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:

New features:

  - Allow filtering out of perf's PID via 'perf record --exclude-perf'. (Wang Nan)

  - 'perf trace' now supports syscall groups, like strace, i.e:

      $ trace -e file touch file

    Will expand 'file' into multiple, file related, syscalls. More work needed to
    add extra groups for other syscall groups, and also to complement what was
    added for the 'file' group, included as a proof of concept. (Arnaldo Carvalho de Melo)

  - Add lock_pi stresser to 'perf bench futex', to test the kernel code
    related to FUTEX_(UN)LOCK_PI. (Davidlohr Bueso)

User visible fixes:

  - Apply --filter to all events in a glob matching, not just the last one. (Wang Nan)

Documentation changes:

  - Document setting '-e pmu/period=N/' in the 'perf record' man page. (Kan Liang)

Infrastructure changes:

  - 'perf probe' code simplifications and movements to separate files. (Masami Hiramatsu)

  - Fix makefile generation under 'dash'. (Sergei Trofimovich)

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

tools/perf/Build

@@ -35,6 +35,7 @@ paths += -DPERF_MAN_PATH="BUILD_STR($(mandir_SQ))"
 CFLAGS_builtin-help.o      += $(paths)
 CFLAGS_builtin-timechart.o += $(paths)
 CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" -include $(OUTPUT)PERF-VERSION-FILE
+CFLAGS_builtin-trace.o	   += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
 
 libperf-y += util/
 libperf-y += arch/

tools/perf/Documentation/perf-bench.txt

@@ -216,6 +216,10 @@ Suite for evaluating parallel wake calls.
 *requeue*::
 Suite for evaluating requeue calls.
 
+*lock-pi*::
+Suite for evaluating futex lock_pi calls.
+
+
 SEE ALSO
 --------
 linkperf:perf[1]

tools/perf/Documentation/perf-record.txt

@@ -45,6 +45,14 @@ OPTIONS
           param1 and param2 are defined as formats for the PMU in:
           /sys/bus/event_sources/devices/<pmu>/format/*
 
+	  There are also some params which are not defined in .../<pmu>/format/*.
+	  These params can be used to set event defaults.
+	  Here is a list of the params.
+	  - 'period': Set event sampling period
+
+	  Note: If user explicitly sets options which conflict with the params,
+	  the value set by the params will be overridden.
+
         - a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
           where addr is the address in memory you want to break in.
           Access is the memory access type (read, write, execute) it can
@@ -61,7 +69,16 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter.
+        Event filter. This option should follow a event selector (-e) which
+	selects tracepoint event(s). Multiple '--filter' options are combined
+	using '&&'.
+
+--exclude-perf::
+	Don't record events issued by perf itself. This option should follow
+	a event selector (-e) which selects tracepoint event(s). It adds a
+	filter expression 'common_pid != $PERFPID' to filters. If other
+	'--filter' exists, the new filter expression will be combined with
+	them by '&&'.
 
 -a::
 --all-cpus::

tools/perf/Makefile.perf

@@ -507,6 +507,11 @@ endif
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-with-kcore) \
 		$(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBAUDIT
+	$(call QUIET_INSTALL, strace/groups) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \
+		$(INSTALL) trace/strace/groups/* -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'
+endif
 ifndef NO_LIBPERL
 	$(call QUIET_INSTALL, perl-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \

tools/perf/bench/Build

@@ -5,6 +5,7 @@ perf-y += futex-hash.o
 perf-y += futex-wake.o
 perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
+perf-y += futex-lock-pi.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o

tools/perf/bench/bench.h

@@ -36,6 +36,8 @@ extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
 extern int bench_futex_wake_parallel(int argc, const char **argv,
 				     const char *prefix);
 extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+/* pi futexes */
+extern int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0

