diff options
Diffstat (limited to 'tools/perf/tests')
60 files changed, 1444 insertions, 350 deletions
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 395f2866094a..58858f3d2bf9 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -23,6 +23,7 @@ perf-test-y += hists_output.o perf-test-y += hists_cumulate.o perf-test-y += bp_signal.o perf-test-y += bp_signal_overflow.o +perf-test-y += event_refresh.o perf-test-y += bp_account.o perf-test-y += wp.o perf-test-y += task-exit.o diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 2735cc26d7ee..9314696858ff 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -167,4 +167,4 @@ out_put_evlist: return ret; } -DEFINE_SUITE("Read backward ring buffer", backward_ring_buffer); +DEFINE_SUITE_NEEDS_MLOCK("Read backward ring buffer", backward_ring_buffer); diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 98134b1c74cf..0b8897fd42ca 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -11,6 +11,7 @@ #include <execinfo.h> #endif #include <setjmp.h> +#include <stdio.h> #include <stdlib.h> #include <string.h> @@ -32,6 +33,8 @@ #include <subcmd/parse-options.h> #include <subcmd/run-command.h> +#include <sys/mman.h> + #include "builtin.h" #include "color.h" #include "config.h" @@ -42,6 +45,9 @@ #include "symbol.h" #include "tests-scripts.h" #include "tests.h" +#include "util/cap.h" +#include "util/event.h" +#include "util/mutex.h" #include "util/rlimit.h" #include "util/strbuf.h" #include "util/term.h" @@ -56,10 +62,23 @@ static struct strbuf junit_xml_buf = STRBUF_INIT; static bool dont_fork; /* Fork the tests in parallel and wait for their completion. */ static bool sequential; +/* List what each test needs, set by the "requisites" subcommand. */ +static bool list_requisites; /* Number of times each test is run. */ static unsigned int runs_per_test = 1; /* Number of lines to include in failure snippet. */ static unsigned int failure_snippet_lines = 10; +/* + * The tests mapping ring buffers take turns using their share of + * kernel.perf_event_mlock_kb via this mutex, shared with the forked test + * processes and robust so that a test killed while holding it doesn't leave + * the budget locked, see mutex_init_pshared_robust(). + */ +struct mlock_budget { + struct mutex lock; +}; + +static struct mlock_budget *mlock_budget; const char *dso_to_test; const char *test_objdump_path = "objdump"; static const char *workload_control; @@ -101,6 +120,7 @@ static struct test_suite *generic_tests[] = { &suite__hists_link, &suite__bp_signal, &suite__bp_signal_overflow, + &suite__event_refresh, &suite__bp_accounting, &suite__wp, &suite__task_exit, @@ -283,6 +303,30 @@ static const char *test_description(const struct test_suite *t, int test_case) return t->desc; } +static void requisites__fprintf(FILE *fp, const struct test_suite *t, int test_case) +{ + bool needs_mlock = t->needs_mlock, exclusive; + + if (test_case < 0) + test_case = test_suite__num_test_cases(t) == 1 ? 0 : -1; + + if (test_case >= 0) { + exclusive = t->test_cases[test_case].exclusive; + /* The catch-all implies every other requisite. */ + needs_mlock = needs_mlock || exclusive; + } else { + exclusive = false; + } + + if (!exclusive && !needs_mlock) + return; + + fprintf(fp, " ("); + if (exclusive) + fprintf(fp, "exclusive, "); + fprintf(fp, "mlock)"); +} + static test_fnptr test_function(const struct test_suite *t, int test_case) { if (test_case <= 0) @@ -352,12 +396,30 @@ static void child_test_sig_handler(int sig) siglongjmp(run_test_jmp_buf, sig); } +static int run_test_case(struct child_test *child) +{ + return test_function(child->test, child->test_case_num)(child->test, child->test_case_num); +} + +/* The thread safety analysis can't express a lock held conditionally. */ +static int run_test_case_mlocked(struct child_test *child) +{ + int err; + + mutex_lock(&mlock_budget->lock); + err = run_test_case(child); + mutex_unlock(&mlock_budget->lock); + + return err; +} + static int run_test_child(struct child_process *process) { const int signals[] = { SIGABRT, SIGBUS, SIGFPE, SIGILL, SIGINT, SIGPIPE, SIGQUIT, SIGSEGV, SIGTERM, }; struct child_test *child = container_of(process, struct child_test, process); + bool needs_mlock = mlock_budget && child->test->needs_mlock; int err; close_parent_fds(); @@ -374,7 +436,12 @@ static int run_test_child(struct child_process *process) pr_debug("---- start ----\n"); pr_debug("test child forked, pid %d\n", getpid()); - err = test_function(child->test, child->test_case_num)(child->test, child->test_case_num); + + if (needs_mlock) + err = run_test_case_mlocked(child); + else + err = run_test_case(child); + pr_debug("---- end(%d) ----\n", err); check_leaks(); @@ -628,6 +695,47 @@ static void print_line_highlighted(FILE *fp, const char *line, size_t len) } +static bool is_blank_line(const char *line, size_t len) +{ + for (size_t i = 0; i < len; i++) { + if (!isspace((unsigned char)line[i])) + return false; + } + return true; +} + +static bool is_stack_line(const char *line, size_t len) +{ + size_t i = 0; + + while (i < len && isspace((unsigned char)line[i])) + i++; + return i + 1 < len && line[i] == '#' && isdigit((unsigned char)line[i + 1]); +} + +static bool is_ignorable_snippet_line(const char *line, size_t len) +{ + return is_blank_line(line, len) || is_stack_line(line, len); +} + +static bool has_non_blank_between(const char **lines, const size_t *line_lens, + size_t start, size_t end) +{ + for (size_t j = start + 1; j < end; j++) { + if (!is_blank_line(lines[j], line_lens[j])) + return true; + } + return false; +} + +static void pick_snippet_line(bool *pick, size_t idx, unsigned int *picked_count) +{ + if (!pick[idx] && *picked_count < failure_snippet_lines) { + pick[idx] = true; + (*picked_count)++; + } +} + static void print_test_failure_snippet(FILE *fp, const char *buf) { size_t num_lines = 0; @@ -698,43 +806,63 @@ static void print_test_failure_snippet(FILE *fp, const char *buf) } /* Pass 0: Always pick the very first line */ - if (num_lines > 0 && picked_count < failure_snippet_lines) { - pick[0] = true; - picked_count++; - } + if (num_lines > 0) + pick_snippet_line(pick, 0, &picked_count); /* Pass 1: Pick lines with failure keywords from start (Highest Priority) */ for (i = 0; i < num_lines && picked_count < failure_snippet_lines; i++) { size_t dummy; - if (find_next_keyword(lines[i], line_lens[i], &dummy)) { - if (!pick[i]) { - pick[i] = true; - picked_count++; - } - /* Prioritize getting the immediate next line for context */ - if (i + 1 < num_lines && !pick[i + 1] && - picked_count < failure_snippet_lines) { - pick[i + 1] = true; - picked_count++; + if (is_ignorable_snippet_line(lines[i], line_lens[i])) + continue; + if (!find_next_keyword(lines[i], line_lens[i], &dummy)) + continue; + + pick_snippet_line(pick, i, &picked_count); + /* + * For unexpected signals, prioritize the preceding non-blank + * line showing where the test had run to before the signal. + */ + if (!strncmp(lines[i], "---- unexpected signal", 22)) { + size_t j = i; + + while (j > 0) { + j--; + if (!is_ignorable_snippet_line(lines[j], line_lens[j])) { + pick_snippet_line(pick, j, &picked_count); + break; + } } } + /* Prioritize getting the immediate next line for context */ + if (i + 1 < num_lines && + !is_ignorable_snippet_line(lines[i + 1], line_lens[i + 1])) + pick_snippet_line(pick, i + 1, &picked_count); } - /* Pass 2: Fill remaining quota from the end backwards */ + /* + * Pass 2: Fill remaining quota from the end backwards, skipping blank + * and stack trace lines so trailing test progress is shown instead of + * outermost stack frames like main/_start. + */ i = num_lines; while (i > 0 && picked_count < failure_snippet_lines) { i--; - if (!pick[i]) { - pick[i] = true; - picked_count++; - } + if (!is_ignorable_snippet_line(lines[i], line_lens[i])) + pick_snippet_line(pick, i, &picked_count); + } + + /* Pass 3: Fallback to top stack frames if quota remains */ + for (i = 0; i < num_lines && picked_count < failure_snippet_lines; i++) { + if (!is_blank_line(lines[i], line_lens[i])) + pick_snippet_line(pick, i, &picked_count); } for (i = 0; i < num_lines; i++) { if (!pick[i]) continue; - if (last_printed != -1 && (int)i > last_printed + 1) { + if (last_printed != -1 && + has_non_blank_between(lines, line_lens, last_printed, i)) { if (perf_use_color_default) fprintf(fp, "%s...%s\n", PERF_COLOR_BLUE, PERF_COLOR_RESET); else @@ -1450,14 +1578,20 @@ static int perf_test__list(FILE *fp, struct test_suite **suites, int argc, const if (!perf_test__matches(test_description(*t, -1), curr_suite, argc, argv)) continue; - fprintf(fp, "%3d: %s\n", curr_suite + 1, test_description(*t, -1)); + fprintf(fp, "%3d: %s", curr_suite + 1, test_description(*t, -1)); + if (list_requisites) + requisites__fprintf(fp, *t, /*test_case=*/-1); + fprintf(fp, "\n"); if (test_suite__num_test_cases(*t) <= 1) continue; test_suite__for_each_test_case(*t, curr_test_case) { - fprintf(fp, "%3d.%1d: %s\n", curr_suite + 1, curr_test_case + 1, + fprintf(fp, "%3d.%1d: %s", curr_suite + 1, curr_test_case + 1, test_description(*t, curr_test_case)); + if (list_requisites) + requisites__fprintf(fp, *t, curr_test_case); + fprintf(fp, "\n"); } } return 0; @@ -1744,10 +1878,97 @@ static struct test_suite **build_suites(void) #undef for_each_suite } +static bool perf_test__shares_mlock_budget(struct test_suite **suites, int argc, + const char *argv[], struct intlist *skiplist) +{ + int sharing = 0; + + /* The selection rules mirrored here are __cmd_test()'s: when they change, change both. */ + for (int curr_suite = 0; suites[curr_suite]; curr_suite++) { + struct test_suite *t = suites[curr_suite]; + int curr_test_case; + bool suite_matched; + + if (!t->needs_mlock || intlist__find(skiplist, curr_suite + 1)) + continue; + + suite_matched = perf_test__matches(test_description(t, /*test_case=*/-1), + curr_suite, argc, argv); + test_suite__for_each_test_case(t, curr_test_case) { + if (test_exclusive(t, curr_test_case)) + continue; + + if (suite_matched || + perf_test__matches(test_description(t, curr_test_case), + curr_suite, argc, argv)) + sharing += runs_per_test; + } + if (sharing > 1) + return true; + } + return false; +} + +/* + * Once the per user budget set in kernel.perf_event_mlock_kb is spent, what + * maps on top of it is charged against RLIMIT_MEMLOCK and the mapping is + * refused with EPERM when that runs out too, but only for the processes the + * kernel is paranoid about and that have no CAP_IPC_LOCK to lift the check, + * see perf_mmap_calc_limits() in the kernel: used by + * perf_test__setup_mlock_budget() below, that has nothing to take turns on + * when neither applies. + */ +static bool perf_test__mlock_budget_exhaustible(void) +{ + if (perf_cap__capable(CAP_IPC_LOCK)) + return false; + + return perf_event_paranoid() > -1; +} + +static void perf_test__setup_mlock_budget(struct test_suite **suites, int argc, + const char *argv[], struct intlist *skiplist) +{ + /* Nothing can be denied the budget, nothing to take turns for. */ + if (!perf_test__mlock_budget_exhaustible()) { + pr_debug("Not taking turns using the perf mlock budget: nothing can exhaust it\n"); + return; + } + + /* Nothing runs at the same time, nothing to share the budget with. */ + if (sequential || !perf_test__shares_mlock_budget(suites, argc, argv, skiplist)) + return; + + mlock_budget = mmap(NULL, sizeof(*mlock_budget), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, /*fd=*/-1, /*offset=*/0); + if (mlock_budget == MAP_FAILED) { + mlock_budget = NULL; + pr_err("Failed to map the shared area used to take turns using the perf mlock budget\n"); + return; + } + + if (!mutex_init_pshared_robust(&mlock_budget->lock)) { + munmap(mlock_budget, sizeof(*mlock_budget)); + mlock_budget = NULL; + pr_debug("Not taking turns using the perf mlock budget\n"); + } +} + +static void perf_test__teardown_mlock_budget(void) +{ + if (!mlock_budget) + return; + + mutex_destroy(&mlock_budget->lock); + munmap(mlock_budget, sizeof(*mlock_budget)); + mlock_budget = NULL; +} + int cmd_test(int argc, const char **argv) { const char *test_usage[] = { - "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", + "perf test [<options>] [{list|requisites} [<test-name-fragment>]|" + "[<test-name-fragments>|<test-numbers>]]", NULL, }; const