diff options
Diffstat (limited to 'tools/perf/builtin-sched.c')
| -rw-r--r-- | tools/perf/builtin-sched.c | 3031 |
1 files changed, 2643 insertions, 388 deletions
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index fed9ae432c16..eca3b1c58c4b 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1,33 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 #include "builtin.h" #include "perf.h" +#include "perf-sys.h" -#include "util/util.h" +#include "util/cpumap.h" #include "util/evlist.h" -#include "util/cache.h" #include "util/evsel.h" +#include "util/evsel_fprintf.h" +#include "util/mutex.h" #include "util/symbol.h" #include "util/thread.h" #include "util/header.h" #include "util/session.h" #include "util/tool.h" - -#include "util/parse-options.h" +#include "util/cloexec.h" +#include "util/thread_map.h" +#include "util/color.h" +#include "util/stat.h" +#include "util/string2.h" +#include "util/callchain.h" +#include "util/time-utils.h" + +#include <subcmd/pager.h> +#include <subcmd/parse-options.h> #include "util/trace-event.h" #include "util/debug.h" +#include "util/event.h" +#include "util/util.h" +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/zalloc.h> #include <sys/prctl.h> #include <sys/resource.h> +#include <inttypes.h> +#include <errno.h> #include <semaphore.h> #include <pthread.h> #include <math.h> +#include <api/fs/fs.h> +#include <perf/cpumap.h> +#include <linux/time64.h> +#include <linux/err.h> + +#include <linux/ctype.h> #define PR_SET_NAME 15 /* Set process name */ #define MAX_CPUS 4096 #define COMM_LEN 20 #define SYM_LEN 129 -#define MAX_PID 65536 +#define MAX_PID 1024000 +#define MAX_PRIO 140 + +static const char *cpu_list; +static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); struct sched_atom; @@ -41,7 +69,6 @@ struct task_desc { struct sched_atom **atoms; pthread_t thread; - sem_t sleep_sem; sem_t ready_for_work; sem_t work_done_sem; @@ -53,12 +80,10 @@ enum sched_event_type { SCHED_EVENT_RUN, SCHED_EVENT_SLEEP, SCHED_EVENT_WAKEUP, - SCHED_EVENT_MIGRATION, }; struct sched_atom { enum sched_event_type type; - int specific_wait; u64 timestamp; u64 duration; unsigned long nr; @@ -66,8 +91,6 @@ struct sched_atom { struct task_desc *wakee; }; -#define TASK_STATE_TO_CHAR_STR "RSDTtZX" - enum thread_state { THREAD_SLEEPING = 0, THREAD_WAIT_CPU, @@ -89,10 +112,12 @@ struct work_atoms { struct thread *thread; struct rb_node node; u64 max_lat; - u64 max_lat_at; + u64 max_lat_start; + u64 max_lat_end; u64 total_lat; u64 nb_atoms; u64 total_runtime; + int num_merged; }; typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *); @@ -100,41 +125,61 @@ typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *); struct perf_sched; struct trace_sched_handler { - int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel, + int (*switch_event)(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel, + int (*runtime_event)(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel, + int (*wakeup_event)(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample); + /* PERF_RECORD_FORK event, not sched_process_fork tracepoint */ + int (*fork_event)(struct perf_sched *sched, union perf_event *event, + struct machine *machine); int (*migrate_task_event)(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine); }; +#define COLOR_PIDS PERF_COLOR_BLUE +#define COLOR_CPUS PERF_COLOR_BG_RED + +struct perf_sched_map { + DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS); + struct perf_cpu *comp_cpus; + bool comp; + struct perf_thread_map *color_pids; + const char *color_pids_str; + struct perf_cpu_map *color_cpus; + const char *color_cpus_str; + const char *task_name; + struct strlist *task_names; + bool fuzzy; + struct perf_cpu_map *cpus; + const char *cpus_str; +}; + struct perf_sched { struct perf_tool tool; const char *sort_order; unsigned long nr_tasks; - struct task_desc *pid_to_task[MAX_PID]; + struct task_desc **pid_to_task; struct task_desc **tasks; const struct trace_sched_handler *tp_handler; - pthread_mutex_t start_work_mutex; - pthread_mutex_t work_done_wait_mutex; + struct mutex start_work_mutex; + struct mutex work_done_wait_mutex; int profile_cpu; /* * Track the current task - that way we can know whether there's any * weird events, such as a task being switched away that is not current. */ - int max_cpu; - u32 curr_pid[MAX_CPUS]; - struct thread *curr_thread[MAX_CPUS]; + struct perf_cpu max_cpu; + u32 *curr_pid; + struct thread **curr_thread; + struct thread **curr_out_thread; char next_shortname1; char next_shortname2; unsigned int replay_repeat; @@ -148,7 +193,6 @@ struct perf_sched { unsigned long nr_runs; unsigned long nr_timestamps; unsigned long nr_unordered_timestamps; - unsigned long nr_state_machine_bugs; unsigned long nr_context_switch_bugs; unsigned long nr_events; unsigned long nr_lost_chunks; @@ -165,18 +209,92 @@ struct perf_sched { u64 run_avg; u64 all_runtime; u64 all_count; - u64 cpu_last_switched[MAX_CPUS]; - struct rb_root atom_root, sorted_atom_root; + u64 *cpu_last_switched; + struct rb_root_cached atom_root, sorted_atom_root, merged_atom_root; struct list_head sort_list, cmp_pid; + bool force; + bool skip_merge; + struct perf_sched_map map; + + /* options for timehist command */ + bool summary; + bool summary_only; + bool idle_hist; + bool show_callchain; + unsigned int max_stack; + bool show_cpu_visual; + bool show_wakeups; + bool show_next; + bool show_migrations; + bool pre_migrations; + bool show_state; + bool show_prio; + u64 skipped_samples; + const char *time_str; + struct perf_time_interval ptime; + struct perf_time_interval hist_time; + volatile bool thread_funcs_exit; + const char *prio_str; + DECLARE_BITMAP(prio_bitmap, MAX_PRIO); }; +/* per thread run time data */ +struct thread_runtime { + u64 last_time; /* time of previous sched in/out event */ + u64 dt_run; /* run time */ + u64 dt_sleep; /* time between CPU access by sleep (off cpu) */ + u64 dt_iowait; /* time between CPU access by iowait (off cpu) */ + u64 dt_preempt; /* time between CPU access by preempt (off cpu) */ + u64 dt_delay; /* time between wakeup and sched-in */ + u64 dt_pre_mig; /* time between migration and wakeup */ + u64 ready_to_run; /* time of wakeup */ + u64 migrated; /* time when a thread is migrated */ + + struct stats run_stats; + u64 total_run_time; + u64 total_sleep_time; + u64 total_iowait_time; + u64 total_preempt_time; + u64 total_delay_time; + u64 total_pre_mig_time; + + char last_state; + + char shortname[3]; + bool comm_changed; + + u64 migrations; + + int prio; +}; + +/* per event run time data */ +struct evsel_runtime { + u64 *last_time; /* time this event was last seen per cpu */ + u32 ncpu; /* highest cpu slot allocated */ +}; + +/* per cpu idle time data */ +struct idle_thread_runtime { + struct thread_runtime tr; + struct thread *last_thread; + struct rb_root_cached sorted_root; + struct callchain_root callchain; + struct callchain_cursor cursor; +}; + +/* track idle times per cpu */ +static struct thread **idle_threads; +static int idle_max_cpu; +static char idle_comm[] = "<idle>"; + static u64 get_nsecs(void) { struct timespec ts; clock_gettime(CLOCK_MONOTONIC, &ts); - return ts.tv_sec * 1000000000ULL + ts.tv_nsec; + return ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec; } static void burn_nsecs(struct perf_sched *sched, u64 nsecs) @@ -200,7 +318,7 @@ static void sleep_nsecs(u64 nsecs) static void calibrate_run_measurement_overhead(struct perf_sched *sched) { - u64 T0, T1, delta, min_delta = 1000000000ULL; + u64 T0, T1, delta, min_delta = NSEC_PER_SEC; int i; for (i = 0; i < 10; i++) { @@ -217,7 +335,7 @@ static void calibrate_run_measurement_overhead(struct perf_sched *sched) static void calibrate_sleep_measurement_overhead(struct perf_sched *sched) { - u64 T0, T1, delta, min_delta = 1000000000ULL; + u64 T0, T1, delta, min_delta = NSEC_PER_SEC; int i; for (i = 0; i < 10; i++) { @@ -305,14 +423,13 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem)); sem_init(wakee_event->wait_sem, 0, 0); - wakee_event->specific_wait = 1; event->wait_sem = wakee_event->wait_sem; sched->nr_wakeup_events++; } static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task, - u64 timestamp, u64 task_state __maybe_unused) + u64 timestamp) { struct sched_atom *event = get_new_event(task, timestamp); @@ -325,8 +442,19 @@ static struct task_desc *register_pid(struct perf_sched *sched, unsigned long pid, const char *comm) { struct task_desc *task; + static int pid_max; - BUG_ON(pid >= MAX_PID); + if (sched->pid_to_task == NULL) { + if (sysctl__read_int("kernel/pid_max", &pid_max) < 0) + pid_max = MAX_PID; + BUG_ON((sched->pid_to_task = calloc(pid_max, sizeof(struct task_desc *))) == NULL); + } + if (pid >= (unsigned long)pid_max) { + BUG_ON((sched->pid_to_task = realloc(sched->pid_to_task, (pid + 1) * + sizeof(struct task_desc *))) == NULL); + while (pid >= (unsigned long)pid_max) + sched->pid_to_task[pid_max++] = NULL; + } task = sched->pid_to_task[pid]; @@ -341,15 +469,15 @@ static struct task_desc *register_pid(struct perf_sched *sched, * every task starts in sleeping state - this gets ignored * if there's no wakeup pointing to this sleep state: */ - add_sched_event_sleep(sched, task, 0, 0); + add_sched_event_sleep(sched, task, 0); sched->pid_to_task[pid] = task; sched->nr_tasks++; - sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_task *)); + sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_desc *)); BUG_ON(!sched->tasks); sched->tasks[task->nr] = task; - if (verbose) + if (verbose > 0) printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm); return task; @@ -402,8 +530,6 @@ static void perf_sched__process_event(struct perf_sched *sched, ret = sem_post(atom->wait_sem); BUG_ON(ret); break; - case SCHED_EVENT_MIGRATION: - break; default: BUG_ON(1); } @@ -418,27 +544,51 @@ static u64 get_cpu_usage_nsec_parent(void) err = getrusage(RUSAGE_SELF, &ru); BUG_ON(err); - sum = ru.ru_utime.tv_sec*1e9 + ru.ru_utime.tv_usec*1e3; - sum += ru.ru_stime.tv_sec*1e9 + ru.ru_stime.tv_usec*1e3; + sum = ru.ru_utime.tv_sec * NSEC_PER_SEC + ru.ru_utime.tv_usec * NSEC_PER_USEC; + sum += ru.ru_stime.tv_sec * NSEC_PER_SEC + ru.ru_stime.tv_usec * NSEC_PER_USEC; return sum; } -static int self_open_counters(void) +static int self_open_counters(struct perf_sched *sched, unsigned long cur_task) { struct perf_event_attr attr; + char sbuf[STRERR_BUFSIZE], info[STRERR_BUFSIZE]; int fd; + struct rlimit limit; + bool need_privilege = false; memset(&attr, 0, sizeof(attr)); attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_TASK_CLOCK; - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - - if (fd < 0) +force_again: + fd = sys_perf_event_open(&attr, 0, -1, -1, + perf_event_open_cloexec_flag()); + + if (fd < 0) { + if (errno == EMFILE) { + if (sched->force) { + BUG_ON(getrlimit(RLIMIT_NOFILE, &limit) == -1); + limit.rlim_cur += sched->nr_tasks - cur_task; + if (limit.rlim_cur > limit.rlim_max) { + limit.rlim_max = limit.rlim_cur; + need_privilege = true; + } + if (setrlimit(RLIMIT_NOFILE, &limit) == -1) { + if (need_privilege && errno == EPERM) + strcpy(info, "Need privilege\n"); + } else + goto force_again; + } else + strcpy(info, "Have a try with -f option\n"); + } pr_err("Error: sys_perf_event_open() syscall returned " - "with %d (%s)\n", fd, strerror(errno)); + "with %d (%s)\n%s", fd, + str_error_r(errno, sbuf, sizeof(sbuf)), info); + exit(EXIT_FAILURE); + } return fd; } @@ -456,6 +606,7 @@ static u64 get_cpu_usage_nsec_self(int fd) struct sched_thread_parms { struct task_desc *task; struct perf_sched *sched; + int fd; }; static void *thread_func(void *ctx) @@ -466,44 +617,42 @@ static void *thread_func(void *ctx) u64 cpu_usage_0, cpu_usage_1; unsigned long i, ret; char comm2[22]; - int fd; + int fd = parms->fd; - free(parms); + zfree(&parms); sprintf(comm2, ":%s", this_task->comm); prctl(PR_SET_NAME, comm2); - fd = self_open_counters(); if (fd < 0) return NULL; -again: - ret = sem_post(&this_task->ready_for_work); - BUG_ON(ret); - ret = pthread_mutex_lock(&sched->start_work_mutex); - BUG_ON(ret); - ret = pthread_mutex_unlock(&sched->start_work_mutex); - BUG_ON(ret); - cpu_usage_0 = get_cpu_usage_nsec_self(fd); + while (!sched->thread_funcs_exit) { + ret = sem_post(&this_task->ready_for_work); + BUG_ON(ret); + mutex_lock(&sched->start_work_mutex); + mutex_unlock(&sched->start_work_mutex); - for (i = 0; i < this_task->nr_events; i++) { - this_task->curr_event = i; - perf_sched__process_event(sched, this_task->atoms[i]); - } + cpu_usage_0 = get_cpu_usage_nsec_self(fd); - cpu_usage_1 = get_cpu_usage_nsec_self(fd); - this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; - ret = sem_post(&this_task->work_done_sem); - BUG_ON(ret); + for (i = 0; i < this_task->nr_events; i++) { + this_task->curr_event = i; + perf_sched__process_event(sched, this_task->atoms[i]); + } - ret = pthread_mutex_lock(&sched->work_done_wait_mutex); - BUG_ON(ret); - ret = pthread_mutex_unlock(&sched->work_done_wait_mutex); - BUG_ON(ret); + cpu_usage_1 = get_cpu_usage_nsec_self(fd); + this_task->cpu_usage = cpu_usage_1 - cpu_usage_0; + ret = sem_post(&this_task->work_done_sem); + BUG_ON(ret); - goto again; + mutex_lock(&sched->work_done_wait_mutex); + mutex_unlock(&sched->work_done_wait_mutex); + } + return NULL; } static void create_tasks(struct perf_sched *sched) + EXCLUSIVE_LOCK_FUNCTION(sched->start_work_mutex) + EXCLUSIVE_LOCK_FUNCTION(sched->work_done_wait_mutex) { struct task_desc *task; pthread_attr_t attr; @@ -513,18 +662,16 @@ static void create_tasks(struct perf_sched *sched) err = pthread_attr_init(&attr); BUG_ON(err); err = pthread_attr_setstacksize(&attr, - (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); - BUG_ON(err); - err = pthread_mutex_lock(&sched->start_work_mutex); - BUG_ON(err); - err = pthread_mutex_lock(&sched->work_done_wait_mutex); + (size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN)); BUG_ON(err); + mutex_lock(&sched->start_work_mutex); + mutex_lock(&sched->work_done_wait_mutex); for (i = 0; i < sched->nr_tasks; i++) { struct sched_thread_parms *parms = malloc(sizeof(*parms)); BUG_ON(parms == NULL); parms->task = task = sched->tasks[i]; parms->sched = sched; - sem_init(&task->sleep_sem, 0, 0); + parms->fd = self_open_counters(sched, i); sem_init(&task->ready_for_work, 0, 0); sem_init(&task->work_done_sem, 0, 0); task->curr_event = 0; @@ -533,7 +680,29 @@ static void create_tasks(struct perf_sched *sched) } } +static void destroy_tasks(struct perf_sched *sched) + UNLOCK_FUNCTION(sched->start_work_mutex) + UNLOCK_FUNCTION(sched->work_done_wait_mutex) +{ + struct task_desc *task; + unsigned long i; + int err; + + mutex_unlock(&sched->start_work_mutex); + mutex_unlock(&sched->work_done_wait_mutex); + /* Get rid of threads so they won't be upset by mutex destrunction */ + for (i = 0; i < sched->nr_tasks; i++) { + task = sched->tasks[i]; + err = pthread_join(task->thread, NULL); + BUG_ON(err); + sem_destroy(&task->ready_for_work); + sem_destroy(&task->work_done_sem); + } +} + static void wait_for_tasks(struct perf_sched *sched) + EXCLUSIVE_LOCKS_REQUIRED(sched->work_done_wait_mutex) + EXCLUSIVE_LOCKS_REQUIRED(sched->start_work_mutex) { u64 cpu_usage_0, cpu_usage_1; struct task_desc *task; @@ -541,7 +710,7 @@ static void wait_for_tasks(struct perf_sched *sched) sched->start_time = get_nsecs(); sched->cpu_usage = 0; - pthread_mutex_unlock(&sched->work_done_wait_mutex); + mutex_unlock(&sched->work_done_wait_mutex); for (i = 0; i < sched->nr_tasks; i++) { task = sched->tasks[i]; @@ -549,12 +718,11 @@ static void wait_for_tasks(struct perf_sched *sched) BUG_ON(ret); sem_init(&task->ready_for_work, 0, 0); } - ret = pthread_mutex_lock(&sched->work_done_wait_mutex); - BUG_ON(ret); + mutex_lock(&sched->work_done_wait_mutex); cpu_usage_0 = get_cpu_usage_nsec_parent(); - pthread_mutex_unlock(&sched->start_work_mutex); + mutex_unlock(&sched->start_work_mutex); for (i = 0; i < sched->nr_tasks; i++) { task = sched->tasks[i]; @@ -568,25 +736,25 @@ static void wait_for_tasks(struct perf_sched *sched) cpu_usage_1 = get_cpu_usage_nsec_parent(); if (!sched->runavg_cpu_usage) sched->runavg_cpu_usage = sched->cpu_usage; - sched->runavg_cpu_usage = (sched->runavg_cpu_usage * 9 + sched->cpu_usage) / 10; + sched->runavg_cpu_usage = (sched->runavg_cpu_usage * (sched->replay_repeat - 1) + sched->cpu_usage) / sched->replay_repeat; sched->parent_cpu_usage = cpu_usage_1 - cpu_usage_0; if (!sched->runavg_parent_cpu_usage) sched->runavg_parent_cpu_usage = sched->parent_cpu_usage; - sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * 9 + - sched->parent_cpu_usage)/10; + sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * (sched->replay_repeat - 1) + + sched->parent_cpu_usage)/sched->replay_repeat; - ret = pthread_mutex_lock(&sched->start_work_mutex); - BUG_ON(ret); + mutex_lock(&sched->start_work_mutex); for (i = 0; i < sched->nr_tasks; i++) { task = sched->tasks[i]; - sem_init(&task->sleep_sem, 0, 0); task->curr_event = 0; } } static void run_one_test(struct perf_sched *sched) + EXCLUSIVE_LOCKS_REQUIRED(sched->work_done_wait_mutex) + EXCLUSIVE_LOCKS_REQUIRED(sched->start_work_mutex) { u64 T0, T1, delta, avg_delta, fluct; @@ -606,14 +774,14 @@ static void run_one_test(struct perf_sched *sched) sched->sum_fluct += fluct; if (!sched->run_avg) sched->run_avg = delta; - sched->run_avg = (sched->run_avg * 9 + delta) / 10; + sched->run_avg = (sched->run_avg * (sched->replay_repeat - 1) + delta) / sched->replay_repeat; - printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0); + printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / NSEC_PER_MSEC); - printf("ravg: %0.2f, ", (double)sched->run_avg / 1e6); + printf("ravg: %0.2f, ", (double)sched->run_avg / NSEC_PER_MSEC); printf("cpu: %0.2f / %0.2f", - (double)sched->cpu_usage / 1e6, (double)sched->runavg_cpu_usage / 1e6); + (double)sched->cpu_usage / NSEC_PER_MSEC, (double)sched->runavg_cpu_usage / NSEC_PER_MSEC); #if 0 /* @@ -621,8 +789,8 @@ static void run_one_test(struct perf_sched *sched) * accurate than the sched->sum_exec_runtime based statistics: */ printf(" [%0.2f / %0.2f]", - (double)sched->parent_cpu_usage/1e6, - (double)sched->runavg_parent_cpu_usage/1e6); + (double)sched->parent_cpu_usage / NSEC_PER_MSEC, + (double)sched->runavg_parent_cpu_usage / NSEC_PER_MSEC); #endif printf("\n"); @@ -637,13 +805,13 @@ static void test_calibrations(struct perf_sched *sched) u64 T0, T1; T0 = get_nsecs(); - burn_nsecs(sched, 1e6); + burn_nsecs(sched, NSEC_PER_MSEC); T1 = get_nsecs(); printf("the run test took %" PRIu64 " nsecs\n", T1 - T0); T0 = get_nsecs(); - sleep_nsecs(1e6); + sleep_nsecs(NSEC_PER_MSEC); T1 = get_nsecs(); printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0); @@ -651,14 +819,14 @@ static void test_calibrations(struct perf_sched *sched) static int replay_wakeup_event(struct perf_sched *sched, - struct perf_evsel *evsel, struct perf_sample *sample, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { - const char *comm = perf_evsel__strval(evsel, sample, "comm"); - const u32 pid = perf_evsel__intval(evsel, sample, "pid"); + const char *comm = evsel__strval(evsel, sample, "comm"); + const u32 pid = evsel__intval(evsel, sample, "pid"); struct task_desc *waker, *wakee; - if (verbose) { + if (verbose > 0) { printf("sched_wakeup event %p\n", evsel); printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid); @@ -672,21 +840,20 @@ replay_wakeup_event(struct perf_sched *sched, } static int replay_switch_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { - const char *prev_comm = perf_evsel__strval(evsel, sample, "prev_comm"), - *next_comm = perf_evsel__strval(evsel, sample, "next_comm"); - const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), - next_pid = perf_evsel__intval(evsel, sample, "next_pid"); - const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state"); + const char *prev_comm = evsel__strval(evsel, sample, "prev_comm"), + *next_comm = evsel__strval(evsel, sample, "next_comm"); + const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"), + next_pid = evsel__intval(evsel, sample, "next_pid"); struct task_desc *prev, __maybe_unused *next; u64 timestamp0, timestamp = sample->time; int cpu = sample->cpu; s64 delta; - if (verbose) + if (verbose > 0) printf("sched_switch event %p\n", evsel); if (cpu >= MAX_CPUS || cpu < 0) @@ -712,27 +879,39 @@ static int replay_switch_event(struct perf_sched *sched, sched->cpu_last_switched[cpu] = timestamp; add_sched_event_run(sched, prev, timestamp, delta); - add_sched_event_sleep(sched, prev, timestamp, prev_state); + add_sched_event_sleep(sched, prev, timestamp); return 0; } -static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample) +static int replay_fork_event(struct perf_sched *sched, + union perf_event *event, + struct machine *machine) { - const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"), - *child_comm = perf_evsel__strval(evsel, sample, "child_comm"); - const u32 parent_pid = perf_evsel__intval(evsel, sample, "parent_pid"), - child_pid = perf_evsel__intval(evsel, sample, "child_pid"); + struct thread *child, *parent; - if (verbose) { - printf("sched_fork event %p\n", evsel); - printf("... parent: %s/%d\n", parent_comm, parent_pid); - printf("... child: %s/%d\n", child_comm, child_pid); + child = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + parent = machine__findnew_thread(machine, event->fork.ppid, + event->fork.ptid); + + if (child == NULL || parent == NULL) { + pr_debug("thread does not exist on fork event: child %p, parent %p\n", + child, parent); + goto out_put; + } + + if (verbose > 0) { + printf("fork event\n"); + printf("... parent: %s/%d\n", thread__comm_str(parent), thread__tid(parent)); + printf("... child: %s/%d\n", thread__comm_str(child), thread__tid(child)); } - register_pid(sched, parent_pid, parent_comm); - register_pid(sched, child_pid, child_comm); + register_pid(sched, thread__tid(parent), thread__comm_str(parent)); + register_pid(sched, thread__tid(child), thread__comm_str(child)); +out_put: + thread__put(child); + thread__put(parent); return 0; } @@ -742,6 +921,43 @@ struct sort_dimension { struct list_head list; }; +static inline void init_prio(struct thread_runtime *r) +{ + r->prio = -1; +} + +/* + * handle runtime stats saved per thread + */ +static struct thread_runtime *thread__init_runtime(struct thread *thread) +{ + struct thread_runtime *r; + + r = zalloc(sizeof(struct thread_runtime)); + if (!r) + return NULL; + + init_stats(&r->run_stats); + init_prio(r); + thread__set_priv(thread, r); + + return r; +} + +static struct thread_runtime *thread__get_runtime(struct thread *thread) +{ + struct thread_runtime *tr; + + tr = thread__priv(thread); + if (tr == NULL) { + tr = thread__init_runtime(thread); + if (tr == NULL) + pr_debug("Failed to malloc memory for runtime data.\n"); + } + + return tr; +} + static int thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r) { @@ -760,10 +976,10 @@ thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms * } static struct work_atoms * -thread_atoms_search(struct rb_root *root, struct thread *thread, +thread_atoms_search(struct rb_root_cached *root, struct thread *thread, struct list_head *sort_list) { - struct rb_node *node = root->rb_node; + struct rb_node *node = root->rb_root.rb_node; struct work_atoms key = { .thread = thread }; while (node) { @@ -778,7 +994,7 @@ thread_atoms_search(struct rb_root *root, struct thread *thread, else if (cmp < 0) node = node->rb_right; else { - BUG_ON(thread != atoms->thread); + BUG_ON(!RC_CHK_EQUAL(thread, atoms->thread)); return atoms; } } @@ -786,10 +1002,11 @@ thread_atoms_search(struct rb_root *root, struct thread *thread, } static void -__thread_latency_insert(struct rb_root *root, struct work_atoms *data, +__thread_latency_insert(struct rb_root_cached *root, struct work_atoms *data, struct list_head *sort_list) { - struct rb_node **new = &(root->rb_node), *parent = NULL; + struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL; + bool leftmost = true; while (*new) { struct work_atoms *this; @@ -802,12 +1019,14 @@ __thread_latency_insert(struct rb_root *root, struct work_atoms *data, if (cmp > 0) new = &((*new)->rb_left); - else + else { new = &((*new)->rb_right); + leftmost = false; + } } rb_link_node(&data->node, parent, new); - rb_insert_color(&data->node, root); + rb_insert_color_cached(&data->node, root, leftmost); } static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) @@ -818,27 +1037,12 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) return -1; } - atoms->thread = thread; + atoms->thread = thread__get(thread); INIT_LIST_HEAD(&atoms->work_list); __thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid); return 0; } -static int latency_fork_event(struct perf_sched *sched __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused) -{ - /* should insert the newcomer */ - return 0; -} - -static char sched_out_state(u64 prev_state) -{ - const char *str = TASK_STATE_TO_CHAR_STR; - - return str[prev_state]; -} - static int add_sched_out_event(struct work_atoms *atoms, char run_state, @@ -901,23 +1105,39 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp) atoms->total_lat += delta; if (delta > atoms->max_lat) { atoms->max_lat = delta; - atoms->max_lat_at = timestamp; + atoms->max_lat_start = atom->wake_up_time; + atoms->max_lat_end = timestamp; } atoms->nb_atoms++; } +static void free_work_atoms(struct work_atoms *atoms) +{ + struct work_atom *atom, *tmp; + + if (atoms == NULL) + return; + + list_for_each_entry_safe(atom, tmp, &atoms->work_list, list) { + list_del(&atom->list); + free(atom); + } + thread__zput(atoms->thread); + free(atoms); +} + static int latency_switch_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), - next_pid = perf_evsel__intval(evsel, sample, "next_pid"); - const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state"); + const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"), + next_pid = evsel__intval(evsel, sample, "next_pid"); + const char prev_state = evsel__taskstate(evsel, sample, "prev_state"); struct work_atoms *out_events, *in_events; struct thread *sched_out, *sched_in; u64 timestamp0, timestamp = sample->time; - int cpu = sample->cpu; + int cpu = sample->cpu, err = -1; s64 delta; BUG_ON(cpu >= MAX_CPUS || cpu < 0); @@ -934,100 +1154,109 @@ static int latency_switch_event(struct perf_sched *sched, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, -1, prev_pid); + sched_in = machine__findnew_thread(machine, -1, next_pid); + if (sched_out == NULL || sched_in == NULL) + goto out_put; out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { if (thread_atoms_insert(sched, sched_out)) - return -1; + goto out_put; out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { pr_err("out-event: Internal tree error"); - return -1; + goto out_put; } } - if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp)) + if (add_sched_out_event(out_events, prev_state, timestamp)) return -1; in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid); if (!in_events) { if (thread_atoms_insert(sched, sched_in)) - return -1; + goto out_put; in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid); if (!in_events) { pr_err("in-event: Internal tree error"); - return -1; + goto out_put; } /* * Take came in we have not heard about yet, * add in an initial atom in runnable state: */ if (add_sched_out_event(in_events, 'R', timestamp)) - return -1; + goto out_put; } add_sched_in_event(in_events, timestamp); - - return 0; + err = 0; +out_put: + thread__put(sched_out); + thread__put(sched_in); + return err; } static int latency_runtime_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 pid = perf_evsel__intval(evsel, sample, "pid"); - const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, pid); + const u32 pid = evsel__intval(evsel, sample, "pid"); + const u64 runtime = evsel__intval(evsel, sample, "runtime"); + struct thread *thread = machine__findnew_thread(machine, -1, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; - int cpu = sample->cpu; + int cpu = sample->cpu, err = -1; + + if (thread == NULL) + return -1; BUG_ON(cpu >= MAX_CPUS || cpu < 0); if (!atoms) { if (thread_atoms_insert(sched, thread)) - return -1; + goto out_put; atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); if (!atoms) { pr_err("in-event: Internal tree error"); - return -1; + goto out_put; } if (add_sched_out_event(atoms, 'R', timestamp)) - return -1; + goto out_put; } add_runtime_event(atoms, runtime, timestamp); - return 0; + err = 0; +out_put: + thread__put(thread); + return err; } static int latency_wakeup_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 pid = perf_evsel__intval(evsel, sample, "pid"), - success = perf_evsel__intval(evsel, sample, "success"); + const u32 pid = evsel__intval(evsel, sample, "pid"); struct work_atoms *atoms; struct work_atom *atom; struct thread *wakee; u64 timestamp = sample->time; + int err = -1; - /* Note for later, it may be interesting to observe the failing cases */ - if (!success) - return 0; - - wakee = machine__findnew_thread(machine, pid); + wakee = machine__findnew_thread(machine, -1, pid); + if (wakee == NULL) + return -1; atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) - return -1; + goto out_put; atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { pr_err("wakeup-event: Internal tree error"); - return -1; + goto out_put; } if (add_sched_out_event(atoms, 'S', timestamp)) - return -1; + goto out_put; } BUG_ON(list_empty(&atoms->work_list)); @@ -1035,34 +1264,45 @@ static int latency_wakeup_event(struct perf_sched *sched, atom = list_entry(atoms->work_list.prev, struct work_atom, list); /* + * As we do not guarantee the wakeup event happens when + * task is out of run queue, also may happen when task is + * on run queue and wakeup only change ->state to TASK_RUNNING, + * then we should not set the ->wake_up_time when wake up a + * task which is on run queue. + * * You WILL be missing events if you've recorded only * one CPU, or are only looking at only one, so don't - * make useless noise. + * skip in this case. */ if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING) - sched->nr_state_machine_bugs++; + goto out_ok; sched->nr_timestamps++; if (atom->sched_out_time > timestamp) { sched->nr_unordered_timestamps++; - return 0; + goto out_ok; } atom->state = THREAD_WAIT_CPU; atom->wake_up_time = timestamp; - return 0; +out_ok: + err = 0; +out_put: + thread__put(wakee); + return err; } static int latency_migrate_task_event(struct perf_sched *sched, - struct perf_evsel *evsel, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 pid = perf_evsel__intval(evsel, sample, "pid"); + const u32 pid = evsel__intval(evsel, sample, "pid"); u64 timestamp = sample->time; struct work_atoms *atoms; struct work_atom *atom; struct thread *migrant; + int err = -1; /* * Only need to worry about migration when profiling one CPU. @@ -1070,19 +1310,21 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, pid); + migrant = machine__findnew_thread(machine, -1, pid); + if (migrant == NULL) + return -1; atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) - return -1; - register_pid(sched, migrant->pid, migrant->comm); + goto out_put; + register_pid(sched, thread__tid(migrant), thread__comm_str(migrant)); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { pr_err("migration-event: Internal tree error"); - return -1; + goto out_put; } if (add_sched_out_event(atoms, 'R', timestamp)) - return -1; + goto out_put; } BUG_ON(list_empty(&atoms->work_list)); @@ -1094,8 +1336,10 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (atom->sched_out_time > timestamp) sched->nr_unordered_timestamps++; - - return 0; + err = 0; +out_put: + thread__put(migrant); + return err; } static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list) @@ -1103,40 +1347,54 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ int i; int ret; u64 avg; + char max_lat_start[32], max_lat_end[32]; if (!work_list->nb_atoms) return; /* * Ignore idle threads: */ - if (!strcmp(work_list->thread->comm, "swapper")) + if (!strcmp(thread__comm_str(work_list->thread), "swapper")) return; sched->all_runtime += work_list->total_runtime; sched->all_count += work_list->nb_atoms; - ret = printf(" %s:%d ", work_list->thread->comm, work_list->thread->pid); + if (work_list->num_merged > 1) { + ret = printf(" %s:(%d) ", thread__comm_str(work_list->thread), + work_list->num_merged); + } else { + ret = printf(" %s:%d ", thread__comm_str(work_list->thread), + thread__tid(work_list->thread)); + } for (i = 0; i < 24 - ret; i++) printf(" "); avg = work_list->total_lat / work_list->nb_atoms; - - printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", - (double)work_list->total_runtime / 1e6, - work_list->nb_atoms, (double)avg / 1e6, - (double)work_list->max_lat / 1e6, - (double)work_list->max_lat_at / 1e9); + timestamp__scnprintf_usec(work_list->max_lat_start, max_lat_start, sizeof(max_lat_start)); + timestamp__scnprintf_usec(work_list->max_lat_end, max_lat_end, sizeof(max_lat_end)); + + printf("|%11.3f ms |%9" PRIu64 " | avg:%8.3f ms | max:%8.3f ms | max start: %12s s | max end: %12s s\n", + (double)work_list->total_runtime / NSEC_PER_MSEC, + work_list->nb_atoms, (double)avg / NSEC_PER_MSEC, + (double)work_list->max_lat / NSEC_PER_MSEC, + max_lat_start, max_lat_end); } static int pid_cmp(struct work_atoms *l, struct work_atoms *r) { - if (l->thread->pid < r->thread->pid) + pid_t l_tid, r_tid; + + if (RC_CHK_EQUAL(l->thread, r->thread)) + return 0; + l_tid = thread__tid(l->thread); + r_tid = thread__tid(r->thread); + if (l_tid < r_tid) return -1; - if (l->thread->pid > r->thread->pid) + if (l_tid > r_tid) return 1; - - return 0; + return (int)(RC_CHK_ACCESS(l->thread) - RC_CHK_ACCESS(r->thread)); } static int avg_cmp(struct work_atoms *l, struct work_atoms *r) @@ -1235,21 +1493,26 @@ static int sort_dimension__add(const char *tok, struct list_head *list) static void perf_sched__sort_lat(struct perf_sched *sched) { struct rb_node *node; - + struct rb_root_cached *root = &sched->atom_root; +again: for (;;) { struct work_atoms *data; - node = rb_first(&sched->atom_root); + node = rb_first_cached(root); if (!node) break; - rb_erase(node, &sched->atom_root); + rb_erase_cached(node, root); data = rb_entry(node, struct work_atoms, node); __thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list); } + if (root == &sched->atom_root) { + root = &sched->merged_atom_root; + goto again; + } } -static int process_sched_wakeup_event(struct perf_tool *tool, - struct perf_evsel *evsel, +static int process_sched_wakeup_event(const struct perf_tool *tool, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1261,24 +1524,138 @@ static int process_sched_wakeup_event(struct perf_tool *tool, return 0; } -static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, +static int process_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unused, + struct evsel *evsel __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +static bool thread__has_color(struct thread *thread) +{ + return thread__priv(thread) != NULL; +} + +static struct thread* +map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid) +{ + struct thread *thread = machine__findnew_thread(machine, pid, tid); + bool color = false; + + if (!sched->map.color_pids || !thread || thread__priv(thread)) + return thread; + + if (thread_map__has(sched->map.color_pids, tid)) + color = true; + + thread__set_priv(thread, color ? ((void*)1) : NULL); + return thread; +} + +static bool sched_match_task(struct perf_sched *sched, const char *comm_str) +{ + bool fuzzy_match = sched->map.fuzzy; + struct strlist *task_names = sched->map.task_names; + struct str_node *node; + + strlist__for_each_entry(node, task_names) { + bool match_found = fuzzy_match ? !!strstr(comm_str, node->s) : + !strcmp(comm_str, node->s); + if (match_found) + return true; + } + + return false; +} + +static void print_sched_map(struct perf_sched *sched, struct perf_cpu this_cpu, int cpus_nr, + const char *color, bool sched_out) +{ + for (int i = 0; i < cpus_nr; i++) { + struct perf_cpu cpu = { + .cpu = sched->map.comp ? sched->map.comp_cpus[i].cpu : i, + }; + struct thread *curr_thread = sched->curr_thread[cpu.cpu]; + struct thread *curr_out_thread = sched->curr_out_thread[cpu.cpu]; + struct thread_runtime *curr_tr; + const char *pid_color = color; + const char *cpu_color = color; + char symbol = ' '; + struct thread *thread_to_check = sched_out ? curr_out_thread : curr_thread; + + if (thread_to_check && thread__has_color(thread_to_check)) + pid_color = COLOR_PIDS; + + if (sched->map.color_cpus && perf_cpu_map__has(sched->map.color_cpus, cpu)) + cpu_color = COLOR_CPUS; + + if (cpu.cpu == this_cpu.cpu) + symbol = '*'; + + color_fprintf(stdout, cpu.cpu != this_cpu.cpu ? color : cpu_color, "%c", symbol); + + thread_to_check = sched_out ? sched->curr_out_thread[cpu.cpu] : + sched->curr_thread[cpu.cpu]; + + if (thread_to_check) { + curr_tr = thread__get_runtime(thread_to_check); + if (curr_tr == NULL) + return; + + if (sched_out) { + if (cpu.cpu == this_cpu.cpu) + color_fprintf(stdout, color, "- "); + else { + curr_tr = thread__get_runtime(sched->curr_thread[cpu.cpu]); + if (curr_tr != NULL) + color_fprintf(stdout, pid_color, "%2s ", + curr_tr->shortname); + } + } else + color_fprintf(stdout, pid_color, "%2s ", curr_tr->shortname); + } else + color_fprintf(stdout, color, " "); + } +} + +static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), - next_pid = perf_evsel__intval(evsel, sample, "next_pid"); - struct thread *sched_out __maybe_unused, *sched_in; + const u32 next_pid = evsel__intval(evsel, sample, "next_pid"); + const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"); + struct thread *sched_in, *sched_out; + struct thread_runtime *tr; int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; - int cpu, this_cpu = sample->cpu; + struct perf_cpu this_cpu = { + .cpu = sample->cpu, + }; + int cpus_nr; + int proceed; + bool new_cpu = false; + const char *color = PERF_COLOR_NORMAL; + char stimestamp[32]; + const char *str; + int ret = -1; - BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0); + BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0); - if (this_cpu > sched->max_cpu) + if (this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu; - timestamp0 = sched->cpu_last_switched[this_cpu]; - sched->cpu_last_switched[this_cpu] = timestamp; + if (sched->map.comp) { + cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS); + if (!