linux/tools/perf/tests/topology.c
Ian Rogers 71bc3ac8e8 perf cpumap: Use perf_cpu_map__for_each_cpu when possible
Rather than manually iterating the CPU map, use
perf_cpu_map__for_each_cpu(). When possible tidy local variables.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Link: https://lore.kernel.org/r/20240202234057.2085863-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-03-21 10:41:28 -03:00

233 lines
7.0 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 "pmus.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, 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));
evlist__delete(session->evlist);
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;
struct perf_cpu cpu;
session = perf_session__new(&data, 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
* dependent 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;
/*
* In powerpc pSeries platform, not all the topology information
* are exposed via sysfs. Due to restriction, detail like
* physical_package_id will be set to -1. Hence skip this
* test if physical_package_id returns -1 for cpu from perf_cpu_map.
*/
if (!strncmp(session->header.env.arch, "ppc64le", 7)) {
if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1)
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++) {
cpu.cpu = i;
if (!perf_cpu_map__has(map, cpu))
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 CPU ID contains socket, die, core and CPU
perf_cpu_map__for_each_cpu(cpu, i, map) {
id = aggr_cpu_id__cpu(cpu, NULL);
TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match",
cpu.cpu == id.cpu.cpu);
TEST_ASSERT_VAL("Cpu map - Core ID doesn't match",
session->header.env.cpu[cpu.cpu].core_id == id.core);
TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match",
session->header.env.cpu[cpu.cpu].socket_id ==
id.socket);
TEST_ASSERT_VAL("Cpu map - Die ID doesn't match",
session->header.env.cpu[cpu.cpu].die_id == id.die);
TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Cpu map - Thread IDX is set", id.thread_idx == -1);
}
// Test that core ID contains socket, die and core
perf_cpu_map__for_each_cpu(cpu, i, map) {
id = aggr_cpu_id__core(cpu, NULL);
TEST_ASSERT_VAL("Core map - Core ID doesn't match",
session->header.env.cpu[cpu.cpu].core_id == id.core);
TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
session->header.env.cpu[cpu.cpu].socket_id ==
id.socket);
TEST_ASSERT_VAL("Core map - Die ID doesn't match",
session->header.env.cpu[cpu.cpu].die_id == id.die);
TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Core map - Thread IDX is set", id.thread_idx == -1);
}
// Test that die ID contains socket and die
perf_cpu_map__for_each_cpu(cpu, i, map) {
id = aggr_cpu_id__die(cpu, NULL);
TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
session->header.env.cpu[cpu.cpu].socket_id ==
id.socket);
TEST_ASSERT_VAL("Die map - Die ID doesn't match",
session->header.env.cpu[cpu.cpu].die_id == id.die);
TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Die map - Core is set", id.core == -1);
TEST_ASSERT_VAL("Die map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Die map - Thread IDX is set", id.thread_idx == -1);
}
// Test that socket ID contains only socket
perf_cpu_map__for_each_cpu(cpu, i, map) {
id = aggr_cpu_id__socket(cpu, NULL);
TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
session->header.env.cpu[cpu.cpu].socket_id ==
id.socket);
TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1);
TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1);
TEST_ASSERT_VAL("Socket map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Socket map - Thread IDX is set", id.thread_idx == -1);
}
// Test that node ID contains only node
perf_cpu_map__for_each_cpu(cpu, i, map) {
id = aggr_cpu_id__node(cpu, NULL);
TEST_ASSERT_VAL("Node map - Node ID doesn't match",
cpu__get_node(cpu) == id.node);
TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1);
TEST_ASSERT_VAL("Node map - Core is set", id.core == -1);
TEST_ASSERT_VAL("Node map - CPU is set", id.cpu.cpu == -1);
TEST_ASSERT_VAL("Node map - Thread IDX is set", id.thread_idx == -1);
}
perf_session__delete(session);
return 0;
}
static int test__session_topology(struct test_suite *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_online_cpus();
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;
}
DEFINE_SUITE("Session topology", session_topology);