diff options
Diffstat (limited to 'tools/perf')
36 files changed, 361 insertions, 143 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..0f711f88894c 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 +3362,24 @@ 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) { + if (cpu.cpu == -1) + continue; + /* 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 +3391,9 @@ 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 +3475,12 @@ 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 +3721,8 @@ 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/mmap-basic.c b/tools/perf/tests/mmap-basic.c index dfb6173b2a82..9e9a2b67de19 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -114,8 +114,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest for (i = 0; i < nsyscalls; ++i) for (j = 0; j < expected_nr_events[i]; ++j) { - int foo = syscalls[i](); - ++foo; + syscalls[i](); } md = &evlist->mmap[0]; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 6a001fcfed68..4952abe716f3 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -332,7 +332,7 @@ out_delete_evlist: out: if (err == -EACCES) return TEST_SKIP; - if (err < 0) + if (err < 0 || errs != 0) return TEST_FAIL; return TEST_OK; } diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh index 00c7285ce1ac..301f95427159 100755 --- a/tools/perf/tests/shell/record.sh +++ b/tools/perf/tests/shell/record.sh @@ -61,7 +61,7 @@ test_register_capture() { echo "Register capture test [Skipped missing registers]" return fi - if ! perf record -o - --intr-regs=di,r8,dx,cx -e cpu/br_inst_retired.near_call/p \ + if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \ -c 1000 --per-thread true 2> /dev/null \ | perf script -F ip,sym,iregs -i - 2> /dev/null \ | egrep -q "DI:" 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/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh new file mode 100755 index 000000000000..d724855d097c --- /dev/null +++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh @@ -0,0 +1,83 @@ +#!/bin/sh +# perf stat --bpf-counters --for-each-cgroup test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +test_cgroups= +if [ "$1" = "-v" ]; then + verbose="1" +fi + +# skip if --bpf-counters --for-each-cgroup is not supported +check_bpf_counter() +{ + if ! perf stat -a --bpf-counters --for-each-cgroup / true > /dev/null 2>&1; then + if [ "${verbose}" = "1" ]; then + echo "Skipping: --bpf-counters --for-each-cgroup not supported" + perf --no-pager stat -a --bpf-counters --for-each-cgroup / true || true + fi + exit 2 + fi +} + +# find two cgroups to measure +find_cgroups() +{ + # try usual systemd slices first + if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then + test_cgroups="system.slice,user.slice" + return + fi + + # try root and self cgroups + local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) + if [ -z ${self_cgrp} ]; then + # cgroup v2 doesn't specify perf_event + self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3) + fi + + if [ -z ${self_cgrp} ]; then + test_cgroups="/" + else + test_cgroups="/,${self_cgrp}" + fi +} + +# As cgroup events are cpu-wide, we cannot simply compare the result. +# Just check if it runs without failure and has non-zero results. +check_system_wide_counted() +{ + local output + + output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1) + if echo ${output} | grep -q -F "<not "; then + echo "Some system-wide events are not counted" + if [ "${verbose}" = "1" ]; then + echo ${output} + fi + exit 1 + fi +} + +check_cpu_list_counted() +{ + local output + + output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1) + if echo ${output} | grep -q -F "<not "; then + echo "Some CPU events are not counted" + if [ "${verbose}" = "1" ]; then + echo ${output} + fi + exit 1 + fi +} + +check_bpf_counter +find_cgroups + +check_system_wide_counted +check_cpu_list_counted + +exit 0 diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index c644f94a6500..ec801cffae6b 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -12,7 +12,8 @@ if ! [ -x "$(command -v cc)" ]; then fi # skip the test if the hardware doesn't support branch stack sampling -perf record -b -o- -B true > /dev/null 2>&1 || exit 2 +# and if the architecture doesn't support filter types: any,save_type,u +perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX) diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 4fd8d703ff19..8ab035b55875 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -43,10 +43,11 @@ static bool is_ignored_symbol(const char *name, char type) /* Symbol names that begin with the following are ignored.