mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 09:45:07 +07:00
da8a58b56c
There are 2 problems wrt. cpu_topology_map on systems with sparse CPUs:
1. offline/absent CPUs will have their socket_id and core_id set to -1
which triggers:
"socket_id number is too big.You may need to upgrade the perf tool."
2. size of cpu_topology_map (perf_env.cpu[]) is allocated based on
_SC_NPROCESSORS_CONF, but can be indexed with CPU ids going above.
Users of perf_env.cpu[] are using CPU id as index. This can lead
to read beyond what was allocated:
==19991== Invalid read of size 4
==19991== at 0x490CEB: check_cpu_topology (topology.c:69)
==19991== by 0x490CEB: test_session_topology (topology.c:106)
...
For example:
_SC_NPROCESSORS_CONF == 16
available: 2 nodes (0-1)
node 0 cpus: 0 6 8 10 16 22 24 26
node 0 size: 12004 MB
node 0 free: 9470 MB
node 1 cpus: 1 7 9 11 23 25 27
node 1 size: 12093 MB
node 1 free: 9406 MB
node distances:
node 0 1
0: 10 20
1: 20 10
This patch changes HEADER_NRCPUS.nr_cpus_available from _SC_NPROCESSORS_CONF
to max_present_cpu and updates any user of cpu_topology_map to iterate
with nr_cpus_avail.
As a consequence HEADER_CPU_TOPOLOGY core_id and socket_id lists get longer,
but maintain compatibility with pre-patch state - index to cpu_topology_map is
CPU id.
perf test 36 -v
36: Session topology :
--- start ---
test child forked, pid 22211
templ file: /tmp/perf-test-gmdX5i
CPU 0, core 0, socket 0
CPU 1, core 0, socket 1
CPU 6, core 10, socket 0
CPU 7, core 10, socket 1
CPU 8, core 1, socket 0
CPU 9, core 1, socket 1
CPU 10, core 9, socket 0
CPU 11, core 9, socket 1
CPU 16, core 0, socket 0
CPU 22, core 10, socket 0
CPU 23, core 10, socket 1
CPU 24, core 1, socket 0
CPU 25, core 1, socket 1
CPU 26, core 9, socket 0
CPU 27, core 9, socket 1
test child finished with 0
---- end ----
Session topology: Ok
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/d7c05c6445fca74a8442c2c73cfffd349c52c44f.1487146877.git.jstancek@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
94 lines
1.8 KiB
C
94 lines
1.8 KiB
C
#include "cpumap.h"
|
|
#include "env.h"
|
|
#include "util.h"
|
|
|
|
struct perf_env perf_env;
|
|
|
|
void perf_env__exit(struct perf_env *env)
|
|
{
|
|
int i;
|
|
|
|
zfree(&env->hostname);
|
|
zfree(&env->os_release);
|
|
zfree(&env->version);
|
|
zfree(&env->arch);
|
|
zfree(&env->cpu_desc);
|
|
zfree(&env->cpuid);
|
|
zfree(&env->cmdline);
|
|
zfree(&env->cmdline_argv);
|
|
zfree(&env->sibling_cores);
|
|
zfree(&env->sibling_threads);
|
|
zfree(&env->pmu_mappings);
|
|
zfree(&env->cpu);
|
|
|
|
for (i = 0; i < env->nr_numa_nodes; i++)
|
|
cpu_map__put(env->numa_nodes[i].map);
|
|
zfree(&env->numa_nodes);
|
|
|
|
for (i = 0; i < env->caches_cnt; i++)
|
|
cpu_cache_level__free(&env->caches[i]);
|
|
zfree(&env->caches);
|
|
}
|
|
|
|
int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
|
|
{
|
|
int i;
|
|
|
|
/* do not include NULL termination */
|
|
env->cmdline_argv = calloc(argc, sizeof(char *));
|
|
if (env->cmdline_argv == NULL)
|
|
goto out_enomem;
|
|
|
|
/*
|
|
* Must copy argv contents because it gets moved around during option
|
|
* parsing:
|
|
*/
|
|
for (i = 0; i < argc ; i++) {
|
|
env->cmdline_argv[i] = argv[i];
|
|
if (env->cmdline_argv[i] == NULL)
|
|
goto out_free;
|
|
}
|
|
|
|
env->nr_cmdline = argc;
|
|
|
|
return 0;
|
|
out_free:
|
|
zfree(&env->cmdline_argv);
|
|
out_enomem:
|
|
return -ENOMEM;
|
|
}
|
|
|
|
int perf_env__read_cpu_topology_map(struct perf_env *env)
|
|
{
|
|
int cpu, nr_cpus;
|
|
|
|
if (env->cpu != NULL)
|
|
return 0;
|
|
|
|
if (env->nr_cpus_avail == 0)
|
|
env->nr_cpus_avail = cpu__max_present_cpu();
|
|
|
|
nr_cpus = env->nr_cpus_avail;
|
|
if (nr_cpus == -1)
|
|
return -EINVAL;
|
|
|
|
env->cpu = calloc(nr_cpus, sizeof(env->cpu[0]));
|
|
if (env->cpu == NULL)
|
|
return -ENOMEM;
|
|
|
|
for (cpu = 0; cpu < nr_cpus; ++cpu) {
|
|
env->cpu[cpu].core_id = cpu_map__get_core_id(cpu);
|
|
env->cpu[cpu].socket_id = cpu_map__get_socket_id(cpu);
|
|
}
|
|
|
|
env->nr_cpus_avail = nr_cpus;
|
|
return 0;
|
|
}
|
|
|
|
void cpu_cache_level__free(struct cpu_cache_level *cache)
|
|
{
|
|
free(cache->type);
|
|
free(cache->map);
|
|
free(cache->size);
|
|
}
|