// SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #include "timer_migration.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> __visible u64 jiffies_64 __cacheline_aligned_in_smp = …; EXPORT_SYMBOL(…); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT … #define LVL_CLK_DIV … #define LVL_CLK_MASK … #define LVL_SHIFT(n) … #define LVL_GRAN(n) … /* * The time start value for each level to select the bucket at enqueue * time. We start from the last possible delta of the previous level * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()). */ #define LVL_START(n) … /* Size of each clock level */ #define LVL_BITS … #define LVL_SIZE … #define LVL_MASK … #define LVL_OFFS(n) … /* Level depth */ #if HZ > 100 #define LVL_DEPTH … # else #define LVL_DEPTH … #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF … #define WHEEL_TIMEOUT_MAX … /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE … #ifdef CONFIG_NO_HZ_COMMON /* * If multiple bases need to be locked, use the base ordering for lock * nesting, i.e. lowest number first. */ #define NR_BASES … #define BASE_LOCAL … #define BASE_GLOBAL … #define BASE_DEF … #else #define NR_BASES … #define BASE_LOCAL … #define BASE_GLOBAL … #define BASE_DEF … #endif /** * struct timer_base - Per CPU timer base (number of base depends on config) * @lock: Lock protecting the timer_base * @running_timer: When expiring timers, the lock is dropped. To make * sure not to race against deleting/modifying a * currently running timer, the pointer is set to the * timer, which expires at the moment. If no timer is * running, the pointer is NULL. * @expiry_lock: PREEMPT_RT only: Lock is taken in softirq around * timer expiry callback execution and when trying to * delete a running timer and it wasn't successful in * the first glance. It prevents priority inversion * when callback was preempted on a remote CPU and a * caller tries to delete the running timer. It also * prevents a life lock, when the task which tries to * delete a timer preempted the softirq thread which * is running the timer callback function. * @timer_waiters: PREEMPT_RT only: Tells, if there is a waiter * waiting for the end of the timer callback function * execution. * @clk: clock of the timer base; is updated before enqueue * of a timer; during expiry, it is 1 offset ahead of * jiffies to avoid endless requeuing to current * jiffies * @next_expiry: expiry value of the first timer; it is updated when * finding the next timer and during enqueue; the * value is not valid, when next_expiry_recalc is set * @cpu: Number of CPU the timer base belongs to * @next_expiry_recalc: States, whether a recalculation of next_expiry is * required. Value is set true, when a timer was * deleted. * @is_idle: Is set, when timer_base is idle. It is triggered by NOHZ * code. This state is only used in standard * base. Deferrable timers, which are enqueued remotely * never wake up an idle CPU. So no matter of supporting it * for this base. * @timers_pending: Is set, when a timer is pending in the base. It is only * reliable when next_expiry_recalc is not set. * @pending_map: bitmap of the timer wheel; each bit reflects a * bucket of the wheel. When a bit is set, at least a * single timer is enqueued in the related bucket. * @vectors: Array of lists; Each array member reflects a bucket * of the timer wheel. The list contains all timers * which are enqueued into a specific bucket. */ struct timer_base { … } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP static unsigned int sysctl_timer_migration = …; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { … } #ifdef CONFIG_SYSCTL static int timer_migration_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { … } static struct ctl_table timer_sysctl[] = …; static int __init timer_sysctl_init(void) { … } device_initcall(timer_sysctl_init); #endif /* CONFIG_SYSCTL */ #else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { … } void timers_update_nohz(void) { … } static inline bool is_timers_nohz_active(void) { … } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { … } /** * __round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies(unsigned long j, int cpu) { … } EXPORT_SYMBOL_GPL(…); /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { … } EXPORT_SYMBOL_GPL(…); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { … } EXPORT_SYMBOL_GPL(…); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { … } EXPORT_SYMBOL_GPL(…); /** * __round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up(unsigned long j, int cpu) { … } EXPORT_SYMBOL_GPL(…); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { … } EXPORT_SYMBOL_GPL(…); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { … } EXPORT_SYMBOL_GPL(…); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { … } EXPORT_SYMBOL_GPL(…); static inline unsigned int timer_get_idx(struct timer_list *timer) { … } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { … } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned long expires, unsigned lvl, unsigned long *bucket_expiry) { … } static int calc_wheel_index(unsigned long expires, unsigned long clk, unsigned long *bucket_expiry) { … } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { … } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap, store the index in the timer flags then wake up * the target CPU if needed. