the closure code was never intended to be bcache specific - hopefully it can be useful elsewhere in the kernel.
Signed-off-by: Kent Overstreet <k...@daterainc.com> Cc: Tejun Heo <t...@kernel.org> Cc: Andrew Morton <a...@linux-foundation.org> Cc: Oleg Nesterov <o...@redhat.com> Cc: Arjan van de Ven <ar...@linux.intel.com> Cc: Dan Williams <dan.j.willi...@intel.com> --- drivers/md/bcache/Kconfig | 9 - drivers/md/bcache/Makefile | 2 +- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/closure.c | 222 ---------------------- drivers/md/bcache/closure.h | 453 -------------------------------------------- drivers/md/bcache/util.h | 3 +- include/linux/closure.h | 451 +++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 8 + lib/Makefile | 2 +- lib/closure.c | 218 +++++++++++++++++++++ 10 files changed, 681 insertions(+), 689 deletions(-) delete mode 100644 drivers/md/bcache/closure.c delete mode 100644 drivers/md/bcache/closure.h create mode 100644 include/linux/closure.h create mode 100644 lib/closure.c diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index 2638417b19..d6d7f792cc 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -16,15 +16,6 @@ config BCACHE_DEBUG Enables extra debugging tools, allows expensive runtime checks to be turned on. -config BCACHE_CLOSURES_DEBUG - bool "Debug closures" - depends on BCACHE - select DEBUG_FS - ---help--- - Keeps all active closures in a linked list and provides a debugfs - interface to list them, which makes it possible to see asynchronous - operations that get stuck. - # cgroup code needs to be updated: # #config CGROUP_BCACHE diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile index 0e9c82523b..17ab9adbdf 100644 --- a/drivers/md/bcache/Makefile +++ b/drivers/md/bcache/Makefile @@ -2,6 +2,6 @@ obj-$(CONFIG_BCACHE) += bcache.o bcache-y := alloc.o btree.o bset.o io.o journal.o writeback.o\ - movinggc.o request.o super.o sysfs.o debug.o util.o trace.o stats.o closure.o + movinggc.o request.o super.o sysfs.o debug.o util.o trace.o stats.o CFLAGS_request.o += -Iblock diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 9d062bc562..79f444a8b9 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -179,6 +179,7 @@ #include <linux/bcache.h> #include <linux/bio.h> +#include <linux/closure.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/mutex.h> @@ -188,7 +189,6 @@ #include <linux/workqueue.h> #include "util.h" -#include "closure.h" struct bucket { atomic_t pin; diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c deleted file mode 100644 index 7a228de95f..0000000000 --- a/drivers/md/bcache/closure.c +++ /dev/null @@ -1,222 +0,0 @@ -/* - * Asynchronous refcounty things - * - * Copyright 2010, 2011 Kent Overstreet <kent.overstr...@gmail.com> - * Copyright 2012 Google, Inc. - */ - -#include <linux/debugfs.h> -#include <linux/module.h> -#include <linux/seq_file.h> - -#include "closure.h" - -static inline void closure_put_after_sub(struct closure *cl, int flags) -{ - int r = flags & CLOSURE_REMAINING_MASK; - - BUG_ON(flags & CLOSURE_GUARD_MASK); - BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR)); - - /* Must deliver precisely one wakeup */ - if (r == 1 && (flags & CLOSURE_SLEEPING)) - wake_up_process(cl->task); - - if (!r) { - if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) { - atomic_set(&cl->remaining, - CLOSURE_REMAINING_INITIALIZER); - closure_queue(cl); - } else { - struct closure *parent = cl->parent; - closure_fn *destructor = cl->fn; - - closure_debug_destroy(cl); - - if (destructor) - destructor(cl); - - if (parent) - closure_put(parent); - } - } -} - -/* For clearing flags with the same atomic op as a put */ -void closure_sub(struct closure *cl, int v) -{ - closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining)); -} -EXPORT_SYMBOL(closure_sub); - -/** - * closure_put - decrement a closure's refcount - */ -void closure_put(struct closure *cl) -{ - closure_put_after_sub(cl, atomic_dec_return(&cl->remaining)); -} -EXPORT_SYMBOL(closure_put); - -/** - * closure_wake_up - wake up all closures on a wait list, without memory barrier - */ -void __closure_wake_up(struct closure_waitlist *wait_list) -{ - struct llist_node *list; - struct closure *cl; - struct llist_node *reverse = NULL; - - list = llist_del_all(&wait_list->list); - - /* We first reverse the list to preserve FIFO ordering and fairness */ - - while (list) { - struct llist_node *t = list; - list = llist_next(list); - - t->next = reverse; - reverse = t; - } - - /* Then do the wakeups */ - - while (reverse) { - cl = container_of(reverse, struct closure, list); - reverse = llist_next(reverse); - - closure_set_waiting(cl, 0); - closure_sub(cl, CLOSURE_WAITING + 1); - } -} -EXPORT_SYMBOL(__closure_wake_up); - -/** - * closure_wait - add a closure to a waitlist - * - * @waitlist will own a ref on @cl, which will be released when - * closure_wake_up() is called on @waitlist. - * - */ -bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl) -{ - if (atomic_read(&cl->remaining) & CLOSURE_WAITING) - return false; - - closure_set_waiting(cl, _RET_IP_); - atomic_add(CLOSURE_WAITING + 1, &cl->remaining); - llist_add(&cl->list, &waitlist->list); - - return true; -} -EXPORT_SYMBOL(closure_wait); - -/** - * closure_sync - sleep until a closure a closure has nothing left to wait on - * - * Sleeps until the refcount hits 1 - the thread that's running the closure owns - * the last refcount. - */ -void closure_sync(struct closure *cl) -{ - while (1) { - __closure_start_sleep(cl); - closure_set_ret_ip(cl); - - if ((atomic_read(&cl->remaining) & - CLOSURE_REMAINING_MASK) == 1) - break; - - schedule(); - } - - __closure_end_sleep(cl); -} -EXPORT_SYMBOL(closure_sync); - -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG - -static LIST_HEAD(closure_list); -static DEFINE_SPINLOCK(closure_list_lock); - -void closure_debug_create(struct closure *cl) -{ - unsigned long flags; - - BUG_ON(cl->magic == CLOSURE_MAGIC_ALIVE); - cl->magic = CLOSURE_MAGIC_ALIVE; - - spin_lock_irqsave(&closure_list_lock, flags); - list_add(&cl->all, &closure_list); - spin_unlock_irqrestore(&closure_list_lock, flags); -} -EXPORT_SYMBOL(closure_debug_create); - -void closure_debug_destroy(struct closure *cl) -{ - unsigned long flags; - - BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE); - cl->magic = CLOSURE_MAGIC_DEAD; - - spin_lock_irqsave(&closure_list_lock, flags); - list_del(&cl->all); - spin_unlock_irqrestore(&closure_list_lock, flags); -} -EXPORT_SYMBOL(closure_debug_destroy); - -static struct dentry *debug; - -#define work_data_bits(work) ((unsigned long *)(&(work)->data)) - -static int debug_seq_show(struct seq_file *f, void *data) -{ - struct closure *cl; - spin_lock_irq(&closure_list_lock); - - list_for_each_entry(cl, &closure_list, all) { - int r = atomic_read(&cl->remaining); - - seq_printf(f, "%p: %pF -> %pf p %p r %i ", - cl, (void *) cl->ip, cl->fn, cl->parent, - r & CLOSURE_REMAINING_MASK); - - seq_printf(f, "%s%s%s%s\n", - test_bit(WORK_STRUCT_PENDING, - work_data_bits(&cl->work)) ? "Q" : "", - r & CLOSURE_RUNNING ? "R" : "", - r & CLOSURE_STACK ? "S" : "", - r & CLOSURE_SLEEPING ? "Sl" : ""); - - if (r & CLOSURE_WAITING) - seq_printf(f, " W %pF\n", - (void *) cl->waiting_on); - - seq_printf(f, "\n"); - } - - spin_unlock_irq(&closure_list_lock); - return 0; -} - -static int debug_seq_open(struct inode *inode, struct file *file) -{ - return single_open(file, debug_seq_show, NULL); -} - -static const struct file_operations debug_ops = { - .owner = THIS_MODULE, - .open = debug_seq_open, - .read = seq_read, - .release = single_release -}; - -void __init closure_debug_init(void) -{ - debug = debugfs_create_file("closures", 0400, NULL, NULL, &debug_ops); -} - -#endif - -MODULE_AUTHOR("Kent Overstreet <koverstr...@google.com>"); -MODULE_LICENSE("GPL"); diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h deleted file mode 100644 index 13c3aa2157..0000000000 --- a/drivers/md/bcache/closure.h +++ /dev/null @@ -1,453 +0,0 @@ -#ifndef _LINUX_CLOSURE_H -#define _LINUX_CLOSURE_H - -#include <linux/llist.h> -#include <linux/sched.h> -#include <linux/workqueue.h> - -/* - * Closure is perhaps the most overused and abused term in computer science, but - * since I've been unable to come up with anything better you're stuck with it - * again. - * - * What are closures? - * - * They embed a refcount. The basic idea is they count "things that are in - * progress" - in flight bios, some other thread that's doing something else - - * anything you might want to wait on. - * - * The refcount may be manipulated with closure_get() and closure_put(). - * closure_put() is where many of the interesting things happen, when it causes - * the refcount to go to 0. - * - * Closures can be used to wait on things both synchronously and asynchronously, - * and synchronous and asynchronous use can be mixed without restriction. To - * wait synchronously, use closure_sync() - you will sleep until your closure's - * refcount hits 1. - * - * To wait asynchronously, use - * continue_at(cl, next_function, workqueue); - * - * passing it, as you might expect, the function to run when nothing is pending - * and the workqueue to run that function out of. - * - * continue_at() also, critically, is a macro that returns the calling function. - * There's good reason for this. - * - * To use safely closures asynchronously, they must always have a refcount while - * they are running owned by the thread that is running them. Otherwise, suppose - * you submit some bios and wish to have a function run when they all complete: - * - * foo_endio(struct bio *bio, int error) - * { - * closure_put(cl); - * } - * - * closure_init(cl); - * - * do_stuff(); - * closure_get(cl); - * bio1->bi_endio = foo_endio; - * bio_submit(bio1); - * - * do_more_stuff(); - * closure_get(cl); - * bio2->bi_endio = foo_endio; - * bio_submit(bio2); - * - * continue_at(cl, complete_some_read, system_wq); - * - * If closure's refcount started at 0, complete_some_read() could run before the - * second bio was submitted - which is almost always not what you want! More - * importantly, it wouldn't be possible to say whether the original thread or - * complete_some_read()'s thread owned the closure - and whatever state it was - * associated with! - * - * So, closure_init() initializes a closure's refcount to 1 - and when a - * closure_fn is run, the refcount will be reset to 1 first. - * - * Then, the rule is - if you got the refcount with closure_get(), release it - * with closure_put() (i.e, in a bio->bi_endio function). If you have a refcount - * on a closure because you called closure_init() or you were run out of a - * closure - _always_ use continue_at(). Doing so consistently will help - * eliminate an entire class of particularly pernicious races. - * - * For a closure to wait on an arbitrary event, we need to introduce waitlists: - * - * struct closure_waitlist list; - * closure_wait_event(list, cl, condition); - * closure_wake_up(wait_list); - * - * These work analagously to wait_event() and wake_up() - except that