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

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

Infrastructure changes:

  - Reference count the cpu_map and thread_map classes. (Jiri Olsa)

  - Set evsel->{cpus,threads} from the evlist, if not set,
    allowing the generalization of some 'perf stat' functions that
    previously were accessing private static evlist variable. (Jiri Olsa)

  - Delete an unnecessary check before the calling
    free_event_desc() (Markus Elfring)

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

tools/perf/builtin-stat.c

@@ -141,16 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 	}
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
-{
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
-}
-
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
-{
-	return perf_evsel__cpus(evsel)->nr;
-}
-
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;

tools/perf/tests/code-reading.c

@@ -545,8 +545,8 @@ out_err:
 	if (evlist) {
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);

tools/perf/tests/keep-tracking.c

@@ -144,8 +144,8 @@ out_err:
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;

tools/perf/tests/mmap-basic.c

@@ -140,8 +140,8 @@ out_delete_evlist:
 	cpus	= NULL;
 	threads = NULL;
 out_free_cpus:
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 out_free_threads:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }

tools/perf/tests/mmap-thread-lookup.c

@@ -143,7 +143,7 @@ static int synth_process(struct machine *machine)
 						perf_event__process,
 						machine, 0, 500);
 
-	thread_map__delete(map);
+	thread_map__put(map);
 	return err;
 }
 

tools/perf/tests/openat-syscall-all-cpus.c

@@ -111,6 +111,6 @@ out_close_fd:
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }

tools/perf/tests/openat-syscall.c

@@ -56,6 +56,6 @@ out_close_fd:
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }

tools/perf/tests/switch-tracking.c

@@ -560,8 +560,8 @@ out:
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;

tools/perf/util/cpumap.c

@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
 {
@@ -22,6 +23,7 @@ static struct cpu_map *cpu_map__default_new(void)
 			cpus->map[i] = i;
 
 		cpus->nr = nr_cpus;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -35,6 +37,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 	if (cpus != NULL) {
 		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
@@ -194,14 +197,32 @@ struct cpu_map *cpu_map__dummy_new(void)
 	if (cpus != NULL) {
 		cpus->nr = 1;
 		cpus->map[0] = -1;
+		atomic_set(&cpus->refcnt, 1);
 	}
 
 	return cpus;
 }
 
-void cpu_map__delete(struct cpu_map *map)
+static void cpu_map__delete(struct cpu_map *map)
 {
-	free(map);
+	if (map) {
+		WARN_ONCE(atomic_read(&map->refcnt) != 0,
+			  "cpu_map refcnt unbalanced\n");
+		free(map);
+	}
+}
+
+struct cpu_map *cpu_map__get(struct cpu_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void cpu_map__put(struct cpu_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		cpu_map__delete(map);
 }
 
 int cpu_map__get_socket(struct cpu_map *map, int idx)
@@ -263,6 +284,7 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	/* ensure we process id in increasing order */
 	qsort(c->map, c->nr, sizeof(int), cmp_ids);
 
+	atomic_set(&cpus->refcnt, 1);
 	*res = c;
 	return 0;
 }

tools/perf/util/cpumap.h

@@ -3,18 +3,19 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/atomic.h>
 
 #include "perf.h"
 #include "util/debug.h"
 
 struct cpu_map {
+	atomic_t refcnt;
 	int nr;
 	int map[];
 };
 
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
-void cpu_map__delete(struct cpu_map *map);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket(struct cpu_map *map, int idx);
@@ -22,6 +23,9 @@ int cpu_map__get_core(struct cpu_map *map, int idx);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
 
+struct cpu_map *cpu_map__get(struct cpu_map *map);
+void cpu_map__put(struct cpu_map *map);
+
 static inline int cpu_map__socket(struct cpu_map *sock, int s)
 {
 	if (!sock || s > sock->nr || s < 0)

tools/perf/util/evlist.c

@@ -114,8 +114,8 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 {
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
-	cpu_map__delete(evlist->cpus);
-	thread_map__delete(evlist->threads);
+	cpu_map__put(evlist->cpus);
+	thread_map__put(evlist->threads);
 	evlist->cpus = NULL;
 	evlist->threads = NULL;
 	perf_evlist__purge(evlist);
@@ -1101,6 +1101,31 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
+static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
+				       struct target *target)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		/*
+		 * We already have cpus for evsel (via PMU sysfs) so
+		 * keep it, if there's no target cpu list defined.
+		 */
+		if (evsel->cpus && target->cpu_list)
+			cpu_map__put(evsel->cpus);
+
+		if (!evsel->cpus || target->cpu_list)
+			evsel->cpus = cpu_map__get(evlist->cpus);
+
+		evsel->threads = thread_map__get(evlist->threads);
+
+		if (!evsel->cpus || !evsel->threads)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
@@ -1117,10 +1142,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return 0;
+	return perf_evlist__propagate_maps(evlist, target);
 
