diff options
Diffstat (limited to 'tools/perf')
48 files changed, 445 insertions, 170 deletions
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..f3bf9297bcc0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -790,6 +793,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9c935f86d172..69473a836bae 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -691,9 +691,8 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt) $(SCRIPTS) : % : %.sh $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@' -$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD ../../.git/ORIG_HEAD +$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) - $(Q)touch $(OUTPUT)PERF-VERSION-FILE # These can record PERF_VERSION perf.spec $(SCRIPTS) \ @@ -724,7 +723,7 @@ endif # get relative building directory (to $(OUTPUT)) # and '.' if it's $(OUTPUT) itself __build-dir = $(subst $(OUTPUT),,$(dir $@)) -build-dir = $(if $(__build-dir),$(__build-dir),.) +build-dir = $(or $(__build-dir),.) prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \ $(fadvise_advice_array) \ @@ -1090,7 +1089,7 @@ bpf-skel-clean: clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf-iostat $(LANG_BINDINGS) - $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ @@ -1139,21 +1138,12 @@ else @echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP" endif -# -# Trick: if ../../.git does not exist - we are building out of tree for example, -# then force version regeneration: -# -ifeq ($(wildcard ../../.git/HEAD),) - GIT-HEAD-PHONY = ../../.git/HEAD ../../.git/ORIG_HEAD -else - GIT-HEAD-PHONY = -endif FORCE: .PHONY: all install clean config-clean strip install-gtk .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell -.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare +.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope FORCE prepare .PHONY: libtraceevent_plugins archheaders endif # force_fixdep diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index cbc555245959..11c71aa219f7 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -199,7 +199,7 @@ static int cs_etm_set_option(struct auxtrace_record *itr, struct evsel *evsel, u32 option) { int i, err = -EINVAL; - struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus; + struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* Set option of each CPU we have */ @@ -299,7 +299,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; struct evsel *evsel, *cs_etm_evsel = NULL; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); int err = 0; @@ -522,7 +522,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, { int i; int etmv3 = 0, etmv4 = 0, ete = 0; - struct perf_cpu_map *event_cpus = evlist->core.cpus; + struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* cpu map is not empty, we have specific CPUs to work with */ @@ -713,7 +713,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, u32 offset; u64 nr_cpu, type; struct perf_cpu_map *cpu_map; - struct perf_cpu_map *event_cpus = session->evlist->core.cpus; + struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 5860bbaea95a..af4d63af8072 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -144,7 +144,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, container_of(itr, struct arm_spe_recording, itr); struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu; struct evsel *evsel, *arm_spe_evsel = NULL; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; @@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 4a76d49d25d6..d68a0f48e41e 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -110,7 +110,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, container_of(itr, struct intel_bts_recording, itr); struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu; struct evsel *evsel, *intel_bts_evsel = NULL; - const struct perf_cpu_map *cpus = evlist->core.cpus; + const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); if (opts->auxtrace_sample_mode) { diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 8c31578d6f4a..38ec2666ec12 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -382,7 +382,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus); + per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -632,7 +632,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; bool have_timing_info, need_immediate = false; struct evsel *evsel, *intel_pt_evsel = NULL; - const struct perf_cpu_map *cpus = evlist->core.cpus; + const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); u64 tsc_bit; int err; diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c index de56601f69ee..5a27691469ed 100644 --- a/tools/perf/bench/evlist-open-close.c +++ b/tools/perf/bench/evlist-open-close.c @@ -151,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr) init_stats(&time_stats); - printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus)); + printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.user_requested_cpus)); printf(" Number of threads:\t%d\n", evlist->core.threads->nr); printf(" Number of events:\t%d (%d fds)\n", evlist->core.nr_entries, evlist__count_evsel_fds(evlist)); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index