char *skip = NULL; @@ -1776,7 +1997,7 @@ int cmd_test(int argc, const char **argv) "Generate junit XML output, default test.xml", "test.xml"), OPT_END() }; - const char * const test_subcommands[] = { "list", NULL }; + const char * const test_subcommands[] = { "list", "requisites", NULL }; struct intlist *skiplist = NULL; struct test_suite **suites; int ret; @@ -1808,10 +2029,11 @@ int cmd_test(int argc, const char **argv) setvbuf(stdout, NULL, _IONBF, 0); argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); - if (argc >= 1 && !strcmp(argv[0], "list")) { + if (argc >= 1 && (!strcmp(argv[0], "list") || !strcmp(argv[0], "requisites"))) { suites = build_suites(); if (!suites) return errno ? -errno : -ENOMEM; + list_requisites = !strcmp(argv[0], "requisites"); ret = perf_test__list(stdout, suites, argc - 1, argv + 1); free(suites); return ret; @@ -1850,7 +2072,9 @@ int cmd_test(int argc, const char **argv) intlist__delete(skiplist); return err ? -err : -ENOMEM; } + perf_test__setup_mlock_budget(suites, argc, argv, skiplist); ret = __cmd_test(suites, argc, argv, skiplist); + perf_test__teardown_mlock_budget(); free(suites); intlist__delete(skiplist); return ret; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index c50b526f44fb..130cd6021f93 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -885,4 +885,4 @@ static int test__code_reading(struct test_suite *test __maybe_unused, int subtes }; } -DEFINE_SUITE("Object code reading", code_reading); +DEFINE_SUITE_NEEDS_MLOCK("Object code reading", code_reading); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 46bc3f597260..18b7052a2dc5 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -138,6 +138,10 @@ static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __ dsos__init(&machine.dsos); dso = dso__new(file); + TEST_ASSERT_VAL("Failed to get dso", dso); + /* override the binary type for dso data access */ + dso__set_binary_type(dso, DSO_BINARY_TYPE__SYSTEM_PATH_DSO); + dso__set_bintype_searched(dso); TEST_ASSERT_VAL("Failed to add dso", !dsos__add(&machine.dsos, dso)); TEST_ASSERT_VAL("Failed to access to dso", dso__data_fd(dso, &machine) >= 0); @@ -226,6 +230,9 @@ static int dsos__create(int cnt, int size, struct dsos *dsos) TEST_ASSERT_VAL("failed to get dso file", file); dso = dso__new(file); TEST_ASSERT_VAL("failed to get dso", dso); + /* override the binary type for dso data access */ + dso__set_binary_type(dso, DSO_BINARY_TYPE__SYSTEM_PATH_DSO); + dso__set_bintype_searched(dso); TEST_ASSERT_VAL("failed to add dso", !dsos__add(dsos, dso)); dso__put(dso); } diff --git a/tools/perf/tests/event_refresh.c b/tools/perf/tests/event_refresh.c new file mode 100644 index 000000000000..726e5de4c795 --- /dev/null +++ b/tools/perf/tests/event_refresh.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Re-arm a sampling event from its overflow signal handler with + * PERF_EVENT_IOC_REFRESH and check that every overflow is delivered. + */ +#include <errno.h> +#include <fcntl.h> +#include <inttypes.h> +#include <signal.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <linux/perf_event.h> + +#include "cloexec.h" +#include "debug.h" +#include "tests.h" +#include "tp_pmu.h" +#include <internal/lib.h> // page_size +#include "../perf-sys.h" + +#define NR_EVENTS 1000 +/* A real-time signal is queued, so no overflow can be coalesced away. */ +#define REFRESH_SIGNAL (SIGRTMIN + 1) + +static volatile sig_atomic_t overflows, hups, refresh_errno; + +static void sig_handler(int signum __maybe_unused, siginfo_t *info, + void *uc __maybe_unused) +{ + int saved_errno = errno; + + overflows++; + if (info->si_code == POLL_HUP) + hups++; + if (ioctl(info->si_fd, PERF_EVENT_IOC_REFRESH, 1) < 0) + refresh_errno = errno; + errno = saved_errno; +} + +/* Count overflow signals for NR_EVENTS calls of trigger(), period 1. */ +static int count_overflows(struct perf_event_attr *attr, void (*trigger)(int i)) +{ + struct sigaction sa, old_sa; + uint64_t count = 0; + int fd, i, err = TEST_FAIL; + + attr->size = sizeof(*attr); + attr->sample_period = 1; + attr->disabled = 1; + + fd = sys_perf_event_open(attr, 0, -1, -1, perf_event_open_cloexec_flag()); + if (fd < 0) { + int open_errno = errno; + + pr_debug("failed opening event: %s\n", strerror(open_errno)); + return open_errno == EACCES || open_errno == EPERM ? TEST_SKIP : TEST_FAIL; + } + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sig_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(REFRESH_SIGNAL, &sa, &old_sa) < 0) { + pr_debug("failed setting up signal handler\n"); + close(fd); + return TEST_FAIL; + } + + if (fcntl(fd, F_SETFL, O_RDWR | O_NONBLOCK | O_ASYNC) < 0 || + fcntl(fd, F_SETSIG, REFRESH_SIGNAL) < 0 || + fcntl(fd, F_SETOWN, getpid()) < 0) { + pr_debug("failed setting up signal delivery: %s\n", strerror(errno)); + goto out; + } + + overflows = 0; + hups = 0; + refresh_errno = 0; + if (ioctl(fd, PERF_EVENT_IOC_REFRESH, 1) < 0) { + pr_debug("PERF_EVENT_IOC_REFRESH failed: %s\n", strerror(errno)); + goto out; + } + for (i = 0; i < NR_EVENTS; i++) + trigger(i); + ioctl(fd, PERF_EVENT_IOC_DISABLE, 0); + + if (read(fd, &count, sizeof(count)) != sizeof(count)) + pr_debug("failed to read the event count\n"); + pr_debug("%d events, count %" PRIu64 ", %d overflows (%d POLL_HUP), re-arm errno %d\n", + NR_EVENTS, count, overflows, hups, refresh_errno); + /* Unrelated page faults can only add overflows, never hide one. */ + if (overflows >= NR_EVENTS) + err = TEST_OK; +out: + /* Close first: a late signal must still find our handler. */ + close(fd); + sigaction(REFRESH_SIGNAL, &old_sa, NULL); + return err; +} + +static char *pages; + +static void touch_page(int i) +{ + pages[(long)i * page_size] = 1; +} + +static int test__event_refresh_sw(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_PAGE_FAULTS, + }; + int err; + + pages = mmap(NULL, (long)NR_EVENTS * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (pages == MAP_FAILED) + return TEST_FAIL; + /* One fault per touched page: a huge page would cover many of them. */ + madvise(pages, (long)NR_EVENTS * page_size, MADV_NOHUGEPAGE); + + err = count_overflows(&attr, touch_page); + munmap(pages, (long)NR_EVENTS * page_size); + return err; +} + +static void call_getppid(int i __maybe_unused) +{ + syscall(SYS_getppid); +} + +static int test__event_refresh_tp(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + }; + int id = tp_pmu__id("syscalls", "sys_enter_getppid"); + + if (id < 0) { + pr_debug("no syscalls:sys_enter_getppid tracepoint\n"); + return TEST_SKIP; + } + attr.config = id; + + return count_overflows(&attr, call_getppid); +} + +static struct test_case tests__event_refresh[] = { + TEST_CASE_REASON("Software event", event_refresh_sw, "permissions"), + TEST_CASE_REASON("Tracepoint event", event_refresh_tp, "permissions"), + { .name = NULL, } +}; + +struct test_suite suite__event_refresh = { + .desc = "Event re-armed with PERF_EVENT_IOC_REFRESH", + .test_cases = tests__event_refresh, +}; diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index b760041bed30..6d8d8cd57200 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -161,4 +161,4 @@ out_err: return err; } -DEFINE_SUITE("Use a dummy software event to keep tracking", keep_tracking); +DEFINE_SUITE_NEEDS_MLOCK("Use a dummy software event to keep tracking", keep_tracking); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 5cec7644952c..602a78d48b10 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -2,6 +2,7 @@ #include <errno.h> #include <inttypes.h> #include <stdlib.h> +#include <unistd.h> #include <fcntl.h> #include <linux/err.h> @@ -12,6 +13,8 @@ #include <perf/evlist.h> #include <perf/mmap.h> +#include <tools/config.h> + #include "cpumap.h" #include "debug.h" #include "event.h" @@ -182,50 +185,83 @@ out_free_threads: } enum user_read_state { - USER_READ_ENABLED, - USER_READ_DISABLED, - USER_READ_UNKNOWN, + USER_READ_ERR_PERM = -2, + USER_READ_ERR_NO_FILE = -1, + + USER_READ_DISABLED = '0', + USER_READ_ENABLED = '1', +#if defined(__i386__) || defined(__x86_64__) || (defined(__riscv) && __riscv_xlen == 64) + /* Unrestricted access on x86, legacy access on RISC-V. */ + USER_READ_LEGACY = '2', +#endif + USER_READ_MAX }; -static enum user_read_state set_user_read(struct perf_pmu *pmu, enum user_read_state enabled) +static enum user_read_state user_read_file_op(int fd, enum user_read_state enabled) { char buf[2] = {0, '\n'}; - ssize_t len; - int events_fd, rdpmc_fd; - enum user_read_state old_user_read = USER_READ_UNKNOWN; - - if (enabled == USER_READ_UNKNOWN) - return USER_READ_UNKNOWN; - - events_fd = perf_pmu__event_source_devices_fd(); - if (events_fd < 0) - return USER_READ_UNKNOWN; - - rdpmc_fd = perf_pmu__pathname_fd(events_fd, pmu->name, "rdpmc", O_RDWR); - if (rdpmc_fd < 0) { - close(events_fd); - return USER_READ_UNKNOWN; - } + ssize_t len = read(fd, buf, 1); + enum user_read_state old_user_read = USER_READ_ERR_NO_FILE; - len = read(rdpmc_fd, buf, sizeof(buf)); - if (len != sizeof(buf)) + if (len <= 0) { pr_debug("%s read failed\n", __func__); + goto out; + } - // Note, on Intel hybrid disabling on 1 PMU will implicitly disable on - // all the core PMUs. - old_user_read = (buf[0] == '1') ? USER_READ_ENABLED : USER_READ_DISABLED; + old_user_read = buf[0]; if (enabled != old_user_read) { - buf[0] = (enabled == USER_READ_ENABLED) ? '1' : '0'; - len = write(rdpmc_fd, buf, sizeof(buf)); + buf[0] = enabled; + lseek(fd, 0, SEEK_SET); + len = write(fd, buf, sizeof(buf)); if (len != sizeof(buf)) pr_debug("%s write failed\n", __func__); } - close(rdpmc_fd); - close(events_fd); + +out: + close(fd); return old_user_read; } +static enum user_read_state set_user_read(struct perf_pmu *pmu, + enum user_read_state enabled) +{ + int events_fd, fd; + enum user_read_state ret = USER_READ_ERR_NO_FILE; + + if (enabled == USER_READ_ERR_NO_FILE || enabled == USER_READ_ERR_PERM) + return enabled; + + events_fd = perf_pmu__event_source_devices_fd(); + if (events_fd >= 0) { + fd = perf_pmu__pathname_fd(events_fd, pmu->name, "rdpmc", O_RDWR); + if (fd >= 0) { + /* + * Note, on Intel hybrid disabling on 1 PMU will implicitly + * disable on all the core PMUs. + */ + ret = user_read_file_op(fd, enabled); + close(events_fd); + return ret; + } else if (errno == EACCES || errno == EROFS) { + /* Permissions failure, flag the failure for a skip. */ + close(events_fd); + return USER_READ_ERR_PERM; + } + close(events_fd); + } + + /* Fallback: perf_user_access interface (arm64, riscv, or similar) */ + fd = open("/proc/sys/kernel/perf_user_access", O_RDWR); + if (fd >= 0) + ret = user_read_file_op(fd, enabled); + else if (errno == EACCES || errno == EROFS) + ret = USER_READ_ERR_PERM; + + return ret; +} + + static int test_stat_user_read(u64 event, enum user_read_state enabled) { struct perf_pmu *pmu = NULL; @@ -246,9 +282,6 @@ static int test_stat_user_read(u64 event, enum user_read_state enabled) .config = perf_pmus__supports_extended_type() ? event | ((u64)pmu->type << PERF_PMU_TYPE_SHIFT) : event, -#ifdef __aarch64__ - .config1 = 0x2, /* Request user access */ -#endif }; struct perf_evsel *evsel = NULL; int err; @@ -256,8 +289,28 @@ static int test_stat_user_read(u64 event, enum user_read_state enabled) bool mapped = false, opened = false, rdpmc_supported; struct perf_counts_values counts = { .val = 0 }; + if (__is_defined(__aarch64__) && enabled == USER_READ_ENABLED) + attr.config1 = 0x2; /* Request user access */ pr_debug("User space counter reading for PMU %s\n", pmu->name); + + if (saved_user_read_state == USER_READ_ERR_PERM) { + pr_debug("User space counter reading for PMU %s [Failed to get user read state]\n", + pmu->name); + ret = TEST_SKIP; + goto cleanup; + } + + /* Check value is in the expected range */ + if (saved_user_read_state != USER_READ_ERR_NO_FILE && + (saved_user_read_state < USER_READ_DISABLED || + saved_user_read_state >= USER_READ_MAX)) { + pr_err("User space counter reading for PMU %s [Unexpected current state %d]\n", + pmu->name, saved_user_read_state); + ret = TEST_FAIL; + goto cleanup; + } + /* * Restrict scheduling to only use the rdpmc on the CPUs the * event can be on. If the test doesn't run on the CPU of the @@ -301,21 +354,18 @@ static int test_stat_user_read(u64 event, enum user_read_state enabled) goto cleanup; } - if (saved_user_read_state == USER_READ_UNKNOWN) - rdpmc_supported = pc->cap_user_rdpmc && pc->index; - else - rdpmc_supported = (enabled == USER_READ_ENABLED); + rdpmc_supported = (enabled == USER_READ_ENABLED); - if (rdpmc_supported && (!pc->cap_user_rdpmc || !pc->index)) { - pr_err("User space counter reading for PMU %s [Failed unexpected supported counter access %d %d]\n", - pmu->name, pc->cap_user_rdpmc, pc->index); + if (rdpmc_supported && !pc->index) { + pr_err("User space counter reading for PMU %s [index must be set when enabled %d]\n", + pmu->name, pc->index); ret = TEST_FAIL; goto cleanup; } - if (!rdpmc_supported && pc->cap_user_rdpmc) { - pr_err("User space counter reading for PMU %s [Failed unexpected unsupported counter access %d]\n", - pmu->name, pc->cap_user_rdpmc); + if (rdpmc_supported != pc->cap_user_rdpmc) { + pr_err("User space counter reading for PMU %s [cap should match requested state %d %d]\n", + pmu->name, pc->cap_user_rdpmc, rdpmc_supported); ret = TEST_FAIL; goto cleanup; } @@ -363,7 +413,8 @@ cleanup: perf_evsel__munmap(evsel); if (opened) perf_evsel__close(evsel); - perf_evsel__delete(evsel); + if (evsel) + perf_evsel__delete(evsel); /* If the affinity was changed, then put it back to all CPUs. */ if (pmu->cpus != NULL) { @@ -378,13 +429,13 @@ cleanup: return ret; } -static int test__mmap_user_read_instr(struct test_suite *test __maybe_unused, +static int __maybe_unused test__mmap_user_read_instr(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS, USER_READ_ENABLED); } -static int test__mmap_user_read_cycles(struct test_suite *test __maybe_unused, +static int __maybe_unused test__mmap_user_read_cycles(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES, USER_READ_ENABLED); @@ -406,46 +457,34 @@ static struct test_case tests__basic_mmap[] = { TEST_CASE_REASON("Read samples using the mmap interface", basic_mmap, "permissions"), - TEST_CASE_REASON_EXCLUSIVE("User space counter reading of instructions", - mmap_user_read_instr, + #if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ (defined(__riscv) && __riscv_xlen == 64) - "permissions" -#else - "unsupported" -#endif - ), + /* + * libperf only supports userspace read for these platforms, see + * tools/lib/perf/mmap.c + */ + TEST_CASE_REASON_EXCLUSIVE("User space counter reading of instructions", + mmap_user_read_instr, + "permissions"), TEST_CASE_REASON_EXCLUSIVE("User space counter reading of cycles", - mmap_user_read_cycles, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ - (defined(__riscv) && __riscv_xlen == 64) - "permissions" -#else - "unsupported" + mmap_user_read_cycles, + "permissions"), #endif - ), + + /* Counter read via userpage fallback is supported on all platforms */ TEST_CASE_REASON_EXCLUSIVE("User space counter disabling instructions", - mmap_user_read_instr_disabled, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ - (defined(__riscv) && __riscv_xlen == 64) - "permissions" -#else - "unsupported" -#endif - ), + mmap_user_read_instr_disabled, + "permissions"), TEST_CASE_REASON_EXCLUSIVE("User space counter disabling cycles", - mmap_user_read_cycles_disabled, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ - (defined(__riscv) && __riscv_xlen == 64) - "permissions" -#else - "unsupported" -#endif - ), + mmap_user_read_cycles_disabled, + "permissions"), + { .name = NULL, } }; struct test_suite suite__basic_mmap = { .desc = "mmap interface tests", .test_cases = tests__basic_mmap, + .needs_mlock = true, }; diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 5365889d326f..1ea336fbc7e7 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -160,4 +160,5 @@ static struct test_case tests__syscall_openat_tp_fields[] = { struct test_suite suite__syscall_openat_tp_fields = { .desc = "syscalls:sys_enter_openat event fields", .test_cases = tests__syscall_openat_tp_fields, + .needs_mlock = true, }; diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c index 30c7da79e109..190520ffc3ad 100644 --- a/tools/perf/tests/pe-file-parsing.c +++ b/tools/perf/tests/pe-file-parsing.c @@ -59,7 +59,7 @@ static int run_dir(const char *d) TEST_ASSERT_VAL("Failed to get dso", dso); ret = dso__load_bfd_symbols(dso, debugfile); - TEST_ASSERT_VAL("Failed to load symbols", ret == 0); + TEST_ASSERT_VAL("Failed to load symbols", ret > 0); dso__sort_by_name(dso); sym = dso__find_symbol_by_name(dso, "main", &idx); @@ -74,17 +74,20 @@ static int test__pe_file_parsing(struct test_suite *test __maybe_unused, { struct stat st; char path_dir[PATH_MAX]; - - /* First try development tree tests. */ - if (!lstat("./tests", &st)) - return run_dir("./tests"); - - /* Then installed path. */ + const char * const tests_dirs[] = { + "./tools/perf/tests", + "./tests", + "./source/tests", + path_dir, + }; snprintf(path_dir, PATH_MAX, "%s/tests", get_argv_exec_path()); - if (!lstat(path_dir, &st)) - return run_dir(path_dir); + for (size_t i = 0; i < ARRAY_SIZE(tests_dirs); ++i) { + if (!lstat(tests_dirs[i], &st)) + return run_dir(tests_dirs[i]); + } + pr_debug("cannot find the tests directory\n"); return TEST_SKIP; } @@ -93,6 +96,7 @@ static int test__pe_file_parsing(struct test_suite *test __maybe_unused, static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { + pr_debug("libbfd is not available\n"); return TEST_SKIP; } diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 0cac6ae1a1fc..370dbde08eac 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -372,4 +372,5 @@ static struct test_case tests__PERF_RECORD[] = { struct test_suite suite__PERF_RECORD = { .desc = "PERF_RECORD_* events & perf_sample fields", .test_cases = tests__PERF_RECORD, + .needs_mlock = true, }; diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index f8f71fdd32b1..0cefa2df2db7 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -218,4 +218,5 @@ static struct test_case time_to_tsc_tests[] = { struct test_suite suite__perf_time_to_tsc = { .desc = "Convert perf time to TSC", .test_cases = time_to_tsc_tests, + .needs_mlock = true, }; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index f507ce39439a..e6e4f4cf1fa2 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -906,9 +906,12 @@ static int test__parsing_callback(const struct pmu_metric *pm, struct metric_expr *mexp; list_for_each_entry (mexp, &me->head, nd) { + double result; + if (strcmp(mexp->metric_name, pm->metric_name)) continue; - pr_debug("Result %f\n", test_generic_metric(mexp, 0)); + result = test_generic_metric(mexp, 0); + pr_debug("Result %f\n", result); err = 0; (*failures)--; goto out_err; diff --git a/tools/perf/tests/shell/attr/README b/tools/perf/tests/shell/attr/README index 67c4ca76b85d..c7b49cdf8729 100644 --- a/tools/perf/tests/shell/attr/README +++ b/tools/perf/tests/shell/attr/README @@ -49,10 +49,10 @@ Following tests are defined (with perf commands): perf record --call-graph dwarf kill (test-record-graph-dwarf) perf record --call-graph fp kill (test-record-graph-fp) perf record --call-graph fp kill (test-record-graph-fp-aarch64) - perf record -e '{cycles,instructions}' kill (test-record-group1) - perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2) - perf record -e '{cycles,cache-misses}:S' kill (test-record-group-sampling1) - perf record -c 10000 -e '{cycles,cache-misses}:S' kill (test-record-group-sampling2) + perf record -e '{cycles,default_core/legacy-hardware-config=1/}' kill (test-record-group1) + perf record -e '{cycles/period=1234000/,default_core/legacy-hardware-config=1,period=6789000/}:S' kill (test-record-group2) + perf record -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill (test-record-group-sampling1) + perf record -c 10000 -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill (test-record-group-sampling2) perf record -D kill (test-record-no-delay) perf record -i kill (test-record-no-inherit) perf record -n kill (test-record-no-samples) @@ -67,5 +67,5 @@ Following tests are defined (with perf commands): perf stat -d kill (test-stat-detailed-1) perf stat -dd kill (test-stat-detailed-2) perf stat -ddd kill (test-stat-detailed-3) - perf stat -e '{cycles,instructions}' kill (test-stat-group1) + perf stat -e '{cycles,default_core/legacy-hardware-config=1/}' kill (test-stat-group1) perf stat -i -e cycles kill (test-stat-no-inherit) diff --git a/tools/perf/tests/shell/attr/base-stat-group b/tools/perf/tests/shell/attr/base-stat-group new file mode 100644 index 000000000000..9bcb8ab3687f --- /dev/null +++ b/tools/perf/tests/shell/attr/base-stat-group @@ -0,0 +1,45 @@ +[event] +fd=1 +group_fd=-1 +# 0 or PERF_FLAG_FD_CLOEXEC flag +flags=0|8 +cpu=* +type=0 +size=176 +config=0 +sample_period=0 +sample_type=65536 +# The default and -d/-dd/-ddd metrics open part of their events in groups: +# the members get read_format=15 and are enabled right away, the standalone +# ones keep read_format=3 and wait for the exec, and the leaders get 15 when +# their group has members, 3 when alone, as create_perf_stat_counter() goes. +read_format=3|15 +disabled=0|1 +inherit=1 +pinned=0 +exclusive=0 +exclude_user=0 +exclude_kernel=0|1 +exclude_hv=0|1 +exclude_idle=0 +mmap=0 +comm=0 +freq=0 +inherit_stat=0 +enable_on_exec=0|1 +task=0 +watermark=0 +precise_ip=0 +mmap_data=0 +sample_id_all=0 +exclude_host=0|1 +exclude_guest=0|1 +exclude_callchain_kernel=0 +exclude_callchain_user=0 +wakeup_events=0 +bp_type=0 +config1=0 +config2=0 +branch_sample_type=0 +sample_regs_user=0 +sample_stack_user=0 diff --git a/tools/perf/tests/shell/attr/test-record-graph-dwarf b/tools/perf/tests/shell/attr/test-record-graph-dwarf index ae92061d611d..fbe0faa8cdb6 100644 --- a/tools/perf/tests/shell/attr/test-record-graph-dwarf +++ b/tools/perf/tests/shell/attr/test-record-graph-dwarf @@ -4,7 +4,7 @@ args = --no-bpf-event --call-graph dwarf -- kill >/dev/null 2>&1 ret = 1 [event:base-record] -sample_type=45359 +sample_type=12583 exclude_callchain_user=1 sample_stack_user=8192 # TODO different for each arch, no support for that now diff --git a/tools/perf/tests/shell/attr/test-record-group-sampling b/tools/perf/tests/shell/attr/test-record-group-sampling index 86a940d7895d..ed47dd1e5984 100644 --- a/tools/perf/tests/shell/attr/test-record-group-sampling +++ b/tools/perf/tests/shell/attr/test-record-group-sampling @@ -1,8 +1,9 @@ [config] command = record -args = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill >/dev/null 2>&1 ret = 1 kernel_until = 6.12 +requires = core-pmu [event-1:base-record] fd=1 @@ -15,7 +16,7 @@ inherit=0 fd=2 group_fd=1 -# cache-misses +# cache-misses, explicitly requested with the legacy hardware encoding type=0 config=3 diff --git a/tools/perf/tests/shell/attr/test-record-group-sampling1 b/tools/perf/tests/shell/attr/test-record-group-sampling1 index 4748ab7bf684..9cf013dc03dd 100644 --- a/tools/perf/tests/shell/attr/test-record-group-sampling1 +++ b/tools/perf/tests/shell/attr/test-record-group-sampling1 @@ -1,8 +1,9 @@ [config] command = record -args = --no-bpf-event -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill >/dev/null 2>&1 ret = 1 kernel_since = 6.12 +requires = core-pmu [event-1:base-record] fd=1 @@ -30,7 +31,7 @@ inherit=1 fd=2 group_fd=1 -# cache-misses +# cache-misses, explicitly requested with the legacy hardware encoding type=0 config=3 diff --git a/tools/perf/tests/shell/attr/test-record-group-sampling2 b/tools/perf/tests/shell/attr/test-record-group-sampling2 index e0432244a0eb..bd1eb4161e4a 100644 --- a/tools/perf/tests/shell/attr/test-record-group-sampling2 +++ b/tools/perf/tests/shell/attr/test-record-group-sampling2 @@ -1,8 +1,9 @@ [config] command = record -args = --no-bpf-event -c 10000 -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 +args = --no-bpf-event -c 10000 -e '{cycles,default_core/legacy-hardware-config=3/}:S' kill >/dev/null 2>&1 ret = 1 kernel_since = 6.12 +requires = core-pmu [event-1:base-record] fd=1 @@ -36,7 +37,7 @@ write_backward=0 fd=2 group_fd=1 -# cache-misses +# cache-misses, explicitly requested with the legacy hardware encoding type=0 config=3 diff --git a/tools/perf/tests/shell/attr/test-record-group1 b/tools/perf/tests/shell/attr/test-record-group1 index eeb1db392bc9..5fdd5288555f 100644 --- a/tools/perf/tests/shell/attr/test-record-group1 +++ b/tools/perf/tests/shell/attr/test-record-group1 @@ -1,7 +1,8 @@ [config] command = record -args = --no-bpf-event -e '{cycles,instructions}' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles,default_core/legacy-hardware-config=1/}' kill >/dev/null 2>&1 ret = 1 +requires = core-pmu [event-1:base-record] fd=1 diff --git a/tools/perf/tests/shell/attr/test-record-group2 b/tools/perf/tests/shell/attr/test-record-group2 index 891d41a7bddf..e7274108f5fd 100644 --- a/tools/perf/tests/shell/attr/test-record-group2 +++ b/tools/perf/tests/shell/attr/test-record-group2 @@ -1,8 +1,9 @@ [config] command = record -args = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles/period=1234000/,default_core/legacy-hardware-config=1,period=6789000/}:S' kill >/dev/null 2>&1 ret = 1 kernel_until = 6.12 +requires = core-pmu [event-1:base-record] fd=1 diff --git a/tools/perf/tests/shell/attr/test-record-group3 b/tools/perf/tests/shell/attr/test-record-group3 index 249be884959e..e74fd3a48ac9 100644 --- a/tools/perf/tests/shell/attr/test-record-group3 +++ b/tools/perf/tests/shell/attr/test-record-group3 @@ -1,8 +1,9 @@ [config] command = record -args = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1 +args = --no-bpf-event -e '{cycles/period=1234000/,default_core/legacy-hardware-config=1,period=6789000/}:S' kill >/dev/null 2>&1 ret = 1 kernel_since = 6.12 +requires = core-pmu [event-1:base-record] fd=1 diff --git a/tools/perf/tests/shell/attr/test-stat-C0 b/tools/perf/tests/shell/attr/test-stat-C0 index a2c76d10b2bb..9d242e93e3a9 100644 --- a/tools/perf/tests/shell/attr/test-stat-C0 +++ b/tools/perf/tests/shell/attr/test-stat-C0 @@ -2,6 +2,7 @@ command = stat args = -e cycles -C 0 kill >/dev/null 2>&1 ret = 1 +requires = core-pmu [event:base-stat] # events are disabled by default when attached to cpu diff --git a/tools/perf/tests/shell/attr/test-stat-basic b/tools/perf/tests/shell/attr/test-stat-basic index 69867d049fda..277897bd2626 100644 --- a/tools/perf/tests/shell/attr/test-stat-basic +++ b/tools/perf/tests/shell/attr/test-stat-basic @@ -2,6 +2,7 @@ command = stat args = -e cycles kill >/dev/null 2>&1 ret = 1 +requires = core-pmu [event:base-stat] optional=1 diff --git a/tools/perf/tests/shell/attr/test-stat-default b/tools/perf/tests/shell/attr/test-stat-default index 8dd27c1fb661..6a0c0c43f233 100644 --- a/tools/perf/tests/shell/attr/test-stat-default +++ b/tools/perf/tests/shell/attr/test-stat-default @@ -2,74 +2,75 @@ command = stat args = kill >/dev/null 2>&1 ret = 1 +requires = core-pmu # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK -[event1:base-stat] +[event1:base-stat-group] fd=1 type=1 config=1 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES -[event2:base-stat] +[event2:base-stat-group] fd=2 type=1 config=3 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS -[event3:base-stat] +[event3:base-stat-group] fd=3 type=1 config=4 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS -[event4:base-stat] +[event4:base-stat-group] fd=4 type=1 config=2 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES -[event5:base-stat] +[event5:base-stat-group] fd=5 type=0 config=0 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND -[event6:base-stat] +[event6:base-stat-group] fd=6 type=0 config=7 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND -[event7:base-stat] +[event7:base-stat-group] fd=7 type=0 config=8 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS -[event8:base-stat] +[event8:base-stat-group] fd=8 type=0 config=1 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS -[event9:base-stat] +[event9:base-stat-group] fd=9 type=0 config=4 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES -[event10:base-stat] +[event10:base-stat-group] fd=10 type=0 config=5 optional=1 # PERF_TYPE_RAW / slots (0x400) -[event11:base-stat] +[event11:base-stat-group] fd=11 group_fd=-1 type=4 @@ -78,7 +79,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-retiring (0x8000) -[event12:base-stat] +[event12:base-stat-group] fd=12 group_fd=11 type=4 @@ -89,7 +90,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-bad-spec (0x8100) -[event13:base-stat] +[event13:base-stat-group] fd=13 group_fd=11 type=4 @@ -100,7 +101,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] +[event14:base-stat-group] fd=14 group_fd=11 type=4 @@ -111,7 +112,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] +[event15:base-stat-group] fd=15 group_fd=11 type=4 @@ -122,7 +123,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-heavy-ops (0x8400) -[event16:base-stat] +[event16:base-stat-group] fd=16 group_fd=11 type=4 @@ -133,7 +134,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-br-mispredict (0x8500) -[event17:base-stat] +[event17:base-stat-group] fd=17 group_fd=11 type=4 @@ -144,7 +145,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fetch-lat (0x8600) -[event18:base-stat] +[event18:base-stat-group] fd=18 group_fd=11 type=4 @@ -155,7 +156,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-mem-bound (0x8700) -[event19:base-stat] +[event19:base-stat-group] fd=19 group_fd=11 type=4 @@ -166,71 +167,99 @@ read_format=15 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event20:base-stat] +[event20:base-stat-group] fd=20 type=4 config=4109 optional=1 # PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ -[event21:base-stat] +[event21:base-stat-group] fd=21 type=4 config=17039629 optional=1 -# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD -[event22:base-stat] +# PERF_TYPE_RAW / cpu-cycles (core PMU sysfs event; Intel 0x3c, AMD 0x76) +[event22:base-stat-group] fd=22 type=4 -config=60 +config=60|118 optional=1 # PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY -[event23:base-stat] +[event23:base-stat-group] fd=23 type=4 config=2097421 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK -[event24:base-stat] +[event24:base-stat-group] fd=24 type=4 config=316 optional=1 # PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE -[event25:base-stat] +[event25:base-stat-group] fd=25 type=4 config=412 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE -[event26:base-stat] +[event26:base-stat-group] fd=26 type=4 config=572 optional=1 # PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS -[event27:base-stat] +[event27:base-stat-group] fd=27 type=4 config=706 optional=1 # PERF_TYPE_RAW / UOPS_ISSUED.ANY -[event28:base-stat] +[event28:base-stat-group] fd=28 type=4 config=270 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event29:base-stat] +[event29:base-stat-group] fd=29 type=4 config=4269 +optional=1 + +# PERF_TYPE_RAW / instructions (core PMU sysfs event) +[event30:base-stat-group] +fd=30 +type=4 +config=192 +optional=1 + +# PERF_TYPE_RAW / branch-misses (core PMU sysfs event; Intel 0xc5, AMD 0xc3) +[event31:base-stat-group] +fd=31 +type=4 +config=197|195 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-frontend (core PMU sysfs event; Intel 0x180010e, AMD 0xd0/0x287/0xa9) +[event32:base-stat-group] +fd=32 +type=4 +config=25166094|208|647|169 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-backend (core PMU sysfs event; Intel 0x18001b1/0x1803fb1, AMD 0xd1/0x187) +[event33:base-stat-group] +fd=33 +type=4 +config=25166257|25182129|209|391 optional=1
\ No newline at end of file diff --git a/tools/perf/tests/shell/attr/test-stat-detailed-1 b/tools/perf/tests/shell/attr/test-stat-detailed-1 index 12a2ebf4e64a..3d47dc6f815f 100644 --- a/tools/perf/tests/shell/attr/test-stat-detailed-1 +++ b/tools/perf/tests/shell/attr/test-stat-detailed-1 @@ -2,76 +2,77 @@ command = stat args = -d kill >/dev/null 2>&1 ret = 1 +requires = core-pmu # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK -[event1:base-stat] +[event1:base-stat-group] fd=1 type=1 config=1 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES -[event2:base-stat] +[event2:base-stat-group] fd=2 type=1 config=3 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS -[event3:base-stat] +[event3:base-stat-group] fd=3 type=1 config=4 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS -[event4:base-stat] +[event4:base-stat-group] fd=4 type=1 config=2 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES -[event5:base-stat] +[event5:base-stat-group] fd=5 type=0 config=0 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND -[event6:base-stat] +[event6:base-stat-group] fd=6 type=0 config=7 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND -[event7:base-stat] +[event7:base-stat-group] fd=7 type=0 config=8 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS -[event8:base-stat] +[event8:base-stat-group] fd=8 type=0 config=1 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS -[event9:base-stat] +[event9:base-stat-group] fd=9 type=0 config=4 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES -[event10:base-stat] +[event10:base-stat-group] fd=10 type=0 config=5 optional=1 # PERF_TYPE_RAW / slots (0x400) -[event11:base-stat] +[event11:base-stat-group] fd=11 group_fd=-1 type=4 @@ -80,7 +81,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-retiring (0x8000) -[event12:base-stat] +[event12:base-stat-group] fd=12 group_fd=11 type=4 @@ -91,7 +92,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-bad-spec (0x8100) -[event13:base-stat] +[event13:base-stat-group] fd=13 group_fd=11 type=4 @@ -102,7 +103,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] +[event14:base-stat-group] fd=14 group_fd=11 type=4 @@ -113,7 +114,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] +[event15:base-stat-group] fd=15 group_fd=11 type=4 @@ -124,7 +125,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-heavy-ops (0x8400) -[event16:base-stat] +[event16:base-stat-group] fd=16 group_fd=11 type=4 @@ -135,7 +136,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-br-mispredict (0x8500) -[event17:base-stat] +[event17:base-stat-group] fd=17 group_fd=11 type=4 @@ -146,7 +147,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fetch-lat (0x8600) -[event18:base-stat] +[event18:base-stat-group] fd=18 group_fd=11 type=4 @@ -157,7 +158,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-mem-bound (0x8700) -[event19:base-stat] +[event19:base-stat-group] fd=19 group_fd=11 type=4 @@ -168,63 +169,63 @@ read_format=15 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event20:base-stat] +[event20:base-stat-group] fd=20 type=4 config=4109 optional=1 # PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ -[event21:base-stat] +[event21:base-stat-group] fd=21 type=4 config=17039629 optional=1 -# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD -[event22:base-stat] +# PERF_TYPE_RAW / cpu-cycles (core PMU sysfs event; Intel 0x3c, AMD 0x76) +[event22:base-stat-group] fd=22 type=4 -config=60 +config=60|118 optional=1 # PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY -[event23:base-stat] +[event23:base-stat-group] fd=23 type=4 config=2097421 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK -[event24:base-stat] +[event24:base-stat-group] fd=24 type=4 config=316 optional=1 # PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE -[event25:base-stat] +[event25:base-stat-group] fd=25 type=4 config=412 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE -[event26:base-stat] +[event26:base-stat-group] fd=26 type=4 config=572 optional=1 # PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS -[event27:base-stat] +[event27:base-stat-group] fd=27 type=4 config=706 optional=1 # PERF_TYPE_RAW / UOPS_ISSUED.ANY -[event28:base-stat] +[event28:base-stat-group] fd=28 type=4 config=270 @@ -234,7 +235,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event29:base-stat] +[event29:base-stat-group] fd=29 type=3 config=0 @@ -244,7 +245,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event30:base-stat] +[event30:base-stat-group] fd=30 type=3 config=65536 @@ -254,7 +255,7 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event31:base-stat] +[event31:base-stat-group] fd=31 type=3 config=2 @@ -264,15 +265,43 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event32:base-stat] +[event32:base-stat-group] fd=32 type=3 config=65538 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event33:base-stat] +[event33:base-stat-group] fd=33 type=4 config=4269 +optional=1 + +# PERF_TYPE_RAW / instructions (core PMU sysfs event) +[event34:base-stat-group] +fd=34 +type=4 +config=192 +optional=1 + +# PERF_TYPE_RAW / branch-misses (core PMU sysfs event; Intel 0xc5, AMD 0xc3) +[event35:base-stat-group] +fd=35 +type=4 +config=197|195 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-frontend (core PMU sysfs event; Intel 0x180010e, AMD 0xd0/0x287/0xa9) +[event36:base-stat-group] +fd=36 +type=4 +config=25166094|208|647|169 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-backend (core PMU sysfs event; Intel 0x18001b1/0x1803fb1, AMD 0xd1/0x187) +[event37:base-stat-group] +fd=37 +type=4 +config=25166257|25182129|209|391 optional=1
