summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/Documentation/intel-hybrid.txt10
-rw-r--r--tools/perf/Documentation/perf-record.txt7
-rw-r--r--tools/perf/Makefile.config2
-rw-r--r--tools/perf/Makefile.perf24
-rw-r--r--tools/perf/builtin-c2c.c12
-rw-r--r--tools/perf/builtin-lock.c3
-rw-r--r--tools/perf/builtin-record.c34
-rw-r--r--tools/perf/builtin-sched.c24
-rw-r--r--tools/perf/builtin-script.c5
-rw-r--r--tools/perf/builtin-stat.c6
-rw-r--r--tools/perf/dlfilters/dlfilter-show-cycles.c4
-rw-r--r--tools/perf/tests/cpumap.c19
-rw-r--r--tools/perf/tests/sample-parsing.c14
-rwxr-xr-xtools/perf/tests/shell/stat.sh19
-rw-r--r--tools/perf/trace/beauty/include/linux/socket.h16
-rw-r--r--tools/perf/util/affinity.c8
-rw-r--r--tools/perf/util/cpumap.c80
-rw-r--r--tools/perf/util/cpumap.h4
-rw-r--r--tools/perf/util/event.h25
-rw-r--r--tools/perf/util/evsel.c29
-rw-r--r--tools/perf/util/genelf.c20
-rw-r--r--tools/perf/util/metricgroup.c3
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c19
-rw-r--r--tools/perf/util/session.c65
-rw-r--r--tools/perf/util/stat-shadow.c24
-rw-r--r--tools/perf/util/synthetic-events.c99
-rw-r--r--tools/perf/util/synthetic-events.h2
27 files changed, 376 insertions, 201 deletions
diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt
index c9302096dc46..e7a776ad25d7 100644
--- a/tools/perf/Documentation/intel-hybrid.txt
+++ b/tools/perf/Documentation/intel-hybrid.txt
@@ -21,11 +21,6 @@ cat /sys/devices/cpu_atom/cpus
It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus.
-Quickstart
-
-List hybrid event
------------------
-
As before, use perf-list to list the symbolic event.
perf list
@@ -40,7 +35,6 @@ the event is belong to. Same event name but with different pmu can
be supported.
Enable hybrid event with a specific pmu
----------------------------------------
To enable a core only event or atom only event, following syntax is supported:
@@ -53,7 +47,6 @@ For example, count the 'cycles' event on core cpus.
perf stat -e cpu_core/cycles/
Create two events for one hardware event automatically
-------------------------------------------------------
When creating one event and the event is available on both atom and core,
two events are created automatically. One is for atom, the other is for
@@ -132,7 +125,6 @@ For perf-stat result, it displays two events:
The first 'cycles' is core event, the second 'cycles' is atom event.
Thread mode example:
---------------------
perf-stat reports the scaled counts for hybrid event and with a percentage
displayed. The percentage is the event's running time/enabling time.
@@ -176,14 +168,12 @@ perf_event_attr:
604,097,080 cpu_atom/cycles/ (99.57%)
perf-record:
-------------
If there is no '-e' specified in perf record, on hybrid platform,
it creates two default 'cycles' and adds them to event list. One
is for core, the other is for atom.
perf-stat:
-----------
If there is no '-e' specified in perf stat, on hybrid platform,
besides of software events, following events are created and
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 099817ef5150..0228efc96686 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -397,6 +397,9 @@ following filters are defined:
- abort_tx: only when the target is a hardware transaction abort
- cond: conditional branches
- save_type: save branch type during sampling in case binary is not available later
+ For the platforms with Intel Arch LBR support (12th-Gen+ client or
+ 4th-Gen Xeon+ server), the save branch type is unconditionally enabled
+ when the taken branch stack sampling is enabled.
+
The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
@@ -757,8 +760,6 @@ events in data directory files. Option specified with no or empty value
defaults to CPU layout. Masks defined or provided by the option value are
filtered through the mask provided by -C option.
-include::intel-hybrid.txt[]
-
--debuginfod[=URLs]::
Specify debuginfod URL to be used when cacheing perf.data binaries,
it follows the same syntax as the DEBUGINFOD_URLS variable, like:
@@ -778,6 +779,8 @@ include::intel-hybrid.txt[]
only, as of now. So the applications built without the frame
pointer might see bogus addresses.
+include::intel-hybrid.txt[]
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0661a1cf9855..2171f02daf59 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -265,7 +265,7 @@ endif
