summaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/arm-spe.c5
-rw-r--r--tools/perf/util/auxtrace.c16
-rw-r--r--tools/perf/util/bpf-event.c4
-rw-r--r--tools/perf/util/bpf-loader.c27
-rw-r--r--tools/perf/util/bpf_counter.c61
-rw-r--r--tools/perf/util/bpf_counter_cgroup.c42
-rw-r--r--tools/perf/util/c++/clang.cpp4
-rw-r--r--tools/perf/util/data.c14
-rw-r--r--tools/perf/util/data.h2
-rw-r--r--tools/perf/util/event.c7
-rw-r--r--tools/perf/util/evlist.c66
-rw-r--r--tools/perf/util/evlist.h2
-rw-r--r--tools/perf/util/evsel.c77
-rw-r--r--tools/perf/util/evsel.h29
-rw-r--r--tools/perf/util/genelf.h3
-rw-r--r--tools/perf/util/header.c62
-rw-r--r--tools/perf/util/header.h15
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.c99
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.h1
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c1
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h1
-rw-r--r--tools/perf/util/intel-pt.c57
-rw-r--r--tools/perf/util/machine.c101
-rw-r--r--tools/perf/util/machine.h5
-rw-r--r--tools/perf/util/mem-events.c32
-rw-r--r--tools/perf/util/mem-events.h1
-rw-r--r--tools/perf/util/metricgroup.c124
-rw-r--r--tools/perf/util/parse-events.c46
-rw-r--r--tools/perf/util/parse-events.l2
-rw-r--r--tools/perf/util/path.c14
-rw-r--r--tools/perf/util/path.h1
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c49
-rw-r--r--tools/perf/util/session.c35
-rw-r--r--tools/perf/util/stat-display.c46
-rw-r--r--tools/perf/util/stat-shadow.c29
-rw-r--r--tools/perf/util/stat.c31
-rw-r--r--tools/perf/util/stat.h22
-rw-r--r--tools/perf/util/symbol-elf.c2
-rw-r--r--tools/perf/util/symbol.c37
-rw-r--r--tools/perf/util/symbol.h3
-rw-r--r--tools/perf/util/symbol_conf.h3
-rw-r--r--tools/perf/util/topdown.c17
-rw-r--r--tools/perf/util/topdown.h3
-rw-r--r--tools/perf/util/util.c5
44 files changed, 933 insertions, 270 deletions
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index d2b64e3f588b..1a80151baed9 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
memset(&attr, 0, sizeof(struct perf_event_attr));
attr.size = sizeof(struct perf_event_attr);
attr.type = PERF_TYPE_HARDWARE;
- attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
+ attr.sample_type = evsel->core.attr.sample_type &
+ (PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
- PERF_SAMPLE_WEIGHT;
+ PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
if (spe->timeless_decoding)
attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
else
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index df1c5bbbaa0d..b11549ae39df 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -636,6 +636,22 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
return -EINVAL;
}
+static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
+{
+ bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+
+ if (per_cpu_mmaps) {
+ struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
+ int cpu_map_idx = perf_cpu_map__idx(evsel->core.cpus, evlist_cpu);
+
+ if (cpu_map_idx == -1)
+ return -EINVAL;
+ return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx);
+ }
+
+ return perf_evsel__enable_thread(&evsel->core, idx);
+}
+
int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
{
struct evsel *evsel;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 94624733af7e..8271ab764eb5 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -22,7 +22,8 @@
#include "record.h"
#include "util/synthetic-events.h"
-struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
+#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+struct btf *btf__load_from_kernel_by_id(__u32 id)
{
struct btf *btf;
#pragma GCC diagnostic push
@@ -32,6 +33,7 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
return err ? ERR_PTR(err) : btf;
}
+#endif
int __weak bpf_prog_load(enum bpf_prog_type prog_type,
const char *prog_name __maybe_unused,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index b72cef1ae959..f8ad581ea247 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -99,16 +99,26 @@ static int bpf_perf_object__add(struct bpf_object *obj)
return perf_obj ? 0 : -ENOMEM;
}
+static int libbpf_init(void)
+{
+ if (libbpf_initialized)
+ return 0;
+
+ libbpf_set_print(libbpf_perf_print);
+ libbpf_initialized = true;
+ return 0;
+}
+
struct bpf_object *
bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
{
LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = name);
struct bpf_object *obj;
+ int err;
- if (!libbpf_initialized) {
- libbpf_set_print(libbpf_perf_print);
- libbpf_initialized = true;
- }
+ err = libbpf_init();
+ if (err)
+ return ERR_PTR(err);
obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
if (IS_ERR_OR_NULL(obj)) {
@@ -135,14 +145,13 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
{
LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename);
struct bpf_object *obj;
+ int err;
- if (!libbpf_initialized) {
- libbpf_set_print(libbpf_perf_print);
- libbpf_initialized = true;
- }
+ err = libbpf_init();
+ if (err)
+ return ERR_PTR(err);
if (source) {
- int err;
void *obj_buf;
size_t obj_buf_sz;
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 3ce8d03cb7ec..d4931f54e1dd 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -224,25 +224,25 @@ static int bpf_program_profiler__disable(struct evsel *evsel)
static int bpf_program_profiler__read(struct evsel *evsel)
{
- // perf_cpu_map uses /sys/devices/system/cpu/online
- int num_cpu = evsel__nr_cpus(evsel);
// BPF_MAP_TYPE_PERCPU_ARRAY uses /sys/devices/system/cpu/possible
// Sometimes possible > online, like on a Ryzen 3900X that has 24
// threads but its possible showed 0-31 -acme
int num_cpu_bpf = libbpf_num_possible_cpus();
struct bpf_perf_event_value values[num_cpu_bpf];
struct bpf_counter *counter;
+ struct perf_counts_values *counts;
int reading_map_fd;
__u32 key = 0;
- int err, cpu;
+ int err, idx, bpf_cpu;
if (list_empty(&evsel->bpf_counter_list))
return -EAGAIN;
- for (cpu = 0; cpu < num_cpu; cpu++) {
- perf_counts(evsel->counts, cpu, 0)->val = 0;
- perf_counts(evsel->counts, cpu, 0)->ena = 0;
- perf_counts(evsel->counts, cpu, 0)->run = 0;
+ perf_cpu_map__for_each_idx(idx, evsel__cpus(evsel)) {
+ counts = perf_counts(evsel->counts, idx, 0);
+ counts->val = 0;
+ counts->ena = 0;
+ counts->run = 0;
}
list_for_each_entry(counter, &evsel->bpf_counter_list, list) {
struct bpf_prog_profiler_bpf *skel = counter->skel;
@@ -256,10 +256,15 @@ static int bpf_program_profiler__read(struct evsel *evsel)
return err;
}
- for (cpu = 0; cpu < num_cpu; cpu++) {
- perf_counts(evsel->counts, cpu, 0)->val += values[cpu].counter;
- perf_counts(evsel->counts, cpu, 0)->ena += values[cpu].enabled;
- perf_counts(evsel->counts, cpu, 0)->run += values[cpu].running;
+ for (bpf_cpu = 0; bpf_cpu < num_cpu_bpf; bpf_cpu++) {
+ idx = perf_cpu_map__idx(evsel__cpus(evsel),
+ (struct perf_cpu){.cpu = bpf_cpu});
+ if (idx == -1)
+ continue;
+ counts = perf_counts(evsel->counts, idx, 0);
+ counts->val += values[bpf_cpu].counter;
+ counts->ena += values[bpf_cpu].enabled;
+ counts->run += values[bpf_cpu].running;
}
}
return 0;
@@ -621,6 +626,7 @@ static int bperf__read(struct evsel *evsel)
struct bperf_follower_bpf *skel = evsel->follower_skel;
__u32 num_cpu_bpf = cpu__max_cpu().cpu;
struct bpf_perf_event_value values[num_cpu_bpf];
+ struct perf_counts_values *counts;
int reading_map_fd, err = 0;
__u32 i;
int j;
@@ -639,29 +645,32 @@ static int bperf__read(struct evsel *evsel)
case BPERF_FILTER_GLOBAL:
assert(i == 0);
- perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) {
- cpu = entry.cpu;
- perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter;
- perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled;
- perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running;
+ perf_cpu_map__for_each_cpu(entry, j, evsel__cpus(evsel)) {
+ counts = perf_counts(evsel->counts, j, 0);
+ counts->val = values[entry.cpu].counter;
+ counts->ena = values[entry.cpu].enabled;
+ counts->run = values[entry.cpu].running;
}
break;
case BPERF_FILTER_CPU:
- cpu = evsel->core.cpus->map[i].cpu;
- perf_counts(evsel->counts, i, 0)->val = values[cpu].counter;
- perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled;
- perf_counts(evsel->counts, i, 0)->run = values[cpu].running;
+ cpu = perf_cpu_map__cpu(evsel__cpus(evsel), i).cpu;
+ assert(cpu >= 0);
+ counts = perf_counts(evsel->counts, i, 0);
+ counts->val = values[cpu].counter;
+ counts->ena = values[cpu].enabled;
+ counts->run = values[cpu].running;
break;
case BPERF_FILTER_PID:
case BPERF_FILTER_TGID:
- perf_counts(evsel->counts, 0, i)->val = 0;
- perf_counts(evsel->counts, 0, i)->ena = 0;
- perf_counts(evsel->counts, 0, i)->run = 0;
