Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit c5869807 authored by Tejun Heo's avatar Tejun Heo Committed by Jens Axboe
Browse files

block, cfq: reorganize cfq_io_context into generic and cfq specific parts 



Currently io_context and cfq logics are mixed without clear boundary.
Most of io_context is independent from cfq but cfq_io_context handling
logic is dispersed between generic ioc code and cfq.

cfq_io_context represents association between an io_context and a
request_queue, which is a concept useful outside of cfq, but it also
contains fields which are useful only to cfq.

This patch takes out generic part and put it into io_cq (io
context-queue) and the rest into cfq_io_cq (cic moniker remains the
same) which contains io_cq.  The following changes are made together.

* cfq_ttime and cfq_io_cq now live in cfq-iosched.c.

* All related fields, functions and constants are renamed accordingly.

* ioc->ioc_data is now "struct io_cq *" instead of "void *" and
  renamed to icq_hint.

This prepares for io_context API cleanup.  Documentation is currently
sparse.  It will be added later.

Changes in this patch are mechanical and don't cause functional
change.

Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 22f746e2

block/blk-ioc.c

+28 −30
Original line number Diff line number Diff line
@@ -46,7 +46,7 @@ EXPORT_SYMBOL(get_io_context); 


/*

 * 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)

{
@@ -56,11 +56,10 @@ static void ioc_release_fn(struct work_struct *work) 


	spin_lock_irq(&ioc->lock);



	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) {

			/*
@@ -89,8 +88,8 @@ static void ioc_release_fn(struct work_struct *work) 
			continue;

		}

		ioc_release_depth_inc(this_q);

		cic->exit(cic);

		cic->release(cic);

		icq->exit(icq);

		icq->release(icq);

		ioc_release_depth_dec(this_q);

	}
@@ -131,10 +130,10 @@ void put_io_context(struct io_context *ioc, struct request_queue *locked_q) 
		return;



	/*

	 * Destroy @ioc.  This is a bit messy because cic's are chained

	 * Destroy @ioc.  This is a bit messy because icq'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.

	 * The inner ioc->lock should be held to walk our icq_list and then

	 * for each icq 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
@@ -153,11 +152,10 @@ void put_io_context(struct io_context *ioc, struct request_queue *locked_q) 
	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;

	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 && last_q != locked_q)
@@ -170,8 +168,8 @@ void put_io_context(struct io_context *ioc, struct request_queue *locked_q) 
			continue;

		}

		ioc_release_depth_inc(this_q);

		cic->exit(cic);

		cic->release(cic);

		icq->exit(icq);

		icq->release(icq);

		ioc_release_depth_dec(this_q);

	}
@@ -180,8 +178,8 @@ void put_io_context(struct io_context *ioc, struct request_queue *locked_q) 


	spin_unlock_irqrestore(&ioc->lock, flags);



	/* if no cic's left, we're done; otherwise, kick release_work */

	if (hlist_empty(&ioc->cic_list))

	/* if no icq is left, we're done; otherwise, kick release_work */

	if (hlist_empty(&ioc->icq_list))

		kmem_cache_free(iocontext_cachep, ioc);

	else

		schedule_work(&ioc->release_work);
@@ -219,8 +217,8 @@ 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 */
@@ -270,11 +268,11 @@ EXPORT_SYMBOL(get_task_io_context); 


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);

}



/**
@@ -282,8 +280,8 @@ void ioc_set_changed(struct io_context *ioc, int which) 
 * @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)
@@ -292,7 +290,7 @@ 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);

}
@@ -300,7 +298,7 @@ void ioc_ioprio_changed(struct io_context *ioc, int ioprio) 
 * 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.

 */
@@ -309,7 +307,7 @@ void ioc_cgroup_changed(struct io_context *ioc) 
	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);

}

block/cfq-iosched.c

+133 −115
Original line number Diff line number Diff line
@@ -54,13 +54,12 @@ static const int cfq_hist_divisor = 4; 
#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)

#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)



#define RQ_CIC(rq)		\

	((struct cfq_io_context *) (rq)->elevator_private[0])

#define RQ_CIC(rq)		icq_to_cic((rq)->elevator_private[0])

#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private[1])

#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private[2])



static struct kmem_cache *cfq_pool;

static struct kmem_cache *cfq_ioc_pool;

static struct kmem_cache *cfq_icq_pool;



#define CFQ_PRIO_LISTS		IOPRIO_BE_NR

#define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
@@ -69,6 +68,14 @@ static struct kmem_cache *cfq_ioc_pool; 
#define sample_valid(samples)	((samples) > 80)

#define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)



struct cfq_ttime {

	unsigned long last_end_request;



	unsigned long ttime_total;

	unsigned long ttime_samples;

	unsigned long ttime_mean;