instead of - * operating on the current thread (for wait_event()) and lists of threads, they - * operate on an explicit closure and lists of closures. - * - * Because it's a closure we can now wait either synchronously or - * asynchronously. closure_wait_event() returns the current value of the - * condition, and if it returned false continue_at() or closure_sync() can be - * used to wait for it to become true. - * - * It's useful for waiting on things when you can't sleep in the context in - * which you must check the condition (perhaps a spinlock held, or you might be - * beneath generic_make_request() - in which case you can't sleep on IO). - * - * closure_wait_event() will wait either synchronously or asynchronously, - * depending on whether the closure is in blocking mode or not. You can pick a - * mode explicitly with closure_wait_event_sync() and - * closure_wait_event_async(), which do just what you might expect. - * - * Lastly, you might have a wait list dedicated to a specific event, and have no - * need for specifying the condition - you just want to wait until someone runs - * closure_wake_up() on the appropriate wait list. In that case, just use - * closure_wait(). It will return either true or false, depending on whether the - * closure was already on a wait list or not - a closure can only be on one wait - * list at a time. - * - * Parents: - * - * closure_init() takes two arguments - it takes the closure to initialize, and - * a (possibly null) parent. - * - * If parent is non null, the new closure will have a refcount for its lifetime; - * a closure is considered to be "finished" when its refcount hits 0 and the - * function to run is null. Hence - * - * continue_at(cl, NULL, NULL); - * - * returns up the (spaghetti) stack of closures, precisely like normal return - * returns up the C stack. continue_at() with non null fn is better thought of - * as doing a tail call. - * - * All this implies that a closure should typically be embedded in a particular - * struct (which its refcount will normally control the lifetime of), and that - * struct can very much be thought of as a stack frame. - */ - -struct closure; -typedef void (closure_fn) (struct closure *); - -struct closure_waitlist { - struct llist_head list; -}; - -enum closure_state { - /* - * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by - * the thread that owns the closure, and cleared by the thread that's - * waking up the closure. - * - * CLOSURE_SLEEPING: Must be set before a thread uses a closure to sleep - * - indicates that cl->task is valid and closure_put() may wake it up. - * Only set or cleared by the thread that owns the closure. - * - * The rest are for debugging and don't affect behaviour: - * - * CLOSURE_RUNNING: Set when a closure is running (i.e. by - * closure_init() and when closure_put() runs then next function), and - * must be cleared before remaining hits 0. Primarily to help guard - * against incorrect usage and accidentally transferring references. - * continue_at() and closure_return() clear it for you, if you're doing - * something unusual you can use closure_set_dead() which also helps - * annotate where references are being transferred. - * - * CLOSURE_STACK: Sanity check - remaining should never hit 0 on a - * closure with this flag set - */ - - CLOSURE_BITS_START = (1 << 23), - CLOSURE_DESTRUCTOR = (1 << 23), - CLOSURE_WAITING = (1 << 25), - CLOSURE_SLEEPING = (1 << 27), - CLOSURE_RUNNING = (1 << 29), - CLOSURE_STACK = (1 << 31), -}; - -#define CLOSURE_GUARD_MASK \ - ((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_SLEEPING| \ - CLOSURE_RUNNING|CLOSURE_STACK) << 1) - -#define CLOSURE_REMAINING_MASK (CLOSURE_BITS_START - 1) -#define CLOSURE_REMAINING_INITIALIZER (1|CLOSURE_RUNNING) - -struct closure { - union { - struct { - struct workqueue_struct *wq; - struct task_struct *task; - struct llist_node list; - closure_fn *fn; - }; - struct work_struct work; - }; - - struct closure *parent; - - atomic_t remaining; - -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG -#define CLOSURE_MAGIC_DEAD 0xc054dead -#define CLOSURE_MAGIC_ALIVE 0xc054a11e - - unsigned magic; - struct list_head all; - unsigned long ip; - unsigned long waiting_on; -#endif -}; - -void closure_sub(struct closure *cl, int v); -void closure_put(struct closure *cl); -void __closure_wake_up(struct closure_waitlist *list); -bool closure_wait(struct closure_waitlist *list, struct closure *cl); -void closure_sync(struct closure *cl); - -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG - -void closure_debug_init(void); -void closure_debug_create(struct closure *cl); -void closure_debug_destroy(struct closure *cl); - -#else - -static inline void closure_debug_init(void) {} -static inline void closure_debug_create(struct closure *cl) {} -static inline void closure_debug_destroy(struct closure *cl) {} - -#endif - -static inline void closure_set_ip(struct closure *cl) -{ -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG - cl->ip = _THIS_IP_; -#endif -} - -static inline void closure_set_ret_ip(struct closure *cl) -{ -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG - cl->ip = _RET_IP_; -#endif -} - -static inline void closure_set_waiting(struct closure *cl, unsigned long f) -{ -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG - cl->waiting_on = f; -#endif -} - -static inline void __closure_end_sleep(struct closure *cl) -{ - __set_current_state(TASK_RUNNING); - - if (atomic_read(&cl->remaining) & CLOSURE_SLEEPING) - atomic_sub(CLOSURE_SLEEPING, &cl->remaining); -} - -static inline void __closure_start_sleep(struct closure *cl) -{ - closure_set_ip(cl); - cl->task = current; - set_current_state(TASK_UNINTERRUPTIBLE); - - if (!