}
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);
+}
+
/*
- * Releasing ioc may nest into another put_io_context() leading to nested
- * fast path release. As the ioc's can't be the same, this is okay but
- * makes lockdep whine. Keep track of nesting and use it as subclass.
+ * Exit and free an icq. Called with both ioc and q locked.
*/
-#ifdef CONFIG_LOCKDEP
-#define ioc_release_depth(q) ((q) ? (q)->ioc_release_depth : 0)
-#define ioc_release_depth_inc(q) (q)->ioc_release_depth++
-#define ioc_release_depth_dec(q) (q)->ioc_release_depth--
-#else
-#define ioc_release_depth(q) 0
-#define ioc_release_depth_inc(q) do { } while (0)
-#define ioc_release_depth_dec(q) do { } while (0)
-#endif
+static void ioc_exit_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);
+
+ if (et->ops.elevator_exit_icq_fn)
+ et->ops.elevator_exit_icq_fn(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 cic's and then frees ioc.
+ * 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);
struct request_queue *last_q = NULL;
+ unsigned long flags;
- spin_lock_irq(&ioc->lock);
+ /*
+ * 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->cic_list)) {
- struct cfq_io_context *cic = hlist_entry(ioc->cic_list.first,
- struct cfq_io_context,
- cic_list);
- struct request_queue *this_q = cic->q;
+ while (!hlist_empty(&ioc->icq_list)) {
+ struct io_cq *icq = hlist_entry(ioc->icq_list.first,
+ struct io_cq, ioc_node);
+ struct request_queue *this_q = icq->q;
if (this_q != last_q) {
/*
*/
if (last_q) {
spin_unlock(last_q->queue_lock);
- spin_unlock_irq(&ioc->lock);
+ spin_unlock_irqrestore(&ioc->lock, flags);
blk_put_queue(last_q);
} else {
- spin_unlock_irq(&ioc->lock);
+ spin_unlock_irqrestore(&ioc->lock, flags);
}
last_q = this_q;
- spin_lock_irq(this_q->queue_lock);
- spin_lock(&ioc->lock);
+ spin_lock_irqsave(this_q->queue_lock, flags);
+ spin_lock_nested(&ioc->lock, 1);
continue;
}
- ioc_release_depth_inc(this_q);
- cic->exit(cic);
- cic->release(cic);
- ioc_release_depth_dec(this_q);
+ ioc_exit_icq(icq);
}
if (last_q) {
spin_unlock(last_q->queue_lock);
- spin_unlock_irq(&ioc->lock);
+ spin_unlock_irqrestore(&ioc->lock, flags);
blk_put_queue(last_q);
} else {
- spin_unlock_irq(&ioc->lock);
+ 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
- * @locked_q: request_queue the caller is holding queue_lock of (hint)
*
* Decrement reference count of @ioc and release it if the count reaches
- * zero. If the caller is holding queue_lock of a queue, it can indicate
- * that with @locked_q. This is an optimization hint and the caller is
- * allowed to pass in %NULL even when it's holding a queue_lock.
+ * zero.
*/
-void put_io_context(struct io_context *ioc, struct request_queue *locked_q)
+void put_io_context(struct io_context *ioc)
{
- struct request_queue *last_q = locked_q;
unsigned long flags;
if (ioc == NULL)
return;
BUG_ON(atomic_long_read(&ioc->refcount) <= 0);
- if (locked_q)
- lockdep_assert_held(locked_q->queue_lock);
-
- if (!atomic_long_dec_and_test(&ioc->refcount))
- return;
/*
- * Destroy @ioc. This is a bit messy because cic's are chained
- * from both ioc and queue, and ioc->lock nests inside queue_lock.
- * The inner ioc->lock should be held to walk our cic_list and then
- * for each cic the outer matching queue_lock should be grabbed.
- * ie. We need to do reverse-order double lock dancing.
- *
- * Another twist is that we are often called with one of the
- * matching queue_locks held as indicated by @locked_q, which
- * prevents performing double-lock dance for other queues.
- *
- * So, we do it in two stages. The fast path uses the queue_lock
- * the caller is holding and, if other queues need to be accessed,
- * uses trylock to avoid introducing locking dependency. This can
- * handle most cases, especially if @ioc was performing IO on only
- * single device.
