From da7bd0a9e0fce9f293b6e30c003f8f3978cee923 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 14 Oct 2024 10:22:19 +0200 Subject: timers: Move *sleep*() and timeout functions into a separate file All schedule_timeout() and *sleep*() related functions are interfaces on top of timer list timers and hrtimers to add a sleep to the code. As they are built on top of the timer list timers and hrtimers, the [hr]timer interfaces are already used except when queuing the timer in schedule_timeout(). But there exists the appropriate interface add_timer() which does the same job with an extra check for an already pending timer. Split all those functions as they are into a separate file and use add_timer() instead of __mod_timer() in schedule_timeout(). While at it fix minor formatting issues and a multi line printk function call in schedule_timeout(). Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241014-devel-anna-maria-b4-timers-flseep-v3-2-dc8b907cb62f@linutronix.de --- kernel/time/timer.c | 192 ---------------------------------------------------- 1 file changed, 192 deletions(-) (limited to 'kernel/time/timer.c') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 0fc9d066a7be..02355b275bab 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -2526,141 +2525,6 @@ void update_process_times(int user_tick) run_posix_cpu_timers(); } -/* - * Since schedule_timeout()'s timer is defined on the stack, it must store - * the target task on the stack as well. - */ -struct process_timer { - struct timer_list timer; - struct task_struct *task; -}; - -static void process_timeout(struct timer_list *t) -{ - struct process_timer *timeout = from_timer(timeout, t, timer); - - wake_up_process(timeout->task); -} - -/** - * schedule_timeout - sleep until timeout - * @timeout: timeout value in jiffies - * - * Make the current task sleep until @timeout jiffies have elapsed. - * The function behavior depends on the current task state - * (see also set_current_state() description): - * - * %TASK_RUNNING - the scheduler is called, but the task does not sleep - * at all. That happens because sched_submit_work() does nothing for - * tasks in %TASK_RUNNING state. - * - * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to - * pass before the routine returns unless the current task is explicitly - * woken up, (e.g. by wake_up_process()). - * - * %TASK_INTERRUPTIBLE - the routine may return early if a signal is - * delivered to the current task or the current task is explicitly woken - * up. - * - * The current task state is guaranteed to be %TASK_RUNNING when this - * routine returns. - * - * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule - * the CPU away without a bound on the timeout. In this case the return - * value will be %MAX_SCHEDULE_TIMEOUT. - * - * Returns 0 when the timer has expired otherwise the remaining time in - * jiffies will be returned. In all cases the return value is guaranteed - * to be non-negative. - */ -signed long __sched schedule_timeout(signed long timeout) -{ - struct process_timer timer; - unsigned long expire; - - switch (timeout) - { - case MAX_SCHEDULE_TIMEOUT: - /* - * These two special cases are useful to be comfortable - * in the caller. Nothing more. We could take - * MAX_SCHEDULE_TIMEOUT from one of the negative value - * but I' d like to return a valid offset (>=0) to allow - * the caller to do everything it want with the retval. - */ - schedule(); - goto out; - default: - /* - * Another bit of PARANOID. Note that the retval will be - * 0 since no piece of kernel is supposed to do a check - * for a negative retval of schedule_timeout() (since it - * should never happens anyway). You just have the printk() - * that will tell you if something is gone wrong and where. - */ - if (timeout < 0) { - printk(KERN_ERR "schedule_timeout: wrong timeout " - "value %lx\n", timeout); - dump_stack(); - __set_current_state(TASK_RUNNING); - goto out; - } - } - - expire = timeout + jiffies; - - timer.task = current; - timer_setup_on_stack(&timer.timer, process_timeout, 0); - __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); - schedule(); - del_timer_sync(&timer.timer); - - /* Remove the timer from the object tracker */ - destroy_timer_on_stack(&timer.timer); - - timeout = expire - jiffies; - - out: - return timeout < 0 ? 0 : timeout; -} -EXPORT_SYMBOL(schedule_timeout); - -/* - * We can use __set_current_state() here because schedule_timeout() calls - * schedule() unconditionally. - */ -signed long __sched schedule_timeout_interruptible(signed long timeout) -{ - __set_current_state(TASK_INTERRUPTIBLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_interruptible); - -signed long __sched schedule_timeout_killable(signed long timeout) -{ - __set_current_state(TASK_KILLABLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_killable); - -signed long __sched schedule_timeout_uninterruptible(signed long timeout) -{ - __set_current_state(TASK_UNINTERRUPTIBLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_uninterruptible); - -/* - * Like schedule_timeout_uninterruptible(), except this task will not contribute - * to load average. - */ -signed long __sched schedule_timeout_idle(signed long timeout) -{ - __set_current_state(TASK_IDLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_idle); - #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { @@ -2757,59 +2621,3 @@ void __init init_timers(void) posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } - -/** - * msleep - sleep safely even with waitqueue interruptions - * @msecs: Time in milliseconds to sleep for - */ -void msleep(unsigned int msecs) -{ - unsigned long timeout = msecs_to_jiffies(msecs); - - while (timeout) - timeout = schedule_timeout_uninterruptible(timeout); -} - -EXPORT_SYMBOL(msleep); - -/** - * msleep_interruptible - sleep waiting for signals - * @msecs: Time in milliseconds to sleep for - */ -unsigned long msleep_interruptible(unsigned int msecs) -{ - unsigned long timeout = msecs_to_jiffies(msecs); - - while (timeout && !signal_pending(current)) - timeout = schedule_timeout_interruptible(timeout); - return jiffies_to_msecs(timeout); -} - -EXPORT_SYMBOL(msleep_interruptible); - -/** - * usleep_range_state - Sleep for an approximate time in a given state - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep - * @state: State of the current task that will be while sleeping - * - * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range_state() instead of udelay(). The sleep improves responsiveness - * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces - * power usage by allowing hrtimers to take advantage of an already- - * scheduled interrupt instead of scheduling a new one just for this sleep. - */ -void __sched usleep_range_state(unsigned long min, unsigned long max, - unsigned int state) -{ - ktime_t exp = ktime_add_us(ktime_get(), min); - u64 delta = (u64)(max - min) * NSEC_PER_USEC; - - for (;;) { - __set_current_state(state); - /* Do not return before the requested sleep time has elapsed */ - if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) - break; - } -} -EXPORT_SYMBOL(usleep_range_state); -- cgit v1.2.3 From 1d4199cbbe95efaba51304cfd844bd0ccd224e61 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 30 Oct 2024 08:53:51 +0100 Subject: timers: Add missing READ_ONCE() in __run_timer_base() __run_timer_base() checks base::next_expiry without holding base::lock. That can race with a remote CPU updating next_expiry under the lock. This is an intentional and harmless data race, but lacks a READ_ONCE(), so KCSAN complains about this. Add the missing READ_ONCE(). All other places are covered already. Fixes: 79f8b28e85f8 ("timers: Annotate possible non critical data race of next_expiry") Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/87a5emyqk0.ffs@tglx Closes: https://lore.kernel.org/oe-lkp/202410301205.ef8e9743-lkp@intel.com --- kernel/time/timer.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/time/timer.c') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 02355b275bab..a283e524835d 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2421,7 +2421,8 @@ static inline void __run_timers(struct timer_base *base) static void __run_timer_base(struct timer_base *base) { - if (time_before(jiffies, base->next_expiry)) + /* Can race against a remote CPU updating next_expiry under the lock */ + if (time_before(jiffies, READ_ONCE(base->next_expiry))) return; timer_base_lock_expiry(base); -- cgit v1.2.3