# defined. get-executable-or-default fails with an error if the first argument is supplied but
# doesn't exist.
override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO))
-override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO)))
+override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG)))
grep-libs = $(filter -l%,$(1))
strip-libs = $(filter-out -l%,$(1))
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e5921b347153..bd947885a639 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -954,11 +954,11 @@ ifndef NO_LIBBPF
$(call QUIET_INSTALL, bpf-headers) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
- $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
- $(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
+ $(INSTALL) include/bpf/*.h -m 644 -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+ $(INSTALL) include/bpf/linux/*.h -m 644 -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
$(call QUIET_INSTALL, bpf-examples) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
- $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+ $(INSTALL) examples/bpf/*.c -m 644 -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
endif
$(call QUIET_INSTALL, perf-archive) \
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -967,13 +967,13 @@ endif
ifndef NO_LIBAUDIT
$(call QUIET_INSTALL, strace/groups) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \
- $(INSTALL) trace/strace/groups/* -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'
+ $(INSTALL) trace/strace/groups/* -m 644 -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'
endif
ifndef NO_LIBPERL
$(call QUIET_INSTALL, perl-scripts) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
- $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
- $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
+ $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
+ $(INSTALL) scripts/perl/*.pl -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \
$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
endif
@@ -990,23 +990,23 @@ endif
$(INSTALL) $(DLFILTERS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/dlfilters';
$(call QUIET_INSTALL, perf_completion-script) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
- $(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+ $(INSTALL) perf-completion.sh -m 644 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
$(call QUIET_INSTALL, perf-tip) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \
- $(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
+ $(INSTALL) Documentation/tips.txt -m 644 -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
install-tests: all install-gtk
$(call QUIET_INSTALL, tests) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
- $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
+ $(INSTALL) tests/attr.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
- $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+ $(INSTALL) tests/attr/* -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
$(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
- $(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
- $(INSTALL) tests/shell/lib/*.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'
+ $(INSTALL) tests/shell/lib/*.sh -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
+ $(INSTALL) tests/shell/lib/*.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'
install-bin: install-tools install-tests install-traceevent-plugins
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 653e13b5037e..438fc222e213 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -146,15 +146,15 @@ static void *c2c_he_zalloc(size_t size)
c2c_he->cpuset = bitmap_zalloc(c2c.cpus_cnt);
if (!c2c_he->cpuset)
- return NULL;
+ goto out_free;
c2c_he->nodeset = bitmap_zalloc(c2c.nodes_cnt);
if (!c2c_he->nodeset)
- return NULL;
+ goto out_free;
c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));
if (!c2c_he->node_stats)
- return NULL;
+ goto out_free;
init_stats(&c2c_he->cstats.lcl_hitm);
init_stats(&c2c_he->cstats.rmt_hitm);
@@ -163,6 +163,12 @@ static void *c2c_he_zalloc(size_t size)
init_stats(&c2c_he->cstats.load);
return &c2c_he->he;
+
+out_free:
+ free(c2c_he->nodeset);
+ free(c2c_he->cpuset);
+ free(c2c_he);
+ return NULL;
}
static void c2c_he_free(void *he)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index dd11d3471baf..ea40ae52cd2c 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1874,8 +1874,7 @@ int cmd_lock(int argc, const char **argv)
NULL
};
const char *const lock_subcommands[] = { "record", "report", "script",
- "info", "contention",
- "contention", NULL };
+ "info", "contention", NULL };
const char *lock_usage[] = {
NULL,
NULL
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4713f0f3a6cf..f87ef43eb820 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1906,14 +1906,18 @@ static int record__synthesize(struct record *rec, bool tail)
err = perf_event__synthesize_bpf_events(session, process_synthesized_event,
machine, opts);
- if (err < 0)
+ if (err < 0) {
pr_warning("Couldn't synthesize bpf events.\n");
+ err = 0;
+ }
if (rec->opts.synth & PERF_SYNTH_CGROUP) {
err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
machine);
- if (err < 0)
+ if (err < 0) {
pr_warning("Couldn't synthesize cgroup events.\n");
+ err = 0;
+ }
}
if (rec->opts.nr_threads_synthesize > 1) {
@@ -3358,16 +3362,22 @@ static struct option __record_options[] = {
struct option *record_options = __record_options;
-static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
+static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
{
struct perf_cpu cpu;
int idx;
if (cpu_map__is_dummy(cpus))
- return;
+ return 0;
- perf_cpu_map__for_each_cpu(cpu, idx, cpus)
+ perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+ /* Return ENODEV is input cpu is greater than max cpu */
+ if ((unsigned long)cpu.cpu > mask->nbits)
+ return -ENODEV;
set_bit(cpu.cpu, mask->bits);
+ }
+
+ return 0;
}
static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const char *mask_spec)
@@ -3379,7 +3389,9 @@ static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const cha
return -ENOMEM;
bitmap_zero(mask->bits, mask->nbits);
- record__mmap_cpu_mask_init(mask, cpus);
+ if (record__mmap_cpu_mask_init(mask, cpus))
+ return -ENODEV;
+
perf_cpu_map__put(cpus);
return 0;
@@ -3461,7 +3473,12 @@ static int record__init_thread_masks_spec(struct record *rec, struct perf_cpu_ma
