summaryrefslogtreecommitdiff
path: root/tools/lib/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/lib/perf')
-rw-r--r--tools/lib/perf/.gitignore5
-rw-r--r--tools/lib/perf/Documentation/Makefile2
-rw-r--r--tools/lib/perf/Documentation/libperf.txt1
-rw-r--r--tools/lib/perf/Makefile39
-rw-r--r--tools/lib/perf/cpumap.c170
-rw-r--r--tools/lib/perf/evlist.c20
-rw-r--r--tools/lib/perf/evsel.c48
-rw-r--r--tools/lib/perf/include/internal/cpumap.h4
-rw-r--r--tools/lib/perf/include/internal/evsel.h63
-rw-r--r--tools/lib/perf/include/perf/cpumap.h25
-rw-r--r--tools/lib/perf/include/perf/event.h6
-rw-r--r--tools/lib/perf/libperf.map5
-rw-r--r--tools/lib/perf/mmap.c2
13 files changed, 255 insertions, 135 deletions
diff --git a/tools/lib/perf/.gitignore b/tools/lib/perf/.gitignore
new file mode 100644
index 000000000000..0f5b4af63f62
--- /dev/null
+++ b/tools/lib/perf/.gitignore
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+libperf.pc
+libperf.so.*
+tests-shared
+tests-static
diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile
index 972754082a85..573ca5b27556 100644
--- a/tools/lib/perf/Documentation/Makefile
+++ b/tools/lib/perf/Documentation/Makefile
@@ -121,7 +121,7 @@ install-man: all
$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \
$(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir);
-install-html:
+install-html: $(MAN_HTML)
$(call QUIET_INSTALL, html) \
$(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \
$(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index fcfb9499ef9c..59aabdd3cabf 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -39,7 +39,6 @@ SYNOPSIS
struct perf_cpu_map *perf_cpu_map__new_any_cpu(void);
struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
- struct perf_cpu_map *perf_cpu_map__read(FILE *file);
struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
struct perf_cpu_map *other);
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index 3a9b2140aa04..7fbb50b74c00 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -39,29 +39,10 @@ libdir = $(prefix)/$(libdir_relative)
libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
-ifeq ("$(origin V)", "command line")
- VERBOSE = $(V)
-endif
-ifndef VERBOSE
- VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
- Q =
-else
- Q = @
-endif
-
TEST_ARGS := $(if $(V),-v)
-# Set compile option CFLAGS
-ifdef EXTRA_CFLAGS
- CFLAGS := $(EXTRA_CFLAGS)
-else
- CFLAGS := -g -Wall
-endif
-
INCLUDES = \
+-I$(OUTPUT)arch/$(SRCARCH)/include/generated/uapi \
-I$(srctree)/tools/lib/perf/include \
-I$(srctree)/tools/lib/ \
-I$(srctree)/tools/include \
@@ -70,11 +51,12 @@ INCLUDES = \
-I$(srctree)/tools/include/uapi
# Append required CFLAGS
-override CFLAGS += $(EXTRA_WARNINGS)
-override CFLAGS += -Werror -Wall
+override CFLAGS += -g -Werror -Wall
override CFLAGS += -fPIC
override CFLAGS += $(INCLUDES)
override CFLAGS += -fvisibility=hidden
+override CFLAGS += $(EXTRA_WARNINGS)
+override CFLAGS += $(EXTRA_CFLAGS)
all:
@@ -118,7 +100,16 @@ $(LIBAPI)-clean:
$(call QUIET_CLEAN, libapi)
$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
-$(LIBPERF_IN): FORCE
+uapi-asm := $(OUTPUT)arch/$(SRCARCH)/include/generated/uapi/asm
+ifeq ($(SRCARCH),arm64)
+ syscall-y := $(uapi-asm)/unistd_64.h
+endif
+uapi-asm-generic:
+ $(if $(syscall-y),\
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-headers obj=$(uapi-asm) \
+ generic=include/uapi/asm-generic $(syscall-y),)
+
+$(LIBPERF_IN): uapi-asm-generic FORCE
$(Q)$(MAKE) $(build)=libperf
$(LIBPERF_A): $(LIBPERF_IN)
@@ -139,7 +130,7 @@ all: fixdep
clean: $(LIBAPI)-clean
$(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \
*.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd tests/*.o LIBPERF-CFLAGS $(LIBPERF_PC) \
- $(TESTS_STATIC) $(TESTS_SHARED)
+ $(TESTS_STATIC) $(TESTS_SHARED) $(syscall-y)
TESTS_IN = tests-in.o
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 4adcd7920d03..4454a5987570 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
#include <perf/cpumap.h>
#include <stdlib.h>
#include <linux/refcount.h>
