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

Author: torvalds

tools/lib/perf/evlist.c

@@ -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

@@ -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

@@ -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

@@ -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

@@ -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) {
@@ -3358,16 +3362,22 @@ 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)
@@ -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;
 

tools/perf/builtin-script.c

@@ -445,6 +445,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	struct perf_event_attr *attr = &evsel->core.attr;
 	bool allow_user_set;
 
+	if (evsel__is_dummy_event(evsel))
+		return 0;
+
 	if (perf_header__has_feat(&session->header, HEADER_STAT))
 		return 0;
 
@@ -566,6 +569,8 @@ static struct evsel *find_first_output_type(struct evlist *evlist,
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
+		if (evsel__is_dummy_event(evsel))
+			continue;
 		if (output_type(evsel->core.attr.type) == (int)type)
 			return evsel;
 	}

tools/perf/builtin-stat.c

@@ -1932,6 +1932,9 @@ static int add_default_attributes(void)
 		free(str);
 	}
 
+	if (!stat_config.topdown_level)
+		stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
+
 	if (!evsel_list->core.nr_entries) {
 		if (target__has_cpu(&target))
 			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
@@ -1948,8 +1951,6 @@ static int add_default_attributes(void)
 		}
 		if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
 			return -1;
-
-		stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
 		/* Platform specific attrs */
 		if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0)
 			return -1;

tools/perf/dlfilters/dlfilter-show-cycles.c

@@ -98,9 +98,9 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo
 static void print_vals(__u64 cycles, __u64 delta)
 {
 	if (delta)
-		printf("%10llu %10llu ", cycles, delta);
+		printf("%10llu %10llu ", (unsigned long long)cycles, (unsigned long long)delta);
 	else
-		printf("%10llu %10s ", cycles, "");
+		printf("%10llu %10s ", (unsigned long long)cycles, "");
 }
 
 int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)

tools/perf/util/affinity.c

@@ -49,8 +49,14 @@ void affinity__set(struct affinity *a, int cpu)
 {
 	int cpu_set_size = get_cpu_set_size();
 
-	if (cpu == -1)
+	/*
+	 * Return:
+	 * - if cpu is -1
+	 * - restrict out of bound access to sched_cpus
+	 */
+	if (cpu == -1 || ((cpu >= (cpu_set_size * 8))))
 		return;
+
 	a->changed = true;
 	set_bit(cpu, a->sched_cpus);
 	/*

tools/perf/util/genelf.c

@@ -30,10 +30,6 @@
 
 #define BUILD_ID_URANDOM /* different uuid for each run */
 
-// FIXME, remove this and fix the deprecation warnings before its removed and
-// We'll break for good here...
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
 #ifdef HAVE_LIBCRYPTO_SUPPORT
 
 #define BUILD_ID_MD5
@@ -45,6 +41,7 @@
 #endif
 
 #ifdef BUILD_ID_MD5
+#include <openssl/evp.h>
 #include <openssl/md5.h>
 #endif
 #endif
@@ -142,15 +139,20 @@ gen_build_id(struct buildid_note *note,
 static void
 gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
 {
-	MD5_CTX context;
+	EVP_MD_CTX *mdctx;
 
 	if (sizeof(note->build_id) < 16)
 		errx(1, "build_id too small for MD5");
 
-	MD5_Init(&context);
-	MD5_Update(&context, &load_addr, sizeof(load_addr));
-	MD5_Update(&context, code, csize);
-	MD5_Final((unsigned char *)note->build_id, &context);
+	mdctx = EVP_MD_CTX_new();
+	if (!mdctx)
+		errx(2, "failed to create EVP_MD_CTX");
+
+	EVP_DigestInit_ex(mdctx, EVP_md5(), NULL);
+	EVP_DigestUpdate(mdctx, &load_addr, sizeof(load_addr));
+	EVP_DigestUpdate(mdctx, code, csize);
+	EVP_DigestFinal_ex(mdctx, (unsigned char *)note->build_id, NULL);
+	EVP_MD_CTX_free(mdctx);
 }
 #endif