pr_err("Failed to allocate CPUs mask\n");
return ret;
}
- record__mmap_cpu_mask_init(&cpus_mask, cpus);
+
+ ret = record__mmap_cpu_mask_init(&cpus_mask, cpus);
+ if (ret) {
+ pr_err("Failed to init cpu mask\n");
+ goto out_free_cpu_mask;
+ }
ret = record__thread_mask_alloc(&full_mask, cpu__max_cpu().cpu);
if (ret) {
@@ -3702,7 +3719,8 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu
if (ret)
return ret;
- record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);
+ if (record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus))
+ return -ENODEV;
rec->nr_threads = 1;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 2f6cd1b8b662..a5cf243c337f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3355,7 +3355,8 @@ static bool schedstat_events_exposed(void)
static int __cmd_record(int argc, const char **argv)
{
unsigned int rec_argc, i, j;
- const char **rec_argv;
+ char **rec_argv;
+ const char **rec_argv_copy;
const char * const record_args[] = {
"record",
"-a",
@@ -3384,6 +3385,7 @@ static int __cmd_record(int argc, const char **argv)
ARRAY_SIZE(schedstat_args) : 0;
struct tep_event *waking_event;
+ int ret;
/*
* +2 for either "-e", "sched:sched_wakeup" or
@@ -3391,14 +3393,18 @@ static int __cmd_record(int argc, const char **argv)
*/
rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
rec_argv = calloc(rec_argc + 1, sizeof(char *));
-
if (rec_argv == NULL)
return -ENOMEM;
+ rec_argv_copy = calloc(rec_argc + 1, sizeof(char *));
+ if (rec_argv_copy == NULL) {
+ free(rec_argv);
+ return -ENOMEM;
+ }
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[i] = strdup(record_args[i]);
- rec_argv[i++] = "-e";
+ rec_argv[i++] = strdup("-e");
waking_event = trace_event__tp_format("sched", "sched_waking");
if (!IS_ERR(waking_event))
rec_argv[i++] = strdup("sched:sched_waking");
@@ -3409,11 +3415,19 @@ static int __cmd_record(int argc, const char **argv)
rec_argv[i++] = strdup(schedstat_args[j]);
for (j = 1; j < (unsigned int)argc; j++, i++)
- rec_argv[i] = argv[j];
+ rec_argv[i] = strdup(argv[j]);
BUG_ON(i != rec_argc);
- return cmd_record(i, rec_argv);
+ memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc);
+ ret = cmd_record(rec_argc, rec_argv_copy);
+
+ for (i = 0; i < rec_argc; i++)
+ free(rec_argv[i]);
+ free(rec_argv);
+ free(rec_argv_copy);
+
+ return ret;
}
int cmd_sched(int argc, const char **argv)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 13580a9c50b8..029b4330e59b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -445,6 +445,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
struct perf_event_attr *attr = &evsel->core.attr;
bool allow_user_set;
+ if (evsel__is_dummy_event(evsel))
+ return 0;
+
if (perf_header__has_feat(&session->header, HEADER_STAT))
return 0;
@@ -566,6 +569,8 @@ static struct evsel *find_first_output_type(struct evlist *evlist,
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
+ if (evsel__is_dummy_event(evsel))
+ continue;
if (output_type(evsel->core.attr.type) == (int)type)
return evsel;
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7fb81a44672d..0b4a62e4ff67 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -826,6 +826,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
}
evlist__for_each_entry(evsel_list, counter) {
+ counter->reset_group = false;
if (bpf_counter__load(counter, &target))
return -1;
if (!evsel__is_bpf(counter))
@@ -1931,6 +1932,9 @@ setup_metrics:
free(str);
}
+ if (!stat_config.topdown_level)
+ stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
+
if (!evsel_list->core.nr_entries) {
if (target__has_cpu(&target))
default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
@@ -1947,8 +1951,6 @@ setup_metrics:
}
if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
return -1;
-
- stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
/* Platform specific attrs */
if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0)
return -1;
diff --git a/tools/perf/dlfilters/dlfilter-show-cycles.c b/tools/perf/dlfilters/dlfilter-show-cycles.c
index 9eccc97bff82..6d47298ebe9f 100644
--- a/tools/perf/dlfilters/dlfilter-show-cycles.c
+++ b/tools/perf/dlfilters/dlfilter-show-cycles.c
@@ -98,9 +98,9 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo
static void print_vals(__u64 cycles, __u64 delta)
{
if (delta)
- printf("%10llu %10llu ", cycles, delta);
+ printf("%10llu %10llu ", (unsigned long long)cycles, (unsigned long long)delta);
else
- printf("%10llu %10s ", cycles, "");
+ printf("%10llu %10s ", (unsigned long long)cycles, "");
}
int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f94929ebb54b..7ea150cdc137 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
struct machine *machine __maybe_unused)
{
struct perf_record_cpu_map *map_event = &event->cpu_map;
- struct perf_record_record_cpu_map *mask;
struct perf_record_cpu_map_data *data;
struct perf_cpu_map *map;
int i;
+ unsigned int long_size;
data = &map_event->data;
TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
- mask = (struct perf_record_record_cpu_map *)data->data;
+ long_size = data->mask32_data.long_size;
- TEST_ASSERT_VAL("wrong nr", mask->nr == 1);
+ TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8);
+
+ TEST_ASSERT_VAL("wrong nr", data->mask32_data.nr == 1);
for (i = 0; i < 20; i++) {
- TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+ TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data));
}
map = cpu_map__new_data(data);
@@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
struct machine *machine __maybe_unused)
{
struct perf_record_cpu_map *map_event = &event->cpu_map;
- struct cpu_map_entries *cpus;
struct perf_record_cpu_map_data *data;
struct perf_cpu_map *map;
@@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
- cpus = (struct cpu_map_entries *)data->data;
-
- TEST_ASSERT_VAL("wrong nr", cpus->nr == 2);
- TEST_ASSERT_VAL("wrong cpu", cpus->cpu[0] == 1);
- TEST_ASSERT_VAL("wrong cpu", cpus->cpu[1] == 256);
+ TEST_ASSERT_VAL("wrong nr", data->cpus_data.nr == 2);
+ TEST_ASSERT_VAL("wrong cpu", data->cpus_data.cpu[0] == 1);
+ TEST_ASSERT_VAL("wrong cpu", data->cpus_data.cpu[1] == 256);
map = cpu_map__new_data(data);
TEST_ASSERT_VAL("wrong nr", perf_cpu_map__nr(map) == 2);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 07f2411b0ad4..20930dd48ee0 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -86,10 +86,15 @@ static bool samples_same(const struct perf_sample *s1,
COMP(read.time_running);
