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

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

  * Add new COMM infrastructure, further improving histogram processing, from
    Frédéric Weisbecker, one fix from Namhyung Kim.

  * Enhance option parse error message, showing just the help lines of the
    options affected, from Namhyung Kim.

  * Fixup PERF_SAMPLE_TRANSACTION handling in sample synthesizing and
    'perf test', from Adrian Hunter.

  * Set up output options for in-stream attributes, from Adrian Hunter.

  * Fix 32-bit cross build, from Adrian Hunter.

  * Fix libunwind build and feature detection for 32-bit build, from Adrian Hunter.

  * Always use perf_evsel__set_sample_bit to set sample_type, from Adrian Hunter.
    perf evlist: Add a debug print if event buffer mmap fails

  * Add missing data.h into LIB_H headers, fix from Jiri Olsa.

  * libtraceevent updates from upstream trace-cmd repo, from Steven Rostedt.

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

35 files changed, 722 insertions, 303 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index d1c2a6a4cd32..8f450adaa9c2 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -305,6 +305,11 @@ int pevent_register_comm(struct pevent *pevent, const char *comm, int pid)
 	return 0;
 }
 
+void pevent_register_trace_clock(struct pevent *pevent, char *trace_clock)
+{
+	pevent->trace_clock = trace_clock;
+}
+
 struct func_map {
 	unsigned long long		addr;
 	char				*func;
@@ -599,10 +604,11 @@ find_printk(struct pevent *pevent, unsigned long long addr)
  * This registers a string by the address it was stored in the kernel.
  * The @fmt passed in is duplicated.
  */
-int pevent_register_print_string(struct pevent *pevent, char *fmt,
+int pevent_register_print_string(struct pevent *pevent, const char *fmt,
 				 unsigned long long addr)
 {
 	struct printk_list *item = malloc(sizeof(*item));
+	char *p;
 
 	if (!item)
 		return -1;
@@ -610,10 +616,21 @@ int pevent_register_print_string(struct pevent *pevent, char *fmt,
 	item->next = pevent->printklist;
 	item->addr = addr;
 
+	/* Strip off quotes and '\n' from the end */
+	if (fmt[0] == '"')
+		fmt++;
 	item->printk = strdup(fmt);
 	if (!item->printk)
 		goto out_free;
 
+	p = item->printk + strlen(item->printk) - 1;
+	if (*p == '"')
+		*p = 0;
+
+	p -= 2;
+	if (strcmp(p, "\\n") == 0)
+		*p = 0;
+
 	pevent->printklist = item;
 	pevent->printk_count++;
 
@@ -3488,6 +3505,7 @@ 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;
+	struct printk_map *printk;
 	unsigned long long val, fval;
 	unsigned long addr;
 	char *str;
@@ -3523,7 +3541,12 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		if (!(field->flags & FIELD_IS_ARRAY) &&
 		    field->size == pevent->long_size) {
 			addr = *(unsigned long *)(data + field->offset);
-			trace_seq_printf(s, "%lx", addr);
+			/* Check if it matches a print format */
+			printk = find_printk(pevent, addr);
+			if (printk)
+				trace_seq_puts(s, printk->printk);
+			else
+				trace_seq_printf(s, "%lx", addr);
 			break;
 		}
 		str = malloc(len + 1);
@@ -3565,15 +3588,23 @@ 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)
-				goto out_warning_field;
-			arg->hex.field->field.field = field;
+		if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) {
+			unsigned long offset;
+			offset = pevent_read_number(pevent,
+				data + arg->hex.field->dynarray.field->offset,
+				arg->hex.field->dynarray.field->size);
+			hex = data + (offset & 0xffff);
+		} else {
+			field = arg->hex.field->field.field;
+			if (!field) {
+				str = arg->hex.field->field.name;
+				field = pevent_find_any_field(event, str);
+				if (!field)
+					goto out_warning_field;
+				arg->hex.field->field.field = field;
+			}
+			hex = data + field->offset;
 		}
-		hex = data + field->offset;
 		len = eval_num_arg(data, size, event, arg->hex.size);
 		for (i = 0; i < len; i++) {
 			if (i)
@@ -3771,8 +3802,8 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 	if (asprintf(&arg->atom.atom, "%lld", ip) < 0)
 		goto out_free;
 
-	/* skip the first "%pf : " */
-	for (ptr = fmt + 6, bptr = data + field->offset;
+	/* skip the first "%pf: " */
+	for (ptr = fmt + 5, bptr = data + field->offset;
 	     bptr < data + size && *ptr; ptr++) {
 		int ls = 0;
 
@@ -3882,7 +3913,6 @@ get_bprint_format(void *data, int size __maybe_unused,
 	struct format_field *field;
 	struct printk_map *printk;
 	char *format;
-	char *p;
 
 	field = pevent->bprint_fmt_field;
 
@@ -3899,25 +3929,13 @@ get_bprint_format(void *data, int size __maybe_unused,
 
 	printk = find_printk(pevent, addr);
 	if (!printk) {
-		if (asprintf(&format, "%%pf : (NO FORMAT FOUND at %llx)\n", addr) < 0)
+		if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
 			return NULL;
 		return format;
 	}
 
-	p = printk->printk;
-	/* Remove any quotes. */
-	if (*p == '"')
-		p++;
-	if (asprintf(&format, "%s : %s", "%pf", p) < 0)
+	if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0)
 		return NULL;
-	/* remove ending quotes and new line since we will add one too */
-	p = format + strlen(format) - 1;
-	if (*p == '"')
-		*p = 0;
-
-	p -= 2;
-	if (strcmp(p, "\\n") == 0)
-		*p = 0;
 
 	return format;
 }
@@ -3963,7 +3981,7 @@ 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]))
+		if (!isprint(p[i]) && !isspace(p[i]))
 		    return 0;
 	return 1;
 }
@@ -4428,11 +4446,11 @@ void pevent_event_info(struct trace_seq *s, struct event_format *event,
 {
 	int print_pretty = 1;
 
-	if (event->pevent->print_raw)
+	if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW))
 		print_event_fields(s, record->data, record->size, event);
 	else {
 
-		if (event->handler)
+		if (event->handler && !(event->flags & EVENT_FL_NOHANDLE))
 			print_pretty = event->handler(s, record, event,
 						      event->context);
 
@@ -4443,8 +4461,21 @@ void pevent_event_info(struct trace_seq *s, struct event_format *event,
 	trace_seq_terminate(s);
 }
 
+static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
+{
+	if (!use_trace_clock)
+		return true;
+
+	if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
+	    || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf"))
+		return true;
+
+	/* trace_clock is setting in tsc or counter mode */
+	return false;
+}
+
 void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
-			struct pevent_record *record)
+			struct pevent_record *record, bool use_trace_clock)
 {
 	static const char *spaces = "                    "; /* 20 spaces */
 	struct event_format *event;
@@ -4457,9 +4488,14 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 	int pid;
 	int len;
 	int p;
+	bool use_usec_format;
 
-	secs = record->ts / NSECS_PER_SEC;
-	nsecs = record->ts - secs * NSECS_PER_SEC;
+	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
+							use_trace_clock);
+	if (use_usec_format) {
+		secs = record->ts / NSECS_PER_SEC;
+		nsecs = record->ts - secs * NSECS_PER_SEC;
+	}
 
 	if (record->size < 0) {
 		do_warning("ug! negative record size %d", record->size);
@@ -4484,15 +4520,20 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 	} else
 		trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
 
-	if (pevent->flags & PEVENT_NSEC_OUTPUT) {
-		usecs = nsecs;
-		p = 9;
-	} else {
-		usecs = (nsecs + 500) / NSECS_PER_USEC;
-		p = 6;
-	}
+	if (use_usec_format) {
+		if (pevent->flags & PEVENT_NSEC_OUTPUT) {
+			usecs = nsecs;
+			p = 9;
+		} else {
+			usecs = (nsecs + 500) / NSECS_PER_USEC;
+			p = 6;
+		}
 