- *
- * If trylock doesn't cut it, we defer to @ioc->release_work which
- * can do all the double-locking dancing.
+ * Releasing ioc requires reverse order double locking and we may
+ * already be holding a queue_lock. Do it asynchronously from wq.
*/
- spin_lock_irqsave_nested(&ioc->lock, flags,
- ioc_release_depth(locked_q));
-
- while (!hlist_empty(&ioc->cic_list)) {
- struct cfq_io_context *cic = hlist_entry(ioc->cic_list.first,
- struct cfq_io_context,
- cic_list);
- struct request_queue *this_q = cic->q;
-
- if (this_q != last_q) {
- if (last_q && last_q != locked_q)
- spin_unlock(last_q->queue_lock);
- last_q = NULL;
-
- if (!spin_trylock(this_q->queue_lock))
- break;
- last_q = this_q;
- continue;
- }
- ioc_release_depth_inc(this_q);
- cic->exit(cic);
- cic->release(cic);
- ioc_release_depth_dec(this_q);
+ 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);
+ spin_unlock_irqrestore(&ioc->lock, flags);
}
-
- if (last_q && last_q != locked_q)
- spin_unlock(last_q->queue_lock);
-
- spin_unlock_irqrestore(&ioc->lock, flags);
-
- /* if no cic's left, we're done; otherwise, kick release_work */
- if (hlist_empty(&ioc->cic_list))
- kmem_cache_free(iocontext_cachep, ioc);
- else
- schedule_work(&ioc->release_work);
}
EXPORT_SYMBOL(put_io_context);
{
struct io_context *ioc;
- /* PF_EXITING prevents new io_context from being attached to @task */
- WARN_ON_ONCE(!(current->flags & PF_EXITING));
-
task_lock(task);
ioc = task->io_context;
task->io_context = NULL;
task_unlock(task);
atomic_dec(&ioc->nr_tasks);
- put_io_context(ioc, NULL);
+ put_io_context(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_exit_icq(icq);
+ spin_unlock(&ioc->lock);
+ }
}
void create_io_context_slowpath(struct task_struct *task, gfp_t gfp_flags,
atomic_long_set(&ioc->refcount, 1);
atomic_set(&ioc->nr_tasks, 1);
spin_lock_init(&ioc->lock);
- INIT_RADIX_TREE(&ioc->radix_root, GFP_ATOMIC | __GFP_HIGH);
- INIT_HLIST_HEAD(&ioc->cic_list);
+ 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, somebody might already have beaten us to it */
+ /*
+ * 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->flags & PF_EXITING))
+ if (!task->io_context &&
+ (task == current || !(task->flags & PF_EXITING)))
task->io_context = ioc;
else
kmem_cache_free(iocontext_cachep, ioc);
task_unlock(task);
}
-EXPORT_SYMBOL(create_io_context_slowpath);
/**
* get_task_io_context - get io_context of a task
}
EXPORT_SYMBOL(get_task_io_context);
+/**
+ * ioc_lookup_icq - lookup io_cq from ioc
+ * @ioc: the associated io_context
+ * @q: the associated request_queue
+ *
+ * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called
+ * with @q->queue_lock held.
+ */
+struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q)
+{
+ struct io_cq *icq;
+
+ lockdep_assert_held(q->queue_lock);
+
+ /*
+ * icq's are indexed from @ioc using radix tree and hint pointer,
+ * both of which are protected with RCU. All removals are done
+ * holding both q and ioc locks, and we're holding q lock - if we
+ * find a icq which points to us, it's guaranteed to be valid.
+ */
+ rcu_read_lock();
+ icq = rcu_dereference(ioc->icq_hint);
+ if (icq && icq->q == q)
+ goto out;
+
+ icq = radix_tree_lookup(&ioc->icq_tree, q->id);
+ if (icq && icq->q == q)
+ rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */
+ else
+ icq = NULL;
+out:
+ rcu_read_unlock();
+ return icq;
+}
+EXPORT_SYMBOL(ioc_lookup_icq);
+
+/**
+ * ioc_create_icq - create and link io_cq
+ * @q: request_queue of interest
+ * @gfp_mask: allocation mask
+ *
+ * Make sure io_cq linking %current->io_context and @q exists. If either
+ * io_context and/or icq don't exist, they will be created using @gfp_mask.