@@ -10,6 +11,9 @@
#include <ctype.h>
#include <limits.h>
#include "internal.h"
+#include <api/fs/fs.h>
+
+#define MAX_NR_CPUS 4096
void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
{
@@ -18,9 +22,13 @@ void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
{
- RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
+ RC_STRUCT(perf_cpu_map) *cpus;
struct perf_cpu_map *result;
+ if (nr_cpus == 0)
+ return NULL;
+
+ cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
if (ADD_RC_CHK(result, cpus)) {
cpus->nr = nr_cpus;
refcount_set(&cpus->refcnt, 1);
@@ -96,12 +104,12 @@ static struct perf_cpu_map *cpu_map__new_sysconf(void)
static struct perf_cpu_map *cpu_map__new_sysfs_online(void)
{
struct perf_cpu_map *cpus = NULL;
- FILE *onlnf;
+ char *buf = NULL;
+ size_t buf_len;
- onlnf = fopen("/sys/devices/system/cpu/online", "r");
- if (onlnf) {
- cpus = perf_cpu_map__read(onlnf);
- fclose(onlnf);
+ if (sysfs__read_str("devices/system/cpu/online", &buf, &buf_len) >= 0) {
+ cpus = perf_cpu_map__new(buf);
+ free(buf);
}
return cpus;
}
@@ -154,62 +162,6 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu
return cpus;
}
-struct perf_cpu_map *perf_cpu_map__read(FILE *file)
-{
- struct perf_cpu_map *cpus = NULL;
- int nr_cpus = 0;
- struct perf_cpu *tmp_cpus = NULL, *tmp;
- int max_entries = 0;
- int n, cpu, prev;
- char sep;
-
- sep = 0;
- prev = -1;
- for (;;) {
- n = fscanf(file, "%u%c", &cpu, &sep);
- if (n <= 0)
- break;
- if (prev >= 0) {
- int new_max = nr_cpus + cpu - prev - 1;
-
- WARN_ONCE(new_max >= MAX_NR_CPUS, "Perf can support %d CPUs. "
- "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS);
-
- if (new_max >= max_entries) {
- max_entries = new_max + MAX_NR_CPUS / 2;
- tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
- if (tmp == NULL)
- goto out_free_tmp;
- tmp_cpus = tmp;
- }
-
- while (++prev < cpu)
- tmp_cpus[nr_cpus++].cpu = prev;
- }
- if (nr_cpus == max_entries) {
- max_entries += MAX_NR_CPUS;
- tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
- if (tmp == NULL)
- goto out_free_tmp;
- tmp_cpus = tmp;
- }
-
- tmp_cpus[nr_cpus++].cpu = cpu;
- if (n == 2 && sep == '-')
- prev = cpu;
- else
- prev = -1;
- if (n == 1 || sep == '\n')
- break;
- }
-
- if (nr_cpus > 0)
- cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-out_free_tmp:
- free(tmp_cpus);
- return cpus;
-}
-
struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
{
struct perf_cpu_map *cpus = NULL;
@@ -233,8 +185,8 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
while (isdigit(*cpu_list)) {
p = NULL;
start_cpu = strtoul(cpu_list, &p, 0);
- if (start_cpu >= INT_MAX
- || (*p != '\0' && *p != ',' && *p != '-'))
+ if (start_cpu >= INT16_MAX
+ || (*p != '\0' && *p != ',' && *p != '-' && *p != '\n'))
goto invalid;
if (*p == '-') {
@@ -242,7 +194,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
p = NULL;
end_cpu = strtoul(cpu_list, &p, 0);
- if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
+ if (end_cpu >= INT16_MAX || (*p != '\0' && *p != ',' && *p != '\n'))
goto invalid;
if (end_cpu < start_cpu)
@@ -257,17 +209,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
for (; start_cpu <= end_cpu; start_cpu++) {
/* check for duplicates */
for (i = 0; i < nr_cpus; i++)
- if (tmp_cpus[i].cpu == (int)start_cpu)
+ if (tmp_cpus[i].cpu == (int16_t)start_cpu)
goto invalid;
if (nr_cpus == max_entries) {
- max_entries += MAX_NR_CPUS;
+ max_entries += max(end_cpu - start_cpu + 1, 16UL);
tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
if (tmp == NULL)
goto invalid;
tmp_cpus = tmp;
}
- tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
+ tmp_cpus[nr_cpus++].cpu = (int16_t)start_cpu;
}
if (*p)
++p;
@@ -275,14 +227,15 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
cpu_list = p;
}
- if (nr_cpus > 0)
+ if (nr_cpus > 0) {
cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
- else if (*cpu_list != '\0') {
+ } else if (*cpu_list != '\0') {
pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.",
cpu_list);
cpus = perf_cpu_map__new_online_cpus();
- } else
