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

perf/core improvements and fixes:

 - Preparatory patches to use hw events in PMU syntax, from Jiri Olsa

 - Remaining backport of trace-cmd's libparseevent, from Namhyung Kim

 - Fix libtraceevent 'clean' make target, from Namhyung Kim

 - Teach ctags about libtraceevent error codes, from Namhyung Kim

 - Fix libtraceevent dependency files usage, from Namhyung Kim

 - Support hex number pretty printing in libtraceevent, fixing
   kvm output, from Namhyung Kim

 - Kill some die() usage in libtraceevent, from Namhyung Kim

 - Improve support for hw breakpoints parsing/pretty printing/testing,
  from Jiri Olsa

 - Clarify perf bench option naming, from Hitoshi Mitake

 - Look for ".note" ELF notes too, used in the kernel vdso, from Jiri Olsa

 - Fix internal PMU list usage, removing leak, from Robert Richter

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

17 files changed, 726 insertions, 314 deletions

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 3d69aa9..46c2f6b 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -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
@@ -270,11 +274,13 @@ endif
 
 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)				\
@@ -290,7 +296,7 @@ install_lib: all_cmd install_plugins install_python
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES).*.d
+	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
 	$(RM) tags TAGS
 
 endif # skip-makefile
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 5548282..5f34aa3 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 ac997bc..5772ad8 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 dfcfe2c1..ad178555 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 f3c716a..7065cd6 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -144,7 +144,7 @@ On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
 Repeat memcpy invocation this number of times.
 
 -c::
---clock::
+--cycle::
 Use perf's cpu-cycles event instead of gettimeofday syscall.
 
 -o::
@@ -176,7 +176,7 @@ On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
 Repeat memset invocation this number of times.
 
 -c::
---clock::
+--cycle::
 Use perf's cpu-cycles event instead of gettimeofday syscall.
 
 -o::
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index d990365..02dad5d 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -24,8 +24,8 @@
 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;
 
@@ -37,7 +37,7 @@ static const struct option options[] = {
 		    "Specify routine to copy"),
 	OPT_INTEGER('i', "iterations", &iterations,
 		    "repeat memcpy() invocation this number of times"),
-	OPT_BOOLEAN('c', "clock", &use_clock,
+	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()"),
@@ -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 bf0d5f55..350cc95 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -24,8 +24,8 @@
 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;
 
@@ -37,7 +37,7 @@ static const struct option options[] = {
 		    "Specify routine to set"),
 	OPT_INTEGER('i', "iterations", &iterations,
 		    "repeat memset() invocation this number of times"),
-	OPT_BOOLEAN('c', "clock", &use_clock,
+	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()"),
@@ -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/util/evsel.c b/tools/perf/util/evsel.c
index 3d1f696..e817713 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,7 @@
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.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))
@@ -152,6 +153,31 @@ static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
 	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;
+}
+
+static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+	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",		},
@@ -285,6 +311,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 		scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
 		break;
 
+	case PERF_TYPE_BREAKPOINT:
+		perf_evsel__bp_name(evsel, bf, sizeof(bf));
+		break;
+
 	default:
 		scnprintf(bf, sizeof(bf), "%s", "unknown attr type");
 		break;
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 1eb804f..b6842c1 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/parse-events-test.c b/tools/perf/util/parse-events-test.c
index a0f61a2..1b997d2 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -181,6 +181,22 @@ 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 +325,8 @@ 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 +340,8 @@ 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 +355,8 @@ 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 +370,27 @@ 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)
 {
 
@@ -585,10 +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",
@@ -600,9 +645,6 @@ 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;
@@ -718,21 +760,17 @@ int parse_events__test(void)
 {
 	int ret;
 
-	do {
-		ret = test_events(test__events, TEST__EVENTS_CNT);
-		if (ret)
-			break;
-
-		if (test_pmu()) {
-			ret = test_events(test__events_pmu,
-					  TEST__EVENTS_PMU_CNT);
-			if (ret)
-				break;
-		}
+#define TEST_EVENTS(tests)				\
+do {							\
+	ret = test_events(tests, ARRAY_SIZE(tests));	\
+	if (ret)					\
+		return ret;				\
+} while (0)
 
-		ret = test_terms(test__terms, TEST__TERMS_CNT);
+	TEST_EVENTS(test__events);
 
-	} while (0);
+	if (test_pmu())
+		TEST_EVENTS(test__events_pmu);
 
-	return ret;
+	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 0cc27da..1aa721d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -19,8 +19,6 @@
 #define MAX_NAME_LEN 100
 
 struct event_symbol {
-	u8		type;
-	u64		config;
 	const char	*symbol;
 	const char	*alias;
 };
@@ -30,30 +28,86 @@ extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
 
-#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",		""			},
+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) \
@@ -383,21 +437,31 @@ 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;
 
@@ -408,7 +472,6 @@ 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;
@@ -427,8 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
 
 	attr.type = PERF_TYPE_BREAKPOINT;
 
-	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,
@@ -816,16 +878,13 @@ 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);
@@ -837,6 +896,14 @@ 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;
@@ -864,26 +931,13 @@ 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) ||
@@ -894,17 +948,31 @@ 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)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 488362e..384ca74 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -56,7 +56,7 @@ static int sym(yyscan_t scanner, int type, int config)
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 
 	yylval->num = (type << 16) + config;
-	return PE_VALUE_SYM;
+	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
 static int term(yyscan_t scanner, int type)
@@ -76,7 +76,7 @@ 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}
 
 %%
 
@@ -152,6 +152,7 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 ,			{ return ','; }
 :			{ return ':'; }
 =			{ return '='; }
+\n			{ }
 
 <mem>{
 {modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9525c45..2bc5fbf 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -26,14 +26,15 @@ do { \
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
-%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%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
@@ -41,6 +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
@@ -109,8 +111,13 @@ PE_NAME '/' event_config '/'
 	$$ = 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;
@@ -123,7 +130,7 @@ PE_VALUE_SYM '/' event_config '/'
 	$$ = list;
 }
 |
-PE_VALUE_SYM sep_slash_dc
+value_sym sep_slash_dc
 {
 	struct parse_events_data__events *data = _data;
 	struct list_head *list = NULL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 74d0948e..67715a4 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;
@@ -252,6 +252,7 @@ static struct perf_pmu *pmu_lookup(char *name)
 	list_splice(&aliases, &pmu->aliases);
 	pmu->name = strdup(name);
 	pmu->type = type;
+	list_add_tail(&pmu->list, &pmus);
 	return pmu;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b3620fe..02dfa19 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:
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index a8ca2f8..ce4d1b0 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:
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 994f4ff..50958bb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1478,14 +1478,31 @@ 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)