__test_and_set_bit(this_cpu.cpu, sched->map.comp_cpus_mask)) { + sched->map.comp_cpus[cpus_nr++] = this_cpu; + new_cpu = true; + } + } else + cpus_nr = sched->max_cpu.cpu; + + timestamp0 = sched->cpu_last_switched[this_cpu.cpu]; + sched->cpu_last_switched[this_cpu.cpu] = timestamp; if (timestamp0) delta = timestamp - timestamp0; else @@ -1289,66 +1666,132 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_in = map__findnew_thread(sched, machine, -1, next_pid); + sched_out = map__findnew_thread(sched, machine, -1, prev_pid); + if (sched_in == NULL || sched_out == NULL) + goto out; - sched->curr_thread[this_cpu] = sched_in; + tr = thread__get_runtime(sched_in); + if (tr == NULL) + goto out; - printf(" "); + thread__put(sched->curr_thread[this_cpu.cpu]); + thread__put(sched->curr_out_thread[this_cpu.cpu]); - new_shortname = 0; - if (!sched_in->shortname[0]) { - sched_in->shortname[0] = sched->next_shortname1; - sched_in->shortname[1] = sched->next_shortname2; + sched->curr_thread[this_cpu.cpu] = thread__get(sched_in); + sched->curr_out_thread[this_cpu.cpu] = thread__get(sched_out); - if (sched->next_shortname1 < 'Z') { - sched->next_shortname1++; - } else { - sched->next_shortname1='A'; - if (sched->next_shortname2 < '9') { - sched->next_shortname2++; + ret = 0; + + str = thread__comm_str(sched_in); + new_shortname = 0; + if (!tr->shortname[0]) { + if (!strcmp(thread__comm_str(sched_in), "swapper")) { + /* + * Don't allocate a letter-number for swapper:0 + * as a shortname. Instead, we use '.' for it. + */ + tr->shortname[0] = '.'; + tr->shortname[1] = ' '; + } else if (!sched->map.task_name || sched_match_task(sched, str)) { + tr->shortname[0] = sched->next_shortname1; + tr->shortname[1] = sched->next_shortname2; + + if (sched->next_shortname1 < 'Z') { + sched->next_shortname1++; } else { - sched->next_shortname2='0'; + sched->next_shortname1 = 'A'; + if (sched->next_shortname2 < '9') + sched->next_shortname2++; + else + sched->next_shortname2 = '0'; } + } else { + tr->shortname[0] = '-'; + tr->shortname[1] = ' '; } new_shortname = 1; } - for (cpu = 0; cpu <= sched->max_cpu; cpu++) { - if (cpu != this_cpu) - printf(" "); + if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, this_cpu)) + goto out; + + proceed = 0; + str = thread__comm_str(sched_in); + /* + * Check which of sched_in and sched_out matches the passed --task-name + * arguments and call the corresponding print_sched_map. + */ + if (sched->map.task_name && !sched_match_task(sched, str)) { + if (!sched_match_task(sched, thread__comm_str(sched_out))) + goto out; else - printf("*"); + goto sched_out; - if (sched->curr_thread[cpu]) { - if (sched->curr_thread[cpu]->pid) - printf("%2s ", sched->curr_thread[cpu]->shortname); - else - printf(". "); - } else - printf(" "); + } else { + str = thread__comm_str(sched_out); + if (!(sched->map.task_name && !sched_match_task(sched, str))) + proceed = 1; } - printf(" %12.6f secs ", (double)timestamp/1e9); - if (new_shortname) { - printf("%s => %s:%d\n", - sched_in->shortname, sched_in->comm, sched_in->pid); - } else { - printf("\n"); + printf(" "); + + print_sched_map(sched, this_cpu, cpus_nr, color, false); + + timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); + color_fprintf(stdout, color, " %12s secs ", stimestamp); + if (new_shortname || tr->comm_changed || (verbose > 0 && thread__tid(sched_in))) { + const char *pid_color = color; + + if (thread__has_color(sched_in)) + pid_color = COLOR_PIDS; + + color_fprintf(stdout, pid_color, "%s => %s:%d", + tr->shortname, thread__comm_str(sched_in), thread__tid(sched_in)); + tr->comm_changed = false; } - return 0; + if (sched->map.comp && new_cpu) + color_fprintf(stdout, color, " (CPU %d)", this_cpu.cpu); + + if (proceed != 1) { + color_fprintf(stdout, color, "\n"); + goto out; + } + +sched_out: + if (sched->map.task_name) { + tr = thread__get_runtime(sched->curr_out_thread[this_cpu.cpu]); + if (strcmp(tr->shortname, "") == 0) + goto out; + + if (proceed == 1) + color_fprintf(stdout, color, "\n"); + + printf(" "); + print_sched_map(sched, this_cpu, cpus_nr, color, true); + timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); + color_fprintf(stdout, color, " %12s secs ", stimestamp); + } + + color_fprintf(stdout, color, "\n"); + +out: + thread__put(sched_out); + thread__put(sched_in); + + return ret; } -static int process_sched_switch_event(struct perf_tool *tool, - struct perf_evsel *evsel, +static int process_sched_switch_event(const struct perf_tool *tool, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); int this_cpu = sample->cpu, err = 0; - u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), - next_pid = perf_evsel__intval(evsel, sample, "next_pid"); + u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"), + next_pid = evsel__intval(evsel, sample, "next_pid"); if (sched->curr_pid[this_cpu] != (u32)-1) { /* @@ -1366,8 +1809,8 @@ static int process_sched_switch_event(struct perf_tool *tool, return err; } -static int process_sched_runtime_event(struct perf_tool *tool, - struct perf_evsel *evsel, +static int process_sched_runtime_event(const struct perf_tool *tool, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1379,30 +1822,25 @@ static int process_sched_runtime_event(struct perf_tool *tool, return 0; } -static int process_sched_fork_event(struct perf_tool *tool, - struct perf_evsel *evsel, - struct perf_sample *sample, - struct machine *machine __maybe_unused) +static int perf_sched__process_fork_event(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - if (sched->tp_handler->fork_event) - return sched->tp_handler->fork_event(sched, evsel, sample); + /* run the fork event through the perf machinery */ + perf_event__process_fork(tool, event, sample, machine); - return 0; -} + /* and then run additional processing needed for this command */ + if (sched->tp_handler->fork_event) + return sched->tp_handler->fork_event(sched, event, machine); -static int process_sched_exit_event(struct perf_tool *tool __maybe_unused, - struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct machine *machine __maybe_unused) -{ - pr_debug("sched_exit event %p\n", evsel); return 0; } -static int process_sched_migrate_task_event(struct perf_tool *tool, - struct perf_evsel *evsel, +static int process_sched_migrate_task_event(const struct perf_tool *tool, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1414,85 +1852,1544 @@ static int process_sched_migrate_task_event(struct perf_tool *tool, return 0; } -typedef int (*tracepoint_handler)(struct perf_tool *tool, - struct perf_evsel *evsel, +typedef int (*tracepoint_handler)(const struct perf_tool *tool, + struct evsel *evsel, struct perf_sample *sample, struct machine *machine); -static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused, +static int perf_sched__process_tracepoint_sample(const struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample, - struct perf_evsel *evsel, + struct evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); int err = 0; - if (thread == NULL) { - pr_debug("problem processing %s event, skipping it.\n", - perf_evsel__name(evsel)); - return -1; + if (evsel->handler != NULL) { + tracepoint_handler f = evsel->handler; + err = f(tool, evsel, sample, machine); } - evsel->hists.stats.total_period += sample->period; - hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + return err; +} - if (evsel->handler.func != NULL) { - tracepoint_handler f = evsel->handler.func; - err = f(tool, evsel, sample, machine); +static int perf_sched__process_comm(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct thread_runtime *tr; + int err; + + err = perf_event__process_comm(tool, event, sample, machine); + if (err) + return err; + + thread = machine__find_thread(machine, sample->pid, sample->tid); + if (!thread) { + pr_err("Internal error: can't find thread\n"); + return -1; } - return err; + tr = thread__get_runtime(thread); + if (tr == NULL) { + thread__put(thread); + return -1; + } + + tr->comm_changed = true; + thread__put(thread); + + return 0; } -static int perf_sched__read_events(struct perf_sched *sched, bool destroy, - struct perf_session **psession) +static int perf_sched__read_events(struct perf_sched *sched) { - const struct perf_evsel_str_handler handlers[] = { + struct evsel_str_handler handlers[] = { { "sched:sched_switch", process_sched_switch_event, }, { "sched:sched_stat_runtime", process_sched_runtime_event, }, { "sched:sched_wakeup", process_sched_wakeup_event, }, + { "sched:sched_waking", process_sched_wakeup_event, }, { "sched:sched_wakeup_new", process_sched_wakeup_event, }, - { "sched:sched_process_fork", process_sched_fork_event, }, - { "sched:sched_process_exit", process_sched_exit_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; struct perf_session *session; + struct perf_data data = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + .force = sched->force, + }; + int rc = -1; - session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool); - if (session == NULL) { - pr_debug("No Memory for session\n"); - return -1; + session = perf_session__new(&data, &sched->tool); + if (IS_ERR(session)) { + pr_debug("Error creating perf session"); + return PTR_ERR(session); } + symbol__init(perf_session__env(session)); + + /* prefer sched_waking if it is captured */ + if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking")) + handlers[2].handler = process_sched_wakeup_ignore; + if (perf_session__set_tracepoints_handlers(session, handlers)) goto out_delete; if (perf_session__has_traces(session, "record -R")) { - int err = perf_session__process_events(session, &sched->tool); + int err = perf_session__process_events(session); if (err) { pr_err("Failed to process events, error %d", err); goto out_delete; } - sched->nr_events = session->stats.nr_events[0]; - sched->nr_lost_events = session->stats.total_lost; - sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; + sched->nr_events = session->evlist->stats.nr_events[0]; + sched->nr_lost_events = session->evlist->stats.total_lost; + sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST]; + } + + rc = 0; +out_delete: + perf_session__delete(session); + return rc; +} + +/* + * scheduling times are printed as msec.usec + */ +static inline void print_sched_time(unsigned long long nsecs, int width) +{ + unsigned long msecs; + unsigned long usecs; + + msecs = nsecs / NSEC_PER_MSEC; + nsecs -= msecs * NSEC_PER_MSEC; + usecs = nsecs / NSEC_PER_USEC; + printf("%*lu.%03lu ", width, msecs, usecs); +} + +/* + * returns runtime data for event, allocating memory for it the + * first time it is used. + */ +static struct evsel_runtime *evsel__get_runtime(struct evsel *evsel) +{ + struct evsel_runtime *r = evsel->priv; + + if (r == NULL) { + r = zalloc(sizeof(struct evsel_runtime)); + evsel->priv = r; } - if (destroy) - perf_session__delete(session); + return r; +} - if (psession) - *psession = session; +/* + * save last time event was seen per cpu + */ +static void evsel__save_time(struct evsel *evsel, u64 timestamp, u32 cpu) +{ + struct evsel_runtime *r = evsel__get_runtime(evsel); + + if (r == NULL) + return; + + if ((cpu >= r->ncpu) || (r->last_time == NULL)) { + int i, n = __roundup_pow_of_two(cpu+1); + void *p = r->last_time; + + p = realloc(r->last_time, n * sizeof(u64)); + if (!p) + return; + + r->last_time = p; + for (i = r->ncpu; i < n; ++i) + r->last_time[i] = (u64) 0; + + r->ncpu = n; + } + + r->last_time[cpu] = timestamp; +} + +/* returns last time this event was seen on the given cpu */ +static u64 evsel__get_time(struct evsel *evsel, u32 cpu) +{ + struct evsel_runtime *r = evsel__get_runtime(evsel); + + if ((r == NULL) || (r->last_time == NULL) || (cpu >= r->ncpu)) + return 0; + + return r->last_time[cpu]; +} + +static void timehist__evsel_priv_destructor(void *priv) +{ + struct evsel_runtime *r = priv; + + if (r) { + free(r->last_time); + free(r); + } +} + +static int comm_width = 30; + +static char *timehist_get_commstr(struct thread *thread) +{ + static char str[32]; + const char *comm = thread__comm_str(thread); + pid_t tid = thread__tid(thread); + pid_t pid = thread__pid(thread); + int n; + + if (pid == 0) + n = scnprintf(str, sizeof(str), "%s", comm); + + else if (tid != pid) + n = scnprintf(str, sizeof(str), "%s[%d/%d]", comm, tid, pid); + + else + n = scnprintf(str, sizeof(str), "%s[%d]", comm, tid); + + if (n > comm_width) + comm_width = n; + + return str; +} + +/* prio field format: xxx or xxx->yyy */ +#define MAX_PRIO_STR_LEN 8 +static char *timehist_get_priostr(struct evsel *evsel, + struct thread *thread, + struct perf_sample *sample) +{ + static char prio_str[16]; + int prev_prio = (int)evsel__intval(evsel, sample, "prev_prio"); + struct thread_runtime *tr = thread__priv(thread); + + if (tr->prio != prev_prio && tr->prio != -1) + scnprintf(prio_str, sizeof(prio_str), "%d->%d", tr->prio, prev_prio); + else + scnprintf(prio_str, sizeof(prio_str), "%d", prev_prio); + + return prio_str; +} + +static void timehist_header(struct perf_sched *sched) +{ + u32 ncpus = sched->max_cpu.cpu + 1; + u32 i, j; + + printf("%15s %6s ", "time", "cpu"); + + if (sched->show_cpu_visual) { + printf(" "); + for (i = 0, j = 0; i < ncpus; ++i) { + printf("%x", j++); + if (j > 15) + j = 0; + } + printf(" "); + } + + printf(" %-*s", comm_width, "task name"); + + if (sched->show_prio) + printf(" %-*s", MAX_PRIO_STR_LEN, "prio"); + + printf(" %9s %9s %9s", "wait time", "sch delay", "run time"); + + if (sched->pre_migrations) + printf(" %9s", "pre-mig time"); + + if (sched->show_state) + printf(" %s", "state"); + + printf("\n"); + + /* + * units row + */ + printf("%15s %-6s ", "", ""); + + if (sched->show_cpu_visual) + printf(" %*s ", ncpus, ""); + + printf(" %-*s", comm_width, "[tid/pid]"); + + if (sched->show_prio) + printf(" %-*s", MAX_PRIO_STR_LEN, ""); + + printf(" %9s %9s %9s", "(msec)", "(msec)", "(msec)"); + + if (sched->pre_migrations) + printf(" %9s", "(msec)"); + + printf("\n"); + + /* + * separator + */ + printf("%.15s %.6s ", graph_dotted_line, graph_dotted_line); + + if (sched->show_cpu_visual) + printf(" %.