-	trace_seq_printf(s, " %5lu.%0*lu: %s: ", secs, p, usecs, event->name);
+		trace_seq_printf(s, " %5lu.%0*lu: %s: ",
+					secs, p, usecs, event->name);
+	} else
+		trace_seq_printf(s, " %12llu: %s: ",
+					record->ts, event->name);
 
 	/* Space out the event names evenly. */
 	len = strlen(event->name);
@@ -5326,6 +5367,48 @@ int pevent_print_num_field(struct trace_seq *s, const char *fmt,
 	return -1;
 }
 
+/**
+ * pevent_print_func_field - print a field and a format for function pointers
+ * @s: The seq to print to
+ * @fmt: The printf format to print the field with.
+ * @event: the event that the field is for
+ * @name: The name of the field
+ * @record: The record with the field name.
+ * @err: print default error if failed.
+ *
+ * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ */
+int pevent_print_func_field(struct trace_seq *s, const char *fmt,
+			    struct event_format *event, const char *name,
+			    struct pevent_record *record, int err)
+{
+	struct format_field *field = pevent_find_field(event, name);
+	struct pevent *pevent = event->pevent;
+	unsigned long long val;
+	struct func_map *func;
+	char tmp[128];
+
+	if (!field)
+		goto failed;
+
+	if (pevent_read_number_field(field, record->data, &val))
+		goto failed;
+
+	func = find_func(pevent, val);
+
+	if (func)
+		snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val);
+	else
+		sprintf(tmp, "0x%08llx", val);
+
+	return trace_seq_printf(s, fmt, tmp);
+
+ failed:
+	if (err)
+		trace_seq_printf(s, "CAN'T FIND FIELD \"%s\"", name);
+	return -1;
+}
+
 static void free_func_handle(struct pevent_function_handler *func)
 {
 	struct pevent_func_params *params;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index c37b2026d04a..8d73d2594f65 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -20,6 +20,7 @@
 #ifndef _PARSE_EVENTS_H
 #define _PARSE_EVENTS_H
 
+#include <stdbool.h>
 #include <stdarg.h>
 #include <regex.h>
 
@@ -307,6 +308,8 @@ enum {
 	EVENT_FL_ISBPRINT	= 0x04,
 	EVENT_FL_ISFUNCENT	= 0x10,
 	EVENT_FL_ISFUNCRET	= 0x20,
+	EVENT_FL_NOHANDLE	= 0x40,
+	EVENT_FL_PRINTRAW	= 0x80,
 
 	EVENT_FL_FAILED		= 0x80000000
 };
@@ -450,6 +453,8 @@ struct pevent {
 
 	/* cache */
 	struct event_format *last_event;
+
+	char *trace_clock;
 };
 
 static inline void pevent_set_flag(struct pevent *pevent, int flag)
@@ -527,14 +532,15 @@ enum trace_flag_type {
 };
 
 int pevent_register_comm(struct pevent *pevent, const char *comm, int pid);
+void pevent_register_trace_clock(struct pevent *pevent, char *trace_clock);
 int pevent_register_function(struct pevent *pevent, char *name,
 			     unsigned long long addr, char *mod);
-int pevent_register_print_string(struct pevent *pevent, char *fmt,
+int pevent_register_print_string(struct pevent *pevent, const char *fmt,
 				 unsigned long long addr);
 int pevent_pid_is_registered(struct pevent *pevent, int pid);
 
 void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
-			struct pevent_record *record);
+			struct pevent_record *record, bool use_trace_clock);
 
 int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long size,
 			     int long_size);
@@ -563,6 +569,10 @@ int pevent_print_num_field(struct trace_seq *s, const char *fmt,
 			   struct event_format *event, const char *name,
 			   struct pevent_record *record, int err);
 
+int pevent_print_func_field(struct trace_seq *s, const char *fmt,
+			   struct event_format *event, const char *name,
+			   struct pevent_record *record, int err);
+
 int pevent_register_event_handler(struct pevent *pevent, int id,
 				  const char *sys_name, const char *event_name,
 				  pevent_event_handler_func func, void *context);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8a9ca3836043..5b8639025aae 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -273,6 +273,7 @@ LIB_H += util/color.h
 LIB_H += util/values.h
 LIB_H += util/sort.h
 LIB_H += util/hist.h
+LIB_H += util/comm.h
 LIB_H += util/thread.h
 LIB_H += util/thread_map.h
 LIB_H += util/trace-event.h
@@ -295,6 +296,7 @@ LIB_H += ui/helpline.h
 LIB_H += ui/progress.h
 LIB_H += ui/util.h
 LIB_H += ui/ui.h
+LIB_H += util/data.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -340,6 +342,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o
 LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/comm.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
 LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
@@ -708,7 +711,7 @@ $(LIB_FILE): $(LIB_OBJS)
 TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch])
 
 $(LIBTRACEEVENT): $(TE_SOURCES)
-	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libtraceevent.a
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) CFLAGS="-g -Wall $(EXTRA_CFLAGS)" libtraceevent.a
 
 $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 1126382659a9..a28970f7ddfb 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -315,7 +315,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
+	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 
 	if (evsel->handler.func != NULL) {
 		tracepoint_handler f = evsel->handler.func;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 33c7253295b9..35f9aaa565cc 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -767,7 +767,7 @@ static void dump_threads(void)
 	while (node) {
 		st = container_of(node, struct thread_stat, rb);
 		t = perf_session__findnew(session, st->tid);
-		pr_info("%10d: %s\n", st->tid, t->comm);
+		pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
 		node = rb_next(node);
 	};
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 98d3891392e2..25f83d5d66fd 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -905,13 +905,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			input_name = "perf.data";
 	}
 
-	if (strcmp(input_name, "-") != 0)
-		setup_browser(true);
-	else {
-		use_browser = 0;
-		perf_hpp__init();
-	}
-
 	file.path  = input_name;
 	file.force = report.force;
 
@@ -954,8 +947,22 @@ repeat:
 			sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
 	}
 
-	if (setup_sorting() < 0)
-		usage_with_options(report_usage, options);
+	if (setup_sorting() < 0) {
+		parse_options_usage(report_usage, options, "s", 1);
+		goto error;
+	}
+
+	if (parent_pattern != default_parent_pattern) {
+		if (sort_dimension__add("parent") < 0)
+			goto error;
+	}
+
+	if (strcmp(input_name, "-") != 0)
+		setup_browser(true);
+	else {
+		use_browser = 0;
+		perf_hpp__init();
+	}
 
 	/*
 	 * Only in the TUI browser we are doing integrated annotation,
@@ -986,11 +993,6 @@ repeat:
 	if (symbol__init() < 0)
 		goto error;
 
-	if (parent_pattern != default_parent_pattern) {
-		if (sort_dimension__add("parent") < 0)
-			goto error;
-	}
-
 	if (argc) {
 		/*
 		 * Special case: if there's an argument left then assume that
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index ddb5dc15be17..a81ab1828aa5 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -737,12 +737,12 @@ static int replay_fork_event(struct perf_sched *sched,
 
 	if (verbose) {
 		printf("fork event\n");
-		printf("... parent: %s/%d\n", parent->comm, parent->tid);
-		printf("...  child: %s/%d\n", child->comm, child->tid);
+		printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
+		printf("...  child: %s/%d\n", thread__comm_str(child), child->tid);
 	}
 
-	register_pid(sched, parent->tid, parent->comm);
-	register_pid(sched, child->tid, child->comm);
+	register_pid(sched, parent->tid, thread__comm_str(parent));
+	register_pid(sched, child->tid, thread__comm_str(child));
 	return 0;
 }
 
