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample, bool swapped);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7400fb3fc50..9b38681add9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -214,7 +214,7 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
 		attrs[i].type	       = PERF_TYPE_TRACEPOINT;
 		attrs[i].config	       = err;
 	        attrs[i].sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
-					  PERF_SAMPLE_CPU);
+					  PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD);
 		attrs[i].sample_period = 1;
 	}
 
@@ -224,8 +224,8 @@ out_free_attrs:
 	return err;
 }
 
-static struct perf_evsel *
-	perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
 	struct perf_evsel *evsel;
 
@@ -881,3 +881,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 
 	return 0;
 }
+
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped)
+{
+	struct perf_evsel *e = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return perf_evsel__parse_sample(e, event, sample, swapped);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 989bee9624c..528c1acd929 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -73,6 +73,9 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
 #define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
 	perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
 
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
+
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id);
 
@@ -119,6 +122,9 @@ u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
 
+int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+			      struct perf_sample *sample, bool swapped);
+
 bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9f6cebd798e..2eaae140def 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,12 +15,12 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
-#include "../../include/linux/perf_event.h"
+#include "../../../include/linux/hw_breakpoint.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
-int __perf_evsel__sample_size(u64 sample_type)
+static int __perf_evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -53,6 +53,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->attr	   = *attr;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
+	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
@@ -78,7 +79,7 @@ static const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
 	"ref-cycles",
 };
 
-const char *__perf_evsel__hw_name(u64 config)
+static const char *__perf_evsel__hw_name(u64 config)
 {
 	if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
 		return perf_evsel__hw_names[config];
@@ -86,16 +87,15 @@ const char *__perf_evsel__hw_name(u64 config)
 	return "unknown-hardware";
 }
 
-static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size)
 {
-	int colon = 0;
+	int colon = 0, r = 0;
 	struct perf_event_attr *attr = &evsel->attr;
-	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(attr->config));
 	bool exclude_guest_default = false;
 
 #define MOD_PRINT(context, mod)	do {					\
 		if (!attr->exclude_##context) {				\
-			if (!colon) colon = r++;			\
+			if (!colon) colon = ++r;			\
 			r += scnprintf(bf + r, size - r, "%c", mod);	\
 		} } while(0)
 
@@ -108,7 +108,7 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
 
 	if (attr->precise_ip) {
 		if (!colon)
-			colon = r++;
+			colon = ++r;
 		r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
 		exclude_guest_default = true;
 	}
@@ -119,39 +119,211 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
 	}
 #undef MOD_PRINT
 	if (colon)
-		bf[colon] = ':';
+		bf[colon - 1] = ':';
+	return r;
+}
+
+static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config));
+	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+static const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
+	"cpu-clock",
+	"task-clock",
+	"page-faults",
+	"context-switches",
+	"CPU-migrations",
+	"minor-faults",
+	"major-faults",
+	"alignment-faults",
+	"emulation-faults",
+};
+
+static const char *__perf_evsel__sw_name(u64 config)
+{
+	if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
+		return perf_evsel__sw_names[config];
+	return "unknown-software";
+}
+
+static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config));
+	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
+{
+	int r;
+
+	r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);
+
+	if (type & HW_BREAKPOINT_R)
+		r += scnprintf(bf + r, size - r, "r");
+
+	if (type & HW_BREAKPOINT_W)
+		r += scnprintf(bf + r, size - r, "w");
+
+	if (type & HW_BREAKPOINT_X)
+		r += scnprintf(bf + r, size - r, "x");
+
 	return r;
 }
 
-int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
 {
-	int ret;
+	struct perf_event_attr *attr = &evsel->attr;
+	int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
+	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_EVSEL__MAX_ALIASES] = {
+ { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
+ { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
+ { "LLC",	"L2",							},
+ { "dTLB",	"d-tlb",	"Data-TLB",				},
+ { "iTLB",	"i-tlb",	"Instruction-TLB",			},
+ { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
+ { "node",								},
+};
+
+const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
+				   [PERF_EVSEL__MAX_ALIASES] = {
+ { "load",	"loads",	"read",					},
+ { "store",	"stores",	"write",				},
+ { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
+};
+
+const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
+				       [PERF_EVSEL__MAX_ALIASES] = {
+ { "refs",	"Reference",	"ops",		"access",		},
+ { "misses",	"miss",							},
+};
+
+#define C(x)		PERF_COUNT_HW_CACHE_##x
+#define CACHE_READ	(1 << C(OP_READ))
+#define CACHE_WRITE	(1 << C(OP_WRITE))
+#define CACHE_PREFETCH	(1 << C(OP_PREFETCH))
+#define COP(x)		(1 << x)
+
+/*
+ * cache operartion stat
+ * L1I : Read and prefetch only
+ * ITLB and BPU : Read-only
+ */
+static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
+ [C(L1D)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(L1I)]	= (CACHE_READ | CACHE_PREFETCH),
+ [C(LL)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(DTLB)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(ITLB)]	= (CACHE_READ),
+ [C(BPU)]	= (CACHE_READ),
+ [C(NODE)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+};
+
+bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
+{
+	if (perf_evsel__hw_cache_stat[type] & COP(op))
+		return true;	/* valid */
+	else
+		return false;	/* invalid */
+}
+
+int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
+					    char *bf, size_t size)
+{
+	if (result) {
+		return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
+				 perf_evsel__hw_cache_op[op][0],
+				 perf_evsel__hw_cache_result[result][0]);
+	}
+
+	return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0],
+			 perf_evsel__hw_cache_op[op][1]);
+}
+
+static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
+{
+	u8 op, result, type = (config >>  0) & 0xff;
+	const char *err = "unknown-ext-hardware-cache-type";
+
+	if (type > PERF_COUNT_HW_CACHE_MAX)
+		goto out_err;
+
+	op = (config >>  8) & 0xff;
+	err = "unknown-ext-hardware-cache-op";
+	if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+		goto out_err;
+
+	result = (config >> 16) & 0xff;
+	err = "unknown-ext-hardware-cache-result";
+	if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+		goto out_err;
+
+	err = "invalid-cache";
+	if (!perf_evsel__is_cache_op_valid(type, op))
+		goto out_err;
+
+	return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
+out_err:
+	return scnprintf(bf, size, "%s", err);
+}
+
+static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size);
+	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+}
+
+static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+}
+
+const char *perf_evsel__name(struct perf_evsel *evsel)
+{
+	char bf[128];
+
+	if (evsel->name)
+		return evsel->name;
 
 	switch (evsel->attr.type) {
 	case PERF_TYPE_RAW:
-		ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+		perf_evsel__raw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_HARDWARE:
-		ret = perf_evsel__hw_name(evsel, bf, size);
+		perf_evsel__hw_name(evsel, bf, sizeof(bf));
+		break;
+
+	case PERF_TYPE_HW_CACHE:
+		perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
 		break;
+
+	case PERF_TYPE_SOFTWARE:
+		perf_evsel__sw_name(evsel, bf, sizeof(bf));
+		break;
+
+	case PERF_TYPE_TRACEPOINT:
+		scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
+		break;
+
+	case PERF_TYPE_BREAKPOINT:
+		perf_evsel__bp_name(evsel, bf, sizeof(bf));
+		break;
+
 	default:
-		/*
-		 * FIXME
- 		 *
-		 * This is the minimal perf_evsel__name so that we can
-		 * reconstruct event names taking into account event modifiers.
-		 *
-		 * The old event_name uses it now for raw anr hw events, so that
-		 * we don't drag all the parsing stuff into the python binding.
-		 *
-		 * On the next devel cycle the rest of the event naming will be
-		 * brought here.
- 		 */
-		return 0;
+		scnprintf(bf, sizeof(bf), "%s", "unknown attr type");
+		break;
 	}
 
-	return ret;
+	evsel->name = strdup(bf);
+
+	return evsel->name ?: "unknown";
 }
 
 void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
@@ -557,10 +729,10 @@ static bool sample_overlap(const union perf_event *event,
 	return false;
 }
 
-int perf_event__parse_sample(const union perf_event *event, u64 type,
-			     int sample_size, bool sample_id_all,
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data, bool swapped)
 {
+	u64 type = evsel->attr.sample_type;
 	const u64 *array;
 
 	/*
@@ -575,14 +747,14 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	data->period = 1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
-		if (!sample_id_all)
+		if (!evsel->attr.sample_id_all)
 			return 0;
 		return perf_event__parse_id_sample(event, type, data, swapped);
 	}
 
 	array = event->sample.array;
 
-	if (sample_size + sizeof(event->header) > event->header.size)
+	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
 	if (type & PERF_SAMPLE_IP) {
@@ -724,7 +896,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[1] = sample->tid;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
@@ -759,7 +931,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		u.val32[0] = sample->cpu;
 		if (swapped) {
 			/*
-			 * Inverse of what is done in perf_event__parse_sample
+			 * Inverse of what is done in perf_evsel__parse_sample
 			 */
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val64 = bswap_64(u.val64);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4ba8b564e6f..b559929983b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -65,6 +65,7 @@ struct perf_evsel {
 		void		*func;
 		void		*data;
 	} handler;
+	unsigned int		sample_size;
 	bool 			supported;
 };
 
@@ -83,8 +84,19 @@ void perf_evsel__config(struct perf_evsel *evsel,
 			struct perf_record_opts *opts,
 			struct perf_evsel *first);
 
-const char* __perf_evsel__hw_name(u64 config);
-int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size);
+bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
+
+#define PERF_EVSEL__MAX_ALIASES 8
+
+extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
+				       [PERF_EVSEL__MAX_ALIASES];
+extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_EVSEL__MAX_ALIASES];
+const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
+				       [PERF_EVSEL__MAX_ALIASES];
+int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
+					    char *bf, size_t size);
+const char *perf_evsel__name(struct perf_evsel *evsel);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
@@ -166,13 +178,8 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
-int __perf_evsel__sample_size(u64 sample_type);
-
-static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
-{
-	return __perf_evsel__sample_size(evsel->attr.sample_type);
-}
-
 void hists__init(struct hists *hists);
 
+int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+			     struct perf_sample *sample, bool swapped);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e909d43cf54..74ea3c2f813 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -174,6 +174,15 @@ perf_header__set_cmdline(int argc, const char **argv)
 {
 	int i;
 
+	/*
+	 * If header_argv has already been set, do not override it.
+	 * This allows a command to set the cmdline, parse args and
+	 * then call another builtin function that implements a
+	 * command -- e.g, cmd_kvm calling cmd_record.
+	 */
+	if (header_argv)
+		return 0;
+
 	header_argc = (u32)argc;
 
 	/* do not include NULL termination */
@@ -641,7 +650,7 @@ static int write_event_desc(int fd, struct perf_header *h __used,
 		/*
 		 * write event string as passed on cmdline
 		 */
-		ret = do_write_string(fd, event_name(attr));
+		ret = do_write_string(fd, perf_evsel__name(attr));
 		if (ret < 0)
 			return ret;
 		/*
@@ -1212,6 +1221,12 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 				attr.exclude_user,
 				attr.exclude_kernel);
 
+		fprintf(fp, ", excl_host = %d, excl_guest = %d",
+				attr.exclude_host,
+				attr.exclude_guest);
+
+		fprintf(fp, ", precise_ip = %d", attr.precise_ip);
+
 		if (nr)
 			fprintf(fp, ", id = {");
 
@@ -1474,15 +1489,15 @@ out:
 
 static int process_tracing_data(struct perf_file_section *section __unused,
 			      struct perf_header *ph __unused,
-			      int feat __unused, int fd)
+			      int feat __unused, int fd, void *data)
 {
-	trace_report(fd, false);
+	trace_report(fd, data, false);
 	return 0;
 }
 
 static int process_build_id(struct perf_file_section *section,
 			    struct perf_header *ph,
-			    int feat __unused, int fd)
+			    int feat __unused, int fd, void *data __used)
 {
 	if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
 		pr_debug("Failed to read buildids, continuing...\n");
@@ -1493,7 +1508,7 @@ 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);
+		       struct perf_header *h, int feat, int fd, void *data);
 	const char *name;
 	bool full_only;
 };
@@ -1988,7 +2003,7 @@ int perf_file_header__read(struct perf_file_header *header,
 
 static int perf_file_section__process(struct perf_file_section *section,
 				      struct perf_header *ph,
-				      int feat, int fd, void *data __used)
+				      int feat, int fd, void *data)
 {
 	if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
 		pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
@@ -2004,7 +2019,7 @@ 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);
+	return feat_ops[feat].process(section, ph, feat, fd, data);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
@@ -2093,9 +2108,11 @@ static int read_attr(int fd, struct perf_header *ph,
 	return ret <= 0 ? -1 : 0;
 }
 
-static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
+static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel,
+					   struct pevent *pevent)
 {
-	struct event_format *event = trace_find_event(evsel->attr.config);
+	struct event_format *event = pevent_find_event(pevent,
+						       evsel->attr.config);
 	char bf[128];
 
 	if (event == NULL)
@@ -2109,13 +2126,14 @@ static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
 	return 0;
 }
 
-static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist)
+static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist,
+					     struct pevent *pevent)
 {
 	struct perf_evsel *pos;
 
 	list_for_each_entry(pos, &evlist->entries, node) {
 		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
-		    perf_evsel__set_tracepoint_name(pos))
+		    perf_evsel__set_tracepoint_name(pos, pevent))
 			return -1;
 	}
 
@@ -2198,12 +2216,12 @@ int perf_session__read_header(struct perf_session *session, int fd)
 		event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
 	}
 
-	perf_header__process_sections(header, fd, NULL,
+	perf_header__process_sections(header, fd, &session->pevent,
 				      perf_file_section__process);
 
 	lseek(fd, header->data_offset, SEEK_SET);
 
-	if (perf_evlist__set_tracepoint_names(session->evlist))
+	if (perf_evlist__set_tracepoint_names(session->evlist, session->pevent))
 		goto out_delete_evlist;
 
 	header->frozen = 1;
@@ -2419,8 +2437,8 @@ int perf_event__process_tracing_data(union perf_event *event,
 	lseek(session->fd, offset + sizeof(struct tracing_data_event),
 	      SEEK_SET);
 
-	size_read = trace_report(session->fd, session->repipe);
-
+	size_read = trace_report(session->fd, &session->pevent,
+				 session->repipe);
 	padding = ALIGN(size_read, sizeof(u64)) - size_read;
 
 	if (read(session->fd, buf, padding) < 0)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 514e2a4b367..f247ef2789a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -708,7 +708,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	bool printed = false;
 	struct rb_node *node;
 	int i = 0;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * If have one single callchain root, don't bother printing
@@ -747,8 +747,11 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
-	return __callchain__fprintf_graph(fp, root, total_samples,
+	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
+	ret += fprintf(fp, "\n");
+
+	return ret;
 }
 
 static size_t __callchain__fprintf_flat(FILE *fp,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 34bb556d621..0b096c27a41 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
 	HISTC_SYMBOL_TO,
 	HISTC_DSO_FROM,
 	HISTC_DSO_TO,
+	HISTC_SRCLINE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 1eb804fd3fb..b6842c1d02a 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -108,4 +108,14 @@ int eprintf(int level,
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
 #endif
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
new file mode 100644
index 00000000000..fd530dced9c
--- /dev/null
+++ b/tools/perf/util/intlist.c
@@ -0,0 +1,101 @@
+/*
+ * Based on intlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+
+#include "intlist.h"
+
+static struct rb_node *intlist__node_new(struct rblist *rblist __used,
+					 const void *entry)
+{
+	int i = (int)((long)entry);
+	struct rb_node *rc = NULL;
+	struct int_node *node = malloc(sizeof(*node));
+
+	if (node != NULL) {
+		node->i = i;
+		rc = &node->rb_node;
+	}
+
+	return rc;
+}
+
+static void int_node__delete(struct int_node *ilist)
+{
+	free(ilist);
+}
+
+static void intlist__node_delete(struct rblist *rblist __used,
+				 struct rb_node *rb_node)
+{
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	int_node__delete(node);
+}
+
+static int intlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	int i = (int)((long)entry);
+	struct int_node *node = container_of(rb_node, struct int_node, rb_node);
+
+	return node->i - i;
+}
+
+int intlist__add(struct intlist *ilist, int i)
+{
+	return rblist__add_node(&ilist->rblist, (void *)((long)i));
+}
+
+void intlist__remove(struct intlist *ilist __used, struct int_node *node)
+{
+	int_node__delete(node);
+}
+
+struct int_node *intlist__find(struct intlist *ilist, int i)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
+
+struct intlist *intlist__new(void)
+{
+	struct intlist *ilist = malloc(sizeof(*ilist));
+
+	if (ilist != NULL) {
+		rblist__init(&ilist->rblist);
+		ilist->rblist.node_cmp    = intlist__node_cmp;
+		ilist->rblist.node_new    = intlist__node_new;
+		ilist->rblist.node_delete = intlist__node_delete;
+	}
+
+	return ilist;
+}
+
+void intlist__delete(struct intlist *ilist)
+{
+	if (ilist != NULL)
+		rblist__delete(&ilist->rblist);
+}
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx)
+{
+	struct int_node *node = NULL;
+	struct rb_node *rb_node;
+
+	rb_node = rblist__entry(&ilist->rblist, idx);
+	if (rb_node)
+		node = container_of(rb_node, struct int_node, rb_node);
+
+	return node;
+}
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
new file mode 100644
index 00000000000..6d63ab90db5
--- /dev/null
+++ b/tools/perf/util/intlist.h
@@ -0,0 +1,75 @@
+#ifndef __PERF_INTLIST_H
+#define __PERF_INTLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+#include "rblist.h"
+
+struct int_node {
+	struct rb_node rb_node;
+	int i;
+};
+
+struct intlist {
+	struct rblist rblist;
+};
+
+struct intlist *intlist__new(void);
+void intlist__delete(struct intlist *ilist);
+
+void intlist__remove(struct intlist *ilist, struct int_node *in);
+int intlist__add(struct intlist *ilist, int i);
+
+struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx);
+struct int_node *intlist__find(struct intlist *ilist, int i);
+
+static inline bool intlist__has_entry(struct intlist *ilist, int i)
+{
+	return intlist__find(ilist, i) != NULL;
+}
+
+static inline bool intlist__empty(const struct intlist *ilist)
+{
+	return rblist__empty(&ilist->rblist);
+}
+
+static inline unsigned int intlist__nr_entries(const struct intlist *ilist)
+{
+	return rblist__nr_entries(&ilist->rblist);
+}
+
+/* For intlist iteration */
+static inline struct int_node *intlist__first(struct intlist *ilist)
+{
+	struct rb_node *rn = rb_first(&ilist->rblist.entries);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+static inline struct int_node *intlist__next(struct int_node *in)
+{
+	struct rb_node *rn;
+	if (!in)
+		return NULL;
+	rn = rb_next(&in->rb_node);
+	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
+}
+
+/**
+ * intlist_for_each      - iterate over a intlist
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each(pos, ilist)	\
+	for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
+
+/**
+ * intlist_for_each_safe - iterate over a intlist safe against removal of
+ *                         int_node
+ * @pos:	the &struct int_node to use as a loop cursor.
+ * @n:		another &struct int_node to use as temporary storage.
+ * @ilist:	the &struct intlist for loop.
+ */
+#define intlist__for_each_safe(pos, n, ilist)	\
+	for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
+	     pos = n, n = intlist__next(n))
+#endif /* __PERF_INTLIST_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 35ae56864e4..cc33486ad9e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -7,6 +7,8 @@
 #include <stdio.h>
 #include <unistd.h>
 #include "map.h"
+#include "thread.h"
+#include "strlist.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -585,7 +587,21 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid)
 	self->kmaps.machine = self;
 	self->pid	    = pid;
 	self->root_dir      = strdup(root_dir);
-	return self->root_dir == NULL ? -ENOMEM : 0;
+	if (self->root_dir == NULL)
+		return -ENOMEM;
+
+	if (pid != HOST_KERNEL_ID) {
+		struct thread *thread = machine__findnew_thread(self, pid);
+		char comm[64];
+
+		if (thread == NULL)
+			return -ENOMEM;
+
+		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
+		thread__set_comm(thread, comm);
+	}
+
+	return 0;
 }
 
 static void dsos__delete(struct list_head *self)
@@ -669,25 +685,34 @@ struct machine *machines__find(struct rb_root *self, pid_t pid)
 struct machine *machines__findnew(struct rb_root *self, pid_t pid)
 {
 	char path[PATH_MAX];
-	const char *root_dir;
+	const char *root_dir = "";
 	struct machine *machine = machines__find(self, pid);
 
-	if (!machine || machine->pid != pid) {
-		if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID)
-			root_dir = "";
-		else {
-			if (!symbol_conf.guestmount)
-				goto out;
-			sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
-			if (access(path, R_OK)) {
+	if (machine && (machine->pid == pid))
+		goto out;
+
+	if ((pid != HOST_KERNEL_ID) &&
+	    (pid != DEFAULT_GUEST_KERNEL_ID) &&
+	    (symbol_conf.guestmount)) {
+		sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+		if (access(path, R_OK)) {
+			static struct strlist *seen;
+
+			if (!seen)
+				seen = strlist__new(true, NULL);
+
+			if (!strlist__has_entry(seen, path)) {
 				pr_err("Can't access file %s\n", path);
-				goto out;
+				strlist__add(seen, path);
 			}
-			root_dir = path;
+			machine = NULL;
+			goto out;
 		}
-		machine = machines__add(self, pid, root_dir);
+		root_dir = path;
 	}
 
+	machine = machines__add(self, pid, root_dir);
+
 out:
 	return machine;
 }
@@ -713,3 +738,16 @@ char *machine__mmap_name(struct machine *self, char *bf, size_t size)
 
 	return bf;
 }
+
+void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size)
+{
+	struct rb_node *node;
+	struct machine *machine;
+
+	for (node = rb_first(machines); node; node = rb_next(node)) {
+		machine = rb_entry(node, struct machine, rb_node);
+		machine->id_hdr_size = id_hdr_size;
+	}
+
+	return;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 81371bad4ef..03a1e9b08b2 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -151,13 +151,14 @@ struct machine *machines__add(struct rb_root *self, pid_t pid,
 struct machine *machines__find_host(struct rb_root *self);
 struct machine *machines__find(struct rb_root *self, pid_t pid);
 struct machine *machines__findnew(struct rb_root *self, pid_t pid);
+void machines__set_id_hdr_size(struct rb_root *self, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *self, char *bf, size_t size);
 int machine__init(struct machine *self, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *self);
 void machine__delete(struct machine *self);
 
 int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel, struct thread *thread,
+			       struct thread *thread,
 			       struct ip_callchain *chain,
 			       struct symbol **parent);
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index 76b98e2a587..127d648cc54 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -13,6 +13,9 @@ do { \
 	} \
 } while (0)
 
+#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
+			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -21,8 +24,7 @@ static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
-		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
-		evsel->attr.sample_type);
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
 	return 0;
 }
@@ -37,8 +39,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 		TEST_ASSERT_VAL("wrong type",
 			PERF_TYPE_TRACEPOINT == evsel->attr.type);
 		TEST_ASSERT_VAL("wrong sample_type",
-			(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU)
-			== evsel->attr.sample_type);
+			PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 		TEST_ASSERT_VAL("wrong sample_period",
 			1 == evsel->attr.sample_period);
 	}
@@ -181,6 +182,22 @@ static int test__checkevent_breakpoint_w(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type",
+			PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type",
+		(HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len",
+			HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+	return 0;
+}
+
 static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -309,6 +326,8 @@ static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u"));
 
 	return test__checkevent_breakpoint(evlist);
 }
@@ -322,6 +341,8 @@ static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0x0:x:k"));
 
 	return test__checkevent_breakpoint_x(evlist);
 }
@@ -335,6 +356,8 @@ static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp"));
 
 	return test__checkevent_breakpoint_r(evlist);
 }
@@ -348,10 +371,27 @@ static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0x0:w:up"));
 
 	return test__checkevent_breakpoint_w(evlist);
 }
 
+static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = list_entry(evlist->entries.next,
+					      struct perf_evsel, node);
+
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp"));
+
+	return test__checkevent_breakpoint_rw(evlist);
+}
+
 static int test__checkevent_pmu(struct perf_evlist *evlist)
 {
 
@@ -389,8 +429,7 @@ static int test__checkevent_list(struct perf_evlist *evlist)
 	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
-		(PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU) ==
-		evsel->attr.sample_type);
+		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
 	TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
@@ -413,19 +452,63 @@ static int test__checkevent_pmu_name(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	/* cpu/config=1,name=krava1/u */
+	/* cpu/config=1,name=krava/u */
 	evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong config",  1 == evsel->attr.config);
-	TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "krava"));
+	TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava"));
 
-	/* cpu/config=2/" */
+	/* cpu/config=2/u" */
 	evsel = list_entry(evsel->node.next, struct perf_evsel, node);
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong config",  2 == evsel->attr.config);
-	TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "raw 0x2"));
+	TEST_ASSERT_VAL("wrong name",
+			!strcmp(perf_evsel__name(evsel), "raw 0x2:u"));
+
+	return 0;
+}
+
+static int test__checkterms_simple(struct list_head *terms)
+{
+	struct parse_events__term *term;
+
+	/* config=10 */
+	term = list_entry(terms->next, struct parse_events__term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 10);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* config1 */
+	term = list_entry(term->list.next, struct parse_events__term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* config2=3 */
+	term = list_entry(term->list.next, struct parse_events__term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 3);
+	TEST_ASSERT_VAL("wrong config", !term->config);
+
+	/* umask=1*/
+	term = list_entry(term->list.next, struct parse_events__term, list);
+	TEST_ASSERT_VAL("wrong type term",
+			term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
+	TEST_ASSERT_VAL("wrong type val",
+			term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+	TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+	TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "umask"));
 
 	return 0;
 }
@@ -541,10 +624,16 @@ static struct test__event_st test__events[] = {
 		.name  = "instructions:H",
 		.check = test__checkevent_exclude_guest_modifier,
 	},
+	[26] = {
+		.name  = "mem:0:rw",
+		.check = test__checkevent_breakpoint_rw,
+	},
+	[27] = {
+		.name  = "mem:0:rw:kp",
+		.check = test__checkevent_breakpoint_rw_modifier,
+	},
 };
 
-#define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
-
 static struct test__event_st test__events_pmu[] = {
 	[0] = {
 		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
@@ -556,10 +645,23 @@ static struct test__event_st test__events_pmu[] = {
 	},
 };
 
-#define TEST__EVENTS_PMU_CNT (sizeof(test__events_pmu) / \
-			      sizeof(struct test__event_st))
+struct test__term {
+	const char *str;
+	__u32 type;
+	int (*check)(struct list_head *terms);
+};
 
-static int test(struct test__event_st *e)
+static struct test__term test__terms[] = {
+	[0] = {
+		.str   = "config=10,config1,config2=3,umask=1",
+		.check = test__checkterms_simple,
+	},
+};
+
+#define TEST__TERMS_CNT (sizeof(test__terms) / \
+			 sizeof(struct test__term))
+
+static int test_event(struct test__event_st *e)
 {
 	struct perf_evlist *evlist;
 	int ret;
@@ -590,7 +692,48 @@ static int test_events(struct test__event_st *events, unsigned cnt)
 		struct test__event_st *e = &events[i];
 
 		pr_debug("running test %d '%s'\n", i, e->name);
-		ret = test(e);
+		ret = test_event(e);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int test_term(struct test__term *t)
+{
+	struct list_head *terms;
+	int ret;
+
+	terms = malloc(sizeof(*terms));
+	if (!terms)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(terms);
+
+	ret = parse_events_terms(terms, t->str);
+	if (ret) {
+		pr_debug("failed to parse terms '%s', err %d\n",
+			 t->str , ret);
+		return ret;
+	}
+
+	ret = t->check(terms);
+	parse_events__free_terms(terms);
+
+	return ret;
+}
+
+static int test_terms(struct test__term *terms, unsigned cnt)
+{
+	int ret = 0;
+	unsigned i;
+
+	for (i = 0; i < cnt; i++) {
+		struct test__term *t = &terms[i];
+
+		pr_debug("running test %d '%s'\n", i, t->str);
+		ret = test_term(t);
 		if (ret)
 			break;
 	}
@@ -617,9 +760,17 @@ int parse_events__test(void)
 {
 	int ret;
 
