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>

18 files changed, 441 insertions, 173 deletions

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,