Merge tag 'perf-tools-fixes-for-v5.14-2021-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Skip invalid hybrid PMU on hybrid systems when the atom (little) CPUs
   are offlined.

 - Fix 'perf test' problems related to the recently added hybrid
   (BIG/little) code.

 - Split ARM's coresight (hw tracing) decode by aux records to avoid
   fatal decoding errors.

 - Fix add event failure in 'perf probe' when running 32-bit perf in a
   64-bit kernel.

 - Fix 'perf sched record' failure when CONFIG_SCHEDSTATS is not set.

 - Fix memory and refcount leaks detected by ASAn when running 'perf
   test', should be clean of warnings now.

 - Remove broken definition of __LITTLE_ENDIAN from tools'
   linux/kconfig.h, which was breaking the build in some systems.

 - Cast PTHREAD_STACK_MIN to int as it may turn into 'long
   sysconf(__SC_THREAD_STACK_MIN_VALUE), breaking the build in some
   systems.

 - Fix libperf build error with LIBPFM4=1.

 - Sync UAPI files changed by the memfd_secret new syscall.

* tag 'perf-tools-fixes-for-v5.14-2021-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (35 commits)
  perf sched: Fix record failure when CONFIG_SCHEDSTATS is not set
  perf probe: Fix add event failure when running 32-bit perf in a 64-bit kernel
  perf data: Close all files in close_dir()
  perf probe-file: Delete namelist in del_events() on the error path
  perf test bpf: Free obj_buf
  perf trace: Free strings in trace__parse_events_option()
  perf trace: Free syscall tp fields in evsel->priv
  perf trace: Free syscall->arg_fmt
  perf trace: Free malloc'd trace fields on exit
  perf lzma: Close lzma stream on exit
  perf script: Fix memory 'threads' and 'cpus' leaks on exit
  perf script: Release zstd data
  perf session: Cleanup trace_event
  perf inject: Close inject.output on exit
  perf report: Free generated help strings for sort option
  perf env: Fix memory leak of cpu_pmu_caps
  perf test maps__merge_in: Fix memory leak of maps
  perf dso: Fix memory leak in dso__new_map()
  perf test event_update: Fix memory leak of unit
  perf test event_update: Fix memory leak of evlist
  ...

Author: torvalds

tools/arch/arm64/include/uapi/asm/unistd.h

@@ -20,5 +20,6 @@
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
 #define __ARCH_WANT_SYS_CLONE3
+#define __ARCH_WANT_MEMFD_SECRET
 
 #include <asm-generic/unistd.h>

tools/include/linux/kconfig.h

@@ -4,12 +4,6 @@
 
 /* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
 
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define __BIG_ENDIAN 4321
-#else
-#define __LITTLE_ENDIAN 1234
-#endif
-
 #define __ARG_PLACEHOLDER_1 0,
 #define __take_second_arg(__ignored, val, ...) val
 

tools/include/uapi/asm-generic/unistd.h

@@ -873,8 +873,13 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 #define __NR_landlock_restrict_self 446
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 
+#ifdef __ARCH_WANT_MEMFD_SECRET
+#define __NR_memfd_secret 447
+__SYSCALL(__NR_memfd_secret, sys_memfd_secret)
+#endif
+
 #undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 448
 
 /*
  * 32 bit systems traditionally used different

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -368,6 +368,7 @@
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
+447	common	memfd_secret		sys_memfd_secret
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

tools/perf/builtin-inject.c

@@ -361,9 +361,10 @@ static struct dso *findnew_dso(int pid, int tid, const char *filename,
 		dso = machine__findnew_dso_id(machine, filename, id);
 	}
 
-	if (dso)
+	if (dso) {
+		nsinfo__put(dso->nsinfo);
 		dso->nsinfo = nsi;
-	else
+	} else
 		nsinfo__put(nsi);
 
 	thread__put(thread);
@@ -992,8 +993,10 @@ int cmd_inject(int argc, const char **argv)
 
 	data.path = inject.input_name;
 	inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
-	if (IS_ERR(inject.session))
-		return PTR_ERR(inject.session);
+	if (IS_ERR(inject.session)) {
+		ret = PTR_ERR(inject.session);
+		goto out_close_output;
+	}
 