-	ret = test_events(test__events, TEST__EVENTS_CNT);
-	if (!ret && test_pmu())
-		ret = test_events(test__events_pmu, TEST__EVENTS_PMU_CNT);
+#define TEST_EVENTS(tests)				\
+do {							\
+	ret = test_events(tests, ARRAY_SIZE(tests));	\
+	if (ret)					\
+		return ret;				\
+} while (0)
 
-	return ret;
+	TEST_EVENTS(test__events);
+
+	if (test_pmu())
+		TEST_EVENTS(test__events_pmu);
+
+	return test_terms(test__terms, ARRAY_SIZE(test__terms));
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 05dbc8b3c76..74a5af4d33e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -11,14 +11,14 @@
 #include "cache.h"
 #include "header.h"
 #include "debugfs.h"
+#include "parse-events-bison.h"
+#define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
 #include "pmu.h"
 
 #define MAX_NAME_LEN 100
 
 struct event_symbol {
-	u8		type;
-	u64		config;
 	const char	*symbol;
 	const char	*alias;
 };
@@ -26,32 +26,88 @@ struct event_symbol {
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-int parse_events_parse(struct list_head *list, int *idx);
-
-#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
-#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
-
-static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),			"cpu-cycles",			"cycles"		},
-  { CHW(STALLED_CYCLES_FRONTEND),	"stalled-cycles-frontend",	"idle-cycles-frontend"	},
-  { CHW(STALLED_CYCLES_BACKEND),	"stalled-cycles-backend",	"idle-cycles-backend"	},
-  { CHW(INSTRUCTIONS),			"instructions",			""			},
-  { CHW(CACHE_REFERENCES),		"cache-references",		""			},
-  { CHW(CACHE_MISSES),			"cache-misses",			""			},
-  { CHW(BRANCH_INSTRUCTIONS),		"branch-instructions",		"branches"		},
-  { CHW(BRANCH_MISSES),			"branch-misses",		""			},
-  { CHW(BUS_CYCLES),			"bus-cycles",			""			},
-  { CHW(REF_CPU_CYCLES),		"ref-cycles",			""			},
-
-  { CSW(CPU_CLOCK),			"cpu-clock",			""			},
-  { CSW(TASK_CLOCK),			"task-clock",			""			},
-  { CSW(PAGE_FAULTS),			"page-faults",			"faults"		},
-  { CSW(PAGE_FAULTS_MIN),		"minor-faults",			""			},
-  { CSW(PAGE_FAULTS_MAJ),		"major-faults",			""			},
-  { CSW(CONTEXT_SWITCHES),		"context-switches",		"cs"			},
-  { CSW(CPU_MIGRATIONS),		"cpu-migrations",		"migrations"		},
-  { CSW(ALIGNMENT_FAULTS),		"alignment-faults",		""			},
-  { CSW(EMULATION_FAULTS),		"emulation-faults",		""			},
+int parse_events_parse(void *data, void *scanner);
+
+static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = {
+		.symbol = "cpu-cycles",
+		.alias  = "cycles",
+	},
+	[PERF_COUNT_HW_INSTRUCTIONS] = {
+		.symbol = "instructions",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_CACHE_REFERENCES] = {
+		.symbol = "cache-references",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_CACHE_MISSES] = {
+		.symbol = "cache-misses",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = {
+		.symbol = "branch-instructions",
+		.alias  = "branches",
+	},
+	[PERF_COUNT_HW_BRANCH_MISSES] = {
+		.symbol = "branch-misses",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_BUS_CYCLES] = {
+		.symbol = "bus-cycles",
+		.alias  = "",
+	},
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = {
+		.symbol = "stalled-cycles-frontend",
+		.alias  = "idle-cycles-frontend",
+	},
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = {
+		.symbol = "stalled-cycles-backend",
+		.alias  = "idle-cycles-backend",
+	},
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = {
+		.symbol = "ref-cycles",
+		.alias  = "",
+	},
+};
+
+static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+	[PERF_COUNT_SW_CPU_CLOCK] = {
+		.symbol = "cpu-clock",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_TASK_CLOCK] = {
+		.symbol = "task-clock",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_PAGE_FAULTS] = {
+		.symbol = "page-faults",
+		.alias  = "faults",
+	},
+	[PERF_COUNT_SW_CONTEXT_SWITCHES] = {
+		.symbol = "context-switches",
+		.alias  = "cs",
+	},
+	[PERF_COUNT_SW_CPU_MIGRATIONS] = {
+		.symbol = "cpu-migrations",
+		.alias  = "migrations",
+	},
+	[PERF_COUNT_SW_PAGE_FAULTS_MIN] = {
+		.symbol = "minor-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_PAGE_FAULTS_MAJ] = {
+		.symbol = "major-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_ALIGNMENT_FAULTS] = {
+		.symbol = "alignment-faults",
+		.alias  = "",
+	},
+	[PERF_COUNT_SW_EMULATION_FAULTS] = {
+		.symbol = "emulation-faults",
+		.alias  = "",
+	},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -62,63 +118,6 @@ static struct event_symbol event_symbols[] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
-	"cpu-clock",
-	"task-clock",
-	"page-faults",
-	"context-switches",
-	"CPU-migrations",
-	"minor-faults",
-	"major-faults",
-	"alignment-faults",
-	"emulation-faults",
-};
-
-#define MAX_ALIASES 8
-
-static const char *hw_cache[PERF_COUNT_HW_CACHE_MAX][MAX_ALIASES] = {
- { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
- { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
- { "LLC",	"L2",							},
- { "dTLB",	"d-tlb",	"Data-TLB",				},
- { "iTLB",	"i-tlb",	"Instruction-TLB",			},
- { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
- { "node",								},
-};
-
-static const char *hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][MAX_ALIASES] = {
- { "load",	"loads",	"read",					},
- { "store",	"stores",	"write",				},
- { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
-};
-
-static const char *hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
-				  [MAX_ALIASES] = {
- { "refs",	"Reference",	"ops",		"access",		},
- { "misses",	"miss",							},
-};
-
-#define C(x)		PERF_COUNT_HW_CACHE_##x
-#define CACHE_READ	(1 << C(OP_READ))
-#define CACHE_WRITE	(1 << C(OP_WRITE))
-#define CACHE_PREFETCH	(1 << C(OP_PREFETCH))
-#define COP(x)		(1 << x)
-
-/*
- * cache operartion stat
- * L1I : Read and prefetch only
- * ITLB and BPU : Read-only
- */
-static unsigned long hw_cache_stat[C(MAX)] = {
- [C(L1D)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(L1I)]	= (CACHE_READ | CACHE_PREFETCH),
- [C(LL)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(DTLB)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(ITLB)]	= (CACHE_READ),
- [C(BPU)]	= (CACHE_READ),
- [C(NODE)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
-};
-
 #define for_each_subsystem(sys_dir, sys_dirent, sys_next)	       \
 	while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next)	       \
 	if (sys_dirent.d_type == DT_DIR &&				       \
@@ -218,48 +217,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	return NULL;
 }
 
-#define TP_PATH_LEN (MAX_EVENT_LENGTH * 2 + 1)
-static const char *tracepoint_id_to_name(u64 config)
-{
-	static char buf[TP_PATH_LEN];
-	struct tracepoint_path *path;
-
-	path = tracepoint_id_to_path(config);
-	if (path) {
-		snprintf(buf, TP_PATH_LEN, "%s:%s", path->system, path->name);
-		free(path->name);
-		free(path->system);
-		free(path);
-	} else
-		snprintf(buf, TP_PATH_LEN, "%s:%s", "unknown", "unknown");
-
-	return buf;
-}
-
-static int is_cache_op_valid(u8 cache_type, u8 cache_op)
-{
-	if (hw_cache_stat[cache_type] & COP(cache_op))
-		return 1;	/* valid */
-	else
-		return 0;	/* invalid */
-}
-
-static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
-{
-	static char name[50];
-
-	if (cache_result) {
-		sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
-			hw_cache_op[cache_op][0],
-			hw_cache_result[cache_result][0]);
-	} else {
-		sprintf(name, "%s-%s", hw_cache[cache_type][0],
-			hw_cache_op[cache_op][1]);
-	}
-
-	return name;
-}
-
 const char *event_type(int type)
 {
 	switch (type) {
@@ -282,76 +239,6 @@ const char *event_type(int type)
 	return "unknown";
 }
 
-const char *event_name(struct perf_evsel *evsel)
-{
-	u64 config = evsel->attr.config;
-	int type = evsel->attr.type;
-
-	if (type == PERF_TYPE_RAW || type == PERF_TYPE_HARDWARE) {
-		/*
- 		 * XXX minimal fix, see comment on perf_evsen__name, this static buffer
- 		 * will go away together with event_name in the next devel cycle.
- 		 */
-		static char bf[128];
-		perf_evsel__name(evsel, bf, sizeof(bf));
-		return bf;
-	}
-
-	if (evsel->name)
-		return evsel->name;
-
-	return __event_name(type, config);
-}
-
-const char *__event_name(int type, u64 config)
-{
-	static char buf[32];
-
-	if (type == PERF_TYPE_RAW) {
-		sprintf(buf, "raw 0x%" PRIx64, config);
-		return buf;
-	}
-
-	switch (type) {
-	case PERF_TYPE_HARDWARE:
-		return __perf_evsel__hw_name(config);
-
-	case PERF_TYPE_HW_CACHE: {
-		u8 cache_type, cache_op, cache_result;
-
-		cache_type   = (config >>  0) & 0xff;
-		if (cache_type > PERF_COUNT_HW_CACHE_MAX)
-			return "unknown-ext-hardware-cache-type";
-
-		cache_op     = (config >>  8) & 0xff;
-		if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX)
-			return "unknown-ext-hardware-cache-op";
-
-		cache_result = (config >> 16) & 0xff;
-		if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
-			return "unknown-ext-hardware-cache-result";
-
-		if (!is_cache_op_valid(cache_type, cache_op))
-			return "invalid-cache";
-
-		return event_cache_name(cache_type, cache_op, cache_result);
-	}
-
-	case PERF_TYPE_SOFTWARE:
-		if (config < PERF_COUNT_SW_MAX && sw_event_names[config])
-			return sw_event_names[config];
-		return "unknown-software";
-
-	case PERF_TYPE_TRACEPOINT:
-		return tracepoint_id_to_name(config);
-
-	default:
-		break;
-	}
-
-	return "unknown";
-}
-
 static int add_event(struct list_head **_list, int *idx,
 		     struct perf_event_attr *attr, char *name)
 {
@@ -373,19 +260,20 @@ static int add_event(struct list_head **_list, int *idx,
 		return -ENOMEM;
 	}
 
-	evsel->name = strdup(name);
+	if (name)
+		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
 	*_list = list;
 	return 0;
 }
 
-static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size)
+static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
 {
 	int i, j;
 	int n, longest = -1;
 
 	for (i = 0; i < size; i++) {
-		for (j = 0; j < MAX_ALIASES && names[i][j]; j++) {
+		for (j = 0; j < PERF_EVSEL__MAX_ALIASES && names[i][j]; j++) {
 			n = strlen(names[i][j]);
 			if (n > longest && !strncasecmp(str, names[i][j], n))
 				longest = n;
@@ -410,7 +298,7 @@ int parse_events_add_cache(struct list_head **list, int *idx,
 	 * No fallback - if we cannot get a clear cache type
 	 * then bail out:
 	 */
-	cache_type = parse_aliases(type, hw_cache,
+	cache_type = parse_aliases(type, perf_evsel__hw_cache,
 				   PERF_COUNT_HW_CACHE_MAX);
 	if (cache_type == -1)
 		return -EINVAL;
@@ -423,18 +311,18 @@ int parse_events_add_cache(struct list_head **list, int *idx,
 		snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str);
 
 		if (cache_op == -1) {
-			cache_op = parse_aliases(str, hw_cache_op,
+			cache_op = parse_aliases(str, perf_evsel__hw_cache_op,
 						 PERF_COUNT_HW_CACHE_OP_MAX);
 			if (cache_op >= 0) {
-				if (!is_cache_op_valid(cache_type, cache_op))
+				if (!perf_evsel__is_cache_op_valid(cache_type, cache_op))
 					return -EINVAL;
 				continue;
 			}
 		}
 
 		if (cache_result == -1) {
-			cache_result = parse_aliases(str, hw_cache_result,
-						PERF_COUNT_HW_CACHE_RESULT_MAX);
+			cache_result = parse_aliases(str, perf_evsel__hw_cache_result,
+						     PERF_COUNT_HW_CACHE_RESULT_MAX);
 			if (cache_result >= 0)
 				continue;
 		}
@@ -489,6 +377,7 @@ static int add_tracepoint(struct list_head **list, int *idx,
 	attr.sample_type |= PERF_SAMPLE_RAW;
 	attr.sample_type |= PERF_SAMPLE_TIME;
 	attr.sample_type |= PERF_SAMPLE_CPU;
+	attr.sample_type |= PERF_SAMPLE_PERIOD;
 	attr.sample_period = 1;
 
 	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
@@ -549,21 +438,31 @@ parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 		if (!type || !type[i])
 			break;
 
+#define CHECK_SET_TYPE(bit)		\
+do {					\
+	if (attr->bp_type & bit)	\
+		return -EINVAL;		\
+	else				\
+		attr->bp_type |= bit;	\
+} while (0)
+
 		switch (type[i]) {
 		case 'r':
-			attr->bp_type |= HW_BREAKPOINT_R;
+			CHECK_SET_TYPE(HW_BREAKPOINT_R);
 			break;
 		case 'w':
-			attr->bp_type |= HW_BREAKPOINT_W;
+			CHECK_SET_TYPE(HW_BREAKPOINT_W);
 			break;
 		case 'x':
-			attr->bp_type |= HW_BREAKPOINT_X;
+			CHECK_SET_TYPE(HW_BREAKPOINT_X);
 			break;
 		default:
 			return -EINVAL;
 		}
 	}
 
+#undef CHECK_SET_TYPE
+
 	if (!attr->bp_type) /* Default */
 		attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
 
@@ -574,7 +473,6 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
 				void *ptr, char *type)
 {
 	struct perf_event_attr attr;
-	char name[MAX_NAME_LEN];
 
 	memset(&attr, 0, sizeof(attr));
 	attr.bp_addr = (unsigned long) ptr;
@@ -592,9 +490,9 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
 		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.sample_period = 1;
 
-	snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw");
-	return add_event(list, idx, &attr, name);
+	return add_event(list, idx, &attr, NULL);
 }
 
 static int config_term(struct perf_event_attr *attr,
@@ -666,8 +564,7 @@ int parse_events_add_numeric(struct list_head **list, int *idx,
 	    config_attr(&attr, head_config, 1))
 		return -EINVAL;
 
-	return add_event(list, idx, &attr,
-			 (char *) __event_name(type, config));
+	return add_event(list, idx, &attr, NULL);
 }
 
 static int parse_events__is_name_term(struct parse_events__term *term)
@@ -675,8 +572,7 @@ static int parse_events__is_name_term(struct parse_events__term *term)
 	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
 }
 
-static char *pmu_event_name(struct perf_event_attr *attr,
-			    struct list_head *head_terms)
+static char *pmu_event_name(struct list_head *head_terms)
 {
 	struct parse_events__term *term;
 
@@ -684,7 +580,7 @@ static char *pmu_event_name(struct perf_event_attr *attr,
 		if (parse_events__is_name_term(term))
 			return term->val.str;
 
-	return (char *) __event_name(PERF_TYPE_RAW, attr->config);
+	return NULL;
 }
 
 int parse_events_add_pmu(struct list_head **list, int *idx,
@@ -699,6 +595,9 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
 
 	memset(&attr, 0, sizeof(attr));
 
+	if (perf_pmu__check_alias(pmu, head_config))
+		return -EINVAL;
+
 	/*
 	 * Configure hardcoded terms first, no need to check
 	 * return value when called with fail == 0 ;)
@@ -709,7 +608,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
 		return -EINVAL;
 
 	return add_event(list, idx, &attr,
-			 pmu_event_name(&attr, head_config));
+			 pmu_event_name(head_config));
 }
 
 void parse_events_update_lists(struct list_head *list_event,
@@ -787,27 +686,62 @@ int parse_events_modifier(struct list_head *list, char *str)
 	return 0;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
+static int parse_events__scanner(const char *str, void *data, int start_token)
 {
-	LIST_HEAD(list);
-	LIST_HEAD(list_tmp);
 	YY_BUFFER_STATE buffer;
-	int ret, idx = evlist->nr_entries;
+	void *scanner;
+	int ret;
+
+	ret = parse_events_lex_init_extra(start_token, &scanner);
+	if (ret)
+		return ret;
 
-	buffer = parse_events__scan_string(str);
+	buffer = parse_events__scan_string(str, scanner);
 
 #ifdef PARSER_DEBUG
 	parse_events_debug = 1;
 #endif
-	ret = parse_events_parse(&list, &idx);
+	ret = parse_events_parse(data, scanner);
 
-	parse_events__flush_buffer(buffer);
-	parse_events__delete_buffer(buffer);
-	parse_events_lex_destroy();
+	parse_events__flush_buffer(buffer, scanner);
+	parse_events__delete_buffer(buffer, scanner);
+	parse_events_lex_destroy(scanner);
+	return ret;
+}
+
+/*
+ * parse event config string, return a list of event terms.
+ */
+int parse_events_terms(struct list_head *terms, const char *str)
+{
+	struct parse_events_data__terms data = {
+		.terms = NULL,
+	};
+	int ret;
 
+	ret = parse_events__scanner(str, &data, PE_START_TERMS);
 	if (!ret) {
-		int entries = idx - evlist->nr_entries;
-		perf_evlist__splice_list_tail(evlist, &list, entries);
+		list_splice(data.terms, terms);
+		free(data.terms);
+		return 0;
+	}
+
+	parse_events__free_terms(data.terms);
+	return ret;
+}
+
+int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
+{
+	struct parse_events_data__events data = {
+		.list = LIST_HEAD_INIT(data.list),
+		.idx  = evlist->nr_entries,
+	};
+	int ret;
+
+	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+	if (!ret) {
+		int entries = data.idx - evlist->nr_entries;
+		perf_evlist__splice_list_tail(evlist, &data.list, entries);
 		return 0;
 	}
 
@@ -946,16 +880,13 @@ int is_valid_tracepoint(const char *event_string)
 	return 0;
 }
 
-void print_events_type(u8 type)
+static void __print_events_type(u8 type, struct event_symbol *syms,
+				unsigned max)
 {
-	struct event_symbol *syms = event_symbols;
-	unsigned int i;
 	char name[64];
+	unsigned i;
 
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-		if (type != syms->type)
-			continue;
-
+	for (i = 0; i < max ; i++, syms++) {
 		if (strlen(syms->alias))
 			snprintf(name, sizeof(name),  "%s OR %s",
 				 syms->symbol, syms->alias);
@@ -967,19 +898,28 @@ void print_events_type(u8 type)
 	}
 }
 
+void print_events_type(u8 type)
+{
+	if (type == PERF_TYPE_SOFTWARE)
+		__print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX);
+	else
+		__print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX);
+}
+
 int print_hwcache_events(const char *event_glob)
 {
 	unsigned int type, op, i, printed = 0;
+	char name[64];
 
 	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
 		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
 			/* skip invalid cache type */
-			if (!is_cache_op_valid(type, op))
+			if (!perf_evsel__is_cache_op_valid(type, op))
 				continue;
 
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				char *name = event_cache_name(type, op, i);
-
+				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
+									name, sizeof(name));
 				if (event_glob != NULL && !strglobmatch(name, event_glob))
 					continue;
 
@@ -993,26 +933,13 @@ int print_hwcache_events(const char *event_glob)
 	return printed;
 }
 
-/*
- * Print the help text for the event symbols:
- */
-void print_events(const char *event_glob)
+static void print_symbol_events(const char *event_glob, unsigned type,
+				struct event_symbol *syms, unsigned max)
 {
-	unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
-	struct event_symbol *syms = event_symbols;
+	unsigned i, printed = 0;
 	char name[MAX_NAME_LEN];
 
-	printf("\n");
-	printf("List of pre-defined events (to be used in -e):\n");
-
-	for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-		type = syms->type;
-
-		if (type != prev_type && printed) {
-			printf("\n");
-			printed = 0;
-			ntypes_printed++;
-		}
+	for (i = 0; i < max; i++, syms++) {
 
 		if (event_glob != NULL && 
 		    !(strglobmatch(syms->symbol, event_glob) ||
@@ -1023,17 +950,31 @@ void print_events(const char *event_glob)
 			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
 		else
 			strncpy(name, syms->symbol, MAX_NAME_LEN);
-		printf("  %-50s [%s]\n", name,
-			event_type_descriptors[type]);
 
-		prev_type = type;
-		++printed;
+		printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
+
+		printed++;
 	}
 
-	if (ntypes_printed) {
-		printed = 0;
+	if (printed)
 		printf("\n");
-	}
+}
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(const char *event_glob)
+{
+
+	printf("\n");
+	printf("List of pre-defined events (to be used in -e):\n");
+
+	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
+			    event_symbols_hw, PERF_COUNT_HW_MAX);
+
+	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
+			    event_symbols_sw, PERF_COUNT_SW_MAX);
+
 	print_hwcache_events(event_glob);
 
 	if (event_glob != NULL)
@@ -1106,6 +1047,13 @@ int parse_events__term_str(struct parse_events__term **term,
 			config, str, 0);
 }
 
+int parse_events__term_clone(struct parse_events__term **new,
+			     struct parse_events__term *term)
+{
+	return new_term(new, term->type_val, term->type_term, term->config,
+			term->val.str, term->val.num);
+}
+
 void parse_events__free_terms(struct list_head *terms)
 {
 	struct parse_events__term *term, *h;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 8cac57ab4ee..ee9c218a193 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -26,13 +26,12 @@ extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
 extern bool have_tracepoints(struct list_head *evlist);
 
 const char *event_type(int type);
-const char *event_name(struct perf_evsel *event);
-extern const char *__event_name(int type, u64 config);
 
 extern int parse_events_option(const struct option *opt, const char *str,
 			       int unset);
 extern int parse_events(struct perf_evlist *evlist, const char *str,
 			int unset);
+extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
@@ -63,11 +62,22 @@ struct parse_events__term {
 	struct list_head list;
 };
 
+struct parse_events_data__events {
+	struct list_head list;
+	int idx;
+};
+
+struct parse_events_data__terms {
+	struct list_head *terms;
+};
+
 int parse_events__is_hardcoded_term(struct parse_events__term *term);
 int parse_events__term_num(struct parse_events__term **_term,
 			   int type_term, char *config, long num);
 int parse_events__term_str(struct parse_events__term **_term,
 			   int type_term, char *config, char *str);
+int parse_events__term_clone(struct parse_events__term **new,
+			     struct parse_events__term *term);
 void parse_events__free_terms(struct list_head *terms);
 int parse_events_modifier(struct list_head *list, char *str);
 int parse_events_add_tracepoint(struct list_head **list, int *idx,
@@ -83,8 +93,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
 			 char *pmu , struct list_head *head_config);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
-void parse_events_error(struct list_head *list_all,
-			int *idx, char const *msg);
+void parse_events_error(void *data, void *scanner, char const *msg);
 int parse_events__test(void);
 
 void print_events(const char *event_glob);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 618a8e78839..384ca74c6b2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -1,4 +1,6 @@
 
+%option reentrant
+%option bison-bridge
 %option prefix="parse_events_"
 %option stack
 
@@ -8,7 +10,10 @@
 #include "parse-events-bison.h"
 #include "parse-events.h"
 
-static int __value(char *str, int base, int token)
+char *parse_events_get_text(yyscan_t yyscanner);
+YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
+
+static int __value(YYSTYPE *yylval, char *str, int base, int token)
 {
 	long num;
 
@@ -17,35 +22,48 @@ static int __value(char *str, int base, int token)
 	if (errno)
 		return PE_ERROR;
 
-	parse_events_lval.num = num;
+	yylval->num = num;
 	return token;
 }
 
-static int value(int base)
+static int value(yyscan_t scanner, int base)
 {
-	return __value(parse_events_text, base, PE_VALUE);
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	return __value(yylval, text, base, PE_VALUE);
 }
 
-static int raw(void)
+static int raw(yyscan_t scanner)
 {
-	return __value(parse_events_text + 1, 16, PE_RAW);
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	return __value(yylval, text + 1, 16, PE_RAW);
 }
 
-static int str(int token)
+static int str(yyscan_t scanner, int token)
 {
-	parse_events_lval.str = strdup(parse_events_text);
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+
+	yylval->str = strdup(text);
 	return token;
 }
 
-static int sym(int type, int config)
+static int sym(yyscan_t scanner, int type, int config)
 {
-	parse_events_lval.num = (type << 16) + config;
-	return PE_VALUE_SYM;
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = (type << 16) + config;
+	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
-static int term(int type)
+static int term(yyscan_t scanner, int type)
 {
-	parse_events_lval.num = type;
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = type;
 	return PE_TERM;
 }
 
@@ -58,28 +76,41 @@ num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
 modifier_event	[ukhpGH]{1,8}
-modifier_bp	[rwx]
+modifier_bp	[rwx]{1,3}
 
 %%
-cpu-cycles|cycles				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
-cpu-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
-task-clock					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
-page-faults|faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
-minor-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
-major-faults					{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
-context-switches|cs				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
-cpu-migrations|migrations			{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
-alignment-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
-emulation-faults				{ return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+
+%{
+	{
+		int start_token;
+
+		start_token = (int) parse_events_get_extra(yyscanner);
+		if (start_token) {
+			parse_events_set_extra(NULL, yyscanner);
+			return start_token;
+		}
+         }
+%}
+
+cpu-cycles|cycles				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 
 L1-dcache|l1-d|l1d|L1-data		|
 L1-icache|l1-i|l1i|L1-instruction	|
@@ -87,14 +118,14 @@ LLC|L2					|
 dTLB|d-tlb|Data-TLB			|
 iTLB|i-tlb|Instruction-TLB		|
 branch|branches|bpu|btb|bpc		|
-node					{ return str(PE_NAME_CACHE_TYPE); }
+node					{ return str(yyscanner, PE_NAME_CACHE_TYPE); }
 
 load|loads|read				|
 store|stores|write			|
 prefetch|prefetches			|
 speculative-read|speculative-load	|
 refs|Reference|ops|access		|
-misses|miss				{ return str(PE_NAME_CACHE_OP_RESULT); }
+misses|miss				{ return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
 
 	/*
 	 * These are event config hardcoded term names to be specified
@@ -102,38 +133,39 @@ misses|miss				{ return str(PE_NAME_CACHE_OP_RESULT); }
 	 * so we can put them here directly. In case the we have a conflict
 	 * in future, this needs to go into '//' condition block.
 	 */
-config			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG); }
-config1			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); }
-config2			{ return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); }
-name			{ return term(PARSE_EVENTS__TERM_TYPE_NAME); }
-period			{ return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
-branch_type		{ return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+name			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
+period			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
 
 mem:			{ BEGIN(mem); return PE_PREFIX_MEM; }
-r{num_raw_hex}		{ return raw(); }
-{num_dec}		{ return value(10); }
-{num_hex}		{ return value(16); }
+r{num_raw_hex}		{ return raw(yyscanner); }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
 
-{modifier_event}	{ return str(PE_MODIFIER_EVENT); }
-{name}			{ return str(PE_NAME); }
+{modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
+{name}			{ return str(yyscanner, PE_NAME); }
 "/"			{ return '/'; }
 -			{ return '-'; }
 ,			{ return ','; }
 :			{ return ':'; }
 =			{ return '='; }
+\n			{ }
 
 <mem>{
-{modifier_bp}		{ return str(PE_MODIFIER_BP); }
+{modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
 :			{ return ':'; }
-{num_dec}		{ return value(10); }
-{num_hex}		{ return value(16); }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
 	/*
 	 * We need to separate 'mem:' scanner part, in order to get specific
 	 * modifier bits parsed out. Otherwise we would need to handle PE_NAME
 	 * and we'd need to parse it manually. During the escape from <mem>
 	 * state we need to put the escaping char back, so we dont miss it.
 	 */
-.			{ unput(*parse_events_text); BEGIN(INITIAL); }
+.			{ unput(*yytext); BEGIN(INITIAL); }
 	/*
 	 * We destroy the scanner after reaching EOF,
 	 * but anyway just to be sure get back to INIT state.
@@ -143,7 +175,7 @@ r{num_raw_hex}		{ return raw(); }
 
