#include <bpf/libbpf.h>
#endif
#include <perf/cpumap.h>
+#include <tools/libc_compat.h> // reallocarray
#include "dso.h"
#include "evlist.h"
#include "debug.h"
#include "cpumap.h"
#include "pmu.h"
+#include "pmus.h"
#include "vdso.h"
#include "strbuf.h"
#include "build-id.h"
#include "bpf-event.h"
#include "bpf-utils.h"
#include "clockid.h"
-#include "pmu-hybrid.h"
#include <linux/ctype.h>
#include <internal/lib.h>
#define CPUINFO_PROC { "Processor", }
#elif defined(__xtensa__)
#define CPUINFO_PROC { "core ID", }
+#elif defined(__loongarch__)
+#define CPUINFO_PROC { "Model Name", }
#else
#define CPUINFO_PROC { "model name", }
#endif
* Do a first pass to count number of pmu to avoid lseek so this
* works in pipe mode as well.
*/
- while ((pmu = perf_pmu__scan(pmu))) {
- if (!pmu->name)
- continue;
+ while ((pmu = perf_pmus__scan(pmu)))
pmu_num++;
- }
ret = do_write(ff, &pmu_num, sizeof(pmu_num));
if (ret < 0)
return ret;
- while ((pmu = perf_pmu__scan(pmu))) {
- if (!pmu->name)
- continue;
-
+ while ((pmu = perf_pmus__scan(pmu))) {
ret = do_write(ff, &pmu->type, sizeof(pmu->type));
if (ret < 0)
return ret;
fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
}
-#define MAX_CACHE_LVL 4
-
-static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
+/*
+ * Build caches levels for a particular CPU from the data in
+ * /sys/devices/system/cpu/cpu<cpu>/cache/
+ * The cache level data is stored in caches[] from index at
+ * *cntp.
+ */
+int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp)
{
- u32 i, cnt = 0;
- u32 nr, cpu;
u16 level;
- nr = cpu__max_cpu().cpu;
+ for (level = 0; level < MAX_CACHE_LVL; level++) {
+ struct cpu_cache_level c;
+ int err;
+ u32 i;
- for (cpu = 0; cpu < nr; cpu++) {
- for (level = 0; level < MAX_CACHE_LVL; level++) {
- struct cpu_cache_level c;
- int err;
+ err = cpu_cache_level__read(&c, cpu, level);
+ if (err < 0)
+ return err;
- err = cpu_cache_level__read(&c, cpu, level);
- if (err < 0)
- return err;
+ if (err == 1)
+ break;
- if (err == 1)
+ for (i = 0; i < *cntp; i++) {
+ if (cpu_cache_level__cmp(&c, &caches[i]))
break;
+ }
- for (i = 0; i < cnt; i++) {
- if (cpu_cache_level__cmp(&c, &caches[i]))
- break;
- }
+ if (i == *cntp) {
+ caches[*cntp] = c;
+ *cntp = *cntp + 1;
+ } else
+ cpu_cache_level__free(&c);
+ }
- if (i == cnt)
- caches[cnt++] = c;
- else
- cpu_cache_level__free(&c);
- }
+ return 0;
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
+{
+ u32 nr, cpu, cnt = 0;
+
+ nr = cpu__max_cpu().cpu;
+
+ for (cpu = 0; cpu < nr; cpu++) {
+ int ret = build_caches_for_cpu(cpu, caches, &cnt);
+
+ if (ret)
+ return ret;
}
*cntp = cnt;
return 0;
return 0;
}
+static void memory_node__delete_nodes(struct memory_node *nodesp, u64 cnt)
+{
+ for (u64 i = 0; i < cnt; i++)
+ bitmap_free(nodesp[i].set);
+
+ free(nodesp);
+}
+
static int memory_node__sort(const void *a, const void *b)
{
const struct memory_node *na = a;
return na->node - nb->node;
}
-static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
+static int build_mem_topology(struct memory_node **nodesp, u64 *cntp)
{
char path[PATH_MAX];
struct dirent *ent;
DIR *dir;
- u64 cnt = 0;
int ret = 0;
+ size_t cnt = 0, size = 0;
+ struct memory_node *nodes = NULL;
scnprintf(path, PATH_MAX, "%s/devices/system/node/",
sysfs__mountpoint());
if (r != 1)
continue;
- if (WARN_ONCE(cnt >= size,
- "failed to write MEM_TOPOLOGY, way too many nodes\n")) {
- closedir(dir);
- return -1;
- }
+ if (cnt >= size) {
+ struct memory_node *new_nodes =
+ reallocarray(nodes, cnt + 4, sizeof(*nodes));
- ret = memory_node__read(&nodes[cnt++], idx);
+ if (!new_nodes) {
+ pr_err("Failed to write MEM_TOPOLOGY, size %zd nodes\n", size);
+ ret = -ENOMEM;
+ goto out;
+ }