+ } else {
cpus = perf_cpu_map__new_any_cpu();
+ }
invalid:
free(tmp_cpus);
out:
@@ -316,6 +269,19 @@ bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map)
return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
}
+bool perf_cpu_map__is_any_cpu_or_is_empty(const struct perf_cpu_map *map)
+{
+ if (!map)
+ return true;
+
+ return __perf_cpu_map__nr(map) == 1 && __perf_cpu_map__cpu(map, 0).cpu == -1;
+}
+
+bool perf_cpu_map__is_empty(const struct perf_cpu_map *map)
+{
+ return map == NULL;
+}
+
int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
int low, high;
@@ -372,6 +338,20 @@ bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map)
return map && __perf_cpu_map__cpu(map, 0).cpu == -1;
}
+struct perf_cpu perf_cpu_map__min(const struct perf_cpu_map *map)
+{
+ struct perf_cpu cpu, result = {
+ .cpu = -1
+ };
+ int idx;
+
+ perf_cpu_map__for_each_cpu_skip_any(cpu, idx, map) {
+ result = cpu;
+ break;
+ }
+ return result;
+}
+
struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
{
struct perf_cpu result = {
@@ -405,46 +385,49 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu
}
/*
- * Merge two cpumaps
+ * Merge two cpumaps.
*
- * orig either gets freed and replaced with a new map, or reused
- * with no reference count change (similar to "realloc")
- * other has its reference count increased.
+ * If 'other' is subset of '*orig', '*orig' keeps itself with no reference count
+ * change (similar to "realloc").
+ *
+ * If '*orig' is subset of 'other', '*orig' reuses 'other' with its reference
+ * count increased.
+ *
+ * Otherwise, '*orig' gets freed and replaced with a new map.
*/
-
-struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
- struct perf_cpu_map *other)
+int perf_cpu_map__merge(struct perf_cpu_map **orig, struct perf_cpu_map *other)
{
struct perf_cpu *tmp_cpus;
int tmp_len;
int i, j, k;
struct perf_cpu_map *merged;
- if (perf_cpu_map__is_subset(orig, other))
- return orig;
- if (perf_cpu_map__is_subset(other, orig)) {
- perf_cpu_map__put(orig);
- return perf_cpu_map__get(other);
+ if (perf_cpu_map__is_subset(*orig, other))
+ return 0;
+ if (perf_cpu_map__is_subset(other, *orig)) {
+ perf_cpu_map__put(*orig);
+ *orig = perf_cpu_map__get(other);
+ return 0;
}
- tmp_len = __perf_cpu_map__nr(orig) + __perf_cpu_map__nr(other);
+ tmp_len = __perf_cpu_map__nr(*orig) + __perf_cpu_map__nr(other);
tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
if (!tmp_cpus)
- return NULL;
+ return -ENOMEM;
/* Standard merge algorithm from wikipedia */
i = j = k = 0;
- while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
- if (__perf_cpu_map__cpu(orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) {
- if (__perf_cpu_map__cpu(orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu)
+ while (i < __perf_cpu_map__nr(*orig) && j < __perf_cpu_map__nr(other)) {
+ if (__perf_cpu_map__cpu(*orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) {
+ if (__perf_cpu_map__cpu(*orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu)
j++;
- tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
+ tmp_cpus[k++] = __perf_cpu_map__cpu(*orig, i++);
} else
tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
}
- while (i < __perf_cpu_map__nr(orig))
- tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
+ while (i < __perf_cpu_map__nr(*orig))
+ tmp_cpus[k++] = __perf_cpu_map__cpu(*orig, i++);
while (j < __perf_cpu_map__nr(other))
tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++);
@@ -452,8 +435,9 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
merged = cpu_map__trim_new(k, tmp_cpus);
free(tmp_cpus);
- perf_cpu_map__put(orig);
- return merged;
+ perf_cpu_map__put(*orig);
+ *orig = merged;
+ return 0;
}
struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index c6d67fc9e57e..b1f4c8176b32 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
*/
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus);
+
+ /*
+ * Empty cpu lists would eventually get opened as "any" so remove
+ * genuinely empty ones before they're opened in the wrong place.
