diff options
Diffstat (limited to 'tools')
45 files changed, 386 insertions, 222 deletions
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 2975632d51e2..c8fe6d177119 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -41,6 +41,7 @@ FEATURE_TESTS ?= \ libelf-getphdrnum \ libelf-mmap \ libnuma \ + numa_num_possible_cpus \ libperl \ libpython \ libpython-version \ @@ -51,7 +52,8 @@ FEATURE_TESTS ?= \ timerfd \ libdw-dwarf-unwind \ zlib \ - lzma + lzma \ + get_cpuid FEATURE_DISPLAY ?= \ dwarf \ @@ -61,13 +63,15 @@ FEATURE_DISPLAY ?= \ libbfd \ libelf \ libnuma \ + numa_num_possible_cpus \ libperl \ libpython \ libslang \ libunwind \ libdw-dwarf-unwind \ zlib \ - lzma + lzma \ + get_cpuid # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 74ca42093d70..e43a2971bf56 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -19,6 +19,7 @@ FILES= \ test-libelf-getphdrnum.bin \ test-libelf-mmap.bin \ test-libnuma.bin \ + test-numa_num_possible_cpus.bin \ test-libperl.bin \ test-libpython.bin \ test-libpython-version.bin \ @@ -34,7 +35,8 @@ FILES= \ test-compile-x32.bin \ test-zlib.bin \ test-lzma.bin \ - test-bpf.bin + test-bpf.bin \ + test-get_cpuid.bin CC := $(CROSS_COMPILE)gcc -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config @@ -87,6 +89,9 @@ test-libelf-getphdrnum.bin: test-libnuma.bin: $(BUILD) -lnuma +test-numa_num_possible_cpus.bin: + $(BUILD) -lnuma + test-libunwind.bin: $(BUILD) -lelf @@ -162,6 +167,9 @@ test-zlib.bin: test-lzma.bin: $(BUILD) -llzma +test-get_cpuid.bin: + $(BUILD) + test-bpf.bin: $(BUILD) diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 84689a67814a..33cf6f20bd4e 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -77,6 +77,10 @@ # include "test-libnuma.c" #undef main +#define main main_test_numa_num_possible_cpus +# include "test-numa_num_possible_cpus.c" +#undef main + #define main main_test_timerfd # include "test-timerfd.c" #undef main @@ -117,6 +121,10 @@ # include "test-lzma.c" #undef main +#define main main_test_get_cpuid +# include "test-get_cpuid.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -136,6 +144,7 @@ int main(int argc, char *argv[]) main_test_libbfd(); main_test_backtrace(); main_test_libnuma(); + main_test_numa_num_possible_cpus(); main_test_timerfd(); main_test_stackprotector_all(); main_test_libdw_dwarf_unwind(); @@ -143,6 +152,7 @@ int main(int argc, char *argv[]) main_test_zlib(); main_test_pthread_attr_setaffinity_np(); main_test_lzma(); + main_test_get_cpuid(); return 0; } diff --git a/tools/build/feature/test-get_cpuid.c b/tools/build/feature/test-get_cpuid.c new file mode 100644 index 000000000000..d7a2c407130d --- /dev/null +++ b/tools/build/feature/test-get_cpuid.c @@ -0,0 +1,7 @@ +#include <cpuid.h> + +int main(void) +{ + unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0; + return __get_cpuid(0x15, &eax, &ebx, &ecx, &edx); +} diff --git a/tools/build/feature/test-numa_num_possible_cpus.c b/tools/build/feature/test-numa_num_possible_cpus.c new file mode 100644 index 000000000000..2606e94b0659 --- /dev/null +++ b/tools/build/feature/test-numa_num_possible_cpus.c @@ -0,0 +1,6 @@ +#include <numa.h> + +int main(void) +{ + return numa_num_possible_cpus(); +} diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 4d885934b919..cf42b090477b 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -3795,7 +3795,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, struct format_field *field; struct printk_map *printk; long long val, fval; - unsigned long addr; + unsigned long long addr; char *str; unsigned char *hex; int print; @@ -3828,13 +3828,30 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, */ if (!(field->flags & FIELD_IS_ARRAY) && field->size == pevent->long_size) { - addr = *(unsigned long *)(data + field->offset); + + /* Handle heterogeneous recording and processing + * architectures + * + * CASE I: + * Traces recorded on 32-bit devices (32-bit + * addressing) and processed on 64-bit devices: + * In this case, only 32 bits should be read. + * + * CASE II: + * Traces recorded on 64 bit devices and processed + * on 32-bit devices: + * In this case, 64 bits must be read. + */ + addr = (pevent->long_size == 8) ? + *(unsigned long long *)(data + field->offset) : + (unsigned long long)*(unsigned int *)(data + field->offset); + /* Check if it matches a print format */ printk = find_printk(pevent, addr); if (printk) trace_seq_puts(s, printk->printk); else - trace_seq_printf(s, "%lx", addr); + trace_seq_printf(s, "%llx", addr); break; } str = malloc(len + 1); diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index 4a0501d7a3b4..c94c9de3173e 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -364,21 +364,6 @@ cyc_thresh Specifies how frequently CYC packets are produced - see cyc CYC packets are not requested by default. -no_force_psb This is a driver option and is not in the IA32_RTIT_CTL MSR. - - It stops the driver resetting the byte count to zero whenever - enabling the trace (for example on context switches) which in - turn results in no PSB being forced. However some processors - will produce a PSB anyway. - - In any case, there