tools/perf/bench/futex-lock-pi.c

@@ -0,0 +1,219 @@
+/*
+ * Copyright (C) 2015 Davidlohr Bueso.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+struct worker {
+	int tid;
+	u_int32_t *futex;
+	pthread_t thread;
+	unsigned long ops;
+};
+
+static u_int32_t global_futex = 0;
+static struct worker *worker;
+static unsigned int nsecs = 10;
+static bool silent = false, multi = false;
+static bool done = false, fshared = false;
+static unsigned int ncpus, nthreads = 0;
+static int futex_flag = 0;
+struct timeval start, end, runtime;
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats throughput_stats;
+static pthread_cond_t thread_parent, thread_worker;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
+	OPT_UINTEGER('r', "runtime", &nsecs,     "Specify runtime (in seconds)"),
+	OPT_BOOLEAN( 'M', "multi",   &multi,     "Use multiple futexes"),
+	OPT_BOOLEAN( 's', "silent",  &silent,    "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,   "Use shared futexes instead of private ones"),
+	OPT_END()
+};
+
+static const char * const bench_futex_lock_pi_usage[] = {
+	"perf bench futex requeue <options>",
+	NULL
+};
+
+static void print_summary(void)
+{
+	unsigned long avg = avg_stats(&throughput_stats);
+	double stddev = stddev_stats(&throughput_stats);
+
+	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
+	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+	       (int) runtime.tv_sec);
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	/* inform all threads that we're done for the day */
+	done = true;
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &runtime);
+}
+
+static void *workerfn(void *arg)
+{
+	struct worker *w = (struct worker *) arg;
+
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	do {
+		int ret;
+	again:
+		ret = futex_lock_pi(w->futex, NULL, 0, futex_flag);
+
+		if (ret) { /* handle lock acquisition */
+			if (!silent)
+				warn("thread %d: Could not lock pi-lock for %p (%d)",
+				     w->tid, w->futex, ret);
+			if (done)
+				break;
+
+			goto again;
+		}
+
+		usleep(1);
+		ret = futex_unlock_pi(w->futex, futex_flag);
+		if (ret && !silent)
+			warn("thread %d: Could not unlock pi-lock for %p (%d)",
+			     w->tid, w->futex, ret);
+		w->ops++; /* account for thread's share of work */
+	}  while (!done);
+
+	return NULL;
+}
+
+static void create_threads(struct worker *w, pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nthreads;
+
+	for (i = 0; i < nthreads; i++) {
+		worker[i].tid = i;
+
+		if (multi) {
+			worker[i].futex = calloc(1, sizeof(u_int32_t));
+			if (!worker[i].futex)
+				err(EXIT_FAILURE, "calloc");
+		} else
+			worker[i].futex = &global_futex;
+
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+int bench_futex_lock_pi(int argc, const char **argv,
+			const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+
+	argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
+	if (argc)
+		goto err;
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	if (!nthreads)
+		nthreads = ncpus;
+
+	worker = calloc(nthreads, sizeof(*worker));
+	if (!worker)
+		err(EXIT_FAILURE, "calloc");
+
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: %d threads doing pi lock/unlock pairing for %d secs.\n\n",
+	       getpid(), nthreads, nsecs);
+
+	init_stats(&throughput_stats);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	threads_starting = nthreads;
+	pthread_attr_init(&thread_attr);
+	gettimeofday(&start, NULL);
+
+	create_threads(worker, thread_attr);
+	pthread_attr_destroy(&thread_attr);
+
+	pthread_mutex_lock(&thread_lock);
+	while (threads_starting)
+		pthread_cond_wait(&thread_parent, &thread_lock);
+	pthread_cond_broadcast(&thread_worker);
+	pthread_mutex_unlock(&thread_lock);
+
+	sleep(nsecs);
+	toggle_done(0, NULL, NULL);
+
+	for (i = 0; i < nthreads; i++) {
+		ret = pthread_join(worker[i].thread, NULL);
+		if (ret)
+			err(EXIT_FAILURE, "pthread_join");
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+
+	for (i = 0; i < nthreads; i++) {
+		unsigned long t = worker[i].ops/runtime.tv_sec;
+
+		update_stats(&throughput_stats, t);
+		if (!silent)
+			printf("[thread %3d] futex: %p [ %ld ops/sec ]\n",
+			       worker[i].tid, worker[i].futex, t);
+
+		if (multi)
+			free(worker[i].futex);
+	}
+
+	print_summary();
+
+	free(worker);
+	return ret;
+err:
+	usage_with_options(bench_futex_lock_pi_usage, options);
+	exit(EXIT_FAILURE);
+}

tools/perf/bench/futex.h

@@ -55,6 +55,26 @@ futex_wake(u_int32_t *uaddr, int nr_wake, int opflags)
 	return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
 }
 