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
- for (i = 0; i < s1->read.group.nr; i++)
- MCOMP(read.group.values[i]);
+ for (i = 0; i < s1->read.group.nr; i++) {
+ /* FIXME: check values without LOST */
+ if (read_format & PERF_FORMAT_LOST)
+ MCOMP(read.group.values[i]);
+ }
} else {
COMP(read.one.id);
+ if (read_format & PERF_FORMAT_LOST)
+ COMP(read.one.lost);
}
}
@@ -263,7 +268,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
.data = (void *)aux_data,
},
};
- struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+ struct sample_read_value values[] = {{1, 5, 0}, {9, 3, 0}, {2, 7, 0}, {6, 4, 1},};
struct perf_sample sample_out, sample_out_endian;
size_t i, sz, bufsz;
int err, ret = -1;
@@ -286,6 +291,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
} else {
sample.read.one.value = 0x08789faeb786aa87ULL;
sample.read.one.id = 99;
+ sample.read.one.lost = 1;
}
sz = perf_event__sample_event_size(&sample, sample_type, read_format);
@@ -370,7 +376,7 @@ out_free:
*/
static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
{
- const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+ const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 28, 29, 30, 31};
u64 sample_type;
u64 sample_regs;
size_t i;
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 9313ef2739e0..26a51b48aee4 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -28,6 +28,24 @@ test_stat_record_report() {
echo "stat record and report test [Success]"
}
+test_stat_repeat_weak_groups() {
+ echo "stat repeat weak groups test"
+ if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
+ true 2>&1 | grep -q 'seconds time elapsed'
+ then
+ echo "stat repeat weak groups test [Skipped event parsing failed]"
+ return
+ fi
+ if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \
+ true > /dev/null 2>&1
+ then
+ echo "stat repeat weak groups test [Failed]"
+ err=1
+ return
+ fi
+ echo "stat repeat weak groups test [Success]"
+}
+
test_topdown_groups() {
# Topdown events must be grouped with the slots event first. Test that
# parse-events reorders this.
@@ -75,6 +93,7 @@ test_topdown_weak_groups() {
test_default_stat
test_stat_record_report
+test_stat_repeat_weak_groups
test_topdown_groups
test_topdown_weak_groups
exit $err
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 17311ad9f9af..de3701a2a212 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -14,6 +14,8 @@ struct file;
struct pid;
struct cred;
struct socket;
+struct sock;
+struct sk_buff;
#define __sockaddr_check_size(size) \
BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -69,6 +71,9 @@ struct msghdr {
unsigned int msg_flags; /* flags on received message */
__kernel_size_t msg_controllen; /* ancillary data buffer length */
struct kiocb *msg_iocb; /* ptr to iocb for async requests */
+ struct ubuf_info *msg_ubuf;
+ int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *from, size_t length);
};
struct user_msghdr {
@@ -416,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg,
struct user_msghdr __user *umsg, unsigned flags,
struct sockaddr __user **uaddr,
struct iovec **iov);
-extern int __copy_msghdr_from_user(struct msghdr *kmsg,
- struct user_msghdr __user *umsg,
- struct sockaddr __user **save_addr,
- struct iovec __user **uiov, size_t *nsegs);
+extern int __copy_msghdr(struct msghdr *kmsg,
+ struct user_msghdr *umsg,
+ struct sockaddr __user **save_addr);
/* helpers which do the actual work for syscalls */
extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
@@ -428,10 +432,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
extern int __sys_sendto(int fd, void __user *buff, size_t len,
unsigned int flags, struct sockaddr __user *addr,
int addr_len);
-extern int __sys_accept4_file(struct file *file, unsigned file_flags,
- struct sockaddr __user *upeer_sockaddr,
- int __user *upeer_addrlen, int flags,
- unsigned long nofile);
extern struct file *do_accept(struct file *file, unsigned file_flags,
struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
index 4d216c0dc425..4ee96b3c755b 100644
--- a/tools/perf/util/affinity.c
+++ b/tools/perf/util/affinity.c
@@ -49,8 +49,14 @@ void affinity__set(struct affinity *a, int cpu)
{
int cpu_set_size = get_cpu_set_size();
- if (cpu == -1)
+ /*
+ * Return:
+ * - if cpu is -1
+ * - restrict out of bound access to sched_cpus
+ */
+ if (cpu == -1 || ((cpu >= (cpu_set_size * 8))))
return;
+
a->changed = true;
set_bit(cpu, a->sched_cpus);
/*
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 12b2243222b0..ae43fb88f444 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -22,54 +22,102 @@ static int max_node_num;
*/
static int *cpunode_map;
-static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+bool perf_record_cpu_map_data__test_bit(int i,
+ const struct perf_record_cpu_map_data *data)
+{
+ int bit_word32 = i / 32;
+ __u32 bit_mask32 = 1U << (i & 31);
+ int bit_word64 = i / 64;
+ __u64 bit_mask64 = ((__u64)1) << (i & 63);
+
+ return (data->mask32_data.long_size == 4)
+ ? (bit_word32 < data->mask32_data.nr) &&
+ (data->mask32_data.mask[bit_word32] & bit_mask32) != 0
+ : (bit_word64 < data->mask64_data.nr) &&
+ (data->mask64_data.mask[bit_word64] & bit_mask64) != 0;
+}
+
+/* Read ith mask value from data into the given 64-bit sized bitmap */
+static void perf_record_cpu_map_data__read_one_mask(const struct perf_record_cpu_map_data *data,
+ int i, unsigned long *bitmap)
+{
+#if __SIZEOF_LONG__ == 8
+ if (data->mask32_data.long_size == 4)
+ bitmap[0] = data->mask32_data.mask[i];
+ else
+ bitmap[0] = data->mask64_data.mask[i];
+#else
+ if (data->mask32_data.long_size == 4) {
+ bitmap[0] = data->mask32_data.mask[i];
+ bitmap[1] = 0;
+ } else {
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ bitmap[0] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+ bitmap[1] = (unsigned long)data->mask64_data.mask[i];
+#else
+ bitmap[0] = (unsigned long)data->mask64_data.mask[i];
+ bitmap[1] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+#endif
+ }
+#endif
+}
+static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_map_data *data)
{
struct perf_cpu_map *map;
- map = perf_cpu_map__empty_new(cpus->nr);
+ map = perf_cpu_map__empty_new(data->cpus_data.nr);
if (map) {
unsigned i;
- for (i = 0; i < cpus->nr; i++) {
+ for (i = 0; i < data->cpus_data.nr; i++) {
/*
* Special treatment for -1, which is not real cpu number,
* and we need to use (int) -1 to initialize map[i],
* otherwise it would become 65535.
