Commit 6497bbc3 authored by Ingo Molnar's avatar Ingo Molnar
Browse files

Merge tag 'perf-urgent-for-mingo-4.17-20180531' of... 

Merge tag 'perf-urgent-for-mingo-4.17-20180531' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

 into perf/urgent

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

- Fix 'perf test Session topology' segfault on s390 (Thomas Richter)

- Fix NULL return handling in bpf__prepare_load() (YueHaibing)

- Fix indexing on Coresight ETM packet queue decoder (Mathieu Poirier)

- Fix perf.data format description of NRCPUS header (Arnaldo Carvalho de Melo)

- Update perf.data documentation section on cpu topology

- Handle uncore event aliases in small groups properly (Kan Liang)

- Add missing perf_sample.addr into python sample dictionary (Leo Yan)

Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parents 786b71f5 18a70574

tools/perf/Documentation/perf.data-file-format.txt

+9 −1
Original line number Diff line number Diff line
@@ -111,8 +111,8 @@ A perf_header_string with the CPU architecture (uname -m) 
A structure defining the number of CPUs.



struct nr_cpus {

       uint32_t nr_cpus_online;

       uint32_t nr_cpus_available; /* CPUs not yet onlined */

       uint32_t nr_cpus_online;

};



	HEADER_CPUDESC = 8,
@@ -153,10 +153,18 @@ struct { 
	HEADER_CPU_TOPOLOGY = 13,



String lists defining the core and CPU threads topology.

The string lists are followed by a variable length array

which contains core_id and socket_id of each cpu.

The number of entries can be determined by the size of the

section minus the sizes of both string lists.



struct {

       struct perf_header_string_list cores; /* Variable length */

       struct perf_header_string_list threads; /* Variable length */

       struct {

	      uint32_t core_id;

	      uint32_t socket_id;

       } cpus[nr]; /* Variable length records */

};



Example:

tools/perf/tests/topology.c

+24 −6
Original line number Diff line number Diff line
@@ -70,6 +70,27 @@ static int check_cpu_topology(char *path, struct cpu_map *map) 
	session = perf_session__new(&data, false, NULL);

	TEST_ASSERT_VAL("can't get session", session);



	/* On platforms with large numbers of CPUs process_cpu_topology()

	 * might issue an error while reading the perf.data file section

	 * HEADER_CPU_TOPOLOGY and the cpu_topology_map pointed to by member

	 * cpu is a NULL pointer.

	 * Example: On s390

	 *   CPU 0 is on core_id 0 and physical_package_id 6

	 *   CPU 1 is on core_id 1 and physical_package_id 3

	 *

	 *   Core_id and physical_package_id are platform and architecture

	 *   dependend and might have higher numbers than the CPU id.

	 *   This actually depends on the configuration.

	 *

	 *  In this case process_cpu_topology() prints error message:

	 *  "socket_id number is too big. You may need to upgrade the

	 *  perf tool."

	 *

	 *  This is the reason why this test might be skipped.

	 */

	if (!session->header.env.cpu)

		return TEST_SKIP;



	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {

		if (!cpu_map__has(map, i))

			continue;
@@ -95,7 +116,7 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe 
{

	char path[PATH_MAX];

	struct cpu_map *map;

	int ret = -1;

	int ret = TEST_FAIL;



	TEST_ASSERT_VAL("can't get templ file", !get_temp(path));
@@ -110,12 +131,9 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe 
		goto free_path;

	}



	if (check_cpu_topology(path, map))

		goto free_map;

	ret = 0;



free_map:

	ret = check_cpu_topology(path, map);

	cpu_map__put(map);



free_path:

	unlink(path);

	return ret;

tools/perf/util/bpf-loader.c

+3 −3
Original line number Diff line number Diff line
@@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) 
	}



	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);

	if (IS_ERR(obj)) {

	if (IS_ERR_OR_NULL(obj)) {

		pr_debug("bpf: failed to load buffer\n");

		return ERR_PTR(-EINVAL);

	}
@@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) 
			pr_debug("bpf: successfull builtin compilation\n");

		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);



		if (!IS_ERR(obj) && llvm_param.dump_obj)

		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)

			llvm__dump_obj(filename, obj_buf, obj_buf_sz);



		free(obj_buf);

	} else

		obj = bpf_object__open(filename);



	if (IS_ERR(obj)) {

	if (IS_ERR_OR_NULL(obj)) {

		pr_debug("bpf: failed to load %s\n", filename);

		return obj;

	}

tools/perf/util/cs-etm-decoder/cs-etm-decoder.c

+10 −2
Original line number Diff line number Diff line
@@ -96,11 +96,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, 
	/* Nothing to do, might as well just return */

	if (decoder->packet_count == 0)

		return 0;

	/*

	 * The queueing process in function cs_etm_decoder__buffer_packet()

	 * increments the tail *before* using it.  This is somewhat counter

	 * intuitive but it has the advantage of centralizing tail management

	 * at a single location.  Because of that we need to follow the same

	 * heuristic with the head, i.e we increment it before using its

	 * value.  Otherwise the first element of the packet queue is not

	 * used.

	 */

	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);



	*packet = decoder->packet_buffer[decoder->head];



	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);



	decoder->packet_count--;



	return 1;

tools/perf/util/evsel.h

+1 −0
Original line number Diff line number Diff line
@@ -127,6 +127,7 @@ struct perf_evsel { 
	bool			precise_max;

	bool			ignore_missing_thread;

	bool			forced_leader;

	bool			use_uncore_alias;

	/* parse modifier helper */

	int			exclude_GH;

	int			nr_members;

CRA Git | Maintained and supported by SUSTech CRA and CCSE