 	if (zstd_init(&(inject.session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed.\n");
@@ -1035,6 +1038,8 @@ int cmd_inject(int argc, const char **argv)
 out_delete:
 	zstd_fini(&(inject.session->zstd_data));
 	perf_session__delete(inject.session);
+out_close_output:
+	perf_data__close(&inject.output);
 	free(inject.itrace_synth_opts.vm_tm_corr_args);
 	return ret;
 }

tools/perf/builtin-report.c

@@ -1175,6 +1175,8 @@ int cmd_report(int argc, const char **argv)
 		.annotation_opts	 = annotation__default_options,
 		.skip_empty		 = true,
 	};
+	char *sort_order_help = sort_help("sort by key(s):");
+	char *field_order_help = sort_help("output field(s): overhead period sample ");
 	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -1209,9 +1211,9 @@ int cmd_report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "header-only", &report.header_only,
 		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   sort_help("sort by key(s):")),
+		   sort_order_help),
 	OPT_STRING('F', "fields", &field_order, "key[,keys...]",
-		   sort_help("output field(s): overhead period sample ")),
+		   field_order_help),
 	OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -1344,11 +1346,11 @@ int cmd_report(int argc, const char **argv)
 	char sort_tmp[128];
 
 	if (ret < 0)
-		return ret;
+		goto exit;
 
 	ret = perf_config(report__config, &report);
 	if (ret)
-		return ret;
+		goto exit;
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 	if (argc) {
@@ -1362,8 +1364,10 @@ int cmd_report(int argc, const char **argv)
 		report.symbol_filter_str = argv[0];
 	}
 
-	if (annotate_check_args(&report.annotation_opts) < 0)
-		return -EINVAL;
+	if (annotate_check_args(&report.annotation_opts) < 0) {
+		ret = -EINVAL;
+		goto exit;
+	}
 
 	if (report.mmaps_mode)
 		report.tasks_mode = true;
@@ -1377,12 +1381,14 @@ int cmd_report(int argc, const char **argv)
 	if (symbol_conf.vmlinux_name &&
 	    access(symbol_conf.vmlinux_name, R_OK)) {
 		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 	if (symbol_conf.kallsyms_name &&
 	    access(symbol_conf.kallsyms_name, R_OK)) {
 		pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	if (report.inverted_callchain)
@@ -1406,12 +1412,14 @@ int cmd_report(int argc, const char **argv)
 
 repeat:
 	session = perf_session__new(&data, false, &report.tool);
-	if (IS_ERR(session))
-		return PTR_ERR(session);
+	if (IS_ERR(session)) {
+		ret = PTR_ERR(session);
+		goto exit;
+	}
 
 	ret = evswitch__init(&report.evswitch, session->evlist, stderr);
 	if (ret)
-		return ret;
+		goto exit;
 
 	if (zstd_init(&(session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
@@ -1646,5 +1654,8 @@ int cmd_report(int argc, const char **argv)
 
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
+exit:
+	free(sort_order_help);
+	free(field_order_help);
 	return ret;
 }

tools/perf/builtin-sched.c

@@ -670,7 +670,7 @@ static void create_tasks(struct perf_sched *sched)
 	err = pthread_attr_init(&attr);
 	BUG_ON(err);
 	err = pthread_attr_setstacksize(&attr,
-			(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
+			(size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN));
 	BUG_ON(err);
 	err = pthread_mutex_lock(&sched->start_work_mutex);
 	BUG_ON(err);
@@ -3335,6 +3335,16 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options
 	sort_dimension__add("pid", &sched->cmp_pid);
 }
 
+static bool schedstat_events_exposed(void)
+{
+	/*
+	 * Select "sched:sched_stat_wait" event to check
+	 * whether schedstat tracepoints are exposed.
+	 */
+	return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ?
+		false : true;
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
@@ -3346,21 +3356,33 @@ static int __cmd_record(int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 		"-e", "sched:sched_switch",
-		"-e", "sched:sched_stat_wait",
-		"-e", "sched:sched_stat_sleep",
-		"-e", "sched:sched_stat_iowait",
 		"-e", "sched:sched_stat_runtime",
 		"-e", "sched:sched_process_fork",
 		"-e", "sched:sched_wakeup_new",
 		"-e", "sched:sched_migrate_task",
 	};
+
+	/*
+	 * The tracepoints trace_sched_stat_{wait, sleep, iowait}
+	 * are not exposed to user if CONFIG_SCHEDSTATS is not set,
+	 * to prevent "perf sched record" execution failure, determine
+	 * whether to record schedstat events according to actual situation.
+	 */
+	const char * const schedstat_args[] = {
+		"-e", "sched:sched_stat_wait",
+		"-e", "sched:sched_stat_sleep",
+		"-e", "sched:sched_stat_iowait",
+	};
+	unsigned int schedstat_argc = schedstat_events_exposed() ?
+		ARRAY_SIZE(schedstat_args) : 0;
+
 	struct tep_event *waking_event;
 