};



/*

 * Most of our rbtree usage is for sorting with min extraction, so

 * if we cache the leftmost node we don't have to walk down the tree
@@ -210,6 +217,12 @@ struct cfq_group { 
	struct cfq_ttime ttime;

};



struct cfq_io_cq {

	struct io_cq		icq;		/* must be the first member */

	struct cfq_queue	*cfqq[2];

	struct cfq_ttime	ttime;

};



/*

 * Per block device queue structure

 */
@@ -261,7 +274,7 @@ struct cfq_data { 
	struct work_struct unplug_work;



	struct cfq_queue *active_queue;

	struct cfq_io_context *active_cic;

	struct cfq_io_cq *active_cic;



	/*

	 * async queue for each priority case
@@ -284,7 +297,7 @@ struct cfq_data { 
	unsigned int cfq_group_idle;

	unsigned int cfq_latency;



	struct list_head cic_list;

	struct list_head icq_list;



	/*

	 * Fallback dummy cfqq for extreme OOM conditions
@@ -457,24 +470,28 @@ static inline int cfqg_busy_async_queues(struct cfq_data *cfqd, 
static void cfq_dispatch_insert(struct request_queue *, struct request *);

static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,

				       struct io_context *, gfp_t);

static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,

						struct io_context *);

static struct cfq_io_cq *cfq_cic_lookup(struct cfq_data *, struct io_context *);



static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,

					    bool is_sync)

static inline struct cfq_io_cq *icq_to_cic(struct io_cq *icq)

{

	/* cic->icq is the first member, %NULL will convert to %NULL */

	return container_of(icq, struct cfq_io_cq, icq);

}



static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_cq *cic, bool is_sync)

{

	return cic->cfqq[is_sync];

}



static inline void cic_set_cfqq(struct cfq_io_context *cic,

				struct cfq_queue *cfqq, bool is_sync)

static inline void cic_set_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq,

				bool is_sync)

{

	cic->cfqq[is_sync] = cfqq;

}



static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic)

static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic)

{

	return cic->q->elevator->elevator_data;

	return cic->icq.q->elevator->elevator_data;

}



/*
@@ -1541,7 +1558,7 @@ static struct request * 
cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)

{

	struct task_struct *tsk = current;

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;

	struct cfq_queue *cfqq;



	cic = cfq_cic_lookup(cfqd, tsk->io_context);
@@ -1655,7 +1672,7 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq, 
			   struct bio *bio)

{

	struct cfq_data *cfqd = q->elevator->elevator_data;

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;

	struct cfq_queue *cfqq;



	/*
@@ -1671,7 +1688,7 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq, 
	 * and %current are guaranteed to be equal.  Avoid lookup which

	 * requires queue_lock by using @rq's cic.

	 */

	if (current->io_context == RQ_CIC(rq)->ioc) {

	if (current->io_context == RQ_CIC(rq)->icq.ioc) {

		cic = RQ_CIC(rq);

	} else {

		cic = cfq_cic_lookup(cfqd, current->io_context);
@@ -1761,7 +1778,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, 
		cfqd->active_queue = NULL;



	if (cfqd->active_cic) {

		put_io_context(cfqd->active_cic->ioc, cfqd->queue);

		put_io_context(cfqd->active_cic->icq.ioc, cfqd->queue);

		cfqd->active_cic = NULL;

	}

}
@@ -1981,7 +1998,7 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq) 
static void cfq_arm_slice_timer(struct cfq_data *cfqd)

{

	struct cfq_queue *cfqq = cfqd->active_queue;

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;

	unsigned long sl, group_idle = 0;



	/*
@@ -2016,7 +2033,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) 
	 * task has exited, don't wait

	 */

	cic = cfqd->active_cic;

	if (!cic || !atomic_read(&cic->ioc->nr_tasks))

	if (!cic || !atomic_read(&cic->icq.ioc->nr_tasks))

		return;



	/*
@@ -2567,9 +2584,9 @@ static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq) 
	cfq_dispatch_insert(cfqd->queue, rq);



	if (!cfqd->active_cic) {

		struct cfq_io_context *cic = RQ_CIC(rq);

		struct cfq_io_cq *cic = RQ_CIC(rq);



		atomic_long_inc(&cic->ioc->refcount);

		atomic_long_inc(&cic->icq.ioc->refcount);

		cfqd->active_cic = cic;

	}
@@ -2652,24 +2669,24 @@ static void cfq_put_queue(struct cfq_queue *cfqq) 
	cfq_put_cfqg(cfqg);