+ */
+ if (perf_cpu_map__is_empty(evsel->cpus)) {
+ struct perf_evsel *next = perf_evlist__next(evlist, evsel);
+
+ perf_evlist__remove(evlist, evsel);
+ /* Keep idx contiguous */
+ if (next)
+ list_for_each_entry_from(next, &evlist->entries, node)
+ next->idx--;
+ }
} else if (!evsel->own_cpus || evlist->has_user_cpus ||
(!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) {
/*
@@ -75,16 +89,16 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
evsel->threads = perf_thread_map__get(evlist->threads);
}
- evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
+ perf_cpu_map__merge(&evlist->all_cpus, evsel->cpus);
}
static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel, *n;
evlist->needs_map_propagation = true;
- perf_evlist__for_each_evsel(evlist, evsel)
+ list_for_each_entry_safe(evsel, n, &evlist->entries, node)
__perf_evlist__propagate_maps(evlist, evsel);
}
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index c07160953224..c475319e2e41 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -5,6 +5,7 @@
#include <perf/evsel.h>
#include <perf/cpumap.h>
#include <perf/threadmap.h>
+#include <linux/hash.h>
#include <linux/list.h>
#include <internal/evsel.h>
#include <linux/zalloc.h>
@@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr,
int idx)
{
INIT_LIST_HEAD(&evsel->node);
+ INIT_LIST_HEAD(&evsel->per_stream_periods);
evsel->attr = *attr;
evsel->idx = idx;
evsel->leader = evsel;
@@ -531,10 +533,56 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
void perf_evsel__free_id(struct perf_evsel *evsel)
{
+ struct perf_sample_id_period *pos, *n;
+
xyarray__delete(evsel->sample_id);
evsel->sample_id = NULL;
zfree(&evsel->id);
evsel->ids = 0;
+
+ perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) {
+ list_del_init(&pos->node);
+ free(pos);
+ }
+}
+
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel)
+{
+ return (evsel->attr.sample_type & PERF_SAMPLE_READ) &&
+ (evsel->attr.sample_type & PERF_SAMPLE_TID) &&
+ evsel->attr.inherit;
+}
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid, bool per_thread)
+{
+ struct hlist_head *head;
+ struct perf_sample_id_period *res;
+ int hash;
+
+ if (!per_thread)
+ return &sid->period;
+
+ hash = hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS);
+ head = &sid->periods[hash];
+
+ hlist_for_each_entry(res, head, hnode)
+ if (res->tid == tid)
+ return &res->period;
+
+ if (sid->evsel == NULL)
+ return NULL;
+
+ res = zalloc(sizeof(struct perf_sample_id_period));
+ if (res == NULL)
+ return NULL;
+
+ INIT_LIST_HEAD(&res->node);
+ res->tid = tid;
+
+ list_add_tail(&res->node, &sid->evsel->per_stream_periods);
+ hlist_add_head(&res->hnode, &sid->periods[hash]);
+
+ return &res->period;
}
void perf_counts_values__scale(struct perf_counts_values *count,
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 49649eb51ce4..e2be2d17c32b 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -21,10 +21,6 @@ DECLARE_RC_STRUCT(perf_cpu_map) {
struct perf_cpu map[];
};
-#ifndef MAX_NR_CPUS
-#define MAX_NR_CPUS 2048
-#endif
-
struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus);
int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 5cd220a61962..ea78defa77d0 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -11,6 +11,32 @@
struct perf_thread_map;
struct xyarray;
+/**
+ * The per-thread accumulated period storage node.
+ */
+struct perf_sample_id_period {
+ struct list_head node;
+ struct hlist_node hnode;
+ /* Holds total ID period value for PERF_SAMPLE_READ processing. */
+ u64 period;
+ /* The TID that the values belongs to */
+ u32 tid;
+};
+
+/**
+ * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the
+ * per_stream_periods
+ * @evlist:perf_evsel instance to iterate
+ * @item: struct perf_sample_id_period iterator
+ * @tmp: struct perf_sample_id_period temp iterator
+ */
+#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \
+ list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node)
+
+
+#define PERF_SAMPLE_ID__HLIST_BITS 4
+#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS)
+
/*
* Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
* more than one entry in the evlist.