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx, unsigned long bucket_expiry) { … } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { … } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr timer_debug_descr; struct timer_hint { … }; #define TIMER_HINT(fn, container, timr, hintfn) … static const struct timer_hint timer_hints[] = …; static void *timer_debug_hint(void *addr) { … } static bool timer_is_static_object(void *addr) { … } /* * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { … } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { … } /* * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { … } /* * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { … } /* * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { … } static const struct debug_obj_descr timer_debug_descr = …; static inline void debug_timer_init(struct timer_list *timer) { … } static inline void debug_timer_activate(struct timer_list *timer) { … } static inline void debug_timer_deactivate(struct timer_list *timer) { … } static inline void debug_timer_assert_init(struct timer_list *timer) { … } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { … } EXPORT_SYMBOL_GPL(…); void destroy_timer_on_stack(struct timer_list *timer) { … } EXPORT_SYMBOL_GPL(…); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { … } static inline void debug_deactivate(struct timer_list *timer) { … } static inline void debug_assert_init(struct timer_list *timer) { … } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { … } /** * init_timer_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * init_timer_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { … } EXPORT_SYMBOL(…); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { … } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { … } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { … } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { … } static inline struct timer_base *get_timer_base(u32 tflags) { … } static inline void __forward_timer_base(struct timer_base *base, unsigned long basej) { … } static inline void forward_timer_base(struct timer_base *base) { … } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { … } #define MOD_TIMER_PENDING_ONLY … #define MOD_TIMER_REDUCE … #define MOD_TIMER_NOTPENDING … static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { … } /** * mod_timer_pending - Modify a pending timer's timeout * @timer: The pending timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), but * will not activate inactive timers. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and not modified or was in * shutdown state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { … } EXPORT_SYMBOL(…); /** * mod_timer - Modify a timer's timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * * mod_timer() is more efficient than the above open coded sequence. In * case that the timer is inactive, the del_timer() part is a NOP. The * timer is in any case activated with the new expiry time @expires. * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * If @timer->function == NULL then the start operation is silently * discarded. In this case the return value is 0 and meaningless. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires did * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { … } EXPORT_SYMBOL(…); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only * modify an enqueued timer if that would reduce the expiration time. If * @timer is not enqueued it starts the timer. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires * did not change the effective expiry time such that the * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { … } EXPORT_SYMBOL(…); /** * add_timer - Start a timer * @timer: The timer to be started * * Start @timer to expire at @timer->expires in the future. @timer->expires * is the absolute expiry time measured in 'jiffies'. When the timer expires * timer->function(timer) will be invoked from soft interrupt context. * * The @timer->expires and @timer->function fields must be set prior * to calling this function. * * If @timer->function == NULL then the start operation is silently * discarded. * * If @timer->expires is already in the past @timer will be queued to * expire at the next timer tick. * * This can only operate on an inactive timer. Attempts to invoke this on * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { … } EXPORT_SYMBOL(…); /** * add_timer_local() - Start a timer on the local CPU * @timer: The timer to be started * * Same as add_timer() except that the timer flag TIMER_PINNED is set. * * See add_timer() for further details. */ void add_timer_local(struct timer_list *timer) { … } EXPORT_SYMBOL(…); /** * add_timer_global() - Start a timer without TIMER_PINNED flag set * @timer: The timer to be started * * Same as add_timer() except that the timer flag TIMER_PINNED is unset. * * See add_timer() for further details. */ void add_timer_global(struct timer_list *timer) { … } EXPORT_SYMBOL(…); /** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * * Same as add_timer() except that it starts the timer on the given CPU and * the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in * the next round, add_timer_global() should be used instead as it unsets * the TIMER_PINNED flag. * * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { … } EXPORT_SYMBOL_GPL(…); /** * __timer_delete - Internal function: Deactivate a timer * @timer: The timer to be deactivated * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the time. In that * case any attempt to rearm @timer after this function returns will be * silently ignored. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete(struct timer_list *timer, bool shutdown) { … } /** * timer_delete - Deactivate a timer * @timer: The timer to be deactivated * * The function only deactivates a pending timer, but contrary to * timer_delete_sync() it does not take into account whether the timer's * callback function is concurrently executed on a different CPU or not. * It neither prevents rearming of the timer. If @timer can be rearmed * concurrently then the return value of this function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete(struct timer_list *timer) { … } EXPORT_SYMBOL(…); /** * timer_shutdown - Deactivate a timer and prevent rearming * @timer: The timer to be deactivated * * The function does not wait for an eventually running timer callback on a * different CPU but it prevents rearming of the timer. Any attempt to arm * @timer after this function returns will be silently ignored. * * This function is useful for teardown code and should only be used when * timer_shutdown_sync() cannot be invoked due to locking or context constraints. