mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 20:51:44 +00:00
1a270cb6b3
Add socket as a separate member so that it doesn't have to be packed into the int value. When the socket ID was larger than 8 bits the output appeared corrupted or incomplete. For example, here on ThunderX2 'perf stat' reports a socket of -1 and an invalid die number: ./perf stat -a --per-die The socket id number is too big. Performance counter stats for 'system wide': S-1-D255 128 687.99 msec cpu-clock # 57.240 CPUs utilized ... S36-D0 128 842.34 msec cpu-clock # 70.081 CPUs utilized ... And with --per-core there is an entry with an invalid core ID: ./perf stat record -a --per-core The socket id number is too big. Performance counter stats for 'system wide': S-1-D255-C65535 128 671.04 msec cpu-clock # 54.112 CPUs utilized ... S36-D0-C0 4 28.27 msec cpu-clock # 2.279 CPUs utilized ... This fixes the "Session topology" self test on ThunderX2. After this fix the output contains the correct socket and die IDs and no longer prints a warning about the size of the socket ID: ./perf stat --per-die -a Performance counter stats for 'system wide': S36-D0 128 169,869.39 msec cpu-clock # 127.501 CPUs utilized ... S3612-D0 128 169,733.05 msec cpu-clock # 127.398 CPUs utilized Signed-off-by: James Clark <james.clark@arm.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: John Garry <john.garry@huawei.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20201126141328.6509-10-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
186 lines
5.2 KiB
C
186 lines
5.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <string.h>
|
|
#include <stdlib.h>
|
|
#include <stdio.h>
|
|
#include <perf/cpumap.h>
|
|
#include "cpumap.h"
|
|
#include "tests.h"
|
|
#include "session.h"
|
|
#include "evlist.h"
|
|
#include "debug.h"
|
|
#include <linux/err.h>
|
|
|
|
#define TEMPL "/tmp/perf-test-XXXXXX"
|
|
#define DATA_SIZE 10
|
|
|
|
static int get_temp(char *path)
|
|
{
|
|
int fd;
|
|
|
|
strcpy(path, TEMPL);
|
|
|
|
fd = mkstemp(path);
|
|
if (fd < 0) {
|
|
perror("mkstemp failed");
|
|
return -1;
|
|
}
|
|
|
|
close(fd);
|
|
return 0;
|
|
}
|
|
|
|
static int session_write_header(char *path)
|
|
{
|
|
struct perf_session *session;
|
|
struct perf_data data = {
|
|
.path = path,
|
|
.mode = PERF_DATA_MODE_WRITE,
|
|
};
|
|
|
|
session = perf_session__new(&data, false, NULL);
|
|
TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
|
|
|
|
session->evlist = evlist__new_default();
|
|
TEST_ASSERT_VAL("can't get evlist", session->evlist);
|
|
|
|
perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
|
|
perf_header__set_feat(&session->header, HEADER_NRCPUS);
|
|
perf_header__set_feat(&session->header, HEADER_ARCH);
|
|
|
|
session->header.data_size += DATA_SIZE;
|
|
|
|
TEST_ASSERT_VAL("failed to write header",
|
|
!perf_session__write_header(session, session->evlist, data.file.fd, true));
|
|
|
|
perf_session__delete(session);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int check_cpu_topology(char *path, struct perf_cpu_map *map)
|
|
{
|
|
struct perf_session *session;
|
|
struct perf_data data = {
|
|
.path = path,
|
|
.mode = PERF_DATA_MODE_READ,
|
|
};
|
|
int i;
|
|
struct aggr_cpu_id id;
|
|
|
|
session = perf_session__new(&data, false, NULL);
|
|
TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
|
|
cpu__setup_cpunode_map();
|
|
|
|
/* 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. aarch64 and
|
|
* s390 always write this part of the header, even when the above
|
|
* condition is true (see do_core_id_test in header.c). So always
|
|
* run this test on those platforms.
|
|
*/
|
|
if (!session->header.env.cpu
|
|
&& strncmp(session->header.env.arch, "s390", 4)
|
|
&& strncmp(session->header.env.arch, "aarch64", 7))
|
|
return TEST_SKIP;
|
|
|
|
TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
|
|
|
|
for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
|
|
if (!cpu_map__has(map, i))
|
|
continue;
|
|
pr_debug("CPU %d, core %d, socket %d\n", i,
|
|
session->header.env.cpu[i].core_id,
|
|
session->header.env.cpu[i].socket_id);
|
|
}
|
|
|
|
// Test that core ID contains socket, die and core
|
|
for (i = 0; i < map->nr; i++) {
|
|
id = cpu_map__get_core(map, i, NULL);
|
|
TEST_ASSERT_VAL("Core map - Core ID doesn't match",
|
|
session->header.env.cpu[map->map[i]].core_id == cpu_map__id_to_cpu(id.id));
|
|
|
|
TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
|
|
session->header.env.cpu[map->map[i]].socket_id == id.socket);
|
|
|
|
TEST_ASSERT_VAL("Core map - Die ID doesn't match",
|
|
session->header.env.cpu[map->map[i]].die_id == cpu_map__id_to_die(id.id));
|
|
TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
|
|
}
|
|
|
|
// Test that die ID contains socket and die
|
|
for (i = 0; i < map->nr; i++) {
|
|
id = cpu_map__get_die(map, i, NULL);
|
|
TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
|
|
session->header.env.cpu[map->map[i]].socket_id == id.socket);
|
|
|
|
TEST_ASSERT_VAL("Die map - Die ID doesn't match",
|
|
session->header.env.cpu[map->map[i]].die_id ==
|
|
cpu_map__id_to_die(id.id << 16));
|
|
|
|
TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
|
|
}
|
|
|
|
// Test that socket ID contains only socket
|
|
for (i = 0; i < map->nr; i++) {
|
|
id = cpu_map__get_socket(map, i, NULL);
|
|
TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
|
|
session->header.env.cpu[map->map[i]].socket_id == id.socket);
|
|
|
|
TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
|
|
TEST_ASSERT_VAL("Socket map - ID is set", id.id == -1);
|
|
}
|
|
|
|
// Test that node ID contains only node
|
|
for (i = 0; i < map->nr; i++) {
|
|
id = cpu_map__get_node(map, i, NULL);
|
|
TEST_ASSERT_VAL("Node map - Node ID doesn't match",
|
|
cpu__get_node(map->map[i]) == id.node);
|
|
TEST_ASSERT_VAL("Node map - ID is set", id.id == -1);
|
|
TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
|
|
}
|
|
perf_session__delete(session);
|
|
|
|
return 0;
|
|
}
|
|
|
|
int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused)
|
|
{
|
|
char path[PATH_MAX];
|
|
struct perf_cpu_map *map;
|
|
int ret = TEST_FAIL;
|
|
|
|
TEST_ASSERT_VAL("can't get templ file", !get_temp(path));
|
|
|
|
pr_debug("templ file: %s\n", path);
|
|
|
|
if (session_write_header(path))
|
|
goto free_path;
|
|
|
|
map = perf_cpu_map__new(NULL);
|
|
if (map == NULL) {
|
|
pr_debug("failed to get system cpumap\n");
|
|
goto free_path;
|
|
}
|
|
|
|
ret = check_cpu_topology(path, map);
|
|
perf_cpu_map__put(map);
|
|
|
|
free_path:
|
|
unlink(path);
|
|
return ret;
|
|
}
|