(atomic_read(&cl->remaining) & CLOSURE_SLEEPING)) - atomic_add(CLOSURE_SLEEPING, &cl->remaining); -} - -static inline void closure_set_stopped(struct closure *cl) -{ - atomic_sub(CLOSURE_RUNNING, &cl->remaining); -} - -static inline void set_closure_fn(struct closure *cl, closure_fn *fn, - struct workqueue_struct *wq) -{ - BUG_ON(object_is_on_stack(cl)); - closure_set_ip(cl); - cl->fn = fn; - cl->wq = wq; - /* between atomic_dec() in closure_put() */ - smp_mb__before_atomic_dec(); -} - -static inline void closure_queue(struct closure *cl) -{ - struct workqueue_struct *wq = cl->wq; - if (wq) { - INIT_WORK(&cl->work, cl->work.func); - BUG_ON(!queue_work(wq, &cl->work)); - } else - cl->fn(cl); -} - -/** - * closure_get - increment a closure's refcount - */ -static inline void closure_get(struct closure *cl) -{ -#ifdef CONFIG_BCACHE_CLOSURES_DEBUG - BUG_ON((atomic_inc_return(&cl->remaining) & - CLOSURE_REMAINING_MASK) <= 1); -#else - atomic_inc(&cl->remaining); -#endif -} - -/** - * closure_init - Initialize a closure, setting the refcount to 1 - * @cl: closure to initialize - * @parent: parent of the new closure. cl will take a refcount on it for its - * lifetime; may be NULL. - */ -static inline void closure_init(struct closure *cl, struct closure *parent) -{ - memset(cl, 0, sizeof(struct closure)); - cl->parent = parent; - if (parent) - closure_get(parent); - - atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); - - closure_debug_create(cl); - closure_set_ip(cl); -} - -static inline void closure_init_stack(struct closure *cl) -{ - memset(cl, 0, sizeof(struct closure)); - atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER|CLOSURE_STACK); -} - -/** - * closure_wake_up - wake up all closures on a wait list. - */ -static inline void closure_wake_up(struct closure_waitlist *list) -{ - smp_mb(); - __closure_wake_up(list); -} - -/** - * closure_wait_event - wait on arbitrary event - * - * Analogous to wait_event() but for closures. - * - * The loop is oddly structured so as to avoid a race; we must check the - * condition again after we've added ourself to the waitlist. We know if we were - * already on the waitlist because closure_wait() returns false; thus, we only - * schedule or break if closure_wait() returns false. If it returns true, we - * just loop again - rechecking the condition. - * - * The __closure_wake_up() is necessary because we may race with the event - * becoming true; i.e. we see event false -> wait -> recheck condition, but the - * thread that made the event true may have called closure_wake_up() before we - * added ourself to the wait list. - * - * We have to call closure_sync() at the end instead of just - * __closure_end_sleep() because a different thread might've called - * closure_wake_up() before us and gotten preempted before they dropped the - * refcount on our closure. If this was a stack allocated closure, that would be - * bad. - */ -#define closure_wait_event(list, cl, condition) \ -({ \ - typeof(condition) ret; \ - \ - while (1) { \ - ret = (condition); \ - if (ret) { \ - __closure_wake_up(list); \ - closure_sync(cl); \ - break; \ - } \ - \ - __closure_start_sleep(cl); \ - \ - if (!closure_wait(list, cl)) \ - schedule(); \ - } \ - \ - ret; \ -}) - -/** - * continue_at - jump to another function with barrier - * - * After @cl is no longer waiting on anything (i.e. all outstanding refs have - * been dropped with closure_put()), it will resume execution at @fn running out - * of @wq (or, if @wq is NULL, @fn will be called by closure_put() directly). - * - * NOTE: This macro expands to a return in the calling function! - * - * This is because after calling continue_at() you no longer have a ref on @cl, - * and whatever @cl owns may be freed out from under you - a running closure fn - * has a ref on its own closure which continue_at() drops. - */ -#define continue_at(_cl, _fn, _wq) \ -do { \ - set_closure_fn(_cl, _fn, _wq); \ - closure_sub(_cl, CLOSURE_RUNNING + 1); \ - return; \ -} while (0) - -/** - * closure_return - finish execution of a closure - * - * This is used to indicate that @cl is finished: when all outstanding refs on - * @cl have been dropped @cl's ref on its parent closure (as passed to - * closure_init()) will be dropped, if one was specified - thus this can be - * thought of as returning to the parent closure. - */ -#define closure_return(_cl) continue_at((_cl), NULL, NULL) - -/** - * continue_at_nobarrier - jump to another function without barrier - * - * Causes @fn to be executed out of @cl, in @wq context (or called directly if - * @wq is NULL). - * - * NOTE: like continue_at(), this macro expands to a return in the caller! - * - * The ref the caller of continue_at_nobarrier() had on @cl is now owned by @fn, - * thus it's not safe to touch anything protected by @cl after a - * continue_at_nobarrier(). - */ -#define continue_at_nobarrier(_cl, _fn, _wq) \ -do { \ - set_closure_fn(_cl, _fn, _wq); \ - closure_queue(_cl); \ - return; \ -} while (0) - -/** - * closure_return - finish execution of a closure, with destructor - * - * Works like closure_return(), except @destructor will be called when all - * outstanding refs on @cl have been dropped; @destructor may be used to safely - * free the memory occupied by @cl, and it is called with the ref on the parent - * closure still held - so @destructor