+ nodes = new_nodes;
+ size += 4;
+ }
+ ret = memory_node__read(&nodes[cnt], idx);
+ if (!ret)
+ cnt += 1;
}
-
- *cntp = cnt;
+out:
closedir(dir);
-
- if (!ret)
+ if (!ret) {
+ *cntp = cnt;
+ *nodesp = nodes;
qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort);
+ } else
+ memory_node__delete_nodes(nodes, cnt);
return ret;
}
-#define MAX_MEMORY_NODES 2000
-
/*
* The MEM_TOPOLOGY holds physical memory map for every
* node in system. The format of data is as follows:
static int write_mem_topology(struct feat_fd *ff __maybe_unused,
struct evlist *evlist __maybe_unused)
{
- static struct memory_node nodes[MAX_MEMORY_NODES];
- u64 bsize, version = 1, i, nr;
+ struct memory_node *nodes = NULL;
+ u64 bsize, version = 1, i, nr = 0;
int ret;
ret = sysfs__read_xll("devices/system/memory/block_size_bytes",
if (ret)
return ret;
- ret = build_mem_topology(&nodes[0], MAX_MEMORY_NODES, &nr);
+ ret = build_mem_topology(&nodes, &nr);
if (ret)
return ret;
}
out:
+ memory_node__delete_nodes(nodes, nr);
return ret;
}
static int write_cpu_pmu_caps(struct feat_fd *ff,
struct evlist *evlist __maybe_unused)
{
- struct perf_pmu *cpu_pmu = perf_pmu__find("cpu");
+ struct perf_pmu *cpu_pmu = perf_pmus__find("cpu");
int ret;
if (!cpu_pmu)
int nr_pmu = 0;
int ret;
- while ((pmu = perf_pmu__scan(pmu))) {
- if (!pmu->name || !strcmp(pmu->name, "cpu") ||
- perf_pmu__caps_parse(pmu) <= 0)
+ while ((pmu = perf_pmus__scan(pmu))) {
+ if (!strcmp(pmu->name, "cpu")) {
+ /*
+ * The "cpu" PMU is special and covered by
+ * HEADER_CPU_PMU_CAPS. Note, core PMUs are
+ * counted/written here for ARM, s390 and Intel hybrid.
+ */
+ continue;
+ }
+ if (perf_pmu__caps_parse(pmu) <= 0)
continue;
nr_pmu++;
}
return 0;
/*
- * Write hybrid pmu caps first to maintain compatibility with
- * older perf tool.
+ * Note older perf tools assume core PMUs come first, this is a property
+ * of perf_pmus__scan.
*/
pmu = NULL;
- perf_pmu__for_each_hybrid_pmu(pmu) {
- ret = __write_pmu_caps(ff, pmu, true);
- if (ret < 0)
- return ret;
- }
-
- pmu = NULL;
- while ((pmu = perf_pmu__scan(pmu))) {
- if (!pmu->name || !strcmp(pmu->name, "cpu") ||
- !pmu->nr_caps || perf_pmu__is_hybrid(pmu->name))
+ while ((pmu = perf_pmus__scan(pmu))) {
+ if (!strcmp(pmu->name, "cpu")) {
+ /* Skip as above. */
+ continue;
+ }
+ if (perf_pmu__caps_parse(pmu) <= 0)
continue;
-
ret = __write_pmu_caps(ff, pmu, true);
if (ret < 0)
return ret;
i = nr = 0;
evlist__for_each_entry(session->evlist, evsel) {
- if (evsel->core.idx == (int) desc[i].leader_idx) {
+ if (i < nr_groups && evsel->core.idx == (int) desc[i].leader_idx) {
evsel__set_leader(evsel, evsel);
/* {anon_group} is a dummy name */
if (strcmp(desc[i].name, "{anon_group}")) {
ret += fprintf(fp, "... ");
map = cpu_map__new_data(&ev->cpus.cpus);
- if (map)
+ if (map) {
ret += cpu_map__fprintf(map, fp);
- else
+ perf_cpu_map__put(map);
+ } else
ret += fprintf(fp, "failed to get cpus\n");
break;
default:
union perf_event *event,
struct evlist **pevlist)
{
- u32 i, ids, n_ids;
+ u32 i, n_ids;
+ u64 *ids;
struct evsel *evsel;
struct evlist *evlist = *pevlist;
evlist__add(evlist, evsel);
- ids = event->header.size;
- ids -= (void *)&event->attr.id - (void *)event;
- n_ids = ids / sizeof(u64);
+ n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+ n_ids = n_ids / sizeof(u64);
/*
* We don't have the cpu and thread maps on the header, so
* for allocating the perf_sample_id table we fake 1 cpu and
if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
return -ENOMEM;
+ ids = perf_record_header_attr_id(event);
for (i = 0; i < n_ids; i++) {
- perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
+ perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
}
return 0;