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;
- }
|