could safely return an item to a - * freelist protected by @cl's parent. - */ -#define closure_return_with_destructor(_cl, _destructor) \ -do { \ - set_closure_fn(_cl, _destructor, NULL); \ - closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1); \ - return; \ -} while (0) - -/** - * closure_call - execute @fn out of a new, uninitialized closure - * - * Typically used when running out of one closure, and we want to run @fn - * asynchronously out of a new closure - @parent will then wait for @cl to - * finish. - */ -static inline void closure_call(struct closure *cl, closure_fn fn, - struct workqueue_struct *wq, - struct closure *parent) -{ - closure_init(cl, parent); - continue_at_nobarrier(cl, fn, wq); -} - -#endif /* _LINUX_CLOSURE_H */ diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 1030c6020e..c51605d34b 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -2,6 +2,7 @@ #ifndef _BCACHE_UTIL_H #define _BCACHE_UTIL_H +#include <linux/closure.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/llist.h> @@ -9,8 +10,6 @@ #include <linux/vmalloc.h> #include <linux/workqueue.h> -#include "closure.h" - #define PAGE_SECTORS (PAGE_SIZE / 512) struct closure; diff --git a/include/linux/closure.h b/include/linux/closure.h new file mode 100644 index 0000000000..038f0bf5df --- /dev/null +++ b/include/linux/closure.h @@ -0,0 +1,451 @@ +#ifndef _LINUX_CLOSURE_H +#define _LINUX_CLOSURE_H + +#include <linux/llist.h> +#include <linux/sched.h> +#include <linux/workqueue.h> + +/* + * Closure is perhaps the most overused and abused term in computer science, but + * since I've been unable to come up with anything better you're stuck with it + * again. + * + * What are closures? + * + * They embed a refcount. The basic idea is they count "things that are in + * progress" - in flight bios, some other thread that's doing something else - + * anything you might want to wait on. + * + * The refcount may be manipulated with closure_get() and closure_put(). + * closure_put() is where many of the interesting things happen, when it causes + * the refcount to go to 0. + * + * Closures can be used to wait on things both synchronously and asynchronously, + * and synchronous and asynchronous use can be mixed without restriction. To + * wait synchronously, use closure_sync() - you will sleep until your closure's + * refcount hits 1. + * + * To wait asynchronously, use + * continue_at(cl, next_function, workqueue); + * + * passing it, as you might expect, the function to run when nothing is pending + * and the workqueue to run that function out of. + * + * continue_at() also, critically, is a macro that returns the calling function. + * There's good reason for this. + * + * To use safely closures asynchronously, they must always have a refcount while + * they are running owned by the thread that is running them. Otherwise, suppose + * you submit some bios and wish to have a function run when they all complete: + * + * foo_endio(struct bio *bio, int error) + * { + * closure_put(cl); + * } + * + * closure_init(cl); + * + * do_stuff(); + * closure_get(cl); + * bio1->bi_endio = foo_endio; + * bio_submit(bio1); + * + * do_more_stuff(); + * closure_get(cl); + * bio2->bi_endio = foo_endio; + * bio_submit(bio2); + * + * continue_at(cl, complete_some_read, system_wq); + * + * If closure's refcount started at 0, complete_some_read() could run before the + * second bio was submitted - which is almost always not what you want! More + * importantly, it wouldn't be possible to say whether the original thread or + * complete_some_read()'s thread owned the closure - and whatever state it was + * associated with! + * + * So, closure_init() initializes a closure's refcount to 1 - and when a + * closure_fn is run, the refcount will be reset to 1 first. + * + * Then, the rule is - if you got the refcount with closure_get(), release it + * with closure_put() (i.e, in a bio->bi_endio function). If you have a refcount + * on a closure because you called closure_init() or you were run out of a + * closure - _always_ use continue_at(). Doing so consistently will help + * eliminate an entire class of particularly pernicious races. + * + * For a closure to wait on an arbitrary event, we need to introduce waitlists: + * + * struct closure_waitlist list; + * closure_wait_event(list, cl, condition); + * closure_wake_up(wait_list); + * + * These work analagously to wait_event() and wake_up() - except that instead of + * operating on the current thread (for wait_event()) and lists of threads, they + * operate on an explicit closure and lists of closures. + * + * Because it's a closure we can now wait either synchronously or + * asynchronously. closure_wait_event() returns the current value of the + * condition, and if it returned false continue_at() or closure_sync() can be + * used to wait for it to become true. + * + * It's useful for waiting on things when you can't sleep in the context in + * which you must check the condition (perhaps a spinlock held, or you might be + * beneath generic_make_request() - in which case you can't sleep on IO). + * + * closure_wait_event() will wait either synchronously or asynchronously, + * depending on whether the closure is in blocking mode or not. You can pick a + * mode explicitly with closure_wait_event_sync() and + * closure_wait_event_async(), which do just what you might expect. + * + * Lastly, you might have a wait list dedicated to a specific event, and have no + * need for specifying the condition - you just want to wait until someone