 out_delete_threads:
-	thread_map__delete(evlist->threads);
+	thread_map__put(evlist->threads);
 	evlist->threads = NULL;
 	return -1;
 }
@@ -1353,7 +1378,7 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 out:
 	return err;
 out_free_cpus:
-	cpu_map__delete(evlist->cpus);
+	cpu_map__put(evlist->cpus);
 	evlist->cpus = NULL;
 	goto out;
 }

tools/perf/util/evsel.c

@@ -885,6 +885,8 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
+	cpu_map__put(evsel->cpus);
+	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);

tools/perf/util/evsel.h

@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include "xyarray.h"
 #include "symbol.h"
+#include "cpumap.h"
 
 struct perf_counts_values {
 	union {
@@ -82,6 +83,7 @@ struct perf_evsel {
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
@@ -113,6 +115,16 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return evsel->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 

tools/perf/util/header.c

@@ -1063,8 +1063,7 @@ out:
 	free(buf);
 	return events;
 error:
-	if (events)
-		free_event_desc(events);
+	free_event_desc(events);
 	events = NULL;
 	goto out;
 }

tools/perf/util/parse-events.c

@@ -17,6 +17,7 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
+#include "cpumap.h"
 #include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
@@ -285,7 +286,9 @@ __add_event(struct list_head *list, int *idx,
 	if (!evsel)
 		return NULL;
 
-	evsel->cpus = cpus;
+	if (cpus)
+		evsel->cpus = cpu_map__get(cpus);
+
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);

tools/perf/util/python.c

@@ -384,7 +384,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
 
 static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
 {
-	cpu_map__delete(pcpus->cpus);
+	cpu_map__put(pcpus->cpus);
 	pcpus->ob_type->tp_free((PyObject*)pcpus);
 }
 
@@ -453,7 +453,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
 
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
-	thread_map__delete(pthreads->threads);
+	thread_map__put(pthreads->threads);
 	pthreads->ob_type->tp_free((PyObject*)pthreads);
 }
 

tools/perf/util/record.c

@@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 	if (!cpus)
 		return false;
 	cpu = cpus->map[0];
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 
 	do {
 		ret = perf_do_probe_api(fn, cpu, try[i++]);
@@ -226,7 +226,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 		struct cpu_map *cpus = cpu_map__new(NULL);
 
 		cpu =  cpus ? cpus->map[0] : 0;
-		cpu_map__delete(cpus);
+		cpu_map__put(cpus);
 	} else {
 		cpu = evlist->cpus->map[0];
 	}

tools/perf/util/session.c

@@ -1895,7 +1895,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	err = 0;
 
 out_delete_map:
-	cpu_map__delete(map);
+	cpu_map__put(map);
 	return err;
 }
 

tools/perf/util/svghelper.c

@@ -748,7 +748,7 @@ static int str_to_bitmap(char *s, cpumask_t *b)
 		set_bit(c, cpumask_bits(b));
 	}
 
-	cpu_map__delete(m);
+	cpu_map__put(m);
 
 	return ret;
 }

tools/perf/util/thread_map.c

@@ -8,6 +8,7 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
 
@@ -22,7 +23,7 @@ static int filter(const struct dirent *dir)
 
 static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
 {
-	size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
 
 	return realloc(map, size);
 }
@@ -47,6 +48,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 		for (i = 0; i < items; i++)
 			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -63,6 +65,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, tid);
 		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -84,6 +87,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
+	atomic_set(&threads->refcnt, 1);
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -212,6 +216,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 out:
 	strlist__delete(slist);
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -231,6 +237,7 @@ struct thread_map *thread_map__new_dummy(void)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, -1);
 		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -273,6 +280,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 		threads->nr = ntasks;
 	}
 out:
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -292,9 +301,26 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	return thread_map__new_by_tid_str(tid);
 }
 
-void thread_map__delete(struct thread_map *threads)
+static void thread_map__delete(struct thread_map *threads)
 {
-	free(threads);
+	if (threads) {
+		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+			  "thread map refcnt unbalanced\n");
+		free(threads);
+	}
+}
+
+struct thread_map *thread_map__get(struct thread_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void thread_map__put(struct thread_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		thread_map__delete(map);
 }
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)

tools/perf/util/thread_map.h

@@ -3,12 +3,14 @@
 
 #include <sys/types.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct thread_map_data {
 	pid_t    pid;
 };
 
 struct thread_map {
+	atomic_t refcnt;
 	int nr;
 	struct thread_map_data map[];
 };
@@ -19,11 +21,12 @@ struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 
+struct thread_map *thread_map__get(struct thread_map *map);
+void thread_map__put(struct thread_map *map);
+
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
-void thread_map__delete(struct thread_map *threads);
-
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)