is still a PSB when the trace is enabled for - the first time. - - no_force_psb can be used to slightly decrease the trace size but - may make it harder for the decoder to recover from errors. - - no_force_psb is not selected by default. - new snapshot option ------------------- diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index eb51325e8ad9..284a76e04628 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -768,8 +768,8 @@ static int process_exit_event(struct perf_tool *tool, if (!evsel->attr.sample_id_all) { sample->cpu = 0; sample->time = 0; - sample->tid = event->comm.tid; - sample->pid = event->comm.pid; + sample->tid = event->fork.tid; + sample->pid = event->fork.pid; } print_sample_start(sample, thread, evsel); perf_event__fprintf(event, stdout); diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 827557fc7511..38a08539f4bf 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -573,9 +573,14 @@ ifndef NO_LIBNUMA msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev); NO_LIBNUMA := 1 else - CFLAGS += -DHAVE_LIBNUMA_SUPPORT - EXTLIBS += -lnuma - $(call detected,CONFIG_NUMA) + ifeq ($(feature-numa_num_possible_cpus), 0) + msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8); + NO_LIBNUMA := 1 + else + CFLAGS += -DHAVE_LIBNUMA_SUPPORT + EXTLIBS += -lnuma + $(call detected,CONFIG_NUMA) + endif endif endif @@ -621,8 +626,13 @@ ifdef LIBBABELTRACE endif ifndef NO_AUXTRACE - $(call detected,CONFIG_AUXTRACE) - CFLAGS += -DHAVE_AUXTRACE_SUPPORT + ifeq ($(feature-get_cpuid), 0) + msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc); + NO_AUXTRACE := 1 + else + $(call detected,CONFIG_AUXTRACE) + CFLAGS += -DHAVE_AUXTRACE_SUPPORT + endif endif # Among the variables below, these: diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 1aa21c90731b..5b83f56a3b6f 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -34,6 +34,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) .disabled = 1, .freq = 1, }; + struct cpu_map *cpus; + struct thread_map *threads; attr.sample_freq = 500; @@ -50,14 +52,19 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) } perf_evlist__add(evlist, evsel); - evlist->cpus = cpu_map__dummy_new(); - evlist->threads = thread_map__new_by_tid(getpid()); - if (!evlist->cpus || !evlist->threads) { + cpus = cpu_map__dummy_new(); + threads = thread_map__new_by_tid(getpid()); + if (!cpus || !threads) { err = -ENOMEM; pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_delete_evlist; + goto out_free_maps; } + perf_evlist__set_maps(evlist, cpus, threads); + + cpus = NULL; + threads = NULL; + if (perf_evlist__open(evlist)) { const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate"; @@ -107,6 +114,9 @@ next_event: err = -1; } +out_free_maps: + cpu_map__put(cpus); + thread_map__put(threads); out_delete_evlist: perf_evlist__delete(evlist); return err; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 3a8fedef83bc..add16385f13e 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -43,6 +43,8 @@ int test__task_exit(void) }; const char *argv[] = { "true", NULL }; char sbuf[STRERR_BUFSIZE]; + struct cpu_map *cpus; + struct thread_map *threads; signal(SIGCHLD, sig_handler); @@ -58,14 +60,19 @@ int test__task_exit(void) * perf_evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - evlist->cpus = cpu_map__dummy_new(); - evlist->threads = thread_map__new_by_tid(-1); - if (!evlist->cpus || !evlist->threads) { + cpus = cpu_map__dummy_new(); + threads = thread_map__new_by_tid(-1); + if (!cpus || !threads) { err = -ENOMEM; pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_delete_evlist; + goto out_free_maps; } + perf_evlist__set_maps(evlist, cpus, threads); + + cpus = NULL; + threads = NULL; + err = perf_evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal); if (err < 0) { @@ -114,6 +121,9 @@ retry: err = -1; } +out_free_maps: + cpu_map__put(cpus); + thread_map__put(threads); out_delete_evlist: perf_evlist__delete(evlist); return err; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index cf86f2d3a5e7..c04c60d4863c 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1968,7 +1968,8 @@ skip_annotation: &options[nr_options], dso); nr_options += add_map_opt(browser, &actions[nr_options], &options[nr_options], - browser->selection->map); + browser->selection ? + browser->selection->map : NULL); /* perf script support */ if (browser->he_selection) { @@ -1976,6 +1977,15 @@ skip_annotation: &actions[nr_options], &options[nr_options], thread, NULL); + /* + * Note that browser->selection != NULL + * when browser->he_selection is not NULL, + * so we don't need to check browser->selection + * before fetching browser->selection->sym like what + * we do before fetching browser->selection->map. + * + * See hist_browser__show_entry. + */ nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d51a5200c8af..c8fc8a258f42 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -124,6 +124,33 @@ void perf_evlist__delete(struct perf_evlist *evlist) free(evlist); } +static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + /* + * We already have cpus for evsel (via PMU sysfs) so + * keep it, if