+ counts = perf_counts(evsel->counts, 0, i);
+ counts->val = 0;
+ counts->ena = 0;
+ counts->run = 0;
for (cpu = 0; cpu < num_cpu_bpf; cpu++) {
- perf_counts(evsel->counts, 0, i)->val += values[cpu].counter;
- perf_counts(evsel->counts, 0, i)->ena += values[cpu].enabled;
- perf_counts(evsel->counts, 0, i)->run += values[cpu].running;
+ counts->val += values[cpu].counter;
+ counts->ena += values[cpu].enabled;
+ counts->run += values[cpu].running;
}
break;
default:
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index ac60c08e8e2a..63b9db657442 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -46,8 +46,8 @@ static int bperf_load_program(struct evlist *evlist)
struct bpf_link *link;
struct evsel *evsel;
struct cgroup *cgrp, *leader_cgrp;
- __u32 i, cpu;
- __u32 nr_cpus = evlist->core.all_cpus->nr;
+ int i, j;
+ struct perf_cpu cpu;
int total_cpus = cpu__max_cpu().cpu;
int map_size, map_fd;
int prog_fd, err;
@@ -93,9 +93,9 @@ static int bperf_load_program(struct evlist *evlist)
goto out;
}
- for (i = 0; i < nr_cpus; i++) {
+ perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
link = bpf_program__attach_perf_event(skel->progs.on_cgrp_switch,
- FD(cgrp_switch, i));
+ FD(cgrp_switch, cpu.cpu));
if (IS_ERR(link)) {
pr_err("Failed to attach cgroup program\n");
err = PTR_ERR(link);
@@ -122,10 +122,9 @@ static int bperf_load_program(struct evlist *evlist)
}
map_fd = bpf_map__fd(skel->maps.events);
- for (cpu = 0; cpu < nr_cpus; cpu++) {
- int fd = FD(evsel, cpu);
- __u32 idx = evsel->core.idx * total_cpus +
- evlist->core.all_cpus->map[cpu].cpu;
+ perf_cpu_map__for_each_cpu(cpu, j, evlist->core.all_cpus) {
+ int fd = FD(evsel, cpu.cpu);
+ __u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
err = bpf_map_update_elem(map_fd, &idx, &fd,
BPF_ANY);
@@ -207,14 +206,12 @@ static int bperf_cgrp__install_pe(struct evsel *evsel __maybe_unused,
*/
static int bperf_cgrp__sync_counters(struct evlist *evlist)
{
- int i, cpu;
- int nr_cpus = evlist->core.all_cpus->nr;
+ struct perf_cpu cpu;
+ int idx;
int prog_fd = bpf_program__fd(skel->progs.trigger_read);
- for (i = 0; i < nr_cpus; i++) {
- cpu = evlist->core.all_cpus->map[i].cpu;
- bperf_trigger_reading(prog_fd, cpu);
- }
+ perf_cpu_map__for_each_cpu(cpu, idx, evlist->core.all_cpus)
+ bperf_trigger_reading(prog_fd, cpu.cpu);
return 0;
}
@@ -244,12 +241,10 @@ static int bperf_cgrp__disable(struct evsel *evsel)
static int bperf_cgrp__read(struct evsel *evsel)
{
struct evlist *evlist = evsel->evlist;
- int i, cpu, nr_cpus = evlist->core.all_cpus->nr;
int total_cpus = cpu__max_cpu().cpu;
struct perf_counts_values *counts;
struct bpf_perf_event_value *values;
int reading_map_fd, err = 0;
- __u32 idx;
if (evsel->core.idx)
return 0;
@@ -263,7 +258,10 @@ static int bperf_cgrp__read(struct evsel *evsel)
reading_map_fd = bpf_map__fd(skel->maps.cgrp_readings);
evlist__for_each_entry(evlist, evsel) {
- idx = evsel->core.idx;
+ __u32 idx = evsel->core.idx;
+ int i;
+ struct perf_cpu cpu;
+
err = bpf_map_lookup_elem(reading_map_fd, &idx, values);
if (err) {
pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n",
@@ -271,13 +269,11 @@ static int bperf_cgrp__read(struct evsel *evsel)
goto out;
}
- for (i = 0; i < nr_cpus; i++) {
- cpu = evlist->core.all_cpus->map[i].cpu;
-
+ perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
counts = perf_counts(evsel->counts, i, 0);
- counts->val = values[cpu].counter;
- counts->ena = values[cpu].enabled;
- counts->run = values[cpu].running;
+ counts->val = values[cpu.cpu].counter;
+ counts->ena = values[cpu.cpu].enabled;
+ counts->run = values[cpu.cpu].running;
}
}
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index df7b18fb6b6e..1aad7d6d34aa 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -20,7 +20,11 @@
#include "llvm/Option/Option.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/ManagedStatic.h"
+#if CLANG_VERSION_MAJOR >= 14
+#include "llvm/MC/TargetRegistry.h"
+#else
#include "llvm/Support/TargetRegistry.h"
+#endif
#include "llvm/Support/TargetSelect.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index a5ace2bbc28d..caabeac24c69 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -479,6 +479,20 @@ int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz)
return mkdir(buf, S_IRWXU);
}
+bool has_kcore_dir(const char *path)
+{
+ char *kcore_dir;
+ int ret;
+
+ if (asprintf(&kcore_dir, "%s/kcore_dir", path) < 0)
+ return false;
+
+ ret = access(kcore_dir, F_OK);
+
+ free(kcore_dir);
+ return !ret;
+}
+
char *perf_data__kallsyms_name(struct perf_data *data)
{
char *kallsyms_name;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index c9de82af5584..7de53d6e2d7f 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -4,6 +4,7 @@
#include <stdio.h>
#include <stdbool.h>
+#include <linux/types.h>
enum perf_data_mode {
PERF_DATA_MODE_WRITE,
@@ -98,6 +99,7 @@ void perf_data__close_dir(struct perf_data *data);
int perf_data__update_dir(struct perf_data *data);
unsigned long perf_data__size(struct perf_data *data);
int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz);
+bool has_kcore_dir(const char *path);
char *perf_data__kallsyms_name(struct perf_data *data);
bool is_perf_data(const char *path);
#endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6439c888ae38..0476bb3a4188 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -683,9 +683,12 @@ static bool check_address_range(struct intlist *addr_list, int addr_range,
int machine__resolve(struct machine *machine, struct addr_location *al,
struct perf_sample *sample)
{
- struct thread *thread = machine__findnew_thread(machine, sample->pid,
- sample->tid);
+ struct thread *thread;
+ if (symbol_conf.guest_code && !machine__is_host(machine))
+ thread = machine__findnew_guest_code(machine, sample->pid);
+ else
+ thread = machine__findnew_thread(machine, sample->pid, sample->tid);
if (thread == NULL)
return -1;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 52ea004ba01e..7f9f588e88c6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -334,14 +334,6 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name,
return 0;
}
-static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel)
-{
- if (evsel->core.system_wide)
- return 1;
- else
- return perf_thread_map__nr(evlist->core.threads);
-}
-
struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity)
{
struct evlist_cpu_iterator itr = {
@@ -546,48 +538,6 @@ void evlist__toggle_enable(struct evlist *evlist)
(evlist->enabled ? evlist__disable : evlist__enable)(evlist);
}
-static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, int cpu)
-{
- int thread;
- int nr_threads = evlist__nr_threads(evlist, evsel);
-
- if (!evsel->core.fd)
- return -EINVAL;
-
- for (thread = 0; thread < nr_threads; thread++) {
- int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
- if (err)
- return err;
- }
- return 0;
-}
-
-static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread)
-{
- int cpu;
- int nr_cpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
-
- if (!evsel->core.fd)
- return -EINVAL;
-
- for (cpu = 0; cpu < nr_cpus; cpu++) {
- int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
- if (err)
- return err;
- }
- return 0;
-}
-
-int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
-{
- bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
-
- if (per_cpu_mmaps)
- return evlist__enable_event_cpu(evlist, evsel, idx);
-
- return evlist__enable_event_thread(evlist, evsel, idx);
-}
-
int evlist__add_pollfd(struct evlist *evlist, int fd)
{
return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN, fdarray_flag__default);
@@ -797,11 +747,13 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
static void
perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist,
+ struct perf_evsel *_evsel __maybe_unused,
struct perf_mmap_param *_mp,
- int idx, bool per_cpu)
+ int idx)
{
struct evlist *evlist = container_of(_evlist, struct evlist, core);
struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
+ bool per_cpu = !perf_cpu_map__empty(_evlist->user_requested_cpus);
auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, idx, per_cpu);
}
@@ -1790,8 +1742,13 @@ struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *
if (evsel__has_leader(c2, leader)) {
if (is_open && close)
perf_evsel__close(&c2->core);
- evsel__set_leader(c2, c2);
- c2->core.nr_members = 0;
+ /*
+ * We want to close all members of the group and reopen
+ * them. Some events, like Intel topdown, require being
+ * in a group and so keep these in the group.
+ */
+ evsel__remove_from_group(c2, leader);
+
/*
* Set this for all former members of the group
* to indicate they get reopened.