 %%
 
-int parse_events_wrap(void)
+int parse_events_wrap(void *scanner __used)
 {
 	return 1;
 }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 362cc59332a..2bc5fbff2b5 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -1,7 +1,8 @@
-
+%pure-parser
 %name-prefix "parse_events_"
-%parse-param {struct list_head *list_all}
-%parse-param {int *idx}
+%parse-param {void *_data}
+%parse-param {void *scanner}
+%lex-param {void* scanner}
 
 %{
 
@@ -12,8 +13,9 @@
 #include "types.h"
 #include "util.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
-extern int parse_events_lex (void);
+extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
 
 #define ABORT_ON(val) \
 do { \
@@ -23,14 +25,16 @@ do { \
 
 %}
 
-%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%token PE_START_EVENTS PE_START_TERMS
+%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
 %token PE_NAME
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP
 %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
 %token PE_PREFIX_MEM PE_PREFIX_RAW
 %token PE_ERROR
 %type <num> PE_VALUE
-%type <num> PE_VALUE_SYM
+%type <num> PE_VALUE_SYM_HW
+%type <num> PE_VALUE_SYM_SW
 %type <num> PE_RAW
 %type <num> PE_TERM
 %type <str> PE_NAME
@@ -38,6 +42,7 @@ do { \
 %type <str> PE_NAME_CACHE_OP_RESULT
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
+%type <num> value_sym
 %type <head> event_config
 %type <term> event_term
 %type <head> event_pmu
@@ -58,24 +63,33 @@ do { \
 }
 %%
 
+start:
+PE_START_EVENTS events
+|
+PE_START_TERMS  terms
+
 events:
 events ',' event | event
 
 event:
 event_def PE_MODIFIER_EVENT
 {
+	struct parse_events_data__events *data = _data;
+
 	/*
 	 * Apply modifier on all events added by single event definition
 	 * (there could be more events added for multiple tracepoint
 	 * definitions via '*?'.
 	 */
 	ABORT_ON(parse_events_modifier($1, $2));
-	parse_events_update_lists($1, list_all);
+	parse_events_update_lists($1, &data->list);
 }
 |
 event_def
 {
-	parse_events_update_lists($1, list_all);
+	struct parse_events_data__events *data = _data;
+
+	parse_events_update_lists($1, &data->list);
 }
 
 event_def: event_pmu |
@@ -89,104 +103,131 @@ event_def: event_pmu |
 event_pmu:
 PE_NAME '/' event_config '/'
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_pmu(&list, idx, $1, $3));
+	ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
 
+value_sym:
+PE_VALUE_SYM_HW
+|
+PE_VALUE_SYM_SW
+
 event_legacy_symbol:
-PE_VALUE_SYM '/' event_config '/'
+value_sym '/' event_config '/'
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 	int type = $1 >> 16;
 	int config = $1 & 255;
 
-	ABORT_ON(parse_events_add_numeric(&list, idx, type, config, $3));
+	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+					  type, config, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
 |
-PE_VALUE_SYM sep_slash_dc
+value_sym sep_slash_dc
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 	int type = $1 >> 16;
 	int config = $1 & 255;
 
-	ABORT_ON(parse_events_add_numeric(&list, idx, type, config, NULL));
+	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+					  type, config, NULL));
 	$$ = list;
 }
 
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, $5));
+	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5));
 	$$ = list;
 }
 |
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, NULL));
+	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL));
 	$$ = list;
 }
 |
 PE_NAME_CACHE_TYPE
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_cache(&list, idx, $1, NULL, NULL));
+	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL));
 	$$ = list;
 }
 
 event_legacy_mem:
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, $4));
+	ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+					     (void *) $2, $4));
 	$$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE sep_dc
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, NULL));
+	ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+					     (void *) $2, NULL));
 	$$ = list;
 }
 
 event_legacy_tracepoint:
 PE_NAME ':' PE_NAME
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_tracepoint(&list, idx, $1, $3));
+	ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3));
 	$$ = list;
 }
 
 event_legacy_numeric:
 PE_VALUE ':' PE_VALUE
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_numeric(&list, idx, $1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(&list, &data->idx, $1, $3, NULL));
 	$$ = list;
 }
 
 event_legacy_raw:
 PE_RAW
 {
+	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
 
-	ABORT_ON(parse_events_add_numeric(&list, idx, PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+					  PERF_TYPE_RAW, $1, NULL));
 	$$ = list;
 }
 
+terms: event_config
+{
+	struct parse_events_data__terms *data = _data;
+	data->terms = $1;
+}
+
 event_config:
 event_config ',' event_term
 {
@@ -267,8 +308,7 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(struct list_head *list_all __used,
-			int *idx __used,
+void parse_events_error(void *data __used, void *scanner __used,
 			char const *msg __used)
 {
 }
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 99d02aa57db..594f8fad5ec 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "parse-options.h"
 #include "cache.h"
+#include "header.h"
 
 #define OPT_SHORT 1
 #define OPT_UNSET 2
@@ -413,6 +414,8 @@ int parse_options(int argc, const char **argv, const struct option *options,
 {
 	struct parse_opt_ctx_t ctx;
 
+	perf_header__set_cmdline(argc, argv);
+
 	parse_options_start(&ctx, argc, argv, flags);
 	switch (parse_options_step(&ctx, options, usagestr)) {
 	case PARSE_OPT_HELP:
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a119a537169..67715a42cd6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -72,7 +72,7 @@ static int pmu_format(char *name, struct list_head *format)
 		 "%s/bus/event_source/devices/%s/format", sysfs, name);
 
 	if (stat(path, &st) < 0)
-		return -1;
+		return 0;	/* no error if format does not exist */
 
 	if (pmu_format_parse(path, format))
 		return -1;
@@ -80,6 +80,114 @@ static int pmu_format(char *name, struct list_head *format)
 	return 0;
 }
 
+static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
+{
+	struct perf_pmu__alias *alias;
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+	buf[ret] = 0;
+
+	alias = malloc(sizeof(*alias));
+	if (!alias)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&alias->terms);
+	ret = parse_events_terms(&alias->terms, buf);
+	if (ret) {
+		free(alias);
+		return ret;
+	}
+
+	alias->name = strdup(name);
+	list_add_tail(&alias->list, list);
+	return 0;
+}
+
+/*
+ * Process all the sysfs attributes located under the directory
+ * specified in 'dir' parameter.
+ */
+static int pmu_aliases_parse(char *dir, struct list_head *head)
+{
+	struct dirent *evt_ent;
+	DIR *event_dir;
+	int ret = 0;
+
+	event_dir = opendir(dir);
+	if (!event_dir)
+		return -EINVAL;
+
+	while (!ret && (evt_ent = readdir(event_dir))) {
+		char path[PATH_MAX];
+		char *name = evt_ent->d_name;
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+		ret = -EINVAL;
+		file = fopen(path, "r");
+		if (!file)
+			break;
+		ret = perf_pmu__new_alias(head, name, file);
+		fclose(file);
+	}
+
+	closedir(event_dir);
+	return ret;
+}
+
+/*
+ * Reading the pmu event aliases definition, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
+ */
+static int pmu_aliases(char *name, struct list_head *head)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs_find_mountpoint();
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		 "%s/bus/event_source/devices/%s/events", sysfs, name);
+
+	if (stat(path, &st) < 0)
+		return -1;
+
+	if (pmu_aliases_parse(path, head))
+		return -1;
+
+	return 0;
+}
+
+static int pmu_alias_terms(struct perf_pmu__alias *alias,
+			   struct list_head *terms)
+{
+	struct parse_events__term *term, *clone;
+	LIST_HEAD(list);
+	int ret;
+
+	list_for_each_entry(term, &alias->terms, list) {
+		ret = parse_events__term_clone(&clone, term);
+		if (ret) {
+			parse_events__free_terms(&list);
+			return ret;
+		}
+		list_add_tail(&clone->list, &list);
+	}
+	list_splice(&list, terms);
+	return 0;
+}
+
 /*
  * Reading/parsing the default pmu type value, which should be
  * located at:
@@ -118,6 +226,7 @@ static struct perf_pmu *pmu_lookup(char *name)
 {
 	struct perf_pmu *pmu;
 	LIST_HEAD(format);
+	LIST_HEAD(aliases);
 	__u32 type;
 
 	/*
@@ -135,10 +244,15 @@ static struct perf_pmu *pmu_lookup(char *name)
 	if (!pmu)
 		return NULL;
 
+	pmu_aliases(name, &aliases);
+
 	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
+	list_splice(&aliases, &pmu->aliases);
 	pmu->name = strdup(name);
 	pmu->type = type;
+	list_add_tail(&pmu->list, &pmus);
 	return pmu;
 }
 
@@ -279,6 +393,59 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 	return pmu_config(&pmu->format, attr, head_terms);
 }
 
+static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu,
+					      struct parse_events__term *term)
+{
+	struct perf_pmu__alias *alias;
+	char *name;
+
+	if (parse_events__is_hardcoded_term(term))
+		return NULL;
+
+	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+		if (term->val.num != 1)
+			return NULL;
+		if (pmu_find_format(&pmu->format, term->config))
+			return NULL;
+		name = term->config;
+	} else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+		if (strcasecmp(term->config, "event"))
+			return NULL;
+		name = term->val.str;
+	} else {
+		return NULL;
+	}
+
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (!strcasecmp(alias->name, name))
+			return alias;
+	}
+	return NULL;
+}
+
+/*
+ * Find alias in the terms list and replace it with the terms
+ * defined for the alias
+ */
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
+{
+	struct parse_events__term *term, *h;
+	struct perf_pmu__alias *alias;
+	int ret;
+
+	list_for_each_entry_safe(term, h, head_terms, list) {
+		alias = pmu_find_alias(pmu, term);
+		if (!alias)
+			continue;
+		ret = pmu_alias_terms(alias, &term->list);
+		if (ret)
+			return ret;
+		list_del(&term->list);
+		free(term);
+	}
+	return 0;
+}
+
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits)
 {
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 68c0db965e1..535f2c5258a 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -19,17 +19,26 @@ struct perf_pmu__format {
 	struct list_head list;
 };
 
+struct perf_pmu__alias {
+	char *name;
+	struct list_head terms;
+	struct list_head list;
+};
+
 struct perf_pmu {
 	char *name;
 	__u32 type;
 	struct list_head format;
+	struct list_head aliases;
 	struct list_head list;
 };
 
 struct perf_pmu *perf_pmu__find(char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
-
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
+struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
+				struct list_head *head_terms);
 int perf_pmu_wrap(void);
 void perf_pmu_error(struct list_head *list, char *name, char const *msg);
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 2884e67ee62..213362850ab 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,10 +10,12 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
 util/cgroup.c
 util/debugfs.c
+util/rblist.c
 util/strlist.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index e03b58a4842..0688bfb6d28 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -797,17 +797,13 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 	event = perf_evlist__mmap_read(evlist, cpu);
 	if (event != NULL) {
-		struct perf_evsel *first;
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		first = list_entry(evlist->entries.next, struct perf_evsel, node);
-		err = perf_event__parse_sample(event, first->attr.sample_type,
-					       perf_evsel__sample_size(first),
-					       sample_id_all, &pevent->sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &pevent->sample, false);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
new file mode 100644
index 00000000000..0171fb61100
--- /dev/null
+++ b/tools/perf/util/rblist.c
@@ -0,0 +1,107 @@
+/*
+ * Based on strlist.c by:
+ * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Licensed under the GPLv2.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "rblist.h"
+
+int rblist__add_node(struct rblist *rblist, const void *new_entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL, *new_node;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, new_entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return -EEXIST;
+	}
+
+	new_node = rblist->node_new(rblist, new_entry);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	rb_link_node(new_node, parent, p);
+	rb_insert_color(new_node, &rblist->entries);
+	++rblist->nr_entries;
+
+	return 0;
+}
+
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
+{
+	rb_erase(rb_node, &rblist->entries);
+	rblist->node_delete(rblist, rb_node);
+}
+
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry)
+{
+	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*p != NULL) {
+		int rc;
+
+		parent = *p;
+
+		rc = rblist->node_cmp(parent, entry);
+		if (rc > 0)
+			p = &(*p)->rb_left;
+		else if (rc < 0)
+			p = &(*p)->rb_right;
+		else
+			return parent;
+	}
+
+	return NULL;
+}
+
+void rblist__init(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		rblist->entries	 = RB_ROOT;
+		rblist->nr_entries = 0;
+	}
+
+	return;
+}
+
+void rblist__delete(struct rblist *rblist)
+{
+	if (rblist != NULL) {
+		struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+		while (next) {
+			pos = next;
+			next = rb_next(pos);
+			rb_erase(pos, &rblist->entries);
+			rblist->node_delete(rblist, pos);
+		}
+		free(rblist);
+	}
+}
+
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx)
+{
+	struct rb_node *node;
+
+	for (node = rb_first(&rblist->entries); node; node = rb_next(node)) {
+		if (!idx--)
+			return node;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
new file mode 100644
index 00000000000..6d0cae5ae83
--- /dev/null
+++ b/tools/perf/util/rblist.h
@@ -0,0 +1,47 @@
+#ifndef __PERF_RBLIST_H
+#define __PERF_RBLIST_H
+
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+/*
+ * create node structs of the form:
+ * struct my_node {
+ *     struct rb_node rb_node;
+ *     ... my data ...
+ * };
+ *
+ * create list structs of the form:
+ * struct mylist {
+ *     struct rblist rblist;
+ *     ... my data ...
+ * };
+ */
+
+struct rblist {
+	struct rb_root entries;
+	unsigned int   nr_entries;
+
+	int (*node_cmp)(struct rb_node *rbn, const void *entry);
+	struct rb_node *(*node_new)(struct rblist *rlist, const void *new_entry);
+	void (*node_delete)(struct rblist *rblist, struct rb_node *rb_node);
+};
+
+void rblist__init(struct rblist *rblist);
+void rblist__delete(struct rblist *rblist);
+int rblist__add_node(struct rblist *rblist, const void *new_entry);
+void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
+struct rb_node *rblist__find(struct rblist *rblist, const void *entry);
+struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx);
+
+static inline bool rblist__empty(const struct rblist *rblist)
+{
+	return rblist->nr_entries == 0;
+}
+
+static inline unsigned int rblist__nr_entries(const struct rblist *rblist)
+{
+	return rblist->nr_entries;
+}
+
+#endif /* __PERF_RBLIST_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 4c1b3d72a1d..02dfa19a467 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -209,6 +209,10 @@ static void define_event_symbols(struct event_format *event,
 		define_symbolic_values(args->symbol.symbols, ev_name,
 				       cur_field_name);
 		break;
+	case PRINT_HEX:
+		define_event_symbols(event, ev_name, args->hex.field);
+		define_event_symbols(event, ev_name, args->hex.size);
+		break;
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_STRING:
@@ -233,7 +237,8 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(int type)
+static inline
+struct event_format *find_cache_event(struct pevent *pevent, int type)
 {
 	static char ev_name[256];
 	struct event_format *event;
@@ -241,7 +246,7 @@ static inline struct event_format *find_cache_event(int type)
 	if (events[type])
 		return events[type];
 
-	events[type] = event = trace_find_event(type);
+	events[type] = event = pevent_find_event(pevent, type);
 	if (!event)
 		return NULL;
 
@@ -252,7 +257,8 @@ static inline struct event_format *find_cache_event(int type)
 	return event;
 }
 
-static void perl_process_tracepoint(union perf_event *pevent __unused,
+static void perl_process_tracepoint(union perf_event *perf_event __unused,
+				    struct pevent *pevent,
 				    struct perf_sample *sample,
 				    struct perf_evsel *evsel,
 				    struct machine *machine __unused,
@@ -275,13 +281,13 @@ static void perl_process_tracepoint(union perf_event *pevent __unused,
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
-	type = trace_parse_common_type(data);
+	type = trace_parse_common_type(pevent, data);
 
-	event = find_cache_event(type);
+	event = find_cache_event(pevent, type);
 	if (!event)
 		die("ug! no event found for type %d", type);
 
-	pid = trace_parse_common_pid(data);
+	pid = trace_parse_common_pid(pevent, data);
 
 	sprintf(handler, "%s::%s", event->system, event->name);
 
@@ -314,7 +320,8 @@ static void perl_process_tracepoint(union perf_event *pevent __unused,
 				offset = field->offset;
 			XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0)));
 		} else { /* FIELD_IS_NUMERIC */
-			val = read_size(data + field->offset, field->size);
+			val = read_size(pevent, data + field->offset,
+					field->size);
 			if (field->flags & FIELD_IS_SIGNED) {
 				XPUSHs(sv_2mortal(newSViv(val)));
 			} else {
@@ -368,14 +375,15 @@ static void perl_process_event_generic(union perf_event *pevent __unused,
 	LEAVE;
 }
 
-static void perl_process_event(union perf_event *pevent,
+static void perl_process_event(union perf_event *event,
+			       struct pevent *pevent,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct machine *machine,
 			       struct thread *thread)
 {
-	perl_process_tracepoint(pevent, sample, evsel, machine, thread);
-	perl_process_event_generic(pevent, sample, evsel, machine, thread);
+	perl_process_tracepoint(event, pevent, sample, evsel, machine, thread);
+	perl_process_event_generic(event, sample, evsel, machine, thread);
 }
 
 static void run_start_sub(void)
@@ -448,7 +456,7 @@ static int perl_stop_script(void)
 	return 0;
 }
 
-static int perl_generate_script(const char *outfile)
+static int perl_generate_script(struct pevent *pevent, const char *outfile)
 {
 	struct event_format *event = NULL;
 	struct format_field *f;
@@ -495,7 +503,7 @@ static int perl_generate_script(const char *outfile)
 	fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n");
 	fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n");
 
-	while ((event = trace_find_next_event(event))) {
+	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
 		fprintf(ofp, "\tmy (");
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index acb9795286c..ce4d1b0c386 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -166,6 +166,10 @@ static void define_event_symbols(struct event_format *event,
 		define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
 			      cur_field_name);
 		break;
+	case PRINT_HEX:
+		define_event_symbols(event, ev_name, args->hex.field);
+		define_event_symbols(event, ev_name, args->hex.size);
+		break;
 	case PRINT_STRING:
 		break;
 	case PRINT_TYPE:
@@ -190,7 +194,8 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(int type)
+static inline
+struct event_format *find_cache_event(struct pevent *pevent, int type)
 {
 	static char ev_name[256];
 	struct event_format *event;
@@ -198,7 +203,7 @@ static inline struct event_format *find_cache_event(int type)
 	if (events[type])
 		return events[type];
 
-	events[type] = event = trace_find_event(type);
+	events[type] = event = pevent_find_event(pevent, type);
 	if (!event)
 		return NULL;
 
@@ -209,7 +214,8 @@ static inline struct event_format *find_cache_event(int type)
 	return event;
 }
 
-static void python_process_event(union perf_event *pevent __unused,
+static void python_process_event(union perf_event *perf_event __unused,
+				 struct pevent *pevent,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel __unused,
 				 struct machine *machine __unused,
@@ -233,13 +239,13 @@ static void python_process_event(union perf_event *pevent __unused,
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	type = trace_parse_common_type(data);
+	type = trace_parse_common_type(pevent, data);
 
-	event = find_cache_event(type);
+	event = find_cache_event(pevent, type);
 	if (!event)
 		die("ug! no event found for type %d", type);
 
-	pid = trace_parse_common_pid(data);
+	pid = trace_parse_common_pid(pevent, data);
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
@@ -284,7 +290,8 @@ static void python_process_event(union perf_event *pevent __unused,
 				offset = field->offset;
 			obj = PyString_FromString((char *)data + offset);
 		} else { /* FIELD_IS_NUMERIC */
-			val = read_size(data + field->offset, field->size);
+			val = read_size(pevent, data + field->offset,
+					field->size);
 			if (field->flags & FIELD_IS_SIGNED) {
 				if ((long long)val >= LONG_MIN &&
 				    (long long)val <= LONG_MAX)
@@ -438,7 +445,7 @@ out:
 	return err;
 }
 
-static int python_generate_script(const char *outfile)
+static int python_generate_script(struct pevent *pevent, const char *outfile)
 {
 	struct event_format *event = NULL;
 	struct format_field *f;
@@ -487,7 +494,7 @@ static int python_generate_script(const char *outfile)
 	fprintf(ofp, "def trace_end():\n");
 	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
 
-	while ((event = trace_find_next_event(event))) {
+	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
 		fprintf(ofp, "event_name, ");
 		fprintf(ofp, "context, ");
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c3e399bcf18..2437fb0b463 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
 #include "sort.h"
 #include "util.h"
 #include "cpumap.h"
+#include "event-parse.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -79,13 +80,12 @@ out_close:
 	return -1;
 }
 
-void perf_session__update_sample_type(struct perf_session *self)
+void perf_session__set_id_hdr_size(struct perf_session *session)
 {
-	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = __perf_evsel__sample_size(self->sample_type);
-	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
-	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
-	self->host_machine.id_hdr_size = self->id_hdr_size;
+	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+
+	session->host_machine.id_hdr_size = id_hdr_size;
+	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -145,7 +145,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
 			goto out_delete;
-		perf_session__update_sample_type(self);
+		perf_session__set_id_hdr_size(self);
 	} else if (mode == O_WRONLY) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
@@ -156,7 +156,7 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !self->sample_id_all) {
+	    tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
 		tool->ordered_samples = false;
 	}
@@ -289,7 +289,6 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 }
 
 int machine__resolve_callchain(struct machine *self,
-			       struct perf_evsel *evsel __used,
 			       struct thread *thread,
 			       struct ip_callchain *chain,
 			       struct symbol **parent)
@@ -672,7 +671,8 @@ static void flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ret = perf_session__parse_sample(s, iter->event, &sample);
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
+						s->header.needs_swap);
 		if (ret)
 			pr_err("Can't parse sample, err = %d\n", ret);
 		else
@@ -864,16 +864,18 @@ static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
+	u64 sample_type = perf_evlist__sample_type(session->evlist);
+
 	if (event->header.type != PERF_RECORD_SAMPLE &&
-	    !session->sample_id_all) {
+	    !perf_evlist__sample_id_all(session->evlist)) {
 		fputs("-1 -1 ", stdout);
 		return;
 	}
 
-	if ((session->sample_type & PERF_SAMPLE_CPU))
+	if ((sample_type & PERF_SAMPLE_CPU))
 		printf("%u ", sample->cpu);
 
-	if (session->sample_type & PERF_SAMPLE_TIME)
+	if (sample_type & PERF_SAMPLE_TIME)
 		printf("%" PRIu64 " ", sample->time);
 }
 
@@ -898,6 +900,8 @@ static void dump_event(struct perf_session *session, union perf_event *event,
 static void dump_sample(struct perf_session *session, union perf_event *event,
 			struct perf_sample *sample)
 {
+	u64 sample_type;
+
 	if (!dump_trace)
 		return;
 
@@ -905,10 +909,12 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
-	if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
+	sample_type = perf_evlist__sample_type(session->evlist);
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
 		callchain__printf(sample);
 
-	if (session->sample_type & PERF_SAMPLE_BRANCH_STACK)
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
 		branch_stack__printf(sample);
 }
 
@@ -918,7 +924,9 @@ static struct machine *
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+	if (perf_guest &&
+	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
+	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
 		if (event->header.type == PERF_RECORD_MMAP)
@@ -926,7 +934,7 @@ static struct machine *
 		else
 			pid = event->ip.pid;
 
-		return perf_session__find_machine(session, pid);
+		return perf_session__findnew_machine(session, pid);
 	}
 
 	return perf_session__find_host_machine(session);
@@ -1003,7 +1011,7 @@ static int perf_session__preprocess_sample(struct perf_session *session,
 					   union perf_event *event, struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+	    !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
 		return 0;
 
 	if (!ip_callchain__valid(sample->callchain, event)) {
@@ -1027,7 +1035,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(event, &session->evlist);
 		if (err == 0)
-			perf_session__update_sample_type(session);
+			perf_session__set_id_hdr_size(session);
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		return tool->event_type(tool, event);
@@ -1062,7 +1070,7 @@ static int perf_session__process_event(struct perf_session *session,
 	int ret;
 
 	if (session->header.needs_swap)
-		event_swap(event, session->sample_id_all);
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
 
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
@@ -1075,7 +1083,8 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	ret = perf_session__parse_sample(session, event, &sample);
+	ret = perf_evlist__parse_sample(session->evlist, event, &sample,
+					session->header.needs_swap);
 	if (ret)
 		return ret;
 
@@ -1386,9 +1395,9 @@ int perf_session__process_events(struct perf_session *self,
 	return err;
 }
 
-bool perf_session__has_traces(struct perf_session *self, const char *msg)
+bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(self->sample_type & PERF_SAMPLE_RAW)) {
+	if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
 		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
 		return false;
 	}
@@ -1449,7 +1458,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 	ret += hists__fprintf_nr_events(&session->hists, fp);
 
 	list_for_each_entry(pos, &session->evlist->entries, node) {
-		ret += fprintf(fp, "%s stats:\n", event_name(pos));
+		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
 		ret += hists__fprintf_nr_events(&pos->hists, fp);
 	}
 
@@ -1490,8 +1499,8 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 }
 
 void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
-			  struct machine *machine, struct perf_evsel *evsel,
-			  int print_sym, int print_dso, int print_symoffset)
+			  struct machine *machine, int print_sym,
+			  int print_dso, int print_symoffset)
 {
 	struct addr_location al;
 	struct callchain_cursor_node *node;
@@ -1505,7 +1514,7 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 
 	if (symbol_conf.use_callchain && sample->callchain) {
 
-		if (machine__resolve_callchain(machine, evsel, al.thread,
+		if (machine__resolve_callchain(machine, al.thread,
 						sample->callchain, NULL) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
@@ -1611,3 +1620,58 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
 	perf_header__fprintf_info(session, fp, full);
 	fprintf(fp, "# ========\n#\n");
 }
+
+
+int __perf_session__set_tracepoints_handlers(struct perf_session *session,
+					     const struct perf_evsel_str_handler *assocs,
+					     size_t nr_assocs)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct event_format *format;
+	struct perf_evsel *evsel;
+	char *tracepoint, *name;
+	size_t i;
+	int err;
+
+	for (i = 0; i < nr_assocs; i++) {
+		err = -ENOMEM;
+		tracepoint = strdup(assocs[i].name);
+		if (tracepoint == NULL)
+			goto out;
+
+		err = -ENOENT;
+		name = strchr(tracepoint, ':');
+		if (name == NULL)
+			goto out_free;
+
+		*name++ = '\0';
+		format = pevent_find_event_by_name(session->pevent,
+						   tracepoint, name);
+		if (format == NULL) {
+			/*
+			 * Adding a handler for an event not in the session,
+			 * just ignore it.
+			 */
+			goto next;
+		}
+
+		evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id);
+		if (evsel == NULL)
+			goto next;
+
+		err = -EEXIST;
+		if (evsel->handler.func != NULL)
+			goto out_free;
+		evsel->handler.func = assocs[i].handler;
+next:
+		free(tracepoint);
+	}
+
+	err = 0;
+out:
+	return err;
+
+out_free:
+	free(tracepoint);
+	goto out;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0c702e3f0a3..1f7ec87db7d 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -33,6 +33,7 @@ struct perf_session {
 	struct machine		host_machine;
 	struct rb_root		machines;
 	struct perf_evlist	*evlist;
+	struct pevent		*pevent;
 	/*
 	 * FIXME: Need to split this up further, we need global
 	 *	  stats + per event stats. 'perf diff' also needs
@@ -40,13 +41,9 @@ struct perf_session {
 	 *	  perf.data file.
 	 */
 	struct hists		hists;
-	u64			sample_type;
-	int			sample_size;
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
-	bool			sample_id_all;
-	u16			id_hdr_size;
 	int			cwdlen;
 	char			*cwd;
 	struct ordered_samples	ordered_samples;
@@ -85,7 +82,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *self);
 
