Merge tag 'perf-tools-fixes-for-v5.16-2021-12-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

torvalds · torvalds · commit 2a987e65025e · 2021-12-07T15:36:45.000-08:00
Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix SMT detection fast read path on sysfs.

 - Fix memory leaks when processing feature headers in perf.data files.

 - Fix 'Simple expression parser' 'perf test' on arch without CPU die
   topology info, such as s/390.

 - Fix building perf with BUILD_BPF_SKEL=1.

 - Fix 'perf bench' by reverting "perf bench: Fix two memory leaks
   detected with ASan".

 - Fix itrace space allowed for new attributes in 'perf script'.

 - Fix the build feature detection fast path, that was always failing on
   systems with python3 development packages, speeding up the build.

 - Reset shadow counts before loading, fixing metrics using
   duration_time.

 - Sync more kernel headers changed by the new futex_waitv syscall: s390
   and powerpc.

* tag 'perf-tools-fixes-for-v5.16-2021-12-07' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf bpf_skel: Do not use typedef to avoid error on old clang
  perf bpf: Fix building perf with BUILD_BPF_SKEL=1 by default in more distros
  perf header: Fix memory leaks when processing feature headers
  perf test: Reset shadow counts before loading
  perf test: Fix 'Simple expression parser' test on arch without CPU die topology info
  tools build: Remove needless libpython-version feature check that breaks test-all fast path
  perf tools: Fix SMT detection fast read path
  tools headers UAPI: Sync powerpc syscall table file changed by new futex_waitv syscall
  perf inject: Fix itrace space allowed for new attributes
  tools headers UAPI: Sync s390 syscall table file changed by new futex_waitv syscall
  Revert "perf bench: Fix two memory leaks detected with ASan"
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
@@ -48,7 +48,6 @@ FEATURE_TESTS_BASIC :=                  \
         numa_num_possible_cpus          \
         libperl                         \
         libpython                       \
-        libpython-version               \
         libslang                        \
         libslang-include-subdir         \
         libtraceevent                   \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
@@ -32,7 +32,6 @@ FILES=                                          \
          test-numa_num_possible_cpus.bin        \
          test-libperl.bin                       \
          test-libpython.bin                     \
-         test-libpython-version.bin             \
          test-libslang.bin                      \
          test-libslang-include-subdir.bin       \
          test-libtraceevent.bin                 \
@@ -227,9 +226,6 @@ $(OUTPUT)test-libperl.bin:
 $(OUTPUT)test-libpython.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
-$(OUTPUT)test-libpython-version.bin:
-	$(BUILD)
-
 $(OUTPUT)test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
@@ -14,10 +14,6 @@
 # include "test-libpython.c"
 #undef main
 
-#define main main_test_libpython_version
-# include "test-libpython-version.c"
-#undef main
-
 #define main main_test_libperl
 # include "test-libperl.c"
 #undef main
@@ -177,7 +173,6 @@
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
-	main_test_libpython_version();
 	main_test_libperl();
 	main_test_hello();
 	main_test_libelf();
diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
@@ -271,8 +271,6 @@ endif
 
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -528,3 +528,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
+449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
@@ -223,8 +223,6 @@ static unsigned int group(pthread_t *pth,
 		snd_ctx->out_fds[i] = fds[1];
 		if (!thread_mode)
 			close(fds[0]);
-
-		free(ctx);
 	}
 
 	/* Now we have all the fds, fork the senders */
@@ -241,8 +239,6 @@ static unsigned int group(pthread_t *pth,
 		for (i = 0; i < num_fds; i++)
 			close(snd_ctx->out_fds[i]);
 
-	free(snd_ctx);
-
 	/* Return number of children to reap */
 	return num_fds * 2;
 }
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
@@ -820,7 +820,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.ordered_events = true;
 		inject->tool.ordering_requires_timestamps = true;
 		/* Allow space in the header for new attributes */
-		output_data_offset = 4096;
+		output_data_offset = roundup(8192 + session->header.data_offset, 4096);
 		if (inject->strip)
 			strip_init(inject);
 	}
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
@@ -169,7 +169,9 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
 	TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies);
 	TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0);
-	TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
+
+	if (num_dies) // Some platforms do not have CPU die support, for example s390
+		TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
 
 	/*
 	 * Source count returns the number of events aggregating in a leader
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
@@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist,
 	struct evsel *evsel;
 	u64 count;
 
+	perf_stat__reset_shadow_stats();
 	evlist__for_each_entry(evlist, evsel) {
 		count = find_value(evsel->name, vals);
 		perf_stat__update_shadow_stats(evsel, count, 0, st);
diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h
diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
@@ -1,14 +1,23 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bperf.h"
 #include "bperf_u.h"
 
-reading_map diff_readings SEC(".maps");
-reading_map accum_readings SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} diff_readings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} accum_readings SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
@@ -1,10 +1,8 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bperf.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -13,8 +11,19 @@ struct {
 	__uint(map_flags, BPF_F_PRESERVE_ELEMS);
 } events SEC(".maps");
 
-reading_map prev_readings SEC(".maps");
-reading_map diff_readings SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} prev_readings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} diff_readings SEC(".maps");
 
 SEC("raw_tp/sched_switch")
 int BPF_PROG(on_switch)
diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2020 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
@@ -2321,6 +2321,7 @@ static int perf_header__read_build_ids(struct perf_header *header,
 #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \
 static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \
 {\
+	free(ff->ph->env.__feat_env);		     \
 	ff->ph->env.__feat_env = do_read_string(ff); \
 	return ff->ph->env.__feat_env ? 0 : -ENOMEM; \
 }
@@ -4124,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session,
 	struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event;
 	int type = fe->header.type;
 	u64 feat = fe->feat_id;
+	int ret = 0;
 
 	if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
@@ -4141,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session,
 	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
-	if (feat_ops[feat].process(&ff, NULL))
-		return -1;
+	if (feat_ops[feat].process(&ff, NULL)) {
+		ret = -1;
+		goto out;
+	}
 
 	if (!feat_ops[feat].print || !tool->show_feat_hdr)
-		return 0;
+		goto out;
 
 	if (!feat_ops[feat].full_only ||
 	    tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
@@ -4154,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session,
 		fprintf(stdout, "# %s info available, use -I to display\n",
 			feat_ops[feat].name);
 	}
-
-	return 0;
+out:
+	free_event_desc(ff.events);
+	return ret;
 }
 
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
@@ -15,7 +15,7 @@ int smt_on(void)
 	if (cached)
 		return cached_result;
 
-	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0)
+	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
 		goto done;
 
 	ncpu = sysconf(_SC_NPROCESSORS_CONF);

Original file line number	Diff line number	Diff line change
`@@ -820,7 +820,7 @@ static int __cmd_inject(struct perf_inject *inject)`
`820`	`820`	`inject->tool.ordered_events = true;`
`821`	`821`	`inject->tool.ordering_requires_timestamps = true;`
`822`	`822`	`/* Allow space in the header for new attributes */`
`823`		`- output_data_offset = 4096;`
	`823`	`+ output_data_offset = roundup(8192 + session->header.data_offset, 4096);`
`824`	`824`	`if (inject->strip)`
`825`	`825`	`strip_init(inject);`
`826`	`826`	`}`