@@ -1799,6 +1756,9 @@ struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *
c2->reset_group = true;
}
}
+ /* Reset the leader count if all entries were removed. */
+ if (leader->core.nr_members == 1)
+ leader->core.nr_members = 0;
return leader;
}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a21daaa5fc1b..4062f5aebfc1 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -196,8 +196,6 @@ void evlist__toggle_enable(struct evlist *evlist);
void evlist__disable_evsel(struct evlist *evlist, char *evsel_name);
void evlist__enable_evsel(struct evlist *evlist, char *evsel_name);
-int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx);
-
void evlist__set_selected(struct evlist *evlist, struct evsel *evsel);
int evlist__create_maps(struct evlist *evlist, struct target *target);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2a1729e7aee4..ef169ad15236 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -59,6 +59,33 @@ struct perf_missing_features perf_missing_features;
static clockid_t clockid;
+static const char *const perf_tool_event__tool_names[PERF_TOOL_MAX] = {
+ NULL,
+ "duration_time",
+ "user_time",
+ "system_time",
+};
+
+const char *perf_tool_event__to_str(enum perf_tool_event ev)
+{
+ if (ev > PERF_TOOL_NONE && ev < PERF_TOOL_MAX)
+ return perf_tool_event__tool_names[ev];
+
+ return NULL;
+}
+
+enum perf_tool_event perf_tool_event__from_str(const char *str)
+{
+ int i;
+
+ perf_tool_event__for_each_event(i) {
+ if (!strcmp(str, perf_tool_event__tool_names[i]))
+ return i;
+ }
+ return PERF_TOOL_NONE;
+}
+
+
static int evsel__no_extra_init(struct evsel *evsel __maybe_unused)
{
return 0;
@@ -486,7 +513,7 @@ out_err:
return ERR_PTR(err);
}
-const char *evsel__hw_names[PERF_COUNT_HW_MAX] = {
+const char *const evsel__hw_names[PERF_COUNT_HW_MAX] = {
"cycles",
"instructions",
"cache-references",
@@ -571,7 +598,7 @@ static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
return r + evsel__add_modifiers(evsel, bf + r, size - r);
}
-const char *evsel__sw_names[PERF_COUNT_SW_MAX] = {
+const char *const evsel__sw_names[PERF_COUNT_SW_MAX] = {
"cpu-clock",
"task-clock",
"page-faults",
@@ -597,6 +624,11 @@ static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
return r + evsel__add_modifiers(evsel, bf + r, size - r);
}
+static int evsel__tool_name(enum perf_tool_event ev, char *bf, size_t size)
+{
+ return scnprintf(bf, size, "%s", perf_tool_event__to_str(ev));
+}
+
static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
{
int r;
@@ -622,7 +654,7 @@ static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
return r + evsel__add_modifiers(evsel, bf + r, size - r);
}
-const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = {
+const char *const evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = {
{ "L1-dcache", "l1-d", "l1d", "L1-data", },
{ "L1-icache", "l1-i", "l1i", "L1-instruction", },
{ "LLC", "L2", },
@@ -632,13 +664,13 @@ const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = {
{ "node", },
};
-const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALIASES] = {
+const char *const evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALIASES] = {
{ "load", "loads", "read", },
{ "store", "stores", "write", },
{ "prefetch", "prefetches", "speculative-read", "speculative-load", },
};
-const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES] = {
+const char *const evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES] = {
{ "refs", "Reference", "ops", "access", },
{ "misses", "miss", },
};
@@ -654,7 +686,7 @@ const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_AL
* L1I : Read and prefetch only
* ITLB and BPU : Read-only
*/
-static unsigned long evsel__hw_cache_stat[C(MAX)] = {
+static const unsigned long evsel__hw_cache_stat[C(MAX)] = {
[C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(L1I)] = (CACHE_READ | CACHE_PREFETCH),
[C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
@@ -723,12 +755,6 @@ static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
return ret + evsel__add_modifiers(evsel, bf + ret, size - ret);
}
-static int evsel__tool_name(char *bf, size_t size)
-{
- int ret = scnprintf(bf, size, "duration_time");
- return ret;
-}
-
const char *evsel__name(struct evsel *evsel)
{
char bf[128];
@@ -753,8 +779,8 @@ const char *evsel__name(struct evsel *evsel)
break;
case PERF_TYPE_SOFTWARE:
- if (evsel->tool_event)
- evsel__tool_name(bf, sizeof(bf));
+ if (evsel__is_tool(evsel))
+ evsel__tool_name(evsel->tool_event, bf, sizeof(bf));
else
evsel__sw_name(evsel, bf, sizeof(bf));
break;
@@ -786,8 +812,8 @@ const char *evsel__metric_id(const struct evsel *evsel)
if (evsel->metric_id)
return evsel->metric_id;
- if (evsel->core.attr.type == PERF_TYPE_SOFTWARE && evsel->tool_event)
- return "duration_time";
+ if (evsel__is_tool(evsel))
+ return perf_tool_event__to_str(evsel->tool_event);
return "unknown";
}
@@ -3077,3 +3103,22 @@ int evsel__source_count(const struct evsel *evsel)
}
return count;
}
+
+bool __weak arch_evsel__must_be_in_group(const struct evsel *evsel __maybe_unused)
+{
+ return false;
+}
+
+/*
+ * Remove an event from a given group (leader).
+ * Some events, e.g., perf metrics Topdown events,
+ * must always be grouped. Ignore the events.
+ */
+void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader)
+{
+ if (!arch_evsel__must_be_in_group(evsel) && evsel != leader) {
+ evsel__set_leader(evsel, evsel);
+ evsel->core.nr_members = 0;
+ leader->core.nr_members--;
+ }
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 041b42d33bf5..73ea48e94079 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -30,8 +30,18 @@ typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
enum perf_tool_event {
PERF_TOOL_NONE = 0,
PERF_TOOL_DURATION_TIME = 1,
+ PERF_TOOL_USER_TIME = 2,
+ PERF_TOOL_SYSTEM_TIME = 3,
+
+ PERF_TOOL_MAX,
};
+const char *perf_tool_event__to_str(enum perf_tool_event ev);
+enum perf_tool_event perf_tool_event__from_str(const char *str);
+
+#define perf_tool_event__for_each_event(ev) \
+ for ((ev) = PERF_TOOL_DURATION_TIME; (ev) < PERF_TOOL_MAX; ev++)
+
/** struct evsel - event selector
*
* @evlist - evlist this evsel is in, if it is in one.
@@ -120,6 +130,7 @@ struct evsel {
bool merged_stat;
bool reset_group;
bool errored;
+ bool needs_auxtrace_mmap;
struct hashmap *per_pkg_mask;
int err;
struct {
@@ -253,11 +264,11 @@ static inline bool evsel__is_bpf(struct evsel *evsel)
#define EVSEL__MAX_ALIASES 8
-extern const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES];
-extern const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALIASES];
-extern const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES];
-extern const char *evsel__hw_names[PERF_COUNT_HW_MAX];
-extern const char *evsel__sw_names[PERF_COUNT_SW_MAX];
+extern const char *const evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES];
+extern const char *const evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALIASES];
+extern const char *const evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES];
+extern const char *const evsel__hw_names[PERF_COUNT_HW_MAX];
+extern const char *const evsel__sw_names[PERF_COUNT_SW_MAX];
extern char *evsel__bpf_counter_events;
bool evsel__match_bpf_counter_events(const char *name);
@@ -265,6 +276,11 @@ int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size
const char *evsel__name(struct evsel *evsel);
const char *evsel__metric_id(const struct evsel *evsel);
+static inline bool evsel__is_tool(const struct evsel *evsel)
+{
+ return evsel->tool_event != PERF_TOOL_NONE;
+}
+
const char *evsel__group_name(struct evsel *evsel);
int evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
@@ -483,6 +499,9 @@ bool evsel__has_leader(struct evsel *evsel, struct evsel *leader);
bool evsel__is_leader(struct evsel *evsel);
void evsel__set_leader(struct evsel *evsel, struct evsel *leader);
int evsel__source_count(const struct evsel *evsel);
+void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader);
+
+bool arch_evsel__must_be_in_group(const struct evsel *evsel);
/*
* Macro to swap the bit-field postition and size.
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index 3db3293213a9..ae138afe6c56 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -38,6 +38,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
#elif defined(__s390x__)
#define GEN_ELF_ARCH EM_S390
#define GEN_ELF_CLASS ELFCLASS64
+#elif defined(__riscv) && __riscv_xlen == 64
+#define GEN_ELF_ARCH EM_RISCV
+#define GEN_ELF_CLASS ELFCLASS64
#else
#error "unsupported architecture"
#endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a27132e5a5ef..53332da100e8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3462,9 +3462,22 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
return 0;
}
+struct header_fw {
+ struct feat_writer fw;
+ struct feat_fd *ff;
+};
+
+static int feat_writer_cb(struct feat_writer *fw, void *buf, size_t sz)
+{
+ struct header_fw *h = container_of(fw, struct header_fw, fw);
+
+ return do_write(h->ff, buf, sz);
+}
+
static int do_write_feat(struct feat_fd *ff, int type,
struct perf_file_section **p,
- struct evlist *evlist)
+ struct evlist *evlist,
+ struct feat_copier *fc)
{
int err;
int ret = 0;
@@ -3478,7 +3491,23 @@ static int do_write_feat(struct feat_fd *ff, int type,
(*p)->offset = lseek(ff->fd, 0, SEEK_CUR);
- err = feat_ops[type].write(ff, evlist);
+ /*
+ * Hook to let perf inject copy features sections from the input
+ * file.