there's no target cpu list defined. + */ + if (!evsel->own_cpus || evlist->has_user_cpus) { + cpu_map__put(evsel->cpus); + evsel->cpus = cpu_map__get(evlist->cpus); + } else if (evsel->cpus != evsel->own_cpus) { + cpu_map__put(evsel->cpus); + evsel->cpus = cpu_map__get(evsel->own_cpus); + } + + thread_map__put(evsel->threads); + evsel->threads = thread_map__get(evlist->threads); +} + +static void perf_evlist__propagate_maps(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + __perf_evlist__propagate_maps(evlist, evsel); +} + void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { entry->evlist = evlist; @@ -133,18 +160,19 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) if (!evlist->nr_entries++) perf_evlist__set_id_pos(evlist); + + __perf_evlist__propagate_maps(evlist, entry); } void perf_evlist__splice_list_tail(struct perf_evlist *evlist, - struct list_head *list, - int nr_entries) + struct list_head *list) { - bool set_id_pos = !evlist->nr_entries; + struct perf_evsel *evsel, *temp; - list_splice_tail(list, &evlist->entries); - evlist->nr_entries += nr_entries; - if (set_id_pos) - perf_evlist__set_id_pos(evlist); + __evlist__for_each_safe(list, temp, evsel) { + list_del_init(&evsel->node); + perf_evlist__add(evlist, evsel); + } } void __perf_evlist__set_leader(struct list_head *list) @@ -210,7 +238,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist, list_add_tail(&evsel->node, &head); } - perf_evlist__splice_list_tail(evlist, &head, nr_attrs); + perf_evlist__splice_list_tail(evlist, &head); return 0; @@ -1103,71 +1131,56 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false); } -static int perf_evlist__propagate_maps(struct perf_evlist *evlist, - bool has_user_cpus) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - /* - * We already have cpus for evsel (via PMU sysfs) so - * keep it, if there's no target cpu list defined. - */ - if (evsel->cpus && has_user_cpus) - cpu_map__put(evsel->cpus); - - if (!evsel->cpus || has_user_cpus) - evsel->cpus = cpu_map__get(evlist->cpus); - - evsel->threads = thread_map__get(evlist->threads); - - if ((evlist->cpus && !evsel->cpus) || - (evlist->threads && !evsel->threads)) - return -ENOMEM; - } - - return 0; -} - int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) { - evlist->threads = thread_map__new_str(target->pid, target->tid, - target->uid); + struct cpu_map *cpus; + struct thread_map *threads; + + threads = thread_map__new_str(target->pid, target->tid, target->uid); - if (evlist->threads == NULL) + if (!threads) return -1; if (target__uses_dummy_map(target)) - evlist->cpus = cpu_map__dummy_new(); + cpus = cpu_map__dummy_new(); else - evlist->cpus = cpu_map__new(target->cpu_list); + cpus = cpu_map__new(target->cpu_list); - if (evlist->cpus == NULL) + if (!cpus) goto out_delete_threads; - return perf_evlist__propagate_maps(evlist, !!target->cpu_list); + evlist->has_user_cpus = !!target->cpu_list; + + perf_evlist__set_maps(evlist, cpus, threads); + + return 0; out_delete_threads: - thread_map__put(evlist->threads); - evlist->threads = NULL; + thread_map__put(threads); return -1; } -int perf_evlist__set_maps(struct perf_evlist *evlist, - struct cpu_map *cpus, - struct thread_map *threads) +void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads) { - if (evlist->cpus) + /* + * Allow for the possibility that one or another of the maps isn't being + * changed i.e. don't put it. Note we are assuming the maps that are + * being applied are brand new and evlist is taking ownership of the + * original reference count of 1. If that is not the case it is up to + * the caller to increase the reference count. + */ + if (cpus != evlist->cpus) { cpu_map__put(evlist->cpus); + evlist->cpus = cpus; + } - evlist->cpus = cpus; - - if (evlist->threads) + if (threads != evlist->threads) { thread_map__put(evlist->threads); + evlist->threads = threads; + } - evlist->threads = threads; - - return perf_evlist__propagate_maps(evlist, false); + perf_evlist__propagate_maps(evlist); } int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) @@ -1387,6 +1400,8 @@ void perf_evlist__close(struct perf_evlist *evlist) static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) { + struct cpu_map *cpus; + struct thread_map *threads; int err = -ENOMEM; /* @@ -1398,20 +1413,19 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) * error, and we may not want to do that fallback to a * default cpu identity map :-\ */ - evlist->cpus = cpu_map__new(NULL); - if (evlist->cpus == NULL) + cpus = cpu_map__new(NULL); + if (!cpus) goto out; - evlist->threads = thread_map__new_dummy(); - if (evlist->threads == NULL) - goto out_free_cpus; + threads = thread_map__new_dummy(); + if (!threads) + goto out_put; - err = 0; + perf_evlist__set_maps(evlist, cpus, threads); out: return err; -out_free_cpus: - cpu_map__put(evlist->cpus); - evlist->cpus = NULL; +out_put: + cpu_map__put(cpus); goto out; } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b39a6198f4ac..115d8b53c601 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -42,6 +42,7 @@ struct perf_evlist { int nr_mmaps; bool overwrite; bool