| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274 | /* * Functions related to io context handling */#include <linux/kernel.h>#include <linux/module.h>#include <linux/init.h>#include <linux/bio.h>#include <linux/blkdev.h>#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */#include <linux/slab.h>#include "blk.h"/* * For io context allocations */static struct kmem_cache *iocontext_cachep;/** * get_io_context - increment reference count to io_context * @ioc: io_context to get * * Increment reference count to @ioc. */void get_io_context(struct io_context *ioc){	BUG_ON(atomic_long_read(&ioc->refcount) <= 0);	atomic_long_inc(&ioc->refcount);}EXPORT_SYMBOL(get_io_context);static void icq_free_icq_rcu(struct rcu_head *head){	struct io_cq *icq = container_of(head, struct io_cq, __rcu_head);	kmem_cache_free(icq->__rcu_icq_cache, icq);}/* Exit an icq. Called with both ioc and q locked. */static void ioc_exit_icq(struct io_cq *icq){	struct elevator_type *et = icq->q->elevator->type;	if (icq->flags & ICQ_EXITED)		return;	if (et->ops.elevator_exit_icq_fn)		et->ops.elevator_exit_icq_fn(icq);	icq->flags |= ICQ_EXITED;}/* Release an icq.  Called with both ioc and q locked. */static void ioc_destroy_icq(struct io_cq *icq){	struct io_context *ioc = icq->ioc;	struct request_queue *q = icq->q;	struct elevator_type *et = q->elevator->type;	lockdep_assert_held(&ioc->lock);	lockdep_assert_held(q->queue_lock);	radix_tree_delete(&ioc->icq_tree, icq->q->id);	hlist_del_init(&icq->ioc_node);	list_del_init(&icq->q_node);	/*	 * Both setting lookup hint to and clearing it from @icq are done	 * under queue_lock.  If it's not pointing to @icq now, it never	 * will.  Hint assignment itself can race safely.	 */	if (rcu_dereference_raw(ioc->icq_hint) == icq)		rcu_assign_pointer(ioc->icq_hint, NULL);	ioc_exit_icq(icq);	/*	 * @icq->q might have gone away by the time RCU callback runs	 * making it impossible to determine icq_cache.  Record it in @icq.	 */	icq->__rcu_icq_cache = et->icq_cache;	call_rcu(&icq->__rcu_head, icq_free_icq_rcu);}/* * Slow path for ioc release in put_io_context().  Performs double-lock * dancing to unlink all icq's and then frees ioc. */static void ioc_release_fn(struct work_struct *work){	struct io_context *ioc = container_of(work, struct io_context,					      release_work);	unsigned long flags;	/*	 * Exiting icq may call into put_io_context() through elevator	 * which will trigger lockdep warning.  The ioc's are guaranteed to	 * be different, use a different locking subclass here.  Use	 * irqsave variant as there's no spin_lock_irq_nested().	 */	spin_lock_irqsave_nested(&ioc->lock, flags, 1);	while (!hlist_empty(&ioc->icq_list)) {		struct io_cq *icq = hlist_entry(ioc->icq_list.first,						struct io_cq, ioc_node);		struct request_queue *q = icq->q;		if (spin_trylock(q->queue_lock)) {			ioc_destroy_icq(icq);			spin_unlock(q->queue_lock);		} else {			spin_unlock_irqrestore(&ioc->lock, flags);			cpu_relax();			spin_lock_irqsave_nested(&ioc->lock, flags, 1);		}	}	spin_unlock_irqrestore(&ioc->lock, flags);	kmem_cache_free(iocontext_cachep, ioc);}/** * put_io_context - put a reference of io_context * @ioc: io_context to put * * Decrement reference count of @ioc and release it if the count reaches * zero. */void put_io_context(struct io_context *ioc){	unsigned long flags;	bool free_ioc = false;	if (ioc == NULL)		return;	BUG_ON(atomic_long_read(&ioc->refcount) <= 0);	/*	 * Releasing ioc requires reverse order double locking and we may	 * already be holding a queue_lock.  Do it asynchronously from wq.	 */	if (atomic_long_dec_and_test(&ioc->refcount)) {		spin_lock_irqsave(&ioc->lock, flags);		if (!hlist_empty(&ioc->icq_list))			schedule_work(&ioc->release_work);		else			free_ioc = true;		spin_unlock_irqrestore(&ioc->lock, flags);	}	if (free_ioc)		kmem_cache_free(iocontext_cachep, ioc);}EXPORT_SYMBOL(put_io_context);/** * put_io_context_active - put active reference on ioc * @ioc: ioc of interest * * Undo get_io_context_active().  If active reference reaches zero after * put, @ioc can never issue further IOs and ioscheds are notified. */void put_io_context_active(struct io_context *ioc){	struct hlist_node *n;	unsigned long flags;	struct io_cq *icq;	if (!atomic_dec_and_test(&ioc->active_ref)) {		put_io_context(ioc);		return;	}	/*	 * Need ioc lock to walk icq_list and q lock to exit icq.  Perform	 * reverse double locking.  Read comment in ioc_release_fn() for	 * explanation on the nested locking annotation.	 */retry:	spin_lock_irqsave_nested(&ioc->lock, flags, 1);	hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node) {		if (icq->flags & ICQ_EXITED)			continue;		if (spin_trylock(icq->q->queue_lock)) {			ioc_exit_icq(icq);			spin_unlock(icq->q->queue_lock);		} else {			spin_unlock_irqrestore(&ioc->lock, flags);			cpu_relax();			goto retry;		}	}	spin_unlock_irqrestore(&ioc->lock, flags);	put_io_context(ioc);}/* Called by the exiting task */void exit_io_context(struct task_struct *task){	struct io_context *ioc;	task_lock(task);	ioc = task->io_context;	task->io_context = NULL;	task_unlock(task);	atomic_dec(&ioc->nr_tasks);	put_io_context_active(ioc);}/** * ioc_clear_queue - break any ioc association with the specified queue * @q: request_queue being cleared * * Walk @q->icq_list and exit all io_cq's.  Must be called with @q locked. */void ioc_clear_queue(struct request_queue *q){	lockdep_assert_held(q->queue_lock);	while (!list_empty(&q->icq_list)) {		struct io_cq *icq = list_entry(q->icq_list.next,					       struct io_cq, q_node);		struct io_context *ioc = icq->ioc;		spin_lock(&ioc->lock);		ioc_destroy_icq(icq);		spin_unlock(&ioc->lock);	}}int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node){	struct io_context *ioc;	int ret;	ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO,				    node);	if (unlikely(!ioc))		return -ENOMEM;	/* initialize */	atomic_long_set(&ioc->refcount, 1);	atomic_set(&ioc->nr_tasks, 1);	atomic_set(&ioc->active_ref, 1);	spin_lock_init(&ioc->lock);	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC | __GFP_HIGH);	INIT_HLIST_HEAD(&ioc->icq_list);	INIT_WORK(&ioc->release_work, ioc_release_fn);	/*	 * Try to install.  ioc shouldn't be installed if someone else	 * already did or @task, which isn't %current, is exiting.  Note	 * that we need to allow ioc creation on exiting %current as exit	 * path may issue IOs from e.g. exit_files().  The exit path is	 * responsible for not issuing IO after exit_io_context().	 */	task_lock(task);	if (!task->io_context &&	    (task == current || !(task->flags & PF_EXITING)))		task->io_context = ioc;	else		kmem_cache_free(iocontext_cachep, ioc);	ret = task->io_context ? 0 : -EBUSY;	task_unlock(task);	return ret;}
 |