-void perf_session__update_sample_type(struct perf_session *self);
+void perf_session__set_id_hdr_size(struct perf_session *session);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
@@ -129,33 +126,24 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 
-static inline int perf_session__parse_sample(struct perf_session *session,
-					     const union perf_event *event,
-					     struct perf_sample *sample)
-{
-	return perf_event__parse_sample(event, session->sample_type,
-					session->sample_size,
-					session->sample_id_all, sample,
-					session->header.needs_swap);
-}
-
-static inline int perf_session__synthesize_sample(struct perf_session *session,
-						  union perf_event *event,
-						  const struct perf_sample *sample)
-{
-	return perf_event__synthesize_sample(event, session->sample_type,
-					     sample, session->header.needs_swap);
-}
-
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
 void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
-			  struct machine *machine, struct perf_evsel *evsel,
-			  int print_sym, int print_dso, int print_symoffset);
+			  struct machine *machine, int print_sym,
+			  int print_dso, int print_symoffset);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);
 
 void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
+
+struct perf_evsel_str_handler;
+
+int __perf_session__set_tracepoints_handlers(struct perf_session *session,
+					     const struct perf_evsel_str_handler *assocs,
+					     size_t nr_assocs);
+
+#define perf_session__set_tracepoints_handlers(session, array) \
+	__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index a27237430c5..0f5a0a496bc 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -241,6 +241,54 @@ struct sort_entry sort_sym = {
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
+/* --sort srcline */
+
+static int64_t
+sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return (int64_t)(right->ip - left->ip);
+}
+
+static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
+				   size_t size, unsigned int width __used)
+{
+	FILE *fp;
+	char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
+	size_t line_len;
+
+	if (path != NULL)
+		goto out_path;
+
+	snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64,
+		 self->ms.map->dso->long_name, self->ip);
+	fp = popen(cmd, "r");
+	if (!fp)
+		goto out_ip;
+
+	if (getline(&path, &line_len, fp) < 0 || !line_len)
+		goto out_ip;
+	fclose(fp);
+	self->srcline = strdup(path);
+	if (self->srcline == NULL)
+		goto out_ip;
+
+	nl = strchr(self->srcline, '\n');
+	if (nl != NULL)
+		*nl = '\0';
+	path = self->srcline;
+out_path:
+	return repsep_snprintf(bf, size, "%s", path);
+out_ip:
+	return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
+}
+
+struct sort_entry sort_srcline = {
+	.se_header	= "Source:Line",
+	.se_cmp		= sort__srcline_cmp,
+	.se_snprintf	= hist_entry__srcline_snprintf,
+	.se_width_idx	= HISTC_SRCLINE,
+};
+
 /* --sort parent */
 
 static int64_t
@@ -439,6 +487,7 @@ static struct sort_dimension sort_dimensions[] = {
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
 	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
+	DIM(SORT_SRCLINE, "srcline", sort_srcline),
 };
 
 int sort_dimension__add(const char *tok)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 472aa5a63a5..e724b26acd5 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -71,6 +71,7 @@ struct hist_entry {
 	char			level;
 	bool			used;
 	u8			filtered;
+	char			*srcline;
 	struct symbol		*parent;
 	union {
 		unsigned long	  position;
@@ -93,6 +94,7 @@ enum sort_type {
 	SORT_SYM_FROM,
 	SORT_SYM_TO,
 	SORT_MISPREDICT,
+	SORT_SRCLINE,
 };
 
 /*
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d5836382ff2..199bc4d8905 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -313,3 +313,25 @@ int strtailcmp(const char *s1, const char *s2)
 	return 0;
 }
 
+/**
+ * rtrim - Removes trailing whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Note that the first trailing whitespace is replaced with a %NUL-terminator
+ * in the given string @s. Returns @s.
+ */
+char *rtrim(char *s)
+{
+	size_t size = strlen(s);
+	char *end;
+
+	if (!size)
+		return s;
+
+	end = s + size - 1;
+	while (end >= s && isspace(*end))
+		end--;
+	*(end + 1) = '\0';
+
+	return s;
+}
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 6783a204355..95856ff3dda 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -10,23 +10,28 @@
 #include <stdlib.h>
 #include <string.h>
 
-static struct str_node *str_node__new(const char *s, bool dupstr)
+static
+struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
 {
-	struct str_node *self = malloc(sizeof(*self));
+	const char *s = entry;
+	struct rb_node *rc = NULL;
+	struct strlist *strlist = container_of(rblist, struct strlist, rblist);
+	struct str_node *snode = malloc(sizeof(*snode));
 
-	if (self != NULL) {
-		if (dupstr) {
+	if (snode != NULL) {
+		if (strlist->dupstr) {
 			s = strdup(s);
 			if (s == NULL)
 				goto out_delete;
 		}
-		self->s = s;
+		snode->s = s;
+		rc = &snode->rb_node;
 	}
 
-	return self;
+	return rc;
 
 out_delete:
-	free(self);
+	free(snode);
 	return NULL;
 }
 
@@ -37,36 +42,26 @@ static void str_node__delete(struct str_node *self, bool dupstr)
 	free(self);
 }
 
-int strlist__add(struct strlist *self, const char *new_entry)
+static
+void strlist__node_delete(struct rblist *rblist, struct rb_node *rb_node)
 {
-	struct rb_node **p = &self->entries.rb_node;
-	struct rb_node *parent = NULL;
-	struct str_node *sn;
-
-	while (*p != NULL) {
-		int rc;
-
-		parent = *p;
-		sn = rb_entry(parent, struct str_node, rb_node);
-		rc = strcmp(sn->s, new_entry);
-
-		if (rc > 0)
-			p = &(*p)->rb_left;
-		else if (rc < 0)
-			p = &(*p)->rb_right;
-		else
-			return -EEXIST;
-	}
+	struct strlist *slist = container_of(rblist, struct strlist, rblist);
+	struct str_node *snode = container_of(rb_node, struct str_node, rb_node);
 
-	sn = str_node__new(new_entry, self->dupstr);
-	if (sn == NULL)
-		return -ENOMEM;
+	str_node__delete(snode, slist->dupstr);
+}
 
-	rb_link_node(&sn->rb_node, parent, p);
-	rb_insert_color(&sn->rb_node, &self->entries);
-	++self->nr_entries;
+static int strlist__node_cmp(struct rb_node *rb_node, const void *entry)
+{
+	const char *str = entry;
+	struct str_node *snode = container_of(rb_node, struct str_node, rb_node);
+
+	return strcmp(snode->s, str);
+}
 
-	return 0;
+int strlist__add(struct strlist *self, const char *new_entry)
+{
+	return rblist__add_node(&self->rblist, new_entry);
 }
 
 int strlist__load(struct strlist *self, const char *filename)
@@ -96,34 +91,20 @@ out:
 	return err;
 }
 
-void strlist__remove(struct strlist *self, struct str_node *sn)
+void strlist__remove(struct strlist *slist, struct str_node *snode)
 {
-	rb_erase(&sn->rb_node, &self->entries);
-	str_node__delete(sn, self->dupstr);
+	str_node__delete(snode, slist->dupstr);
 }
 
-struct str_node *strlist__find(struct strlist *self, const char *entry)
+struct str_node *strlist__find(struct strlist *slist, const char *entry)
 {
-	struct rb_node **p = &self->entries.rb_node;
-	struct rb_node *parent = NULL;
-
-	while (*p != NULL) {
-		struct str_node *sn;
-		int rc;
-
-		parent = *p;
-		sn = rb_entry(parent, struct str_node, rb_node);
-		rc = strcmp(sn->s, entry);
-
-		if (rc > 0)
-			p = &(*p)->rb_left;
-		else if (rc < 0)
-			p = &(*p)->rb_right;
-		else
-			return sn;
-	}
+	struct str_node *snode = NULL;
+	struct rb_node *rb_node = rblist__find(&slist->rblist, entry);
 
-	return NULL;
+	if (rb_node)
+		snode = container_of(rb_node, struct str_node, rb_node);
+
+	return snode;
 }
 
 static int strlist__parse_list_entry(struct strlist *self, const char *s)
@@ -156,9 +137,12 @@ struct strlist *strlist__new(bool dupstr, const char *slist)
 	struct strlist *self = malloc(sizeof(*self));
 
 	if (self != NULL) {
-		self->entries	 = RB_ROOT;
+		rblist__init(&self->rblist);
+		self->rblist.node_cmp    = strlist__node_cmp;
+		self->rblist.node_new    = strlist__node_new;
+		self->rblist.node_delete = strlist__node_delete;
+
 		self->dupstr	 = dupstr;
-		self->nr_entries = 0;
 		if (slist && strlist__parse_list(self, slist) != 0)
 			goto out_error;
 	}
@@ -171,30 +155,18 @@ out_error:
 
 void strlist__delete(struct strlist *self)
 {
-	if (self != NULL) {
-		struct str_node *pos;
-		struct rb_node *next = rb_first(&self->entries);
-
-		while (next) {
-			pos = rb_entry(next, struct str_node, rb_node);
-			next = rb_next(&pos->rb_node);
-			strlist__remove(self, pos);
-		}
-		self->entries = RB_ROOT;
-		free(self);
-	}
+	if (self != NULL)
+		rblist__delete(&self->rblist);
 }
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx)
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx)
 {
-	struct rb_node *nd;
+	struct str_node *snode = NULL;
+	struct rb_node *rb_node;
 
-	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
-		struct str_node *pos = rb_entry(nd, struct str_node, rb_node);
+	rb_node = rblist__entry(&slist->rblist, idx);
+	if (rb_node)
+		snode = container_of(rb_node, struct str_node, rb_node);
 
-		if (!idx--)
-			return pos;
-	}
-
-	return NULL;
+	return snode;
 }
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index 3ba839007d2..dd9f922ec67 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -4,14 +4,15 @@
 #include <linux/rbtree.h>
 #include <stdbool.h>
 
+#include "rblist.h"
+
 struct str_node {
 	struct rb_node rb_node;
 	const char     *s;
 };
 
 struct strlist {
-	struct rb_root entries;
-	unsigned int   nr_entries;
+	struct rblist rblist;
 	bool	       dupstr;
 };
 
@@ -32,18 +33,18 @@ static inline bool strlist__has_entry(struct strlist *self, const char *entry)
 
 static inline bool strlist__empty(const struct strlist *self)
 {
-	return self->nr_entries == 0;
+	return rblist__empty(&self->rblist);
 }
 
 static inline unsigned int strlist__nr_entries(const struct strlist *self)
 {
-	return self->nr_entries;
+	return rblist__nr_entries(&self->rblist);
 }
 
 /* For strlist iteration */
 static inline struct str_node *strlist__first(struct strlist *self)
 {
-	struct rb_node *rn = rb_first(&self->entries);
+	struct rb_node *rn = rb_first(&self->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3e2e5ea0f03..8b63b678e12 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,6 +29,7 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
+static void dso_cache__free(struct rb_root *root);
 static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
@@ -48,6 +49,31 @@ struct symbol_conf symbol_conf = {
 	.symfs            = "",
 };
 
+static enum dso_binary_type binary_type_symtab[] = {
+	DSO_BINARY_TYPE__KALLSYMS,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
+
+static enum dso_binary_type binary_type_data[] = {
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__DATA_CNT ARRAY_SIZE(binary_type_data)
+
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -318,7 +344,9 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->symtab_type = SYMTAB__NOT_FOUND;
+		dso->cache = RB_ROOT;
+		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
@@ -352,6 +380,7 @@ void dso__delete(struct dso *dso)
 		free((char *)dso->short_name);
 	if (dso->lname_alloc)
 		free(dso->long_name);
+	dso_cache__free(&dso->cache);
 	free(dso);
 }
 
@@ -806,9 +835,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	symbols__fixup_end(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 	else
-		dso->symtab_type = SYMTAB__KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	return dso__split_kallsyms(dso, map, filter);
 }
@@ -1478,14 +1507,31 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 		goto out;
 	}
 
-	sec = elf_section_by_name(elf, &ehdr, &shdr,
-				  ".note.gnu.build-id", NULL);
-	if (sec == NULL) {
+	/*
+	 * Check following sections for notes:
+	 *   '.note.gnu.build-id'
+	 *   '.notes'
+	 *   '.note' (VDSO specific)
+	 */
+	do {
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".note.gnu.build-id", NULL);
+		if (sec)
+			break;
+
 		sec = elf_section_by_name(elf, &ehdr, &shdr,
 					  ".notes", NULL);
-		if (sec == NULL)
-			goto out;
-	}
+		if (sec)
+			break;
+
+		sec = elf_section_by_name(elf, &ehdr, &shdr,
+					  ".note", NULL);
+		if (sec)
+			break;
+
+		return err;
+
+	} while (0);
 
 	data = elf_getdata(sec, NULL);
 	if (data == NULL)
@@ -1590,34 +1636,163 @@ out:
 	return err;
 }
 
+static int filename__read_debuglink(const char *filename,
+				    char *debuglink, size_t size)
+{
+	int fd, err = -1;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	Elf_Data *data;
+	Elf_Scn *sec;
+	Elf_Kind ek;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		goto out;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL) {
+		pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
+		goto out_close;
+	}
+
+	ek = elf_kind(elf);
+	if (ek != ELF_K_ELF)
+		goto out_close;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		pr_err("%s: cannot get elf header.\n", __func__);
+		goto out_close;
+	}
+
+	sec = elf_section_by_name(elf, &ehdr, &shdr,
+				  ".gnu_debuglink", NULL);
+	if (sec == NULL)
+		goto out_close;
+
+	data = elf_getdata(sec, NULL);
+	if (data == NULL)
+		goto out_close;
+
+	/* the start of this section is a zero-terminated string */
+	strncpy(debuglink, data->d_buf, size);
+
+	elf_end(elf);
+
+out_close:
+	close(fd);
+out:
+	return err;
+}
+
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
-		[SYMTAB__KALLSYMS]	      = 'k',
-		[SYMTAB__JAVA_JIT]	      = 'j',
-		[SYMTAB__BUILD_ID_CACHE]      = 'B',
-		[SYMTAB__FEDORA_DEBUGINFO]    = 'f',
-		[SYMTAB__UBUNTU_DEBUGINFO]    = 'u',
-		[SYMTAB__BUILDID_DEBUGINFO]   = 'b',
-		[SYMTAB__SYSTEM_PATH_DSO]     = 'd',
-		[SYMTAB__SYSTEM_PATH_KMODULE] = 'K',
-		[SYMTAB__GUEST_KALLSYMS]      =  'g',
-		[SYMTAB__GUEST_KMODULE]	      =  'G',
+		[DSO_BINARY_TYPE__KALLSYMS]		= 'k',
+		[DSO_BINARY_TYPE__JAVA_JIT]		= 'j',
+		[DSO_BINARY_TYPE__DEBUGLINK]		= 'l',
+		[DSO_BINARY_TYPE__BUILD_ID_CACHE]	= 'B',
+		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]	= 'f',
+		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]	= 'u',
+		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]	= 'b',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]	= 'd',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]	= 'K',
+		[DSO_BINARY_TYPE__GUEST_KALLSYMS]	= 'g',
+		[DSO_BINARY_TYPE__GUEST_KMODULE]	= 'G',
 	};
 
-	if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
+	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
 		return '!';
 	return origin[dso->symtab_type];
 }
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size)
+{
+	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	int ret = 0;
+
+	switch (type) {
+	case DSO_BINARY_TYPE__DEBUGLINK: {
+		char *debuglink;
+
+		strncpy(file, dso->long_name, size);
+		debuglink = file + dso->long_name_len;
+		while (debuglink != file && *debuglink != '/')
+			debuglink--;
+		if (*debuglink == '/')
+			debuglink++;
+		filename__read_debuglink(dso->long_name, debuglink,
+					 size - (debuglink - file));
+		}
+		break;
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		/* skip the locally configured cache if a symfs is given */
+		if (symbol_conf.symfs[0] ||
+		    (dso__build_id_filename(dso, file, size) == NULL))
+			ret = -1;
+		break;
+
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s.debug",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+		if (!dso->has_build_id) {
+			ret = -1;
+			break;
+		}
+
+		build_id__sprintf(dso->build_id,
+				  sizeof(dso->build_id),
+				  build_id_hex);
+		snprintf(file, size,
+			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+		snprintf(file, size, "%s%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+			 root_dir, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		snprintf(file, size, "%s%s", symbol_conf.symfs,
+			 dso->long_name);
+		break;
+
+	default:
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__NOT_FOUND:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
-	int size = PATH_MAX;
 	char *name;
 	int ret = -1;
 	int fd;
+	u_int i;
 	struct machine *machine;
-	const char *root_dir;
+	char *root_dir = (char *) "";
 	int want_symtab;
 
 	dso__set_loaded(dso, map->type);
@@ -1632,7 +1807,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	else
 		machine = NULL;
 
-	name = malloc(size);
+	name = malloc(PATH_MAX);
 	if (!name)
 		return -1;
 
@@ -1651,69 +1826,27 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
-		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
-					      SYMTAB__NOT_FOUND;
+		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
+					     DSO_BINARY_TYPE__NOT_FOUND;
 		return ret;
 	}
 
+	if (machine)
+		root_dir = machine->root_dir;
+
 	/* Iterate over candidate debug images.
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
 	want_symtab = 1;
 restart:
-	for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE;
-	     dso->symtab_type != SYMTAB__NOT_FOUND;
-	     dso->symtab_type++) {
-		switch (dso->symtab_type) {
-		case SYMTAB__BUILD_ID_CACHE:
-			/* skip the locally configured cache if a symfs is given */
-			if (symbol_conf.symfs[0] ||
-			    (dso__build_id_filename(dso, name, size) == NULL)) {
-				continue;
-			}
-			break;
-		case SYMTAB__FEDORA_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s.debug",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__UBUNTU_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__BUILDID_DEBUGINFO: {
-			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-
-			if (!dso->has_build_id)
-				continue;
+	for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
 
-			build_id__sprintf(dso->build_id,
-					  sizeof(dso->build_id),
-					  build_id_hex);
-			snprintf(name, size,
-				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
-			}
-			break;
-		case SYMTAB__SYSTEM_PATH_DSO:
-			snprintf(name, size, "%s%s",
-			     symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__GUEST_KMODULE:
-			if (map->groups && machine)
-				root_dir = machine->root_dir;
-			else
-				root_dir = "";
-			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
-				 root_dir, dso->long_name);
-			break;
+		dso->symtab_type = binary_type_symtab[i];
 
-		case SYMTAB__SYSTEM_PATH_KMODULE:
-			snprintf(name, size, "%s%s", symbol_conf.symfs,
-				 dso->long_name);
-			break;
-		default:;
-		}
+		if (dso__binary_type_file(dso, dso->symtab_type,
+					  root_dir, name, PATH_MAX))
+			continue;
 
 		/* Name is now the name of the next image to try */
 		fd = open(name, O_RDONLY);
@@ -1930,9 +2063,9 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		return NULL;
 
 	if (machine__is_host(machine))
-		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
-		dso->symtab_type = SYMTAB__GUEST_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
@@ -2484,8 +2617,15 @@ int machine__create_kernel_maps(struct machine *machine)
 	    __machine__create_kernel_maps(machine, kernel) < 0)
 		return -1;
 
-	if (symbol_conf.use_modules && machine__create_modules(machine) < 0)
-		pr_debug("Problems creating module maps, continuing anyway...\n");
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
+		if (machine__is_host(machine))
+			pr_debug("Problems creating module maps, "
+				 "continuing anyway...\n");
+		else
+			pr_debug("Problems creating module maps for guest %d, "
+				 "continuing anyway...\n", machine->pid);
+	}
+
 	/*
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
@@ -2735,6 +2875,7 @@ int machines__create_guest_kernel_maps(struct rb_root *machines)
 	int i, items = 0;
 	char path[PATH_MAX];
 	pid_t pid;
+	char *endp;
 
 	if (symbol_conf.default_guest_vmlinux_name ||
 	    symbol_conf.default_guest_modules ||
@@ -2751,7 +2892,14 @@ int machines__create_guest_kernel_maps(struct rb_root *machines)
 				/* Filter out . and .. */
 				continue;
 			}
-			pid = atoi(namelist[i]->d_name);
+			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
+			if ((*endp != '\0') ||
+			    (endp == namelist[i]->d_name) ||
+			    (errno == ERANGE)) {
+				pr_debug("invalid directory (%s). Skipping.\n",
+					 namelist[i]->d_name);
+				continue;
+			}
 			sprintf(path, "%s/%s/proc/kallsyms",
 				symbol_conf.guestmount,
 				namelist[i]->d_name);
@@ -2825,3 +2973,218 @@ struct map *dso__new_map(const char *name)
 
 	return map;
 }
+
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	char *root_dir = (char *) "";
+	char *name;
+	int fd;
+
+	name = malloc(PATH_MAX);
+	if (!name)
+		return -ENOMEM;
+
+	if (machine)
+		root_dir = machine->root_dir;
+
+	if (dso__binary_type_file(dso, dso->data_type,
+				  root_dir, name, PATH_MAX)) {
+		free(name);
+		return -EINVAL;
+	}
+
+	fd = open(name, O_RDONLY);
+	free(name);
+	return fd;
+}
+
+int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int i = 0;
+
+	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+		return open_dso(dso, machine);
+
+	do {
+		int fd;
+
+		dso->data_type = binary_type_data[i++];
+
+		fd = open_dso(dso, machine);
+		if (fd >= 0)
+			return fd;
+
+	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+
+	return -EINVAL;
+}
+
+static void
+dso_cache__free(struct rb_root *root)
+{
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct dso_cache *cache;
+
+		cache = rb_entry(next, struct dso_cache, rb_node);
+		next = rb_next(&cache->rb_node);
+		rb_erase(&cache->rb_node, root);
+		free(cache);
+	}
+}
+
+static struct dso_cache*
+dso_cache__find(struct rb_root *root, u64 offset)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+		else
+			return cache;
+	}
+	return NULL;
+}
+
+static void
+dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+	u64 offset = new->offset;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+}
+
+static ssize_t
+dso_cache__memcpy(struct dso_cache *cache, u64 offset,
+		  u8 *data, u64 size)
+{
+	u64 cache_offset = offset - cache->offset;
+	u64 cache_size   = min(cache->size - cache_offset, size);
+
+	memcpy(data, cache->data + cache_offset, cache_size);
+	return cache_size;
+}
+
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+		 u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+	ssize_t ret;
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return -1;
+
+	do {
+		u64 cache_offset;
+
+		ret = -ENOMEM;
+
+		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+		if (!cache)
+			break;
+
+		cache_offset = offset & DSO__DATA_CACHE_MASK;
+		ret = -EINVAL;
+
+		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+			break;
+
+		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		if (ret <= 0)
+			break;
+
+		cache->offset = cache_offset;
+		cache->size   = ret;
+		dso_cache__insert(&dso->cache, cache);
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+
+	} while (0);
+
+	if (ret <= 0)
+		free(cache);
+
+	close(fd);
+	return ret;
+}
+
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+
+	cache = dso_cache__find(&dso->cache, offset);
+	if (cache)
+		return dso_cache__memcpy(cache, offset, data, size);
+	else
+		return dso_cache__read(dso, machine, offset, data, size);
+}
+
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	ssize_t r = 0;
+	u8 *p = data;
+
+	do {
+		ssize_t ret;
+
+		ret = dso_cache_read(dso, machine, offset, p, size);
+		if (ret < 0)
+			return ret;
+
+		/* Reached EOF, return what we have. */
+		if (!ret)
+			break;
+
+		BUG_ON(ret > size);
+
+		r      += ret;
+		p      += ret;
+		offset += ret;
+		size   -= ret;
+
+	} while (size);
+
+	return r;
+}
+
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size)
+{
+	u64 offset = map->map_ip(map, addr);
+	return dso__data_read_offset(dso, machine, offset, data, size);
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index af0752b1aca..1fe733a1e21 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -155,6 +155,21 @@ struct addr_location {
 	s32	      cpu;
 };
 
+enum dso_binary_type {
+	DSO_BINARY_TYPE__KALLSYMS = 0,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
 enum dso_kernel_type {
 	DSO_TYPE_USER = 0,
 	DSO_TYPE_KERNEL,
@@ -167,19 +182,31 @@ enum dso_swap_type {
 	DSO_SWAP__YES,
 };
 
+#define DSO__DATA_CACHE_SIZE 4096
+#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
+
+struct dso_cache {
+	struct rb_node	rb_node;
+	u64 offset;
+	u64 size;
+	char data[0];
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 cache;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
+	enum dso_binary_type	symtab_type;
+	enum dso_binary_type	data_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
 	u8		 sname_alloc:1;
 	u8		 lname_alloc:1;
-	unsigned char	 symtab_type;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
@@ -253,20 +280,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 				    enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
-enum symtab_type {
-	SYMTAB__KALLSYMS = 0,
-	SYMTAB__GUEST_KALLSYMS,
-	SYMTAB__JAVA_JIT,
-	SYMTAB__BUILD_ID_CACHE,
-	SYMTAB__FEDORA_DEBUGINFO,
-	SYMTAB__UBUNTU_DEBUGINFO,
-	SYMTAB__BUILDID_DEBUGINFO,
-	SYMTAB__SYSTEM_PATH_DSO,
-	SYMTAB__GUEST_KMODULE,
-	SYMTAB__SYSTEM_PATH_KMODULE,
-	SYMTAB__NOT_FOUND,
-};
-
 char dso__symtab_origin(const struct dso *dso);
 void dso__set_long_name(struct dso *dso, char *name);
 void dso__set_build_id(struct dso *dso, void *build_id);
@@ -303,4 +316,14 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size);
+
+int dso__data_fd(struct dso *dso, struct machine *machine);
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size);
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size);
+int dso__test_data(void);
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 1064d5b148a..051eaa68095 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -110,8 +110,17 @@ int perf_target__strerror(struct perf_target *target, int errnum,
 	int idx;
 	const char *msg;
 
+	BUG_ON(buflen == 0);
+
 	if (errnum >= 0) {
-		strerror_r(errnum, buf, buflen);
+		const char *err = strerror_r(errnum, buf, buflen);
+
+		if (err != buf) {
+			size_t len = strlen(err);
+			char *c = mempcpy(buf, err, min(buflen - 1, len));
+			*c = '\0';
+		}
+
 		return 0;
 	}
 
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index abe0e8e9506..7eeebcee291 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -65,7 +65,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 				top->freq ? "Hz" : "");
 	}
 
-	ret += SNPRINTF(bf + ret, size - ret, "%s", event_name(top->sym_evsel));
+	ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
 
 	ret += SNPRINTF(bf + ret, size - ret, "], ");
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index df2fddbf0cd..0715c843c2e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -32,29 +32,25 @@ int header_page_size_size;
 int header_page_ts_size;
 int header_page_data_offset;
 
-struct pevent *perf_pevent;
-static struct pevent *pevent;
-
 bool latency_format;
 
-int read_trace_init(int file_bigendian, int host_bigendian)
+struct pevent *read_trace_init(int file_bigendian, int host_bigendian)
 {
-	if (pevent)
-		return 0;
-
-	perf_pevent = pevent_alloc();
-	pevent = perf_pevent;
+	struct pevent *pevent = pevent_alloc();
 
-	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-	pevent_set_file_bigendian(pevent, file_bigendian);
-	pevent_set_host_bigendian(pevent, host_bigendian);
+	if (pevent != NULL) {
+		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+		pevent_set_file_bigendian(pevent, file_bigendian);
+		pevent_set_host_bigendian(pevent, host_bigendian);
+	}
 
-	return 0;
+	return pevent;
 }
 
 static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
+	struct pevent *pevent = context->pevent;
 	struct event_format *event;
 	struct format_field *field;
 
@@ -150,7 +146,7 @@ void *raw_field_ptr(struct event_format *event, const char *name, void *data)
 	return data + field->offset;
 }
 
-int trace_parse_common_type(void *data)
+int trace_parse_common_type(struct pevent *pevent, void *data)
 {
 	struct pevent_record record;
 
@@ -158,7 +154,7 @@ int trace_parse_common_type(void *data)
 	return pevent_data_type(pevent, &record);
 }
 
-int trace_parse_common_pid(void *data)
+int trace_parse_common_pid(struct pevent *pevent, void *data)
 {
 	struct pevent_record record;
 
@@ -166,27 +162,21 @@ int trace_parse_common_pid(void *data)
 	return pevent_data_pid(pevent, &record);
 }
 