runs + * closure_wake_up() on the appropriate wait list. In that case, just use + * closure_wait(). It will return either true or false, depending on whether the + * closure was already on a wait list or not - a closure can only be on one wait + * list at a time. + * + * Parents: + * + * closure_init() takes two arguments - it takes the closure to initialize, and + * a (possibly null) parent. + * + * If parent is non null, the new closure will have a refcount for its lifetime; + * a closure is considered to be "finished" when its refcount hits 0 and the + * function to run is null. Hence + * + * continue_at(cl, NULL, NULL); + * + * returns up the (spaghetti) stack of closures, precisely like normal return + * returns up the C stack. continue_at() with non null fn is better thought of + * as doing a tail call. + * + * All this implies that a closure should typically be embedded in a particular + * struct (which its refcount will normally control the lifetime of), and that + * struct can very much be thought of as a stack frame. + */ + +struct closure; +typedef void (closure_fn) (struct closure *); + +struct closure_waitlist { + struct llist_head list; +}; + +enum closure_state { + /* + * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by + * the thread that owns the closure, and cleared by the thread that's + * waking up the closure. + * + * CLOSURE_SLEEPING: Must be set before a thread uses a closure to sleep + * - indicates that cl->task is valid and closure_put() may wake it up. + * Only set or cleared by the thread that owns the closure. + * + * The rest are for debugging and don't affect behaviour: + * + * CLOSURE_RUNNING: Set when a closure is running (i.e. by + * closure_init() and when closure_put() runs then next function), and + * must be cleared before remaining hits 0. Primarily to help guard + * against incorrect usage and accidentally transferring references. + * continue_at() and closure_return() clear it for you, if you're doing + * something unusual you can use closure_set_dead() which also helps + * annotate where references are being transferred. + * + * CLOSURE_STACK: Sanity check - remaining should never hit 0 on a + * closure with this flag set + */ + + CLOSURE_BITS_START = (1 << 23), + CLOSURE_DESTRUCTOR = (1 << 23), + CLOSURE_WAITING = (1 << 25), + CLOSURE_SLEEPING = (1 << 27), + CLOSURE_RUNNING = (1 << 29), + CLOSURE_STACK = (1 << 31), +}; + +#define CLOSURE_GUARD_MASK \ + ((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_SLEEPING| \ + CLOSURE_RUNNING|CLOSURE_STACK) << 1) + +#define CLOSURE_REMAINING_MASK (CLOSURE_BITS_START - 1) +#define CLOSURE_REMAINING_INITIALIZER (1|CLOSURE_RUNNING) + +struct closure { + union { + struct { + struct workqueue_struct *wq; + struct task_struct *task; + struct llist_node list; + closure_fn *fn; + }; + struct work_struct work; + }; + + struct closure *parent; + + atomic_t remaining; + +#ifdef CONFIG_CLOSURE_DEBUG +#define CLOSURE_MAGIC_DEAD 0xc054dead +#define CLOSURE_MAGIC_ALIVE 0xc054a11e + + unsigned magic; + struct list_head all; + unsigned long ip; + unsigned long waiting_on; +#endif +}; + +void closure_sub(struct closure *cl, int v); +void closure_put(struct closure *cl); +void __closure_wake_up(struct closure_waitlist *list); +bool closure_wait(struct closure_waitlist *list, struct closure *cl); +void closure_sync(struct closure *cl); + +#ifdef CONFIG_CLOSURE_DEBUG + +void closure_debug_create(struct closure *cl); +void closure_debug_destroy(struct closure *cl); + +#else + +static inline void closure_debug_create(struct closure *cl) {} +static inline void closure_debug_destroy(struct closure *cl) {} + +#endif + +static inline void closure_set_ip(struct closure *cl) +{ +#ifdef CONFIG_CLOSURE_DEBUG + cl->ip = _THIS_IP_; +#endif +} + +static inline void closure_set_ret_ip(struct closure *cl) +{ +#ifdef CONFIG_CLOSURE_DEBUG + cl->ip = _RET_IP_; +#endif +} + +static inline void closure_set_waiting(struct closure *cl, unsigned long f) +{ +#ifdef CONFIG_CLOSURE_DEBUG + cl->waiting_on = f; +#endif +} + +static inline void __closure_end_sleep(struct closure *cl) +{ + __set_current_state(TASK_RUNNING); + + if (atomic_read(&cl->remaining) & CLOSURE_SLEEPING) + atomic_sub(CLOSURE_SLEEPING, &cl->remaining); +} + +static inline void __closure_start_sleep(struct closure *cl) +{ + closure_set_ip(cl); + cl->task = current; + set_current_state(TASK_UNINTERRUPTIBLE); + + if (!(atomic_read(&cl->remaining) & CLOSURE_SLEEPING)) + atomic_add(CLOSURE_SLEEPING, &cl->remaining); +} + +static inline void closure_set_stopped(struct closure *cl) +{ + atomic_sub(CLOSURE_RUNNING, &cl->remaining); +} + +static inline void set_closure_fn(struct closure *cl, closure_fn *fn, + struct workqueue_struct *wq) +{ + BUG_ON(object_is_on_stack(cl)); + closure_set_ip(cl); + cl->fn = fn; + cl->wq = wq; + /* between atomic_dec() in closure_put() */ + smp_mb__before_atomic_dec(); +} + +static inline void closure_queue(struct closure *cl) +{ + struct workqueue_struct *wq = cl->wq; + if (wq) { + INIT_WORK(&cl->work, cl->work.func); + BUG_ON(!queue_work(wq, &cl->work)); + } else + cl->fn(cl); +} + +/** + * closure_get - increment a closure's refcount + */ +static inline void closure_get(struct closure *cl) +{ +#ifdef CONFIG_CLOSURE_DEBUG + BUG_ON((atomic_inc_return(&cl->remaining) & + CLOSURE_REMAINING_MASK) <= 1); +#else + atomic_inc(&cl->remaining); +#endif +} + +/** + * closure_init - Initialize a closure, setting the refcount to 1 + * @cl: closure to initialize + * @parent: parent of the new closure. cl