*/ static const char * const ignored_prefixes[] = { "$", /* local symbols for ARM, MIPS, etc. */ - ".LASANPC", /* s390 kasan local symbols */ + ".L", /* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */ "__crc_", /* modversions */ "__efistub_", /* arm64 EFI stub namespace */ - "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__kvm_nvhe_$", /* arm64 local symbols in non-VHE KVM namespace */ + "__kvm_nvhe_.L", /* arm64 local symbols in non-VHE KVM namespace */ "__AArch64ADRPThunk_", /* arm64 lld */ "__ARMV5PILongThunk_", /* arm lld */ "__ARMV7PILongThunk_", diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index 9d4c45184e71..56455da30341 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -2,7 +2,9 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include <errno.h> #include <sys/ioctl.h> +#include <linux/compiler.h> #include <linux/hw_breakpoint.h> #include <linux/kernel.h> #include "tests.h" @@ -137,8 +139,7 @@ static int test__wp_rw(struct test_suite *test __maybe_unused, #endif } -static int test__wp_modify(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) +static int test__wp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { #if defined(__s390x__) return TEST_SKIP; @@ -160,6 +161,11 @@ static int test__wp_modify(struct test_suite *test __maybe_unused, new_attr.disabled = 1; ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr); if (ret < 0) { + if (errno == ENOTTY) { + test->test_cases[subtest].skip_reason = "missing kernel support"; + ret = TEST_SKIP; + } + pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n"); close(fd); return ret; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 9dfae1bda9cc..485e1a343165 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -269,7 +269,7 @@ CFLAGS_expr-flex.o += $(flex_flags) bison_flags := -DYYENABLE_NLS=0 BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35) ifeq ($(BISON_GE_35),1) - bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum + bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option else bison_flags += -w endif 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/arm-spe.c b/tools/perf/util/arm-spe.c index 22dcfe07e886..906476a839e1 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -498,7 +498,7 @@ static void arm_spe__synth_data_source_generic(const struct arm_spe_record *reco static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr) { union perf_mem_data_src data_src = { 0 }; - bool is_neoverse = is_midr_in_range(midr, neoverse_spe); + bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe); if (record->op == ARM_SPE_LD) data_src.mem_op = PERF_MEM_OP_LOAD; diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 63b9db657442..3c2df7522f6f 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -95,7 +95,7 @@ static int bperf_load_program(struct evlist *evlist) 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, cpu.cpu)); + FD(cgrp_switch, i)); if (IS_ERR(link)) { pr_err("Failed to attach cgroup program\n"); err = PTR_ERR(link); @@ -115,15 +115,15 @@ static int bperf_load_program(struct evlist *evlist) evsel->cgrp = NULL; /* open single copy of the events w/o cgroup */ - err = evsel__open_per_cpu(evsel, evlist->core.all_cpus, -1); + err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1); if (err) { pr_err("Failed to open first cgroup events\n"); goto out; } map_fd = bpf_map__fd(skel->maps.events); - perf_cpu_map__for_each_cpu(cpu, j, evlist->core.all_cpus) { - int fd = FD(evsel, cpu.cpu); + perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) { + int fd = FD(evsel, j); __u32 idx = evsel->core.idx * total_cpus + cpu.cpu; err = bpf_map_update_elem(map_fd, &idx, &fd, @@ -269,7 +269,7 @@ static int bperf_cgrp__read(struct evsel *evsel) goto out; } - perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) { + perf_cpu_map__for_each_cpu(cpu, i, evsel->core.cpus) { counts = perf_counts(evsel->counts, i, 0); counts->val = values[cpu.cpu].counter; counts->ena = values[cpu.cpu].enabled; diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index 292c430768b5..9aa8cdd93de4 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -48,6 +48,7 @@ const volatile __u32 num_cpus = 1; int enabled = 0; int use_cgroup_v2 = 0; +int perf_subsys_id = -1; static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) { @@ -58,7 +59,15 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) int level; int cnt; - cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_event_cgrp_id], cgroup); + if (perf_subsys_id == -1) { +#if __has_builtin(__builtin_preserve_enum_value) + perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id, + perf_event_cgrp_id); +#else + perf_subsys_id = perf_event_cgrp_id; +#endif + } + cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_subsys_id], cgroup); level = BPF_CORE_READ(cgrp, level); for (cnt = 0; i < MAX_LEVELS; i++) { @@ -176,7 +185,7 @@ static int bperf_cgroup_count(void) } // This will be attached to cgroup-switches event for each cpu -SEC("perf_events") +SEC("perf_event") int BPF_PROG(on_cgrp_switch) { return bperf_cgroup_count(); diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index c4ba2bcf179f..38e3b287dbb2 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -94,6 +94,8 @@ const volatile bool has_prev_state = false; const volatile bool needs_cgroup = false; const volatile bool uses_cgroup_v1 = false; +int perf_subsys_id = -1; + /* * Old kernel used to call it task_struct->state and now it's '__state'. * Use BPF CO-RE "ignored suffix rule" to deal with it like below: @@ -119,11 +121,19 @@ static inline __u64 get_cgroup_id(struct task_struct *t) { struct cgroup *cgrp; - if (uses_cgroup_v1) - cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup); - else - cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp); + if (!uses_cgroup_v1) + return BPF_CORE_READ(t, cgroups, dfl_cgrp, kn, id); + + if (perf_subsys_id == -1) { +#if __has_builtin(__builtin_preserve_enum_value) + perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id, + perf_event_cgrp_id); +#else + perf_subsys_id = perf_event_cgrp_id; +#endif + } + cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_subsys_id], cgroup); return BPF_CORE_READ(cgrp, kn, id); } diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index 953338b9e887..d81b54563e96 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 @@ -251,6 +253,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, Elf_Data *d; Elf_Scn *scn; Elf_Ehdr *ehdr; + Elf_Phdr *phdr; Elf_Shdr *shdr; uint64_t eh_frame_base_offset; char *strsym = NULL; @@ -286,6 +289,19 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */ /* + * setup program header + */ + phdr = elf_newphdr(e, 1); + phdr[0].p_type = PT_LOAD; + phdr[0].p_offset = 0; + phdr[0].p_vaddr = 0; + phdr[0].p_paddr = 0; + phdr[0].p_filesz = csize; + phdr[0].p_memsz = csize; + phdr[0].p_flags = PF_X | PF_R; + phdr[0].p_align = 8; + + /* * setup text section */ scn = elf_newscn(e); diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index ae138afe6c56..b5c909546e3f 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -53,8 +53,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #if GEN_ELF_CLASS == ELFCLASS64 #define elf_newehdr elf64_newehdr +#define elf_newphdr elf64_newphdr #define elf_getshdr elf64_getshdr #define Elf_Ehdr Elf64_Ehdr +#define Elf_Phdr Elf64_Phdr #define Elf_Shdr Elf64_Shdr #define Elf_Sym Elf64_Sym #define ELF_ST_TYPE(a) ELF64_ST_TYPE(a) @@ -62,8 +64,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #define ELF_ST_VIS(a) ELF64_ST_VISIBILITY(a) #else #define elf_newehdr elf32_newehdr +#define elf_newphdr elf32_newphdr #define elf_getshdr elf32_getshdr #define Elf_Ehdr Elf32_Ehdr +#define Elf_Phdr Elf32_Phdr #define Elf_Shdr Elf32_Shdr #define Elf_Sym Elf32_Sym #define ELF_ST_TYPE(a) ELF32_ST_TYPE(a) 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/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c index 284f8eabd3b9..7c9f9150bad5 100644 --- a/tools/perf/util/parse-events-hybrid.c +++ b/tools/perf/util/parse-events-hybrid.c @@ -33,7 +33,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr, * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. */ attr->type = type; - attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT); + attr->config = (attr->config & PERF_HW_EVENT_MASK) | + ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT); } static int create_event_hybrid(__u32 config_type, int *idx, @@ -48,13 +49,25 @@ static int create_event_hybrid(__u32 config_type, int *idx, __u64 config = attr->config; config_hybrid_attr(attr, config_type, pmu->type); + + /* + * Some hybrid hardware cache events are only available on one CPU + * PMU. For example, the 'L1-dcache-load-misses' is only available + * on cpu_core, while the 'L1-icache-loads' is only available on + * cpu_atom. We need to remove "not supported" hybrid cache events. + */ + if (attr->type == PERF_TYPE_HW_CACHE + && !is_event_supported(attr->type, attr->config)) + return 0; + evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id, pmu, config_terms); - if (evsel) + if (evsel) { evsel->pmu_name = strdup(pmu->name); - else + if (!evsel->pmu_name) + return -ENOMEM; + } else return -ENOMEM; - attr->type = type; attr->config = config; return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f05e15acd33f..f3b2c2a87456 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -28,6 +28,7 @@ #include "util/parse-events-hybrid.h" #include "util/pmu-hybrid.h" #include "tracepoint.h" +#include "thread_map.h" #define MAX_NAME_LEN 100 @@ -157,6 +158,44 