-unsigned long long read_size(void *ptr, int size)
+unsigned long long read_size(struct pevent *pevent, void *ptr, int size)
 {
 	return pevent_read_number(pevent, ptr, size);
 }
 
-struct event_format *trace_find_event(int type)
-{
-	return pevent_find_event(pevent, type);
-}
-
-
-void print_trace_event(int cpu, void *data, int size)
+void print_trace_event(struct pevent *pevent, int cpu, void *data, int size)
 {
 	struct event_format *event;
 	struct pevent_record record;
 	struct trace_seq s;
 	int type;
 
-	type = trace_parse_common_type(data);
+	type = trace_parse_common_type(pevent, data);
 
-	event = trace_find_event(type);
+	event = pevent_find_event(pevent, type);
 	if (!event) {
 		warning("ug! no event found for type %d", type);
 		return;
@@ -198,13 +188,12 @@ void print_trace_event(int cpu, void *data, int size)
 	record.data = data;
 
 	trace_seq_init(&s);
-	pevent_print_event(pevent, &s, &record);
+	pevent_event_info(&s, event, &record);
 	trace_seq_do_printf(&s);
-	printf("\n");
 }
 
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-		  char *comm)
+void print_event(struct pevent *pevent, int cpu, void *data, int size,
+		 unsigned long long nsecs, char *comm)
 {
 	struct pevent_record record;
 	struct trace_seq s;
@@ -227,7 +216,8 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs,
 	printf("\n");
 }
 
-void parse_proc_kallsyms(char *file, unsigned int size __unused)
+void parse_proc_kallsyms(struct pevent *pevent,
+			 char *file, unsigned int size __unused)
 {
 	unsigned long long addr;
 	char *func;
@@ -258,7 +248,8 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused)
 	}
 }
 
-void parse_ftrace_printk(char *file, unsigned int size __unused)
+void parse_ftrace_printk(struct pevent *pevent,
+			 char *file, unsigned int size __unused)
 {
 	unsigned long long addr;
 	char *printk;
@@ -282,17 +273,19 @@ void parse_ftrace_printk(char *file, unsigned int size __unused)
 	}
 }
 
-int parse_ftrace_file(char *buf, unsigned long size)
+int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
 {
 	return pevent_parse_event(pevent, buf, size, "ftrace");
 }
 
-int parse_event_file(char *buf, unsigned long size, char *sys)
+int parse_event_file(struct pevent *pevent,
+		     char *buf, unsigned long size, char *sys)
 {
 	return pevent_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct event_format *event)
+struct event_format *trace_find_next_event(struct pevent *pevent,
+					   struct event_format *event)
 {
 	static int idx;
 
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f097e0dd6c5..719ed74a856 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -114,20 +114,20 @@ static void skip(int size)
 	};
 }
 
-static unsigned int read4(void)
+static unsigned int read4(struct pevent *pevent)
 {
 	unsigned int data;
 
 	read_or_die(&data, 4);
-	return __data2host4(perf_pevent, data);
+	return __data2host4(pevent, data);
 }
 
-static unsigned long long read8(void)
+static unsigned long long read8(struct pevent *pevent)
 {
 	unsigned long long data;
 
 	read_or_die(&data, 8);
-	return __data2host8(perf_pevent, data);
+	return __data2host8(pevent, data);
 }
 
 static char *read_string(void)
@@ -168,12 +168,12 @@ static char *read_string(void)
 	return str;
 }
 
-static void read_proc_kallsyms(void)
+static void read_proc_kallsyms(struct pevent *pevent)
 {
 	unsigned int size;
 	char *buf;
 
-	size = read4();
+	size = read4(pevent);
 	if (!size)
 		return;
 
@@ -181,29 +181,29 @@ static void read_proc_kallsyms(void)
 	read_or_die(buf, size);
 	buf[size] = '\0';
 
-	parse_proc_kallsyms(buf, size);
+	parse_proc_kallsyms(pevent, buf, size);
 
 	free(buf);
 }
 
-static void read_ftrace_printk(void)
+static void read_ftrace_printk(struct pevent *pevent)
 {
 	unsigned int size;
 	char *buf;
 
-	size = read4();
+	size = read4(pevent);
 	if (!size)
 		return;
 
 	buf = malloc_or_die(size);
 	read_or_die(buf, size);
 
-	parse_ftrace_printk(buf, size);
+	parse_ftrace_printk(pevent, buf, size);
 
 	free(buf);
 }
 
-static void read_header_files(void)
+static void read_header_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	char *header_event;
@@ -214,7 +214,7 @@ static void read_header_files(void)
 	if (memcmp(buf, "header_page", 12) != 0)
 		die("did not read header page");
 
-	size = read8();
+	size = read8(pevent);
 	skip(size);
 
 	/*
@@ -227,47 +227,48 @@ static void read_header_files(void)
 	if (memcmp(buf, "header_event", 13) != 0)
 		die("did not read header event");
 
-	size = read8();
+	size = read8(pevent);
 	header_event = malloc_or_die(size);
 	read_or_die(header_event, size);
 	free(header_event);
 }
 
-static void read_ftrace_file(unsigned long long size)
+static void read_ftrace_file(struct pevent *pevent, unsigned long long size)
 {
 	char *buf;
 
 	buf = malloc_or_die(size);
 	read_or_die(buf, size);
-	parse_ftrace_file(buf, size);
+	parse_ftrace_file(pevent, buf, size);
 	free(buf);
 }
 
-static void read_event_file(char *sys, unsigned long long size)
+static void read_event_file(struct pevent *pevent, char *sys,
+			    unsigned long long size)
 {
 	char *buf;
 
 	buf = malloc_or_die(size);
 	read_or_die(buf, size);
-	parse_event_file(buf, size, sys);
+	parse_event_file(pevent, buf, size, sys);
 	free(buf);
 }
 
-static void read_ftrace_files(void)
+static void read_ftrace_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	int count;
 	int i;
 
-	count = read4();
+	count = read4(pevent);
 
 	for (i = 0; i < count; i++) {
-		size = read8();
-		read_ftrace_file(size);
+		size = read8(pevent);
+		read_ftrace_file(pevent, size);
 	}
 }
 
-static void read_event_files(void)
+static void read_event_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	char *sys;
@@ -275,15 +276,15 @@ static void read_event_files(void)
 	int count;
 	int i,x;
 
-	systems = read4();
+	systems = read4(pevent);
 
 	for (i = 0; i < systems; i++) {
 		sys = read_string();
 
-		count = read4();
+		count = read4(pevent);
 		for (x=0; x < count; x++) {
-			size = read8();
-			read_event_file(sys, size);
+			size = read8(pevent);
+			read_event_file(pevent, sys, size);
 		}
 	}
 }
@@ -377,7 +378,7 @@ static int calc_index(void *ptr, int cpu)
 	return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page;
 }
 
-struct pevent_record *trace_peek_data(int cpu)
+struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu)
 {
 	struct pevent_record *data;
 	void *page = cpu_data[cpu].page;
@@ -399,15 +400,15 @@ struct pevent_record *trace_peek_data(int cpu)
 		/* FIXME: handle header page */
 		if (header_page_ts_size != 8)
 			die("expected a long long type for timestamp");
-		cpu_data[cpu].timestamp = data2host8(perf_pevent, ptr);
+		cpu_data[cpu].timestamp = data2host8(pevent, ptr);
 		ptr += 8;
 		switch (header_page_size_size) {
 		case 4:
-			cpu_data[cpu].page_size = data2host4(perf_pevent, ptr);
+			cpu_data[cpu].page_size = data2host4(pevent, ptr);
 			ptr += 4;
 			break;
 		case 8:
-			cpu_data[cpu].page_size = data2host8(perf_pevent, ptr);
+			cpu_data[cpu].page_size = data2host8(pevent, ptr);
 			ptr += 8;
 			break;
 		default:
@@ -421,10 +422,10 @@ read_again:
 
 	if (idx >= cpu_data[cpu].page_size) {
 		get_next_page(cpu);
-		return trace_peek_data(cpu);
+		return trace_peek_data(pevent, cpu);
 	}
 
-	type_len_ts = data2host4(perf_pevent, ptr);
+	type_len_ts = data2host4(pevent, ptr);
 	ptr += 4;
 
 	type_len = type_len4host(type_len_ts);
@@ -434,14 +435,14 @@ read_again:
 	case RINGBUF_TYPE_PADDING:
 		if (!delta)
 			die("error, hit unexpected end of page");
-		length = data2host4(perf_pevent, ptr);
+		length = data2host4(pevent, ptr);
 		ptr += 4;
 		length *= 4;
 		ptr += length;
 		goto read_again;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
-		extend = data2host4(perf_pevent, ptr);
+		extend = data2host4(pevent, ptr);
 		ptr += 4;
 		extend <<= TS_SHIFT;
 		extend += delta;
@@ -452,7 +453,7 @@ read_again:
 		ptr += 12;
 		break;
 	case 0:
-		length = data2host4(perf_pevent, ptr);
+		length = data2host4(pevent, ptr);
 		ptr += 4;
 		die("here! length=%d", length);
 		break;
@@ -477,17 +478,17 @@ read_again:
 	return data;
 }
 
-struct pevent_record *trace_read_data(int cpu)
+struct pevent_record *trace_read_data(struct pevent *pevent, int cpu)
 {
 	struct pevent_record *data;
 
-	data = trace_peek_data(cpu);
+	data = trace_peek_data(pevent, cpu);
 	cpu_data[cpu].next = NULL;
 
 	return data;
 }
 
-ssize_t trace_report(int fd, bool __repipe)
+ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 {
 	char buf[BUFSIZ];
 	char test[] = { 23, 8, 68 };
@@ -519,30 +520,32 @@ ssize_t trace_report(int fd, bool __repipe)
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
-	read_trace_init(file_bigendian, host_bigendian);
+	*ppevent = read_trace_init(file_bigendian, host_bigendian);
+	if (*ppevent == NULL)
+		die("read_trace_init failed");
 
 	read_or_die(buf, 1);
 	long_size = buf[0];
 
-	page_size = read4();
+	page_size = read4(*ppevent);
 
-	read_header_files();
+	read_header_files(*ppevent);
 
-	read_ftrace_files();
-	read_event_files();
-	read_proc_kallsyms();
-	read_ftrace_printk();
+	read_ftrace_files(*ppevent);
+	read_event_files(*ppevent);
+	read_proc_kallsyms(*ppevent);
+	read_ftrace_printk(*ppevent);
 
 	size = calc_data_size - 1;
 	calc_data_size = 0;
 	repipe = false;
 
 	if (show_funcs) {
-		pevent_print_funcs(perf_pevent);
+		pevent_print_funcs(*ppevent);
 		return size;
 	}
 	if (show_printk) {
-		pevent_print_printk(perf_pevent);
+		pevent_print_printk(*ppevent);
 		return size;
 	}
 
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 18ae6c1831d..474aa7a7df4 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -36,6 +36,7 @@ static int stop_script_unsupported(void)
 }
 
 static void process_event_unsupported(union perf_event *event __unused,
+				      struct pevent *pevent __unused,
 				      struct perf_sample *sample __unused,
 				      struct perf_evsel *evsel __unused,
 				      struct machine *machine __unused,
@@ -61,7 +62,8 @@ static int python_start_script_unsupported(const char *script __unused,
 	return -1;
 }
 
-static int python_generate_script_unsupported(const char *outfile __unused)
+static int python_generate_script_unsupported(struct pevent *pevent __unused,
+					      const char *outfile __unused)
 {
 	print_python_unsupported_msg();
 
@@ -122,7 +124,8 @@ static int perl_start_script_unsupported(const char *script __unused,
 	return -1;
 }
 
-static int perl_generate_script_unsupported(const char *outfile __unused)
+static int perl_generate_script_unsupported(struct pevent *pevent __unused,
+					    const char *outfile __unused)
 {
 	print_perl_unsupported_msg();
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 639852ac111..8fef1d6687b 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -8,6 +8,7 @@
 struct machine;
 struct perf_sample;
 union perf_event;
+struct perf_tool;
 struct thread;
 
 extern int header_page_size_size;
@@ -29,35 +30,36 @@ enum {
 
 int bigendian(void);
 
-int read_trace_init(int file_bigendian, int host_bigendian);
-void print_trace_event(int cpu, void *data, int size);
+struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
+void print_trace_event(struct pevent *pevent, int cpu, void *data, int size);
 
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-		  char *comm);
+void print_event(struct pevent *pevent, int cpu, void *data, int size,
+		 unsigned long long nsecs, char *comm);
 
-int parse_ftrace_file(char *buf, unsigned long size);
-int parse_event_file(char *buf, unsigned long size, char *sys);
+int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
+int parse_event_file(struct pevent *pevent,
+		     char *buf, unsigned long size, char *sys);
 
-struct pevent_record *trace_peek_data(int cpu);
-struct event_format *trace_find_event(int type);
+struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu);
 
 unsigned long long
 raw_field_value(struct event_format *event, const char *name, void *data);
 void *raw_field_ptr(struct event_format *event, const char *name, void *data);
 
-void parse_proc_kallsyms(char *file, unsigned int size __unused);
-void parse_ftrace_printk(char *file, unsigned int size __unused);
+void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
+void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
 
-ssize_t trace_report(int fd, bool repipe);
+ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
 
-int trace_parse_common_type(void *data);
-int trace_parse_common_pid(void *data);
+int trace_parse_common_type(struct pevent *pevent, void *data);
+int trace_parse_common_pid(struct pevent *pevent, void *data);
 
-struct event_format *trace_find_next_event(struct event_format *event);
-unsigned long long read_size(void *ptr, int size);
+struct event_format *trace_find_next_event(struct pevent *pevent,
+					   struct event_format *event);
+unsigned long long read_size(struct pevent *pevent, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
-struct pevent_record *trace_read_data(int cpu);
+struct pevent_record *trace_read_data(struct pevent *pevent, int cpu);
 int read_tracing_data(int fd, struct list_head *pattrs);
 
 struct tracing_data {
@@ -77,11 +79,12 @@ struct scripting_ops {
 	int (*start_script) (const char *script, int argc, const char **argv);
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
+			       struct pevent *pevent,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct machine *machine,
 			       struct thread *thread);
-	int (*generate_script) (const char *outfile);
+	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
 int script_spec_register(const char *spec, struct scripting_ops *ops);
@@ -90,6 +93,7 @@ void setup_perl_scripting(void);
 void setup_python_scripting(void);
 
 struct scripting_context {
+	struct pevent *pevent;
 	void *event_data;
 };
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2daaedb83d8..b13c7331eaf 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -264,4 +264,6 @@ bool is_power_of_2(unsigned long n)
 
 size_t hex_width(u64 v);
 
+char *rtrim(char *s);
+
 #endif
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index fd8e1f1297a..f8564955419 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,4 +1,5 @@
 turbostat : turbostat.c
+CFLAGS +=	-Wall
 
 clean :
 	rm -f turbostat
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index adf175f6149..74e44507dfe 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -27,7 +27,11 @@ supports an "invariant" TSC, plus the APERF and MPERF MSRs.
 on processors that additionally support C-state residency counters.
 
 .SS Options
-The \fB-s\fP option prints only a 1-line summary for each sample interval.
+The \fB-s\fP option limits output to a 1-line system summary for each interval.
+.PP
+The \fB-c\fP option limits output to the 1st thread in each core.
+.PP
+The \fB-p\fP option limits output to the 1st thread in each package.
 .PP
 The \fB-v\fP option increases verbosity.
 .PP
@@ -65,19 +69,19 @@ Subsequent rows show per-CPU statistics.
 .nf
 [root@x980]# ./turbostat
 cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-          0.60 1.63 3.38   2.91   0.00  96.49   0.00  76.64
-  0   0   0.59 1.62 3.38   4.51   0.00  94.90   0.00  76.64
-  0   6   1.13 1.64 3.38   3.97   0.00  94.90   0.00  76.64
-  1   2   0.08 1.62 3.38   0.07   0.00  99.85   0.00  76.64
-  1   8   0.03 1.62 3.38   0.12   0.00  99.85   0.00  76.64
-  2   4   0.01 1.62 3.38   0.06   0.00  99.93   0.00  76.64
-  2  10   0.04 1.62 3.38   0.02   0.00  99.93   0.00  76.64
-  8   1   2.85 1.62 3.38  11.71   0.00  85.44   0.00  76.64
-  8   7   1.98 1.62 3.38  12.58   0.00  85.44   0.00  76.64
-  9   3   0.36 1.62 3.38   0.71   0.00  98.93   0.00  76.64
-  9   9   0.09 1.62 3.38   0.98   0.00  98.93   0.00  76.64
- 10   5   0.03 1.62 3.38   0.09   0.00  99.87   0.00  76.64
- 10  11   0.07 1.62 3.38   0.06   0.00  99.87   0.00  76.64
+          0.09 1.62 3.38   1.83   0.32  97.76   1.26  83.61
+  0   0   0.15 1.62 3.38  10.23   0.05  89.56   1.26  83.61
+  0   6   0.05 1.62 3.38  10.34
+  1   2   0.03 1.62 3.38   0.07   0.05  99.86
+  1   8   0.03 1.62 3.38   0.06
+  2   4   0.21 1.62 3.38   0.10   1.49  98.21
+  2  10   0.02 1.62 3.38   0.29
+  8   1   0.04 1.62 3.38   0.04   0.08  99.84
+  8   7   0.01 1.62 3.38   0.06
+  9   3   0.53 1.62 3.38   0.10   0.20  99.17
+  9   9   0.02 1.62 3.38   0.60
+ 10   5   0.01 1.62 3.38   0.02   0.04  99.92
+ 10  11   0.02 1.62 3.38   0.02
 .fi
 .SH SUMMARY EXAMPLE
 The "-s" option prints the column headers just once,
@@ -86,9 +90,10 @@ and then the one line system summary for each sample interval.
 .nf
 [root@x980]# ./turbostat -s
    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-  0.61 1.89 3.38   5.95   0.00  93.44   0.00  66.33
-  0.52 1.62 3.38   6.83   0.00  92.65   0.00  61.11
-  0.62 1.92 3.38   5.47   0.00  93.91   0.00  67.31
+  0.23 1.67 3.38   2.00   0.30  97.47   1.07  82.12
+  0.10 1.62 3.38   1.87   2.25  95.77  12.02  72.60
+  0.20 1.64 3.38   1.98   0.11  97.72   0.30  83.36
+  0.11 1.70 3.38   1.86   1.81  96.22   9.71  74.90
 .fi
 .SH VERBOSE EXAMPLE
 The "-v" option adds verbosity to the output:
@@ -120,30 +125,28 @@ until ^C while the other CPUs are mostly idle:
 [root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
 ^C
 cor CPU    %c0  GHz  TSC    %c1    %c3    %c6   %pc3   %pc6
-          8.63 3.64 3.38  14.46   0.49  76.42   0.00   0.00
-  0   0   0.34 3.36 3.38  99.66   0.00   0.00   0.00   0.00
-  0   6  99.96 3.64 3.38   0.04   0.00   0.00   0.00   0.00
-  1   2   0.14 3.50 3.38   1.75   2.04  96.07   0.00   0.00
-  1   8   0.38 3.57 3.38   1.51   2.04  96.07   0.00   0.00
-  2   4   0.01 2.65 3.38   0.06   0.00  99.93   0.00   0.00
-  2  10   0.03 2.12 3.38   0.04   0.00  99.93   0.00   0.00
-  8   1   0.91 3.59 3.38  35.27   0.92  62.90   0.00   0.00
-  8   7   1.61 3.63 3.38  34.57   0.92  62.90   0.00   0.00
-  9   3   0.04 3.38 3.38   0.20   0.00  99.76   0.00   0.00
-  9   9   0.04 3.29 3.38   0.20   0.00  99.76   0.00   0.00
- 10   5   0.03 3.08 3.38   0.12   0.00  99.85   0.00   0.00
- 10  11   0.05 3.07 3.38   0.10   0.00  99.85   0.00   0.00
-4.907015 sec
-
+          8.86 3.61 3.38  15.06  31.19  44.89   0.00   0.00
+  0   0   1.46 3.22 3.38  16.84  29.48  52.22   0.00   0.00
+  0   6   0.21 3.06 3.38  18.09
+  1   2   0.53 3.33 3.38   2.80  46.40  50.27
+  1   8   0.89 3.47 3.38   2.44
+  2   4   1.36 3.43 3.38   9.04  23.71  65.89
+  2  10   0.18 2.86 3.38  10.22
+  8   1   0.04 2.87 3.38  99.96   0.01   0.00
+  8   7  99.72 3.63 3.38   0.27
+  9   3   0.31 3.21 3.38   7.64  56.55  35.50
+  9   9   0.08 2.95 3.38   7.88
+ 10   5   1.42 3.43 3.38   2.14  30.99  65.44
+ 10  11   0.16 2.88 3.38   3.40
 .fi
-Above the cycle soaker drives cpu6 up 3.6 Ghz turbo limit
+Above the cycle soaker drives cpu7 up its 3.6 Ghz turbo limit
 while the other processors are generally in various states of idle.
 
-Note that cpu0 is an HT sibling sharing core0
-with cpu6, and thus it is unable to get to an idle state
-deeper than c1 while cpu6 is busy.
+Note that cpu1 and cpu7 are HT siblings within core8.
+As cpu7 is very busy, it prevents its sibling, cpu1,
+from entering a c-state deeper than c1.
 
-Note that turbostat reports average GHz of 3.64, while
+Note that turbostat reports average GHz of 3.63, while
 the arithmetic average of the GHz column above is lower.
 This is a weighted average, where the weight is %c0.  ie. it is the total number of
 un-halted cycles elapsed per time divided by the number of CPUs.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 16de7ad4850..861d7719020 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -67,92 +67,119 @@ double bclk;
 unsigned int show_pkg;
 unsigned int show_core;
 unsigned int show_cpu;
+unsigned int show_pkg_only;
+unsigned int show_core_only;
+char *output_buffer, *outp;
 
 int aperf_mperf_unstable;
 int backwards_count;
 char *progname;
 
-int num_cpus;
-cpu_set_t *cpu_present_set, *cpu_mask;
-size_t cpu_present_setsize, cpu_mask_size;
-
-struct counters {
-	unsigned long long tsc;		/* per thread */
-	unsigned long long aperf;	/* per thread */
-	unsigned long long mperf;	/* per thread */
-	unsigned long long c1;	/* per thread (calculated) */
-	unsigned long long c3;	/* per core */
-	unsigned long long c6;	/* per core */
-	unsigned long long c7;	/* per core */
-	unsigned long long pc2;	/* per package */
-	unsigned long long pc3;	/* per package */
-	unsigned long long pc6;	/* per package */
-	unsigned long long pc7;	/* per package */
-	unsigned long long extra_msr;	/* per thread */
-	int pkg;
-	int core;
-	int cpu;
-	struct counters *next;
-};
-
-struct counters *cnt_even;
-struct counters *cnt_odd;
-struct counters *cnt_delta;
-struct counters *cnt_average;
-struct timeval tv_even;
-struct timeval tv_odd;
-struct timeval tv_delta;
-
-int mark_cpu_present(int pkg, int core, int cpu)
+cpu_set_t *cpu_present_set, *cpu_affinity_set;
+size_t cpu_present_setsize, cpu_affinity_setsize;
+
+struct thread_data {
+	unsigned long long tsc;
+	unsigned long long aperf;
+	unsigned long long mperf;
+	unsigned long long c1;	/* derived */
+	unsigned long long extra_msr;
+	unsigned int cpu_id;
+	unsigned int flags;
+#define CPU_IS_FIRST_THREAD_IN_CORE	0x2
+#define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
+} *thread_even, *thread_odd;
+
+struct core_data {
+	unsigned long long c3;
+	unsigned long long c6;
+	unsigned long long c7;
+	unsigned int core_id;
+} *core_even, *core_odd;
+
+struct pkg_data {
+	unsigned long long pc2;
+	unsigned long long pc3;
+	unsigned long long pc6;
+	unsigned long long pc7;
+	unsigned int package_id;
+} *package_even, *package_odd;
+
+#define ODD_COUNTERS thread_odd, core_odd, package_odd
+#define EVEN_COUNTERS thread_even, core_even, package_even
+
+#define GET_THREAD(thread_base, thread_no, core_no, pkg_no) \
+	(thread_base + (pkg_no) * topo.num_cores_per_pkg * \
+		topo.num_threads_per_core + \
+		(core_no) * topo.num_threads_per_core + (thread_no))
+#define GET_CORE(core_base, core_no, pkg_no) \
+	(core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
+#define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
+
+struct system_summary {
+	struct thread_data threads;
+	struct core_data cores;
+	struct pkg_data packages;
+} sum, average;
+
+
+struct topo_params {
+	int num_packages;
+	int num_cpus;
+	int num_cores;
+	int max_cpu_num;
+	int num_cores_per_pkg;
+	int num_threads_per_core;
+} topo;
+
+struct timeval tv_even, tv_odd, tv_delta;
+
+void setup_all_buffers(void);
+
+int cpu_is_not_present(int cpu)
 {
-	CPU_SET_S(cpu, cpu_present_setsize, cpu_present_set);
-	return 0;
+	return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
 }
-
 /*
- * cpu_mask_init(ncpus)
- *
- * allocate and clear cpu_mask
- * set cpu_mask_size
+ * run func(thread, core, package) in topology order
+ * skip non-present cpus
  */
-void cpu_mask_init(int ncpus)
+
+int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *),
+	struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
 {
-	cpu_mask = CPU_ALLOC(ncpus);
-	if (cpu_mask == NULL) {
-		perror("CPU_ALLOC");
-		exit(3);
-	}
-	cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
-	CPU_ZERO_S(cpu_mask_size, cpu_mask);
+	int retval, pkg_no, core_no, thread_no;
 
-	/*
-	 * Allocate and initialize cpu_present_set
-	 */
-	cpu_present_set = CPU_ALLOC(ncpus);
-	if (cpu_present_set == NULL) {
-		perror("CPU_ALLOC");
-		exit(3);
-	}
-	cpu_present_setsize = CPU_ALLOC_SIZE(ncpus);
-	CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
-	for_all_cpus(mark_cpu_present);
-}
+	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
+		for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
+			for (thread_no = 0; thread_no <
+				topo.num_threads_per_core; ++thread_no) {
+				struct thread_data *t;
+				struct core_data *c;
+				struct pkg_data *p;
 
-void cpu_mask_uninit()
-{
-	CPU_FREE(cpu_mask);
-	cpu_mask = NULL;
-	cpu_mask_size = 0;
-	CPU_FREE(cpu_present_set);
-	cpu_present_set = NULL;
-	cpu_present_setsize = 0;
+				t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
+
+				if (cpu_is_not_present(t->cpu_id))
+					continue;
+
+				c = GET_CORE(core_base, core_no, pkg_no);
+				p = GET_PKG(pkg_base, pkg_no);
+
+				retval = func(t, c, p);
+				if (retval)
+					return retval;
+			}
+		}
+	}
+	return 0;
 }
 
 int cpu_migrate(int cpu)
 {
-	CPU_ZERO_S(cpu_mask_size, cpu_mask);
-	CPU_SET_S(cpu, cpu_mask_size, cpu_mask);
-	if (sched_setaffinity(0, cpu_mask_size, cpu_mask) == -1)
+	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
+	CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set);
+	if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1)
 		return -1;
 	else
 		return 0;
@@ -181,67 +208,72 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 void print_header(void)
 {
 	if (show_pkg)
-		fprintf(stderr, "pk");
+		outp += sprintf(outp, "pk");
 	if (show_pkg)
-		fprintf(stderr, " ");
+		outp += sprintf(outp, " ");
 	if (show_core)
-		fprintf(stderr, "cor");
+		outp += sprintf(outp, "cor");
 	if (show_cpu)
-		fprintf(stderr, " CPU");
+		outp += sprintf(outp, " CPU");
 	if (show_pkg || show_core || show_cpu)
-		fprintf(stderr, " ");
+		outp += sprintf(outp, " ");
 	if (do_nhm_cstates)
-		fprintf(stderr, "   %%c0");
+		outp += sprintf(outp, "   %%c0");
 	if (has_aperf)
-		fprintf(stderr, "  GHz");
-	fprintf(stderr, "  TSC");
+		outp += sprintf(outp, "  GHz");
+	outp += sprintf(outp, "  TSC");
 	if (do_nhm_cstates)
-		fprintf(stderr, "    %%c1");
+		outp += sprintf(outp, "    %%c1");
 	if (do_nhm_cstates)
-		fprintf(stderr, "    %%c3");
+		outp += sprintf(outp, "    %%c3");
 	if (do_nhm_cstates)
-		fprintf(stderr, "    %%c6");
+		outp += sprintf(outp, "    %%c6");
 	if (do_snb_cstates)
-		fprintf(stderr, "    %%c7");
+		outp += sprintf(outp, "    %%c7");
 	if (do_snb_cstates)
-		fprintf(stderr, "   %%pc2");
+		outp += sprintf(outp, "   %%pc2");
 	if (do_nhm_cstates)
-		fprintf(stderr, "   %%pc3");
+		outp += sprintf(outp, "   %%pc3");
 	if (do_nhm_cstates)
-		fprintf(stderr, "   %%pc6");
+		outp += sprintf(outp, "   %%pc6");
 	if (do_snb_cstates)
-		fprintf(stderr, "   %%pc7");
+		outp += sprintf(outp, "   %%pc7");
 	if (extra_msr_offset)
-		fprintf(stderr, "        MSR 0x%x ", extra_msr_offset);
+		outp += sprintf(outp, "        MSR 0x%x ", extra_msr_offset);
 