@@ -1077,7 +1077,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
 			return -1;
-		register_pid(sched, migrant->tid, migrant->comm);
+		register_pid(sched, migrant->tid, thread__comm_str(migrant));
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("migration-event: Internal tree error");
@@ -1111,13 +1111,13 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	/*
 	 * Ignore idle threads:
 	 */
-	if (!strcmp(work_list->thread->comm, "swapper"))
+	if (!strcmp(thread__comm_str(work_list->thread), "swapper"))
 		return;
 
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->tid);
+	ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1334,7 +1334,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	printf("  %12.6f secs ", (double)timestamp/1e9);
 	if (new_shortname) {
 		printf("%s => %s:%d\n",
-			sched_in->shortname, sched_in->comm, sched_in->tid);
+		       sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
 	} else {
 		printf("\n");
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 0ae88c2538a1..baf17989a216 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -229,6 +229,24 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	return 0;
 }
 
+static void set_print_ip_opts(struct perf_event_attr *attr)
+{
+	unsigned int type = attr->type;
+
+	output[type].print_ip_opts = 0;
+	if (PRINT_FIELD(IP))
+		output[type].print_ip_opts |= PRINT_IP_OPT_IP;
+
+	if (PRINT_FIELD(SYM))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SYM;
+
+	if (PRINT_FIELD(DSO))
+		output[type].print_ip_opts |= PRINT_IP_OPT_DSO;
+
+	if (PRINT_FIELD(SYMOFFSET))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+}
+
 /*
  * verify all user requested events exist and the samples
  * have the expected data
@@ -237,7 +255,6 @@ static int perf_session__check_output_opt(struct perf_session *session)
 {
 	int j;
 	struct perf_evsel *evsel;
-	struct perf_event_attr *attr;
 
 	for (j = 0; j < PERF_TYPE_MAX; ++j) {
 		evsel = perf_session__find_first_evtype(session, j);
@@ -260,20 +277,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		if (evsel == NULL)
 			continue;
 
-		attr = &evsel->attr;
-
-		output[j].print_ip_opts = 0;
-		if (PRINT_FIELD(IP))
-			output[j].print_ip_opts |= PRINT_IP_OPT_IP;
-
-		if (PRINT_FIELD(SYM))
-			output[j].print_ip_opts |= PRINT_IP_OPT_SYM;
-
-		if (PRINT_FIELD(DSO))
-			output[j].print_ip_opts |= PRINT_IP_OPT_DSO;
-
-		if (PRINT_FIELD(SYMOFFSET))
-			output[j].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+		set_print_ip_opts(&evsel->attr);
 	}
 
 	return 0;
@@ -291,11 +295,11 @@ static void print_sample_start(struct perf_sample *sample,
 
 	if (PRINT_FIELD(COMM)) {
 		if (latency_format)
-			printf("%8.8s ", thread->comm);
+			printf("%8.8s ", thread__comm_str(thread));
 		else if (PRINT_FIELD(IP) && symbol_conf.use_callchain)
-			printf("%s ", thread->comm);
+			printf("%s ", thread__comm_str(thread));
 		else
-			printf("%16s ", thread->comm);
+			printf("%16s ", thread__comm_str(thread));
 	}
 
 	if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
@@ -547,6 +551,34 @@ struct perf_script {
 	struct perf_session	*session;
 };
 
+static int process_attr(struct perf_tool *tool, union perf_event *event,
+			struct perf_evlist **pevlist)
+{
+	struct perf_script *scr = container_of(tool, struct perf_script, tool);
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel, *pos;
+	int err;
+
+	err = perf_event__process_attr(tool, event, pevlist);
+	if (err)
+		return err;
+
+	evlist = *pevlist;
+	evsel = perf_evlist__last(*pevlist);
+
+	if (evsel->attr.type >= PERF_TYPE_MAX)
+		return 0;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (pos->attr.type == evsel->attr.type && pos != evsel)
+			return 0;
+	}
+
+	set_print_ip_opts(&evsel->attr);
+
+	return perf_evsel__check_attr(evsel, scr->session);
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -1272,7 +1304,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm		 = perf_event__process_comm,
 			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
-			.attr		 = perf_event__process_attr,
+			.attr		 = process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
 			.ordered_samples = true,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1a9c95d270aa..0fc1c941a73c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1596,7 +1596,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf stat [<options>] [<command>]",
 		NULL
 	};
-	int status = -ENOMEM, run_idx;
+	int status = -EINVAL, run_idx;
 	const char *mode;
 
 	setlocale(LC_ALL, "");
@@ -1614,12 +1614,15 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (output_name && output_fd) {
 		fprintf(stderr, "cannot use both --output and --log-fd\n");
-		usage_with_options(stat_usage, options);
+		parse_options_usage(stat_usage, options, "o", 1);
+		parse_options_usage(NULL, options, "log-fd", 0);
+		goto out;
 	}
 
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
-		usage_with_options(stat_usage, options);
+		parse_options_usage(stat_usage, options, "log-fd", 0);
+		goto out;
 	}
 
 	if (!output) {
@@ -1656,7 +1659,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
-			usage_with_options(stat_usage, options);
+			parse_options_usage(stat_usage, options, "B", 1);
+			parse_options_usage(NULL, options, "x", 1);
+			goto out;
 		} else /* Nope, so disable big number formatting */
 			big_num = false;
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
@@ -1666,7 +1671,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(stat_usage, options);
 
 	if (run_count < 0) {
-		usage_with_options(stat_usage, options);
+		pr_err("Run count must be a positive number\n");
+		parse_options_usage(stat_usage, options, "r", 1);
+		goto out;
 	} else if (run_count == 0) {
 		forever = true;
 		run_count = 1;
@@ -1678,8 +1685,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
 
-		usage_with_options(stat_usage, options);
-		return -1;
+		parse_options_usage(stat_usage, options, "G", 1);
+		parse_options_usage(NULL, options, "A", 1);
+		parse_options_usage(NULL, options, "a", 1);
+		goto out;
 	}
 
 	if (add_default_attributes())
@@ -1688,25 +1697,28 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	perf_target__validate(&target);
 
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
-		if (perf_target__has_task(&target))
+		if (perf_target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
-		if (perf_target__has_cpu(&target))
+			parse_options_usage(stat_usage, options, "p", 1);
+			parse_options_usage(NULL, options, "t", 1);
+		} else if (perf_target__has_cpu(&target)) {
 			perror("failed to parse CPUs map");
-
-		usage_with_options(stat_usage, options);
-		return -1;
+			parse_options_usage(stat_usage, options, "C", 1);
+			parse_options_usage(NULL, options, "a", 1);
+		}
+		goto out;
 	}
 	if (interval && interval < 100) {
 		pr_err("print interval must be >= 100ms\n");
-		usage_with_options(stat_usage, options);
-		return -1;
+		parse_options_usage(stat_usage, options, "I", 1);
+		goto out_free_maps;
 	}
 
 	if (perf_evlist__alloc_stats(evsel_list, interval))
 		goto out_free_maps;
 
 	if (perf_stat_init_aggr_mode())
-		goto out;
+		goto out_free_maps;
 
 	/*
 	 * We dont want to block the signals - that would cause
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a6ea956a533e..ca5ca37980fb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -856,7 +856,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 						   &sample, machine);
 		} else if (event->header.type < PERF_RECORD_MAX) {
 			hists__inc_nr_events(&evsel->hists, event->header.type);
-			machine__process_event(machine, event);
+			machine__process_event(machine, event, &sample);
 		} else
 			++session->stats.nr_unknown_events;
 next_event:
@@ -1040,7 +1040,7 @@ parse_percent_limit(const struct option *opt, const char *arg,
 