\ No newline at end of file diff --git a/tools/perf/tests/shell/attr/test-stat-detailed-2 b/tools/perf/tests/shell/attr/test-stat-detailed-2 index 66ea25b7d38f..ebe1f9e2736d 100644 --- a/tools/perf/tests/shell/attr/test-stat-detailed-2 +++ b/tools/perf/tests/shell/attr/test-stat-detailed-2 @@ -2,76 +2,77 @@ command = stat args = -dd kill >/dev/null 2>&1 ret = 1 +requires = core-pmu # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK -[event1:base-stat] +[event1:base-stat-group] fd=1 type=1 config=1 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES -[event2:base-stat] +[event2:base-stat-group] fd=2 type=1 config=3 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS -[event3:base-stat] +[event3:base-stat-group] fd=3 type=1 config=4 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS -[event4:base-stat] +[event4:base-stat-group] fd=4 type=1 config=2 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES -[event5:base-stat] +[event5:base-stat-group] fd=5 type=0 config=0 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND -[event6:base-stat] +[event6:base-stat-group] fd=6 type=0 config=7 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND -[event7:base-stat] +[event7:base-stat-group] fd=7 type=0 config=8 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS -[event8:base-stat] +[event8:base-stat-group] fd=8 type=0 config=1 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS -[event9:base-stat] +[event9:base-stat-group] fd=9 type=0 config=4 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES -[event10:base-stat] +[event10:base-stat-group] fd=10 type=0 config=5 optional=1 # PERF_TYPE_RAW / slots (0x400) -[event11:base-stat] +[event11:base-stat-group] fd=11 group_fd=-1 type=4 @@ -80,7 +81,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-retiring (0x8000) -[event12:base-stat] +[event12:base-stat-group] fd=12 group_fd=11 type=4 @@ -91,7 +92,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-bad-spec (0x8100) -[event13:base-stat] +[event13:base-stat-group] fd=13 group_fd=11 type=4 @@ -102,7 +103,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] +[event14:base-stat-group] fd=14 group_fd=11 type=4 @@ -113,7 +114,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] +[event15:base-stat-group] fd=15 group_fd=11 type=4 @@ -124,7 +125,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-heavy-ops (0x8400) -[event16:base-stat] +[event16:base-stat-group] fd=16 group_fd=11 type=4 @@ -135,7 +136,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-br-mispredict (0x8500) -[event17:base-stat] +[event17:base-stat-group] fd=17 group_fd=11 type=4 @@ -146,7 +147,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fetch-lat (0x8600) -[event18:base-stat] +[event18:base-stat-group] fd=18 group_fd=11 type=4 @@ -157,7 +158,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-mem-bound (0x8700) -[event19:base-stat] +[event19:base-stat-group] fd=19 group_fd=11 type=4 @@ -168,63 +169,63 @@ read_format=15 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event20:base-stat] +[event20:base-stat-group] fd=20 type=4 config=4109 optional=1 # PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ -[event21:base-stat] +[event21:base-stat-group] fd=21 type=4 config=17039629 optional=1 -# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD -[event22:base-stat] +# PERF_TYPE_RAW / cpu-cycles (core PMU sysfs event; Intel 0x3c, AMD 0x76) +[event22:base-stat-group] fd=22 type=4 -config=60 +config=60|118 optional=1 # PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY -[event23:base-stat] +[event23:base-stat-group] fd=23 type=4 config=2097421 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK -[event24:base-stat] +[event24:base-stat-group] fd=24 type=4 config=316 optional=1 # PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE -[event25:base-stat] +[event25:base-stat-group] fd=25 type=4 config=412 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE -[event26:base-stat] +[event26:base-stat-group] fd=26 type=4 config=572 optional=1 # PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS -[event27:base-stat] +[event27:base-stat-group] fd=27 type=4 config=706 optional=1 # PERF_TYPE_RAW / UOPS_ISSUED.ANY -[event28:base-stat] +[event28:base-stat-group] fd=28 type=4 config=270 @@ -234,7 +235,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event29:base-stat] +[event29:base-stat-group] fd=29 type=3 config=0 @@ -244,7 +245,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event30:base-stat] +[event30:base-stat-group] fd=30 type=3 config=65536 @@ -254,7 +255,7 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event31:base-stat] +[event31:base-stat-group] fd=31 type=3 config=2 @@ -264,7 +265,7 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event32:base-stat] +[event32:base-stat-group] fd=32 type=3 config=65538 @@ -274,7 +275,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event33:base-stat] +[event33:base-stat-group] fd=33 type=3 config=1 @@ -284,7 +285,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event34:base-stat] +[event34:base-stat-group] fd=34 type=3 config=65537 @@ -294,7 +295,7 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event35:base-stat] +[event35:base-stat-group] fd=35 type=3 config=3 @@ -304,7 +305,7 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event36:base-stat] +[event36:base-stat-group] fd=36 type=3 config=65539 @@ -314,7 +315,7 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event37:base-stat] +[event37:base-stat-group] fd=37 type=3 config=4 @@ -324,15 +325,43 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event38:base-stat] +[event38:base-stat-group] fd=38 type=3 config=65540 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event39:base-stat] +[event39:base-stat-group] fd=39 type=4 config=4269 +optional=1 + +# PERF_TYPE_RAW / instructions (core PMU sysfs event) +[event40:base-stat-group] +fd=40 +type=4 +config=192 +optional=1 + +# PERF_TYPE_RAW / branch-misses (core PMU sysfs event; Intel 0xc5, AMD 0xc3) +[event41:base-stat-group] +fd=41 +type=4 +config=197|195 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-frontend (core PMU sysfs event; Intel 0x180010e, AMD 0xd0/0x287/0xa9) +[event42:base-stat-group] +fd=42 +type=4 +config=25166094|208|647|169 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-backend (core PMU sysfs event; Intel 0x18001b1/0x1803fb1, AMD 0xd1/0x187) +[event43:base-stat-group] +fd=43 +type=4 +config=25166257|25182129|209|391 optional=1
\ No newline at end of file diff --git a/tools/perf/tests/shell/attr/test-stat-detailed-3 b/tools/perf/tests/shell/attr/test-stat-detailed-3 index 4a27bbfb9f87..e7eef828245c 100644 --- a/tools/perf/tests/shell/attr/test-stat-detailed-3 +++ b/tools/perf/tests/shell/attr/test-stat-detailed-3 @@ -2,76 +2,77 @@ command = stat args = -ddd kill >/dev/null 2>&1 ret = 1 +requires = core-pmu # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK -[event1:base-stat] +[event1:base-stat-group] fd=1 type=1 config=1 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES -[event2:base-stat] +[event2:base-stat-group] fd=2 type=1 config=3 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS -[event3:base-stat] +[event3:base-stat-group] fd=3 type=1 config=4 # PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS -[event4:base-stat] +[event4:base-stat-group] fd=4 type=1 config=2 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES -[event5:base-stat] +[event5:base-stat-group] fd=5 type=0 config=0 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND -[event6:base-stat] +[event6:base-stat-group] fd=6 type=0 config=7 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND -[event7:base-stat] +[event7:base-stat-group] fd=7 type=0 config=8 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS -[event8:base-stat] +[event8:base-stat-group] fd=8 type=0 config=1 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS -[event9:base-stat] +[event9:base-stat-group] fd=9 type=0 config=4 optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES -[event10:base-stat] +[event10:base-stat-group] fd=10 type=0 config=5 optional=1 # PERF_TYPE_RAW / slots (0x400) -[event11:base-stat] +[event11:base-stat-group] fd=11 group_fd=-1 type=4 @@ -80,7 +81,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-retiring (0x8000) -[event12:base-stat] +[event12:base-stat-group] fd=12 group_fd=11 type=4 @@ -91,7 +92,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-bad-spec (0x8100) -[event13:base-stat] +[event13:base-stat-group] fd=13 group_fd=11 type=4 @@ -102,7 +103,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fe-bound (0x8200) -[event14:base-stat] +[event14:base-stat-group] fd=14 group_fd=11 type=4 @@ -113,7 +114,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-be-bound (0x8300) -[event15:base-stat] +[event15:base-stat-group] fd=15 group_fd=11 type=4 @@ -124,7 +125,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-heavy-ops (0x8400) -[event16:base-stat] +[event16:base-stat-group] fd=16 group_fd=11 type=4 @@ -135,7 +136,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-br-mispredict (0x8500) -[event17:base-stat] +[event17:base-stat-group] fd=17 group_fd=11 type=4 @@ -146,7 +147,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-fetch-lat (0x8600) -[event18:base-stat] +[event18:base-stat-group] fd=18 group_fd=11 type=4 @@ -157,7 +158,7 @@ read_format=15 optional=1 # PERF_TYPE_RAW / topdown-mem-bound (0x8700) -[event19:base-stat] +[event19:base-stat-group] fd=19 group_fd=11 type=4 @@ -168,63 +169,63 @@ read_format=15 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event20:base-stat] +[event20:base-stat-group] fd=20 type=4 config=4109 optional=1 # PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ -[event21:base-stat] +[event21:base-stat-group] fd=21 type=4 config=17039629 optional=1 -# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD -[event22:base-stat] +# PERF_TYPE_RAW / cpu-cycles (core PMU sysfs event; Intel 0x3c, AMD 0x76) +[event22:base-stat-group] fd=22 type=4 -config=60 +config=60|118 optional=1 # PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY -[event23:base-stat] +[event23:base-stat-group] fd=23 type=4 config=2097421 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK -[event24:base-stat] +[event24:base-stat-group] fd=24 type=4 config=316 optional=1 # PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE -[event25:base-stat] +[event25:base-stat-group] fd=25 type=4 config=412 optional=1 # PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE -[event26:base-stat] +[event26:base-stat-group] fd=26 type=4 config=572 optional=1 # PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS -[event27:base-stat] +[event27:base-stat-group] fd=27 type=4 config=706 optional=1 # PERF_TYPE_RAW / UOPS_ISSUED.ANY -[event28:base-stat] +[event28:base-stat-group] fd=28 type=4 config=270 @@ -234,7 +235,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event29:base-stat] +[event29:base-stat-group] fd=29 type=3 config=0 @@ -244,7 +245,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event30:base-stat] +[event30:base-stat-group] fd=30 type=3 config=65536 @@ -254,7 +255,7 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event31:base-stat] +[event31:base-stat-group] fd=31 type=3 config=2 @@ -264,7 +265,7 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event32:base-stat] +[event32:base-stat-group] fd=32 type=3 config=65538 @@ -274,7 +275,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event33:base-stat] +[event33:base-stat-group] fd=33 type=3 config=1 @@ -284,7 +285,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event34:base-stat] +[event34:base-stat-group] fd=34 type=3 config=65537 @@ -294,7 +295,7 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event35:base-stat] +[event35:base-stat-group] fd=35 type=3 config=3 @@ -304,7 +305,7 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event36:base-stat] +[event36:base-stat-group] fd=36 type=3 config=65539 @@ -314,7 +315,7 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event37:base-stat] +[event37:base-stat-group] fd=37 type=3 config=4 @@ -324,7 +325,7 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event38:base-stat] +[event38:base-stat-group] fd=38 type=3 config=65540 @@ -334,7 +335,7 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event39:base-stat] +[event39:base-stat-group] fd=39 type=3 config=512 @@ -344,15 +345,43 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event40:base-stat] +[event40:base-stat-group] fd=40 type=3 config=66048 optional=1 # PERF_TYPE_RAW / INT_MISC.UOP_DROPPING -[event41:base-stat] +[event41:base-stat-group] fd=41 type=4 config=4269 +optional=1 + +# PERF_TYPE_RAW / instructions (core PMU sysfs event) +[event42:base-stat-group] +fd=42 +type=4 +config=192 +optional=1 + +# PERF_TYPE_RAW / branch-misses (core PMU sysfs event; Intel 0xc5, AMD 0xc3) +[event43:base-stat-group] +fd=43 +type=4 +config=197|195 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-frontend (core PMU sysfs event; Intel 0x180010e, AMD 0xd0/0x287/0xa9) +[event44:base-stat-group] +fd=44 +type=4 +config=25166094|208|647|169 +optional=1 + +# PERF_TYPE_RAW / stalled-cycles-backend (core PMU sysfs event; Intel 0x18001b1/0x1803fb1, AMD 0xd1/0x187) +[event45:base-stat-group] +fd=45 +type=4 +config=25166257|25182129|209|391 optional=1