f2640179ada9..44e1f8a44087 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -34,6 +34,7 @@ #include <linux/numa.h> #include <linux/zalloc.h> +#include "../util/header.h" #include <numa.h> #include <numaif.h> @@ -54,7 +55,7 @@ struct thread_data { int curr_cpu; - cpu_set_t bind_cpumask; + cpu_set_t *bind_cpumask; int bind_node; u8 *process_data; int process_nr; @@ -266,71 +267,115 @@ static bool node_has_cpus(int node) return ret; } -static cpu_set_t bind_to_cpu(int target_cpu) +static cpu_set_t *bind_to_cpu(int target_cpu) { - cpu_set_t orig_mask, mask; - int ret; + int nrcpus = numa_num_possible_cpus(); + cpu_set_t *orig_mask, *mask; + size_t size; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); + + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; - CPU_ZERO(&mask); + CPU_ZERO_S(size, mask); if (target_cpu == -1) { int cpu; for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { - BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); - CPU_SET(target_cpu, &mask); + if (target_cpu < 0 || target_cpu >= g->p.nr_cpus) + goto err; + + CPU_SET_S(target_cpu, size, mask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); } -static cpu_set_t bind_to_node(int target_node) +static cpu_set_t *bind_to_node(int target_node) { - cpu_set_t orig_mask, mask; + int nrcpus = numa_num_possible_cpus(); + size_t size; + cpu_set_t *orig_mask, *mask; int cpu; - int ret; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); - CPU_ZERO(&mask); + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_node == NUMA_NO_NODE) { for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { struct bitmask *cpumask = numa_allocate_cpumask(); - BUG_ON(!cpumask); + if (!cpumask) + goto err; + if (!numa_node_to_cpus(target_node, cpumask)) { for (cpu = 0; cpu < (int)cpumask->size; cpu++) { if (numa_bitmask_isbitset(cpumask, cpu)) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } } numa_free_cpumask(cpumask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); } -static void bind_to_cpumask(cpu_set_t mask) +static void bind_to_cpumask(cpu_set_t *mask) { int ret; + size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus()); - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + ret = sched_setaffinity(0, size, mask); + if (ret) { + CPU_FREE(mask); + BUG_ON(ret); + } } static void mempol_restore(void) @@ -376,7 +421,7 @@ do { \ static u8 *alloc_data(ssize_t bytes0, int map_flags, int init_zero, int init_cpu0, int thp, int init_random) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask = NULL; ssize_t bytes; u8 *buf; int ret; @@ -434,6 +479,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Restore affinity: */ if (init_cpu0) { bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); mempol_restore(); } @@ -585,10 +631,16 @@ static int parse_setup_cpu_list(void) return -1; } + if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) { + printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n"); + return -1; + } + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus); int i; for (i = 0; i < mul; i++) { @@ -608,10 +660,15 @@ static int parse_setup_cpu_list(void) tprintf("%2d", bind_cpu); } - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(size, td->bind_cpumask); for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { - BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); - CPU_SET(cpu, &td->bind_cpumask); + if (cpu < 0 || cpu >= g->p.nr_cpus) { + CPU_FREE(td->bind_cpumask); + BUG_ON(-1); + } + CPU_SET_S(cpu, size, td->bind_cpumask); } t++; } @@ -752,8 +809,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused, return parse_node_list(arg); } -#define BIT(x) (1ul << x) - static inline uint32_t lfsr_32(uint32_t lfsr) { const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); @@ -1241,7 +1296,7 @@ static void *worker_thread(void *__tdata) * by migrating to CPU#0: */ if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask; int target_cpu; int this_cpu; @@ -1265,6 +1320,7 @@ static void *worker_thread(void *__tdata) printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); } if (details >= 3) { @@ -1398,21 +1454,31 @@ static void init_thread_data(void) for (t = 0; t < g->p.nr_tasks; t++) { struct thread_data *td = g->threads + t; + size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus); int cpu; /* Allow all nodes by default: */ td->bind_node = NUMA_NO_NODE; /* Allow all CPUs by default: */ - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(cpuset_size, td->bind_cpumask); for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &td->bind_cpumask); + CPU_SET_S(cpu, cpuset_size, td->bind_cpumask); } } static void deinit_thread_data(void) { ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + /* Free the bind_cpumask allocated for thread_data */ + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + CPU_FREE(td->bind_cpumask); + } free_data(g->threads, size); } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index ad9ce1bfffa1..7de07bb16d23 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -301,7 +301,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap) static int set_tracing_cpu(struct perf_ftrace *ftrace) { - struct perf_cpu_map *cpumap = ftrace->evlist->core.cpus; + struct perf_cpu_map *cpumap = ftrace->evlist->core.user_requested_cpus; if (!target__has_cpu(&ftrace->target)) return 0; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0b4abed555d8..069825c48d40 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -987,10 +987,13 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru int m, tm, nr_mmaps = evlist->core.nr_mmaps; struct mmap *mmap = evlist->mmap; struct mmap *overwrite_mmap = evlist->overwrite_mmap; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; - thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, - thread_data->mask->maps.nbits); + if (cpu_map__is_dummy(cpus)) + thread_data->nr_mmaps = nr_mmaps; + else + thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, + thread_data->mask->maps.nbits); if (mmap) { thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *)); if (!thread_data->maps) @@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps); for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { - if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { + if (cpu_map__is_dummy(cpus) || + test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { if (thread_data->maps) { thread_data->maps[tm] = &mmap[m]; pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } if (thread_data->overwrite_maps) { thread_data->overwrite_maps[tm] = &overwrite_mmap[m]; pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } tm++; } @@ -1881,7 +1885,7 @@ static int record__synthesize(struct record *rec, bool tail) return err; } - err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.cpus, + err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus, process_synthesized_event, NULL); if (err < 0) { pr_err("Couldn't synthesize cpu map.\n"); @@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c { int c; + if (cpu_map__is_dummy(cpus)) + return; + for (c = 0; c < cpus->nr; c++) set_bit(cpus->map[c].cpu, mask->bits); } @@ -3675,11 +3682,16 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu static int record__init_thread_masks(struct record *rec) { int ret = 0; - struct perf_cpu_map *cpus = rec->evlist->core.cpus; + struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus; if (!record__threads_enabled(rec)) return record__init_thread_default_masks(rec, cpus); + if (cpu_map__is_dummy(cpus)) { + pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n"); + return -EINVAL; + } + switch (rec->opts.threads_spec) { case THREAD_SPEC__CPU: ret = record__init_thread_cpu_masks(rec, cpus); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 4ee40de698a4..a96f106dc93a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -804,7 +804,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (group) evlist__set_leader(evsel_list); - if (!cpu_map__is_dummy(evsel_list->core.cpus)) { + if (!cpu_map__is_dummy(evsel_list->core.user_requested_cpus)) { if (affinity__setup(&saved_affinity) < 0) return -1; affinity = &saved_affinity; @@ -1458,7 +1458,7 @@ static int perf_stat_init_aggr_mode(void) aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode); if (get_id) { - stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, /*data=*/NULL); if (!stat_config.aggr_map) { pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); @@ -1472,7 +1472,10 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - nr = perf_cpu_map__max(evsel_list->core.cpus).cpu; + if (evsel_list->core.user_requested_cpus) + nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu; + else + nr = 0; stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } @@ -1627,7 +1630,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) if (!get_id) return 0; - stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env); + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, env); if (!stat_config.aggr_map) { pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); return -1; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 9b08e44a31d9..fd8fd913c533 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1021,7 +1021,7 @@ static int perf_top__start_counters(struct perf_top *top) evlist__for_each_entry(evlist, counter) { try_again: - if (evsel__open(counter, top->evlist->core.cpus, + if (evsel__open(counter, top->evlist->core.user_requested_cpus, top->evlist->core.threads) < 0) { /* diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py index 461848c7f57d..bba68a6d4515 100755 --- a/tools/perf/python/tracepoint.py +++ b/tools/perf/python/tracepoint.py @@ -34,7 +34,7 @@ def main(): if not isinstance(event, perf.sample_event): continue - print "time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % ( + print("time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % ( event.sample_time, event.prev_comm, event.prev_pid, @@ -42,7 +42,7 @@ def main(): event.prev_state, event.next_comm, event.next_pid, - event.next_prio) + event.next_prio)) if __name__ == '__main__': main() diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..cc6df49a65a1 