Commit d8a450a8 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'perf-tools-fixes-for-v6.0-2022-09-08' of... 

Merge tag 'perf-tools-fixes-for-v6.0-2022-09-08' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix per-thread mmaps for multi-threaded targets, noticed with
   'perf top --pid' with multithreaded targets

 - Fix synthesis failure warnings in 'perf record'

 - Fix L2 Topdown metrics disappearance for raw events in 'perf stat'

 - Fix out of bound access in some CPU masks

 - Fix segfault if there is no CPU PMU table and a metric is sought,
   noticed when building with NO_JEVENTS=1

 - Skip dummy event attr check in 'perf script' fixing nonsensical
   warning about UREGS attribute not set, as 'dummy' events have no
   samples

 - Fix 'iregs' field handling with dummy events on hybrid systems in
   'perf script'

 - Prevent potential memory leak in c2c_he_zalloc() in 'perf c2c'

 - Don't install data files with x permissions

 - Fix types for print format in dlfilter-show-cycles

 - Switch deprecated openssl MD5_* functions to new EVP API in 'genelf'

 - Remove redundant word 'contention' in 'perf lock' help message

* tag 'perf-tools-fixes-for-v6.0-2022-09-08' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf record: Fix synthesis failure warnings
  perf tools: Don't install data files with x permissions
  perf script: Fix Cannot print 'iregs' field for hybrid systems
  perf lock: Remove redundant word 'contention' in help message
  perf dlfilter dlfilter-show-cycles: Fix types for print format
  libperf evlist: Fix per-thread mmaps for multi-threaded targets
  perf c2c: Prevent potential memory leak in c2c_he_zalloc()
  perf genelf: Switch deprecated openssl MD5_* functions to new EVP API
  tools/perf: Fix out of bound access to cpu mask array
  perf affinity: Fix out of bound access to "sched_cpus" mask
  perf stat: Fix L2 Topdown metrics disappear for raw events
  perf script: Skip dummy event attr check
  perf metric: Return early if no CPU PMU table exists
parents 460a75a6 faf59ec8

tools/lib/perf/evlist.c

+50 −0
Original line number Diff line number Diff line
@@ -486,6 +486,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, 
			if (ops->idx)

				ops->idx(evlist, evsel, mp, idx);



			pr_debug("idx %d: mmapping fd %d\n", idx, *output);

			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)

				return -1;
@@ -494,6 +495,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, 
			if (!idx)

				perf_evlist__set_mmap_first(evlist, map, overwrite);

		} else {

			pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output);

			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)

				return -1;
@@ -519,6 +521,48 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, 
	return 0;

}



static int

mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,

		struct perf_mmap_param *mp)

{

	int nr_threads = perf_thread_map__nr(evlist->threads);

	int nr_cpus    = perf_cpu_map__nr(evlist->all_cpus);

	int cpu, thread, idx = 0;

	int nr_mmaps = 0;



	pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n",

		 __func__, nr_cpus, nr_threads);



	/* per-thread mmaps */

	for (thread = 0; thread < nr_threads; thread++, idx++) {

		int output = -1;

		int output_overwrite = -1;



		if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output,

				   &output_overwrite, &nr_mmaps))

			goto out_unmap;

	}



	/* system-wide mmaps i.e. per-cpu */

	for (cpu = 1; cpu < nr_cpus; cpu++, idx++) {

		int output = -1;

		int output_overwrite = -1;



		if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &output,

				   &output_overwrite, &nr_mmaps))

			goto out_unmap;

	}



	if (nr_mmaps != evlist->nr_mmaps)

		pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps);



	return 0;



out_unmap:

	perf_evlist__munmap(evlist);

	return -1;

}



static int

mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,

	     struct perf_mmap_param *mp)
@@ -528,6 +572,8 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, 
	int nr_mmaps = 0;

	int cpu, thread;



	pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads);



	for (cpu = 0; cpu < nr_cpus; cpu++) {

		int output = -1;

		int output_overwrite = -1;
@@ -569,6 +615,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, 
			  struct perf_evlist_mmap_ops *ops,

			  struct perf_mmap_param *mp)

{

	const struct perf_cpu_map *cpus = evlist->all_cpus;

	struct perf_evsel *evsel;



	if (!ops || !ops->get || !ops->mmap)
@@ -588,6 +635,9 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, 
	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)

		return -ENOMEM;



	if (perf_cpu_map__empty(cpus))

		return mmap_per_thread(evlist, ops, mp);



	return mmap_per_cpu(evlist, ops, mp);

}

tools/perf/Makefile.perf

+12 −12
Original line number Diff line number Diff line
@@ -954,11 +954,11 @@ ifndef NO_LIBBPF 
	$(call QUIET_INSTALL, bpf-headers) \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \

		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \

		$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'

		$(INSTALL) include/bpf/*.h -m 644 -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \

		$(INSTALL) include/bpf/linux/*.h -m 644 -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'

	$(call QUIET_INSTALL, bpf-examples) \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \

		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'

		$(INSTALL) examples/bpf/*.c -m 644 -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'

endif

	$(call QUIET_INSTALL, perf-archive) \

		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -967,13 +967,13 @@ endif 
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)'