*s ", ncpus, graph_dotted_line); + + printf(" %.*s", comm_width, graph_dotted_line); + + if (sched->show_prio) + printf(" %.*s", MAX_PRIO_STR_LEN, graph_dotted_line); + + printf(" %.9s %.9s %.9s", graph_dotted_line, graph_dotted_line, graph_dotted_line); + + if (sched->pre_migrations) + printf(" %.9s", graph_dotted_line); + + if (sched->show_state) + printf(" %.5s", graph_dotted_line); + + printf("\n"); +} + +static void timehist_print_sample(struct perf_sched *sched, + struct evsel *evsel, + struct perf_sample *sample, + struct addr_location *al, + struct thread *thread, + u64 t, const char state) +{ + struct thread_runtime *tr = thread__priv(thread); + const char *next_comm = evsel__strval(evsel, sample, "next_comm"); + const u32 next_pid = evsel__intval(evsel, sample, "next_pid"); + u32 max_cpus = sched->max_cpu.cpu + 1; + char tstr[64]; + char nstr[30]; + u64 wait_time; + + if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + return; + + timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); + printf("%15s [%04d] ", tstr, sample->cpu); + + if (sched->show_cpu_visual) { + u32 i; + char c; + + printf(" "); + for (i = 0; i < max_cpus; ++i) { + /* flag idle times with 'i'; others are sched events */ + if (i == sample->cpu) + c = (thread__tid(thread) == 0) ? 'i' : 's'; + else + c = ' '; + printf("%c", c); + } + printf(" "); + } + + if (!thread__comm_set(thread)) { + const char *prev_comm = evsel__strval(evsel, sample, "prev_comm"); + thread__set_comm(thread, prev_comm, sample->time); + } + + printf(" %-*s ", comm_width, timehist_get_commstr(thread)); + + if (sched->show_prio) + printf(" %-*s ", MAX_PRIO_STR_LEN, timehist_get_priostr(evsel, thread, sample)); + + wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt; + print_sched_time(wait_time, 6); + + print_sched_time(tr->dt_delay, 6); + print_sched_time(tr->dt_run, 6); + if (sched->pre_migrations) + print_sched_time(tr->dt_pre_mig, 6); + + if (sched->show_state) + printf(" %5c ", thread__tid(thread) == 0 ? 'I' : state); + + if (sched->show_next) { + snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid); + printf(" %-*s", comm_width, nstr); + } + + if (sched->show_wakeups && !sched->show_next) + printf(" %-*s", comm_width, ""); + + if (thread__tid(thread) == 0) + goto out; + + if (sched->show_callchain) + printf(" "); + + sample__fprintf_sym(sample, al, 0, + EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE | + EVSEL__PRINT_CALLCHAIN_ARROW | + EVSEL__PRINT_SKIP_IGNORED, + get_tls_callchain_cursor(), symbol_conf.bt_stop_list, stdout); + +out: + printf("\n"); +} + +/* + * Explanation of delta-time stats: + * + * t = time of current schedule out event + * tprev = time of previous sched out event + * also time of schedule-in event for current task + * last_time = time of last sched change event for current task + * (i.e, time process was last scheduled out) + * ready_to_run = time of wakeup for current task + * migrated = time of task migration to another CPU + * + * -----|-------------|-------------|-------------|-------------|----- + * last ready migrated tprev t + * time to run + * + * |---------------- dt_wait ----------------| + * |--------- dt_delay ---------|-- dt_run --| + * |- dt_pre_mig -| + * + * dt_run = run time of current task + * dt_wait = time between last schedule out event for task and tprev + * represents time spent off the cpu + * dt_delay = time between wakeup and schedule-in of task + * dt_pre_mig = time between wakeup and migration to another CPU + */ + +static void timehist_update_runtime_stats(struct thread_runtime *r, + u64 t, u64 tprev) +{ + r->dt_delay = 0; + r->dt_sleep = 0; + r->dt_iowait = 0; + r->dt_preempt = 0; + r->dt_run = 0; + r->dt_pre_mig = 0; + + if (tprev) { + r->dt_run = t - tprev; + if (r->ready_to_run) { + if (r->ready_to_run > tprev) + pr_debug("time travel: wakeup time for task > previous sched_switch event\n"); + else + r->dt_delay = tprev - r->ready_to_run; + + if ((r->migrated > r->ready_to_run) && (r->migrated < tprev)) + r->dt_pre_mig = r->migrated - r->ready_to_run; + } + + if (r->last_time > tprev) + pr_debug("time travel: last sched out time for task > previous sched_switch event\n"); + else if (r->last_time) { + u64 dt_wait = tprev - r->last_time; + + if (r->last_state == 'R') + r->dt_preempt = dt_wait; + else if (r->last_state == 'D') + r->dt_iowait = dt_wait; + else + r->dt_sleep = dt_wait; + } + } + + update_stats(&r->run_stats, r->dt_run); + + r->total_run_time += r->dt_run; + r->total_delay_time += r->dt_delay; + r->total_sleep_time += r->dt_sleep; + r->total_iowait_time += r->dt_iowait; + r->total_preempt_time += r->dt_preempt; + r->total_pre_mig_time += r->dt_pre_mig; +} + +static bool is_idle_sample(struct perf_sample *sample, + struct evsel *evsel) +{ + /* pid 0 == swapper == idle task */ + if (evsel__name_is(evsel, "sched:sched_switch")) + return evsel__intval(evsel, sample, "prev_pid") == 0; + + return sample->pid == 0; +} + +static void save_task_callchain(struct perf_sched *sched, + struct perf_sample *sample, + struct evsel *evsel, + struct machine *machine) +{ + struct callchain_cursor *cursor; + struct thread *thread; + + /* want main thread for process - has maps */ + thread = machine__findnew_thread(machine, sample->pid, sample->pid); + if (thread == NULL) { + pr_debug("Failed to get thread for pid %d.\n", sample->pid); + return; + } + + if (!sched->show_callchain || sample->callchain == NULL) { + thread__put(thread); + return; + } + + cursor = get_tls_callchain_cursor(); + + if (thread__resolve_callchain(thread, cursor, evsel, sample, + NULL, NULL, sched->max_stack + 2) != 0) { + if (verbose > 0) + pr_err("Failed to resolve callchain. Skipping\n"); + + thread__put(thread); + return; + } + + callchain_cursor_commit(cursor); + thread__put(thread); + + while (true) { + struct callchain_cursor_node *node; + struct symbol *sym; + + node = callchain_cursor_current(cursor); + if (node == NULL) + break; + + sym = node->ms.sym; + if (sym) { + if (!strcmp(sym->name, "schedule") || + !strcmp(sym->name, "__schedule") || + !strcmp(sym->name, "preempt_schedule")) + sym->ignore = 1; + } + + callchain_cursor_advance(cursor); + } +} + +static int init_idle_thread(struct thread *thread) +{ + struct idle_thread_runtime *itr; + + thread__set_comm(thread, idle_comm, 0); + + itr = zalloc(sizeof(*itr)); + if (itr == NULL) + return -ENOMEM; + + init_prio(&itr->tr); + init_stats(&itr->tr.run_stats); + callchain_init(&itr->callchain); + callchain_cursor_reset(&itr->cursor); + thread__set_priv(thread, itr); return 0; +} -out_delete: +/* + * Track idle stats per cpu by maintaining a local thread + * struct for the idle task on each cpu. + */ +static int init_idle_threads(int ncpu) +{ + int i, ret; + + idle_threads = zalloc(ncpu * sizeof(struct thread *)); + if (!idle_threads) + return -ENOMEM; + + idle_max_cpu = ncpu; + + /* allocate the actual thread struct if needed */ + for (i = 0; i < ncpu; ++i) { + idle_threads[i] = thread__new(0, 0); + if (idle_threads[i] == NULL) + return -ENOMEM; + + ret = init_idle_thread(idle_threads[i]); + if (ret < 0) + return ret; + } + + return 0; +} + +static void free_idle_threads(void) +{ + int i; + + if (idle_threads == NULL) + return; + + for (i = 0; i < idle_max_cpu; ++i) { + struct thread *idle = idle_threads[i]; + + if (idle) { + struct idle_thread_runtime *itr; + + itr = thread__priv(idle); + if (itr) + thread__put(itr->last_thread); + + thread__delete(idle); + } + } + + free(idle_threads); +} + +static struct thread *get_idle_thread(int cpu) +{ + /* + * expand/allocate array of pointers to local thread + * structs if needed + */ + if ((cpu >= idle_max_cpu) || (idle_threads == NULL)) { + int i, j = __roundup_pow_of_two(cpu+1); + void *p; + + p = realloc(idle_threads, j * sizeof(struct thread *)); + if (!p) + return NULL; + + idle_threads = (struct thread **) p; + for (i = idle_max_cpu; i < j; ++i) + idle_threads[i] = NULL; + + idle_max_cpu = j; + } + + /* allocate a new thread struct if needed */ + if (idle_threads[cpu] == NULL) { + idle_threads[cpu] = thread__new(0, 0); + + if (idle_threads[cpu]) { + if (init_idle_thread(idle_threads[cpu]) < 0) + return NULL; + } + } + + return thread__get(idle_threads[cpu]); +} + +static void save_idle_callchain(struct perf_sched *sched, + struct idle_thread_runtime *itr, + struct perf_sample *sample) +{ + struct callchain_cursor *cursor; + + if (!sched->show_callchain || sample->callchain == NULL) + return; + + cursor = get_tls_callchain_cursor(); + if (cursor == NULL) + return; + + callchain_cursor__copy(&itr->cursor, cursor); +} + +static struct thread *timehist_get_thread(struct perf_sched *sched, + struct perf_sample *sample, + struct machine *machine, + struct evsel *evsel) +{ + struct thread *thread; + + if (is_idle_sample(sample, evsel)) { + thread = get_idle_thread(sample->cpu); + if (thread == NULL) + pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu); + + } else { + /* there were samples with tid 0 but non-zero pid */ + thread = machine__findnew_thread(machine, sample->pid, + sample->tid ?: sample->pid); + if (thread == NULL) { + pr_debug("Failed to get thread for tid %d. skipping sample.\n", + sample->tid); + } + + save_task_callchain(sched, sample, evsel, machine); + if (sched->idle_hist) { + struct thread *idle; + struct idle_thread_runtime *itr; + + idle = get_idle_thread(sample->cpu); + if (idle == NULL) { + pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu); + return NULL; + } + + itr = thread__priv(idle); + if (itr == NULL) + return NULL; + + thread__put(itr->last_thread); + itr->last_thread = thread__get(thread); + + /* copy task callchain when entering to idle */ + if (evsel__intval(evsel, sample, "next_pid") == 0) + save_idle_callchain(sched, itr, sample); + } + } + + return thread; +} + +static bool timehist_skip_sample(struct perf_sched *sched, + struct thread *thread, + struct evsel *evsel, + struct perf_sample *sample) +{ + bool rc = false; + int prio = -1; + struct thread_runtime *tr = NULL; + + if (thread__is_filtered(thread)) { + rc = true; + sched->skipped_samples++; + } + + if (sched->prio_str) { + /* + * Because priority may be changed during task execution, + * first read priority from prev sched_in event for current task. + * If prev sched_in event is not saved, then read priority from + * current task sched_out event. + */ + tr = thread__get_runtime(thread); + if (tr && tr->prio != -1) + prio = tr->prio; + else if (evsel__name_is(evsel, "sched:sched_switch")) + prio = evsel__intval(evsel, sample, "prev_prio"); + + if (prio != -1 && !test_bit(prio, sched->prio_bitmap)) { + rc = true; + sched->skipped_samples++; + } + } + + if (sched->idle_hist) { + if (!evsel__name_is(evsel, "sched:sched_switch")) + rc = true; + else if (evsel__intval(evsel, sample, "prev_pid") != 0 && + evsel__intval(evsel, sample, "next_pid") != 0) + rc = true; + } + + return rc; +} + +static void timehist_print_wakeup_event(struct perf_sched *sched, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine, + struct thread *awakened) +{ + struct thread *thread; + char tstr[64]; + + thread = machine__findnew_thread(machine, sample->pid, sample->tid); + if (thread == NULL) + return; + + /* show wakeup unless both awakee and awaker are filtered */ + if (timehist_skip_sample(sched, thread, evsel, sample) && + timehist_skip_sample(sched, awakened, evsel, sample)) { + thread__put(thread); + return; + } + + timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr)); + printf("%15s [%04d] ", tstr, sample->cpu); + if (sched->show_cpu_visual) + printf(" %*s ", sched->max_cpu.cpu + 1, ""); + + printf(" %-*s ", comm_width, timehist_get_commstr(thread)); + + /* dt spacer */ + printf(" %9s %9s %9s ", "", "", ""); + + printf("awakened: %s", timehist_get_commstr(awakened)); + + printf("\n"); + + thread__put(thread); +} + +static int timehist_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct evsel *evsel __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +static int timehist_sched_wakeup_event(const struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + struct thread *thread; + struct thread_runtime *tr = NULL; + /* want pid of awakened task not pid in sample */ + const u32 pid = evsel__intval(evsel, sample, "pid"); + + thread = machine__findnew_thread(machine, 0, pid); + if (thread == NULL) + return -1; + + tr = thread__get_runtime(thread); + if (tr == NULL) { + thread__put(thread); + return -1; + } + + if (tr->ready_to_run == 0) + tr->ready_to_run = sample->time; + + /* show wakeups if requested */ + if (sched->show_wakeups && + !perf_time__skip_sample(&sched->ptime, sample->time)) + timehist_print_wakeup_event(sched, evsel, sample, machine, thread); + + thread__put(thread); + return 0; +} + +static void timehist_print_migration_event(struct perf_sched *sched, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine, + struct thread *migrated) +{ + struct thread *thread; + char tstr[64]; + u32 max_cpus; + u32 ocpu, dcpu; + + if (sched->summary_only) + return; + + max_cpus = sched->max_cpu.cpu + 1; + ocpu = evsel__intval(evsel, sample, "orig_cpu"); + dcpu = evsel__intval(evsel, sample, "dest_cpu"); + + thread = machine__findnew_thread(machine, sample->pid, sample->tid); + if (thread == NULL) + return; + + if (timehist_skip_sample(sched, thread, evsel, sample) && + timehist_skip_sample(sched, migrated, evsel, sample)) { + thread__put(thread); + return; + } + + timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr)); + printf("%15s [%04d] ", tstr, sample->cpu); + + if (sched->show_cpu_visual) { + u32 i; + char c; + + printf(" "); + for (i = 0; i < max_cpus; ++i) { + c = (i == sample->cpu) ? 