+/**
+ * futex_lock_pi() - block on uaddr as a PI mutex
+ * @detect:	whether (1) or not (0) to perform deadlock detection
+ */
+static inline int
+futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int detect,
+	      int opflags)
+{
+	return futex(uaddr, FUTEX_LOCK_PI, detect, timeout, NULL, 0, opflags);
+}
+
+/**
+ * futex_unlock_pi() - release uaddr as a PI mutex, waking the top waiter
+ */
+static inline int
+futex_unlock_pi(u_int32_t *uaddr, int opflags)
+{
+	return futex(uaddr, FUTEX_UNLOCK_PI, 0, NULL, NULL, 0, opflags);
+}
+
 /**
 * futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
 * @nr_wake:        wake up to this many tasks

tools/perf/builtin-bench.c

@@ -60,6 +60,8 @@ static struct bench futex_benchmarks[] = {
 	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
 	{ "wake-parallel", "Benchmark for parallel futex wake calls",   bench_futex_wake_parallel },
 	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
+	/* pi-futexes */
+	{ "lock-pi",	"Benchmark for futex lock_pi calls",            bench_futex_lock_pi	},
 	{ "all",	"Test all futex benchmarks",			NULL			},
 	{ NULL,		NULL,						NULL			}
 };

tools/perf/builtin-buildid-cache.c

@@ -127,7 +127,7 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 
 static int build_id_cache__add_kcore(const char *filename, bool force)
 {
-	char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1];
+	char dir[32], sbuildid[SBUILD_ID_SIZE];
 	char from_dir[PATH_MAX], to_dir[PATH_MAX];
 	char *p;
 
@@ -184,7 +184,7 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
 
 static int build_id_cache__add_file(const char *filename)
 {
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 	u8 build_id[BUILD_ID_SIZE];
 	int err;
 
@@ -204,7 +204,7 @@ static int build_id_cache__add_file(const char *filename)
 static int build_id_cache__remove_file(const char *filename)
 {
 	u8 build_id[BUILD_ID_SIZE];
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 
 	int err;
 
@@ -276,7 +276,7 @@ static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *f
 static int build_id_cache__update_file(const char *filename)
 {
 	u8 build_id[BUILD_ID_SIZE];
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 
 	int err = 0;
 
@@ -363,7 +363,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	setup_pager();
 
 	if (add_name_list_str) {
-		list = strlist__new(true, add_name_list_str);
+		list = strlist__new(add_name_list_str, NULL);
 		if (list) {
 			strlist__for_each(pos, list)
 				if (build_id_cache__add_file(pos->s)) {
@@ -381,7 +381,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	}
 
 	if (remove_name_list_str) {
-		list = strlist__new(true, remove_name_list_str);
+		list = strlist__new(remove_name_list_str, NULL);
 		if (list) {
 			strlist__for_each(pos, list)
 				if (build_id_cache__remove_file(pos->s)) {
@@ -399,7 +399,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	}
 
 	if (purge_name_list_str) {
-		list = strlist__new(true, purge_name_list_str);
+		list = strlist__new(purge_name_list_str, NULL);
 		if (list) {
 			strlist__for_each(pos, list)
 				if (build_id_cache__purge_path(pos->s)) {
@@ -420,7 +420,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 		ret = build_id_cache__fprintf_missing(session, stdout);
 
 	if (update_name_list_str) {
-		list = strlist__new(true, update_name_list_str);
+		list = strlist__new(update_name_list_str, NULL);
 		if (list) {
 			strlist__for_each(pos, list)
 				if (build_id_cache__update_file(pos->s)) {

tools/perf/builtin-buildid-list.c

@@ -20,7 +20,7 @@
 static int sysfs__fprintf_build_id(FILE *fp)
 {
 	u8 kallsyms_build_id[BUILD_ID_SIZE];
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 
 	if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
 				 sizeof(kallsyms_build_id)) != 0)
@@ -35,7 +35,7 @@ static int sysfs__fprintf_build_id(FILE *fp)
 static int filename__fprintf_build_id(const char *name, FILE *fp)
 {
 	u8 build_id[BUILD_ID_SIZE];
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 
 	if (filename__read_build_id(name, build_id,
 				    sizeof(build_id)) != sizeof(build_id))

tools/perf/builtin-record.c

@@ -992,6 +992,9 @@ struct option __record_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
 		     "event filter", parse_filter),
+	OPT_CALLBACK_NOOPT(0, "exclude-perf", &record.evlist,
+			   NULL, "don't record events from perf itself",
+			   exclude_perf),
 	OPT_STRING('p', "pid", &record.opts.target.pid, "pid",
 		    "record events on existing process id"),
 	OPT_STRING('t', "tid", &record.opts.target.tid, "tid",

tools/perf/builtin-trace.c

@@ -3,6 +3,7 @@
 #include "util/color.h"
 #include "util/debug.h"
 #include "util/evlist.h"
+#include "util/exec_cmd.h"
 #include "util/machine.h"
 #include "util/session.h"
 #include "util/thread.h"
@@ -2927,11 +2928,14 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (ev_qualifier_str != NULL) {
 		const char *s = ev_qualifier_str;
+		struct strlist_config slist_config = {
+			.dirname = system_path(STRACE_GROUPS_DIR),
+		};
 