enabled; + bool has_user_cpus; size_t mmap_len; int id_pos; int is_pos; @@ -155,9 +156,8 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist, void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); -int perf_evlist__set_maps(struct perf_evlist *evlist, - struct cpu_map *cpus, - struct thread_map *threads); +void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads); int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target); int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel); @@ -179,8 +179,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, - struct list_head *list, - int nr_entries); + struct list_head *list); static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c53f79123b37..5410483d5219 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1033,6 +1033,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) perf_evsel__free_config_terms(evsel); close_cgroup(evsel->cgrp); cpu_map__put(evsel->cpus); + cpu_map__put(evsel->own_cpus); thread_map__put(evsel->threads); zfree(&evsel->group_name); zfree(&evsel->name); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 298e6bbca200..ef8925f7211a 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -98,6 +98,7 @@ struct perf_evsel { struct cgroup_sel *cgrp; void *handler; struct cpu_map *cpus; + struct cpu_map *own_cpus; struct thread_map *threads; unsigned int sample_size; int id_pos; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 41814547da15..fce6634aebe2 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1438,7 +1438,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, if (ph->needs_swap) nr = bswap_32(nr); - ph->env.nr_cpus_online = nr; + ph->env.nr_cpus_avail = nr; ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) @@ -1447,7 +1447,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, if (ph->needs_swap) nr = bswap_32(nr); - ph->env.nr_cpus_avail = nr; + ph->env.nr_cpus_online = nr; return 0; } diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index ea768625ab5b..eb0e7f8bf515 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -623,7 +623,7 @@ static int intel_bts_process_event(struct perf_session *session, if (err) return err; if (event->header.type == PERF_RECORD_EXIT) { - err = intel_bts_process_tid_exit(bts, event->comm.tid); + err = intel_bts_process_tid_exit(bts, event->fork.tid); if (err) return err; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index bb41c20e6005..535d86f8e4d1 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1494,7 +1494,7 @@ static int intel_pt_process_event(struct perf_session *session, if (pt->timeless_decoding) { if (event->header.type == PERF_RECORD_EXIT) { err = intel_pt_process_timeless_queues(pt, - event->comm.tid, + event->fork.tid, sample->time); } } else if (timestamp) { diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d826e6f515db..21ed6ee63da9 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -287,8 +287,8 @@ __add_event(struct list_head *list, int *idx, if (!evsel) return NULL; - if (cpus) - evsel->cpus = cpu_map__get(cpus); + evsel->cpus = cpu_map__get(cpus); + evsel->own_cpus = cpu_map__get(cpus); if (name) evsel->name = strdup(name); @@ -1140,10 +1140,9 @@ int parse_events(struct perf_evlist *evlist, const char *str, ret = parse_events__scanner(str, &data, PE_START_EVENTS); perf_pmu__parse_cleanup(); if (!ret) { - int entries = data.idx - evlist->nr_entries; struct perf_evsel *last; - perf_evlist__splice_list_tail(evlist, &data.list, entries); + perf_evlist__splice_list_tail(evlist, &data.list); evlist->nr_groups += data.nr_groups; last = perf_evlist__last(evlist); last->cmdline_group_boundary = true; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 591905a02b92..9cd70819c795 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -255,7 +255,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc list_add_tail(&term->list, head); ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head)); + ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); parse_events__free_terms(head); $$ = list; } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index eb5f18b75402..c6f9af78f6f5 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -270,12 +270,13 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) int ret = 0; if (module) { - list_for_each_entry(dso, &host_machine->dsos.head, node) { - if (!dso->kernel) - continue; - if (strncmp(dso->short_name + 1, module, - dso->short_name_len - 2) == 0) - goto found; + char module_name[128]; + + snprintf(module_name, sizeof(module_name), "[%s]", module); + map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name); + if (map) { + dso = map->dso; + goto found; } pr_debug("Failed to find module %s.