+ */
+ if (fc && fc->copy) {
+ struct header_fw h = {
+ .fw.write = feat_writer_cb,
+ .ff = ff,
+ };
+
+ /* ->copy() returns 0 if the feature was not copied */
+ err = fc->copy(fc, type, &h.fw);
+ } else {
+ err = 0;
+ }
+ if (!err)
+ err = feat_ops[type].write(ff, evlist);
if (err < 0) {
pr_debug("failed to write feature %s\n", feat_ops[type].name);
@@ -3494,7 +3523,8 @@ static int do_write_feat(struct feat_fd *ff, int type,
}
static int perf_header__adds_write(struct perf_header *header,
- struct evlist *evlist, int fd)
+ struct evlist *evlist, int fd,
+ struct feat_copier *fc)
{
int nr_sections;
struct feat_fd ff;
@@ -3523,7 +3553,7 @@ static int perf_header__adds_write(struct perf_header *header,
lseek(fd, sec_start + sec_size, SEEK_SET);
for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
- if (do_write_feat(&ff, feat, &p, evlist))
+ if (do_write_feat(&ff, feat, &p, evlist, fc))
perf_header__clear_feat(header, feat);
}
@@ -3561,9 +3591,10 @@ int perf_header__write_pipe(int fd)
return 0;
}
-int perf_session__write_header(struct perf_session *session,
- struct evlist *evlist,
- int fd, bool at_exit)
+static int perf_session__do_write_header(struct perf_session *session,
+ struct evlist *evlist,
+ int fd, bool at_exit,
+ struct feat_copier *fc)
{
struct perf_file_header f_header;
struct perf_file_attr f_attr;
@@ -3615,7 +3646,7 @@ int perf_session__write_header(struct perf_session *session,
header->feat_offset = header->data_offset + header->data_size;
if (at_exit) {
- err = perf_header__adds_write(header, evlist, fd);
+ err = perf_header__adds_write(header, evlist, fd, fc);
if (err < 0)
return err;
}
@@ -3648,6 +3679,21 @@ int perf_session__write_header(struct perf_session *session,
return 0;
}
+int perf_session__write_header(struct perf_session *session,
+ struct evlist *evlist,
+ int fd, bool at_exit)
+{
+ return perf_session__do_write_header(session, evlist, fd, at_exit, NULL);
+}
+
+int perf_session__inject_header(struct perf_session *session,
+ struct evlist *evlist,
+ int fd,
+ struct feat_copier *fc)
+{
+ return perf_session__do_write_header(session, evlist, fd, true, fc);
+}
+
static int perf_header__getbuffer64(struct perf_header *header,
int fd, void *buf, size_t size)
{
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 0eb4bc29a5a4..08563c1f1bff 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -121,6 +121,21 @@ int perf_session__write_header(struct perf_session *session,
int fd, bool at_exit);
int perf_header__write_pipe(int fd);
+/* feat_writer writes a feature section to output */
+struct feat_writer {
+ int (*write)(struct feat_writer *fw, void *buf, size_t sz);
+};
+
+/* feat_copier copies a feature section using feat_writer to output */
+struct feat_copier {
+ int (*copy)(struct feat_copier *fc, int feat, struct feat_writer *fw);
+};
+
+int perf_session__inject_header(struct perf_session *session,
+ struct evlist *evlist,
+ int fd,
+ struct feat_copier *fc);
+
void perf_header__set_feat(struct perf_header *header, int feat);
void perf_header__clear_feat(struct perf_header *header, int feat);
bool perf_header__has_feat(const struct perf_header *header, int feat);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index e1d8f7504cbe..0ac860c8dd2b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -137,6 +137,7 @@ struct intel_pt_decoder {
bool in_psb;
bool hop;
bool leap;
+ bool emulated_ptwrite;
bool vm_time_correlation;
bool vm_tm_corr_dry_run;
bool vm_tm_corr_reliable;
@@ -481,6 +482,8 @@ static int intel_pt_ext_err(int code)
return INTEL_PT_ERR_LOST;
case -ELOOP:
return INTEL_PT_ERR_NELOOP;
+ case -ECONNRESET:
+ return INTEL_PT_ERR_EPTW;
default:
return INTEL_PT_ERR_UNK;
}
@@ -497,6 +500,7 @@ static const char *intel_pt_err_msgs[] = {
[INTEL_PT_ERR_LOST] = "Lost trace data",
[INTEL_PT_ERR_UNK] = "Unknown error!",
[INTEL_PT_ERR_NELOOP] = "Never-ending loop (refer perf config intel-pt.max-loops)",
+ [INTEL_PT_ERR_EPTW] = "Broken emulated ptwrite",
};
int intel_pt__strerror(int code, char *buf, size_t buflen)
@@ -1535,17 +1539,108 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
return intel_pt_bug(decoder);
}
+struct eptw_data {
+ int bit_countdown;
+ uint64_t payload;
+};
+
+static int intel_pt_eptw_lookahead_cb(struct intel_pt_pkt_info *pkt_info)
+{
+ struct eptw_data *data = pkt_info->data;
+ int nr_bits;
+
+ switch (pkt_info->packet.type) {
+ case INTEL_PT_PAD:
+ case INTEL_PT_MNT:
+ case INTEL_PT_MODE_EXEC:
+ case INTEL_PT_MODE_TSX:
+ case INTEL_PT_MTC:
+ case INTEL_PT_FUP:
+ case INTEL_PT_CYC:
+ case INTEL_PT_CBR:
+ case INTEL_PT_TSC:
+ case INTEL_PT_TMA:
+ case INTEL_PT_PIP:
+ case INTEL_PT_VMCS:
+ case INTEL_PT_PSB:
+ case INTEL_PT_PSBEND:
+ case INTEL_PT_PTWRITE:
+ case INTEL_PT_PTWRITE_IP:
+ case INTEL_PT_EXSTOP:
+ case INTEL_PT_EXSTOP_IP:
+ case INTEL_PT_MWAIT:
+ case INTEL_PT_PWRE:
+ case INTEL_PT_PWRX:
+ case INTEL_PT_BBP:
+ case INTEL_PT_BIP:
+ case INTEL_PT_BEP:
+ case INTEL_PT_BEP_IP:
+ case INTEL_PT_CFE:
+ case INTEL_PT_CFE_IP:
+ case INTEL_PT_EVD:
+ break;
+
+ case INTEL_PT_TNT:
+ nr_bits = data->bit_countdown;
+ if (nr_bits > pkt_info->packet.count)
+ nr_bits = pkt_info->packet.count;
+ data->payload <<= nr_bits;
+ data->payload |= pkt_info->packet.payload >> (64 - nr_bits);
+ data->bit_countdown -= nr_bits;
+ return !data->bit_countdown;
+
+ case INTEL_PT_TIP_PGE:
+ case INTEL_PT_TIP_PGD:
+ case INTEL_PT_TIP:
+ case INTEL_PT_BAD:
+ case INTEL_PT_OVF:
+ case INTEL_PT_TRACESTOP:
+ default:
+ return 1;
+ }
+
+ return 0;
+}
+
+static int intel_pt_emulated_ptwrite(struct intel_pt_decoder *decoder)
+{
+ int n = 64 - decoder->tnt.count;
+ struct eptw_data data = {
+ .bit_countdown = n,
+ .payload = decoder->tnt.payload >> n,
+ };
+
+ decoder->emulated_ptwrite = false;
+ intel_pt_log("Emulated ptwrite detected\n");
+
+ intel_pt_pkt_lookahead(decoder, intel_pt_eptw_lookahead_cb, &data);
+ if (data.bit_countdown)
+ return -ECONNRESET;
+
+ decoder->state.type = INTEL_PT_PTW;
+ decoder->state.from_ip = decoder->ip;
+ decoder->state.to_ip = 0;
+ decoder->state.ptw_payload = data.payload;
+ return 0;
+}
+
static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
{
struct intel_pt_insn intel_pt_insn;
int err;
while (1) {
+ if (decoder->emulated_ptwrite)
+ return intel_pt_emulated_ptwrite(decoder);
err = intel_pt_walk_insn(decoder, &intel_pt_insn, 0);
- if (err == INTEL_PT_RETURN)
+ if (err == INTEL_PT_RETURN) {
+ decoder->emulated_ptwrite = intel_pt_insn.emulated_ptwrite;
return 0;
- if (err)
+ }
+ if (err) {
+ decoder->emulated_ptwrite = false;
return err;
+ }
if (intel_pt_insn.op == INTEL_PT_OP_RET) {
if (!decoder->return_compression) {
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index efb2cb3ae0ca..c773028df80e 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -58,6 +58,7 @@ enum {
INTEL_PT_ERR_LOST,
INTEL_PT_ERR_UNK,
INTEL_PT_ERR_NELOOP,
+ INTEL_PT_ERR_EPTW,
INTEL_PT_ERR_MAX,
};
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 9d5e65cec89b..1376077183f7 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -32,6 +32,7 @@ static void intel_pt_insn_decoder(struct insn *insn,
int ext;
intel_pt_insn->rel = 0;
+ intel_pt_insn->emulated_ptwrite = false;
if (insn_is_avx(insn)) {
intel_pt_insn->op = INTEL_PT_OP_OTHER;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
index c2861cfdd768..e3338b56a75f 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
@@ -37,6 +37,7 @@ enum intel_pt_insn_branch {
struct intel_pt_insn {
enum intel_pt_insn_op op;
enum intel_pt_insn_branch branch;
+ bool emulated_ptwrite;
int length;
int32_t rel;
unsigned char buf[INTEL_PT_INSN_BUF_SZ];
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index ec43d364d0de..62b2f375a94d 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -192,6 +192,7 @@ struct intel_pt_queue {
pid_t next_tid;
struct thread *thread;
struct machine *guest_machine;
+ struct thread *guest_thread;
struct thread *unknown_guest_thread;
pid_t guest_machine_pid;
bool exclude_kernel;
@@ -530,6 +531,7 @@ struct intel_pt_cache_entry {
u64 byte_cnt;
enum intel_pt_insn_op op;
enum intel_pt_insn_branch branch;
+ bool emulated_ptwrite;
int length;
int32_t rel;
char insn[INTEL_PT_INSN_BUF_SZ];
@@ -616,6 +618,7 @@ static int intel_pt_cache_add(struct dso *dso, struct machine *machine,
e->byte_cnt = byte_cnt;
e->op = intel_pt_insn->op;
e->branch = intel_pt_insn->branch;
+ e->emulated_ptwrite = intel_pt_insn->emulated_ptwrite;
e->length = intel_pt_insn->length;
e->rel = intel_pt_insn->rel;
memcpy(e->insn, intel_pt_insn->buf, INTEL_PT_INSN_BUF_SZ);
@@ -688,6 +691,11 @@ static int intel_pt_get_guest(struct intel_pt_queue *ptq)
ptq->guest_machine = NULL;
thread__zput(ptq->unknown_guest_thread);
+ if (symbol_conf.guest_code) {
+ thread__zput(ptq->guest_thread);
+ ptq->guest_thread = machines__findnew_guest_code(machines, pid);
+ }
+
machine = machines__find_guest(machines, pid);
if (!machine)
return -1;
@@ -702,6 +710,28 @@ static int intel_pt_get_guest(struct intel_pt_queue *ptq)
return 0;
}
+static inline bool intel_pt_jmp_16(struct intel_pt_insn *intel_pt_insn)
+{
+ return intel_pt_insn->rel == 16 && intel_pt_insn->branch == INTEL_PT_BR_UNCONDITIONAL;
+}
+
+#define PTWRITE_MAGIC "\x0f\x0bperf,ptwrite "
+#define PTWRITE_MAGIC_LEN 16
+
+static bool intel_pt_emulated_ptwrite(struct dso *dso, struct machine *machine, u64 offset)
+{
+ unsigned char buf[PTWRITE_MAGIC_LEN];
+ ssize_t len;
+
+ len = dso__data_read_offset(dso, machine, offset, buf, PTWRITE_MAGIC_LEN);
+ if (len == PTWRITE_MAGIC_LEN && !memcmp(buf, PTWRITE_MAGIC, PTWRITE_MAGIC_LEN)) {
+ intel_pt_log("Emulated ptwrite signature found\n");
+ return true;
+ }
+ intel_pt_log("Emulated ptwrite signature not found\n");
+ return false;
+}
+
static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
uint64_t *insn_cnt_ptr, uint64_t *ip,
uint64_t to_ip, uint64_t max_insn_cnt,
@@ -729,11 +759,16 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
cpumode = intel_pt_nr_cpumode(ptq, *ip, nr);
if (nr) {
- if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL ||
+ if ((!symbol_conf.guest_code && cpumode != PERF_RECORD_MISC_GUEST_KERNEL) ||
intel_pt_get_guest(ptq))
return -EINVAL;
machine = ptq->guest_machine;
- thread = ptq->unknown_guest_thread;
+ thread = ptq->guest_thread;
+ if (!thread) {
+ if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL)
+ return -EINVAL;
+ thread = ptq->unknown_guest_thread;
+ }
} else {
thread = ptq->thread;
if (!thread) {
@@ -764,6 +799,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
*ip += e->byte_cnt;
intel_pt_insn->op = e->op;
intel_pt_insn->branch = e->branch;
+ intel_pt_insn->emulated_ptwrite = e->emulated_ptwrite;
intel_pt_insn->length = e->length;
intel_pt_insn->rel = e->rel;
memcpy(intel_pt_insn->buf, e->insn,
@@ -795,8 +831,18 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
insn_cnt += 1;
- if (intel_pt_insn->branch != INTEL_PT_BR_NO_BRANCH)
+ if (intel_pt_insn->branch != INTEL_PT_BR_NO_BRANCH) {
+ bool eptw;
+ u64 offs;
+
+ if (!intel_pt_jmp_16(intel_pt_insn))
+ goto out;
+ /* Check for emulated ptwrite */
+ offs = offset + intel_pt_insn->length;
+ eptw = intel_pt_emulated_ptwrite(al.map->dso, machine, offs);
+ intel_pt_insn->emulated_ptwrite = eptw;
goto out;
+ }
if (max_insn_cnt && insn_cnt >= max_insn_cnt)
goto out_no_cache;
@@ -1300,6 +1346,7 @@ static void intel_pt_free_queue(void *priv)
if (!ptq)
return;
thread__zput(ptq->thread);
+ thread__zput(ptq->guest_thread);
thread__zput(ptq->unknown_guest_thread);
intel_pt_decoder_free(ptq->decoder);
zfree(&ptq->event_buf);
@@ -2372,6 +2419,10 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
ptq->sample_ipc = ptq->state->flags & INTEL_PT_SAMPLE_IPC;
}
+ /* Ensure guest code maps are set up */
+ if (symbol_conf.guest_code && (state->from_nr || state->to_nr))
+ intel_pt_get_guest(ptq);
+
/*
* Do PEBS first to allow for the possibility that the PEBS timestamp
* precedes the current timestamp.