 		trace.not_ev_qualifier = *s == '!';
 		if (trace.not_ev_qualifier)
 			++s;
-		trace.ev_qualifier = strlist__new(true, s);
+		trace.ev_qualifier = strlist__new(s, &slist_config);
 		if (trace.ev_qualifier == NULL) {
 			fputs("Not enough memory to parse event qualifier",
 			      trace.output);

tools/perf/config/Makefile

@@ -11,7 +11,7 @@ ifneq ($(obj-perf),)
 obj-perf := $(abspath $(obj-perf))/
 endif
 
-$(shell echo -n > $(OUTPUT).config-detected)
+$(shell printf "" > $(OUTPUT).config-detected)
 detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
 detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
@@ -644,6 +644,7 @@ infodir = share/info
 perfexecdir = libexec/perf-core
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
+STRACE_GROUPS_DIR = share/perf-core/strace/groups
 htmldir = share/doc/perf-doc
 ifeq ($(prefix),/usr)
 sysconfdir = /etc
@@ -663,6 +664,7 @@ libdir = $(prefix)/$(lib)
 
 # Shell quote (do not use $(call) to accommodate ancient setups);
 ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
+STRACE_GROUPS_DIR_SQ = $(subst ','\'',$(STRACE_GROUPS_DIR))
 DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
 bindir_SQ = $(subst ','\'',$(bindir))
 mandir_SQ = $(subst ','\'',$(mandir))
@@ -676,10 +678,13 @@ libdir_SQ = $(subst ','\'',$(libdir))
 
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
+STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
+STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
 
 # If we install to $(HOME) we keep the traceevent default:
 # $(HOME)/.traceevent/plugins
@@ -713,6 +718,7 @@ $(call detected_var,htmldir_SQ)
 $(call detected_var,infodir_SQ)
 $(call detected_var,mandir_SQ)
 $(call detected_var,ETC_PERFCONFIG_SQ)
+$(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
 $(call detected_var,LIBDIR)

tools/perf/trace/strace/groups/file

@@ -0,0 +1,18 @@
+access
+chmod
+creat
+execve
+faccessat
+getcwd
+lstat
+mkdir
+open
+openat
+quotactl
+readlink
+rename
+rmdir
+stat
+statfs
+symlink
+unlink

tools/perf/util/Build

@@ -79,6 +79,7 @@ libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-y += parse-branch-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
+libperf-$(CONFIG_LIBELF) += probe-file.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
 
 ifndef CONFIG_LIBELF

tools/perf/util/build-id.c

@@ -124,7 +124,7 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
-	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	char build_id_hex[SBUILD_ID_SIZE];
 
 	if (!dso->has_build_id)
 		return NULL;
@@ -291,7 +291,7 @@ int build_id_cache__list_build_ids(const char *pathname,
 	struct dirent *d;
 	int ret = 0;
 
-	list = strlist__new(true, NULL);
+	list = strlist__new(NULL, NULL);
 	dir_name = build_id_cache__dirname_from_path(pathname, false, false);
 	if (!list || !dir_name) {
 		ret = -ENOMEM;
@@ -384,7 +384,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 				 const char *name, bool is_kallsyms,
 				 bool is_vdso)
 {
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	char sbuild_id[SBUILD_ID_SIZE];
 
 	build_id__sprintf(build_id, build_id_size, sbuild_id);
 

tools/perf/util/build-id.h

@@ -1,7 +1,8 @@
 #ifndef PERF_BUILD_ID_H_
 #define PERF_BUILD_ID_H_ 1
 
-#define BUILD_ID_SIZE 20
+#define BUILD_ID_SIZE	20
+#define SBUILD_ID_SIZE	(BUILD_ID_SIZE * 2 + 1)
 
 #include "tool.h"
 #include "strlist.h"

tools/perf/util/evsel.c

@@ -210,6 +210,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	perf_evsel__object.init(evsel);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 	perf_evsel__calc_id_pos(evsel);
+	evsel->cmdline_group_boundary = false;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)

tools/perf/util/evsel.h

@@ -86,6 +86,7 @@ struct perf_evsel {
 	unsigned long		*per_pkg_mask;
 	struct perf_evsel	*leader;
 	char			*group_name;
+	bool			cmdline_group_boundary;
 };
 
 union u64_swap {