*/
- if (cpus->cpu[i] == (u16) -1)
+ if (data->cpus_data.cpu[i] == (u16) -1)
map->map[i].cpu = -1;
else
- map->map[i].cpu = (int) cpus->cpu[i];
+ map->map[i].cpu = (int) data->cpus_data.cpu[i];
}
}
return map;
}
-static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask)
+static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_data *data)
{
+ DECLARE_BITMAP(local_copy, 64);
+ int weight = 0, mask_nr = data->mask32_data.nr;
struct perf_cpu_map *map;
- int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
- nr = bitmap_weight(mask->mask, nbits);
+ for (int i = 0; i < mask_nr; i++) {
+ perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+ weight += bitmap_weight(local_copy, 64);
+ }
+
+ map = perf_cpu_map__empty_new(weight);
+ if (!map)
+ return NULL;
- map = perf_cpu_map__empty_new(nr);
- if (map) {
- int cpu, i = 0;
+ for (int i = 0, j = 0; i < mask_nr; i++) {
+ int cpus_per_i = (i * data->mask32_data.long_size * BITS_PER_BYTE);
+ int cpu;
- for_each_set_bit(cpu, mask->mask, nbits)
- map->map[i++].cpu = cpu;
+ perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+ for_each_set_bit(cpu, local_copy, 64)
+ map->map[j++].cpu = cpu + cpus_per_i;
}
return map;
}
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data)
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data)
{
if (data->type == PERF_CPU_MAP__CPUS)
- return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+ return cpu_map__from_entries(data);
else
- return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data);
+ return cpu_map__from_mask(data);
}
size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 703ae6d3386e..fa8a5acdcae1 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -37,9 +37,11 @@ struct cpu_aggr_map {
struct perf_record_cpu_map_data;
+bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data);
+
struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data);
size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a7b0931d5137..12eae6917022 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -65,7 +65,8 @@ struct stack_dump {
struct sample_read_value {
u64 value;
- u64 id;
+ u64 id; /* only if PERF_FORMAT_ID */
+ u64 lost; /* only if PERF_FORMAT_LOST */
};
struct sample_read {
@@ -80,6 +81,24 @@ struct sample_read {
};
};
+static inline size_t sample_read_value_size(u64 read_format)
+{
+ /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+ if (read_format & PERF_FORMAT_LOST)
+ return sizeof(struct sample_read_value);
+ else
+ return offsetof(struct sample_read_value, lost);
+}
+
+static inline struct sample_read_value *
+next_sample_read_value(struct sample_read_value *v, u64 read_format)
+{
+ return (void *)v + sample_read_value_size(read_format);
+}
+
+#define sample_read_group__for_each(v, nr, rf) \
+ for (int __i = 0; __i < (int)nr; v = next_sample_read_value(v, rf), __i++)
+
struct ip_callchain {
u64 nr;
u64 ips[];
@@ -463,10 +482,6 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL
int kallsyms__get_function_start(const char *kallsyms_filename,
const char *symbol_name, u64 *addr);
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max);
-void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
- u16 type, int max);
-
void event_attr_init(struct perf_event_attr *attr);
int perf_event_paranoid(void);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4852089e1d79..18c3eb864d55 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1541,7 +1541,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
}
static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
- u64 val, u64 ena, u64 run)
+ u64 val, u64 ena, u64 run, u64 lost)
{
struct perf_counts_values *count;
@@ -1550,6 +1550,7 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
count->val = val;
count->ena = ena;
count->run = run;
+ count->lost = lost;
perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
}
@@ -1558,7 +1559,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
{
u64 read_format = leader->core.attr.read_format;
struct sample_read_value *v;
- u64 nr, ena = 0, run = 0, i;
+ u64 nr, ena = 0, run = 0, lost = 0;
nr = *data++;
@@ -1571,18 +1572,18 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
run = *data++;
- v = (struct sample_read_value *) data;
-
- evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
-
- for (i = 1; i < nr; i++) {
+ v = (void *)data;
+ sample_read_group__for_each(v, nr, read_format) {
struct evsel *counter;
- counter = evlist__id2evsel(leader->evlist, v[i].id);
+ counter = evlist__id2evsel(leader->evlist, v->id);
if (!counter)
return -EINVAL;
- evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
+ if (read_format & PERF_FORMAT_LOST)
+ lost = v->lost;
+
+ evsel__set_count(counter, cpu_map_idx, thread, v->value, ena, run, lost);
}
return 0;
@@ -2475,8 +2476,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
if (data->read.group.nr > max_group_nr)
return -EFAULT;
- sz = data->read.group.nr *
- sizeof(struct sample_read_value);
+
+ sz = data->read.group.nr * sample_read_value_size(read_format);
OVERFLOW_CHECK(array, sz, max_size);
data->read.group.values =
(struct sample_read_value *)array;
@@ -2485,6 +2486,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
OVERFLOW_CHECK_u64(array);
data->read.one.id = *array;
array++;
+
+ if (read_format & PERF_FORMAT_LOST) {
+ OVERFLOW_CHECK_u64(array);
+ data->read.one.lost = *array;
+ array++;
+ }
}
}
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index 953338b9e887..ed28a0dbcb7f 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -30,10 +30,6 @@
#define BUILD_ID_URANDOM /* different uuid for each run */
-// FIXME, remove this and fix the deprecation warnings before its removed and
-// We'll break for good here...