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) +bool is_event_supported(u8 type, u64 config) +{ + bool ret = true; + int open_return; + struct evsel *evsel; + struct perf_event_attr attr = { + .type = type, + .config = config, + .disabled = 1, + }; + struct perf_thread_map *tmap = thread_map__new_by_tid(0); + + if (tmap == NULL) + return false; + + evsel = evsel__new(&attr); + if (evsel) { + open_return = evsel__open(evsel, NULL, tmap); + ret = open_return >= 0; + + if (open_return == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->core.attr.exclude_kernel = 1; + ret = evsel__open(evsel, NULL, tmap) >= 0; + } + evsel__delete(evsel); + } + + perf_thread_map__put(tmap); + return ret; +} + const char *event_type(int type) { switch (type) { diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 7e6a601d9cd0..07df7bb7b042 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -19,6 +19,7 @@ struct option; struct perf_pmu; bool have_tracepoints(struct list_head *evlist); +bool is_event_supported(u8 type, u64 config); const char *event_type(int type); diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index ba1ab5134685..c4d5d87fae2f 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -22,7 +22,6 @@ #include "probe-file.h" #include "string2.h" #include "strlist.h" -#include "thread_map.h" #include "tracepoint.h" #include "pfm.h" #include "pmu-hybrid.h" @@ -239,44 +238,6 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, strlist__delete(sdtlist); } -static bool is_event_supported(u8 type, unsigned int config) -{ - bool ret = true; - int open_return; - struct evsel *evsel; - struct perf_event_attr attr = { - .type = type, - .config = config, - .disabled = 1, - }; - struct perf_thread_map *tmap = thread_map__new_by_tid(0); - - if (tmap == NULL) - return false; - - evsel = evsel__new(&attr); - if (evsel) { - open_return = evsel__open(evsel, NULL, tmap); - ret = open_return >= 0; - - if (open_return == -EACCES) { - /* - * This happens if the paranoid value - * /proc/sys/kernel/perf_event_paranoid is set to 2 - * Re-run with exclude_kernel set; we don't do that - * by default as some ARM machines do not support it. - * - */ - evsel->core.attr.exclude_kernel = 1; - ret = evsel__open(evsel, NULL, tmap) >= 0; - } - evsel__delete(evsel); - } - - perf_thread_map__put(tmap); - return ret; -} - int print_hwcache_events(const char *event_glob, bool name_only) { unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0; diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index c92326c2233a..0f5ba28339cf 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -3,4 +3,4 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum -CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-error=deprecated-declarations +CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations 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/symbol-elf.c b/tools/perf/util/symbol-elf.c index 75bec32d4f57..647b7dff8ef3 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -2102,8 +2102,8 @@ static int kcore_copy__compare_file(const char *from_dir, const char *to_dir, * unusual. One significant peculiarity is that the mapping (start -> pgoff) * is not the same for the kernel map and the modules map. That happens because * the data is copied adjacently whereas the original kcore has gaps. Finally, - * kallsyms and modules files are compared with their copies to check that - * modules have not been loaded or unloaded while the copies were taking place. + * kallsyms file is compared with its copy to check that modules have not been + * loaded or unloaded while the copies were taking place. * * Return: %0 on success, %-1 on failure. */ @@ -2166,9 +2166,6 @@ int kcore_copy(const char *from_dir, const char *to_dir) goto out_extract_close; } - if (kcore_copy__compare_file(from_dir, to_dir, "modules")) - goto out_extract_close; - if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms")) goto out_extract_close; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 812424dbf2d5..538790758e24 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -367,13 +367,24 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event, bool is_kernel) { struct build_id bid; + struct nsinfo *nsi; + struct nscookie nc; int rc; - if (is_kernel) + if (is_kernel) { rc = sysfs__read_build_id("/sys/kernel/notes", &bid); - else - rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1; + goto out; + } + + nsi = nsinfo__new(event->pid); + nsinfo__mountns_enter(nsi, &nc); + rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1; + + nsinfo__mountns_exit(&nc); + nsinfo__put(nsi); + +out: if (rc == 0) { memcpy(event->build_id, bid.data, sizeof(bid.data)); event->build_id_size = (u8) bid.size; |