}



static void cfq_cic_free_rcu(struct rcu_head *head)

static void cfq_icq_free_rcu(struct rcu_head *head)

{

	kmem_cache_free(cfq_ioc_pool,

			container_of(head, struct cfq_io_context, rcu_head));

	kmem_cache_free(cfq_icq_pool,

			icq_to_cic(container_of(head, struct io_cq, rcu_head)));

}



static void cfq_cic_free(struct cfq_io_context *cic)

static void cfq_icq_free(struct io_cq *icq)

{

	call_rcu(&cic->rcu_head, cfq_cic_free_rcu);

	call_rcu(&icq->rcu_head, cfq_icq_free_rcu);

}



static void cfq_release_cic(struct cfq_io_context *cic)

static void cfq_release_icq(struct io_cq *icq)

{

	struct io_context *ioc = cic->ioc;

	struct io_context *ioc = icq->ioc;



	radix_tree_delete(&ioc->radix_root, cic->q->id);

	hlist_del(&cic->cic_list);

	cfq_cic_free(cic);

	radix_tree_delete(&ioc->icq_tree, icq->q->id);

	hlist_del(&icq->ioc_node);

	cfq_icq_free(icq);

}



static void cfq_put_cooperator(struct cfq_queue *cfqq)
@@ -2705,20 +2722,21 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) 
	cfq_put_queue(cfqq);

}



static void cfq_exit_cic(struct cfq_io_context *cic)

static void cfq_exit_icq(struct io_cq *icq)

{

	struct cfq_io_cq *cic = icq_to_cic(icq);

	struct cfq_data *cfqd = cic_to_cfqd(cic);

	struct io_context *ioc = cic->ioc;

	struct io_context *ioc = icq->ioc;



	list_del_init(&cic->queue_list);

	list_del_init(&icq->q_node);



	/*

	 * Both setting lookup hint to and clearing it from @cic are done

	 * under queue_lock.  If it's not pointing to @cic now, it never

	 * 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->ioc_data) == cic)

		rcu_assign_pointer(ioc->ioc_data, NULL);

	if (rcu_dereference_raw(ioc->icq_hint) == icq)

		rcu_assign_pointer(ioc->icq_hint, NULL);



	if (cic->cfqq[BLK_RW_ASYNC]) {

		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
@@ -2731,19 +2749,18 @@ static void cfq_exit_cic(struct cfq_io_context *cic) 
	}

}



static struct cfq_io_context *

cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)

static struct cfq_io_cq *cfq_alloc_cic(struct cfq_data *cfqd, gfp_t gfp_mask)

{

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;



	cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask | __GFP_ZERO,

	cic = kmem_cache_alloc_node(cfq_icq_pool, gfp_mask | __GFP_ZERO,

							cfqd->queue->node);

	if (cic) {

		cic->ttime.last_end_request = jiffies;

		INIT_LIST_HEAD(&cic->queue_list);

		INIT_HLIST_NODE(&cic->cic_list);

		cic->exit = cfq_exit_cic;

		cic->release = cfq_release_cic;

		INIT_LIST_HEAD(&cic->icq.q_node);

		INIT_HLIST_NODE(&cic->icq.ioc_node);

		cic->icq.exit = cfq_exit_icq;

		cic->icq.release = cfq_release_icq;

	}



	return cic;
@@ -2791,7 +2808,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) 
	cfq_clear_cfqq_prio_changed(cfqq);

}



static void changed_ioprio(struct cfq_io_context *cic)

static void changed_ioprio(struct cfq_io_cq *cic)

{

	struct cfq_data *cfqd = cic_to_cfqd(cic);

	struct cfq_queue *cfqq;
@@ -2802,7 +2819,7 @@ static void changed_ioprio(struct cfq_io_context *cic) 
	cfqq = cic->cfqq[BLK_RW_ASYNC];

	if (cfqq) {

		struct cfq_queue *new_cfqq;

		new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc,

		new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->icq.ioc,

						GFP_ATOMIC);

		if (new_cfqq) {

			cic->cfqq[BLK_RW_ASYNC] = new_cfqq;
@@ -2836,7 +2853,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, 
}



#ifdef CONFIG_CFQ_GROUP_IOSCHED

static void changed_cgroup(struct cfq_io_context *cic)

static void changed_cgroup(struct cfq_io_cq *cic)

{

	struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);

	struct cfq_data *cfqd = cic_to_cfqd(cic);
@@ -2864,7 +2881,7 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync, 
		     struct io_context *ioc, gfp_t gfp_mask)

{

	struct cfq_queue *cfqq, *new_cfqq = NULL;

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;

	struct cfq_group *cfqg;



retry:
@@ -2956,56 +2973,57 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc, 
}



/**

 * cfq_cic_lookup - lookup cfq_io_context

 * cfq_cic_lookup - lookup cfq_io_cq

 * @cfqd: the associated cfq_data

 * @ioc: the associated io_context

 *

 * Look up cfq_io_context associated with @cfqd - @ioc pair.  Must be

 * called with queue_lock held.