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 95391236f5f6..009061852808 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -84,6 +84,14 @@ static int machine__set_mmap_name(struct machine *machine)
return machine->mmap_name ? 0 : -ENOMEM;
}
+static void thread__set_guest_comm(struct thread *thread, pid_t pid)
+{
+ char comm[64];
+
+ snprintf(comm, sizeof(comm), "[guest/%d]", pid);
+ thread__set_comm(thread, comm, 0);
+}
+
int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
{
int err = -ENOMEM;
@@ -119,13 +127,11 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
if (pid != HOST_KERNEL_ID) {
struct thread *thread = machine__findnew_thread(machine, -1,
pid);
- char comm[64];
if (thread == NULL)
goto out;
- snprintf(comm, sizeof(comm), "[guest/%d]", pid);
- thread__set_comm(thread, comm, 0);
+ thread__set_guest_comm(thread, pid);
thread__put(thread);
}
@@ -299,6 +305,8 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
rb_link_node(&machine->rb_node, parent, p);
rb_insert_color_cached(&machine->rb_node, &machines->guests, leftmost);
+ machine->machines = machines;
+
return machine;
}
@@ -384,6 +392,93 @@ struct machine *machines__find_guest(struct machines *machines, pid_t pid)
return machine;
}
+/*
+ * A common case for KVM test programs is that the test program acts as the
+ * hypervisor, creating, running and destroying the virtual machine, and
+ * providing the guest object code from its own object code. In this case,
+ * the VM is not running an OS, but only the functions loaded into it by the
+ * hypervisor test program, and conveniently, loaded at the same virtual
+ * addresses.
+ *
+ * Normally to resolve addresses, MMAP events are needed to map addresses
+ * back to the object code and debug symbols for that object code.
+ *
+ * Currently, there is no way to get such mapping information from guests
+ * but, in the scenario described above, the guest has the same mappings
+ * as the hypervisor, so support for that scenario can be achieved.
+ *
+ * To support that, copy the host thread's maps to the guest thread's maps.
+ * Note, we do not discover the guest until we encounter a guest event,
+ * which works well because it is not until then that we know that the host
+ * thread's maps have been set up.
+ *
+ * This function returns the guest thread. Apart from keeping the data
+ * structures sane, using a thread belonging to the guest machine, instead
+ * of the host thread, allows it to have its own comm (refer
+ * thread__set_guest_comm()).
+ */
+static struct thread *findnew_guest_code(struct machine *machine,
+ struct machine *host_machine,
+ pid_t pid)
+{
+ struct thread *host_thread;
+ struct thread *thread;
+ int err;
+
+ if (!machine)
+ return NULL;
+
+ thread = machine__findnew_thread(machine, -1, pid);
+ if (!thread)
+ return NULL;
+
+ /* Assume maps are set up if there are any */
+ if (thread->maps->nr_maps)
+ return thread;
+
+ host_thread = machine__find_thread(host_machine, -1, pid);
+ if (!host_thread)
+ goto out_err;
+
+ thread__set_guest_comm(thread, pid);
+
+ /*
+ * Guest code can be found in hypervisor process at the same address
+ * so copy host maps.
+ */
+ err = maps__clone(thread, host_thread->maps);
+ thread__put(host_thread);
+ if (err)
+ goto out_err;
+
+ return thread;
+
+out_err:
+ thread__zput(thread);
+ return NULL;
+}
+
+struct thread *machines__findnew_guest_code(struct machines *machines, pid_t pid)
+{
+ struct machine *host_machine = machines__find(machines, HOST_KERNEL_ID);
+ struct machine *machine = machines__findnew(machines, pid);
+
+ return findnew_guest_code(machine, host_machine, pid);
+}
+
+struct thread *machine__findnew_guest_code(struct machine *machine, pid_t pid)
+{
+ struct machines *machines = machine->machines;
+ struct machine *host_machine;
+
+ if (!machines)
+ return NULL;
+
+ host_machine = machines__find(machines, HOST_KERNEL_ID);
+
+ return findnew_guest_code(machine, host_machine, pid);
+}
+
void machines__process_guests(struct machines *machines,
machine__process_t process, void *data)
{
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 0023165422aa..5d7daf7cb7bc 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -18,6 +18,7 @@ struct symbol;
struct target;
struct thread;
union perf_event;
+struct machines;
/* Native host kernel uses -1 as pid index in machine */
#define HOST_KERNEL_ID (-1)
@@ -59,6 +60,7 @@ struct machine {
void *priv;
u64 db_id;
};
+ struct machines *machines;
bool trampolines_mapped;
};
@@ -162,10 +164,11 @@ void machines__process_guests(struct machines *machines,
struct machine *machines__add(struct machines *machines, pid_t pid,
const char *root_dir);
-struct machine *machines__find_host(struct machines *machines);
struct machine *machines__find(struct machines *machines, pid_t pid);
struct machine *machines__findnew(struct machines *machines, pid_t pid);
struct machine *machines__find_guest(struct machines *machines, pid_t pid);
+struct thread *machines__findnew_guest_code(struct machines *machines, pid_t pid);
+struct thread *machine__findnew_guest_code(struct machine *machine, pid_t pid);
void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
void machines__set_comm_exec(struct machines *machines, bool comm_exec);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index ed0ab838bcc5..c3c21a9c350b 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -314,6 +314,30 @@ static const char * const mem_hops[] = {
"board",
};
+static int perf_mem__op_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+ u64 op = PERF_MEM_LOCK_NA;
+ int l;
+
+ if (mem_info)
+ op = mem_info->data_src.mem_op;
+
+ if (op & PERF_MEM_OP_NA)
+ l = scnprintf(out, sz, "N/A");
+ else if (op & PERF_MEM_OP_LOAD)
+ l = scnprintf(out, sz, "LOAD");
+ else if (op & PERF_MEM_OP_STORE)
+ l = scnprintf(out, sz, "STORE");
+ else if (op & PERF_MEM_OP_PFETCH)
+ l = scnprintf(out, sz, "PFETCH");
+ else if (op & PERF_MEM_OP_EXEC)
+ l = scnprintf(out, sz, "EXEC");
+ else
+ l = scnprintf(out, sz, "No");
+
+ return l;
+}
+
int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
{
size_t i, l = 0;
@@ -466,7 +490,10 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in
{
int i = 0;
- i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+ i += scnprintf(out, sz, "|OP ");
+ i += perf_mem__op_scnprintf(out + i, sz - i, mem_info);
+ i += scnprintf(out + i, sz - i, "|LVL ");
+ i += perf_mem__lvl_scnprintf(out + i, sz, mem_info);
i += scnprintf(out + i, sz - i, "|SNP ");
i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
i += scnprintf(out + i, sz - i, "|TLB ");
@@ -582,6 +609,8 @@ do { \
}
if (lvl & P(LVL, MISS))
if (lvl & P(LVL, L1)) stats->st_l1miss++;
+ if (lvl & P(LVL, NA))
+ stats->st_na++;
} else {
/* unparsable data_src? */
stats->noparse++;
@@ -608,6 +637,7 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
stats->st_noadrs += add->st_noadrs;
stats->st_l1hit += add->st_l1hit;
stats->st_l1miss += add->st_l1miss;
+ stats->st_na += add->st_na;
stats->load += add->load;
stats->ld_excl += add->ld_excl;
stats->ld_shared += add->ld_shared;
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 916242f8020a..8a8b568baeee 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -63,6 +63,7 @@ struct c2c_stats {
u32 st_noadrs; /* cacheable store with no address */
u32 st_l1hit; /* count of stores that hit L1D */
u32 st_l1miss; /* count of stores that miss L1D */
+ u32 st_na; /* count of stores with memory level is not available */
u32 load; /* count of all loads in trace */
u32 ld_excl; /* exclusive loads, rmt/lcl DRAM - snp none/miss */
u32 ld_shared; /* shared loads, rmt/lcl DRAM - snp hit */
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index d8492e339521..ee8fcfa115e5 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -728,22 +728,23 @@ static int metricgroup__build_event_string(struct strbuf *events,
{
struct hashmap_entry *cur;
size_t bkt;
- bool no_group = true, has_duration = false;
+ bool no_group = true, has_tool_events = false;
+ bool tool_events[PERF_TOOL_MAX] = {false};
int ret = 0;
#define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0)
hashmap__for_each_entry(ctx->ids, cur, bkt) {
const char *sep, *rsep, *id = cur->key;
+ enum perf_tool_event ev;
pr_debug("found event %s\n", id);
- /*
- * Duration time maps to a software event and can make
- * groups not count. Always use it outside a
- * group.