\ No newline at end of file diff --git a/tools/perf/tests/shell/attr/test-stat-group1 b/tools/perf/tests/shell/attr/test-stat-group1 index 1746751123dc..7a31b27933f1 100644 --- a/tools/perf/tests/shell/attr/test-stat-group1 +++ b/tools/perf/tests/shell/attr/test-stat-group1 @@ -1,7 +1,8 @@ [config] command = stat -args = -e '{cycles,instructions}' kill >/dev/null 2>&1 +args = -e '{cycles,default_core/legacy-hardware-config=1/}' kill >/dev/null 2>&1 ret = 1 +requires = core-pmu [event-1:base-stat] fd=1 diff --git a/tools/perf/tests/shell/attr/test-stat-no-inherit b/tools/perf/tests/shell/attr/test-stat-no-inherit index 924fbb9300d1..38f746855b1b 100644 --- a/tools/perf/tests/shell/attr/test-stat-no-inherit +++ b/tools/perf/tests/shell/attr/test-stat-no-inherit @@ -2,6 +2,7 @@ command = stat args = -i -e cycles kill >/dev/null 2>&1 ret = 1 +requires = core-pmu [event:base-stat] inherit=0 diff --git a/tools/perf/tests/shell/drm_pmu.sh b/tools/perf/tests/shell/drm_pmu.sh index e629fe0e8463..c827e613fc66 100755 --- a/tools/perf/tests/shell/drm_pmu.sh +++ b/tools/perf/tests/shell/drm_pmu.sh @@ -1,5 +1,5 @@ #!/bin/bash -# DRM PMU +# DRM PMU (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/ftrace.sh b/tools/perf/tests/shell/ftrace.sh index 9f6e590f6437..84d6126bf94d 100755 --- a/tools/perf/tests/shell/ftrace.sh +++ b/tools/perf/tests/shell/ftrace.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf ftrace tests +# perf ftrace tests (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/kallsyms.sh b/tools/perf/tests/shell/kallsyms.sh index d0eb99753f47..e3674cc52b30 100755 --- a/tools/perf/tests/shell/kallsyms.sh +++ b/tools/perf/tests/shell/kallsyms.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf kallsyms tests +# perf kallsyms tests (no_mlock) # SPDX-License-Identifier: GPL-2.0 err=0 diff --git a/tools/perf/tests/shell/lib/attr.py b/tools/perf/tests/shell/lib/attr.py index 68f06df9565a..df1993883199 100644 --- a/tools/perf/tests/shell/lib/attr.py +++ b/tools/perf/tests/shell/lib/attr.py @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 import configparser +import errno import os import sys import glob @@ -28,6 +29,192 @@ def data_equal(a, b): return False +CORE_PMU_AVAILABLE = None +CORE_PMU_COUNT = None + +def core_pmu_available(): + """ + Is there a core PMU on this machine? Without one hardware events aren't + supported and get replaced by the software fallback, so there's no way to + check the expectations that pin their legacy encodings. The answer can't + change while the tests run, so probe the binding only once. + """ + core_pmu_probe() + return CORE_PMU_AVAILABLE + +def core_pmu_probe(): + """ + Ask perf itself, through its python binding, to parse and open 'cycles' + once: a parse failure or an ENOENT means no PMU can count it, any other + error means we can't tell whether there is one, and the number of events + it expanded to is the number of core PMUs, see + parse_events_multi_pmu_add(), which is what core_pmu_count() asks for. + """ + global CORE_PMU_AVAILABLE, CORE_PMU_COUNT + + if CORE_PMU_AVAILABLE is not None: + return + + try: + import perf + parse_events = perf.parse_events + except (ImportError, AttributeError): + # Nothing to ask about it, let the expectations speak. + CORE_PMU_AVAILABLE = True + return + + try: + evlist = parse_events('cycles') + except OSError: + # No PMU that can count it, the same as the ENOENT below. + CORE_PMU_AVAILABLE = False + return + + CORE_PMU_COUNT = len(evlist) + try: + evlist.open() + except OSError as err: + # Anything else is a permission problem or alike, not our business here. + CORE_PMU_AVAILABLE = err.errno != errno.ENOENT + return + evlist.close() + + CORE_PMU_AVAILABLE = True + +PERF_TYPE_HARDWARE = 0 +PERF_TYPE_HW_CACHE = 3 +PERF_SAMPLE_ID = 1 << 6 +PERF_SAMPLE_IDENTIFIER = 1 << 16 +PERF_TYPE_SOFTWARE = 1 +PERF_COUNT_SW_DUMMY = 9 + +def is_dummy_tracking_event(event): + """ + Is this the dummy event perf opens to carry the tracking events (mmap, + comm, task) when the requested ones can't, like when there is more than one + core PMU and each core PMU's events run on only part of the CPUs? + """ + return (event.get('type') == str(PERF_TYPE_SOFTWARE) and + event.get('config') == str(PERF_COUNT_SW_DUMMY)) + +# With more than one core PMU the tracking terms go to the dummy tracking event, +# leaving the requested events without them, so they can't be matched there. +TRACKING_TERMS = ['mmap', 'comm', 'task', 'mmap_data'] + +# The legacy event types, where perf may qualify 'config' with the core PMU +# type in its top 32 bits when there is more than one core PMU. +LEGACY_TYPES = (str(PERF_TYPE_HARDWARE), str(PERF_TYPE_HW_CACHE)) + +def mask_bits(value, bits): + """ + Take the bits in 'bits' out of each of the '|'-separated alternatives in + 'value', keeping the rest of the expression, wildcards included. + """ + masked = [] + + for alternative in value.split('|'): + try: + alternative = str(int(alternative, 0) & ~bits) + except ValueError: + pass + masked.append(alternative) + + return '|'.join(masked) + +def hide_core_pmu_type(value): + """ + The kernel can be told which core PMU a legacy type event is meant for by + putting its type in the top 32 bits of 'config', which perf only does when + there is more than one core PMU, so take those bits out to keep the + expectations written for the single core PMU case matching on + heterogeneous machines. + """ + return mask_bits(value, 0xffffffff00000000) + +# The two sample id bits mean the same thing here: how the samples of the +# events in the evlist get associated with the event that produced them. +SAMPLE_ID_BITS = PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER + +# No real sample_type bit is this high, so it can stand for "either of the +# sample id bits" when comparing the two sides. +SAMPLE_ID_EITHER = 1 << 40 + +PERF_FORMAT_GROUP = 1 << 3 + +def core_pmu_count(): + """ + How many core PMUs does perf see? An event with no PMU named in it + becomes one event per core PMU, see parse_events_multi_pmu_add(), and + that is the expansion that leaves the clones for the other core PMUs + without any group members and that makes perf qualify 'config' with the + type of the PMU it is for, so this is the number of events perf makes of + 'cycles', from the probe core_pmu_available() shares. + """ + core_pmu_probe() + return CORE_PMU_COUNT + +def single_core_pmu(): + """ + Does perf see only one core PMU? Asked for by the comparisons that need + it, not at import time, as a run may never get to one. + """ + return core_pmu_count() == 1 + +def hide_group_format(expected, recorded): + """ + read_format's PERF_FORMAT_GROUP bit asks for the group members to be read + along with the leader, which aside from this bit is verified with the + fd/group_fd based group checking, and with more than one core PMU a group + whose members are pinned to one of them, say 'default_core', leaves the + clones for the other core PMUs without any members, so that bit isn't + there: whether it is there is a consequence of how the evlist got + expanded to more than one core PMU, not of what the expectations are + about, so take it out on both sides. On a machine with a single core PMU + there is nothing to expand, so the expectations keep verifying it. + """ + if single_core_pmu(): + return expected, recorded + + return (mask_bits(expected, PERF_FORMAT_GROUP), + mask_bits(recorded, PERF_FORMAT_GROUP)) + +def hide_sample_id(expected, recorded): + """ + perf asks for a way to tell the samples apart, PERF_SAMPLE_IDENTIFIER where + available, PERF_SAMPLE_ID otherwise, see evlist__config(): whenever the + evlist has more than one event, and when asked to outright, with + --sample-identifier, by an auxtrace session, or by record__config() for a + pipe run, none of which depends on the sample types, as those only choose + between the two bits: + with more than one core PMU the dummy tracking events make the sample types + differ, so IDENTIFIER is asked for even for events whose expectations ask + for ID, written on a machine with a single core PMU. + + So treat the two as the same thing: when the expectation asks for either + of them, ask for "an id of some sort" on both sides, and when the + expectation doesn't ask for any, take the bits out of what got recorded. + """ + try: + asked = int(expected, 0) & SAMPLE_ID_BITS + except ValueError: + # The expectation is a wildcard or a set of alternatives. + return expected, recorded + + try: + recorded_id_bits = int(recorded, 0) & SAMPLE_ID_BITS + except ValueError: + # The recorded side is a wildcard or a set of alternatives. + return expected, mask_bits(recorded, SAMPLE_ID_BITS) + + if not asked: + if single_core_pmu(): + return expected, recorded + return expected, mask_bits(recorded, SAMPLE_ID_BITS) + + return (str(int(expected, 0) & ~SAMPLE_ID_BITS | SAMPLE_ID_EITHER), + str(int(recorded, 0) & ~SAMPLE_ID_BITS | + (SAMPLE_ID_EITHER if recorded_id_bits else 0))) + class Fail(Exception): def __init__(self, test, msg): self.msg = msg @@ -36,17 +223,20 @@ class Fail(Exception): return '\'%s\' - %s' % (self.test.path, self.msg) class Notest(Exception): - def __init__(self, test, arch): - self.arch = arch + def __init__(self, test, reason): + self.reason = reason self.test = test def getMsg(self): - return '[%s] \'%s\'' % (self.arch, self.test.path) + return '[%s] \'%s\'' % (self.reason, self.test.path) class Unsup(Exception): - def __init__(self, test): + def __init__(self, test, ret, expected): self.test = test + self.ret = ret + self.expected = expected def getMsg(self): - return '\'%s\'' % self.test.path + return '\'%s\' exit %d, expected %s, no attrs recorded to verify' % ( + self.test.path, self.ret, self.expected) class Event(dict): terms = [ @@ -101,12 +291,76 @@ class Event(dict): self.add(base) self.add(data) + def hide_core_pmu_type_terms(self, other): + """ + Is this a legacy type event? Then the core PMU type that perf may have + put in the top 32 bits of 'config' to tell the kernel which core PMU it + wants isn't part of what we asked for, see hide_core_pmu_type(). + """ + for event in (self, other): + for type in event.get('type', '').split('|'): + if type in LEGACY_TYPES: + return True + + return False + + def hide_core_pmu_type(self, term, value, other): + if term == 'config' and self.hide_core_pmu_type_terms(other): + return hide_core_pmu_type(value) + + return value + + def hide_event_count_dependent_terms(self, term, expected, recorded): + if term == 'sample_type': + return hide_sample_id(expected, recorded) + if term == 'read_format': + return hide_group_format(expected, recorded) + + return expected, recorded + + def recorded_side(self, other): + """ + Which one is what perf recorded? Both directions get compared, see + Test.compare(), so this can't be taken from the arguments' order. + """ + if