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -124,8 +131,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +198,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +207,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9e48652662d4..df1c5bbbaa0d 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, mp->idx = idx; if (per_cpu) { - mp->cpu = perf_cpu_map__cpu(evlist->core.cpus, idx); + mp->cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, idx); if (evlist->core.threads) mp->tid = perf_thread_map__pid(evlist->core.threads, 0); else diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 4f4d3aaff37c..7a4297d8fd2c 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -38,7 +38,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { - ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus); + ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus); bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus); } @@ -63,7 +63,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) fd = bpf_map__fd(skel->maps.cpu_filter); for (i = 0; i < ncpus; i++) { - cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu; + cpu = perf_cpu_map__cpu(ftrace->evlist->core.user_requested_cpus, i).cpu; bpf_map_update_elem(fd, &cpu, &val, BPF_ANY); } } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9bb79e049957..52ea004ba01e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -440,7 +440,7 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name) bool has_imm = false; // See explanation in evlist__close() - if (!cpu_map__is_dummy(evlist->core.cpus)) { + if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) { if (affinity__setup(&saved_affinity) < 0) return; affinity = &saved_affinity; @@ -500,7 +500,7 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name) struct affinity saved_affinity, *affinity = NULL; // See explanation in evlist__close() - if (!cpu_map__is_dummy(evlist->core.cpus)) { + if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) { if (affinity__setup(&saved_affinity) < 0) return; affinity = &saved_affinity; @@ -565,7 +565,7 @@ static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread) { int cpu; - int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); + int nr_cpus = perf_cpu_map__nr(evlist->core.user_requested_cpus); if (!evsel->core.fd) return -EINVAL; @@ -580,7 +580,7 @@ static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evse int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx) { - bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus); + bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus); if (per_cpu_mmaps) return evlist__enable_event_cpu(evlist, evsel, idx); @@ -1301,10 +1301,11 @@ void evlist__close(struct evlist *evlist) struct affinity affinity; /* - * With perf record core.cpus is usually NULL. + * With perf record core.user_requested_cpus is usually NULL. * Use the old method to handle this for now. */ - if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) { + if (!evlist->core.user_requested_cpus || + cpu_map__is_dummy(evlist->core.user_requested_cpus)) { evlist__for_each_entry_reverse(evlist, evsel) evsel__close(evsel); return; @@ -1330,7 +1331,6 @@ static int evlist__create_syswide_maps(struct evlist *evlist) { struct perf_cpu_map *cpus; struct perf_thread_map *threads; - int err = -ENOMEM; /* * Try reading /sys/devices/system/cpu/online to get @@ -1355,7 +1355,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist) out_put: perf_cpu_map__put(cpus); out: - return err; + return -ENOMEM; } int evlist__open(struct evlist *evlist) @@ -1367,7 +1367,7 @@ int evlist__open(struct evlist *evlist) * Default: one fd per CPU, all threads, aka systemwide * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL */ - if (evlist->core.threads == NULL && evlist->core.cpus == NULL) { + if (evlist->core.threads == NULL && evlist->core.user_requested_cpus == NULL) { err = evlist__create_syswide_maps(evlist); if (err < 0) goto out_err; diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c index 3c20b126d60d..aeb09c288716 100644 --- a/tools/perf/util/hashmap.c +++ b/tools/perf/util/hashmap.c @@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map) void hashmap__free(struct hashmap *map) { - if (!map) + if (IS_ERR_OR_NULL(map)) return; hashmap__clear(map); @@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key, return true; } - diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d546ff724dbe..a27132e5a5ef 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff, return do_write(ff, &data->dir.version, sizeof(data->dir.version)); } +/* + * Check whether a CPU is online + * + * Returns: + * 1 -> if CPU is online + * 0 -> if CPU is offline + * -1 -> error case + */ +int is_cpu_online(unsigned int cpu) +{ + char *str; + size_t strlen; + char buf[256]; + int status = -1; + struct stat statbuf; + + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d", cpu); + if (stat(buf, &statbuf) != 0) + return 0; + + /* + * Check if /sys/devices/system/cpu/cpux/online file + * exists. Some cases