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
#ifdef HAVE_LIBCRYPTO_SUPPORT
#define BUILD_ID_MD5
@@ -45,6 +41,7 @@
#endif
#ifdef BUILD_ID_MD5
+#include <openssl/evp.h>
#include <openssl/md5.h>
#endif
#endif
@@ -142,15 +139,20 @@ gen_build_id(struct buildid_note *note,
static void
gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
{
- MD5_CTX context;
+ EVP_MD_CTX *mdctx;
if (sizeof(note->build_id) < 16)
errx(1, "build_id too small for MD5");
- MD5_Init(&context);
- MD5_Update(&context, &load_addr, sizeof(load_addr));
- MD5_Update(&context, code, csize);
- MD5_Final((unsigned char *)note->build_id, &context);
+ mdctx = EVP_MD_CTX_new();
+ if (!mdctx)
+ errx(2, "failed to create EVP_MD_CTX");
+
+ EVP_DigestInit_ex(mdctx, EVP_md5(), NULL);
+ EVP_DigestUpdate(mdctx, &load_addr, sizeof(load_addr));
+ EVP_DigestUpdate(mdctx, code, csize);
+ EVP_DigestFinal_ex(mdctx, (unsigned char *)note->build_id, NULL);
+ EVP_MD_CTX_free(mdctx);
}
#endif
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 464475fd6b9a..c93bcaf6d55d 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1655,6 +1655,9 @@ int metricgroup__parse_groups(const struct option *opt,
struct evlist *perf_evlist = *(struct evlist **)opt->value;
const struct pmu_events_table *table = pmu_events_table__find();
+ if (!table)
+ return -EINVAL;
+
return parse_groups(perf_evlist, str, metric_no_group,
metric_no_merge, NULL, metric_events, table);
}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9ef2406e0ede..1f2040f36d4e 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -642,15 +642,19 @@ exit:
return pylist;
}
-static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
+static PyObject *get_sample_value_as_tuple(struct sample_read_value *value,
+ u64 read_format)
{
PyObject *t;
- t = PyTuple_New(2);
+ t = PyTuple_New(3);
if (!t)
Py_FatalError("couldn't create Python tuple");
PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id));
PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value));
+ if (read_format & PERF_FORMAT_LOST)
+ PyTuple_SetItem(t, 2, PyLong_FromUnsignedLongLong(value->lost));
+
return t;
}
@@ -681,12 +685,17 @@ static void set_sample_read_in_dict(PyObject *dict_sample,
Py_FatalError("couldn't create Python list");
if (read_format & PERF_FORMAT_GROUP) {
- for (i = 0; i < sample->read.group.nr; i++) {
- PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]);
+ struct sample_read_value *v = sample->read.group.values;
+
+ i = 0;
+ sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+ PyObject *t = get_sample_value_as_tuple(v, read_format);
PyList_SET_ITEM(values, i, t);
+ i++;
}
} else {
- PyObject *t = get_sample_value_as_tuple(&sample->read.one);
+ PyObject *t = get_sample_value_as_tuple(&sample->read.one,
+ read_format);
PyList_SET_ITEM(values, 0, t);
}
pydict_set_item_string_decref(dict_sample, "values", values);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 98e16659a149..192c9274f7ad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -916,30 +916,30 @@ static void perf_event__cpu_map_swap(union perf_event *event,
bool sample_id_all __maybe_unused)
{
struct perf_record_cpu_map_data *data = &event->cpu_map.data;
- struct cpu_map_entries *cpus;
- struct perf_record_record_cpu_map *mask;
- unsigned i;
data->type = bswap_16(data->type);
switch (data->type) {
case PERF_CPU_MAP__CPUS:
- cpus = (struct cpu_map_entries *)data->data;
-
- cpus->nr = bswap_16(cpus->nr);
+ data->cpus_data.nr = bswap_16(data->cpus_data.nr);
- for (i = 0; i < cpus->nr; i++)
- cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+ for (unsigned i = 0; i < data->cpus_data.nr; i++)
+ data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]);
break;
case PERF_CPU_MAP__MASK:
- mask = (struct perf_record_record_cpu_map *)data->data;
-
- mask->nr = bswap_16(mask->nr);
- mask->long_size = bswap_16(mask->long_size);
+ data->mask32_data.long_size = bswap_16(data->mask32_data.long_size);
- switch (mask->long_size) {
- case 4: mem_bswap_32(&mask->mask, mask->nr); break;
- case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+ switch (data->mask32_data.long_size) {
+ case 4:
+ data->mask32_data.nr = bswap_16(data->mask32_data.nr);
+ for (unsigned i = 0; i < data->mask32_data.nr; i++)
+ data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]);
+ break;
+ case 8:
+ data->mask64_data.nr = bswap_16(data->mask64_data.nr);
+ for (unsigned i = 0; i < data->mask64_data.nr; i++)
+ data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]);
+ break;
default:
pr_err("cpu_map swap: unsupported long size\n");
}
@@ -1283,21 +1283,25 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
sample->read.time_running);
if (read_format & PERF_FORMAT_GROUP) {
- u64 i;
+ struct sample_read_value *value = sample->read.group.values;
printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
- for (i = 0; i < sample->read.group.nr; i++) {
- struct sample_read_value *value;
-
- value = &sample->read.group.values[i];
+ sample_read_group__for_each(value, sample->read.group.nr, read_format) {
printf("..... id %016" PRIx64
- ", value %016" PRIx64 "\n",
+ ", value %016" PRIx64,
value->id, value->value);
+ if (read_format & PERF_FORMAT_LOST)
+ printf(", lost %" PRIu64, value->lost);