'm' : ' '; + printf("%c", c); + } + printf(" "); + } + + printf(" %-*s ", comm_width, timehist_get_commstr(thread)); + + /* dt spacer */ + printf(" %9s %9s %9s ", "", "", ""); + + printf("migrated: %s", timehist_get_commstr(migrated)); + printf(" cpu %d => %d", ocpu, dcpu); + + printf("\n"); + thread__put(thread); +} + +static int timehist_migrate_task_event(const struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + struct thread *thread; + struct thread_runtime *tr = NULL; + /* want pid of migrated task not pid in sample */ + const u32 pid = evsel__intval(evsel, sample, "pid"); + + thread = machine__findnew_thread(machine, 0, pid); + if (thread == NULL) + return -1; + + tr = thread__get_runtime(thread); + if (tr == NULL) { + thread__put(thread); + return -1; + } + + tr->migrations++; + tr->migrated = sample->time; + + /* show migrations if requested */ + if (sched->show_migrations) { + timehist_print_migration_event(sched, evsel, sample, + machine, thread); + } + thread__put(thread); + + return 0; +} + +static void timehist_update_task_prio(struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct thread_runtime *tr = NULL; + const u32 next_pid = evsel__intval(evsel, sample, "next_pid"); + const u32 next_prio = evsel__intval(evsel, sample, "next_prio"); + + if (next_pid == 0) + thread = get_idle_thread(sample->cpu); + else + thread = machine__findnew_thread(machine, -1, next_pid); + + if (thread == NULL) + return; + + tr = thread__get_runtime(thread); + if (tr != NULL) + tr->prio = next_prio; + + thread__put(thread); +} + +static int timehist_sched_change_event(const struct perf_tool *tool, + union perf_event *event, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + struct perf_time_interval *ptime = &sched->ptime; + struct addr_location al; + struct thread *thread = NULL; + struct thread_runtime *tr = NULL; + u64 tprev, t = sample->time; + int rc = 0; + const char state = evsel__taskstate(evsel, sample, "prev_state"); + + addr_location__init(&al); + if (machine__resolve(machine, &al, sample) < 0) { + pr_err("problem processing %d event. skipping it\n", + event->header.type); + rc = -1; + goto out; + } + + if (sched->show_prio || sched->prio_str) + timehist_update_task_prio(evsel, sample, machine); + + thread = timehist_get_thread(sched, sample, machine, evsel); + if (thread == NULL) { + rc = -1; + goto out; + } + + if (timehist_skip_sample(sched, thread, evsel, sample)) + goto out; + + tr = thread__get_runtime(thread); + if (tr == NULL) { + rc = -1; + goto out; + } + + tprev = evsel__get_time(evsel, sample->cpu); + + /* + * If start time given: + * - sample time is under window user cares about - skip sample + * - tprev is under window user cares about - reset to start of window + */ + if (ptime->start && ptime->start > t) + goto out; + + if (tprev && ptime->start > tprev) + tprev = ptime->start; + + /* + * If end time given: + * - previous sched event is out of window - we are done + * - sample time is beyond window user cares about - reset it + * to close out stats for time window interest + * - If tprev is 0, that is, sched_in event for current task is + * not recorded, cannot determine whether sched_in event is + * within time window interest - ignore it + */ + if (ptime->end) { + if (!tprev || tprev > ptime->end) + goto out; + + if (t > ptime->end) + t = ptime->end; + } + + if (!sched->idle_hist || thread__tid(thread) == 0) { + if (!cpu_list || test_bit(sample->cpu, cpu_bitmap)) + timehist_update_runtime_stats(tr, t, tprev); + + if (sched->idle_hist) { + struct idle_thread_runtime *itr = (void *)tr; + struct thread_runtime *last_tr; + + if (itr->last_thread == NULL) + goto out; + + /* add current idle time as last thread's runtime */ + last_tr = thread__get_runtime(itr->last_thread); + if (last_tr == NULL) + goto out; + + timehist_update_runtime_stats(last_tr, t, tprev); + /* + * remove delta time of last thread as it's not updated + * and otherwise it will show an invalid value next + * time. we only care total run time and run stat. + */ + last_tr->dt_run = 0; + last_tr->dt_delay = 0; + last_tr->dt_sleep = 0; + last_tr->dt_iowait = 0; + last_tr->dt_preempt = 0; + + if (itr->cursor.nr) + callchain_append(&itr->callchain, &itr->cursor, t - tprev); + + itr->last_thread = NULL; + } + + if (!sched->summary_only) + timehist_print_sample(sched, evsel, sample, &al, thread, t, state); + } + +out: + if (sched->hist_time.start == 0 && t >= ptime->start) + sched->hist_time.start = t; + if (ptime->end == 0 || t <= ptime->end) + sched->hist_time.end = t; + + if (tr) { + /* time of this sched_switch event becomes last time task seen */ + tr->last_time = sample->time; + + /* last state is used to determine where to account wait time */ + tr->last_state = state; + + /* sched out event for task so reset ready to run time and migrated time */ + if (state == 'R') + tr->ready_to_run = t; + else + tr->ready_to_run = 0; + + tr->migrated = 0; + } + + evsel__save_time(evsel, sample->time, sample->cpu); + + thread__put(thread); + addr_location__exit(&al); + return rc; +} + +static int timehist_sched_switch_event(const struct perf_tool *tool, + union perf_event *event, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine __maybe_unused) +{ + return timehist_sched_change_event(tool, event, evsel, sample, machine); +} + +static int process_lost(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine __maybe_unused) +{ + char tstr[64]; + + timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr)); + printf("%15s ", tstr); + printf("lost %" PRI_lu64 " events on cpu %d\n", event->lost.lost, sample->cpu); + + return 0; +} + + +static void print_thread_runtime(struct thread *t, + struct thread_runtime *r) +{ + double mean = avg_stats(&r->run_stats); + float stddev; + + printf("%*s %5d %9" PRIu64 " ", + comm_width, timehist_get_commstr(t), thread__ppid(t), + (u64) r->run_stats.n); + + print_sched_time(r->total_run_time, 8); + stddev = rel_stddev_stats(stddev_stats(&r->run_stats), mean); + print_sched_time(r->run_stats.min, 6); + printf(" "); + print_sched_time((u64) mean, 6); + printf(" "); + print_sched_time(r->run_stats.max, 6); + printf(" "); + printf("%5.2f", stddev); + printf(" %5" PRIu64, r->migrations); + printf("\n"); +} + +static void print_thread_waittime(struct thread *t, + struct thread_runtime *r) +{ + printf("%*s %5d %9" PRIu64 " ", + comm_width, timehist_get_commstr(t), thread__ppid(t), + (u64) r->run_stats.n); + + print_sched_time(r->total_run_time, 8); + print_sched_time(r->total_sleep_time, 6); + printf(" "); + print_sched_time(r->total_iowait_time, 6); + printf(" "); + print_sched_time(r->total_preempt_time, 6); + printf(" "); + print_sched_time(r->total_delay_time, 6); + printf("\n"); +} + +struct total_run_stats { + struct perf_sched *sched; + u64 sched_count; + u64 task_count; + u64 total_run_time; +}; + +static int show_thread_runtime(struct thread *t, void *priv) +{ + struct total_run_stats *stats = priv; + struct thread_runtime *r; + + if (thread__is_filtered(t)) + return 0; + + r = thread__priv(t); + if (r && r->run_stats.n) { + stats->task_count++; + stats->sched_count += r->run_stats.n; + stats->total_run_time += r->total_run_time; + + if (stats->sched->show_state) + print_thread_waittime(t, r); + else + print_thread_runtime(t, r); + } + + return 0; +} + +static size_t callchain__fprintf_folded(FILE *fp, struct callchain_node *node) +{ + const char *sep = " <- "; + struct callchain_list *chain; + size_t ret = 0; + char bf[1024]; + bool first; + + if (node == NULL) + return 0; + + ret = callchain__fprintf_folded(fp, node->parent); + first = (ret == 0); + + list_for_each_entry(chain, &node->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + if (chain->ms.sym && chain->ms.sym->ignore) + continue; + ret += fprintf(fp, "%s%s", first ? "" : sep, + callchain_list__sym_name(chain, bf, sizeof(bf), + false)); + first = false; + } + + return ret; +} + +static size_t timehist_print_idlehist_callchain(struct rb_root_cached *root) +{ + size_t ret = 0; + FILE *fp = stdout; + struct callchain_node *chain; + struct rb_node *rb_node = rb_first_cached(root); + + printf(" %16s %8s %s\n", "Idle time (msec)", "Count", "Callchains"); + printf(" %.16s %.8s %.50s\n", graph_dotted_line, graph_dotted_line, + graph_dotted_line); + + while (rb_node) { + chain = rb_entry(rb_node, struct callchain_node, rb_node); + rb_node = rb_next(rb_node); + + ret += fprintf(fp, " "); + print_sched_time(chain->hit, 12); + ret += 16; /* print_sched_time returns 2nd arg + 4 */ + ret += fprintf(fp, " %8d ", chain->count); + ret += callchain__fprintf_folded(fp, chain); + ret += fprintf(fp, "\n"); + } + + return ret; +} + +static void timehist_print_summary(struct perf_sched *sched, + struct perf_session *session) +{ + struct machine *m = &session->machines.host; + struct total_run_stats totals; + u64 task_count; + struct thread *t; + struct thread_runtime *r; + int i; + u64 hist_time = sched->hist_time.end - sched->hist_time.start; + + memset(&totals, 0, sizeof(totals)); + totals.sched = sched; + + if (sched->idle_hist) { + printf("\nIdle-time summary\n"); + printf("%*s parent sched-out ", comm_width, "comm"); + printf(" idle-time min-idle avg-idle max-idle stddev migrations\n"); + } else if (sched->show_state) { + printf("\nWait-time summary\n"); + printf("%*s parent sched-in ", comm_width, "comm"); + printf(" run-time sleep iowait preempt delay\n"); + } else { + printf("\nRuntime summary\n"); + printf("%*s parent sched-in ", comm_width, "comm"); + printf(" run-time min-run avg-run max-run stddev migrations\n"); + } + printf("%*s (count) ", comm_width, ""); + printf(" (msec) (msec) (msec) (msec) %s\n", + sched->show_state ? "(msec)" : "%"); + printf("%.117s\n", graph_dotted_line); + + machine__for_each_thread(m, show_thread_runtime, &totals); + task_count = totals.task_count; + if (!task_count) + printf("<no still running tasks>\n"); + + /* CPU idle stats not tracked when samples were skipped */ + if (sched->skipped_samples && !sched->idle_hist) + return; + + printf("\nIdle stats:\n"); + for (i = 0; i < idle_max_cpu; ++i) { + if (cpu_list && !test_bit(i, cpu_bitmap)) + continue; + + t = idle_threads[i]; + if (!t) + continue; + + r = thread__priv(t); + if (r && r->run_stats.n) { + totals.sched_count += r->run_stats.n; + printf(" CPU %2d idle for ", i); + print_sched_time(r->total_run_time, 6); + printf(" msec (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time); + } else + printf(" CPU %2d idle entire time window\n", i); + } + + if (sched->idle_hist && sched->show_callchain) { + callchain_param.mode = CHAIN_FOLDED; + callchain_param.value = CCVAL_PERIOD; + + callchain_register_param(&callchain_param); + + printf("\nIdle stats by callchain:\n"); + for (i = 0; i < idle_max_cpu; ++i) { + struct idle_thread_runtime *itr; + + t = idle_threads[i]; + if (!t) + continue; + + itr = thread__priv(t); + if (itr == NULL) + continue; + + callchain_param.sort(&itr->sorted_root.rb_root, &itr->callchain, + 0, &callchain_param); + + printf(" CPU %2d:", i); + print_sched_time(itr->tr.total_run_time, 6); + printf(" msec\n"); + timehist_print_idlehist_callchain(&itr->sorted_root); + printf("\n"); + } + } + + printf("\n" + " Total number of unique tasks: %" PRIu64 "\n" + "Total number of context switches: %" PRIu64 "\n", + totals.task_count, totals.sched_count); + + printf(" Total run time (msec): "); + print_sched_time(totals.total_run_time, 2); + printf("\n"); + + printf(" Total scheduling time (msec): "); + print_sched_time(hist_time, 2); + printf(" (x %d)\n", sched->max_cpu.cpu); +} + +typedef int (*sched_handler)(const struct perf_tool *tool, + union perf_event *event, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine); + +static int perf_timehist__process_sample(const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct evsel *evsel, + struct machine *machine) +{ + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + int err = 0; + struct perf_cpu this_cpu = { + .cpu = sample->cpu, + }; + + if (this_cpu.cpu > sched->max_cpu.cpu) + sched->max_cpu = this_cpu; + + if (evsel->handler != NULL) { + sched_handler f = evsel->handler; + + err = f(tool, event, evsel, sample, machine); + } + + return err; +} + +static int timehist_check_attr(struct perf_sched *sched, + struct evlist *evlist) +{ + struct evsel *evsel; + struct evsel_runtime *er; + + list_for_each_entry(evsel, &evlist->core.entries, core.node) { + er = evsel__get_runtime(evsel); + if (er == NULL) { + pr_err("Failed to allocate memory for evsel runtime data\n"); + return -1; + } + + /* only need to save callchain related to sched_switch event */ + if (sched->show_callchain && + evsel__name_is(evsel, "sched:sched_switch") && + !evsel__has_callchain(evsel)) { + pr_info("Samples of sched_switch event do not have callchains.