		$(INSTALL) trace/strace/groups/* -m 644 -t '$(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'; \

		$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \

		$(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \

		$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \

		$(INSTALL) scripts/perl/*.pl -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \

		$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'

endif
@@ -990,23 +990,23 @@ endif 
		$(INSTALL) $(DLFILTERS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/dlfilters';

	$(call QUIET_INSTALL, perf_completion-script) \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \

		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'

		$(INSTALL) perf-completion.sh -m 644 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'

	$(call QUIET_INSTALL, perf-tip) \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \

		$(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'

		$(INSTALL) Documentation/tips.txt -m 644 -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'



install-tests: all install-gtk

	$(call QUIET_INSTALL, tests) \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \

		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \

		$(INSTALL) tests/attr.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \

		$(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \

		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \

		$(INSTALL) tests/attr/* -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \

		$(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \

		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \

		$(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \

		$(INSTALL) tests/shell/lib/*.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'

		$(INSTALL) tests/shell/lib/*.sh -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \

		$(INSTALL) tests/shell/lib/*.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'



install-bin: install-tools install-tests install-traceevent-plugins

tools/perf/builtin-c2c.c

+9 −3
Original line number Diff line number Diff line
@@ -146,15 +146,15 @@ static void *c2c_he_zalloc(size_t size) 


	c2c_he->cpuset = bitmap_zalloc(c2c.cpus_cnt);

	if (!c2c_he->cpuset)

		return NULL;

		goto out_free;



	c2c_he->nodeset = bitmap_zalloc(c2c.nodes_cnt);

	if (!c2c_he->nodeset)

		return NULL;

		goto out_free;



	c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));

	if (!c2c_he->node_stats)

		return NULL;

		goto out_free;



	init_stats(&c2c_he->cstats.lcl_hitm);

	init_stats(&c2c_he->cstats.rmt_hitm);
@@ -163,6 +163,12 @@ static void *c2c_he_zalloc(size_t size) 
	init_stats(&c2c_he->cstats.load);



	return &c2c_he->he;



out_free:

	free(c2c_he->nodeset);

	free(c2c_he->cpuset);

	free(c2c_he);

	return NULL;

}



static void c2c_he_free(void *he)

tools/perf/builtin-lock.c

+1 −2
Original line number Diff line number Diff line
@@ -1874,8 +1874,7 @@ int cmd_lock(int argc, const char **argv) 
		NULL

	};

	const char *const lock_subcommands[] = { "record", "report", "script",

						 "info", "contention",

						 "contention", NULL };

						 "info", "contention", NULL };

	const char *lock_usage[] = {

		NULL,

		NULL

tools/perf/builtin-record.c

+26 −8
Original line number Diff line number Diff line
@@ -1906,14 +1906,18 @@ static int record__synthesize(struct record *rec, bool tail) 


	err = perf_event__synthesize_bpf_events(session, process_synthesized_event,

						machine, opts);

	if (err < 0)

	if (err < 0) {

		pr_warning("Couldn't synthesize bpf events.\n");

		err = 0;

	}



	if (rec->opts.synth & PERF_SYNTH_CGROUP) {

		err = perf_event__synthesize_cgroups(tool, process_synthesized_event,

						     machine);

		if (err < 0)

		if (err < 0) {

			pr_warning("Couldn't synthesize cgroup events.\n");

			err = 0;

		}

	}



	if (rec->opts.nr_threads_synthesize > 1) {
@@ -3358,18 +3362,24 @@ static struct option __record_options[] = { 


struct option *record_options = __record_options;



static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)

static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)

{

	struct perf_cpu cpu;

	int idx;



	if (cpu_map__is_dummy(cpus))

		return;

		return 0;



	perf_cpu_map__for_each_cpu(cpu, idx, cpus)

	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {

		/* Return ENODEV is input cpu is greater than max cpu */

		if ((unsigned long)cpu.cpu > mask->nbits)

			return -ENODEV;

		set_bit(cpu.cpu, mask->bits);

	}



	return 0;

}



static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const char *mask_spec)

{

	struct perf_cpu_map *cpus;
@@ -3379,7 +3389,9 @@ static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const cha 
		return -ENOMEM;



	bitmap_zero(mask->bits, mask->nbits);

	record__mmap_cpu_mask_init(mask, cpus);

	if (record__mmap_cpu_mask_init(mask, cpus))

		return -ENODEV;



	perf_cpu_map__put(cpus);



	return 0;
@@ -3461,7 +3473,12 @@ static int record__init_thread_masks_spec(struct record *rec, struct perf_cpu_ma 
		pr_err("Failed to allocate CPUs mask\n");

		return ret;

	}

	record__mmap_cpu_mask_init(&cpus_mask, cpus);



	ret = record__mmap_cpu_mask_init(&cpus_mask, cpus);

	if (ret) {

		pr_err("Failed to init cpu mask\n");

		goto out_free_cpu_mask;

	}



	ret = record__thread_mask_alloc(&full_mask, cpu__max_cpu().cpu);

	if (ret) {
@@ -3702,7 +3719,8 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu 
	if (ret)

		return ret;



	record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);

	if (record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus))

		return -ENODEV;



	rec->nr_threads = 1;