- */
- if (!strcmp(id, "duration_time")) {
- has_duration = true;
+
+ /* Always move tool events outside of the group. */
+ ev = perf_tool_event__from_str(id);
+ if (ev != PERF_TOOL_NONE) {
+ has_tool_events = true;
+ tool_events[ev] = true;
continue;
}
/* Separate events with commas and open the group if necessary. */
@@ -802,16 +803,25 @@ static int metricgroup__build_event_string(struct strbuf *events,
RETURN_IF_NON_ZERO(ret);
}
}
- if (has_duration) {
- if (no_group) {
- /* Strange case of a metric of just duration_time. */
- ret = strbuf_addf(events, "duration_time");
- } else if (!has_constraint)
- ret = strbuf_addf(events, "}:W,duration_time");
- else
- ret = strbuf_addf(events, ",duration_time");
- } else if (!no_group && !has_constraint)
+ if (!no_group && !has_constraint) {
ret = strbuf_addf(events, "}:W");
+ RETURN_IF_NON_ZERO(ret);
+ }
+ if (has_tool_events) {
+ int i;
+
+ perf_tool_event__for_each_event(i) {
+ if (tool_events[i]) {
+ if (!no_group) {
+ ret = strbuf_addch(events, ',');
+ RETURN_IF_NON_ZERO(ret);
+ }
+ no_group = false;
+ ret = strbuf_addstr(events, perf_tool_event__to_str(i));
+ RETURN_IF_NON_ZERO(ret);
+ }
+ }
+ }
return ret;
#undef RETURN_IF_NON_ZERO
@@ -1117,7 +1127,7 @@ out:
/**
* metric_list_cmp - list_sort comparator that sorts metrics with more events to
- * the front. duration_time is excluded from the count.
+ * the front. tool events are excluded from the count.
*/
static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l,
const struct list_head *r)
@@ -1125,15 +1135,19 @@ static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l,
const struct metric *left = container_of(l, struct metric, nd);
const struct metric *right = container_of(r, struct metric, nd);
struct expr_id_data *data;
- int left_count, right_count;
+ int i, left_count, right_count;
left_count = hashmap__size(left->pctx->ids);
- if (!expr__get_id(left->pctx, "duration_time", &data))
- left_count--;
+ perf_tool_event__for_each_event(i) {
+ if (!expr__get_id(left->pctx, perf_tool_event__to_str(i), &data))
+ left_count--;
+ }
right_count = hashmap__size(right->pctx->ids);
- if (!expr__get_id(right->pctx, "duration_time", &data))
- right_count--;
+ perf_tool_event__for_each_event(i) {
+ if (!expr__get_id(right->pctx, perf_tool_event__to_str(i), &data))
+ right_count--;
+ }
return right_count - left_count;
}
@@ -1270,6 +1284,30 @@ static void metricgroup__free_metrics(struct list_head *metric_list)
}
/**
+ * find_tool_events - Search for the pressence of tool events in metric_list.
+ * @metric_list: List to take metrics from.
+ * @tool_events: Array of false values, indices corresponding to tool events set
+ * to true if tool event is found.
+ */
+static void find_tool_events(const struct list_head *metric_list,
+ bool tool_events[PERF_TOOL_MAX])
+{
+ struct metric *m;
+
+ list_for_each_entry(m, metric_list, nd) {
+ int i;
+
+ perf_tool_event__for_each_event(i) {
+ struct expr_id_data *data;
+
+ if (!tool_events[i] &&
+ !expr__get_id(m->pctx, perf_tool_event__to_str(i), &data))
+ tool_events[i] = true;
+ }
+ }
+}
+
+/**
* build_combined_expr_ctx - Make an expr_parse_ctx with all has_constraint
* metric IDs, as the IDs are held in a set,
* duplicates will be removed.
@@ -1318,11 +1356,14 @@ err_out:
* @ids: the event identifiers parsed from a metric.
* @modifier: any modifiers added to the events.
* @has_constraint: false if events should be placed in a weak group.
+ * @tool_events: entries set true if the tool event of index could be present in
+ * the overall list of metrics.
* @out_evlist: the created list of events.
*/
static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
struct expr_parse_ctx *ids, const char *modifier,
- bool has_constraint, struct evlist **out_evlist)
+ bool has_constraint, const bool tool_events[PERF_TOOL_MAX],
+ struct evlist **out_evlist)
{
struct parse_events_error parse_error;
struct evlist *parsed_evlist;
@@ -1331,26 +1372,29 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
*out_evlist = NULL;
if (!metric_no_merge || hashmap__size(ids->ids) == 0) {
- char *tmp;
+ int i;
/*
- * We may fail to share events between metrics because
- * duration_time isn't present in one metric. For example, a
- * ratio of cache misses doesn't need duration_time but the same
- * events may be used for a misses per second. Events without
- * sharing implies multiplexing, that is best avoided, so place
- * duration_time in every group.
+ * We may fail to share events between metrics because a tool
+ * event isn't present in one metric. For example, a ratio of
+ * cache misses doesn't need duration_time but the same events
+ * may be used for a misses per second. Events without sharing
+ * implies multiplexing, that is best avoided, so place
+ * all tool events in every group.
*
* Also, there may be no ids/events in the expression parsing
* context because of constant evaluation, e.g.:
* event1 if #smt_on else 0
- * Add a duration_time event to avoid a parse error on an empty
- * string.
+ * Add a tool event to avoid a parse error on an empty string.
*/
- tmp = strdup("duration_time");
- if (!tmp)
- return -ENOMEM;
+ perf_tool_event__for_each_event(i) {
+ if (tool_events[i]) {
+ char *tmp = strdup(perf_tool_event__to_str(i));
- ids__insert(ids->ids, tmp);
+ if (!tmp)
+ return -ENOMEM;
+ ids__insert(ids->ids, tmp);
+ }
+ }
}
ret = metricgroup__build_event_string(&events, ids, modifier,
has_constraint);
@@ -1392,6 +1436,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
struct evlist *combined_evlist = NULL;
LIST_HEAD(metric_list);
struct metric *m;
+ bool tool_events[PERF_TOOL_MAX] = {false};
int ret;
if (metric_events_list->nr_entries == 0)
@@ -1407,12 +1452,15 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
if (!metric_no_merge) {
struct expr_parse_ctx *combined = NULL;
+ find_tool_events(&metric_list, tool_events);
+
ret = build_combined_expr_ctx(&metric_list, &combined);
if (!ret && combined && hashmap__size(combined->ids)) {
ret = parse_ids(metric_no_merge, fake_pmu, combined,
/*modifier=*/NULL,
/*has_constraint=*/true,
+ tool_events,
&combined_evlist);
}
if (combined)
@@ -1460,7 +1508,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
}
if (!metric_evlist) {
ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
- m->has_constraint, &m->evlist);
+ m->has_constraint, tool_events, &m->evlist);
if (ret)
goto out;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index dd84fed698a3..30a9d915853d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -154,6 +154,21 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
},
};
+struct event_symbol event_symbols_tool[PERF_TOOL_MAX] = {
+ [PERF_TOOL_DURATION_TIME] = {
+ .symbol = "duration_time",
+ .alias = "",
+ },
+ [PERF_TOOL_USER_TIME] = {
+ .symbol = "user_time",
+ .alias = "",
+ },
+ [PERF_TOOL_SYSTEM_TIME] = {
+ .symbol = "system_time",
+ .alias = "",
+ },
+};
+
#define __PERF_EVENT_FIELD(config, name) \
((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
@@ -402,14 +417,16 @@ static int add_event_tool(struct list_head *list, int *idx,
if (!evsel)
return -ENOMEM;
evsel->tool_event = tool_event;
- if (tool_event == PERF_TOOL_DURATION_TIME) {
+ if (tool_event == PERF_TOOL_DURATION_TIME
+ || tool_event == PERF_TOOL_USER_TIME
+ || tool_event == PERF_TOOL_SYSTEM_TIME) {
free((char *)evsel->unit);
evsel->unit = strdup("ns");
}
return 0;
}
-static int parse_aliases(char *str, const char *names[][EVSEL__MAX_ALIASES], int size)
+static int parse_aliases(char *str, const char *const names[][EVSEL__MAX_ALIASES], int size)
{
int i, j;
int n, longest = -1;
@@ -3056,21 +3073,34 @@ out_enomem:
return evt_num;
}
-static void print_tool_event(const char *name, const char *event_glob,
+static void print_tool_event(const struct event_symbol *syms, const char *event_glob,
bool name_only)
{
- if (event_glob && !strglobmatch(name, event_glob))
+ if (syms->symbol == NULL)
+ return;
+
+ if (event_glob && !(strglobmatch(syms->symbol, event_glob) ||
+ (syms->alias && strglobmatch(syms->alias, event_glob))))
return;
+
if (name_only)
- printf("%s ", name);
- else
+ printf("%s ", syms->symbol);
+ else {
+ char name[MAX_NAME_LEN];
+ if (syms->alias && strlen(syms->alias))
+ snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
+ else
+ strlcpy(name, syms->symbol, MAX_NAME_LEN);
printf(" %-50s [%s]\n", name, "Tool event");
-
+ }
}
void print_tool_events(const char *event_glob, bool name_only)
{
- print_tool_event("duration_time", event_glob, name_only);
+ // Start at 1 because the first enum entry symbols no tool event
+ for (int i = 1; i < PERF_TOOL_MAX; ++i) {
+ print_tool_event(event_symbols_tool + i, event_glob, name_only);
+ }
if (pager_in_use())
printf("\n");
}
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5b6e4b5249cf..3a9ce96c8bce 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -353,6 +353,8 @@ alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_AL
emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
duration_time { return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
+user_time { return tool(yyscanner, PERF_TOOL_USER_TIME); }
+system_time { return tool(yyscanner, PERF_TOOL_SYSTEM_TIME); }
bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index caed0336429f..ce80b79be103 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -86,9 +86,21 @@ bool is_directory(const char *base_path, const struct dirent *dent)
char path[PATH_MAX];
struct stat st;
- sprintf(path, "%s/%s", base_path, dent->d_name);
+ snprintf(path, sizeof(path), "%s/%s", base_path, dent->d_name);
if (stat(path, &st))
return false;
return S_ISDIR(st.st_mode);
}
+
+bool is_executable_file(const char *base_path, const struct dirent *dent)
+{
+ char path[PATH_MAX];
+ struct stat st;
+
+ snprintf(path, sizeof(path), "%s/%s", base_path, dent->d_name);