@@ -34,8 +60,32 @@ struct perf_sample_id {
pid_t machine_pid;
struct perf_cpu vcpu;
- /* Holds total ID period value for PERF_SAMPLE_READ processing. */
- u64 period;
+ /*
+ * Per-thread, and global event counts are mutually exclusive:
+ * Whilst it is possible to combine events into a group with differing
+ * values of PERF_SAMPLE_READ, it is not valid to have inconsistent
+ * values for `inherit`. Therefore it is not possible to have a
+ * situation where a per-thread event is sampled as a global event;
+ * all !inherit groups are global, and all groups where the sampling
+ * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event
+ * that is part of such a group that is inherit but not PERF_SAMPLE_READ
+ * will be read as per-thread. If such an event can also trigger a
+ * sample (such as with sample_period > 0) then it will not cause
+ * `read_format` to be included in its PERF_RECORD_SAMPLE, and
+ * therefore will not expose the per-thread group members as global.
+ */
+ union {
+ /*
+ * Holds total ID period value for PERF_SAMPLE_READ processing
+ * (when period is not per-thread).
+ */
+ u64 period;
+ /*
+ * Holds total ID period value for PERF_SAMPLE_READ processing
+ * (when period is per-thread).
+ */
+ struct hlist_head periods[PERF_SAMPLE_ID__HLIST_SIZE];
+ };
};
struct perf_evsel {
@@ -58,6 +108,10 @@ struct perf_evsel {
u32 ids;
struct perf_evsel *leader;
+ /* For events where the read_format value is per-thread rather than
+ * global, stores the per-thread cumulative period */
+ struct list_head per_stream_periods;
+
/* parse modifier helper */
int nr_members;
/*
@@ -88,4 +142,9 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
void perf_evsel__free_id(struct perf_evsel *evsel);
+bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evsel);
+
+u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 tid,
+ bool per_thread);
+
#endif /* __LIBPERF_INTERNAL_EVSEL_H */
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 228c6c629b0c..8c1ab0f9194e 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -3,12 +3,12 @@
#define __LIBPERF_CPUMAP_H
#include <perf/core.h>
-#include <stdio.h>
#include <stdbool.h>
+#include <stdint.h>
/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
struct perf_cpu {
- int cpu;
+ int16_t cpu;
};
struct perf_cache {
@@ -37,10 +37,9 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void);
* perf_cpu_map__new_online_cpus is returned.
*/
LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
-LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
- struct perf_cpu_map *other);
+LIBPERF_API int perf_cpu_map__merge(struct perf_cpu_map **orig,
+ struct perf_cpu_map *other);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
struct perf_cpu_map *other);
LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
@@ -61,6 +60,22 @@ LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
* perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
*/
LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__is_any_cpu_or_is_empty - is map either empty or the "any CPU"/dummy value.
+ */
+LIBPERF_API bool perf_cpu_map__is_any_cpu_or_is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__is_empty - does the map contain no values and it doesn't
+ * contain the special "any CPU"/dummy value.
+ */
+LIBPERF_API bool perf_cpu_map__is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__min - the minimum CPU value or -1 if empty or just the "any CPU"/dummy value.
+ */
+LIBPERF_API struct perf_cpu perf_cpu_map__min(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__max - the maximum CPU value or -1 if empty or just the "any CPU"/dummy value.
+ */
LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index ae64090184d3..37bb7771d914 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -77,6 +77,12 @@ struct perf_record_lost_samples {
__u64 lost;
};
+#define MAX_ID_HDR_ENTRIES 6
+struct perf_record_lost_samples_and_ids {
+ struct perf_record_lost_samples lost;
+ __u64 sample_ids[MAX_ID_HDR_ENTRIES];
+};
+
/*
* PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID | PERF_FORMAT_LOST
*/
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 10b3f3722642..fdd8304fe9d0 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -6,10 +6,13 @@ LIBPERF_0.0.1 {
perf_cpu_map__get;
perf_cpu_map__put;
perf_cpu_map__new;
- perf_cpu_map__read;
perf_cpu_map__nr;
perf_cpu_map__cpu;
perf_cpu_map__has_any_cpu_or_is_empty;
+ perf_cpu_map__is_any_cpu_or_is_empty;
+ perf_cpu_map__is_empty;
+ perf_cpu_map__has_any_cpu;
+ perf_cpu_map__min;
perf_cpu_map__max;
perf_cpu_map__has;
perf_thread_map__new_array;
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 0c903c2372c9..c1a51d925e0e 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -279,7 +279,7 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
if (!refcount_read(&map->refcnt))
return NULL;
- /* non-overwirte doesn't pause the ringbuffer */
+ /* non-overwrite doesn't pause the ringbuffer */
if (!map->overwrite)
map->end = perf_mmap__read_head(map);
generated by cgit (git 2.34.1) at 2025-07-23 09:58:20 +0000