\n", module); return -ENOENT; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8a4537ee9bc3..fc3f7c922f99 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1580,7 +1580,10 @@ static int __perf_session__process_events(struct perf_session *session, file_offset = page_offset; head = data_offset - page_offset; - if (data_size && (data_offset + data_size < file_size)) + if (data_size == 0) + goto out; + + if (data_offset + data_size < file_size) file_size = data_offset + data_size; ui_progress__init(&prog, file_size, "Processing events..."); diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 415c359de465..2d065d065b67 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter) memset(counter->per_pkg_mask, 0, MAX_NR_CPUS); } -static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) +static int check_per_pkg(struct perf_evsel *counter, + struct perf_counts_values *vals, int cpu, bool *skip) { unsigned long *mask = counter->per_pkg_mask; struct cpu_map *cpus = perf_evsel__cpus(counter); @@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) counter->per_pkg_mask = mask; } + /* + * we do not consider an event that has not run as a good + * instance to mark a package as used (skip=1). Otherwise + * we may run into a situation where the first CPU in a package + * is not running anything, yet the second is, and this function + * would mark the package as used after the first CPU and would + * not read the values from the second CPU. + */ + if (!(vals->run && vals->ena)) + return 0; + s = cpu_map__get_socket(cpus, cpu); if (s < 0) return -1; @@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel static struct perf_counts_values zero; bool skip = false; - if (check_per_pkg(evsel, cpu, &skip)) { + if (check_per_pkg(evsel, count, cpu, &skip)) { pr_err("failed to read per-pkg counter\n"); return -1; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 53bb5f59ec58..475d88d0a1c9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -38,7 +38,7 @@ static inline char *bfd_demangle(void __maybe_unused *v, #endif #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT -int elf_getphdrnum(Elf *elf, size_t *dst) +static int elf_getphdrnum(Elf *elf, size_t *dst) { GElf_Ehdr gehdr; GElf_Ehdr *ehdr; @@ -1271,8 +1271,6 @@ out_close: static int kcore__init(struct kcore *kcore, char *filename, int elfclass, bool temp) { - GElf_Ehdr *ehdr; - kcore->elfclass = elfclass; if (temp) @@ -1289,9 +1287,7 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass, if (!gelf_newehdr(kcore->elf, elfclass)) goto out_end; - ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr); - if (!ehdr) - goto out_end; + memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr)); return 0; @@ -1348,23 +1344,18 @@ static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count) static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset, u64 addr, u64 len) { - GElf_Phdr gphdr; - GElf_Phdr *phdr; - - phdr = gelf_getphdr(kcore->elf, idx, &gphdr); - if (!phdr) - return -1; - - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R | PF_W | PF_X; - phdr->p_offset = offset; - phdr->p_vaddr = addr; - phdr->p_paddr = 0; - phdr->p_filesz = len; - phdr->p_memsz = len; - phdr->p_align = page_size; - - if (!gelf_update_phdr(kcore->elf, idx, phdr)) + GElf_Phdr phdr = { + .p_type = PT_LOAD, + .p_flags = PF_R | PF_W | PF_X, + .p_offset = offset, + .p_vaddr = addr, + .p_paddr = 0, + .p_filesz = len, + .p_memsz = len, + .p_align = page_size, + }; + + if (!gelf_update_phdr(kcore->elf, idx, &phdr)) return -1; return 0; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 7acafb3c5592..c2cd9bf2348b 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -709,7 +709,7 @@ bool find_process(const char *name) dir = opendir(procfs__mountpoint()); if (!dir) - return -1; + return false; /* Walk through the directory. */ while (ret && (d = readdir(dir)) != NULL) { diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9655cb49c7cb..bde0ef1a63df 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -71,8 +71,11 @@ unsigned int extra_msr_offset32; unsigned int extra_msr_offset64; unsigned int extra_delta_offset32; unsigned int extra_delta_offset64; +unsigned int aperf_mperf_multiplier = 1; int do_smi; double bclk; +double base_hz; +double tsc_tweak = 1.0; unsigned int show_pkg; unsigned int show_core; unsigned int show_cpu; @@ -502,7 +505,7 @@ int format_counters(struct thread_data *t, struct core_data *c, /* %Busy */ if (has_aperf) { if (!skip_c0) - outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc); + outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak); else outp += sprintf(outp, "********"); } @@ -510,7 +513,7 @@ int format_counters(struct thread_data *t, struct core_data *c, /* Bzy_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", - 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); + 1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float); /* TSC_MHz */ outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float); @@ -984,6 +987,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -3; if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) return -4; + t->aperf = t->aperf * aperf_mperf_multiplier; + t->mperf = t->mperf * aperf_mperf_multiplier; } if (do_smi) { @@ -1149,6 +1154,19 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; + +static void +calculate_tsc_tweak() +{ + unsigned long long msr; + unsigned int base_ratio; + + get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); + base_ratio = (msr >> 8) & 0xFF; + base_hz = base_ratio * bclk * 1000000; + tsc_tweak = base_hz / tsc_hz; +} + static void dump_nhm_platform_info(void) { @@ -1926,8 +1944,6 @@ int has_config_tdp(unsigned int family, unsigned int model) switch (model) { case 0x3A: /* IVB */ - case 0x3E: /* IVB Xeon */ - case 0x3C: /* HSW */ case 0x3F: /* HSX */ case 0x45: /* HSW */ @@ -2543,6 +2559,13 @@ int is_knl(unsigned int family, unsigned int model) return 0; } +unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model) +{ + if (is_knl(family, model)) + return 1024; + return 1; +} + #define SLM_BCLK_FREQS 5 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0}; @@ -2744,6 +2767,9 @@ void process_cpuid() } } + if (has_aperf) + aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model); + do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model); do_snb_cstates = has_snb_msrs(family, model); do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2); @@ -2762,6 +2788,9 @@ void process_cpuid() if (debug) dump_cstate_pstate_config_info(); + if (has_skl_msrs(family, model)) + calculate_tsc_tweak(); + return; } @@ -3090,7 +3119,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(stderr, "turbostat version 4.7 17-June, 2015" + fprintf(stderr, "turbostat version 4.8 26-Sep, 2015" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 89b05e2222c9..cfe121353eec 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -16,12 +16,12 @@ TARGETS += powerpc TARGETS += ptrace TARGETS += seccomp TARGETS += size +TARGETS += static_keys TARGETS += sysctl ifneq (1, $(quicktest)) TARGETS += timers endif TARGETS += user -TARGETS += jumplabel TARGETS += vm TARGETS += x86 TARGETS += zram diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index 6b76bfdc847e..4e400eb83657 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -1,6 +1,6 @@ CFLAGS = -Wall BINARIES = execveat -DEPS = execveat.symlink execveat.denatured script +DEPS = execveat.symlink execveat.denatured script subdir all: $(BINARIES) $(DEPS) subdir: @@ -22,7 +22,5 @@ TEST_FILES := $(DEPS) include ../lib.mk -override EMIT_TESTS := echo "mkdir -p subdir; (./execveat && echo \"selftests: execveat [PASS]\") || echo \"selftests: execveat [FAIL]\"" - clean: rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx* diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index 0acbeca47225..4e6ed13e7f66 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,7 @@ all: TEST_PROGS := ftracetest -TEST_DIRS := test.d/ +TEST_DIRS := test.d include ../lib.mk diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 97f1c6742066..50a93f5f13d6 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -12,13 +12,10 @@ run_tests: all $(RUN_TESTS) define INSTALL_RULE - @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - mkdir -p $(INSTALL_PATH); \ - for TEST_DIR in $(TEST_DIRS); do \ - cp -r $$TEST_DIR $(INSTALL_PATH); \ - done; \ - echo "install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)"; \ - install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES); \ + @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ + mkdir -p ${INSTALL_PATH}; \ + echo "rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ fi endef diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile index 877a50355d7f..a1a97085847d 100644 --- a/tools/testing/selftests/membarrier/Makefile +++ b/tools/testing/selftests/membarrier/Makefile @@ -1,11 +1,10 @@ CFLAGS += -g -I../../../../usr/include/ -all: - $(CC) $(CFLAGS) membarrier_test.c -o membarrier_test - TEST_PROGS := membarrier_test +all: $(TEST_PROGS) + include ../lib.mk clean: - $(RM) membarrier_test + $(RM) $(TEST_PROGS) diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c index dde312508007..535f0fef4d0b 100644 --- a/tools/testing/selftests/membarrier/membarrier_test.c +++ b/tools/testing/selftests/membarrier/membarrier_test.c @@ -1,9 +1,6 @@ #define _GNU_SOURCE -#define __EXPORTED_HEADERS__ - #include <linux/membarrier.h> -#include <asm-generic/unistd.h> -#include <sys/syscall.h> +#include <syscall.h> #include <stdio.h> #include <errno.h> #include <string.h> diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 0e3b41eb85cd..eebac29acbd9 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -1,8 +1,8 @@ -CFLAGS = -O2 +CFLAGS += -O2 +LDLIBS = -lrt -lpthread -lpopt +TEST_PROGS := mq_open_tests mq_perf_tests -all: - $(CC) $(CFLAGS) mq_open_tests.c -o mq_open_tests -lrt - $(CC) $(CFLAGS) -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt +all: $(TEST_PROGS) include ../lib.mk @@ -11,8 +11,6 @@ override define RUN_TESTS @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef -TEST_PROGS := mq_open_tests mq_perf_tests - override define EMIT_TESTS echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\"" echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\"" diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index a004b4cce99e..770f47adf295 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1210,6 +1210,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) # define ARCH_REGS struct pt_regs # define SYSCALL_NUM gpr[0] # define SYSCALL_RET gpr[3] +#elif defined(__s390__) +# define ARCH_REGS s390_regs +# define SYSCALL_NUM gprs[2] +# define