+ if (stat(path, &st))
+ return false;
+
+ return !S_ISDIR(st.st_mode) && (st.st_mode & S_IXUSR);
+}
diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h
index 083429b7efa3..d94902c22222 100644
--- a/tools/perf/util/path.h
+++ b/tools/perf/util/path.h
@@ -12,5 +12,6 @@ int path__join3(char *bf, size_t size, const char *path1, const char *path2, con
bool is_regular_file(const char *file);
bool is_directory(const char *base_path, const struct dirent *dent);
+bool is_executable_file(const char *base_path, const struct dirent *dent);
#endif /* _PERF_PATH_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 413f2d19c13f..659eb4e4b34b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -392,6 +392,18 @@ static const char *get_dsoname(struct map *map)
return dsoname;
}
+static unsigned long get_offset(struct symbol *sym, struct addr_location *al)
+{
+ unsigned long offset;
+
+ if (al->addr < sym->end)
+ offset = al->addr - sym->start;
+ else
+ offset = al->addr - al->map->start - sym->start;
+
+ return offset;
+}
+
static PyObject *python_process_callchain(struct perf_sample *sample,
struct evsel *evsel,
struct addr_location *al)
@@ -443,6 +455,25 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
_PyUnicode_FromStringAndSize(node->ms.sym->name,
node->ms.sym->namelen));
pydict_set_item_string_decref(pyelem, "sym", pysym);
+
+ if (node->ms.map) {
+ struct map *map = node->ms.map;
+ struct addr_location node_al;
+ unsigned long offset;
+
+ node_al.addr = map->map_ip(map, node->ip);
+ node_al.map = map;
+ offset = get_offset(node->ms.sym, &node_al);
+
+ pydict_set_item_string_decref(
+ pyelem, "sym_off",
+ PyLong_FromUnsignedLongLong(offset));
+ }
+ if (node->srcline && strcmp(":0", node->srcline)) {
+ pydict_set_item_string_decref(
+ pyelem, "sym_srcline",
+ _PyUnicode_FromString(node->srcline));
+ }
}
if (node->ms.map) {
@@ -520,18 +551,6 @@ exit:
return pylist;
}
-static unsigned long get_offset(struct symbol *sym, struct addr_location *al)
-{
- unsigned long offset;
-
- if (al->addr < sym->end)
- offset = al->addr - sym->start;
- else
- offset = al->addr - al->map->start - sym->start;
-
- return offset;
-}
-
static int get_symoff(struct symbol *sym, struct addr_location *al,
bool print_off, char *bf, int size)
{
@@ -2074,7 +2093,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
fprintf(ofp, "\t\tfor node in common_callchain:");
fprintf(ofp, "\n\t\t\tif 'sym' in node:");
- fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
+ fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x] %%s%%s%%s%%s\" %% (");
+ fprintf(ofp, "\n\t\t\t\t\tnode['ip'], node['sym']['name'],");
+ fprintf(ofp, "\n\t\t\t\t\t\"+0x{:x}\".format(node['sym_off']) if 'sym_off' in node else \"\",");
+ fprintf(ofp, "\n\t\t\t\t\t\" ({})\".format(node['dso']) if 'dso' in node else \"\",");
+ fprintf(ofp, "\n\t\t\t\t\t\" \" + node['sym_srcline'] if 'sym_srcline' in node else \"\"))");
fprintf(ofp, "\n\t\t\telse:");
fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
fprintf(ofp, "\t\tprint()\n\n");
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 45a30040ec8d..0aa818977d2b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
struct branch_entry *entries = perf_sample__branch_entries(sample);
uint64_t i;
- printf("%s: nr:%" PRIu64 "\n",
- !callstack ? "... branch stack" : "... branch callstack",
- sample->branch_stack->nr);
+ if (!callstack) {
+ printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+ } else {
+ /* the reason of adding 1 to nr is because after expanding
+ * branch stack it generates nr + 1 callstack records. e.g.,
+ * B()->C()
+ * A()->B()
+ * the final callstack should be:
+ * C()
+ * B()
+ * A()
+ */
+ printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+ }
for (i = 0; i < sample->branch_stack->nr; i++) {
struct branch_entry *e = &entries[i];
@@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
(unsigned)e->flags.reserved,
e->flags.type ? branch_type_name(e->flags.type) : "");
} else {
- printf("..... %2"PRIu64": %016" PRIx64 "\n",
- i, i > 0 ? e->from : e->to);
+ if (i == 0) {
+ printf("..... %2"PRIu64": %016" PRIx64 "\n"
+ "..... %2"PRIu64": %016" PRIx64 "\n",
+ i, e->to, i+1, e->from);
+ } else {
+ printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+ }
}
}
}
@@ -1410,6 +1426,13 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
else
pid = sample->pid;
+ /*
+ * Guest code machine is created as needed and does not use
+ * DEFAULT_GUEST_KERNEL_ID.
+ */
+ if (symbol_conf.guest_code)
+ return machines__findnew(machines, pid);
+
return machines__find_guest(machines, pid);
}
@@ -2576,7 +2599,7 @@ int perf_session__process_events(struct perf_session *session)
if (perf_data__is_pipe(session->data))
return __perf_session__process_pipe_events(session);
- if (perf_data__is_dir(session->data))
+ if (perf_data__is_dir(session->data) && session->data->dir.nr)
return __perf_session__process_dir_events(session);
return __perf_session__process_events(session);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 138e3ab9d638..606f09b09226 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -610,6 +610,19 @@ static bool hybrid_uniquify(struct evsel *evsel)
return perf_pmu__has_hybrid() && !is_uncore(evsel);
}
+static bool hybrid_merge(struct evsel *counter, struct perf_stat_config *config,
+ bool check)
+{
+ if (hybrid_uniquify(counter)) {
+ if (check)
+ return config && config->hybrid_merge;
+ else
+ return config && !config->hybrid_merge;
+ }
+
+ return false;
+}
+
static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
bool first),
@@ -618,9 +631,9 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
if (counter->merged_stat)
return false;
cb(config, counter, data, true);
- if (config->no_merge || hybrid_uniquify(counter))
+ if (config->no_merge || hybrid_merge(counter, config, false))
uniquify_event_name(counter);
- else if (counter->auto_merge_stats)
+ else if (counter->auto_merge_stats || hybrid_merge(counter, config, true))
collect_all_aliases(config, counter, cb, data);
return true;
}
@@ -751,11 +764,11 @@ static int cmp_val(const void *a, const void *b)
static struct perf_aggr_thread_value *sort_aggr_thread(
struct evsel *counter,
- int nthreads, int ncpus,
int *ret,
struct target *_target)
{
- int cpu, thread, i = 0;
+ int nthreads = perf_thread_map__nr(counter->core.threads);
+ int i = 0;
double uval;
struct perf_aggr_thread_value *buf;
@@ -763,13 +776,17 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
if (!buf)
return NULL;
- for (thread = 0; thread < nthreads; thread++) {
+ for (int thread = 0; thread < nthreads; thread++) {
+ int idx;
u64 ena = 0, run = 0, val = 0;
- for (cpu = 0; cpu < ncpus; cpu++) {
- val += perf_counts(counter->counts, cpu, thread)->val;
- ena += perf_counts(counter->counts, cpu, thread)->ena;
- run += perf_counts(counter->counts, cpu, thread)->run;
+ perf_cpu_map__for_each_idx(idx, evsel__cpus(counter)) {
+ struct perf_counts_values *counts =
+ perf_counts(counter->counts, idx, thread);
+
+ val += counts->val;
+ ena += counts->ena;
+ run += counts->run;
}
uval = val * counter->scale;
@@ -804,13 +821,11 @@ static void print_aggr_thread(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
FILE *output = config->output;
- int nthreads = perf_thread_map__nr(counter->core.threads);
- int ncpus = perf_cpu_map__nr(counter->core.cpus);
int thread, sorted_threads;
struct aggr_cpu_id id;
struct perf_aggr_thread_value *buf;
- buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
+ buf = sort_aggr_thread(counter, &sorted_threads, _target);
if (!buf) {
perror("cannot sort aggr thread");
return;
@@ -933,8 +948,6 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
struct evsel *counter;
bool first = true;
- if (prefix)
- fputs(prefix, config->output);
evlist__for_each_entry(evlist, counter) {
u64 ena, run, val;
double uval;
@@ -946,6 +959,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
if (first) {
+ if (prefix)
+ fputs(prefix, config->output);
aggr_printout(config, counter, id, 0);
first = false;
}
@@ -957,7 +972,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
printout(config, id, 0, counter, uval, prefix,
run, ena, 1.0, &rt_stat);
}
- fputc('\n', config->output);
+ if (!first)
+ fputc('\n', config->output);
}
}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 10af7804e482..979c8cb918f7 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -26,6 +26,7 @@
struct runtime_stat rt_stat;
struct stats walltime_nsecs_stats;
+struct rusage_stats ru_stats;
struct saved_value {
struct rb_node rb_node;
@@ -199,6 +200,7 @@ void perf_stat__reset_shadow_stats(void)
{
reset_stat(&rt_stat);
memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+ memset(&ru_stats, 0, sizeof(ru_stats));
}
void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
@@ -831,10 +833,31 @@ static int prepare_metric(struct evsel **metric_events,
u64 metric_total = 0;
int source_count;
- if (!strcmp(metric_events[i]->name, "duration_time")) {
- stats = &walltime_nsecs_stats;
- scale = 1e-9;
+ if (evsel__is_tool(metric_events[i])) {
source_count = 1;
+ switch (metric_events[i]->tool_event) {
+ case PERF_TOOL_DURATION_TIME:
+ stats = &walltime_nsecs_stats;
+ scale = 1e-9;
+ break;
+ case PERF_TOOL_USER_TIME:
+ stats = &ru_stats.ru_utime_usec_stat;
+ scale = 1e-6;
+ break;
+ case PERF_TOOL_SYSTEM_TIME:
+ stats = &ru_stats.ru_stime_usec_stat;
+ scale = 1e-6;
+ break;
+ case PERF_TOOL_NONE:
+ pr_err("Invalid tool event 'none'");
+ abort();
+ case PERF_TOOL_MAX:
+ pr_err("Invalid tool event 'max'");
+ abort();
+ default:
+ pr_err("Unknown tool event '%s'", evsel__name(metric_events[i]));
+ abort();
+ }
} else {
v = saved_value_lookup(metric_events[i], cpu_map_idx, false,