+ printf("\n");
}
- } else
- printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+ } else {
+ printf("..... id %016" PRIx64 ", value %016" PRIx64,
sample->read.one.id, sample->read.one.value);
+ if (read_format & PERF_FORMAT_LOST)
+ printf(", lost %" PRIu64, sample->read.one.lost);
+ printf("\n");
+ }
}
static void dump_event(struct evlist *evlist, union perf_event *event,
@@ -1411,6 +1415,9 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
if (read_format & PERF_FORMAT_ID)
printf("... id : %" PRI_lu64 "\n", read_event->id);
+
+ if (read_format & PERF_FORMAT_LOST)
+ printf("... lost : %" PRI_lu64 "\n", read_event->lost);
}
static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1479,14 +1486,14 @@ static int deliver_sample_group(struct evlist *evlist,
struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
- struct machine *machine)
+ struct machine *machine,
+ u64 read_format)
{
int ret = -EINVAL;
- u64 i;
+ struct sample_read_value *v = sample->read.group.values;
- for (i = 0; i < sample->read.group.nr; i++) {
- ret = deliver_sample_value(evlist, tool, event, sample,
- &sample->read.group.values[i],
+ sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+ ret = deliver_sample_value(evlist, tool, event, sample, v,
machine);
if (ret)
break;
@@ -1510,7 +1517,7 @@ static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
/* For PERF_SAMPLE_READ we have either single or group mode. */
if (read_format & PERF_FORMAT_GROUP)
return deliver_sample_group(evlist, tool, event, sample,
- machine);
+ machine, read_format);
else
return deliver_sample_value(evlist, tool, event, sample,
&sample->read.one, machine);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 979c8cb918f7..788ce5e46470 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1193,7 +1193,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
&rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
- print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+ print_metric(config, ctxp, color, "%8.1f%%", "Retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
full_td(cpu_map_idx, st, &rsd)) {
@@ -1202,7 +1202,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
&rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+ print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
full_td(cpu_map_idx, st, &rsd)) {
@@ -1211,7 +1211,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
&rsd);
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+ print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound",
be_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
full_td(cpu_map_idx, st, &rsd)) {
@@ -1220,7 +1220,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
&rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+ print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1234,13 +1234,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (retiring > 0.7 && heavy_ops > 0.1)
color = PERF_COLOR_GREEN;
- print_metric(config, ctxp, color, "%8.1f%%", "heavy operations",
+ print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations",
heavy_ops * 100.);
if (retiring > 0.7 && light_ops > 0.6)
color = PERF_COLOR_GREEN;
else
color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "light operations",
+ print_metric(config, ctxp, color, "%8.1f%%", "Light Operations",
light_ops * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1254,13 +1254,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (bad_spec > 0.1 && br_mis > 0.05)
color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict",
+ print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict",
br_mis * 100.);
if (bad_spec > 0.1 && m_clears > 0.05)
color = PERF_COLOR_RED;
else
color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
+ print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears",
m_clears * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1274,13 +1274,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (fe_bound > 0.2 && fetch_lat > 0.15)
color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "fetch latency",
+ print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency",
fetch_lat * 100.);
if (fe_bound > 0.2 && fetch_bw > 0.1)
color = PERF_COLOR_RED;
else
color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
+ print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth",
fetch_bw * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1294,13 +1294,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (be_bound > 0.2 && mem_bound > 0.2)
color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "memory bound",
+ print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound",
mem_bound * 100.);
if (be_bound > 0.2 && core_bound > 0.1)
color = PERF_COLOR_RED;
else
color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "Core bound",
+ print_metric(config, ctxp, color, "%8.1f%%", "Core Bound",
core_bound * 100.);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 2ae59c03ae77..812424dbf2d5 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1184,52 +1184,48 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool,
return err;
}
-static void synthesize_cpus(struct cpu_map_entries *cpus,
- struct perf_cpu_map *map)