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	int status;
+	int status = -1;
 	char errbuf[BUFSIZ];
 	struct perf_top top = {
 		.count_filter	     = 5,
@@ -1159,8 +1159,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (sort_order == default_sort_order)
 		sort_order = "dso,symbol";
 
-	if (setup_sorting() < 0)
-		usage_with_options(top_usage, options);
+	if (setup_sorting() < 0) {
+		parse_options_usage(top_usage, options, "s", 1);
+		goto out_delete_evlist;
+	}
 
 	/* display thread wants entries to be collapsed in a different tree */
 	sort__need_collapse = 1;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dc3da654ff12..b3e57dc64546 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1114,7 +1114,7 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 
 	if (trace->multiple_threads) {
 		if (trace->show_comm)
-			printed += fprintf(fp, "%.14s/", thread->comm);
+			printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
 		printed += fprintf(fp, "%d ", thread->tid);
 	}
 
@@ -1122,7 +1122,7 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 }
 
 static int trace__process_event(struct trace *trace, struct machine *machine,
-				union perf_event *event)
+				union perf_event *event, struct perf_sample *sample)
 {
 	int ret = 0;
 
@@ -1130,9 +1130,9 @@ static int trace__process_event(struct trace *trace, struct machine *machine,
 	case PERF_RECORD_LOST:
 		color_fprintf(trace->output, PERF_COLOR_RED,
 			      "LOST %" PRIu64 " events!\n", event->lost.lost);
-		ret = machine__process_lost_event(machine, event);
+		ret = machine__process_lost_event(machine, event, sample);
 	default:
-		ret = machine__process_event(machine, event);
+		ret = machine__process_event(machine, event, sample);
 		break;
 	}
 
@@ -1141,11 +1141,11 @@ static int trace__process_event(struct trace *trace, struct machine *machine,
 
 static int trace__tool_process(struct perf_tool *tool,
 			       union perf_event *event,
-			       struct perf_sample *sample __maybe_unused,
+			       struct perf_sample *sample,
 			       struct machine *machine)
 {
 	struct trace *trace = container_of(tool, struct trace, tool);
-	return trace__process_event(trace, machine, event);
+	return trace__process_event(trace, machine, event, sample);
 }
 
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
@@ -1751,7 +1751,7 @@ again:
 				trace->base_time = sample.time;
 
 			if (type != PERF_RECORD_SAMPLE) {
-				trace__process_event(trace, trace->host, event);
+				trace__process_event(trace, trace->host, event, &sample);
 				continue;
 			}
 
@@ -1986,7 +1986,7 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	else if (ratio > 5.0)
 		color = PERF_COLOR_YELLOW;
 
-	printed += color_fprintf(fp, color, "%20s", thread->comm);
+	printed += color_fprintf(fp, color, "%20s", thread__comm_str(thread));
 	printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
 	printed += color_fprintf(fp, color, "%5.1f%%", ratio);
 	printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 543aa953bab1..ffb5f55c8fba 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -25,9 +25,11 @@ ifeq ($(ARCH),x86_64)
     RAW_ARCH := x86_64
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
+    LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
+  else
+    LIBUNWIND_LIBS = -lunwind -lunwind-x86
   endif
   NO_PERF_REGS := 0
-  LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
 endif
 
 ifeq ($(NO_PERF_REGS),0)
@@ -96,7 +98,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) LDFLAGS=$(LDFLAGS) -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -173,7 +175,7 @@ ifeq ($(feature-all), 1)
   #
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat)))
 else
-  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(CORE_FEATURE_TESTS) >/dev/null 2>&1)
+  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(CORE_FEATURE_TESTS) >/dev/null 2>&1)
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
 
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 452b67cc4d7b..d37d58d273fe 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -31,12 +31,12 @@ CC := $(CC) -MD
 
 all: $(FILES)
 
-BUILD = $(CC) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
+BUILD = $(CC) $(CFLAGS) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
 
 ###############################
 
 test-all:
-	$(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lunwind -lunwind-x86_64 -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
 test-hello:
 	$(BUILD)
@@ -72,7 +72,7 @@ test-libnuma:
 	$(BUILD) -lnuma
 
 test-libunwind:
-	$(BUILD) -lunwind -lunwind-x86_64 -lelf
+	$(BUILD) $(LIBUNWIND_LIBS) -lelf
 
 test-libaudit:
 	$(BUILD) -laudit
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index e3fedfa2906e..49ccc3b2995e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -276,7 +276,7 @@ static int process_event(struct machine *machine, struct perf_evlist *evlist,
 		return process_sample_event(machine, evlist, event, state);
 
 	if (event->header.type < PERF_RECORD_MAX)
-		return machine__process_event(machine, event);
+		return machine__process_event(machine, event, NULL);
 
 	return 0;
 }
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index b51abcb2c243..6c337e653540 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -93,7 +93,7 @@ static struct machine *setup_fake_machine(struct machines *machines)
 		if (thread == NULL)
 			goto out;
 
-		thread__set_comm(thread, fake_threads[i].comm);
+		thread__set_comm(thread, fake_threads[i].comm, 0);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
@@ -110,7 +110,7 @@ static struct machine *setup_fake_machine(struct machines *machines)
 		strcpy(fake_mmap_event.mmap.filename,
 		       fake_mmap_info[i].filename);
 
-		machine__process_mmap_event(machine, &fake_mmap_event);
+		machine__process_mmap_event(machine, &fake_mmap_event, NULL);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
@@ -421,7 +421,7 @@ static void print_hists(struct hists *hists)
 		he = rb_entry(node, struct hist_entry, rb_node_in);
 
 		pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n",
-			i, he->thread->comm, he->ms.map->dso->short_name,
+			i, thread__comm_str(he->thread), he->ms.map->dso->short_name,
 			he->ms.sym->name, he->stat.period);
 
 		i++;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 61c9da2eb3a9..1b677202638d 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -121,6 +121,9 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_DATA_SRC)
 		COMP(data_src);
 
+	if (type & PERF_SAMPLE_TRANSACTION)
+		COMP(transaction);
+
 	return true;
 }
 
@@ -165,6 +168,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		.cpu		= 110,
 		.raw_size	= sizeof(raw_data),
 		.data_src	= 111,
+		.transaction	= 112,
 		.raw_data	= (void *)raw_data,
 		.callchain	= &callchain.callchain,
 		.branch_stack	= &branch_stack.branch_stack,
@@ -273,7 +277,8 @@ int test__sample_parsing(void)
 
 	/*
 	 * Fail the test if it has not been updated when new sample format bits
-	 * were added.
+	 * were added.  Please actually update the test rather than just change
+	 * the condition below.
 	 */
 	if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7ef36c360471..a91b6b219412 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1255,7 +1255,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 	if (thread)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
-				    (thread->comm_set ? thread->comm : ""),
+				     (thread->comm_set ? thread__comm_str(thread) : ""),
 				    thread->tid);
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
@@ -1578,7 +1578,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		if (thread != NULL &&
 		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
 			     (browser->hists->thread_filter ? "out of" : "into"),
-			     (thread->comm_set ? thread->comm : ""),
+			     (thread->comm_set ? thread__comm_str(thread) : ""),
 			     thread->tid) > 0)
 			zoom_thread = nr_options++;
 