-	putc('\n', stderr);
+	outp += sprintf(outp, "\n");
 }
 
-void dump_cnt(struct counters *cnt)
+int dump_counters(struct thread_data *t, struct core_data *c,
+	struct pkg_data *p)
 {
-	if (!cnt)
-		return;
-	if (cnt->pkg) fprintf(stderr, "package: %d ", cnt->pkg);
-	if (cnt->core) fprintf(stderr, "core:: %d ", cnt->core);
-	if (cnt->cpu) fprintf(stderr, "CPU: %d ", cnt->cpu);
-	if (cnt->tsc) fprintf(stderr, "TSC: %016llX\n", cnt->tsc);
-	if (cnt->c3) fprintf(stderr, "c3: %016llX\n", cnt->c3);
-	if (cnt->c6) fprintf(stderr, "c6: %016llX\n", cnt->c6);
-	if (cnt->c7) fprintf(stderr, "c7: %016llX\n", cnt->c7);
-	if (cnt->aperf) fprintf(stderr, "aperf: %016llX\n", cnt->aperf);
-	if (cnt->pc2) fprintf(stderr, "pc2: %016llX\n", cnt->pc2);
-	if (cnt->pc3) fprintf(stderr, "pc3: %016llX\n", cnt->pc3);
-	if (cnt->pc6) fprintf(stderr, "pc6: %016llX\n", cnt->pc6);
-	if (cnt->pc7) fprintf(stderr, "pc7: %016llX\n", cnt->pc7);
-	if (cnt->extra_msr) fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, cnt->extra_msr);
-}
+	fprintf(stderr, "t %p, c %p, p %p\n", t, c, p);
+
+	if (t) {
+		fprintf(stderr, "CPU: %d flags 0x%x\n", t->cpu_id, t->flags);
+		fprintf(stderr, "TSC: %016llX\n", t->tsc);
+		fprintf(stderr, "aperf: %016llX\n", t->aperf);
+		fprintf(stderr, "mperf: %016llX\n", t->mperf);
+		fprintf(stderr, "c1: %016llX\n", t->c1);
+		fprintf(stderr, "msr0x%x: %016llX\n",
+			extra_msr_offset, t->extra_msr);
+	}
 
-void dump_list(struct counters *cnt)
-{
-	printf("dump_list 0x%p\n", cnt);
+	if (c) {
+		fprintf(stderr, "core: %d\n", c->core_id);
+		fprintf(stderr, "c3: %016llX\n", c->c3);
+		fprintf(stderr, "c6: %016llX\n", c->c6);
+		fprintf(stderr, "c7: %016llX\n", c->c7);
+	}
 
-	for (; cnt; cnt = cnt->next)
-		dump_cnt(cnt);
+	if (p) {
+		fprintf(stderr, "package: %d\n", p->package_id);
+		fprintf(stderr, "pc2: %016llX\n", p->pc2);
+		fprintf(stderr, "pc3: %016llX\n", p->pc3);
+		fprintf(stderr, "pc6: %016llX\n", p->pc6);
+		fprintf(stderr, "pc7: %016llX\n", p->pc7);
+	}
+	return 0;
 }
 
 /*
@@ -253,321 +285,389 @@ void dump_list(struct counters *cnt)
  * TSC: "TSC" 3 columns %3.2
  * percentage " %pc3" %6.2
  */
-void print_cnt(struct counters *p)
+int format_counters(struct thread_data *t, struct core_data *c,
+	struct pkg_data *p)
 {
 	double interval_float;
 
+	 /* if showing only 1st thread in core and this isn't one, bail out */
+	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+		return 0;
+
+	 /* if showing only 1st thread in pkg and this isn't one, bail out */
+	if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		return 0;
+
 	interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
 
-	/* topology columns, print blanks on 1st (average) line */
-	if (p == cnt_average) {
+	/* topo columns, print blanks on 1st (average) line */
+	if (t == &average.threads) {
 		if (show_pkg)
-			fprintf(stderr, "  ");
+			outp += sprintf(outp, "  ");
 		if (show_pkg && show_core)
-			fprintf(stderr, " ");
+			outp += sprintf(outp, " ");
 		if (show_core)
-			fprintf(stderr, "   ");
+			outp += sprintf(outp, "   ");
 		if (show_cpu)
-			fprintf(stderr, " " "   ");
+			outp += sprintf(outp, " " "   ");
 	} else {
-		if (show_pkg)
-			fprintf(stderr, "%2d", p->pkg);
+		if (show_pkg) {
+			if (p)
+				outp += sprintf(outp, "%2d", p->package_id);
+			else
+				outp += sprintf(outp, "  ");
+		}
 		if (show_pkg && show_core)
-			fprintf(stderr, " ");
-		if (show_core)
-			fprintf(stderr, "%3d", p->core);
+			outp += sprintf(outp, " ");
+		if (show_core) {
+			if (c)
+				outp += sprintf(outp, "%3d", c->core_id);
+			else
+				outp += sprintf(outp, "   ");
+		}
 		if (show_cpu)
-			fprintf(stderr, " %3d", p->cpu);
+			outp += sprintf(outp, " %3d", t->cpu_id);
 	}
 
 	/* %c0 */
 	if (do_nhm_cstates) {
 		if (show_pkg || show_core || show_cpu)
-			fprintf(stderr, " ");
+			outp += sprintf(outp, " ");
 		if (!skip_c0)
-			fprintf(stderr, "%6.2f", 100.0 * p->mperf/p->tsc);
+			outp += sprintf(outp, "%6.2f", 100.0 * t->mperf/t->tsc);
 		else
-			fprintf(stderr, "  ****");
+			outp += sprintf(outp, "  ****");
 	}
 
 	/* GHz */
 	if (has_aperf) {
 		if (!aperf_mperf_unstable) {
-			fprintf(stderr, " %3.2f",
-				1.0 * p->tsc / units * p->aperf /
-				p->mperf / interval_float);
+			outp += sprintf(outp, " %3.2f",
+				1.0 * t->tsc / units * t->aperf /
+				t->mperf / interval_float);
 		} else {
-			if (p->aperf > p->tsc || p->mperf > p->tsc) {
-				fprintf(stderr, " ***");
+			if (t->aperf > t->tsc || t->mperf > t->tsc) {
+				outp += sprintf(outp, " ***");
 			} else {
-				fprintf(stderr, "%3.1f*",
-					1.0 * p->tsc /
-					units * p->aperf /
-					p->mperf / interval_float);
+				outp += sprintf(outp, "%3.1f*",
+					1.0 * t->tsc /
+					units * t->aperf /
+					t->mperf / interval_float);
 			}
 		}
 	}
 
 	/* TSC */
-	fprintf(stderr, "%5.2f", 1.0 * p->tsc/units/interval_float);
+	outp += sprintf(outp, "%5.2f", 1.0 * t->tsc/units/interval_float);
 
 	if (do_nhm_cstates) {
 		if (!skip_c1)
-			fprintf(stderr, " %6.2f", 100.0 * p->c1/p->tsc);
+			outp += sprintf(outp, " %6.2f", 100.0 * t->c1/t->tsc);
 		else
-			fprintf(stderr, "  ****");
+			outp += sprintf(outp, "  ****");
 	}
+
+	/* print per-core data only for 1st thread in core */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+		goto done;
+
 	if (do_nhm_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->c3/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * c->c3/t->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->c6/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * c->c6/t->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->c7/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * c->c7/t->tsc);
+
+	/* print per-package data only for 1st core in package */
+	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		goto done;
+
 	if (do_snb_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->pc2/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc2/t->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->pc3/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc3/t->tsc);
 	if (do_nhm_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->pc6/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc6/t->tsc);
 	if (do_snb_cstates)
-		fprintf(stderr, " %6.2f", 100.0 * p->pc7/p->tsc);
+		outp += sprintf(outp, " %6.2f", 100.0 * p->pc7/t->tsc);
+done:
 	if (extra_msr_offset)
-		fprintf(stderr, "  0x%016llx", p->extra_msr);
-	putc('\n', stderr);
+		outp += sprintf(outp, "  0x%016llx", t->extra_msr);
+	outp += sprintf(outp, "\n");
+
+	return 0;
 }
 
-void print_counters(struct counters *counters)
+void flush_stdout()
+{
+	fputs(output_buffer, stdout);
+	outp = output_buffer;
+}
+void flush_stderr()
+{
+	fputs(output_buffer, stderr);
+	outp = output_buffer;
+}
+void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
-	struct counters *cnt;
 	static int printed;
 
-
 	if (!printed || !summary_only)
 		print_header();
 
-	if (num_cpus > 1)
-		print_cnt(cnt_average);
+	if (topo.num_cpus > 1)
+		format_counters(&average.threads, &average.cores,
+			&average.packages);
 
 	printed = 1;
 
 	if (summary_only)
 		return;
 
-	for (cnt = counters; cnt != NULL; cnt = cnt->next)
-		print_cnt(cnt);
-
+	for_all_cpus(format_counters, t, c, p);
 }
 
-#define SUBTRACT_COUNTER(after, before, delta) (delta = (after - before), (before > after))
+void
+delta_package(struct pkg_data *new, struct pkg_data *old)
+{
+	old->pc2 = new->pc2 - old->pc2;
+	old->pc3 = new->pc3 - old->pc3;
+	old->pc6 = new->pc6 - old->pc6;
+	old->pc7 = new->pc7 - old->pc7;
+}
 
-int compute_delta(struct counters *after,
-	struct counters *before, struct counters *delta)
+void
+delta_core(struct core_data *new, struct core_data *old)
 {
-	int errors = 0;
-	int perf_err = 0;
+	old->c3 = new->c3 - old->c3;
+	old->c6 = new->c6 - old->c6;
+	old->c7 = new->c7 - old->c7;
+}
 
-	skip_c0 = skip_c1 = 0;
+/*
+ * old = new - old
+ */
+void
+delta_thread(struct thread_data *new, struct thread_data *old,
+	struct core_data *core_delta)
+{
+	old->tsc = new->tsc - old->tsc;
+
+	/* check for TSC < 1 Mcycles over interval */
+	if (old->tsc < (1000 * 1000)) {
+		fprintf(stderr, "Insanely slow TSC rate, TSC stops in idle?\n");
+		fprintf(stderr, "You can disable all c-states by booting with \"idle=poll\"\n");
+		fprintf(stderr, "or just the deep ones with \"processor.max_cstate=1\"\n");
+		exit(-3);
+	}
 
-	for ( ; after && before && delta;
-		after = after->next, before = before->next, delta = delta->next) {
-		if (before->cpu != after->cpu) {
-			printf("cpu configuration changed: %d != %d\n",
-				before->cpu, after->cpu);
-			return -1;
-		}
+	old->c1 = new->c1 - old->c1;
 
-		if (SUBTRACT_COUNTER(after->tsc, before->tsc, delta->tsc)) {
-			fprintf(stderr, "cpu%d TSC went backwards %llX to %llX\n",
-				before->cpu, before->tsc, after->tsc);
-			errors++;
-		}
-		/* check for TSC < 1 Mcycles over interval */
-		if (delta->tsc < (1000 * 1000)) {
-			fprintf(stderr, "Insanely slow TSC rate,"
-				" TSC stops in idle?\n");
-			fprintf(stderr, "You can disable all c-states"
-				" by booting with \"idle=poll\"\n");
-			fprintf(stderr, "or just the deep ones with"
-				" \"processor.max_cstate=1\"\n");
-			exit(-3);
-		}
-		if (SUBTRACT_COUNTER(after->c3, before->c3, delta->c3)) {
-			fprintf(stderr, "cpu%d c3 counter went backwards %llX to %llX\n",
-				before->cpu, before->c3, after->c3);
-			errors++;
-		}
-		if (SUBTRACT_COUNTER(after->c6, before->c6, delta->c6)) {
-			fprintf(stderr, "cpu%d c6 counter went backwards %llX to %llX\n",
-				before->cpu, before->c6, after->c6);
-			errors++;
-		}
-		if (SUBTRACT_COUNTER(after->c7, before->c7, delta->c7)) {
-			fprintf(stderr, "cpu%d c7 counter went backwards %llX to %llX\n",
-				before->cpu, before->c7, after->c7);
-			errors++;
-		}
-		if (SUBTRACT_COUNTER(after->pc2, before->pc2, delta->pc2)) {
-			fprintf(stderr, "cpu%d pc2 counter went backwards %llX to %llX\n",
-				before->cpu, before->pc2, after->pc2);
-			errors++;
-		}
-		if (SUBTRACT_COUNTER(after->pc3, before->pc3, delta->pc3)) {
-			fprintf(stderr, "cpu%d pc3 counter went backwards %llX to %llX\n",
-				before->cpu, before->pc3, after->pc3);
-			errors++;
-		}
-		if (SUBTRACT_COUNTER(after->pc6, before->pc6, delta->pc6)) {
-			fprintf(stderr, "cpu%d pc6 counter went backwards %llX to %llX\n",
-				before->cpu, before->pc6, after->pc6);
-			errors++;
-		}
-		if (SUBTRACT_COUNTER(after->pc7, before->pc7, delta->pc7)) {
-			fprintf(stderr, "cpu%d pc7 counter went backwards %llX to %llX\n",
-				before->cpu, before->pc7, after->pc7);
-			errors++;
-		}
+	if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
+		old->aperf = new->aperf - old->aperf;
+		old->mperf = new->mperf - old->mperf;
+	} else {
 
-		perf_err = SUBTRACT_COUNTER(after->aperf, before->aperf, delta->aperf);
-		if (perf_err) {
-			fprintf(stderr, "cpu%d aperf counter went backwards %llX to %llX\n",
-				before->cpu, before->aperf, after->aperf);
-		}
-		perf_err |= SUBTRACT_COUNTER(after->mperf, before->mperf, delta->mperf);
-		if (perf_err) {
-			fprintf(stderr, "cpu%d mperf counter went backwards %llX to %llX\n",
-				before->cpu, before->mperf, after->mperf);
-		}
-		if (perf_err) {
-			if (!aperf_mperf_unstable) {
-				fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname);
-				fprintf(stderr, "* Frequency results do not cover entire interval *\n");
-				fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n");
+		if (!aperf_mperf_unstable) {
+			fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname);
+			fprintf(stderr, "* Frequency results do not cover entire interval *\n");
+			fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n");
 
-				aperf_mperf_unstable = 1;
-			}
-			/*
-			 * mperf delta is likely a huge "positive" number
-			 * can not use it for calculating c0 time
-			 */
-			skip_c0 = 1;
-			skip_c1 = 1;
+			aperf_mperf_unstable = 1;
 		}
-
 		/*
-		 * As mperf and tsc collection are not atomic,
-		 * it is possible for mperf's non-halted cycles
-		 * to exceed TSC's all cycles: show c1 = 0% in that case.
+		 * mperf delta is likely a huge "positive" number
+		 * can not use it for calculating c0 time
 		 */
-		if (delta->mperf > delta->tsc)
-			delta->c1 = 0;
-		else /* normal case, derive c1 */
-			delta->c1 = delta->tsc - delta->mperf
-				- delta->c3 - delta->c6 - delta->c7;
+		skip_c0 = 1;
+		skip_c1 = 1;
+	}
 
-		if (delta->mperf == 0)
-			delta->mperf = 1;	/* divide by 0 protection */
 
-		/*
-		 * for "extra msr", just copy the latest w/o subtracting
-		 */
-		delta->extra_msr = after->extra_msr;
-		if (errors) {
-			fprintf(stderr, "ERROR cpu%d before:\n", before->cpu);
-			dump_cnt(before);
-			fprintf(stderr, "ERROR cpu%d after:\n", before->cpu);
-			dump_cnt(after);
-			errors = 0;
-		}
+	/*
+	 * As counter collection is not atomic,
+	 * it is possible for mperf's non-halted cycles + idle states
+	 * to exceed TSC's all cycles: show c1 = 0% in that case.
+	 */
+	if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc)
+		old->c1 = 0;
+	else {
+		/* normal case, derive c1 */
+		old->c1 = old->tsc - old->mperf - core_delta->c3
+				- core_delta->c6 - core_delta->c7;
 	}
+
+	if (old->mperf == 0) {
+		if (verbose > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id);
+		old->mperf = 1;	/* divide by 0 protection */
+	}
+
+	/*
+	 * for "extra msr", just copy the latest w/o subtracting
+	 */
+	old->extra_msr = new->extra_msr;
+}
+
+int delta_cpu(struct thread_data *t, struct core_data *c,
+	struct pkg_data *p, struct thread_data *t2,
+	struct core_data *c2, struct pkg_data *p2)
+{
+	/* calculate core delta only for 1st thread in core */
+	if (t->flags & CPU_IS_FIRST_THREAD_IN_CORE)
+		delta_core(c, c2);
+
+	/* always calculate thread delta */
+	delta_thread(t, t2, c2);	/* c2 is core delta */
+
+	/* calculate package delta only for 1st core in package */
+	if (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)
+		delta_package(p, p2);
+
 	return 0;
 }
 
-void compute_average(struct counters *delta, struct counters *avg)
+void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	t->tsc = 0;
+	t->aperf = 0;
+	t->mperf = 0;
+	t->c1 = 0;
+
+	/* tells format_counters to dump all fields from this set */
+	t->flags = CPU_IS_FIRST_THREAD_IN_CORE | CPU_IS_FIRST_CORE_IN_PACKAGE;
+
+	c->c3 = 0;
+	c->c6 = 0;
+	c->c7 = 0;
+
+	p->pc2 = 0;
+	p->pc3 = 0;
+	p->pc6 = 0;
+	p->pc7 = 0;
+}
+int sum_counters(struct thread_data *t, struct core_data *c,
+	struct pkg_data *p)
 {
-	struct counters *sum;
+	average.threads.tsc += t->tsc;
+	average.threads.aperf += t->aperf;
+	average.threads.mperf += t->mperf;
+	average.threads.c1 += t->c1;
 
-	sum = calloc(1, sizeof(struct counters));
-	if (sum == NULL) {
-		perror("calloc sum");
-		exit(1);
-	}
+	/* sum per-core values only for 1st thread in core */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+		return 0;
 
-	for (; delta; delta = delta->next) {
-		sum->tsc += delta->tsc;
-		sum->c1 += delta->c1;
-		sum->c3 += delta->c3;
-		sum->c6 += delta->c6;
-		sum->c7 += delta->c7;
-		sum->aperf += delta->aperf;
-		sum->mperf += delta->mperf;
-		sum->pc2 += delta->pc2;
-		sum->pc3 += delta->pc3;
-		sum->pc6 += delta->pc6;
-		sum->pc7 += delta->pc7;
-	}
-	avg->tsc = sum->tsc/num_cpus;
-	avg->c1 = sum->c1/num_cpus;
-	avg->c3 = sum->c3/num_cpus;
-	avg->c6 = sum->c6/num_cpus;
-	avg->c7 = sum->c7/num_cpus;
-	avg->aperf = sum->aperf/num_cpus;
-	avg->mperf = sum->mperf/num_cpus;
-	avg->pc2 = sum->pc2/num_cpus;
-	avg->pc3 = sum->pc3/num_cpus;
-	avg->pc6 = sum->pc6/num_cpus;
-	avg->pc7 = sum->pc7/num_cpus;
-
-	free(sum);
+	average.cores.c3 += c->c3;
+	average.cores.c6 += c->c6;
+	average.cores.c7 += c->c7;
+
+	/* sum per-pkg values only for 1st core in pkg */
+	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		return 0;
+
+	average.packages.pc2 += p->pc2;
+	average.packages.pc3 += p->pc3;
+	average.packages.pc6 += p->pc6;
+	average.packages.pc7 += p->pc7;
+
+	return 0;
+}
+/*
+ * sum the counters for all cpus in the system
+ * compute the weighted average
+ */
+void compute_average(struct thread_data *t, struct core_data *c,
+	struct pkg_data *p)
+{
+	clear_counters(&average.threads, &average.cores, &average.packages);
+
+	for_all_cpus(sum_counters, t, c, p);
+
+	average.threads.tsc /= topo.num_cpus;
+	average.threads.aperf /= topo.num_cpus;
+	average.threads.mperf /= topo.num_cpus;
+	average.threads.c1 /= topo.num_cpus;
+
+	average.cores.c3 /= topo.num_cores;
+	average.cores.c6 /= topo.num_cores;
+	average.cores.c7 /= topo.num_cores;
+
+	average.packages.pc2 /= topo.num_packages;
+	average.packages.pc3 /= topo.num_packages;
+	average.packages.pc6 /= topo.num_packages;
+	average.packages.pc7 /= topo.num_packages;
 }
 
-int get_counters(struct counters *cnt)
+static unsigned long long rdtsc(void)
 {
-	for ( ; cnt; cnt = cnt->next) {
+	unsigned int low, high;
 
-		if (cpu_migrate(cnt->cpu))
-			return -1;
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
 
-		if (get_msr(cnt->cpu, MSR_TSC, &cnt->tsc))
-			return -1;
+	return low | ((unsigned long long)high) << 32;
+}
 
-		if (has_aperf) {
-			if (get_msr(cnt->cpu, MSR_APERF, &cnt->aperf))
-				return -1;
-			if (get_msr(cnt->cpu, MSR_MPERF, &cnt->mperf))
-				return -1;
-		}
 
-		if (do_nhm_cstates) {
-			if (get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY, &cnt->c3))
-				return -1;
-			if (get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY, &cnt->c6))
-				return -1;
-		}
+/*
+ * get_counters(...)
+ * migrate to cpu
+ * acquire and record local counters for that cpu
+ */
+int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	int cpu = t->cpu_id;
 
-		if (do_snb_cstates)
-			if (get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY, &cnt->c7))
-				return -1;
+	if (cpu_migrate(cpu))
+		return -1;
 
-		if (do_nhm_cstates) {
-			if (get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY, &cnt->pc3))
-				return -1;
-			if (get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY, &cnt->pc6))
-				return -1;
-		}
-		if (do_snb_cstates) {
-			if (get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY, &cnt->pc2))
-				return -1;
-			if (get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY, &cnt->pc7))
-				return -1;
-		}
-		if (extra_msr_offset)
-			if (get_msr(cnt->cpu, extra_msr_offset, &cnt->extra_msr))
-				return -1;
+	t->tsc = rdtsc();	/* we are running on local CPU of interest */
+
+	if (has_aperf) {
+		if (get_msr(cpu, MSR_APERF, &t->aperf))
+			return -3;
+		if (get_msr(cpu, MSR_MPERF, &t->mperf))
+			return -4;
+	}
+
+	if (extra_msr_offset)
+		if (get_msr(cpu, extra_msr_offset, &t->extra_msr))
+			return -5;
+
+	/* collect core counters only for 1st thread in core */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+		return 0;
+
+	if (do_nhm_cstates) {
+		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
+			return -6;
+		if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
+			return -7;
+	}
+
+	if (do_snb_cstates)
+		if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
+			return -8;
+
+	/* collect package counters only for 1st core in package */
+	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		return 0;
+
+	if (do_nhm_cstates) {
+		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
+			return -9;
+		if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6))
+			return -10;
+	}
+	if (do_snb_cstates) {
+		if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2))
+			return -11;
+		if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7))
+			return -12;
 	}
 	return 0;
 }
 
-void print_nehalem_info(void)
+void print_verbose_header(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
@@ -615,143 +715,82 @@ void print_nehalem_info(void)
 
 }
 
-void free_counter_list(struct counters *list)
+void free_all_buffers(void)
 {
-	struct counters *p;
+	CPU_FREE(cpu_present_set);
+	cpu_present_set = NULL;
+	cpu_present_set = 0;
 
-	for (p = list; p; ) {
-		struct counters *free_me;
+	CPU_FREE(cpu_affinity_set);
+	cpu_affinity_set = NULL;
+	cpu_affinity_setsize = 0;
 
-		free_me = p;
-		p = p->next;
-		free(free_me);
-	}
-}
+	free(thread_even);
+	free(core_even);
+	free(package_even);
 
-void free_all_counters(void)
-{
-	free_counter_list(cnt_even);
-	cnt_even = NULL;
+	thread_even = NULL;
+	core_even = NULL;
+	package_even = NULL;
 
-	free_counter_list(cnt_odd);
-	cnt_odd = NULL;
+	free(thread_odd);
+	free(core_odd);
+	free(package_odd);
 
-	free_counter_list(cnt_delta);
-	cnt_delta = NULL;
+	thread_odd = NULL;
+	core_odd = NULL;
+	package_odd = NULL;
 
-	free_counter_list(cnt_average);
-	cnt_average = NULL;
+	free(output_buffer);
+	output_buffer = NULL;
+	outp = NULL;
 }
 
-void insert_counters(struct counters **list,
-	struct counters *new)
+/*
+ * cpu_is_first_sibling_in_core(cpu)
+ * return 1 if given CPU is 1st HT sibling in the core
+ */
+int cpu_is_first_sibling_in_core(int cpu)
 {
-	struct counters *prev;
-
-	/*
-	 * list was empty
-	 */
-	if (*list == NULL) {
-		new->next = *list;
-		*list = new;
-		return;
-	}
-
-	if (!summary_only)
-		show_cpu = 1;	/* there is more than one CPU */
-
-	/*
-	 * insert on front of list.
-	 * It is sorted by ascending package#, core#, cpu#
-	 */
-	if (((*list)->pkg > new->pkg) ||
-	    (((*list)->pkg == new->pkg) && ((*list)->core > new->core)) ||
-	    (((*list)->pkg == new->pkg) && ((*list)->core == new->core) && ((*list)->cpu > new->cpu))) {
-		new->next = *list;
-		*list = new;
-		return;
-	}
-
-	prev = *list;
-
-	while (prev->next && (prev->next->pkg < new->pkg)) {
-		prev = prev->next;
-		if (!summary_only)
-			show_pkg = 1;	/* there is more than 1 package */
-	}
-
-	while (prev->next && (prev->next->pkg == new->pkg)
-		&& (prev->next->core < new->core)) {
-		prev = prev->next;
-		if (!summary_only)
-			show_core = 1;	/* there is more than 1 core */
-	}
+	char path[64];
+	FILE *filep;
+	int first_cpu;
 
-	while (prev->next && (prev->next->pkg == new->pkg)
-		&& (prev->next->core == new->core)
-		&& (prev->next->cpu < new->cpu)) {
-		prev = prev->next;
+	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
+	filep = fopen(path, "r");
+	if (filep == NULL) {
+		perror(path);
+		exit(1);
 	}
-
-	/*
-	 * insert after "prev"
-	 */
-	new->next = prev->next;
-	prev->next = new;
+	fscanf(filep, "%d", &first_cpu);
+	fclose(filep);
+	return (cpu == first_cpu);
 }
 