cpu0 won't have online file since + * it is not expected to be turned off generally. + * In kernels without CONFIG_HOTPLUG_CPU, this + * file won't exist + */ + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d/online", cpu); + if (stat(buf, &statbuf) != 0) + return 1; + + /* + * Read online file using sysfs__read_str. + * If read or open fails, return -1. + * If read succeeds, return value from file + * which gets stored in "str" + */ + snprintf(buf, sizeof(buf), + "devices/system/cpu/cpu%d/online", cpu); + + if (sysfs__read_str(buf, &str, &strlen) < 0) + return status; + + status = atoi(str); + + free(str); + return status; +} + #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, struct evlist *evlist __maybe_unused) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index c9e3265832d9..0eb4bc29a5a4 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size); int write_padded(struct feat_fd *fd, const void *bf, size_t count, size_t count_aligned); +int is_cpu_online(unsigned int cpu); /* * arch specific callback */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 24997925ae00..dd84fed698a3 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, bool use_uncore_alias; LIST_HEAD(config_terms); - if (verbose > 1) { + pmu = parse_state->fake_pmu ?: perf_pmu__find(name); + + if (verbose > 1 && !(pmu && pmu->selectable)) { fprintf(stderr, "Attempting to add event pmu '%s' with '", name); if (head_config) { @@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, fprintf(stderr, "' that may result in non-fatal errors\n"); } - pmu = parse_state->fake_pmu ?: perf_pmu__find(name); if (!pmu) { char *err_str; diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 007a64681416..5b09ecbb05dc 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call if (opts->group) evlist__set_leader(evlist); - if (perf_cpu_map__cpu(evlist->core.cpus, 0).cpu < 0) + if (perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0).cpu < 0) opts->no_inherit = true; use_comm_exec = perf_can_comm_exec(); @@ -244,7 +244,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) evsel = evlist__last(temp_evlist); - if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { + if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) { struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); if (cpus) @@ -252,7 +252,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) perf_cpu_map__put(cpus); } else { - cpu = perf_cpu_map__cpu(evlist->core.cpus, 0); + cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0); } while (1) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..45a30040ec8d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c index 748371ac22be..388846f17bc1 100644 --- a/tools/perf/util/sideband_evlist.c +++ b/tools/perf/util/sideband_evlist.c @@ -114,7 +114,8 @@ int evlist__start_sb_thread(struct evlist *evlist, struct target *target) } evlist__for_each_entry(evlist, counter) { - if (evsel__open(counter, evlist->core.cpus, evlist->core.threads) < 0) + if (evsel__open(counter, evlist->core.user_requested_cpus, + evlist->core.threads) < 0) goto out_delete_evlist; } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 9cbe351b141f..138e3ab9d638 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -929,7 +929,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config, int all_idx; struct perf_cpu cpu; - perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) { + perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) { struct evsel *counter; bool first = true; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ee6f03481215..817a2de264b4 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/err.h> #include <inttypes.h> #include <math.h> #include <string.h> @@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, if (!mask) { mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL); - if (!mask) + if (IS_ERR(mask)) return -ENOMEM; counter->per_pkg_mask = mask; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index b654de0841f8..27acdc5e5723 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2127,7 +2127,7 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p return err; } - err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL); + err = perf_event__synthesize_cpu_map(tool, evlist->core.user_requested_cpus, process, NULL); if (err < 0) { pr_err("Couldn't synthesize thread map.\n"); return err; diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index c1ebfc5d2e0c..b8b32431d2f7 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -95,15 +95,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "", + perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1 + ? "s" : "", target->cpu_list); else { if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", - perf_cpu_map__nr(top->evlist->core.cpus), - perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : ""); + perf_cpu_map__nr(top->evlist->core.user_requested_cpus), + perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1 + ? "s" : ""); } perf_top__reset_sample_counters(top); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } |