From 99076b3731a5d8976993c64bb25ce735d7e805a5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 12 Dec 2011 12:29:04 +0100 Subject: [PATCH] wait-simple: Simple waitqueue implementation wait_queue is a swiss army knife and in most of the cases the complexity is not needed. For RT waitqueues are a constant source of trouble as we can't convert the head lock to a raw spinlock due to fancy and long lasting callbacks. Provide a slim version, which allows RT to replace wait queues. This should go mainline as well, as it lowers memory consumption and runtime overhead. Signed-off-by: Thomas Gleixner smp_mb() added by Steven Rostedt to fix a race condition with swait wakeups vs adding items to the list. --- include/linux/wait-simple.h | 235 ++++++++++++++++++++++++++++++++++++ kernel/sched/Makefile | 2 +- kernel/sched/wait-simple.c | 68 +++++++++++ 3 files changed, 304 insertions(+), 1 deletion(-) create mode 100644 include/linux/wait-simple.h create mode 100644 kernel/sched/wait-simple.c diff --git a/include/linux/wait-simple.h b/include/linux/wait-simple.h new file mode 100644 index 000000000000..a9f24692cbe1 --- /dev/null +++ b/include/linux/wait-simple.h @@ -0,0 +1,235 @@ +#ifndef _LINUX_WAIT_SIMPLE_H +#define _LINUX_WAIT_SIMPLE_H + +#include +#include + +#include + +struct swaiter { + struct task_struct *task; + struct list_head node; +}; + +#define DEFINE_SWAITER(name) \ + struct swaiter name = { \ + .task = current, \ + .node = LIST_HEAD_INIT((name).node), \ + } + +struct swait_head { + raw_spinlock_t lock; + struct list_head list; +}; + +#define DEFINE_SWAIT_HEAD(name) \ + struct swait_head name = { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .list = LIST_HEAD_INIT((name).list), \ + } + +extern void __init_swait_head(struct swait_head *h, struct lock_class_key *key); + +#define init_swait_head(swh) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_swait_head((swh), &__key); \ + } while (0) + +/* + * Waiter functions + */ +static inline bool swaiter_enqueued(struct swaiter *w) +{ + return w->task != NULL; +} + +extern void swait_prepare(struct swait_head *head, struct swaiter *w, int state); +extern void swait_finish(struct swait_head *head, struct swaiter *w); + +/* + * Adds w to head->list. Must be called with head->lock locked. + */ +static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w) +{ + list_add(&w->node, &head->list); + /* We can't let the condition leak before the setting of head */ + smp_mb(); +} + +/* + * Removes w from head->list. Must be called with head->lock locked. + */ +static inline void __swait_dequeue(struct swaiter *w) +{ + list_del_init(&w->node); +} + +/* + * Check whether a head has waiters enqueued + */ +static inline bool swait_head_has_waiters(struct swait_head *h) +{ + /* Make sure the condition is visible before checking list_empty() */ + smp_mb(); + return !list_empty(&h->list); +} + +/* + * Wakeup functions + */ +extern int __swait_wake(struct swait_head *head, unsigned int state); + +static inline int swait_wake(struct swait_head *head) +{ + return swait_head_has_waiters(head) ? + __swait_wake(head, TASK_NORMAL) : 0; +} + +static inline int swait_wake_interruptible(struct swait_head *head) +{ + return swait_head_has_waiters(head) ? + __swait_wake(head, TASK_INTERRUPTIBLE) : 0; +} + +/* + * Event API + */ + +#define __swait_event(wq, condition) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + schedule(); \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +/** + * swait_event - sleep until a condition gets true + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + */ +#define swait_event(wq, condition) \ +do { \ + if (condition) \ + break; \ + __swait_event(wq, condition); \ +} while (0) + +#define __swait_event_interruptible(wq, condition, ret) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + schedule(); \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +#define __swait_event_interruptible_timeout(wq, condition, ret) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + ret = schedule_timeout(ret); \ + if (!ret) \ + break; \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +/** + * swait_event_interruptible - sleep until a condition gets true + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + */ +#define swait_event_interruptible(wq, condition) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __swait_event_interruptible(wq, condition, __ret); \ + __ret; \ +}) + +#define swait_event_interruptible_timeout(wq, condition, timeout) \ +({ \ + int __ret = timeout; \ + if (!(condition)) \ + __swait_event_interruptible_timeout(wq, condition, __ret); \ + __ret; \ +}) + +#define __swait_event_timeout(wq, condition, ret) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + ret = schedule_timeout(ret); \ + if (!ret) \ + break; \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +/** + * swait_event_timeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if the @timeout elapsed, and the remaining + * jiffies if the condition evaluated to true before the timeout elapsed. + */ +#define swait_event_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!(condition)) \ + __swait_event_timeout(wq, condition, __ret); \ + __ret; \ +}) + +#endif diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 9a95c8c2af2a..b14a512da520 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -13,7 +13,7 @@ endif obj-y += core.o proc.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o completion.o +obj-y += wait.o wait-simple.o completion.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/wait-simple.c b/kernel/sched/wait-simple.c new file mode 100644 index 000000000000..040d7146e4df --- /dev/null +++ b/kernel/sched/wait-simple.c @@ -0,0 +1,68 @@ +/* + * Simple waitqueues without fancy flags and callbacks + * + * (C) 2011 Thomas Gleixner + * + * Based on kernel/wait.c + * + * For licencing details see kernel-base/COPYING + */ +#include +#include +#include +#include + +void __init_swait_head(struct swait_head *head, struct lock_class_key *key) +{ + raw_spin_lock_init(&head->lock); + lockdep_set_class(&head->lock, key); + INIT_LIST_HEAD(&head->list); +} +EXPORT_SYMBOL(__init_swait_head); + +void swait_prepare(struct swait_head *head, struct swaiter *w, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&head->lock, flags); + w->task = current; + if (list_empty(&w->node)) + __swait_enqueue(head, w); + set_current_state(state); + raw_spin_unlock_irqrestore(&head->lock, flags); +} +EXPORT_SYMBOL(swait_prepare); + +void swait_finish(struct swait_head *head, struct swaiter *w) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + if (w->task) { + raw_spin_lock_irqsave(&head->lock, flags); + __swait_dequeue(w); + raw_spin_unlock_irqrestore(&head->lock, flags); + } +} +EXPORT_SYMBOL(swait_finish); + +int __swait_wake(struct swait_head *head, unsigned int state) +{ + struct swaiter *curr, *next; + unsigned long flags; + int woken = 0; + + raw_spin_lock_irqsave(&head->lock, flags); + + list_for_each_entry_safe(curr, next, &head->list, node) { + if (wake_up_state(curr->task, state)) { + __swait_dequeue(curr); + curr->task = NULL; + woken++; + } + } + + raw_spin_unlock_irqrestore(&head->lock, flags); + return woken; +} +EXPORT_SYMBOL(__swait_wake);