-void alloc_new_counters(int pkg, int core, int cpu)
+/*
+ * cpu_is_first_core_in_package(cpu)
+ * return 1 if given CPU is 1st core in package
+ */
+int cpu_is_first_core_in_package(int cpu)
 {
-	struct counters *new;
-
-	if (verbose > 1)
-		printf("pkg%d core%d, cpu%d\n", pkg, core, cpu);
-
-	new = (struct counters *)calloc(1, sizeof(struct counters));
-	if (new == NULL) {
-		perror("calloc");
-		exit(1);
-	}
-	new->pkg = pkg;
-	new->core = core;
-	new->cpu = cpu;
-	insert_counters(&cnt_odd, new);
-
-	new = (struct counters *)calloc(1,
-		sizeof(struct counters));
-	if (new == NULL) {
-		perror("calloc");
-		exit(1);
-	}
-	new->pkg = pkg;
-	new->core = core;
-	new->cpu = cpu;
-	insert_counters(&cnt_even, new);
-
-	new = (struct counters *)calloc(1, sizeof(struct counters));
-	if (new == NULL) {
-		perror("calloc");
-		exit(1);
-	}
-	new->pkg = pkg;
-	new->core = core;
-	new->cpu = cpu;
-	insert_counters(&cnt_delta, new);
+	char path[64];
+	FILE *filep;
+	int first_cpu;
 
-	new = (struct counters *)calloc(1, sizeof(struct counters));
-	if (new == NULL) {
-		perror("calloc");
+	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu);
+	filep = fopen(path, "r");
+	if (filep == NULL) {
+		perror(path);
 		exit(1);
 	}
-	new->pkg = pkg;
-	new->core = core;
-	new->cpu = cpu;
-	cnt_average = new;
+	fscanf(filep, "%d", &first_cpu);
+	fclose(filep);
+	return (cpu == first_cpu);
 }
 
 int get_physical_package_id(int cpu)
 {
-	char path[64];
+	char path[80];
 	FILE *filep;
 	int pkg;
 
@@ -768,7 +807,7 @@ int get_physical_package_id(int cpu)
 
 int get_core_id(int cpu)
 {
-	char path[64];
+	char path[80];
 	FILE *filep;
 	int core;
 
@@ -783,14 +822,87 @@ int get_core_id(int cpu)
 	return core;
 }
 
+int get_num_ht_siblings(int cpu)
+{
+	char path[80];
+	FILE *filep;
+	int sib1, sib2;
+	int matches;
+	char character;
+
+	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
+	filep = fopen(path, "r");
+	if (filep == NULL) {
+		perror(path);
+		exit(1);
+	}
+	/*
+	 * file format:
+	 * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4)
+	 * otherwinse 1 sibling (self).
+	 */
+	matches = fscanf(filep, "%d%c%d\n", &sib1, &character, &sib2);
+
+	fclose(filep);
+
+	if (matches == 3)
+		return 2;
+	else
+		return 1;
+}
+
 /*
- * run func(pkg, core, cpu) on every cpu in /proc/stat
+ * run func(thread, core, package) in topology order
+ * skip non-present cpus
  */
 
-int for_all_cpus(void (func)(int, int, int))
+int for_all_cpus_2(int (func)(struct thread_data *, struct core_data *,
+	struct pkg_data *, struct thread_data *, struct core_data *,
+	struct pkg_data *), struct thread_data *thread_base,
+	struct core_data *core_base, struct pkg_data *pkg_base,
+	struct thread_data *thread_base2, struct core_data *core_base2,
+	struct pkg_data *pkg_base2)
+{
+	int retval, pkg_no, core_no, thread_no;
+
+	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
+		for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
+			for (thread_no = 0; thread_no <
+				topo.num_threads_per_core; ++thread_no) {
+				struct thread_data *t, *t2;
+				struct core_data *c, *c2;
+				struct pkg_data *p, *p2;
+
+				t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
+
+				if (cpu_is_not_present(t->cpu_id))
+					continue;
+
+				t2 = GET_THREAD(thread_base2, thread_no, core_no, pkg_no);
+
+				c = GET_CORE(core_base, core_no, pkg_no);
+				c2 = GET_CORE(core_base2, core_no, pkg_no);
+
+				p = GET_PKG(pkg_base, pkg_no);
+				p2 = GET_PKG(pkg_base2, pkg_no);
+
+				retval = func(t, c, p, t2, c2, p2);
+				if (retval)
+					return retval;
+			}
+		}
+	}
+	return 0;
+}
+
+/*
+ * run func(cpu) on every cpu in /proc/stat
+ * return max_cpu number
+ */
+int for_all_proc_cpus(int (func)(int))
 {
 	FILE *fp;
-	int cpu_count;
+	int cpu_num;
 	int retval;
 
 	fp = fopen(proc_stat, "r");
@@ -805,78 +917,88 @@ int for_all_cpus(void (func)(int, int, int))
 		exit(1);
 	}
 
-	for (cpu_count = 0; ; cpu_count++) {
-		int cpu;
-
-		retval = fscanf(fp, "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", &cpu);
+	while (1) {
+		retval = fscanf(fp, "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", &cpu_num);
 		if (retval != 1)
 			break;
 
-		func(get_physical_package_id(cpu), get_core_id(cpu), cpu);
+		retval = func(cpu_num);
+		if (retval) {
+			fclose(fp);
+			return(retval);
+		}
 	}
 	fclose(fp);
-	return cpu_count;
+	return 0;
 }
 
 void re_initialize(void)
 {
-	free_all_counters();
-	num_cpus = for_all_cpus(alloc_new_counters);
-	cpu_mask_uninit();
-	cpu_mask_init(num_cpus);
-	printf("turbostat: re-initialized with num_cpus %d\n", num_cpus);
+	free_all_buffers();
+	setup_all_buffers();
+	printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
 }
 
-void dummy(int pkg, int core, int cpu) { return; }
+
 /*
- * check to see if a cpu came on-line
+ * count_cpus()
+ * remember the last one seen, it will be the max
  */
-int verify_num_cpus(void)
+int count_cpus(int cpu)
 {
-	int new_num_cpus;
-
-	new_num_cpus = for_all_cpus(dummy);
+	if (topo.max_cpu_num < cpu)
+		topo.max_cpu_num = cpu;
 
-	if (new_num_cpus != num_cpus) {
-		if (verbose)
-			printf("num_cpus was %d, is now  %d\n",
-				num_cpus, new_num_cpus);
-		return -1;
-	}
+	topo.num_cpus += 1;
+	return 0;
+}
+int mark_cpu_present(int cpu)
+{
+	CPU_SET_S(cpu, cpu_present_setsize, cpu_present_set);
 	return 0;
 }
 
 void turbostat_loop()
 {
+	int retval;
+
 restart:
-	get_counters(cnt_even);
+	retval = for_all_cpus(get_counters, EVEN_COUNTERS);
+	if (retval) {
+		re_initialize();
+		goto restart;
+	}
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	while (1) {
-		if (verify_num_cpus()) {
+		if (for_all_proc_cpus(cpu_is_not_present)) {
 			re_initialize();
 			goto restart;
 		}
 		sleep(interval_sec);
-		if (get_counters(cnt_odd)) {
+		retval = for_all_cpus(get_counters, ODD_COUNTERS);
+		if (retval) {
 			re_initialize();
 			goto restart;
 		}
 		gettimeofday(&tv_odd, (struct timezone *)NULL);
-		compute_delta(cnt_odd, cnt_even, cnt_delta);
 		timersub(&tv_odd, &tv_even, &tv_delta);
-		compute_average(cnt_delta, cnt_average);
-		print_counters(cnt_delta);
+		for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
+		compute_average(EVEN_COUNTERS);
+		format_all_counters(EVEN_COUNTERS);
+		flush_stdout();
 		sleep(interval_sec);
-		if (get_counters(cnt_even)) {
+		retval = for_all_cpus(get_counters, EVEN_COUNTERS);
+		if (retval) {
 			re_initialize();
 			goto restart;
 		}
 		gettimeofday(&tv_even, (struct timezone *)NULL);
-		compute_delta(cnt_even, cnt_odd, cnt_delta);
 		timersub(&tv_even, &tv_odd, &tv_delta);
-		compute_average(cnt_delta, cnt_average);
-		print_counters(cnt_delta);
+		for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS);
+		compute_average(ODD_COUNTERS);
+		format_all_counters(ODD_COUNTERS);
+		flush_stdout();
 	}
 }
 
@@ -1051,6 +1173,208 @@ int open_dev_cpu_msr(int dummy1)
 	return 0;
 }
 
+void topology_probe()
+{
+	int i;
+	int max_core_id = 0;
+	int max_package_id = 0;
+	int max_siblings = 0;
+	struct cpu_topology {
+		int core_id;
+		int physical_package_id;
+	} *cpus;
+
+	/* Initialize num_cpus, max_cpu_num */
+	topo.num_cpus = 0;
+	topo.max_cpu_num = 0;
+	for_all_proc_cpus(count_cpus);
+	if (!summary_only && topo.num_cpus > 1)
+		show_cpu = 1;
+
+	if (verbose > 1)
+		fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
+
+	cpus = calloc(1, (topo.max_cpu_num  + 1) * sizeof(struct cpu_topology));
+	if (cpus == NULL) {
+		perror("calloc cpus");
+		exit(1);
+	}
+
+	/*
+	 * Allocate and initialize cpu_present_set
+	 */
+	cpu_present_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_present_set == NULL) {
+		perror("CPU_ALLOC");
+		exit(3);
+	}
+	cpu_present_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
+	for_all_proc_cpus(mark_cpu_present);
+
+	/*
+	 * Allocate and initialize cpu_affinity_set
+	 */
+	cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_affinity_set == NULL) {
+		perror("CPU_ALLOC");
+		exit(3);
+	}
+	cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
+
+
+	/*
+	 * For online cpus
+	 * find max_core_id, max_package_id
+	 */
+	for (i = 0; i <= topo.max_cpu_num; ++i) {
+		int siblings;
+
+		if (cpu_is_not_present(i)) {
+			if (verbose > 1)
+				fprintf(stderr, "cpu%d NOT PRESENT\n", i);
+			continue;
+		}
+		cpus[i].core_id = get_core_id(i);
+		if (cpus[i].core_id > max_core_id)
+			max_core_id = cpus[i].core_id;
+
+		cpus[i].physical_package_id = get_physical_package_id(i);
+		if (cpus[i].physical_package_id > max_package_id)
+			max_package_id = cpus[i].physical_package_id;
+
+		siblings = get_num_ht_siblings(i);
+		if (siblings > max_siblings)
+			max_siblings = siblings;
+		if (verbose > 1)
+			fprintf(stderr, "cpu %d pkg %d core %d\n",
+				i, cpus[i].physical_package_id, cpus[i].core_id);
+	}
+	topo.num_cores_per_pkg = max_core_id + 1;
+	if (verbose > 1)
+		fprintf(stderr, "max_core_id %d, sizing for %d cores per package\n",
+			max_core_id, topo.num_cores_per_pkg);
+	if (!summary_only && topo.num_cores_per_pkg > 1)
+		show_core = 1;
+
+	topo.num_packages = max_package_id + 1;
+	if (verbose > 1)
+		fprintf(stderr, "max_package_id %d, sizing for %d packages\n",
+			max_package_id, topo.num_packages);
+	if (!summary_only && topo.num_packages > 1)
+		show_pkg = 1;
+
+	topo.num_threads_per_core = max_siblings;
+	if (verbose > 1)
+		fprintf(stderr, "max_siblings %d\n", max_siblings);
+
+	free(cpus);
+}
+
+void
+allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data **p)
+{
+	int i;
+
+	*t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
+		topo.num_packages, sizeof(struct thread_data));
+	if (*t == NULL)
+		goto error;
+
+	for (i = 0; i < topo.num_threads_per_core *
+		topo.num_cores_per_pkg * topo.num_packages; i++)
+		(*t)[i].cpu_id = -1;
+
+	*c = calloc(topo.num_cores_per_pkg * topo.num_packages,
+		sizeof(struct core_data));
+	if (*c == NULL)
+		goto error;
+
+	for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
+		(*c)[i].core_id = -1;
+
+	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
+	if (*p == NULL)
+		goto error;
+
+	for (i = 0; i < topo.num_packages; i++)
+		(*p)[i].package_id = i;
+
+	return;
+error:
+	perror("calloc counters");
+	exit(1);
+}
+/*
+ * init_counter()
+ *
+ * set cpu_id, core_num, pkg_num
+ * set FIRST_THREAD_IN_CORE and FIRST_CORE_IN_PACKAGE
+ *
+ * increment topo.num_cores when 1st core in pkg seen
+ */
+void init_counter(struct thread_data *thread_base, struct core_data *core_base,
+	struct pkg_data *pkg_base, int thread_num, int core_num,
+	int pkg_num, int cpu_id)
+{
+	struct thread_data *t;
+	struct core_data *c;
+	struct pkg_data *p;
+
+	t = GET_THREAD(thread_base, thread_num, core_num, pkg_num);
+	c = GET_CORE(core_base, core_num, pkg_num);
+	p = GET_PKG(pkg_base, pkg_num);
+
+	t->cpu_id = cpu_id;
+	if (thread_num == 0) {
+		t->flags |= CPU_IS_FIRST_THREAD_IN_CORE;
+		if (cpu_is_first_core_in_package(cpu_id))
+			t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE;
+	}
+
+	c->core_id = core_num;
+	p->package_id = pkg_num;
+}
+
+
+int initialize_counters(int cpu_id)
+{
+	int my_thread_id, my_core_id, my_package_id;
+
+	my_package_id = get_physical_package_id(cpu_id);
+	my_core_id = get_core_id(cpu_id);
+
+	if (cpu_is_first_sibling_in_core(cpu_id)) {
+		my_thread_id = 0;
+		topo.num_cores++;
+	} else {
+		my_thread_id = 1;
+	}
+
+	init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
+	init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
+	return 0;
+}
+
+void allocate_output_buffer()
+{
+	output_buffer = calloc(1, (1 + topo.num_cpus) * 128);
+	outp = output_buffer;
+	if (outp == NULL) {
+		perror("calloc");
+		exit(-1);
+	}
+}
+
+void setup_all_buffers(void)
+{
+	topology_probe();
+	allocate_counters(&thread_even, &core_even, &package_even);
+	allocate_counters(&thread_odd, &core_odd, &package_odd);
+	allocate_output_buffer();
+	for_all_proc_cpus(initialize_counters);
+}
 void turbostat_init()
 {
 	check_cpuid();
@@ -1058,21 +1382,19 @@ void turbostat_init()
 	check_dev_msr();
 	check_super_user();
 
-	num_cpus = for_all_cpus(alloc_new_counters);
-	cpu_mask_init(num_cpus);
+	setup_all_buffers();
 
 	if (verbose)
-		print_nehalem_info();
+		print_verbose_header();
 }
 
 int fork_it(char **argv)
 {
-	int retval;
 	pid_t child_pid;
-	get_counters(cnt_even);
 
-        /* clear affinity side-effect of get_counters() */
-        sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
+	for_all_cpus(get_counters, EVEN_COUNTERS);
+	/* clear affinity side-effect of get_counters() */
+	sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	child_pid = fork();
@@ -1095,14 +1417,17 @@ int fork_it(char **argv)
 			exit(1);
 		}
 	}
-	get_counters(cnt_odd);
+	/*
+	 * n.b. fork_it() does not check for errors from for_all_cpus()
+	 * because re-starting is problematic when forking
+	 */
+	for_all_cpus(get_counters, ODD_COUNTERS);
 	gettimeofday(&tv_odd, (struct timezone *)NULL);
-	retval = compute_delta(cnt_odd, cnt_even, cnt_delta);
-
 	timersub(&tv_odd, &tv_even, &tv_delta);
-	compute_average(cnt_delta, cnt_average);
-	if (!retval)
-		print_counters(cnt_delta);
+	for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
+	compute_average(EVEN_COUNTERS);
+	format_all_counters(EVEN_COUNTERS);
+	flush_stderr();
 
 	fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
 
@@ -1115,8 +1440,14 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+svi:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "+cpsvi:M:")) != -1) {
 		switch (opt) {
+		case 'c':
+			show_core_only++;
+			break;
+		case 'p':
+			show_pkg_only++;
+			break;
 		case 's':
 			summary_only++;
 			break;
@@ -1142,10 +1473,8 @@ int main(int argc, char **argv)
 	cmdline(argc, argv);
 
 	if (verbose > 1)
-		fprintf(stderr, "turbostat Dec 6, 2010"
+		fprintf(stderr, "turbostat v2.0 May 16, 2012"
 			" - Len Brown <lenb@kernel.org>\n");
-	if (verbose > 1)
-		fprintf(stderr, "http://userweb.kernel.org/~lenb/acpi/utils/pmtools/turbostat/\n");
 
 	turbostat_init();
 
diff --git a/tools/testing/fault-injection/failcmd.sh b/tools/testing/fault-injection/failcmd.sh
new file mode 100644
index 00000000000..78a9ed7fecd
--- /dev/null
+++ b/tools/testing/fault-injection/failcmd.sh
@@ -0,0 +1,219 @@
+#!/bin/bash
+#
+# NAME
+#	failcmd.sh - run a command with injecting slab/page allocation failures
+#
+# SYNOPSIS
+#	failcmd.sh --help
+#	failcmd.sh [<options>] command [arguments]
+#
+# DESCRIPTION
+#	Run command with injecting slab/page allocation failures by fault
+#	injection.
+#
+#	NOTE: you need to run this script as root.
+#
+
+usage()
+{
+	cat >&2 <<EOF
+Usage: $0 [options] command [arguments]
+
+OPTIONS
+	-p percent
+	--probability=percent
+		likelihood of failure injection, in percent.
+		Default value is 1
+
+	-t value
+	--times=value
+		specifies how many times failures may happen at most.
+		Default value is 1
+
+	--oom-kill-allocating-task=value
+		set /proc/sys/vm/oom_kill_allocating_task to specified value
+		before running the command.
+		Default value is 1
+
+	-h, --help
+		Display a usage message and exit
+
+	--interval=value, --space=value, --verbose=value, --task-filter=value,
+	--stacktrace-depth=value, --require-start=value, --require-end=value,
+	--reject-start=value, --reject-end=value, --ignore-gfp-wait=value
+		See Documentation/fault-injection/fault-injection.txt for more
+		information
+
+	failslab options:
+	--cache-filter=value
+
+	fail_page_alloc options:
+	--ignore-gfp-highmem=value, --min-order=value
+
+ENVIRONMENT
+	FAILCMD_TYPE
+		The following values for FAILCMD_TYPE are recognized:
+
+		failslab
+			inject slab allocation failures
+		fail_page_alloc
+			inject page allocation failures
+
+		If FAILCMD_TYPE is not defined, then failslab is used.
+EOF
+}
+
+if [ $UID != 0 ]; then
+	echo must be run as root >&2
+	exit 1
+fi
+
+DEBUGFS=`mount -t debugfs | head -1 | awk '{ print $3}'`
+
+if [ ! -d "$DEBUGFS" ]; then
+	echo debugfs is not mounted >&2
+	exit 1
+fi
+
+FAILCMD_TYPE=${FAILCMD_TYPE:-failslab}
+FAULTATTR=$DEBUGFS/$FAILCMD_TYPE
+
+if [ ! -d $FAULTATTR ]; then
+	echo $FAILCMD_TYPE is not available >&2
+	exit 1
+fi
+
+LONGOPTS=probability:,interval:,times:,space:,verbose:,task-filter:
+LONGOPTS=$LONGOPTS,stacktrace-depth:,require-start:,require-end:
+LONGOPTS=$LONGOPTS,reject-start:,reject-end:,oom-kill-allocating-task:,help
+
+if [ $FAILCMD_TYPE = failslab ]; then
+	LONGOPTS=$LONGOPTS,ignore-gfp-wait:,cache-filter:
+elif [ $FAILCMD_TYPE = fail_page_alloc ]; then
+	LONGOPTS=$LONGOPTS,ignore-gfp-wait:,ignore-gfp-highmem:,min-order:
+fi
+
+TEMP=`getopt -o p:i:t:s:v:h --long $LONGOPTS -n 'failcmd.sh' -- "$@"`
+
+if [ $? != 0 ]; then
+	usage
+	exit 1
+fi
+
+eval set -- "$TEMP"
+
+fault_attr_default()
+{
+	echo N > $FAULTATTR/task-filter
+	echo 0 > $FAULTATTR/probability
+	echo 1 > $FAULTATTR/times
+}
+
+fault_attr_default
+
+oom_kill_allocating_task_saved=`cat /proc/sys/vm/oom_kill_allocating_task`
+
+restore_values()
+{
+	fault_attr_default
+	echo $oom_kill_allocating_task_saved \
+		> /proc/sys/vm/oom_kill_allocating_task
+}
+
+#
+# Default options
+#
+declare -i oom_kill_allocating_task=1
+declare task_filter=Y
+declare -i probability=1
+declare -i times=1
+
+while true; do
+	case "$1" in
+	-p|--probability)
+		probability=$2
+		shift 2
+		;;
+	-i|--interval)
+		echo $2 > $FAULTATTR/interval
+		shift 2
+		;;
+	-t|--times)
+		times=$2
+		shift 2
+		;;
+	-s|--space)
+		echo $2 > $FAULTATTR/space
+		shift 2
+		;;
+	-v|--verbose)
+		echo $2 > $FAULTATTR/verbose
+		shift 2
+		;;
+	--task-filter)
+		task_filter=$2
+		shift 2
+		;;
+	--stacktrace-depth)
+		echo $2 > $FAULTATTR/stacktrace-depth
+		shift 2
+		;;
+	--require-start)
+		echo $2 > $FAULTATTR/require-start
+		shift 2
+		;;
+	--require-end)
+		echo $2 > $FAULTATTR/require-end
+		shift 2
+		;;
+	--reject-start)
+		echo $2 > $FAULTATTR/reject-start
+		shift 2
+		;;
+	--reject-end)
+		echo $2 > $FAULTATTR/reject-end
+		shift 2
+		;;
+	--oom-kill-allocating-task)
+		oom_kill_allocating_task=$2
+		shift 2
+		;;
+	--ignore-gfp-wait)
+		echo $2 > $FAULTATTR/ignore-gfp-wait
+		shift 2
+		;;
+	--cache-filter)
+		echo $2 > $FAULTATTR/cache_filter
+		shift 2
+		;;
+	--ignore-gfp-highmem)
+		echo $2 > $FAULTATTR/ignore-gfp-highmem
+		shift 2
+		;;
+	--min-order)
+		echo $2 > $FAULTATTR/min-order
+		shift 2
+		;;
+	-h|--help)
+		usage
+		exit 0
+		shift
+		;;
+	--)
+		shift
+		break
+		;;
+	esac
+done
+
+[ -z "$1" ] && exit 0
+
+echo $oom_kill_allocating_task > /proc/sys/vm/oom_kill_allocating_task
+echo $task_filter > $FAULTATTR/task-filter
+echo $probability > $FAULTATTR/probability
+echo $times > $FAULTATTR/times
+
+trap "restore_values" SIGINT SIGTERM EXIT
+
+cmd="echo 1 > /proc/self/make-it-fail && exec $@"
+bash -c "$cmd"
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 292b13ad03f..52b7959cd51 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -52,6 +52,7 @@ my %default = (
     "STOP_AFTER_SUCCESS"	=> 10,
     "STOP_AFTER_FAILURE"	=> 60,
     "STOP_TEST_AFTER"		=> 600,
+    "MAX_MONITOR_WAIT"		=> 1800,
 
 # required, and we will ask users if they don't have them but we keep the default
 # value something that is common.
@@ -77,6 +78,11 @@ my $output_config;
 my $test_type;
 my $build_type;
 my $build_options;
+my $final_post_ktest;
+my $pre_ktest;
+my $post_ktest;
+my $pre_test;
+my $post_test;
 my $pre_build;
 my $post_build;
 my $pre_build_die;
@@ -93,6 +99,7 @@ my $reboot_on_success;
 my $die_on_failure;
 my $powercycle_after_reboot;
 my $poweroff_after_halt;
+my $max_monitor_wait;
 my $ssh_exec;
 my $scp_to_target;
 my $scp_to_target_install;
@@ -101,6 +108,7 @@ my $grub_menu;
 my $grub_number;
 my $target;
 my $make;
+my $pre_install;
 my $post_install;
 my $no_install;
 my $noclean;
@@ -167,6 +175,7 @@ my $bisect_check;
 
 my $config_bisect;
 my $config_bisect_type;
+my $config_bisect_check;
 
 my $patchcheck_type;
 my $patchcheck_start;
@@ -182,6 +191,9 @@ my $newconfig = 0;
 my %entered_configs;
 my %config_help;
 my %variable;
+
+# force_config is the list of configs that we force enabled (or disabled)
+# in a .config file. The MIN_CONFIG and ADD_CONFIG configs.
 my %force_config;
 
 # do not force reboots on config problems
@@ -197,6 +209,10 @@ my %option_map = (
     "OUTPUT_DIR"		=> \$outputdir,
     "BUILD_DIR"			=> \$builddir,
     "TEST_TYPE"			=> \$test_type,
+    "PRE_KTEST"			=> \$pre_ktest,
+    "POST_KTEST"		=> \$post_ktest,
+    "PRE_TEST"			=> \$pre_test,
+    "POST_TEST"			=> \$post_test,
     "BUILD_TYPE"		=> \$build_type,
     "BUILD_OPTIONS"		=> \$build_options,
     "PRE_BUILD"			=> \$pre_build,
@@ -216,6 +232,7 @@ my %option_map = (
     "ADD_CONFIG"		=> \$addconfig,
     "REBOOT_TYPE"		=> \$reboot_type,
     "GRUB_MENU"			=> \$grub_menu,
+    "PRE_INSTALL"		=> \$pre_install,
     "POST_INSTALL"		=> \$post_install,
     "NO_INSTALL"		=> \$no_install,
     "REBOOT_SCRIPT"		=> \$reboot_script,
@@ -228,6 +245,7 @@ my %option_map = (
     "POWER_OFF"			=> \$power_off,
     "POWERCYCLE_AFTER_REBOOT"	=> \$powercycle_after_reboot,
     "POWEROFF_AFTER_HALT"	=> \$poweroff_after_halt,
+    "MAX_MONITOR_WAIT"		=> \$max_monitor_wait,
     "SLEEP_TIME"		=> \$sleep_time,
     "BISECT_SLEEP_TIME"		=> \$bisect_sleep_time,
     "PATCHCHECK_SLEEP_TIME"	=> \$patchcheck_sleep_time,
@@ -272,6 +290,7 @@ my %option_map = (
 
     "CONFIG_BISECT"		=> \$config_bisect,
     "CONFIG_BISECT_TYPE"	=> \$config_bisect_type,
+    "CONFIG_BISECT_CHECK"	=> \$config_bisect_check,
 
     "PATCHCHECK_TYPE"		=> \$patchcheck_type,
     "PATCHCHECK_START"		=> \$patchcheck_start,
@@ -604,6 +623,10 @@ sub process_compare {
 	return $lval eq $rval;
     } elsif ($cmp eq "!=") {
 	return $lval ne $rval;
+    } elsif ($cmp eq "=~") {
+	return $lval =~ m/$rval/;
+    } elsif ($cmp eq "!~") {
+	return $lval !~ m/$rval/;
     }
 
     my $statement = "$lval $cmp $rval";
@@ -659,7 +682,7 @@ sub process_expression {
 	}
     }
 
-    if ($val =~ /(.*)(==|\!=|>=|<=|>|<)(.*)/) {
+    if ($val =~ /(.*)(==|\!=|>=|<=|>|<|=~|\!~)(.*)/) {
 	my $ret = process_compare($1, $2, $3);
 	if ($ret < 0) {
 	    die "$name: $.: Unable to process comparison\n";
@@ -1117,7 +1140,11 @@ sub reboot {
     }
 
     if (defined($time)) {
-	wait_for_monitor($time, $reboot_success_line);
+	if (wait_for_monitor($time, $reboot_success_line)) {
+	    # reboot got stuck?
+	    doprint "Reboot did not finish. Forcing power cycle\n";
+	    run_command "$power_cycle";
+	}
 	end_monitor;
     }
 }
@@ -1212,6 +1239,11 @@ sub wait_for_monitor {
     my $full_line = "";
     my $line;
     my $booted = 0;
+    my $start_time = time;
+    my $skip_call_trace = 0;
+    my $bug = 0;
+    my $bug_ignored = 0;
+    my $now;
 
     doprint "** Wait for monitor to settle down **\n";
 