 	/*
 	 * +2 for either "-e", "sched:sched_wakeup" or
 	 * "-e", "sched:sched_waking"
 	 */
-	rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1;
+	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -3376,6 +3398,9 @@ static int __cmd_record(int argc, const char **argv)
 	else
 		rec_argv[i++] = strdup("sched:sched_wakeup");
 
+	for (j = 0; j < schedstat_argc; j++)
+		rec_argv[i++] = strdup(schedstat_args[j]);
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 

tools/perf/builtin-script.c

@@ -2601,6 +2601,12 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script)
 	}
 }
 
+static void perf_script__exit(struct perf_script *script)
+{
+	perf_thread_map__put(script->threads);
+	perf_cpu_map__put(script->cpus);
+}
+
 static int __cmd_script(struct perf_script *script)
 {
 	int ret;
@@ -4143,8 +4149,10 @@ int cmd_script(int argc, const char **argv)
 		zfree(&script.ptime_range);
 	}
 
+	zstd_fini(&(session->zstd_data));
 	evlist__free_stats(session->evlist);
 	perf_session__delete(session);
+	perf_script__exit(&script);
 
 	if (script_started)
 		cleanup_scripting();

tools/perf/builtin-stat.c

@@ -2445,9 +2445,6 @@ int cmd_stat(int argc, const char **argv)
 
 	evlist__check_cpu_maps(evsel_list);
 
-	if (perf_pmu__has_hybrid())
-		stat_config.no_merge = true;
-
 	/*
 	 * Initialize thread_map with comm names,
 	 * so we could print it out on output.

tools/perf/builtin-trace.c

@@ -2266,6 +2266,14 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam
 	return augmented_args;
 }
 
+static void syscall__exit(struct syscall *sc)
+{
+	if (!sc)
+		return;
+
+	free(sc->arg_fmt);
+}
+
 static int trace__sys_enter(struct trace *trace, struct evsel *evsel,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
@@ -3095,6 +3103,21 @@ static struct evsel *evsel__new_pgfault(u64 config)
 	return evsel;
 }
 
+static void evlist__free_syscall_tp_fields(struct evlist *evlist)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		struct evsel_trace *et = evsel->priv;
+
+		if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls"))
+			continue;
+
+		free(et->fmt);
+		free(et);
+	}
+}
+
 static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
 {
 	const u32 type = event->header.type;
@@ -4130,7 +4153,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 out_delete_evlist:
 	trace__symbols__exit(trace);
-
+	evlist__free_syscall_tp_fields(evlist);
 	evlist__delete(evlist);
 	cgroup__put(trace->cgroup);
 	trace->evlist = NULL;
@@ -4636,6 +4659,9 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 		err = parse_events_option(&o, lists[0], 0);
 	}
 out:
+	free(strace_groups_dir);
+	free(lists[0]);
+	free(lists[1]);
 	if (sep)
 		*sep = ',';
 
@@ -4701,6 +4727,21 @@ static int trace__config(const char *var, const char *value, void *arg)
 	return err;
 }
 
+static void trace__exit(struct trace *trace)
+{
+	int i;
+
+	strlist__delete(trace->ev_qualifier);
+	free(trace->ev_qualifier_ids.entries);
+	if (trace->syscalls.table) {
+		for (i = 0; i <= trace->sctbl->syscalls.max_id; i++)
+			syscall__exit(&trace->syscalls.table[i]);
+		free(trace->syscalls.table);
+	}
+	syscalltbl__delete(trace->sctbl);
+	zfree(&trace->perfconfig_events);
+}
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -5135,6 +5176,6 @@ int cmd_trace(int argc, const char **argv)
 	if (output_name != NULL)
 		fclose(trace.output);
 out:
-	zfree(&trace.perfconfig_events);
+	trace__exit(&trace);
 	return err;
 }

tools/perf/tests/bpf.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/epoll.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -276,6 +277,7 @@ static int __test__bpf(int idx)
 	}
 
 out:
+	free(obj_buf);
 	bpf__clear();
 	return ret;
 }