diff --git a/fs/proc/base.c b/fs/proc/base.c index 8e7e61b28f31..03deeac1e835 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2179,7 +2179,7 @@ static const struct file_operations proc_map_files_operations = { .llseek = generic_file_llseek, }; -#ifdef CONFIG_CHECKPOINT_RESTORE +#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; @@ -2936,7 +2936,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif -#ifdef CONFIG_CHECKPOINT_RESTORE +#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), diff --git a/include/linux/delay.h b/include/linux/delay.h index a6ecb34cf547..2ecb3c46b20a 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -5,6 +5,17 @@ * Copyright (C) 1993 Linus Torvalds * * Delay routines, using a pre-computed "loops_per_jiffy" value. + * + * Please note that ndelay(), udelay() and mdelay() may return early for + * several reasons: + * 1. computed loops_per_jiffy too low (due to the time taken to + * execute the timer interrupt.) + * 2. cache behaviour affecting the time it takes to execute the + * loop function. + * 3. CPU clock rate changes. + * + * Please see this thread: + * http://lists.openwall.net/linux-kernel/2011/01/09/56 */ #include diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 325f649d77ff..3a85d61f7614 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -42,6 +42,27 @@ extern struct fs_struct init_fs; #define INIT_PREV_CPUTIME(x) #endif +#ifdef CONFIG_POSIX_TIMERS +#define INIT_POSIX_TIMERS(s) \ + .posix_timers = LIST_HEAD_INIT(s.posix_timers), +#define INIT_CPU_TIMERS(s) \ + .cpu_timers = { \ + LIST_HEAD_INIT(s.cpu_timers[0]), \ + LIST_HEAD_INIT(s.cpu_timers[1]), \ + LIST_HEAD_INIT(s.cpu_timers[2]), \ + }, +#define INIT_CPUTIMER(s) \ + .cputimer = { \ + .cputime_atomic = INIT_CPUTIME_ATOMIC, \ + .running = false, \ + .checking_timer = false, \ + }, +#else +#define INIT_POSIX_TIMERS(s) +#define INIT_CPU_TIMERS(s) +#define INIT_CPUTIMER(s) +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \ @@ -49,14 +70,10 @@ extern struct fs_struct init_fs; .shared_pending = { \ .list = LIST_HEAD_INIT(sig.shared_pending.list), \ .signal = {{0}}}, \ - .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ - .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ + INIT_POSIX_TIMERS(sig) \ + INIT_CPU_TIMERS(sig) \ .rlim = INIT_RLIMITS, \ - .cputimer = { \ - .cputime_atomic = INIT_CPUTIME_ATOMIC, \ - .running = false, \ - .checking_timer = false, \ - }, \ + INIT_CPUTIMER(sig) \ INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ @@ -247,7 +264,7 @@ extern struct task_group root_task_group; .blocked = {{0}}, \ .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ .journal_info = NULL, \ - .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + INIT_CPU_TIMERS(tsk) \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ @@ -274,13 +291,6 @@ extern struct task_group root_task_group; } -#define INIT_CPU_TIMERS(cpu_timers) \ -{ \ - LIST_HEAD_INIT(cpu_timers[0]), \ - LIST_HEAD_INIT(cpu_timers[1]), \ - LIST_HEAD_INIT(cpu_timers[2]), \ -} - /* Attach to the init_task data structure for proper alignment */ #define __init_task_data __attribute__((__section__(".data..init_task"))) diff --git a/include/linux/sched.h b/include/linux/sched.h index ad3ec9ec61f7..6e4782eae076 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -734,13 +734,14 @@ struct signal_struct { unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; +#ifdef CONFIG_POSIX_TIMERS + /* POSIX.1b Interval Timers */ int posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; - struct pid *leader_pid; ktime_t it_real_incr; /* @@ -759,12 +760,16 @@ struct signal_struct { /* Earliest-expiration cache. */ struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; + +#endif + + struct pid *leader_pid; + #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif - struct list_head cpu_timers[3]; - struct pid *tty_old_pgrp; /* boolean value for session group leader */ @@ -1691,8 +1696,10 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; +#ifdef CONFIG_POSIX_TIMERS struct task_cputime cputime_expires; struct list_head cpu_timers[3]; +#endif /* process credentials */ const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */ diff --git a/kernel/fork.c b/kernel/fork.c index 11c5c8ab827c..105c6676d93b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1304,6 +1304,7 @@ void __cleanup_sighand(struct sighand_struct *sighand) } } +#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a thread group. */ @@ -1322,6 +1323,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) INIT_LIST_HEAD(&sig->cpu_timers[1]); INIT_LIST_HEAD(&sig->cpu_timers[2]); } +#else +static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { } +#endif static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { @@ -1346,11 +1350,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); - INIT_LIST_HEAD(&sig->posix_timers); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS + INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif @@ -1425,6 +1429,7 @@ static void rt_mutex_init_task(struct task_struct *p) #endif } +#ifdef CONFIG_POSIX_TIMERS /* * Initialize POSIX timer handling for a single task. */ @@ -1437,6 +1442,9 @@ static void posix_cpu_timers_init(struct task_struct *tsk) INIT_LIST_HEAD(&tsk->cpu_timers[1]); INIT_LIST_HEAD(&tsk->cpu_timers[2]); } +#else +static inline void posix_cpu_timers_init(struct task_struct *tsk) { } +#endif static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2516b8df6dbb..a688a8206727 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2246,6 +2246,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) } } +#ifdef CONFIG_POSIX_TIMERS static void watchdog(struct rq *rq, struct task_struct *p) { unsigned long soft, hard; @@ -2267,6 +2268,9 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } +#else +static inline void watchdog(struct rq *rq, struct task_struct *p) { } +#endif static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) { diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 34659a853505..c69a9870ab79 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -172,18 +172,19 @@ sched_info_switch(struct rq *rq, */ /** - * cputimer_running - return true if cputimer is running + * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running * * @tsk: Pointer to target task. */ -static inline bool cputimer_running(struct task_struct *tsk) - +#ifdef CONFIG_POSIX_TIMERS +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; /* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(cputimer->running)) - return false; + return NULL; /* * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime @@ -200,10 +201,17 @@ static inline bool cputimer_running(struct task_struct *tsk) * clock delta is behind the expiring timer value. */ if (unlikely(!tsk->sighand)) - return false; + return NULL; - return true; + return cputimer; } +#else +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + return NULL; +} +#endif /** * account_group_user_time - Maintain utime for a thread group. @@ -218,9 +226,9 @@ static inline bool cputimer_running(struct task_struct *tsk) static inline void account_group_user_time(struct task_struct *tsk, cputime_t cputime) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.utime); @@ -239,9 +247,9 @@ static inline void account_group_user_time(struct task_struct *tsk, static inline void account_group_system_time(struct task_struct *tsk, cputime_t cputime) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.stime); @@ -260,9 +268,9 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); - if (!cputimer_running(tsk)) + if (!cputimer) return; atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index db087d7e106d..95b258dd75db 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1275,27 +1275,8 @@ int timekeeping_inject_offset(struct timespec *ts) } EXPORT_SYMBOL(timekeeping_inject_offset); - /** - * timekeeping_get_tai_offset - Returns current TAI offset from UTC - * - */ -s32 timekeeping_get_tai_offset(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned int seq; - s32 ret; - - do { - seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tai_offset; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - return ret; -} - -/** - * __timekeeping_set_tai_offset - Lock free worker function + * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic * */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) @@ -1304,24 +1285,6 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } -/** - * timekeeping_set_tai_offset - Sets the current TAI offset from UTC - * - */ -void timekeeping_set_tai_offset(s32 tai_offset) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; - - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - __timekeeping_set_tai_offset(tk, tai_offset); - timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - clock_was_set(); -} - /** * change_clocksource - Swaps clocksources if a new one is available * diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 704f595ce83f..d0914676d4c5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -11,8 +11,6 @@ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); extern int timekeeping_inject_offset(struct timespec *ts); -extern s32 timekeeping_get_tai_offset(void); -extern void timekeeping_set_tai_offset(s32 tai_offset); extern int timekeeping_suspend(void); extern void timekeeping_resume(void);