@@ -1227,11 +1259,39 @@ sub wait_for_monitor {
 	    $booted = 1;
 	}
 
+	if ($full_line =~ /\[ backtrace testing \]/) {
+	    $skip_call_trace = 1;
+	}
+
+	if ($full_line =~ /call trace:/i) {
+	    if (!$bug && !$skip_call_trace) {
+		if ($ignore_errors) {
+		    $bug_ignored = 1;
+		} else {
+		    $bug = 1;
+		}
+	    }
+	}
+
+	if ($full_line =~ /\[ end of backtrace testing \]/) {
+	    $skip_call_trace = 0;
+	}
+
+	if ($full_line =~ /Kernel panic -/) {
+	    $bug = 1;
+	}
+
 	if ($line =~ /\n/) {
 	    $full_line = "";
 	}
+	$now = time;
+	if ($now - $start_time >= $max_monitor_wait) {
+	    doprint "Exiting monitor flush due to hitting MAX_MONITOR_WAIT\n";
+	    return 1;
+	}
     }
     print "** Monitor flushed **\n";
+    return $bug;
 }
 
 sub save_logs {
@@ -1273,6 +1333,10 @@ sub save_logs {
 
 sub fail {
 
+	if (defined($post_test)) {
+		run_command $post_test;
+	}
+
 	if ($die_on_failure) {
 		dodie @_;
 	}
@@ -1656,6 +1720,12 @@ sub install {
 
     return if ($no_install);
 
+    if (defined($pre_install)) {
+	my $cp_pre_install = eval_kernel_version $pre_install;
+	run_command "$cp_pre_install" or
+	    dodie "Failed to run pre install";
+    }
+
     my $cp_target = eval_kernel_version $target_image;
 
     run_scp_install "$outputdir/$build_target", "$cp_target" or
@@ -1814,6 +1884,7 @@ sub make_oldconfig {
 sub load_force_config {
     my ($config) = @_;
 
+    doprint "Loading force configs from $config\n";
     open(IN, $config) or
 	dodie "failed to read $config";
     while (<IN>) {
@@ -1937,6 +2008,10 @@ sub halt {
 sub success {
     my ($i) = @_;
 
+    if (defined($post_test)) {
+	run_command $post_test;
+    }
+
     $successes++;
 
     my $name = "";
@@ -2003,6 +2078,7 @@ sub do_run_test {
     my $line;
     my $full_line;
     my $bug = 0;
+    my $bug_ignored = 0;
 
     wait_for_monitor 1;
 
@@ -2027,7 +2103,11 @@ sub do_run_test {
 	    doprint $line;
 
 	    if ($full_line =~ /call trace:/i) {
-		$bug = 1;
+		if ($ignore_errors) {
+		    $bug_ignored = 1;
+		} else {
+		    $bug = 1;
+		}
 	    }
 
 	    if ($full_line =~ /Kernel panic -/) {
@@ -2040,6 +2120,10 @@ sub do_run_test {
 	}
     } while (!$child_done && !$bug);
 
+    if (!$bug && $bug_ignored) {
+	doprint "WARNING: Call Trace detected but ignored due to IGNORE_ERRORS=1\n";
+    }
+
     if ($bug) {
 	my $failure_start = time;
 	my $now;
@@ -2362,9 +2446,24 @@ sub bisect {
     success $i;
 }
 
+# config_ignore holds the configs that were set (or unset) for
+# a good config and we will ignore these configs for the rest
+# of a config bisect. These configs stay as they were.
 my %config_ignore;
+
+# config_set holds what all configs were set as.
 my %config_set;
 
+# config_off holds the set of configs that the bad config had disabled.
+# We need to record them and set them in the .config when running
+# oldnoconfig, because oldnoconfig does not turn off new symbols, but
+# instead just keeps the defaults.
+my %config_off;
+
+# config_off_tmp holds a set of configs to turn off for now
+my @config_off_tmp;
+
+# config_list is the set of configs that are being tested
 my %config_list;
 my %null_config;
 
@@ -2443,12 +2542,21 @@ sub create_config {
 	}
     }
 
+    # turn off configs to keep off
+    foreach my $config (keys %config_off) {
+	print OUT "# $config is not set\n";
+    }
+
+    # turn off configs that should be off for now
+    foreach my $config (@config_off_tmp) {
+	print OUT "# $config is not set\n";
+    }
+
     foreach my $config (keys %config_ignore) {
 	print OUT "$config_ignore{$config}\n";
     }
     close(OUT);
 
-#    exit;
     make_oldconfig;
 }
 
@@ -2525,6 +2633,13 @@ sub run_config_bisect {
     do {
 	my @tophalf = @start_list[0 .. $half];
 
+	# keep the bottom half off
+	if ($half < $#start_list) {
+	    @config_off_tmp = @start_list[$half + 1 .. $#start_list];
+	} else {
+	    @config_off_tmp = ();
+	}
+
 	create_config @tophalf;
 	read_current_config \%current_config;
 
@@ -2541,7 +2656,11 @@ sub run_config_bisect {
 	if (!$found) {
 	    # try the other half
 	    doprint "Top half produced no set configs, trying bottom half\n";
+
+	    # keep the top half off
+	    @config_off_tmp = @tophalf;
 	    @tophalf = @start_list[$half + 1 .. $#start_list];
+
 	    create_config @tophalf;
 	    read_current_config \%current_config;
 	    foreach my $config (@tophalf) {
@@ -2679,6 +2798,10 @@ sub config_bisect {
 		$added_configs{$2} = $1;
 		$config_list{$2} = $1;
 	    }
+	} elsif (/^# ((CONFIG\S*).*)/) {
+	    # Keep these configs disabled
+	    $config_set{$2} = $1;
+	    $config_off{$2} = $1;
 	}
     }
     close(IN);
@@ -2701,6 +2824,8 @@ sub config_bisect {
     my %config_test;
     my $once = 0;
 
+    @config_off_tmp = ();
+
     # Sometimes kconfig does weird things. We must make sure
     # that the config we autocreate has everything we need
     # to test, otherwise we may miss testing configs, or
@@ -2719,6 +2844,18 @@ sub config_bisect {
 	}
     }
     my $ret;
+
+    if (defined($config_bisect_check) && $config_bisect_check) {
+	doprint " Checking to make sure bad config with min config fails\n";
+	create_config keys %config_list;
+	$ret = run_config_bisect_test $config_bisect_type;
+	if ($ret) {
+	    doprint " FAILED! Bad config with min config boots fine\n";
+	    return -1;
+	}
+	doprint " Bad config with min config fails as expected\n";
+    }
+
     do {
 	$ret = run_config_bisect;
     } while (!$ret);
@@ -3510,6 +3647,8 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 
     $iteration = $i;
 
+    undef %force_config;
+
     my $makecmd = set_test_option("MAKE_CMD", $i);
 
     # Load all the options into their mapped variable names
@@ -3519,6 +3658,18 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 
     $start_minconfig_defined = 1;
 
+    # The first test may override the PRE_KTEST option
+    if (defined($pre_ktest) && $i == 1) {
+	doprint "\n";
+	run_command $pre_ktest;
+    }
+
+    # Any test can override the POST_KTEST option
+    # The last test takes precedence.
+    if (defined($post_ktest)) {
+	$final_post_ktest = $post_ktest;
+    }
+
     if (!defined($start_minconfig)) {
 	$start_minconfig_defined = 0;
 	$start_minconfig = $minconfig;
@@ -3573,6 +3724,10 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
     doprint "\n\n";
     doprint "RUNNING TEST $i of $opt{NUM_TESTS} with option $test_type $run_type$installme\n\n";
 
+    if (defined($pre_test)) {
+	run_command $pre_test;
+    }
+
     unlink $dmesg;
     unlink $buildlog;
     unlink $testlog;
@@ -3638,6 +3793,10 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
     success $i;
 }
 
+if (defined($final_post_ktest)) {
+    run_command $final_post_ktest;
+}
+
 if ($opt{"POWEROFF_ON_SUCCESS"}) {
     halt;
 } elsif ($opt{"REBOOT_ON_SUCCESS"} && !do_not_reboot && $reboot_success) {
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index cf362b3d1ec..de28a0a3b8f 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -376,6 +376,24 @@
 # DEFAULTS
 # DEFAULTS SKIP
 
+# If you want to execute some command before the first test runs
+# you can set this option. Note, it can be set as a default option
+# or an option in the first test case. All other test cases will
+# ignore it. If both the default and first test have this option
+# set, then the first test will take precedence.
+#
+# default (undefined)
+#PRE_KTEST = ${SSH} ~/set_up_test
+
+# If you want to execute some command after all the tests have
+# completed, you can set this option. Note, it can be set as a
+# default or any test case can override it. If multiple test cases
+# set this option, then the last test case that set it will take
+# precedence
+#
+# default (undefined)
+#POST_KTEST = ${SSH} ~/dismantle_test
+
 # The default test type (default test)
 # The test types may be:
 #   build   - only build the kernel, do nothing else
@@ -408,6 +426,14 @@
 # (default "")
 #BUILD_OPTIONS = -j20
 
+# If you need to do some special handling before installing
+# you can add a script with this option.
+# The environment variable KERNEL_VERSION will be set to the
+# kernel version that is used.
+#
+# default (undefined)
+#PRE_INSTALL = ssh user@target rm -rf '/lib/modules/*-test*'
+
 # If you need an initrd, you can add a script or code here to install
 # it. The environment variable KERNEL_VERSION will be set to the
 # kernel version that is used. Remember to add the initrd line
@@ -426,6 +452,18 @@
 # (default 0)
 #NO_INSTALL = 1
 
+# If there is a command that you want to run before the individual test
+# case executes, then you can set this option
+#
+# default (undefined)
+#PRE_TEST = ${SSH} reboot_to_special_kernel
+
+# If there is a command you want to run after the individual test case
+# completes, then you can set this option.
+#
+# default (undefined)
+#POST_TEST = cd ${BUILD_DIR}; git reset --hard
+
 # If there is a script that you require to run before the build is done
 # you can specify it with PRE_BUILD.
 #
@@ -657,6 +695,14 @@
 # (default 60)
 #BISECT_SLEEP_TIME = 60
 
+# The max wait time (in seconds) for waiting for the console to finish.
+# If for some reason, the console is outputting content without
+# ever finishing, this will cause ktest to get stuck. This
+# option is the max time ktest will wait for the monitor (console)
+# to settle down before continuing.
+# (default 1800)
+#MAX_MONITOR_WAIT
+
 # The time in between patch checks to sleep (in seconds)
 # (default 60)
 #PATCHCHECK_SLEEP_TIME = 60
@@ -1039,6 +1085,12 @@
 #  can specify it with CONFIG_BISECT_GOOD. Otherwise
 #  the MIN_CONFIG is the base.
 #
+# CONFIG_BISECT_CHECK (optional)
+#  Set this to 1 if you want to confirm that the config ktest
+#  generates (the bad config with the min config) is still bad.
+#  It may be that the min config fixes what broke the bad config
+#  and the test will not return a result.
+#
 # Example:
 #   TEST_START
 #   TEST_TYPE = config_bisect
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index a4162e15c25..85baf11e2ac 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,4 +1,4 @@
-TARGETS = breakpoints kcmp mqueue vm
+TARGETS = breakpoints kcmp mqueue vm cpu-hotplug memory-hotplug
 
 all:
 	for TARGET in $(TARGETS); do \
diff --git a/tools/testing/selftests/cpu-hotplug/Makefile b/tools/testing/selftests/cpu-hotplug/Makefile
new file mode 100644
index 00000000000..7c9c20ff578
--- /dev/null
+++ b/tools/testing/selftests/cpu-hotplug/Makefile
@@ -0,0 +1,6 @@
+all:
+
+run_tests:
+	./on-off-test.sh
+
+clean:
diff --git a/tools/testing/selftests/cpu-hotplug/on-off-test.sh b/tools/testing/selftests/cpu-hotplug/on-off-test.sh
new file mode 100644
index 00000000000..bdde7cf428b
--- /dev/null
+++ b/tools/testing/selftests/cpu-hotplug/on-off-test.sh
@@ -0,0 +1,221 @@
+#!/bin/bash
+
+SYSFS=
+
+prerequisite()
+{
+	msg="skip all tests:"
+
+	if [ $UID != 0 ]; then
+		echo $msg must be run as root >&2
+		exit 0
+	fi
+
+	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
+
+	if [ ! -d "$SYSFS" ]; then
+		echo $msg sysfs is not mounted >&2
+		exit 0
+	fi
+
+	if ! ls $SYSFS/devices/system/cpu/cpu* > /dev/null 2>&1; then
+		echo $msg cpu hotplug is not supported >&2
+		exit 0
+	fi
+}
+
+#
+# list all hot-pluggable CPUs
+#
+hotpluggable_cpus()
+{
+	local state=${1:-.\*}
+
+	for cpu in $SYSFS/devices/system/cpu/cpu*; do
+		if [ -f $cpu/online ] && grep -q $state $cpu/online; then
+			echo ${cpu##/*/cpu}
+		fi
+	done
+}
+
+hotplaggable_offline_cpus()
+{
+	hotpluggable_cpus 0
+}
+
+hotpluggable_online_cpus()
+{
+	hotpluggable_cpus 1
+}
+
+cpu_is_online()
+{
+	grep -q 1 $SYSFS/devices/system/cpu/cpu$1/online
+}
+
+cpu_is_offline()
+{
+	grep -q 0 $SYSFS/devices/system/cpu/cpu$1/online
+}
+
+online_cpu()
+{
+	echo 1 > $SYSFS/devices/system/cpu/cpu$1/online
+}
+
+offline_cpu()
+{
+	echo 0 > $SYSFS/devices/system/cpu/cpu$1/online
+}
+
+online_cpu_expect_success()
+{
+	local cpu=$1
+
+	if ! online_cpu $cpu; then
+		echo $FUNCNAME $cpu: unexpected fail >&2
+	elif ! cpu_is_online $cpu; then
+		echo $FUNCNAME $cpu: unexpected offline >&2
+	fi
+}
+
+online_cpu_expect_fail()
+{
+	local cpu=$1
+
+	if online_cpu $cpu 2> /dev/null; then
+		echo $FUNCNAME $cpu: unexpected success >&2
+	elif ! cpu_is_offline $cpu; then
+		echo $FUNCNAME $cpu: unexpected online >&2
+	fi
+}
+
+offline_cpu_expect_success()
+{
+	local cpu=$1
+
+	if ! offline_cpu $cpu; then
+		echo $FUNCNAME $cpu: unexpected fail >&2
+	elif ! cpu_is_offline $cpu; then
+		echo $FUNCNAME $cpu: unexpected offline >&2
+	fi
+}
+
+offline_cpu_expect_fail()
+{
+	local cpu=$1
+
+	if offline_cpu $cpu 2> /dev/null; then
+		echo $FUNCNAME $cpu: unexpected success >&2
+	elif ! cpu_is_online $cpu; then
+		echo $FUNCNAME $cpu: unexpected offline >&2
+	fi
+}
+
+error=-12
+priority=0
+
+while getopts e:hp: opt; do
+	case $opt in
+	e)
+		error=$OPTARG
+		;;
+	h)
+		echo "Usage $0 [ -e errno ] [ -p notifier-priority ]"
+		exit
+		;;
+	p)
+		priority=$OPTARG
+		;;
+	esac
+done
+
+if ! [ "$error" -ge -4095 -a "$error" -lt 0 ]; then
+	echo "error code must be -4095 <= errno < 0" >&2
+	exit 1
+fi
+
+prerequisite
+
+#
+# Online all hot-pluggable CPUs
+#
+for cpu in `hotplaggable_offline_cpus`; do
+	online_cpu_expect_success $cpu
+done
+
+#
+# Offline all hot-pluggable CPUs
+#
+for cpu in `hotpluggable_online_cpus`; do
+	offline_cpu_expect_success $cpu
+done
+
+#
+# Online all hot-pluggable CPUs again
+#
+for cpu in `hotplaggable_offline_cpus`; do
+	online_cpu_expect_success $cpu
+done
+
+#
+# Test with cpu notifier error injection
+#
+
+DEBUGFS=`mount -t debugfs | head -1 | awk '{ print $3 }'`
+NOTIFIER_ERR_INJECT_DIR=$DEBUGFS/notifier-error-inject/cpu
+
+prerequisite_extra()
+{
+	msg="skip extra tests:"
+
+	/sbin/modprobe -q -r cpu-notifier-error-inject
+	/sbin/modprobe -q cpu-notifier-error-inject priority=$priority
+
+	if [ ! -d "$DEBUGFS" ]; then
+		echo $msg debugfs is not mounted >&2
+		exit 0
+	fi
+
+	if [ ! -d $NOTIFIER_ERR_INJECT_DIR ]; then
+		echo $msg cpu-notifier-error-inject module is not available >&2
+		exit 0
+	fi
+}
+
+prerequisite_extra
+
+#
+# Offline all hot-pluggable CPUs
+#
+echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/CPU_DOWN_PREPARE/error
+for cpu in `hotpluggable_online_cpus`; do
+	offline_cpu_expect_success $cpu
+done
+
+#
+# Test CPU hot-add error handling (offline => online)
+#
+echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/CPU_UP_PREPARE/error
+for cpu in `hotplaggable_offline_cpus`; do
+	online_cpu_expect_fail $cpu
+done
+
+#
+# Online all hot-pluggable CPUs
+#
+echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/CPU_UP_PREPARE/error
+for cpu in `hotplaggable_offline_cpus`; do
+	online_cpu_expect_success $cpu
+done
+
+#
+# Test CPU hot-remove error handling (online => offline)
+#
+echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/CPU_DOWN_PREPARE/error
+for cpu in `hotpluggable_online_cpus`; do
+	offline_cpu_expect_fail $cpu
+done
+
+echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/CPU_DOWN_PREPARE/error
+/sbin/modprobe -q -r cpu-notifier-error-inject
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
new file mode 100644
index 00000000000..7c9c20ff578
--- /dev/null
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -0,0 +1,6 @@
+all:
+
+run_tests:
+	./on-off-test.sh
+
+clean:
diff --git a/tools/testing/selftests/memory-hotplug/on-off-test.sh b/tools/testing/selftests/memory-hotplug/on-off-test.sh
new file mode 100644
index 00000000000..a2816f63154
--- /dev/null
+++ b/tools/testing/selftests/memory-hotplug/on-off-test.sh
@@ -0,0 +1,230 @@
+#!/bin/bash
+
+SYSFS=
+
+prerequisite()
+{
+	msg="skip all tests:"
+
+	if [ $UID != 0 ]; then
+		echo $msg must be run as root >&2
+		exit 0
+	fi
+
+	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
+
+	if [ ! -d "$SYSFS" ]; then
+		echo $msg sysfs is not mounted >&2
+		exit 0
+	fi
+
+	if ! ls $SYSFS/devices/system/memory/memory* > /dev/null 2>&1; then
+		echo $msg memory hotplug is not supported >&2
+		exit 0
+	fi
+}
+
+#
+# list all hot-pluggable memory
+#
+hotpluggable_memory()
+{
+	local state=${1:-.\*}
+
+	for memory in $SYSFS/devices/system/memory/memory*; do
+		if grep -q 1 $memory/removable &&
+		   grep -q $state $memory/state; then
+			echo ${memory##/*/memory}
+		fi
+	done
+}
+
+hotplaggable_offline_memory()
+{
+	hotpluggable_memory offline
+}
+
+hotpluggable_online_memory()
+{
+	hotpluggable_memory online
+}
+
+memory_is_online()
+{
+	grep -q online $SYSFS/devices/system/memory/memory$1/state
+}
+
+memory_is_offline()
+{
+	grep -q offline $SYSFS/devices/system/memory/memory$1/state
+}
+
+online_memory()
+{
+	echo online > $SYSFS/devices/system/memory/memory$1/state
+}
+
+offline_memory()
+{
+	echo offline > $SYSFS/devices/system/memory/memory$1/state
+}
+
+online_memory_expect_success()
+{
+	local memory=$1
+
+	if ! online_memory $memory; then
+		echo $FUNCNAME $memory: unexpected fail >&2
+	elif ! memory_is_online $memory; then
+		echo $FUNCNAME $memory: unexpected offline >&2
+	fi
+}
+
+online_memory_expect_fail()
+{
+	local memory=$1
+
+	if online_memory $memory 2> /dev/null; then
+		echo $FUNCNAME $memory: unexpected success >&2
+	elif ! memory_is_offline $memory; then
+		echo $FUNCNAME $memory: unexpected online >&2
+	fi
+}
+
+offline_memory_expect_success()
+{
+	local memory=$1
+
+	if ! offline_memory $memory; then
+		echo $FUNCNAME $memory: unexpected fail >&2
+	elif ! memory_is_offline $memory; then
+		echo $FUNCNAME $memory: unexpected offline >&2
+	fi
+}
+
+offline_memory_expect_fail()
+{
+	local memory=$1
+
+	if offline_memory $memory 2> /dev/null; then
+		echo $FUNCNAME $memory: unexpected success >&2
+	elif ! memory_is_online $memory; then
+		echo $FUNCNAME $memory: unexpected offline >&2
+	fi
+}
+
+error=-12
+priority=0
+ratio=10
+
+while getopts e:hp:r: opt; do
+	case $opt in
+	e)
+		error=$OPTARG
+		;;
+	h)
+		echo "Usage $0 [ -e errno ] [ -p notifier-priority ] [ -r percent-of-memory-to-offline ]"
+		exit
+		;;
+	p)
+		priority=$OPTARG
+		;;
+	r)
+		ratio=$OPTARG
+		;;
+	esac
+done
+
+if ! [ "$error" -ge -4095 -a "$error" -lt 0 ]; then
+	echo "error code must be -4095 <= errno < 0" >&2
+	exit 1
+fi
+
+prerequisite
+
+#
+# Online all hot-pluggable memory
+#
+for memory in `hotplaggable_offline_memory`; do
+	online_memory_expect_success $memory
+done
+
+#
+# Offline $ratio percent of hot-pluggable memory
+#
+for memory in `hotpluggable_online_memory`; do
+	if [ $((RANDOM % 100)) -lt $ratio ]; then
+		offline_memory_expect_success $memory
+	fi
+done
+
+#
+# Online all hot-pluggable memory again
+#
+for memory in `hotplaggable_offline_memory`; do
+	online_memory_expect_success $memory
+done
+
+#
+# Test with memory notifier error injection
+#
+
+DEBUGFS=`mount -t debugfs | head -1 | awk '{ print $3 }'`
+NOTIFIER_ERR_INJECT_DIR=$DEBUGFS/notifier-error-inject/memory
+
+prerequisite_extra()
+{
+	msg="skip extra tests:"
+
+	/sbin/modprobe -q -r memory-notifier-error-inject
+	/sbin/modprobe -q memory-notifier-error-inject priority=$priority
+
+	if [ ! -d "$DEBUGFS" ]; then
+		echo $msg debugfs is not mounted >&2
+		exit 0
+	fi
+
+	if [ ! -d $NOTIFIER_ERR_INJECT_DIR ]; then
+		echo $msg memory-notifier-error-inject module is not available >&2
+		exit 0
+	fi
+}
+
+prerequisite_extra
+
+#
+# Offline $ratio percent of hot-pluggable memory
+#
+echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
+for memory in `hotpluggable_online_memory`; do
+	if [ $((RANDOM % 100)) -lt $ratio ]; then
+		offline_memory_expect_success $memory
+	fi
+done
+
+#
+# Test memory hot-add error handling (offline => online)
+#
+echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_ONLINE/error
+for memory in `hotplaggable_offline_memory`; do
+	online_memory_expect_fail $memory
+done
+
+#
+# Online all hot-pluggable memory
+#
+echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_ONLINE/error
+for memory in `hotplaggable_offline_memory`; do
+	online_memory_expect_success $memory
+done
+
+#
+# Test memory hot-remove error handling (online => offline)
+#
+echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
+for memory in `hotpluggable_online_memory`; do
+	offline_memory_expect_fail $memory
+done
+
+echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
+/sbin/modprobe -q -r memory-notifier-error-inject
diff --git a/tools/usb/testusb.c b/tools/usb/testusb.c
index 82d7c590c02..b0adb2710c0 100644
--- a/tools/usb/testusb.c
+++ b/tools/usb/testusb.c
@@ -425,7 +425,7 @@ int main (int argc, char **argv)
 	/* for easy use when hotplugging */
 	device = getenv ("DEVICE");
 
-	while ((c = getopt (argc, argv, "D:aA:c:g:hns:t:v:")) != EOF)
+	while ((c = getopt (argc, argv, "D:aA:c:g:hlns:t:v:")) != EOF)
 	switch (c) {
 	case 'D':	/* device, if only one */
 		device = optarg;
@@ -468,10 +468,21 @@ int main (int argc, char **argv)
 	case 'h':
 	default:
 usage:
-		fprintf (stderr, "usage: %s [-n] [-D dev | -a | -A usbfs-dir]\n"
-			"\t[-c iterations]  [-t testnum]\n"
-			"\t[-s packetsize] [-g sglen] [-v vary]\n",
-			argv [0]);
+		fprintf (stderr,
+			"usage: %s [options]\n"
+			"Options:\n"
+			"\t-D dev		only test specific device\n"
+			"\t-A usbfs-dir\n"
+			"\t-a		test all recognized devices\n"
+			"\t-l		loop forever(for stress test)\n"
+			"\t-t testnum	only run specified case\n"
+			"\t-n		no test running, show devices to be tested\n"
+			"Case arguments:\n"
+			"\t-c iterations	default 1000\n"
+			"\t-s packetsize	default 512\n"
+			"\t-g sglen	default 32\n"
+			"\t-v vary		default 512\n",
+			argv[0]);
 		return 1;
 	}
 	if (optind != argc)
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 164cbcf6110..808d5a9d5dc 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -437,34 +437,34 @@ static void slab_stats(struct slabinfo *s)
 	printf("Fastpath             %8lu %8lu %3lu %3lu\n",
 		s->alloc_fastpath, s->free_fastpath,
 		s->alloc_fastpath * 100 / total_alloc,
-		s->free_fastpath * 100 / total_free);
+		total_free ? s->free_fastpath * 100 / total_free : 0);
 	printf("Slowpath             %8lu %8lu %3lu %3lu\n",
 		total_alloc - s->alloc_fastpath, s->free_slowpath,
 		(total_alloc - s->alloc_fastpath) * 100 / total_alloc,
-		s->free_slowpath * 100 / total_free);
+		total_free ? s->free_slowpath * 100 / total_free : 0);
 	printf("Page Alloc           %8lu %8lu %3lu %3lu\n",
 		s->alloc_slab, s->free_slab,
 		s->alloc_slab * 100 / total_alloc,
-		s->free_slab * 100 / total_free);
+		total_free ? s->free_slab * 100 / total_free : 0);
 	printf("Add partial          %8lu %8lu %3lu %3lu\n",
 		s->deactivate_to_head + s->deactivate_to_tail,
 		s->free_add_partial,
 		(s->deactivate_to_head + s->deactivate_to_tail) * 100 / total_alloc,
-		s->free_add_partial * 100 / total_free);
+		total_free ? s->free_add_partial * 100 / total_free : 0);
 	printf("Remove partial       %8lu %8lu %3lu %3lu\n",
 		s->alloc_from_partial, s->free_remove_partial,
 		s->alloc_from_partial * 100 / total_alloc,
-		s->free_remove_partial * 100 / total_free);
+		total_free ? s->free_remove_partial * 100 / total_free : 0);
 
 	printf("Cpu partial list     %8lu %8lu %3lu %3lu\n",
 		s->cpu_partial_alloc, s->cpu_partial_free,
 		s->cpu_partial_alloc * 100 / total_alloc,
-		s->cpu_partial_free * 100 / total_free);
+		total_free ? s->cpu_partial_free * 100 / total_free : 0);
 
 	printf("RemoteObj/SlabFrozen %8lu %8lu %3lu %3lu\n",
 		s->deactivate_remote_frees, s->free_frozen,
 		s->deactivate_remote_frees * 100 / total_alloc,
-		s->free_frozen * 100 / total_free);
+		total_free ? s->free_frozen * 100 / total_free : 0);
 
 	printf("Total                %8lu %8lu\n\n", total_alloc, total_free);