will take a refcount on it for its + * lifetime; may be NULL. + */ +static inline void closure_init(struct closure *cl, struct closure *parent) +{ + memset(cl, 0, sizeof(struct closure)); + cl->parent = parent; + if (parent) + closure_get(parent); + + atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); + + closure_debug_create(cl); + closure_set_ip(cl); +} + +static inline void closure_init_stack(struct closure *cl) +{ + memset(cl, 0, sizeof(struct closure)); + atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER|CLOSURE_STACK); +} + +/** + * closure_wake_up - wake up all closures on a wait list. + */ +static inline void closure_wake_up(struct closure_waitlist *list) +{ + smp_mb(); + __closure_wake_up(list); +} + +/** + * closure_wait_event - wait on arbitrary event + * + * Analogous to wait_event() but for closures. + * + * The loop is oddly structured so as to avoid a race; we must check the + * condition again after we've added ourself to the waitlist. We know if we were + * already on the waitlist because closure_wait() returns false; thus, we only + * schedule or break if closure_wait() returns false. If it returns true, we + * just loop again - rechecking the condition. + * + * The __closure_wake_up() is necessary because we may race with the event + * becoming true; i.e. we see event false -> wait -> recheck condition, but the + * thread that made the event true may have called closure_wake_up() before we + * added ourself to the wait list. + * + * We have to call closure_sync() at the end instead of just + * __closure_end_sleep() because a different thread might've called + * closure_wake_up() before us and gotten preempted before they dropped the + * refcount on our closure. If this was a stack allocated closure, that would be + * bad. + */ +#define closure_wait_event(list, cl, condition) \ +({ \ + typeof(condition) ret; \ + \ + while (1) { \ + ret = (condition); \ + if (ret) { \ + __closure_wake_up(list); \ + closure_sync(cl); \ + break; \ + } \ + \ + __closure_start_sleep(cl); \ + \ + if (!closure_wait(list, cl)) \ + schedule(); \ + } \ + \ + ret; \ +}) + +/** + * continue_at - jump to another function with barrier + * + * After @cl is no longer waiting on anything (i.e. all outstanding refs have + * been dropped with closure_put()), it will resume execution at @fn running out + * of @wq (or, if @wq is NULL, @fn will be called by closure_put() directly). + * + * NOTE: This macro expands to a return in the calling function! + * + * This is because after calling continue_at() you no longer have a ref on @cl, + * and whatever @cl owns may be freed out from under you - a running closure fn + * has a ref on its own closure which continue_at() drops. + */ +#define continue_at(_cl, _fn, _wq) \ +do { \ + set_closure_fn(_cl, _fn, _wq); \ + closure_sub(_cl, CLOSURE_RUNNING + 1); \ + return; \ +} while (0) + +/** + * closure_return - finish execution of a closure + * + * This is used to indicate that @cl is finished: when all outstanding refs on + * @cl have been dropped @cl's ref on its parent closure (as passed to + * closure_init()) will be dropped, if one was specified - thus this can be + * thought of as returning to the parent closure. + */ +#define closure_return(_cl) continue_at((_cl), NULL, NULL) + +/** + * continue_at_nobarrier - jump to another function without barrier + * + * Causes @fn to be executed out of @cl, in @wq context (or called directly if + * @wq is NULL). + * + * NOTE: like continue_at(), this macro expands to a return in the caller! + * + * The ref the caller of continue_at_nobarrier() had on @cl is now owned by @fn, + * thus it's not safe to touch anything protected by @cl after a + * continue_at_nobarrier(). + */ +#define continue_at_nobarrier(_cl, _fn, _wq) \ +do { \ + set_closure_fn(_cl, _fn, _wq); \ + closure_queue(_cl); \ + return; \ +} while (0) + +/** + * closure_return - finish execution of a closure, with destructor + * + * Works like closure_return(), except @destructor will be called when all + * outstanding refs on @cl have been dropped; @destructor may be used to safely + * free the memory occupied by @cl, and it is called with the ref on the parent + * closure still held - so @destructor could safely return an item to a + * freelist protected by @cl's parent. + */ +#define closure_return_with_destructor(_cl, _destructor) \ +do { \ + set_closure_fn(_cl, _destructor, NULL); \ + closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1); \ + return; \ +} while (0) + +/** + * closure_call - execute @fn out of a new, uninitialized closure + * + * Typically used when running out of one closure, and we want to run @fn + * asynchronously out of a new closure - @parent will then wait for @cl to + * finish. + */ +static inline void closure_call(struct closure *cl, closure_fn fn, + struct workqueue_struct *wq, + struct closure *parent) +{ + closure_init(cl, parent); + continue_at_nobarrier(cl, fn, wq); +} + +#endif /* _LINUX_CLOSURE_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index db25707aa4..0d1dbbf07a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1240,6 +1240,14 @@ config DEBUG_BLOCK_EXT_DEVT Say N if you are unsure. +config CLOSURE_DEBUG + bool "Debug closures" + select DEBUG_FS + ---help--- + Keeps all active closures in a linked list and provides a debugfs + interface to list them, which makes it possible to see asynchronous + operations that get stuck. + config NOTIFIER_ERROR_INJECTION tristate "Notifier error injection" depends on DEBUG_KERNEL diff --git a/lib/Makefile b/lib/Makefile index a459c31e8c..907c11b788 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \ - percpu-refcount.o percpu_ida.o + percpu-refcount.o percpu_ida.o closure.o obj-y += string_helpers.o obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += kstrtox.o diff --git a/lib/closure.c b/lib/closure.c new file mode 100644 index 0000000000..10ec8a1711 --- /dev/null +++ b/lib/closure.c @@ -0,0 +1,218 @@ +/* + * Asynchronous refcounty things + * + * Copyright 2010, 2011 Kent Overstreet <kent.overstr...