STAT_NONE, 0, st,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 817a2de264b4..37ea2d044708 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -117,7 +117,9 @@ static void perf_stat_evsel_id_init(struct evsel *evsel)
/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
- if (!strcmp(evsel__name(evsel), id_str[i])) {
+ if (!strcmp(evsel__name(evsel), id_str[i]) ||
+ (strstr(evsel__name(evsel), id_str[i]) && evsel->pmu_name
+ && strstr(evsel__name(evsel), evsel->pmu_name))) {
ps->id = i;
break;
}
@@ -235,14 +237,12 @@ void evlist__reset_prev_raw_counts(struct evlist *evlist)
static void evsel__copy_prev_raw_counts(struct evsel *evsel)
{
- int ncpus = evsel__nr_cpus(evsel);
- int nthreads = perf_thread_map__nr(evsel->core.threads);
+ int idx, nthreads = perf_thread_map__nr(evsel->core.threads);
for (int thread = 0; thread < nthreads; thread++) {
- for (int cpu = 0; cpu < ncpus; cpu++) {
- *perf_counts(evsel->counts, cpu, thread) =
- *perf_counts(evsel->prev_raw_counts, cpu,
- thread);
+ perf_cpu_map__for_each_idx(idx, evsel__cpus(evsel)) {
+ *perf_counts(evsel->counts, idx, thread) =
+ *perf_counts(evsel->prev_raw_counts, idx, thread);
}
}
@@ -472,9 +472,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
int perf_event__process_stat_event(struct perf_session *session,
union perf_event *event)
{
- struct perf_counts_values count;
+ struct perf_counts_values count, *ptr;
struct perf_record_stat *st = &event->stat;
struct evsel *counter;
+ int cpu_map_idx;
count.val = st->val;
count.ena = st->ena;
@@ -485,8 +486,18 @@ int perf_event__process_stat_event(struct perf_session *session,
pr_err("Failed to resolve counter for stat event.\n");
return -EINVAL;
}
-
- *perf_counts(counter->counts, st->cpu, st->thread) = count;
+ cpu_map_idx = perf_cpu_map__idx(evsel__cpus(counter), (struct perf_cpu){.cpu = st->cpu});
+ if (cpu_map_idx == -1) {
+ pr_err("Invalid CPU %d for event %s.\n", st->cpu, evsel__name(counter));
+ return -EINVAL;
+ }
+ ptr = perf_counts(counter->counts, cpu_map_idx, st->thread);
+ if (ptr == NULL) {
+ pr_err("Failed to find perf count for CPU %d thread %d on event %s.\n",
+ st->cpu, st->thread, evsel__name(counter));
+ return -EINVAL;
+ }
+ *ptr = count;
counter->supported = true;
return 0;
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 335d19cc3063..b5aeb8e6d34b 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -108,6 +108,11 @@ struct runtime_stat {
struct rblist value_list;
};
+struct rusage_stats {
+ struct stats ru_utime_usec_stat;
+ struct stats ru_stime_usec_stat;
+};
+
typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu);
struct perf_stat_config {
@@ -122,6 +127,7 @@ struct perf_stat_config {
bool ru_display;
bool big_num;
bool no_merge;
+ bool hybrid_merge;
bool walltime_run_table;
bool all_kernel;
bool all_user;
@@ -148,6 +154,7 @@ struct perf_stat_config {
const char *csv_sep;
struct stats *walltime_nsecs_stats;
struct rusage ru_data;
+ struct rusage_stats *ru_stats;
struct cpu_aggr_map *aggr_map;
aggr_get_id_t aggr_get_id;
struct cpu_aggr_map *cpus_aggr_map;
@@ -177,6 +184,20 @@ static inline void init_stats(struct stats *stats)
stats->max = 0;
}
+static inline void init_rusage_stats(struct rusage_stats *ru_stats) {
+ init_stats(&ru_stats->ru_utime_usec_stat);
+ init_stats(&ru_stats->ru_stime_usec_stat);
+}
+
+static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rusage* rusage) {
+ const u64 us_to_ns = 1000;
+ const u64 s_to_ns = 1000000000;
+ update_stats(&ru_stats->ru_utime_usec_stat,
+ (rusage->ru_utime.tv_usec * us_to_ns + rusage->ru_utime.tv_sec * s_to_ns));
+ update_stats(&ru_stats->ru_stime_usec_stat,
+ (rusage->ru_stime.tv_usec * us_to_ns + rusage->ru_stime.tv_sec * s_to_ns));
+}
+
struct evsel;
struct evlist;
@@ -196,6 +217,7 @@ bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id);
extern struct runtime_stat rt_stat;
extern struct stats walltime_nsecs_stats;
+extern struct rusage_stats ru_stats;
typedef void (*print_metric_t)(struct perf_stat_config *config,
void *ctx, const char *color, const char *unit,
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 31cd59a2b66e..ecd377938eea 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
* For misannotated, zeroed, ASM function sizes.
*/
if (nr > 0) {
- symbols__fixup_end(&dso->symbols);
+ symbols__fixup_end(&dso->symbols, false);
symbols__fixup_duplicate(&dso->symbols);
if (kmap) {
/*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dea0fc495185..f72baf636724 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str)
return tail - str;
}
-void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- p->end = c->start;
-}
-
const char * __weak arch__normalize_symbol_name(const char *name)
{
return name;
@@ -217,7 +212,8 @@ again:
}
}
-void symbols__fixup_end(struct rb_root_cached *symbols)
+/* Update zero-sized symbols using the address of the next symbol */
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
{
struct rb_node *nd, *prevnd = rb_first_cached(symbols);
struct symbol *curr, *prev;
@@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
prev = curr;
curr = rb_entry(nd, struct symbol, rb_node);
- if (prev->end == prev->start || prev->end != curr->start)
- arch__symbols__fixup_end(prev, curr);
+ /*
+ * On some architecture kernel text segment start is located at
+ * some low memory address, while modules are located at high
+ * memory addresses (or vice versa). The gap between end of
+ * kernel text segment and beginning of first module's text
+ * segment is very big. Therefore do not fill this gap and do
+ * not assign it to the kernel dso map (kallsyms).
+ *
+ * In kallsyms, it determines module symbols using '[' character
+ * like in:
+ * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi]
+ */
+ if (prev->end == prev->start) {
+ /* Last kernel/module symbol mapped to end of page */
+ if (is_kallsyms && (!strchr(prev->name, '[') !=
+ !strchr(curr->name, '[')))
+ prev->end = roundup(prev->end + 4096, 4096);
+ else
+ prev->end = curr->start;
+
+ pr_debug4("%s sym:%s end:%#" PRIx64 "\n",
+ __func__, prev->name, prev->end);
+ }
}
/* Last entry */
@@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
if (kallsyms__delta(kmap, filename, &delta))
return -1;
- symbols__fixup_end(&dso->symbols);
+ symbols__fixup_end(&dso->symbols, true);
symbols__fixup_duplicate(&dso->symbols);
if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
@@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
#undef bfd_asymbol_section
#endif
- symbols__fixup_end(&dso->symbols);
+ symbols__fixup_end(&dso->symbols, false);
symbols__fixup_duplicate(&dso->symbols);
dso->adjust_symbols = 1;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fbf866d82dcc..0b893dcc8ea6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
bool kernel);
void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
void symbols__fixup_duplicate(struct rb_root_cached *symbols);
-void symbols__fixup_end(struct rb_root_cached *symbols);
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms);
void maps__fixup_end(struct maps *maps);
typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
@@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name);
#define SYMBOL_A 0
#define SYMBOL_B 1
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
int arch__compare_symbol_names(const char *namea, const char *nameb);
int arch__compare_symbol_names_n(const char *namea, const char *nameb,
unsigned int n);
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index a70b3ec09dac..bc3d046fbb63 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -43,7 +43,8 @@ struct symbol_conf {
report_individual_block,
inline_name,
disable_add2line_warn,
- buildid_mmap2;
+ buildid_mmap2,
+ guest_code;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
diff --git a/tools/perf/util/topdown.c b/tools/perf/util/topdown.c
index 1081b20f9891..a369f84ceb6a 100644
--- a/tools/perf/util/topdown.c
+++ b/tools/perf/util/topdown.c
@@ -1,18 +1,24 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include "pmu.h"
+#include "pmu-hybrid.h"
#include "topdown.h"
-int topdown_filter_events(const char **attr, char **str, bool use_group)
+int topdown_filter_events(const char **attr, char **str, bool use_group,
+ const char *pmu_name)
{
int off = 0;
int i;
int len = 0;
char *s;
+ bool is_hybrid = perf_pmu__is_hybrid(pmu_name);
for (i = 0; attr[i]; i++) {
- if (pmu_have_event("cpu", attr[i])) {
- len += strlen(attr[i]) + 1;
+ if (pmu_have_event(pmu_name, attr[i])) {
+ if (is_hybrid)
+ len += strlen(attr[i]) + strlen(pmu_name) + 3;
+ else
+ len += strlen(attr[i]) + 1;
attr[i - off] = attr[i];
} else
off++;
@@ -30,7 +36,10 @@ int topdown_filter_events(const char **attr, char **str, bool use_group)
if (use_group)
*s++ = '{';
for (i = 0; attr[i]; i++) {
- strcpy(s, attr[i]);
+ if (!is_hybrid)
+ strcpy(s, attr[i]);
+ else
+ sprintf(s, "%s/%s/", pmu_name, attr[i]);
s += strlen(s);
*s++ = ',';
}
diff --git a/tools/perf/util/topdown.h b/tools/perf/util/topdown.h
index 2f0d0b887639..118e75281f93 100644
--- a/tools/perf/util/topdown.h
+++ b/tools/perf/util/topdown.h
@@ -7,6 +7,7 @@ bool arch_topdown_check_group(bool *warn);
void arch_topdown_group_warn(void);
bool arch_topdown_sample_read(struct evsel *leader);
-int topdown_filter_events(const char **attr, char **str, bool use_group);
+int topdown_filter_events(const char **attr, char **str, bool use_group,
+ const char *pmu_name);
#endif
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index f8571a66d063..eeb83c80f458 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -430,6 +430,11 @@ void perf_debuginfod_setup(struct perf_debuginfod *di)
setenv("DEBUGINFOD_URLS", di->urls, 1);
pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS"));
+
+#ifndef HAVE_DEBUGINFOD_SUPPORT
+ if (di->set)
+ pr_warning("WARNING: debuginfod support requested, but perf is not built with it\n");
+#endif
}
/*