+static void synthesize_cpus(struct perf_record_cpu_map_data *data,
+ const struct perf_cpu_map *map)
{
int i, map_nr = perf_cpu_map__nr(map);
- cpus->nr = map_nr;
+ data->cpus_data.nr = map_nr;
for (i = 0; i < map_nr; i++)
- cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu;
+ data->cpus_data.cpu[i] = perf_cpu_map__cpu(map, i).cpu;
}
-static void synthesize_mask(struct perf_record_record_cpu_map *mask,
- struct perf_cpu_map *map, int max)
+static void synthesize_mask(struct perf_record_cpu_map_data *data,
+ const struct perf_cpu_map *map, int max)
{
- int i;
+ int idx;
+ struct perf_cpu cpu;
+
+ /* Due to padding, the 4bytes per entry mask variant is always smaller. */
+ data->mask32_data.nr = BITS_TO_U32(max);
+ data->mask32_data.long_size = 4;
- mask->nr = BITS_TO_LONGS(max);
- mask->long_size = sizeof(long);
+ perf_cpu_map__for_each_cpu(cpu, idx, map) {
+ int bit_word = cpu.cpu / 32;
+ __u32 bit_mask = 1U << (cpu.cpu & 31);
- for (i = 0; i < perf_cpu_map__nr(map); i++)
- set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask);
+ data->mask32_data.mask[bit_word] |= bit_mask;
+ }
}
-static size_t cpus_size(struct perf_cpu_map *map)
+static size_t cpus_size(const struct perf_cpu_map *map)
{
return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16);
}
-static size_t mask_size(struct perf_cpu_map *map, int *max)
+static size_t mask_size(const struct perf_cpu_map *map, int *max)
{
- int i;
-
- *max = 0;
-
- for (i = 0; i < perf_cpu_map__nr(map); i++) {
- /* bit position of the cpu is + 1 */
- int bit = perf_cpu_map__cpu(map, i).cpu + 1;
-
- if (bit > *max)
- *max = bit;
- }
-
- return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
+ *max = perf_cpu_map__max(map).cpu;
+ return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32);
}
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
+static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size,
+ u16 *type, int *max)
{
size_t size_cpus, size_mask;
bool is_dummy = perf_cpu_map__empty(map);
@@ -1258,30 +1254,31 @@ void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int
*type = PERF_CPU_MAP__MASK;
}
- *size += sizeof(struct perf_record_cpu_map_data);
+ *size += sizeof(__u16); /* For perf_record_cpu_map_data.type. */
*size = PERF_ALIGN(*size, sizeof(u64));
return zalloc(*size);
}
-void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
- u16 type, int max)
+static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data,
+ const struct perf_cpu_map *map,
+ u16 type, int max)
{
data->type = type;
switch (type) {
case PERF_CPU_MAP__CPUS:
- synthesize_cpus((struct cpu_map_entries *) data->data, map);
+ synthesize_cpus(data, map);
break;
case PERF_CPU_MAP__MASK:
- synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
+ synthesize_mask(data, map, max);
default:
break;
}
}
-static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
+static struct perf_record_cpu_map *cpu_map_event__new(const struct perf_cpu_map *map)
{
- size_t size = sizeof(struct perf_record_cpu_map);
+ size_t size = sizeof(struct perf_event_header);
struct perf_record_cpu_map *event;
int max;
u16 type;
@@ -1299,7 +1296,7 @@ static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
}
int perf_event__synthesize_cpu_map(struct perf_tool *tool,
- struct perf_cpu_map *map,
+ const struct perf_cpu_map *map,
perf_event__handler_t process,
struct machine *machine)
{
@@ -1432,11 +1429,12 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
result += sizeof(u64);
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
- sz = sample->read.group.nr *
- sizeof(struct sample_read_value);
- result += sz;
+ sz = sample_read_value_size(read_format);
+ result += sz * sample->read.group.nr;
} else {
result += sizeof(u64);
+ if (read_format & PERF_FORMAT_LOST)
+ result += sizeof(u64);
}
}
@@ -1521,6 +1519,20 @@ void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data,
*array = data->weight;
}
+static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
+ const struct perf_sample *sample)
+{
+ size_t sz = sample_read_value_size(read_format);
+ struct sample_read_value *v = sample->read.group.values;
+
+ sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+ /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+ memcpy(array, v, sz);
+ array = (void *)array + sz;
+ }
+ return array;
+}
+
int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
const struct perf_sample *sample)
{
@@ -1602,13 +1614,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
- sz = sample->read.group.nr *
- sizeof(struct sample_read_value);
- memcpy(array, sample->read.group.values, sz);
- array = (void *)array + sz;
+ array = copy_read_group_values(array, read_format,
+ sample);
} else {
*array = sample->read.one.id;
array++;
+
+ if (read_format & PERF_FORMAT_LOST) {
+ *array = sample->read.one.lost;
+ array++;
+ }
}
}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index 81cb3d6af0b9..53737d1619a4 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -46,7 +46,7 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *e
int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process);
int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool, const struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2025-02-01 17:26:32 +0000