getattr(other, 'recorded', False): + return other + + return self if getattr(self, 'recorded', False) else None + + def hide_tracking_via_dummy(self, term, other): + """ + The tracking terms are set on the tracking event, which is the dummy + event when there is more than one core PMU, leaving the requested + events without them, nothing to match on then. + """ + if term not in TRACKING_TERMS: + return False + + for event in (self, other): + if term in getattr(event, 'tracking_moved_to_dummy', ()): + return True + + return False + def equal(self, other): for t in Event.terms: log.debug(" [%s] %s %s", t, self[t], other[t]) if t not in self or t not in other: return False - if not data_equal(self[t], other[t]): + if self.hide_tracking_via_dummy(t, other): + continue + + recorded = self.recorded_side(other) + if recorded is self: + expected, got_event = other, self + else: + expected, got_event = self, other + exp = self.hide_core_pmu_type(t, expected[t], other) + got = self.hide_core_pmu_type(t, got_event[t], other) + if recorded is not None: + exp, got = self.hide_event_count_dependent_terms(t, exp, got) + if not data_equal(exp, got): return False return True @@ -119,14 +373,30 @@ class Event(dict): for t in Event.terms: if t not in self or t not in other: continue - if not data_equal(self[t], other[t]): - log.warning("expected %s=%s, got %s", t, self[t], other[t]) + if self.hide_tracking_via_dummy(t, other): + continue + + recorded = self.recorded_side(other) + if recorded is self: + expected, got_event = other, self + else: + expected, got_event = self, other + exp = self.hide_core_pmu_type(t, expected[t], other) + got = self.hide_core_pmu_type(t, got_event[t], other) + if recorded is not None: + exp, got = self.hide_event_count_dependent_terms(t, exp, got) + if not data_equal(exp, got): + log.warning("expected %s=%s, got %s", t, expected[t], + got_event[t]) def parse_version(version): if not version: return None return [int(v) for v in version.split(".")[0:2]] +def format_version(version): + return ".".join(str(v) for v in version) + # Test file description needs to have following sections: # [config] # - just single instance in file @@ -138,6 +408,9 @@ def parse_version(version): # 'arch' - architecture specific test (optional) # comma separated list, ! at the beginning # negates it. +# 'requires' - Comma separated list of things the test needs, it is +# skipped when any of them isn't there, currently: +# core-pmu - the machine can count hardware events. # 'auxv' - Truthy statement that is evaled in the scope of the auxv map. When false, # the test is skipped. For example 'auxv["AT_HWCAP"] == 10'. (optional) # 'kernel_since' - Inclusive kernel version from which the test will start running. Only the @@ -173,6 +446,7 @@ class Test(object): self.arch = '' self.auxv = parser.get('config', 'auxv', fallback=None) + self.requires = parser.get('config', 'requires', fallback='') self.kernel_since = parse_version(parser.get('config', 'kernel_since', fallback=None)) self.kernel_until = parse_version(parser.get('config', 'kernel_until', fallback=None)) self.expect = {} @@ -188,13 +462,17 @@ class Test(object): def skip_test_kernel_since(self): if not self.kernel_since: - return False - return not self.kernel_since <= parse_version(platform.release()) + return None + if self.kernel_since <= parse_version(platform.release()): + return None + return "kernel older than %s" % format_version(self.kernel_since) def skip_test_kernel_until(self): if not self.kernel_until: - return False - return not parse_version(platform.release()) < self.kernel_until + return None + if parse_version(platform.release()) < self.kernel_until: + return None + return "kernel newer than %s" % format_version(self.kernel_until) def skip_test_auxv(self): def new_auxv(a, pattern): @@ -210,18 +488,20 @@ class Test(object): return (items[0], value) if not self.auxv: - return False + return None auxv = subprocess.check_output("LD_SHOW_AUXV=1 sleep 0", shell=True) \ .decode(sys.stdout.encoding) pattern = re.compile(r"[: ]+") auxv = dict([new_auxv(a, pattern) for a in auxv.splitlines()]) - return not eval(self.auxv) + if eval(self.auxv): + return None + + return "the auxv condition doesn't hold here" def skip_test_arch(self, myarch): # If architecture not set always run test if self.arch == '': - # log.warning("test for arch %s is ok" % myarch) - return False + return None # Allow multiple values in assignment separated by ',' arch_list = self.arch.split(',') @@ -231,16 +511,26 @@ class Test(object): arch_list[0] = arch_list[0][1:] log.warning("excluded architecture list %s", arch_list) for arch_item in arch_list: - # log.warning("test for %s arch is %s" % (arch_item, myarch)) if arch_item == myarch: - return True - return False + return "arch = %s, machine = %s" % (self.arch, myarch) + return None for arch_item in arch_list: - # log.warning("test for architecture '%s' current '%s'" % (arch_item, myarch)) if arch_item == myarch: - return False - return True + return None + + return "arch = %s, machine = %s" % (self.arch, myarch) + + def skip_test_requires(self): + for requirement in filter(None, map(str.strip, self.requires.split(','))): + if requirement == 'core-pmu': + if not core_pmu_available(): + log.warning("test limitation 'requires %s'", requirement) + return "needs a core PMU, none here" + else: + log.warning("unknown requirement '%s', ignored", requirement) + + return None def restore_sample_rate(self, value=10000): try: @@ -284,17 +574,36 @@ class Test(object): def run_cmd(self, tempdir): _junk1, _junk2, _junk3, _junk4, myarch = (os.uname()) - if self.skip_test_arch(myarch): - raise Notest(self, myarch) - - if self.skip_test_auxv(): - raise Notest(self, "auxv skip") - - if self.skip_test_kernel_since(): - raise Notest(self, "old kernel skip") - - if self.skip_test_kernel_until(): - raise Notest(self, "new kernel skip") + arch = self.skip_test_arch(myarch) + if arch: + log.debug(" detail: the test file has arch = %s, the machine reports %s", + self.arch, myarch) + raise Notest(self, arch) + + auxv = self.skip_test_auxv() + if auxv: + log.debug(" detail: the auxv condition %s doesn't hold, the bits come " + "from the LD_SHOW_AUXV=1 output", self.auxv) + raise Notest(self, auxv) + + kernel = self.skip_test_kernel_since() + if kernel: + log.debug(" detail: the test file's kernel_since = %s, this kernel is %s", + format_version(self.kernel_since), platform.release()) + raise Notest(self, kernel) + + kernel = self.skip_test_kernel_until() + if kernel: + log.debug(" detail: the test file's kernel_until = %s, this kernel is %s", + format_version(self.kernel_until), platform.release()) + raise Notest(self, kernel) + + requirement = self.skip_test_requires() + if requirement: + log.debug(" detail: requires core-pmu, nothing countable here, check " + "kernel.perf_event_paranoid and the PMU nodes under " + "/sys/bus/event_source/") + raise Notest(self, requirement) self.restore_sample_rate() cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir, @@ -304,12 +613,80 @@ class Test(object): log.info(" '%s' ret '%s', expected '%s'", cmd, str(ret), str(self.ret)) if not data_equal(str(ret), str(self.ret)): + plain_cmd = "%s %s -o /dev/null %s" % ( + self.perf, self.command, + self.args.split('>/dev/null')[0].rstrip()) if self.test_ret: raise Fail(self, "Perf exit code failure") else: - raise Unsup(self) + log.debug(" detail: '%s' exited with %d, the expectations want the " + "workload's %s exit, so there are no attrs recorded to " + "verify; this is normally a capability problem, run '%s' " + "to see why", plain_cmd, ret, self.ret, plain_cmd) + raise Unsup(self, ret, str(self.ret)) + + def drop_dummy_tracking_events(self): + """ + Leave out the dummy event perf itself opened, see + is_dummy_tracking_event(), unless the expectations ask for one. + """ + if any(is_dummy_tracking_event(e) for e in self.expect.values()): + return + + if not any(is_dummy_tracking_event(e) for e in self.result.values()): + return + + moved = set() + for name, event in list(self.result.items()): + if is_dummy_tracking_event(event): + log.debug(" dropping dummy tracking event [%s]", name) + moved.update(t for t in TRACKING_TERMS if event.get(t) == '1') + del self.result[name] + + # The tracking terms the dropped dummies carried, flag the remaining + # events so that the match leaves only those out. + for event in self.result.values(): + event.tracking_moved_to_dummy = moved + + def drop_other_core_pmu_events(self, devices='/sys/bus/event_source/devices'): + """ + Leave out the events of the other core PMUs, which have their own + encodings, when the expectations name one of the core PMUs. + """ + asked = set() + for event in self.expect.values(): + types = event.get('type', '').split('|') + if '*' in types: + return + asked.update(types) - def compare(self, expect, result): + try: + names = os.listdir(devices) + except OSError: + return + + core = set() + for name in names: + path = os.path.join(devices, name) + has_cpus = os.path.exists(os.path.join(path, 'cpus')) + if name not in ('cpu', 'cpum_cf') and not has_cpus: + continue + try: + with open(os.path.join(path, 'type'), encoding='utf-8') as f: + core.add(f.read().strip()) + except OSError: + pass + + if not core & asked: + return + + others = core - asked + for name, event in list(self.result.items()): + if event.get('type') in others: + log.debug(" dropping other core PMU event [%s]", name) + del self.result[name] + + def compare(self, expect, result, strict_groups=True): match = {} log.debug(" compare") @@ -343,8 +720,9 @@ class Test(object): match[exp_name] = exp_list - # For each defined group in the expected events - # check we match the same group in the result. + # Check that each expected group is matched in the result; an event + # opened in a group may match an expectation that doesn't declare + # one, as those only verify the event attributes. for exp_name, exp_event in expect.items(): group = exp_event.group @@ -353,6 +731,8 @@ class Test(object): for res_name in match[exp_name]: res_group = result[res_name].group + if res_group == '' and not strict_groups: + continue if res_group not in match[group]: raise Fail(self, 'group failure') @@ -384,6 +764,11 @@ class Test(object): log.debug(" loading result events") for f in glob.glob(tempdir + '/event*'): self.load_events(f, self.result) + for event in self.result.values(): + event.recorded = True + + self.drop_dummy_tracking_events() + self.drop_other_core_pmu_events() # resolve group_fd to event names self.resolve_groups(self.expect) @@ -391,7 +776,7 @@ class Test(object): # do the expectation - results matching - both ways self.compare(self.expect, self.result) - self.compare(self.result, self.expect) + self.compare(self.result, self.expect, strict_groups=False) finally: # cleanup diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh index 14a03e0290ed..d4a0b04154d6 100755 --- a/tools/perf/tests/shell/list.sh +++ b/tools/perf/tests/shell/list.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf list tests +# perf list tests (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/perf_sched_stats.sh b/tools/perf/tests/shell/perf_sched_stats.sh index f13eb0a75b76..4ede9d701630 100755 --- a/tools/perf/tests/shell/perf_sched_stats.sh +++ b/tools/perf/tests/shell/perf_sched_stats.sh @@ -1,5 +1,5 @@ #!/bin/sh -# perf sched stats tests +# perf sched stats tests (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh index c40e5f3f0825..43bdd693076b 100755 --- a/tools/perf/tests/shell/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/probe_vfs_getname.sh @@ -1,5 +1,5 @@ #!/bin/bash -# Add vfs_getname probe to get syscall args filenames +# Add vfs_getname probe to get syscall args filenames (no_mlock) # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 diff --git a/tools/perf/tests/shell/python-use.sh b/tools/perf/tests/shell/python-use.sh index 2d6017d5dd9d..ece4d306869a 100755 --- a/tools/perf/tests/shell/python-use.sh +++ b/tools/perf/tests/shell/python-use.sh @@ -1,5 +1,5 @@ #!/bin/bash -# 'import perf' in python +# 'import perf' in python (no_mlock) # SPDX-License-Identifier: GPL-2.0 # Just test if we can load the python binding. set -e diff --git a/tools/perf/tests/shell/schedstat_snapshots.sh b/tools/perf/tests/shell/schedstat_snapshots.sh index a4bdf2673d43..2050478e3f1a 100755 --- a/tools/perf/tests/shell/schedstat_snapshots.sh +++ b/tools/perf/tests/shell/schedstat_snapshots.sh @@ -1,5 +1,5 @@ #!