SYSCALL_RET gprs[2] #else # error "Do not know how to find your architecture's registers and syscalls" #endif @@ -1243,7 +1247,8 @@ void change_syscall(struct __test_metadata *_metadata, ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov); EXPECT_EQ(0, ret); -#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) || defined(__powerpc__) +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) || \ + defined(__powerpc__) || defined(__s390__) { regs.SYSCALL_NUM = syscall; } @@ -1281,17 +1286,21 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg); EXPECT_EQ(0, ret); + /* Validate and take action on expected syscalls. */ switch (msg) { case 0x1002: /* change getpid to getppid. */ + EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee)); change_syscall(_metadata, tracee, __NR_getppid); break; case 0x1003: /* skip gettid. */ + EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee)); change_syscall(_metadata, tracee, -1); break; case 0x1004: /* do nothing (allow getppid) */ + EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee)); break; default: EXPECT_EQ(0, msg) { @@ -1409,6 +1418,8 @@ TEST_F(TRACE_syscall, syscall_dropped) # define __NR_seccomp 277 # elif defined(__powerpc__) # define __NR_seccomp 358 +# elif defined(__s390__) +# define __NR_seccomp 348 # else # warning "seccomp syscall number unknown for this architecture" # define __NR_seccomp 0xffff @@ -1453,6 +1464,9 @@ TEST(seccomp_syscall) /* Reject insane operation. */ ret = seccomp(-1, 0, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } EXPECT_EQ(EINVAL, errno) { TH_LOG("Did not reject crazy op value!"); } @@ -1501,6 +1515,9 @@ TEST(seccomp_syscall_mode_lock) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } EXPECT_EQ(0, ret) { TH_LOG("Could not install filter!"); } @@ -1535,6 +1552,9 @@ TEST(TSYNC_first) ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } EXPECT_EQ(0, ret) { TH_LOG("Could not install initial filter with TSYNC!"); } @@ -1694,6 +1714,9 @@ TEST_F(TSYNC, siblings_fail_prctl) /* Check prctl failure detection by requesting sib 0 diverge. */ ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("setting filter failed"); } @@ -1731,6 +1754,9 @@ TEST_F(TSYNC, two_siblings_with_ancestor) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } @@ -1805,6 +1831,9 @@ TEST_F(TSYNC, two_siblings_with_no_filter) ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, &self->apply_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Could install filter on all threads!"); } @@ -1833,6 +1862,9 @@ TEST_F(TSYNC, two_siblings_with_one_divergence) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } @@ -1890,6 +1922,9 @@ TEST_F(TSYNC, two_siblings_not_under_filter) } ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } diff --git a/tools/testing/selftests/seccomp/test_harness.h b/tools/testing/selftests/seccomp/test_harness.h index 977a6afc4489..fb2841601f2f 100644 --- a/tools/testing/selftests/seccomp/test_harness.h +++ b/tools/testing/selftests/seccomp/test_harness.h @@ -370,11 +370,8 @@ __typeof__(_expected) __exp = (_expected); \ __typeof__(_seen) __seen = (_seen); \ if (!(__exp _t __seen)) { \ - unsigned long long __exp_print = 0; \ - unsigned long long __seen_print = 0; \ - /* Avoid casting complaints the scariest way we can. */ \ - memcpy(&__exp_print, &__exp, sizeof(__exp)); \ - memcpy(&__seen_print, &__seen, sizeof(__seen)); \ + unsigned long long __exp_print = (unsigned long long)__exp; \ + unsigned long long __seen_print = (unsigned long long)__seen; \ __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ #_expected, __exp_print, #_t, \ #_seen, __seen_print); \ diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index d36fab7d8ebd..3c53cac15de1 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,6 +1,6 @@ # Makefile for vm selftests -CFLAGS = -Wall +CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) BINARIES = compaction_test BINARIES += hugepage-mmap BINARIES += hugepage-shm @@ -12,8 +12,11 @@ BINARIES += userfaultfd all: $(BINARIES) %: %.c $(CC) $(CFLAGS) -o $@ $^ -lrt -userfaultfd: userfaultfd.c - $(CC) $(CFLAGS) -O2 -o $@ $^ -lpthread +userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h + $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread + +../../../../usr/include/linux/kernel.h: + make -C ../../../.. headers_install TEST_PROGS := run_vmtests TEST_FILES := $(BINARIES) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 2c7cca6f26a4..d77ed41b2094 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -64,17 +64,9 @@ #include <sys/syscall.h> #include <sys/ioctl.h> #include <pthread.h> -#include "../../../../include/uapi/linux/userfaultfd.h" - -#ifdef __x86_64__ -#define __NR_userfaultfd 323 -#elif defined(__i386__) -#define __NR_userfaultfd 374 -#elif defined(__powewrpc__) -#define __NR_userfaultfd 364 -#else -#error "missing __NR_userfaultfd definition" -#endif +#include <linux/userfaultfd.h> + +#ifdef __NR_userfaultfd static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; @@ -430,7 +422,7 @@ static int userfaultfd_stress(void) struct uffdio_register uffdio_register; struct uffdio_api uffdio_api; unsigned