+ *
+ * The caller is responsible for ensuring @ioc won't go away and @q is
+ * alive and will stay alive until this function returns.
+ */
+struct io_cq *ioc_create_icq(struct request_queue *q, gfp_t gfp_mask)
+{
+ struct elevator_type *et = q->elevator->type;
+ struct io_context *ioc;
+ struct io_cq *icq;
+
+ /* allocate stuff */
+ ioc = create_io_context(current, gfp_mask, q->node);
+ if (!ioc)
+ return NULL;
+
+ icq = kmem_cache_alloc_node(et->icq_cache, gfp_mask | __GFP_ZERO,
+ q->node);
+ if (!icq)
+ return NULL;
+
+ if (radix_tree_preload(gfp_mask) < 0) {
+ kmem_cache_free(et->icq_cache, icq);
+ return NULL;
+ }
+
+ icq->ioc = ioc;
+ icq->q = q;
+ INIT_LIST_HEAD(&icq->q_node);
+ INIT_HLIST_NODE(&icq->ioc_node);
+
+ /* lock both q and ioc and try to link @icq */
+ spin_lock_irq(q->queue_lock);
+ spin_lock(&ioc->lock);
+
+ if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
+ hlist_add_head(&icq->ioc_node, &ioc->icq_list);
+ list_add(&icq->q_node, &q->icq_list);
+ if (et->ops.elevator_init_icq_fn)
+ et->ops.elevator_init_icq_fn(icq);
+ } else {
+ kmem_cache_free(et->icq_cache, icq);
+ icq = ioc_lookup_icq(ioc, q);
+ if (!icq)
+ printk(KERN_ERR "cfq: icq link failed!\n");
+ }
+
+ spin_unlock(&ioc->lock);
+ spin_unlock_irq(q->queue_lock);
+ radix_tree_preload_end();
+ return icq;
+}
+
void ioc_set_changed(struct io_context *ioc, int which)
{
- struct cfq_io_context *cic;
+ struct io_cq *icq;
struct hlist_node *n;
- hlist_for_each_entry(cic, n, &ioc->cic_list, cic_list)
- set_bit(which, &cic->changed);
+ hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node)
+ set_bit(which, &icq->changed);
}
/**
* @ioc: io_context of interest
* @ioprio: new ioprio
*
- * @ioc's ioprio has changed to @ioprio. Set %CIC_IOPRIO_CHANGED for all
- * cic's. iosched is responsible for checking the bit and applying it on
+ * @ioc's ioprio has changed to @ioprio. Set %ICQ_IOPRIO_CHANGED for all
+ * icq's. iosched is responsible for checking the bit and applying it on
* request issue path.
*/
void ioc_ioprio_changed(struct io_context *ioc, int ioprio)
spin_lock_irqsave(&ioc->lock, flags);
ioc->ioprio = ioprio;
- ioc_set_changed(ioc, CIC_IOPRIO_CHANGED);
+ ioc_set_changed(ioc, ICQ_IOPRIO_CHANGED);
spin_unlock_irqrestore(&ioc->lock, flags);
}
* ioc_cgroup_changed - notify cgroup change
* @ioc: io_context of interest
*
- * @ioc's cgroup has changed. Set %CIC_CGROUP_CHANGED for all cic's.
+ * @ioc's cgroup has changed. Set %ICQ_CGROUP_CHANGED for all icq's.
* iosched is responsible for checking the bit and applying it on request
* issue path.
*/
unsigned long flags;
spin_lock_irqsave(&ioc->lock, flags);
- ioc_set_changed(ioc, CIC_CGROUP_CHANGED);
+ ioc_set_changed(ioc, ICQ_CGROUP_CHANGED);
spin_unlock_irqrestore(&ioc->lock, flags);
}
+EXPORT_SYMBOL(ioc_cgroup_changed);
static int __init blk_ioc_init(void)
{