@gmail.com> + * Copyright 2012 Google, Inc. + */ + +#include <linux/closure.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +static inline void closure_put_after_sub(struct closure *cl, int flags) +{ + int r = flags & CLOSURE_REMAINING_MASK; + + BUG_ON(flags & CLOSURE_GUARD_MASK); + BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR)); + + /* Must deliver precisely one wakeup */ + if (r == 1 && (flags & CLOSURE_SLEEPING)) + wake_up_process(cl->task); + + if (!r) { + if (cl->fn && !(flags & CLOSURE_DESTRUCTOR)) { + atomic_set(&cl->remaining, + CLOSURE_REMAINING_INITIALIZER); + closure_queue(cl); + } else { + struct closure *parent = cl->parent; + closure_fn *destructor = cl->fn; + + closure_debug_destroy(cl); + + if (destructor) + destructor(cl); + + if (parent) + closure_put(parent); + } + } +} + +/* For clearing flags with the same atomic op as a put */ +void closure_sub(struct closure *cl, int v) +{ + closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining)); +} +EXPORT_SYMBOL(closure_sub); + +/** + * closure_put - decrement a closure's refcount + */ +void closure_put(struct closure *cl) +{ + closure_put_after_sub(cl, atomic_dec_return(&cl->remaining)); +} +EXPORT_SYMBOL(closure_put); + +/** + * closure_wake_up - wake up all closures on a wait list, without memory barrier + */ +void __closure_wake_up(struct closure_waitlist *wait_list) +{ + struct llist_node *list; + struct closure *cl; + struct llist_node *reverse = NULL; + + list = llist_del_all(&wait_list->list); + + /* We first reverse the list to preserve FIFO ordering and fairness */ + + while (list) { + struct llist_node *t = list; + list = llist_next(list); + + t->next = reverse; + reverse = t; + } + + /* Then do the wakeups */ + + while (reverse) { + cl = container_of(reverse, struct closure, list); + reverse = llist_next(reverse); + + closure_set_waiting(cl, 0); + closure_sub(cl, CLOSURE_WAITING + 1); + } +} +EXPORT_SYMBOL(__closure_wake_up); + +/** + * closure_wait - add a closure to a waitlist + * + * @waitlist will own a ref on @cl, which will be released when + * closure_wake_up() is called on @waitlist. + * + */ +bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl) +{ + if (atomic_read(&cl->remaining) & CLOSURE_WAITING) + return false; + + closure_set_waiting(cl, _RET_IP_); + atomic_add(CLOSURE_WAITING + 1, &cl->remaining); + llist_add(&cl->list, &waitlist->list); + + return true; +} +EXPORT_SYMBOL(closure_wait); + +/** + * closure_sync - sleep until a closure a closure has nothing left to wait on + * + * Sleeps until the refcount hits 1 - the thread that's running the closure owns + * the last refcount. + */ +void closure_sync(struct closure *cl) +{ + while (1) { + __closure_start_sleep(cl); + closure_set_ret_ip(cl); + + if ((atomic_read(&cl->remaining) & + CLOSURE_REMAINING_MASK) == 1) + break; + + schedule(); + } + + __closure_end_sleep(cl); +} +EXPORT_SYMBOL(closure_sync); + +#ifdef CONFIG_CLOSURE_DEBUG + +static LIST_HEAD(closure_list); +static DEFINE_SPINLOCK(closure_list_lock); + +void closure_debug_create(struct closure *cl) +{ + unsigned long flags; + + BUG_ON(cl->magic == CLOSURE_MAGIC_ALIVE); + cl->magic = CLOSURE_MAGIC_ALIVE; + + spin_lock_irqsave(&closure_list_lock, flags); + list_add(&cl->all, &closure_list); + spin_unlock_irqrestore(&closure_list_lock, flags); +} +EXPORT_SYMBOL(closure_debug_create); + +void closure_debug_destroy(struct closure *cl) +{ + unsigned long flags; + + BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE); + cl->magic = CLOSURE_MAGIC_DEAD; + + spin_lock_irqsave(&closure_list_lock, flags); + list_del(&cl->all); + spin_unlock_irqrestore(&closure_list_lock, flags); +} +EXPORT_SYMBOL(closure_debug_destroy); + +static struct dentry *debug; + +#define work_data_bits(work) ((unsigned long *)(&(work)->data)) + +static int debug_seq_show(struct seq_file *f, void *data) +{ + struct closure *cl; + spin_lock_irq(&closure_list_lock); + + list_for_each_entry(cl, &closure_list, all) { + int r = atomic_read(&cl->remaining); + + seq_printf(f, "%p: %pF -> %pf p %p r %i ", + cl, (void *) cl->ip, cl->fn, cl->parent, + r & CLOSURE_REMAINING_MASK); + + seq_printf(f, "%s%s%s%s\n", + test_bit(WORK_STRUCT_PENDING, + work_data_bits(&cl->work)) ? "Q" : "", + r & CLOSURE_RUNNING ? "R" : "", + r & CLOSURE_STACK ? "S" : "", + r & CLOSURE_SLEEPING ? "Sl" : ""); + + if (r & CLOSURE_WAITING) + seq_printf(f, " W %pF\n", + (void *) cl->waiting_on); + + seq_printf(f, "\n"); + } + + spin_unlock_irq(&closure_list_lock); + return 0; +} + +static int debug_seq_open(struct inode *inode, struct file *file) +{ + return single_open(file, debug_seq_show, NULL); +} + +static const struct file_operations debug_ops = { + .open = debug_seq_open, + .read = seq_read, + .release = single_release +}; + +static int __init closure_debug_init(void) +{ + debug = debugfs_create_file("closures", 0400, NULL, NULL, &debug_ops); + return 0; +} +late_initcall(closure_debug_init); + +#endif -- 1.8.5.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/