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown(struct timer_list *timer) { … } EXPORT_SYMBOL_GPL(…); /** * __try_to_del_timer_sync - Internal function: Try to deactivate a timer * @timer: Timer to deactivate * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the timer. Any * attempt to rearm @timer after this function returns will be silently * ignored. * * This function cannot guarantee that the timer cannot be rearmed * right after dropping the base lock if @shutdown is false. That * needs to be prevented by the calling code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown) { … } /** * try_to_del_timer_sync - Try to deactivate a timer * @timer: Timer to deactivate * * This function tries to deactivate a timer. On success the timer is not * queued and the timer callback function is not running on any CPU. * * This function does not guarantee that the timer cannot be rearmed right * after dropping the base lock. That needs to be prevented by the calling * code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { spin_lock_init(&base->expiry_lock); } static inline void timer_base_lock_expiry(struct timer_base *base) { spin_lock(&base->expiry_lock); } static inline void timer_base_unlock_expiry(struct timer_base *base) { spin_unlock(&base->expiry_lock); } /* * The counterpart to del_timer_wait_running(). * * If there is a waiter for base->expiry_lock, then it was waiting for the * timer callback to finish. Drop expiry_lock and reacquire it. That allows * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); raw_spin_lock_irq(&base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion, if the softirq thread on a remote CPU * got preempted, and it prevents a life lock when the task which tries to * delete a timer preempted the softirq thread running the timer callback * function. */ static void del_timer_wait_running(struct timer_list *timer) { u32 tf; tf = READ_ONCE(timer->flags); if (!(tf & (TIMER_MIGRATING | TIMER_IRQSAFE))) { struct timer_base *base = get_timer_base(tf); /* * Mark the base as contended and grab the expiry lock, * which is held by the softirq across the timer * callback. Drop the lock immediately so the softirq can * expire the next timer. In theory the timer could already * be running again, but that's more than unlikely and just * causes another wait loop. */ atomic_inc(&base->timer_waiters); spin_lock_bh(&base->expiry_lock); atomic_dec(&base->timer_waiters); spin_unlock_bh(&base->expiry_lock); } } #else static inline void timer_base_init_expiry_lock(struct timer_base *base) { … } static inline void timer_base_lock_expiry(struct timer_base *base) { … } static inline void timer_base_unlock_expiry(struct timer_base *base) { … } static inline void timer_sync_wait_running(struct timer_base *base) { … } static inline void del_timer_wait_running(struct timer_list *timer) { … } #endif /** * __timer_delete_sync - Internal function: Deactivate a timer and wait * for the handler to finish. * @timer: The timer to be deactivated * @shutdown: If true, @timer->function will be set to NULL under the * timer base lock which prevents rearming of @timer * * If @shutdown is not set the timer can be rearmed later. If the timer can * be rearmed concurrently, i.e. after dropping the base lock then the * return value is meaningless. * * If @shutdown is set then @timer->function is set to NULL under timer * base lock which prevents rearming of the timer. Any attempt to rearm * a shutdown timer is silently ignored. * * If the timer should be reused after shutdown it has to be initialized * again. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete_sync(struct timer_list *timer, bool shutdown) { … } /** * timer_delete_sync - Deactivate a timer and wait for the handler to finish. * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's callback * function. The timer's handler must not call add_timer_on(). Upon exit * the timer is not queued and the handler is not running on any CPU. * * For !irqsafe timers, the caller must not hold locks that are held in * interrupt context. Even if the lock has nothing to do with the timer in * question. Here's why:: * * CPU0 CPU1 * ---- ---- * <SOFTIRQ> * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * * Now timer_delete_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but it has * interrupted the softirq that CPU0 is waiting to finish. * * This function cannot guarantee that the timer is not rearmed again by * some concurrent or preempting code, right after it dropped the base * lock. If there is the possibility of a concurrent rearm then the return * value of the function is meaningless. * * If such a guarantee is needed, e.g. for teardown situations then use * timer_shutdown_sync() instead. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete_sync(struct timer_list *timer) { … } EXPORT_SYMBOL(…); /** * timer_shutdown_sync - Shutdown a timer and prevent rearming * @timer: The timer to be shutdown * * When the function returns it is guaranteed that: * - @timer is not queued * - The callback function of @timer is not running * - @timer cannot be enqueued again. Any attempt to rearm * @timer is silently ignored. * * See timer_delete_sync() for synchronization rules. * * This function is useful for final teardown of an infrastructure where * the timer is subject to a circular dependency problem. * * A common pattern for this is a timer and a workqueue where the timer can * schedule work and work can arm the timer. On shutdown the workqueue must * be destroyed and the timer must be prevented from rearming. Unless the * code has conditionals like 'if (mything->in_shutdown)' to prevent that * there is no way to get this correct with timer_delete_sync(). * * timer_shutdown_sync() is solving the problem. The correct ordering of * calls in this case is: * * timer_shutdown_sync(&mything->timer); * workqueue_destroy(&mything->workqueue); * * After this 'mything' can be safely freed. * * This obviously implies that the timer is not required to be functional * for the rest of the shutdown operation. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown_sync(struct timer_list *timer) { … } EXPORT_SYMBOL_GPL(…); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), unsigned long baseclk) { … } static void expire_timers(struct timer_base *base, struct hlist_head *head) { … } static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { … } /* * Find the next pending bucket of a level. Search from level start (@offset) * + @clk upwards and if nothing there, search from start of the level * (@offset) up to @offset + clk. */ static int next_pending_bucket(struct timer_base *base, unsigned offset, unsigned clk) { … } /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. * * Store next expiry time in base->next_expiry. */ static void next_expiry_recalc(struct timer_base *base) { … } #ifdef CONFIG_NO_HZ_COMMON /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { … } static unsigned long next_timer_interrupt(struct timer_base *base, unsigned long basej) { … } static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem, struct timer_base *base_local, struct timer_base *base_global, struct timer_events *tevt) { … } # ifdef CONFIG_SMP /** * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic * @tevt: Pointer to the storage for the expiry values * @cpu: Remote CPU * * Stores the next pending local and global timer expiry values in the * struct pointed to by @tevt. If a queue is empty the corresponding * field is set to KTIME_MAX. If local event expires before global * event, global event is set to KTIME_MAX as well. * * Caller needs to make sure timer base locks are held (use * timer_lock_remote_bases() for this purpose). */ void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, struct timer_events *tevt, unsigned int cpu) { … } /** * timer_unlock_remote_bases - unlock timer bases of cpu * @cpu: Remote CPU * * Unlocks the remote timer bases. */ void timer_unlock_remote_bases(unsigned int cpu) __releases(timer_bases[BASE_LOCAL]->lock) __releases(timer_bases[BASE_GLOBAL]->lock) { … } /** * timer_lock_remote_bases - lock timer bases of cpu * @cpu: Remote CPU * * Locks the remote timer bases. */ void timer_lock_remote_bases(unsigned int cpu) __acquires(timer_bases[BASE_LOCAL]->lock) __acquires(timer_bases[BASE_GLOBAL]->lock) { … } /** * timer_base_is_idle() - Return whether timer base is set idle * * Returns value of local timer base is_idle value. */ bool timer_base_is_idle(void) { … } static void __run_timer_base(struct timer_base *base); /** * timer_expire_remote() - expire global timers of cpu * @cpu: Remote CPU * * Expire timers of global base of remote CPU. */ void timer_expire_remote(unsigned int cpu) { … } static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { … } # else static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { /* * Make sure first event is written into tevt->local to not miss a * timer on !SMP systems. */ tevt->local = min_t(u64, tevt->local, tevt->global); } # endif /* CONFIG_SMP */ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, bool *idle) { … } /** * get_next_timer_interrupt() - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. If timer of global base was queued into * timer migration hierarchy, first global timer is not taken into account. If * it was the last CPU of timer migration hierarchy going idle, first global * event is taken into account. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { … } /** * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases * @basej: base time jiffies * @basem: base time clock monotonic * @idle: pointer to store the value of timer_base->is_idle on return; * *idle contains the information whether tick was already stopped * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is * returned as well. */ u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) { … } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { … } #endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { … } static void __run_timer_base(struct timer_base *base) { … } static void run_timer_base(int index) { … } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { … } /* * Called by the local, per-CPU timer interrupt on SMP. */ static void run_local_timers(void) { … } /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { … } /* * Since schedule_timeout()'s timer is defined on the stack, it must store * the target task on the stack as well. */ struct process_timer { … }; static void process_timeout(struct timer_list *t) { … } /** * 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) { … } EXPORT_SYMBOL(…); /* * We can use __set_current_state() here because schedule_timeout() calls * schedule() unconditionally. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { … } EXPORT_SYMBOL(…); signed long __sched schedule_timeout_killable(signed long timeout) { … } EXPORT_SYMBOL(…); signed long __sched schedule_timeout_uninterruptible(signed long timeout) { … } EXPORT_SYMBOL(…); /* * Like schedule_timeout_uninterruptible(), except this task will not contribute * to load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { … } int timers_prepare_cpu(unsigned int cpu) { … } int timers_dead_cpu(unsigned int cpu) { … } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { … } static void __init init_timer_cpus(void) { … } void __init init_timers(void) { … } /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Time in milliseconds to sleep for */ void msleep(unsigned int msecs) { … } EXPORT_SYMBOL(…); /** * msleep_interruptible - sleep waiting for signals * @msecs: Time in milliseconds to sleep for */ unsigned long msleep_interruptible(unsigned int msecs) { … } EXPORT_SYMBOL(…); /** * 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) { … } EXPORT_SYMBOL(…);
Codebase Browser
linux