\n"); + sched->show_callchain = 0; + symbol_conf.use_callchain = 0; + } + } + + return 0; +} + +static int timehist_parse_prio_str(struct perf_sched *sched) +{ + char *p; + unsigned long start_prio, end_prio; + const char *str = sched->prio_str; + + if (!str) + return 0; + + while (isdigit(*str)) { + p = NULL; + start_prio = strtoul(str, &p, 0); + if (start_prio >= MAX_PRIO || (*p != '\0' && *p != ',' && *p != '-')) + return -1; + + if (*p == '-') { + str = ++p; + p = NULL; + end_prio = strtoul(str, &p, 0); + + if (end_prio >= MAX_PRIO || (*p != '\0' && *p != ',')) + return -1; + + if (end_prio < start_prio) + return -1; + } else { + end_prio = start_prio; + } + + for (; start_prio <= end_prio; start_prio++) + __set_bit(start_prio, sched->prio_bitmap); + + if (*p) + ++p; + + str = p; + } + + return 0; +} + +static int perf_sched__timehist(struct perf_sched *sched) +{ + struct evsel_str_handler handlers[] = { + { "sched:sched_switch", timehist_sched_switch_event, }, + { "sched:sched_wakeup", timehist_sched_wakeup_event, }, + { "sched:sched_waking", timehist_sched_wakeup_event, }, + { "sched:sched_wakeup_new", timehist_sched_wakeup_event, }, + }; + const struct evsel_str_handler migrate_handlers[] = { + { "sched:sched_migrate_task", timehist_migrate_task_event, }, + }; + struct perf_data data = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + .force = sched->force, + }; + + struct perf_session *session; + struct perf_env *env; + struct evlist *evlist; + int err = -1; + + /* + * event handlers for timehist option + */ + sched->tool.sample = perf_timehist__process_sample; + sched->tool.mmap = perf_event__process_mmap; + sched->tool.comm = perf_event__process_comm; + sched->tool.exit = perf_event__process_exit; + sched->tool.fork = perf_event__process_fork; + sched->tool.lost = process_lost; + sched->tool.attr = perf_event__process_attr; + sched->tool.tracing_data = perf_event__process_tracing_data; + sched->tool.build_id = perf_event__process_build_id; + + sched->tool.ordering_requires_timestamps = true; + + symbol_conf.use_callchain = sched->show_callchain; + + session = perf_session__new(&data, &sched->tool); + if (IS_ERR(session)) + return PTR_ERR(session); + + env = perf_session__env(session); + if (cpu_list) { + err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); + if (err < 0) + goto out; + } + + evlist = session->evlist; + + symbol__init(env); + + if (perf_time__parse_str(&sched->ptime, sched->time_str) != 0) { + pr_err("Invalid time string\n"); + err = -EINVAL; + goto out; + } + + if (timehist_check_attr(sched, evlist) != 0) + goto out; + + if (timehist_parse_prio_str(sched) != 0) { + pr_err("Invalid prio string\n"); + goto out; + } + + setup_pager(); + + evsel__set_priv_destructor(timehist__evsel_priv_destructor); + + /* prefer sched_waking if it is captured */ + if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking")) + handlers[1].handler = timehist_sched_wakeup_ignore; + + /* setup per-evsel handlers */ + if (perf_session__set_tracepoints_handlers(session, handlers)) + goto out; + + /* sched_switch event at a minimum needs to exist */ + if (!evlist__find_tracepoint_by_name(session->evlist, "sched:sched_switch")) { + pr_err("No sched_switch events found. Have you run 'perf sched record'?\n"); + goto out; + } + + if ((sched->show_migrations || sched->pre_migrations) && + perf_session__set_tracepoints_handlers(session, migrate_handlers)) + goto out; + + /* pre-allocate struct for per-CPU idle stats */ + sched->max_cpu.cpu = env->nr_cpus_online; + if (sched->max_cpu.cpu == 0) + sched->max_cpu.cpu = 4; + if (init_idle_threads(sched->max_cpu.cpu)) + goto out; + + /* summary_only implies summary option, but don't overwrite summary if set */ + if (sched->summary_only) + sched->summary = sched->summary_only; + + if (!sched->summary_only) + timehist_header(sched); + + err = perf_session__process_events(session); + if (err) { + pr_err("Failed to process events, error %d", err); + goto out; + } + + sched->nr_events = evlist->stats.nr_events[0]; + sched->nr_lost_events = evlist->stats.total_lost; + sched->nr_lost_chunks = evlist->stats.nr_events[PERF_RECORD_LOST]; + + if (sched->summary) + timehist_print_summary(sched, session); + +out: + free_idle_threads(); perf_session__delete(session); - return -1; + + return err; } + static void print_bad_events(struct perf_sched *sched) { if (sched->nr_unordered_timestamps && sched->nr_timestamps) { @@ -1505,14 +3402,6 @@ static void print_bad_events(struct perf_sched *sched) (double)sched->nr_lost_events/(double)sched->nr_events * 100.0, sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks); } - if (sched->nr_state_machine_bugs && sched->nr_timestamps) { - printf(" INFO: %.3f%% state machine bugs (%ld out of %ld)", - (double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0, - sched->nr_state_machine_bugs, sched->nr_timestamps); - if (sched->nr_lost_events) - printf(" (due to lost events?)"); - printf("\n"); - } if (sched->nr_context_switch_bugs && sched->nr_timestamps) { printf(" INFO: %.3f%% context switch bugs (%ld out of %ld)", (double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0, @@ -1523,21 +3412,109 @@ static void print_bad_events(struct perf_sched *sched) } } +static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *data) +{ + struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL; + struct work_atoms *this; + const char *comm = thread__comm_str(data->thread), *this_comm; + bool leftmost = true; + + while (*new) { + int cmp; + + this = container_of(*new, struct work_atoms, node); + parent = *new; + + this_comm = thread__comm_str(this->thread); + cmp = strcmp(comm, this_comm); + if (cmp > 0) { + new = &((*new)->rb_left); + } else if (cmp < 0) { + new = &((*new)->rb_right); + leftmost = false; + } else { + this->num_merged++; + this->total_runtime += data->total_runtime; + this->nb_atoms += data->nb_atoms; + this->total_lat += data->total_lat; + list_splice_init(&data->work_list, &this->work_list); + if (this->max_lat < data->max_lat) { + this->max_lat = data->max_lat; + this->max_lat_start = data->max_lat_start; + this->max_lat_end = data->max_lat_end; + } + free_work_atoms(data); + return; + } + } + + data->num_merged++; + rb_link_node(&data->node, parent, new); + rb_insert_color_cached(&data->node, root, leftmost); +} + +static void perf_sched__merge_lat(struct perf_sched *sched) +{ + struct work_atoms *data; + struct rb_node *node; + + if (sched->skip_merge) + return; + + while ((node = rb_first_cached(&sched->atom_root))) { + rb_erase_cached(node, &sched->atom_root); + data = rb_entry(node, struct work_atoms, node); + __merge_work_atoms(&sched->merged_atom_root, data); + } +} + +static int setup_cpus_switch_event(struct perf_sched *sched) +{ + unsigned int i; + + sched->cpu_last_switched = calloc(MAX_CPUS, sizeof(*(sched->cpu_last_switched))); + if (!sched->cpu_last_switched) + return -1; + + sched->curr_pid = malloc(MAX_CPUS * sizeof(*(sched->curr_pid))); + if (!sched->curr_pid) { + zfree(&sched->cpu_last_switched); + return -1; + } + + for (i = 0; i < MAX_CPUS; i++) + sched->curr_pid[i] = -1; + + return 0; +} + +static void free_cpus_switch_event(struct perf_sched *sched) +{ + zfree(&sched->curr_pid); + zfree(&sched->cpu_last_switched); +} + static int perf_sched__lat(struct perf_sched *sched) { + int rc = -1; struct rb_node *next; - struct perf_session *session; setup_pager(); - if (perf_sched__read_events(sched, false, &session)) - return -1; + + if (setup_cpus_switch_event(sched)) + return rc; + + if (perf_sched__read_events(sched)) + goto out_free_cpus_switch_event; + + perf_sched__merge_lat(sched); perf_sched__sort_lat(sched); - printf("\n ---------------------------------------------------------------------------------------------------------------\n"); - printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); - printf(" ---------------------------------------------------------------------------------------------------------------\n"); + printf("\n -------------------------------------------------------------------------------------------------------------------------------------------\n"); + printf(" Task | Runtime ms | Count | Avg delay ms | Max delay ms | Max delay start | Max delay end |\n"); + printf(" -------------------------------------------------------------------------------------------------------------------------------------------\n"); - next = rb_first(&sched->sorted_atom_root); + next = rb_first_cached(&sched->sorted_atom_root); while (next) { struct work_atoms *work_list; @@ -1547,41 +3524,161 @@ static int perf_sched__lat(struct perf_sched *sched) next = rb_next(next); } - printf(" -----------------------------------------------------------------------------------------\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n", - (double)sched->all_runtime / 1e6, sched->all_count); + (double)sched->all_runtime / NSEC_PER_MSEC, sched->all_count); printf(" ---------------------------------------------------\n"); print_bad_events(sched); printf("\n"); - perf_session__delete(session); + rc = 0; + + while ((next = rb_first_cached(&sched->sorted_atom_root))) { + struct work_atoms *data; + + data = rb_entry(next, struct work_atoms, node); + rb_erase_cached(next, &sched->sorted_atom_root); + free_work_atoms(data); + } +out_free_cpus_switch_event: + free_cpus_switch_event(sched); + return rc; +} + +static int setup_map_cpus(struct perf_sched *sched) +{ + sched->max_cpu.cpu = sysconf(_SC_NPROCESSORS_CONF); + + if (sched->map.comp) { + sched->map.comp_cpus = zalloc(sched->max_cpu.cpu * sizeof(int)); + if (!sched->map.comp_cpus) + return -1; + } + + if (sched->map.cpus_str) { + sched->map.cpus = perf_cpu_map__new(sched->map.cpus_str); + if (!sched->map.cpus) { + pr_err("failed to get cpus map from %s\n", sched->map.cpus_str); + zfree(&sched->map.comp_cpus); + return -1; + } + } + + return 0; +} + +static int setup_color_pids(struct perf_sched *sched) +{ + struct perf_thread_map *map; + + if (!sched->map.color_pids_str) + return 0; + + map = thread_map__new_by_tid_str(sched->map.color_pids_str); + if (!map) { + pr_err("failed to get thread map from %s\n", sched->map.color_pids_str); + return -1; + } + + sched->map.color_pids = map; + return 0; +} + +static int setup_color_cpus(struct perf_sched *sched) +{ + struct perf_cpu_map *map; + + if (!sched->map.color_cpus_str) + return 0; + + map = perf_cpu_map__new(sched->map.color_cpus_str); + if (!map) { + pr_err("failed to get thread map from %s\n", sched->map.color_cpus_str); + return -1; + } + + sched->map.color_cpus = map; return 0; } static int perf_sched__map(struct perf_sched *sched) { - sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + int rc = -1; + + sched->curr_thread = calloc(MAX_CPUS, sizeof(*(sched->curr_thread))); + if (!sched->curr_thread) + return rc; + + sched->curr_out_thread = calloc(MAX_CPUS, sizeof(*(sched->curr_out_thread))); + if (!sched->curr_out_thread) + goto out_free_curr_thread; + + if (setup_cpus_switch_event(sched)) + goto out_free_curr_out_thread; + + if (setup_map_cpus(sched)) + goto out_free_cpus_switch_event; + + if (setup_color_pids(sched)) + goto out_put_map_cpus; + + if (setup_color_cpus(sched)) + goto out_put_color_pids; setup_pager(); - if (perf_sched__read_events(sched, true, NULL)) - return -1; + if (perf_sched__read_events(sched)) + goto out_put_color_cpus; + + rc = 0; print_bad_events(sched); - return 0; + +out_put_color_cpus: + perf_cpu_map__put(sched->map.color_cpus); + +out_put_color_pids: + perf_thread_map__put(sched->map.color_pids); + +out_put_map_cpus: + zfree(&sched->map.comp_cpus); + perf_cpu_map__put(sched->map.cpus); + +out_free_cpus_switch_event: + free_cpus_switch_event(sched); + +out_free_curr_out_thread: + for (int i = 0; i < MAX_CPUS; i++) + thread__put(sched->curr_out_thread[i]); + zfree(&sched->curr_out_thread); + +out_free_curr_thread: + for (int i = 0; i < MAX_CPUS; i++) + thread__put(sched->curr_thread[i]); + zfree(&sched->curr_thread); + return rc; } static int perf_sched__replay(struct perf_sched *sched) { + int ret; unsigned long i; + mutex_init(&sched->start_work_mutex); + mutex_init(&sched->work_done_wait_mutex); + + ret = setup_cpus_switch_event(sched); + if (ret) + goto out_mutex_destroy; + calibrate_run_measurement_overhead(sched); calibrate_sleep_measurement_overhead(sched); test_calibrations(sched); - if (perf_sched__read_events(sched, true, NULL)) - return -1; + ret = perf_sched__read_events(sched); + if (ret) + goto out_free_cpus_switch_event; printf("nr_run_events: %ld\n", sched->nr_run_events); printf("nr_sleep_events: %ld\n", sched->nr_sleep_events); @@ -1598,12 +3695,25 @@ static int perf_sched__replay(struct perf_sched *sched) print_task_traces(sched); add_cross_task_wakeups(sched); + sched->thread_funcs_exit = false; create_tasks(sched); printf("------------------------------------------------------------\n"); + if (sched->replay_repeat == 0) + sched->replay_repeat = UINT_MAX; + for (i = 0; i < sched->replay_repeat; i++) run_one_test(sched); - return 0; + sched->thread_funcs_exit = true; + destroy_tasks(sched); + +out_free_cpus_switch_event: + free_cpus_switch_event(sched); + +out_mutex_destroy: + mutex_destroy(&sched->start_work_mutex); + mutex_destroy(&sched->work_done_wait_mutex); + return ret; } static void setup_sorting(struct perf_sched *sched, const struct option *options, @@ -1614,8 +3724,8 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { if (sort_dimension__add(tok, &sched->sort_list) < 0) { - error("Unknown --sort key: `%s'", tok); - usage_with_options(usage_msg, options); + usage_with_options_msg(usage_msg, options, + "Unknown --sort key: `%s'", tok); } } @@ -1624,10 +3734,21 @@ static void setup_sorting(struct perf_sched *sched, const struct option *options sort_dimension__add("pid", &sched->cmp_pid); } +static bool schedstat_events_exposed(void) +{ + /* + * Select "sched:sched_stat_wait" event to check + * whether schedstat tracepoints are exposed. + */ + return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ? + false : true; +} + static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; - const char **rec_argv; + char **rec_argv; + const char **rec_argv_copy; const char * const record_args[] = { "record", "-a", @@ -1635,84 +3756,161 @@ static int __cmd_record(int argc, const char **argv) "-m", "1024", "-c", "1", "-e", "sched:sched_switch", - "-e", "sched:sched_stat_wait", - "-e", "sched:sched_stat_sleep", - "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", - "-e", "sched:sched_process_exit", "-e", "sched:sched_process_fork", - "-e", "sched:sched_wakeup", + "-e", "sched:sched_wakeup_new", "-e", "sched:sched_migrate_task", }; - rec_argc = ARRAY_SIZE(record_args) + argc - 1; - rec_argv = calloc(rec_argc + 1, sizeof(char *)); + /* + * The tracepoints trace_sched_stat_{wait, sleep, iowait} + * are not exposed to user if CONFIG_SCHEDSTATS is not set, + * to prevent "perf sched record" execution failure, determine + * whether to record schedstat events according to actual situation. + */ + const char * const schedstat_args[] = { + "-e", "sched:sched_stat_wait", + "-e", "sched:sched_stat_sleep", + "-e", "sched:sched_stat_iowait", + }; + unsigned int schedstat_argc = schedstat_events_exposed() ? + ARRAY_SIZE(schedstat_args) : 0; + struct tep_event *waking_event; + int ret; + + /* + * +2 for either "-e", "sched:sched_wakeup" or + * "-e", "sched:sched_waking" + */ + rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) return -ENOMEM; + rec_argv_copy = calloc(rec_argc + 1, sizeof(char *)); + if (rec_argv_copy == NULL) { + free(rec_argv); + return -ENOMEM; + } for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = strdup(record_args[i]); + rec_argv[i++] = strdup("-e"); + waking_event = trace_event__tp_format("sched", "sched_waking"); + if (!IS_ERR(waking_event)) + rec_argv[i++] = strdup("sched:sched_waking"); + else + rec_argv[i++] = strdup("sched:sched_wakeup"); + + for (j = 0; j < schedstat_argc; j++) + rec_argv[i++] = strdup(schedstat_args[j]); + for (j = 1; j < (unsigned int)argc; j++, i++) - rec_argv[i] = argv[j]; + rec_argv[i] = strdup(argv[j]); BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv, NULL); + memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc); + ret = cmd_record(rec_argc, rec_argv_copy); + + for (i = 0; i < rec_argc; i++) + free(rec_argv[i]); + free(rec_argv); + free(rec_argv_copy); + + return ret; } -int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_sched(int argc, const char **argv) { - const char default_sort_order[] = "avg, max, switch, runtime"; + static const char default_sort_order[] = "avg, max, switch, runtime"; struct perf_sched sched = { - .tool = { - .sample = perf_sched__process_tracepoint_sample, - .comm = perf_event__process_comm, - .lost = perf_event__process_lost, - .fork = perf_event__process_fork, - .ordered_samples = true, - }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), .sort_list = LIST_HEAD_INIT(sched.sort_list), - .start_work_mutex = PTHREAD_MUTEX_INITIALIZER, - .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER, - .curr_pid = { [0 ... MAX_CPUS - 1] = -1 }, .sort_order = default_sort_order, .replay_repeat = 10, .profile_cpu = -1, .next_shortname1 = 'A', .next_shortname2 = '0', + .skip_merge = 0, + .show_callchain = 1, + .max_stack = 5, }; - const struct option latency_options[] = { - OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]", - "sort by key(s): runtime, switch, avg, max"), + const struct option sched_options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), - OPT_INTEGER('C', "CPU", &sched.profile_cpu, - "CPU to profile on"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN('f', "force", &sched.force, "don't complain, do it"), OPT_END() }; + const struct option latency_options[] = { + OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]", + "sort by key(s): runtime, switch, avg, max"), + OPT_INTEGER('C', "CPU", &sched.profile_cpu, + "CPU to profile on"), + OPT_BOOLEAN('p', "pids", &sched.skip_merge, + "latency stats per pid instead of per comm"), + OPT_PARENT(sched_options) + }; const struct option replay_options[] = { OPT_UINTEGER('r', "repeat", &sched.replay_repeat, - "repeat the workload replay N times (-1: infinite)"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, - "dump raw trace in ASCII"), - OPT_END() + "repeat the workload replay N times (0: infinite)"), + OPT_PARENT(sched_options) }; - const struct option sched_options[] = { - OPT_STRING('i', "input", &input_name, "file", - "input file name"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, - "dump raw trace in ASCII"), - OPT_END() + const struct option map_options[] = { + OPT_BOOLEAN(0, "compact", &sched.map.comp, + "map output in compact mode"), + OPT_STRING(0, "color-pids", &sched.map.color_pids_str, "pids", + "highlight given pids in map"), + OPT_STRING(0, "color-cpus", &sched.map.color_cpus_str, "cpus", + "highlight given CPUs in map"), + OPT_STRING(0, "cpus", &sched.map.cpus_str, "cpus", + "display given CPUs in map"), + OPT_STRING(0, "task-name", &sched.map.task_name, "task", + "map output only for the given task name(s)."), + OPT_BOOLEAN(0, "fuzzy-name", &sched.map.fuzzy, + "given command name can be partially matched (fuzzy matching)"), + OPT_PARENT(sched_options) }; + const struct option timehist_options[] = { + OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), + OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, + "file", "kallsyms pathname"), + OPT_BOOLEAN('g', "call-graph", &sched.show_callchain, + "Display call chains if present (default on)"), + OPT_UINTEGER(0, "max-stack", &sched.max_stack, + "Maximum number of functions to display backtrace."), + OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", + "Look for files with symbols relative to this directory"), + OPT_BOOLEAN('s', "summary", &sched.summary_only, + "Show only syscall summary with statistics"), + OPT_BOOLEAN('S', "with-summary", &sched.summary, + "Show all syscalls and summary with statistics"), + OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"), + OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"), + OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"), + OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"), + OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"), + OPT_STRING(0, "time", &sched.time_str, "str", + "Time span for analysis (start,stop)"), + OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"), + OPT_STRING('p', "pid", &symbol_conf.pid_list_str, "pid[,pid...]", + "analyze events only for given process id(s)"), + OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]", + "analyze events only for given thread id(s)"), + OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), + OPT_BOOLEAN(0, "show-prio", &sched.show_prio, "Show task priority"), + OPT_STRING(0, "prio", &sched.prio_str, "prio", + "analyze events only for given task priority(ies)"), + OPT_BOOLEAN('P', "pre-migrations", &sched.pre_migrations, "Show pre-migration wait time"), + OPT_PARENT(sched_options) + }; + const char * const latency_usage[] = { "perf sched latency [<options>]", NULL @@ -1721,15 +3919,25 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) "perf sched replay [<options>]", NULL }; - const char * const sched_usage[] = { - "perf sched [<options>] {record|latency|map|replay|script}", + const char * const map_usage[] = { + "perf sched map [<options>]", + NULL + }; + const char * const timehist_usage[] = { + "perf sched timehist [<options>]", + NULL + }; + const char *const sched_subcommands[] = { "record", "latency", "map", + "replay", "script", + "timehist", NULL }; + const char *sched_usage[] = { + NULL, NULL }; struct trace_sched_handler lat_ops = { .wakeup_event = latency_wakeup_event, .switch_event = latency_switch_event, .runtime_event = latency_runtime_event, - .fork_event = latency_fork_event, .migrate_task_event = latency_migrate_task_event, }; struct trace_sched_handler map_ops = { @@ -1740,22 +3948,30 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .switch_event = replay_switch_event, .fork_event = replay_fork_event, }; + int ret; - argc = parse_options(argc, argv, sched_options, sched_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + perf_tool__init(&sched.tool, /*ordered_events=*/true); + sched.tool.sample = perf_sched__process_tracepoint_sample; + sched.tool.comm = perf_sched__process_comm; + sched.tool.namespaces = perf_event__process_namespaces; + sched.tool.lost = perf_event__process_lost; + sched.tool.fork = perf_sched__process_fork_event; + + argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands, + sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(sched_usage, sched_options); + thread__set_priv_destructor(free); + /* * Aliased to 'perf script' for now: */ - if (!strcmp(argv[0], "script")) - return cmd_script(argc, argv, prefix); - - symbol__init(); - if (!strncmp(argv[0], "rec", 3)) { - return __cmd_record(argc, argv); - } else if (!strncmp(argv[0], "lat", 3)) { + if (!strcmp(argv[0], "script")) { + ret = cmd_script(argc, argv); + } else if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { + ret = __cmd_record(argc, argv); + } else if (strlen(argv[0]) > 2 && strstarts("latency", argv[0])) { sched.tp_handler = &lat_ops; if (argc > 1) { argc = parse_options(argc, argv, latency_options, latency_usage, 0); @@ -1763,22 +3979,61 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(latency_usage, latency_options); } setup_sorting(&sched, latency_options, latency_usage); - return perf_sched__lat(&sched); + ret = perf_sched__lat(&sched); } else if (!strcmp(argv[0], "map")) { + if (argc) { + argc = parse_options(argc, argv, map_options, map_usage, 0); + if (argc) + usage_with_options(map_usage, map_options); + + if (sched.map.task_name) { + sched.map.task_names = strlist__new(sched.map.task_name, NULL); + if (sched.map.task_names == NULL) { + fprintf(stderr, "Failed to parse task names\n"); + ret = -1; + goto out; + } + } + } sched.tp_handler = &map_ops; setup_sorting(&sched, latency_options, latency_usage); - return perf_sched__map(&sched); - } else if (!strncmp(argv[0], "rep", 3)) { + ret = perf_sched__map(&sched); + } else if (strlen(argv[0]) > 2 && strstarts("replay", argv[0])) { sched.tp_handler = &replay_ops; if (argc) { argc = parse_options(argc, argv, replay_options, replay_usage, 0); if (argc) usage_with_options(replay_usage, replay_options); } - return perf_sched__replay(&sched); + ret = perf_sched__replay(&sched); + } else if (!strcmp(argv[0], "timehist")) { + if (argc) { + argc = parse_options(argc, argv, timehist_options, + timehist_usage, 0); + if (argc) + usage_with_options(timehist_usage, timehist_options); + } + if ((sched.show_wakeups || sched.show_next) && + sched.summary_only) { + pr_err(" Error: -s and -[n|w] are mutually exclusive.\n"); + parse_options_usage(timehist_usage, timehist_options, "s", true); + if (sched.show_wakeups) + parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_next) + parse_options_usage(NULL, timehist_options, "n", true); + ret = -EINVAL; + goto out; + } + ret = symbol__validate_sym_arguments(); + if (!ret) + ret = perf_sched__timehist(&sched); } else { usage_with_options(sched_usage, sched_options); } - return 0; +out: + /* free usage string allocated by parse_options_subcommand */ + free((void *)sched_usage[0]); + + return ret; } |