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 d1c2a6a4cd3..8f450adaa9c 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 c37b2026d04..8d73d2594f6 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 8a9ca383604..5b8639025aa 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 1126382659a..a28970f7ddf 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 33c7253295b..35f9aaa565c 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 98d3891392e..25f83d5d66f 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 ddb5dc15be1..a81ab1828aa 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 0ae88c2538a..baf17989a21 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 1a9c95d270a..0fc1c941a73 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 a6ea956a533..ca5ca37980f 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, &