/bin/sh -# Validate CPU and domain pairing in perf sched stats snapshots +# Validate CPU and domain pairing in perf sched stats snapshots (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index a5b34c42e8d7..8beb6c674d05 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat CSV output linter +# perf stat CSV output linter (no_mlock) # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) # Tests various perf stat CSV output commands for the # correct number of fields and the CSV separator set to ','. diff --git a/tools/perf/tests/shell/stat+csv_summary.sh b/tools/perf/tests/shell/stat+csv_summary.sh index 9a4353db3825..6d8beb88fb6f 100755 --- a/tools/perf/tests/shell/stat+csv_summary.sh +++ b/tools/perf/tests/shell/stat+csv_summary.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat csv summary test +# perf stat csv summary test (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh index b5dec6b6da36..f5c6fa30d8db 100755 --- a/tools/perf/tests/shell/stat+event_uniquifying.sh +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat events uniquifying +# perf stat events uniquifying (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index 4969ad70b67b..cbf7a4ffd7e8 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat JSON output linter +# perf stat JSON output linter (no_mlock) # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) # Checks various perf stat JSON output commands for the # correct number of fields. diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh index cabbbf17c662..7a58e1507ce2 100755 --- a/tools/perf/tests/shell/stat+shadow_stat.sh +++ b/tools/perf/tests/shell/stat+shadow_stat.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat metrics (shadow stat) test +# perf stat metrics (shadow stat) test (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh index 64c2b81f02de..b915656a20f6 100755 --- a/tools/perf/tests/shell/stat+std_output.sh +++ b/tools/perf/tests/shell/stat+std_output.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat STD output linter +# perf stat STD output linter (no_mlock) # SPDX-License-Identifier: GPL-2.0 # Tests various perf stat STD output commands for # default event and metricgroup diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 1f5d4cc05807..ac9e031831da 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat tests +# perf stat tests (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh index 81bc7070b5ab..074a437da0ae 100755 --- a/tools/perf/tests/shell/stat_all_metricgroups.sh +++ b/tools/perf/tests/shell/stat_all_metricgroups.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf all metricgroups test +# perf all metricgroups test (no_mlock) # SPDX-License-Identifier: GPL-2.0 ParanoidAndNotRoot() diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh index df5fa27b21ae..9d0d4b8a217e 100755 --- a/tools/perf/tests/shell/stat_all_metrics.sh +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf all metrics test +# perf all metrics test (no_mlock) # SPDX-License-Identifier: GPL-2.0 ParanoidAndNotRoot() diff --git a/tools/perf/tests/shell/stat_all_pfm.sh b/tools/perf/tests/shell/stat_all_pfm.sh index c08c186af2c4..78d8006fb729 100755 --- a/tools/perf/tests/shell/stat_all_pfm.sh +++ b/tools/perf/tests/shell/stat_all_pfm.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf all libpfm4 events test +# perf all libpfm4 events test (no_mlock) # SPDX-License-Identifier: GPL-2.0 if perf version --build-options | grep HAVE_LIBPFM | grep -q OFF diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh index febe3af06441..d1b4632c17a3 100755 --- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh +++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat --bpf-counters --for-each-cgroup test +# perf stat --bpf-counters --for-each-cgroup test (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat_metrics_cgrp.sh b/tools/perf/tests/shell/stat_metrics_cgrp.sh index 0728f48f21fa..75b8e01d11cc 100755 --- a/tools/perf/tests/shell/stat_metrics_cgrp.sh +++ b/tools/perf/tests/shell/stat_metrics_cgrp.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf stat metrics --for-each-cgroup test +# perf stat metrics --for-each-cgroup test (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh index 0982f6b9737a..3e073a0e5b9f 100755 --- a/tools/perf/tests/shell/stat_metrics_values.sh +++ b/tools/perf/tests/shell/stat_metrics_values.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf metrics value validation +# perf metrics value validation (no_mlock) # SPDX-License-Identifier: GPL-2.0 shelldir=$(dirname "$0") diff --git a/tools/perf/tests/shell/test_ilist_python.sh b/tools/perf/tests/shell/test_ilist_python.sh index 83048474710d..a235539c0176 100755 --- a/tools/perf/tests/shell/test_ilist_python.sh +++ b/tools/perf/tests/shell/test_ilist_python.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf script ilist and perf list --tui test +# perf script ilist and perf list --tui test (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/shell/test_stat_cpi_python.sh b/tools/perf/tests/shell/test_stat_cpi_python.sh index 6cb376c92e2f..d1571a20f468 100755 --- a/tools/perf/tests/shell/test_stat_cpi_python.sh +++ b/tools/perf/tests/shell/test_stat_cpi_python.sh @@ -1,6 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# stat-cpi python test +# stat-cpi python test (no_mlock) set -e diff --git a/tools/perf/tests/shell/test_test_junit_output.sh b/tools/perf/tests/shell/test_test_junit_output.sh index 38a29e646906..8fc92e083c34 100755 --- a/tools/perf/tests/shell/test_test_junit_output.sh +++ b/tools/perf/tests/shell/test_test_junit_output.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# perf test junit XML output validation +# perf test junit XML output validation (no_mlock) +# +# Waiving the mlock requisite this way holds only while the 'perf test' +# runs below keep picking tests that don't map ring buffers. set -e diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh index 33bf36c4037e..0a02ff9b86d6 100755 --- a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -1,5 +1,5 @@ #!/bin/bash -# test perf probe of function from different CU +# test perf probe of function from different CU (no_mlock) # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index d18185881635..1b62dae55f07 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -149,4 +149,4 @@ static int test__sw_clock_freq(struct test_suite *test __maybe_unused, int subte return ret; } -DEFINE_SUITE("Software clock events period values", sw_clock_freq); +DEFINE_SUITE_NEEDS_MLOCK("Software clock events period values", sw_clock_freq); diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 95393edbfe36..9fac426ac2f9 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -158,4 +158,5 @@ struct test_case tests__task_exit[] = { struct test_suite suite__task_exit = { .desc = "Number of exit events of a simple workload", .test_cases = tests__task_exit, + .needs_mlock = true, }; diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c index 0370bc701373..a86b5289f09b 100644 --- a/tools/perf/tests/tests-scripts.c +++ b/tools/perf/tests/tests-scripts.c @@ -2,6 +2,7 @@ #include <dirent.h> #include <errno.h> #include <fcntl.h> +#include <stdio.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/string.h> @@ -179,6 +180,79 @@ static int shell_test__run(struct test_suite *test, int subtest __maybe_unused) return WEXITSTATUS(err) == 2 ? TEST_SKIP : TEST_FAIL; } +/* + * The requisites are a comma separated list in the parens ending the + * description line, e.g. "perf stat tests (no_mlock)": "exclusive" is the + * catch-all, implying every other requisite, "no_mlock" waives the default of + * needing room in the per user budget set in kernel.perf_event_mlock_kb. + */ +static void shell_test__requisites(char *desc, bool *exclusive, bool *needs_mlock) +{ + char *lparen, *rparen, *requisites, *token, *tokp; + bool known = false; + + /* Only a list closing the description line is taken for requisites. */ + rparen = strrchr(desc, ')'); + if (rparen == NULL || rparen[1] != '\0') + return; + + lparen = strrchr(desc, '('); + if (lparen == NULL || lparen > rparen) + return; + + /* Tokenize a copy: a list with nothing recognized leaves desc alone. */ + requisites = strndup(lparen + 1, rparen - lparen - 1); + if (requisites == NULL) { + pr_err("Failed to copy the requisites of '%s'\n", desc); + return; + } + + for (token = strtok_r(requisites, ",", &tokp); token; + token = strtok_r(NULL, ",", &tokp)) { + char *end = token + strlen(token); + const char *requisite = token; + bool waived; + + while (isspace(*token)) + token++; + while (end > token && isspace(end[-1])) + end--; + *end = '\0'; + + /* A "no_" prefix waives the requisite named after it. */ + waived = strncmp(token, "no_", sizeof("no_") - 1) == 0; + if (waived) + token += sizeof("no_") - 1; + + if (!strcmp(token, "mlock")) { + *needs_mlock = !waived; + } else if (!strcmp(token, "exclusive") && !waived) { + *exclusive = true; + } else { + pr_debug("Ignoring %s requisite '%s' in '%s'\n", + strcmp(token, "exclusive") == 0 ? "a waived" : "an unknown", + requisite, desc); + continue; + } + + known = true; + } + + zfree(&requisites); + + if (!known) + return; + + /* Drop the list and the space before it from the description. */ + *lparen = '\0'; + if (lparen > desc && isspace(lparen[-1])) + lparen[-1] = '\0'; + + /* The catch-all implies every other requisite, whatever the order. */ + if (*exclusive) + *needs_mlock = true; +} + static void append_script(int dir_fd, const char *name, char *desc, struct test_suite ***result, size_t *result_sz) @@ -187,7 +261,8 @@ static void append_script(int dir_fd, const char *name, char *desc, struct test_suite *test_suite, **result_tmp; struct test_case *tests; ssize_t len; - char *exclusive; + /* Shell tests run perf, that maps ring buffers, so they need the budget. */ + bool exclusive = false, needs_mlock = true; snprintf(link, sizeof(link), "/proc/%d/fd/%d", getpid(), dir_fd); len = readlink(link, filename, sizeof(filename) - 1); @@ -204,11 +279,8 @@ static void append_script(int dir_fd, const char *name, char *desc, return; } tests[0].name = strdup_check(name); - exclusive = strstr(desc, " (exclusive)"); - if (exclusive != NULL) { - tests[0].exclusive = true; - exclusive[0] = '\0'; - } + shell_test__requisites(desc, &exclusive, &needs_mlock); + tests[0].exclusive = exclusive; tests[0].desc = strdup_check(desc); tests[0].run_case = shell_test__run; test_suite = zalloc(sizeof(*test_suite)); @@ -220,6 +292,7 @@ static void append_script(int dir_fd, const char *name, char *desc, test_suite->desc = desc; test_suite->test_cases = tests; test_suite->priv = strdup_check(filename); + test_suite->needs_mlock = needs_mlock; /* Realloc is good enough, though we could realloc by chunks, not that * anyone will ever measure performance here */ result_tmp = realloc(*result, (*result_sz + 1) * sizeof(*result_tmp)); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index f379620069d3..20ae3609892b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -46,6 +46,12 @@ struct test_suite { struct test_case *test_cases; void *priv; int (*setup)(struct test_suite *suite); + /* + * Set for the suites mapping perf ring buffers, that need room in the + * per user budget set in kernel.perf_event_mlock_kb, see + * shell_test__requisites() for the shell suites. + */ + bool needs_mlock; }; #define DECLARE_SUITE(name) \ @@ -103,6 +109,17 @@ struct test_suite { .test_cases = tests__##_name, \ } +#define DEFINE_SUITE_NEEDS_MLOCK(description, _name) \ + struct test_case tests__##_name[] = { \ + TEST_CASE(description, _name), \ + { .name = NULL, } \ + }; \ + struct test_suite suite__##_name = { \ + .desc = description, \ + .test_cases = tests__##_name, \ + .needs_mlock = true, \ + } + /* Tests */ DECLARE_SUITE(vmlinux_matches_kallsyms); DECLARE_SUITE(openat_syscall_event); @@ -124,6 +141,7 @@ DECLARE_SUITE(parse_events); DECLARE_SUITE(hists_link); DECLARE_SUITE(bp_signal); DECLARE_SUITE(bp_signal_overflow); +DECLARE_SUITE(event_refresh); DECLARE_SUITE(bp_accounting); DECLARE_SUITE(wp); DECLARE_SUITE(task_exit); |