@@ -1598,7 +1598,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			struct symbol *sym;
 
 			if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]",
-				browser->he_selection->thread->comm) > 0)
+				     thread__comm_str(browser->he_selection->thread)) > 0)
 				scripts_comm = nr_options++;
 
 			sym = browser->he_selection->ms.sym;
@@ -1701,7 +1701,7 @@ zoom_out_thread:
 				sort_thread.elide = false;
 			} else {
 				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
-						   thread->comm_set ? thread->comm : "",
+						   thread->comm_set ? thread__comm_str(thread) : "",
 						   thread->tid);
 				browser->hists->thread_filter = thread;
 				sort_thread.elide = true;
@@ -1717,7 +1717,7 @@ do_scripts:
 			memset(script_opt, 0, 64);
 
 			if (choice == scripts_comm)
-				sprintf(script_opt, " -c %s ", browser->he_selection->thread->comm);
+				sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread));
 
 			if (choice == scripts_symbol)
 				sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name);
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
new file mode 100644
index 000000000000..ee0df0e24cdb
--- /dev/null
+++ b/tools/perf/util/comm.c
@@ -0,0 +1,121 @@
+#include "comm.h"
+#include "util.h"
+#include <stdlib.h>
+#include <stdio.h>
+
+struct comm_str {
+	char *str;
+	struct rb_node rb_node;
+	int ref;
+};
+
+/* Should perhaps be moved to struct machine */
+static struct rb_root comm_str_root;
+
+static void comm_str__get(struct comm_str *cs)
+{
+	cs->ref++;
+}
+
+static void comm_str__put(struct comm_str *cs)
+{
+	if (!--cs->ref) {
+		rb_erase(&cs->rb_node, &comm_str_root);
+		free(cs->str);
+		free(cs);
+	}
+}
+
+static struct comm_str *comm_str__alloc(const char *str)
+{
+	struct comm_str *cs;
+
+	cs = zalloc(sizeof(*cs));
+	if (!cs)
+		return NULL;
+
+	cs->str = strdup(str);
+	if (!cs->str) {
+		free(cs);
+		return NULL;
+	}
+
+	return cs;
+}
+
+static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct comm_str *iter, *new;
+	int cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct comm_str, rb_node);
+
+		cmp = strcmp(str, iter->str);
+		if (!cmp)
+			return iter;
+
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	new = comm_str__alloc(str);
+	if (!new)
+		return NULL;
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+
+	return new;
+}
+
+struct comm *comm__new(const char *str, u64 timestamp)
+{
+	struct comm *comm = zalloc(sizeof(*comm));
+
+	if (!comm)
+		return NULL;
+
+	comm->start = timestamp;
+
+	comm->comm_str = comm_str__findnew(str, &comm_str_root);
+	if (!comm->comm_str) {
+		free(comm);
+		return NULL;
+	}
+
+	comm_str__get(comm->comm_str);
+
+	return comm;
+}
+
+void comm__override(struct comm *comm, const char *str, u64 timestamp)
+{
+	struct comm_str *old = comm->comm_str;
+
+	comm->comm_str = comm_str__findnew(str, &comm_str_root);
+	if (!comm->comm_str) {
+		comm->comm_str = old;
+		return;
+	}
+
+	comm->start = timestamp;
+	comm_str__get(comm->comm_str);
+	comm_str__put(old);
+}
+
+void comm__free(struct comm *comm)
+{
+	comm_str__put(comm->comm_str);
+	free(comm);
+}
+
+const char *comm__str(const struct comm *comm)
+{
+	return comm->comm_str->str;
+}
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
new file mode 100644
index 000000000000..7a86e5656710
--- /dev/null
+++ b/tools/perf/util/comm.h
@@ -0,0 +1,21 @@
+#ifndef __PERF_COMM_H
+#define __PERF_COMM_H
+
+#include "../perf.h"
+#include <linux/rbtree.h>
+#include <linux/list.h>
+
+struct comm_str;
+
+struct comm {
+	struct comm_str *comm_str;
+	u64 start;
+	struct list_head list;
+};
+
+void comm__free(struct comm *comm);
+struct comm *comm__new(const char *str, u64 timestamp);
+const char *comm__str(const struct comm *comm);
+void comm__override(struct comm *comm, const char *str, u64 timestamp);
+
+#endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 49096ea58a15..c26b3539187b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -512,18 +512,18 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __maybe_unused,
+			     struct perf_sample *sample,
 			     struct machine *machine)
 {
-	return machine__process_comm_event(machine, event);
+	return machine__process_comm_event(machine, event, sample);
 }
 
 int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __maybe_unused,
+			     struct perf_sample *sample,
 			     struct machine *machine)
 {
-	return machine__process_lost_event(machine, event);
+	return machine__process_lost_event(machine, event, sample);
 }
 
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
@@ -546,18 +546,18 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __maybe_unused,
+			     struct perf_sample *sample,
 			     struct machine *machine)
 {
-	return machine__process_mmap_event(machine, event);
+	return machine__process_mmap_event(machine, event, sample);
 }
 
 int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __maybe_unused,
+			     struct perf_sample *sample,
 			     struct machine *machine)
 {
-	return machine__process_mmap2_event(machine, event);
+	return machine__process_mmap2_event(machine, event, sample);
 }
 
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
@@ -569,18 +569,18 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
 
 int perf_event__process_fork(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __maybe_unused,
+			     struct perf_sample *sample,
 			     struct machine *machine)
 {
-	return machine__process_fork_event(machine, event);
+	return machine__process_fork_event(machine, event, sample);
 }
 
 int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_sample *sample __maybe_unused,
+			     struct perf_sample *sample,
 			     struct machine *machine)
 {
-	return machine__process_exit_event(machine, event);
+	return machine__process_exit_event(machine, event, sample);
 }
 
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
@@ -611,10 +611,10 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 
 int perf_event__process(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
-			struct perf_sample *sample __maybe_unused,
+			struct perf_sample *sample,
 			struct machine *machine)
 {
-	return machine__process_event(machine, event);
+	return machine__process_event(machine, event, sample);
 }
 
 void thread__find_addr_map(struct thread *self,
@@ -721,10 +721,10 @@ int perf_event__preprocess_sample(const union perf_event *event,
 		return -1;
 
 	if (symbol_conf.comm_list &&
-	    !strlist__has_entry(symbol_conf.comm_list, thread->comm))
+	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread)))
 		goto out_filtered;
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
+	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
 	 *
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 0582f67fbefc..1c173ccb0ef2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -607,6 +607,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
 	if (evlist->mmap[idx].base == MAP_FAILED) {
+		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
+			  errno);
 		evlist->mmap[idx].base = NULL;
 		return -1;
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3a334f001997..5280820ed389 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -663,7 +663,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	}
 
 	if (opts->sample_address)
-		attr->sample_type	|= PERF_SAMPLE_DATA_SRC;
+		perf_evsel__set_sample_bit(evsel, DATA_SRC);
 
 	if (opts->no_delay) {
 		attr->watermark = 0;
@@ -675,13 +675,13 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	}
 
 	if (opts->sample_weight)
-		attr->sample_type	|= PERF_SAMPLE_WEIGHT;
+		perf_evsel__set_sample_bit(evsel, WEIGHT);
 
 	attr->mmap  = track;
 	attr->comm  = track;
 
 	if (opts->sample_transaction)
-		attr->sample_type	|= PERF_SAMPLE_TRANSACTION;
+		perf_evsel__set_sample_bit(evsel, TRANSACTION);
 
 	/*
 	 * XXX see the function comment above
@@ -1051,6 +1051,8 @@ retry_open:
 								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0) {
 				err = -errno;
+				pr_debug2("perf_event_open failed, error %d\n",
+					  err);
 				goto try_fallback;
 			}
 			set_rlimit = NO_CHANGE;
@@ -1479,6 +1481,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	data->transaction = 0;
 	if (type & PERF_SAMPLE_TRANSACTION) {
+		OVERFLOW_CHECK_u64(array);
 		data->transaction = *array;
 		array++;
 	}
@@ -1575,6 +1578,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_DATA_SRC)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_TRANSACTION)
+		result += sizeof(u64);
+
 	return result;
 }
 