long cpu; - int uffd_flags; + int uffd_flags, err; unsigned long userfaults[nr_cpus]; if (posix_memalign(&area, page_size, nr_pages * page_size)) { @@ -473,6 +465,14 @@ static int userfaultfd_stress(void) *area_mutex(area_src, nr) = (pthread_mutex_t) PTHREAD_MUTEX_INITIALIZER; count_verify[nr] = *area_count(area_src, nr) = 1; + /* + * In the transition between 255 to 256, powerpc will + * read out of order in my_bcmp and see both bytes as + * zero, so leave a placeholder below always non-zero + * after the count, to avoid my_bcmp to trigger false + * positives. + */ + *(area_count(area_src, nr) + 1) = 1; } pipefd = malloc(sizeof(int) * nr_cpus * 2); @@ -499,6 +499,7 @@ static int userfaultfd_stress(void) pthread_attr_init(&attr); pthread_attr_setstacksize(&attr, 16*1024*1024); + err = 0; while (bounces--) { unsigned long expected_ioctls; @@ -579,20 +580,13 @@ static int userfaultfd_stress(void) /* verification */ if (bounces & BOUNCE_VERIFY) { for (nr = 0; nr < nr_pages; nr++) { - if (my_bcmp(area_dst, - area_dst + nr * page_size, - sizeof(pthread_mutex_t))) { - fprintf(stderr, - "error mutex 2 %lu\n", - nr); - bounces = 0; - } if (*area_count(area_dst, nr) != count_verify[nr]) { fprintf(stderr, "error area_count %Lu %Lu %lu\n", *area_count(area_src, nr), count_verify[nr], nr); + err = 1; bounces = 0; } } @@ -609,7 +603,7 @@ static int userfaultfd_stress(void) printf("\n"); } - return 0; + return err; } int main(int argc, char **argv) @@ -618,8 +612,8 @@ int main(int argc, char **argv) fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); page_size = sysconf(_SC_PAGE_SIZE); - if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) > - page_size) + if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 + > page_size) fprintf(stderr, "Impossible to run this test\n"), exit(2); nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size / nr_cpus; @@ -637,3 +631,15 @@ int main(int argc, char **argv) nr_pages, nr_pages_per_cpu); return userfaultfd_stress(); } + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n"); + return 0; +} + +#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c index 9a43a59a9bb4..421c607a8856 100644 --- a/tools/testing/selftests/x86/entry_from_vm86.c +++ b/tools/testing/selftests/x86/entry_from_vm86.c @@ -116,8 +116,9 @@ static bool do_test(struct vm86plus_struct *v86, unsigned long eip, v86->regs.eip = eip; ret = vm86(VM86_ENTER, v86); - if (ret == -1 && errno == ENOSYS) { - printf("[SKIP]\tvm86 not supported\n"); + if (ret == -1 && (errno == ENOSYS || errno == EPERM)) { + printf("[SKIP]\tvm86 %s\n", + errno == ENOSYS ? "not supported" : "not allowed"); return false; } diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 20de9a761269..683a292e3290 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -1,15 +1,7 @@ #!/bin/bash TCID="zram.sh" -check_prereqs() -{ - local msg="skip all tests:" - - if [ $UID != 0 ]; then - echo $msg must be run as root >&2 - exit 0 - fi -} +. ./zram_lib.sh run_zram () { echo "--------------------" diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index 424e68ed1487..f6a9c73e7a44 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -23,8 +23,9 @@ trap INT check_prereqs() { local msg="skip all tests:" + local uid=$(id -u) - if [ $UID != 0 ]; then + if [ $uid -ne 0 ]; then echo $msg must be run as root >&2 exit 0 fi diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 505ad51b3b51..39c89a5ea990 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -6,7 +6,7 @@ vringh_test: vringh_test.o vringh.o virtio_ring.o CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE vpath %.c ../../drivers/virtio ../../drivers/vhost mod: - ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test + ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V} .PHONY: all test mod clean clean: ${RM} *.o vringh_test virtio_test vhost_test/*.o vhost_test/.*.cmd \ diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index aff61e13306c..26b7926bda88 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -3,6 +3,8 @@ #define mb() __sync_synchronize() #define smp_mb() mb() +# define dma_rmb() barrier() +# define dma_wmb() barrier() # define smp_rmb() barrier() # define smp_wmb() barrier() /* Weak barriers should be used. If not - it's a bug */ diff --git a/tools/virtio/linux/export.h b/tools/virtio/linux/export.h new file mode 100644 index 000000000000..416875e29254 --- /dev/null +++ b/tools/virtio/linux/export.h @@ -0,0 +1,3 @@ +#define EXPORT_SYMBOL_GPL(sym) extern typeof(sym) sym +#define EXPORT_SYMBOL(sym) extern typeof(sym) sym + diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 1e8ce6979c1e..0a3da64638ce 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -22,6 +22,7 @@ typedef unsigned long long dma_addr_t; typedef size_t __kernel_size_t; +typedef unsigned int __wsum; struct page { unsigned long long dummy; @@ -47,6 +48,13 @@ static inline void *kmalloc(size_t s, gfp_t gfp) return __kmalloc_fake; return malloc(s); } +static inline void *kzalloc(size_t s, gfp_t gfp) +{ + void *p = kmalloc(s, gfp); + + memset(p, 0, s); + return p; +} static inline void kfree(void *p) { |