@@ -1748,6 +1754,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		*array = sample->transaction;
+		array++;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 7e80253074b0..30793f98c8bb 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -416,6 +416,7 @@ struct hist_entry *__hists__add_mem_entry(struct hists *hists,
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
+		.comm = thread__comm(al->thread),
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,
@@ -446,6 +447,7 @@ struct hist_entry *__hists__add_branch_entry(struct hists *hists,
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
+		.comm = thread__comm(al->thread),
 		.ms = {
 			.map	= bi->to.map,
 			.sym	= bi->to.sym,
@@ -475,6 +477,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
+		.comm = thread__comm(al->thread),
 		.ms = {
 			.map	= al->map,
 			.sym	= al->sym,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ea93425cce95..ce034c183a7e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -40,7 +40,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 			return -ENOMEM;
 
 		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
-		thread__set_comm(thread, comm);
+		thread__set_comm(thread, comm, 0);
 	}
 
 	return 0;
@@ -331,7 +331,8 @@ struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 	return __machine__findnew_thread(machine, 0, tid, false);
 }
 
-int machine__process_comm_event(struct machine *machine, union perf_event *event)
+int machine__process_comm_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample)
 {
 	struct thread *thread = machine__findnew_thread(machine,
 							event->comm.pid,
@@ -340,7 +341,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
-	if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
+	if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
@@ -349,7 +350,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 }
 
 int machine__process_lost_event(struct machine *machine __maybe_unused,
-				union perf_event *event)
+				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
 	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
 		    event->lost.id, event->lost.lost);
@@ -984,7 +985,8 @@ out_problem:
 }
 
 int machine__process_mmap2_event(struct machine *machine,
-				 union perf_event *event)
+				 union perf_event *event,
+				 struct perf_sample *sample __maybe_unused)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
@@ -1031,7 +1033,8 @@ out_problem:
 	return 0;
 }
 
-int machine__process_mmap_event(struct machine *machine, union perf_event *event)
+int machine__process_mmap_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample __maybe_unused)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
@@ -1088,7 +1091,8 @@ static void machine__remove_thread(struct machine *machine, struct thread *th)
 	list_add_tail(&th->node, &machine->dead_threads);
 }
 
-int machine__process_fork_event(struct machine *machine, union perf_event *event)
+int machine__process_fork_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample)
 {
 	struct thread *thread = machine__find_thread(machine, event->fork.tid);
 	struct thread *parent = machine__findnew_thread(machine,
@@ -1105,7 +1109,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 		perf_event__fprintf_task(event, stdout);
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent) < 0) {
+	    thread__fork(thread, parent, sample->time) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		return -1;
 	}
@@ -1113,8 +1117,8 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	return 0;
 }
 
-int machine__process_exit_event(struct machine *machine __maybe_unused,
-				union perf_event *event)
+int machine__process_exit_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample __maybe_unused)
 {
 	struct thread *thread = machine__find_thread(machine, event->fork.tid);
 
@@ -1127,23 +1131,24 @@ int machine__process_exit_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-int machine__process_event(struct machine *machine, union perf_event *event)
+int machine__process_event(struct machine *machine, union perf_event *event,
+			   struct perf_sample *sample)
 {
 	int ret;
 
 	switch (event->header.type) {
 	case PERF_RECORD_COMM:
-		ret = machine__process_comm_event(machine, event); break;
+		ret = machine__process_comm_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP:
-		ret = machine__process_mmap_event(machine, event); break;
+		ret = machine__process_mmap_event(machine, event, sample); break;
 	case PERF_RECORD_MMAP2:
-		ret = machine__process_mmap2_event(machine, event); break;
+		ret = machine__process_mmap2_event(machine, event, sample); break;
 	case PERF_RECORD_FORK:
-		ret = machine__process_fork_event(machine, event); break;
+		ret = machine__process_fork_event(machine, event, sample); break;
 	case PERF_RECORD_EXIT:
-		ret = machine__process_exit_event(machine, event); break;
+		ret = machine__process_exit_event(machine, event, sample); break;
 	case PERF_RECORD_LOST:
-		ret = machine__process_lost_event(machine, event); break;
+		ret = machine__process_lost_event(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 4c1f5d567f54..2389ba81fafe 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -40,13 +40,20 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 
 struct thread *machine__find_thread(struct machine *machine, pid_t tid);
 
-int machine__process_comm_event(struct machine *machine, union perf_event *event);
-int machine__process_exit_event(struct machine *machine, union perf_event *event);
-int machine__process_fork_event(struct machine *machine, union perf_event *event);
-int machine__process_lost_event(struct machine *machine, union perf_event *event);
-int machine__process_mmap_event(struct machine *machine, union perf_event *event);
-int machine__process_mmap2_event(struct machine *machine, union perf_event *event);
-int machine__process_event(struct machine *machine, union perf_event *event);
+int machine__process_comm_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_exit_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_fork_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_lost_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_mmap_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
+int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
+				 struct perf_sample *sample);
+int machine__process_event(struct machine *machine, union perf_event *event,
+				struct perf_sample *sample);
 
 typedef void (*machine__process_t)(struct machine *machine, void *data);
 
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 2bc9e70df7e2..31f404a032a9 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -339,10 +339,10 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		if (arg[1] != '-') {
 			ctx->opt = arg + 1;
 			if (internal_help && *ctx->opt == 'h')
-				return parse_options_usage(usagestr, options);
+				return usage_with_options_internal(usagestr, options, 0);
 			switch (parse_short_opt(ctx, options)) {
 			case -1:
-				return parse_options_usage(usagestr, options);
+				return parse_options_usage(usagestr, options, arg + 1, 1);
 			case -2:
 				goto unknown;
 			default:
@@ -352,10 +352,11 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 				check_typos(arg + 1, options);
 			while (ctx->opt) {
 				if (internal_help && *ctx->opt == 'h')
-					return parse_options_usage(usagestr, options);
+					return usage_with_options_internal(usagestr, options, 0);
+				arg = ctx->opt;
 				switch (parse_short_opt(ctx, options)) {
 				case -1:
-					return parse_options_usage(usagestr, options);
+					return parse_options_usage(usagestr, options, arg, 1);
 				case -2:
 					/* fake a short option thing to hide the fact that we may have
 					 * started to parse aggregated stuff
@@ -383,12 +384,12 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		if (internal_help && !strcmp(arg + 2, "help-all"))
 			return usage_with_options_internal(usagestr, options, 1);
 		if (internal_help && !strcmp(arg + 2, "help"))
-			return parse_options_usage(usagestr, options);
+			return usage_with_options_internal(usagestr, options, 0);
 		if (!strcmp(arg + 2, "list-opts"))
 			return PARSE_OPT_LIST;
 		switch (parse_long_opt(ctx, arg + 2, options)) {
 		case -1:
-			return parse_options_usage(usagestr, options);
+			return parse_options_usage(usagestr, options, arg + 2, 0);
 		case -2:
 			goto unknown;
 		default:
@@ -445,6 +446,89 @@ int parse_options(int argc, const char **argv, const struct option *options,
 #define USAGE_OPTS_WIDTH 24
 #define USAGE_GAP         2
 
+static void print_option_help(const struct option *opts, int full)
+{
+	size_t pos;
+	int pad;
+
+	if (opts->type == OPTION_GROUP) {
+		fputc('\n', stderr);
+		if (*opts->help)
+			fprintf(stderr, "%s\n", opts->help);
+		return;
+	}
+	if (!full && (opts->flags & PARSE_OPT_HIDDEN))
+		return;
+
+	pos = fprintf(stderr, "    ");
+	if (opts->short_name)
+		pos += fprintf(stderr, "-%c", opts->short_name);
+	else
+		pos += fprintf(stderr, "    ");
+
+	if (opts->long_name && opts->short_name)
+		pos += fprintf(stderr, ", ");
+	if (opts->long_name)
+		pos += fprintf(stderr, "--%s", opts->long_name);
+
+	switch (opts->type) {
+	case OPTION_ARGUMENT:
+		break;
+	case OPTION_LONG:
+	case OPTION_U64:
+	case OPTION_INTEGER:
+	case OPTION_UINTEGER:
+		if (opts->flags & PARSE_OPT_OPTARG)
+			if (opts->long_name)
+				pos += fprintf(stderr, "[=<n>]");
+			else
+				pos += fprintf(stderr, "[<n>]");
+		else
+			pos += fprintf(stderr, " <n>");
+		break;
+	case OPTION_CALLBACK:
+		if (opts->flags & PARSE_OPT_NOARG)
+			break;
+		/* FALLTHROUGH */
+	case OPTION_STRING:
+		if (opts->argh) {
+			if (opts->flags & PARSE_OPT_OPTARG)
+				if (opts->long_name)
+					pos += fprintf(stderr, "[=<%s>]", opts->argh);
+				else
+					pos += fprintf(stderr, "[<%s>]", opts->argh);
+			else
+				pos += fprintf(stderr, " <%s>", opts->argh);
+		} else {
+			if (opts->flags & PARSE_OPT_OPTARG)
+				if (opts->long_name)
+					pos += fprintf(stderr, "[=...]");
+				else
+					pos += fprintf(stderr, "[...]");
+			else
+				pos += fprintf(stderr, " ...");
+		}
+		break;
+	default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
+	case OPTION_END:
+	case OPTION_GROUP:
+	case OPTION_BIT:
+	case OPTION_BOOLEAN:
+	case OPTION_INCR:
+	case OPTION_SET_UINT:
+	case OPTION_SET_PTR:
+		break;
+	}
+
+	if (pos <= USAGE_OPTS_WIDTH)
+		pad = USAGE_OPTS_WIDTH - pos;
+	else {
+		fputc('\n', stderr);
+		pad = USAGE_OPTS_WIDTH;
+	}
+	fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+}
+
 int usage_with_options_internal(const char * const *usagestr,
 				const struct option *opts, int full)
 {
@@ -464,87 +548,9 @@ int usage_with_options_internal(const char * const *usagestr,
 	if (opts->type != OPTION_GROUP)
 		fputc('\n', stderr);
 
-	for (; opts->type != OPTION_END; opts++) {
-		size_t pos;
-		int pad;
-
-		if (opts->type == OPTION_GROUP) {
-			fputc('\n', stderr);
-			if (*opts->help)
-				fprintf(stderr, "%s\n", opts->help);
-			continue;
-		}
-		if (!full && (opts->flags & PARSE_OPT_HIDDEN))
-			continue;
-
-		pos = fprintf(stderr, "    ");
-		if (opts->short_name)
-			pos += fprintf(stderr, "-%c", opts->short_name);
-		else
-			pos += fprintf(stderr, "    ");
-
-		if (opts->long_name && opts->short_name)
-			pos += fprintf(stderr, ", ");
-		if (opts->long_name)
-			pos += fprintf(stderr, "--%s", opts->long_name);
-
-		switch (opts->type) {
-		case OPTION_ARGUMENT:
-			break;
-		case OPTION_LONG:
-		case OPTION_U64:
-		case OPTION_INTEGER:
-		case OPTION_UINTEGER:
-			if (opts->flags & PARSE_OPT_OPTARG)
-				if (opts->long_name)
-					pos += fprintf(stderr, "[=<n>]");
-				else
-					pos += fprintf(stderr, "[<n>]");
-			else
-				pos += fprintf(stderr, " <n>");
-			break;
-		case OPTION_CALLBACK:
-			if (opts->flags & PARSE_OPT_NOARG)
-				break;
-			/* FALLTHROUGH */
-		case OPTION_STRING:
-			if (opts->argh) {
-				if (opts->flags & PARSE_OPT_OPTARG)
-					if (opts->long_name)
-						pos += fprintf(stderr, "[=<%s>]", opts->argh);
-					else
-						pos += fprintf(stderr, "[<%s>]", opts->argh);
-				else
-					pos += fprintf(stderr, " <%s>", opts->argh);
-			} else {
-				if (opts->flags & PARSE_OPT_OPTARG)
-					if (opts->long_name)
-						pos += fprintf(stderr, "[=...]");
-					else
-						pos += fprintf(stderr, "[...]");
-				else
-					pos += fprintf(stderr, " ...");
-			}
-			break;
-		default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
-		case OPTION_END:
-		case OPTION_GROUP:
-		case OPTION_BIT:
-		case OPTION_BOOLEAN:
-		case OPTION_INCR:
-		case OPTION_SET_UINT:
-		case OPTION_SET_PTR:
-			break;
-		}
+	for (  ; opts->type != OPTION_END; opts++)
+		print_option_help(opts, full);
 
-		if (pos <= USAGE_OPTS_WIDTH)
-			pad = USAGE_OPTS_WIDTH - pos;
-		else {
-			fputc('\n', stderr);
-			pad = USAGE_OPTS_WIDTH;
-		}
-		fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
-	}
 	fputc('\n', stderr);
 
 	return PARSE_OPT_HELP;
@@ -559,9 +565,45 @@ void usage_with_options(const char * const *usagestr,
 }
 
 int parse_options_usage(const char * const *usagestr,
-			const struct option *opts)
+			const struct option *opts,
+			const char *optstr, bool short_opt)
 {
-	return usage_with_options_internal(usagestr, opts, 0);
+	if (!usagestr)
+		goto opt;
+
+	fprintf(stderr, "\n usage: %s\n", *usagestr++);
+	while (*usagestr && **usagestr)
+		fprintf(stderr, "    or: %s\n", *usagestr++);
+	while (*usagestr) {
+		fprintf(stderr, "%s%s\n",
+				**usagestr ? "    " : "",
+				*usagestr);
+		usagestr++;
+	}
+	fputc('\n', stderr);
+
+opt:
+	for (  ; opts->type != OPTION_END; opts++) {
+		if (short_opt) {
+			if (opts->short_name == *optstr)
+				break;
+			continue;
+		}
+
+		if (opts->long_name == NULL)
+			continue;
+
+		if (!prefixcmp(optstr, opts->long_name))
+			break;
+		if (!prefixcmp(optstr, "no-") &&
+		    !prefixcmp(optstr + 3, opts->long_name))
+			break;
+	}
+
+	if (opts->type != OPTION_END)
+		print_option_help(opts, 0);
+
+	return PARSE_OPT_HELP;
 }
 
 
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 7bb5999940ca..b0241e28eaf7 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -158,7 +158,9 @@ struct parse_opt_ctx_t {
 };
 
 extern int parse_options_usage(const char * const *usagestr,
-			       const struct option *opts);
+			       const struct option *opts,
+			       const char *optstr,
+			       bool short_opt);
 
 extern void parse_options_start(struct parse_opt_ctx_t *ctx,
 				int argc, const char **argv, int flags);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index e41b0941e18f..2200dad4c3f4 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -583,7 +583,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 	}
 
 	if (die_find_member(&type, field->name, die_mem) == NULL) {
-		pr_warning("%s(tyep:%s) has no member %s.\n", varname,
+		pr_warning("%s(type:%s) has no member %s.\n", varname,
 			   dwarf_diename(&type), field->name);
 		return -EINVAL;
 	}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index c0c9795c4f02..d5e5969f6fea 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -273,7 +273,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;
 	unsigned long long nsecs = sample->time;
-	char *comm = thread->comm;
+	const char *comm = thread__comm_str(thread);
 
 	dSP;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 95d91a0b23af..53c20e7fd900 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -250,7 +250,7 @@ static void python_process_tracepoint(union perf_event *perf_event
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;
 	unsigned long long nsecs = sample->time;
-	char *comm = thread->comm;
+	const char *comm = thread__comm_str(thread);
 
 	t = PyTuple_New(MAX_FIELDS);
 	if (!t)
@@ -389,7 +389,7 @@ static void python_process_general_event(union perf_event *perf_event
 	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
 			(const char *)sample->raw_data, sample->raw_size));
 	pydict_set_item_string_decref(dict, "comm",
-			PyString_FromString(thread->comm));
+			PyString_FromString(thread__comm_str(thread)));
 	if (al->map) {
 		pydict_set_item_string_decref(dict, "dso",
 			PyString_FromString(al->map->dso->name));
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4ba7b548e055..3c1b30103d54 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1100,7 +1100,7 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
 {
 	struct thread *thread = perf_session__findnew(self, 0);
 
-	if (thread == NULL || thread__set_comm(thread, "swapper")) {
+	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
 		pr_err("problem inserting idle task.\n");
 		thread = NULL;
 	}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 19b4aa279d1e..3c1b75c8b9a6 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,5 +1,6 @@
 #include "sort.h"
 #include "hist.h"
+#include "comm.h"
 #include "symbol.h"
 
 regex_t		parent_regex;
@@ -42,7 +43,7 @@ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 	return n;
 }
 
-static int64_t cmp_null(void *l, void *r)
+static int64_t cmp_null(const void *l, const void *r)
 {
 	if (!l && !r)
 		return 0;
@@ -63,8 +64,9 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
+	const char *comm = thread__comm_str(he->thread);
 	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-			      he->thread->comm ?: "", he->thread->tid);
+			       comm ?: "", he->thread->tid);
 }
 
 struct sort_entry sort_thread = {
@@ -79,25 +81,21 @@ struct sort_entry sort_thread = {
 static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return right->thread->tid - left->thread->tid;
+	/* Compare the addr that should be unique among comm */
+	return comm__str(right->comm) - comm__str(left->comm);
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
-	char *comm_l = left->thread->comm;
-	char *comm_r = right->thread->comm;
-
-	if (!comm_l || !comm_r)
-		return cmp_null(comm_l, comm_r);
-
-	return strcmp(comm_l, comm_r);
+	/* Compare the addr that should be unique among comm */
+	return comm__str(right->comm) - comm__str(left->comm);
 }
 
 static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
 				     size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*s", width, he->thread->comm);
+	return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
 }
 
 struct sort_entry sort_comm = {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index bf4333694d3a..f4e16f359d64 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -84,6 +84,7 @@ struct hist_entry {
 	struct he_stat		stat;
 	struct map_symbol	ms;
 	struct thread		*thread;
+	struct comm		*comm;
 	u64			ip;
 	u64			transaction;
 	s32			cpu;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 80d19a086072..cd8e2f592719 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -6,9 +6,12 @@
 #include "thread.h"
 #include "util.h"
 #include "debug.h"
+#include "comm.h"
 
 struct thread *thread__new(pid_t pid, pid_t tid)
 {
+	char *comm_str;
+	struct comm *comm;
 	struct thread *thread = zalloc(sizeof(*thread));
 
 	if (thread != NULL) {
@@ -16,41 +19,88 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->pid_ = pid;
 		thread->tid = tid;
 		thread->ppid = -1;
-		thread->comm = malloc(32);
-		if (thread->comm)
-			snprintf(thread->comm, 32, ":%d", thread->tid);
+		INIT_LIST_HEAD(&thread->comm_list);
+
+		comm_str = malloc(32);
+		if (!comm_str)
+			goto err_thread;
+
+		snprintf(comm_str, 32, ":%d", tid);
+		comm = comm__new(comm_str, 0);
+		free(comm_str);
+		if (!comm)
+			goto err_thread;
+
+		list_add(&comm->list, &thread->comm_list);
 	}
 
 	return thread;
+
+err_thread:
+	free(thread);
+	return NULL;
 }
 
 void thread__delete(struct thread *thread)
 {
+	struct comm *comm, *tmp;
+
 	map_groups__exit(&thread->mg);
-	free(thread->comm);
+	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+		list_del(&comm->list);
+		comm__free(comm);
+	}
+
 	free(thread);
 }
 
-int thread__set_comm(struct thread *thread, const char *comm)
+struct comm *thread__comm(const struct thread *thread)
 {
-	int err;
+	if (list_empty(&thread->comm_list))
+		return NULL;
 
-	if (thread->comm)
-		free(thread->comm);
-	thread->comm = strdup(comm);
-	err = thread->comm == NULL ? -ENOMEM : 0;
-	if (!err) {
-		thread->comm_set = true;
+	return list_first_entry(&thread->comm_list, struct comm, list);
+}
+
+/* CHECKME: time should always be 0 if event aren't ordered */
+int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+{
+	struct comm *new, *curr = thread__comm(thread);
+
+	/* Override latest entry if it had no specific time coverage */
+	if (!curr->start) {
+		comm__override(curr, str, timestamp);
+		return 0;
 	}
-	return err;
+
+	new = comm__new(str, timestamp);
+	if (!new)
+		return -ENOMEM;
+
+	list_add(&new->list, &thread->comm_list);
+	thread->comm_set = true;
+
+	return 0;
+}
+
+const char *thread__comm_str(const struct thread *thread)
+{
+	const struct comm *comm = thread__comm(thread);
+
+	if (!comm)
+		return NULL;
+
+	return comm__str(comm);
 }
 
+/* CHECKME: it should probably better return the max comm len from its comm list */
 int thread__comm_len(struct thread *thread)
 {
 	if (!thread->comm_len) {
-		if (!thread->comm)
+		const char *comm = thread__comm_str(thread);
+		if (!comm)
 			return 0;
-		thread->comm_len = strlen(thread->comm);
+		thread->comm_len = strlen(comm);
 	}
 
 	return thread->comm_len;
@@ -58,7 +108,7 @@ int thread__comm_len(struct thread *thread)
 
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
-	return fprintf(fp, "Thread %d %s\n", thread->tid, thread->comm) +
+	return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
 	       map_groups__fprintf(&thread->mg, verbose, fp);
 }
 
@@ -68,16 +118,17 @@ void thread__insert_map(struct thread *thread, struct map *map)
 	map_groups__insert(&thread->mg, map);
 }
 
-int thread__fork(struct thread *thread, struct thread *parent)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 {
-	int i;
+	int i, err;
 
 	if (parent->comm_set) {
-		if (thread->comm)
-			free(thread->comm);
-		thread->comm = strdup(parent->comm);
-		if (!thread->comm)
+		const char *comm = thread__comm_str(parent);
+		if (!comm)
 			return -ENOMEM;
+		err = thread__set_comm(thread, comm, timestamp);
+		if (!err)
+			return err;
 		thread->comm_set = true;
 	}
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 4ebbb40d46d4..373c055989ed 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -2,6 +2,7 @@
 #define __PERF_THREAD_H
 
 #include <linux/rbtree.h>
+#include <linux/list.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include "symbol.h"
@@ -18,13 +19,14 @@ struct thread {
 	char			shortname[3];
 	bool			comm_set;
 	bool			dead; /* if set thread has exited */
-	char			*comm;
+	struct list_head	comm_list;
 	int			comm_len;
 
 	void			*priv;
 };
 
 struct machine;
+struct comm;
 
 struct thread *thread__new(pid_t pid, pid_t tid);
 void thread__delete(struct thread *self);
@@ -33,10 +35,12 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
-int thread__set_comm(struct thread *self, const char *comm);
+int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
 int thread__comm_len(struct thread *self);
+struct comm *thread__comm(const struct thread *thread);
+const char *thread__comm_str(const struct thread *thread);
 void thread__insert_map(struct thread *self, struct map *map);
-int thread__fork(struct thread *self, struct thread *parent);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 static inline struct map *thread__find_map(struct thread *self,