 * Look up cfq_io_cq associated with @cfqd - @ioc pair.  Must be called

 * with queue_lock held.

 */

static struct cfq_io_context *

static struct cfq_io_cq *

cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)

{

	struct request_queue *q = cfqd->queue;

	struct cfq_io_context *cic;

	struct io_cq *icq;



	lockdep_assert_held(cfqd->queue->queue_lock);

	if (unlikely(!ioc))

		return NULL;



	/*

	 * cic's are indexed from @ioc using radix tree and hint pointer,

	 * 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 cic which points to us, it's guaranteed to be valid.

	 * find a icq which points to us, it's guaranteed to be valid.

	 */

	rcu_read_lock();

	cic = rcu_dereference(ioc->ioc_data);

	if (cic && cic->q == q)

	icq = rcu_dereference(ioc->icq_hint);

	if (icq && icq->q == q)

		goto out;



	cic = radix_tree_lookup(&ioc->radix_root, cfqd->queue->id);

	if (cic && cic->q == q)

		rcu_assign_pointer(ioc->ioc_data, cic);	/* allowed to race */

	icq = radix_tree_lookup(&ioc->icq_tree, cfqd->queue->id);

	if (icq && icq->q == q)

		rcu_assign_pointer(ioc->icq_hint, icq);	/* allowed to race */

	else

		cic = NULL;

		icq = NULL;

out:

	rcu_read_unlock();

	return cic;

	return icq_to_cic(icq);

}



/**

 * cfq_create_cic - create and link a cfq_io_context

 * cfq_create_cic - create and link a cfq_io_cq

 * @cfqd: cfqd of interest

 * @gfp_mask: allocation mask

 *

 * Make sure cfq_io_context linking %current->io_context and @cfqd exists.

 * If ioc and/or cic doesn't exist, they will be created using @gfp_mask.

 * Make sure cfq_io_cq linking %current->io_context and @cfqd exists.  If

 * ioc and/or cic doesn't exist, they will be created using @gfp_mask.

 */

static int cfq_create_cic(struct cfq_data *cfqd, gfp_t gfp_mask)

{

	struct request_queue *q = cfqd->queue;

	struct cfq_io_context *cic = NULL;

	struct io_cq *icq = NULL;

	struct cfq_io_cq *cic;

	struct io_context *ioc;

	int ret = -ENOMEM;
@@ -3016,26 +3034,27 @@ static int cfq_create_cic(struct cfq_data *cfqd, gfp_t gfp_mask) 
	if (!ioc)

		goto out;



	cic = cfq_alloc_io_context(cfqd, gfp_mask);

	cic = cfq_alloc_cic(cfqd, gfp_mask);

	if (!cic)

		goto out;

	icq = &cic->icq;



	ret = radix_tree_preload(gfp_mask);

	if (ret)

		goto out;



	cic->ioc = ioc;

	cic->q = cfqd->queue;

	icq->ioc = ioc;

	icq->q = cfqd->queue;



	/* lock both q and ioc and try to link @cic */

	/* lock both q and ioc and try to link @icq */

	spin_lock_irq(q->queue_lock);

	spin_lock(&ioc->lock);



	ret = radix_tree_insert(&ioc->radix_root, q->id, cic);

	ret = radix_tree_insert(&ioc->icq_tree, q->id, icq);

	if (likely(!ret)) {

		hlist_add_head(&cic->cic_list, &ioc->cic_list);

		list_add(&cic->queue_list, &cfqd->cic_list);

		cic = NULL;

		hlist_add_head(&icq->ioc_node, &ioc->icq_list);

		list_add(&icq->q_node, &cfqd->icq_list);

		icq = NULL;

	} else if (ret == -EEXIST) {

		/* someone else already did it */

		ret = 0;
@@ -3047,29 +3066,28 @@ static int cfq_create_cic(struct cfq_data *cfqd, gfp_t gfp_mask) 
	radix_tree_preload_end();

out:

	if (ret)

		printk(KERN_ERR "cfq: cic link failed!\n");

	if (cic)

		cfq_cic_free(cic);

		printk(KERN_ERR "cfq: icq link failed!\n");

	if (icq)

		cfq_icq_free(icq);

	return ret;

}



/**

 * cfq_get_io_context - acquire cfq_io_context and bump refcnt on io_context

 * cfq_get_cic - acquire cfq_io_cq and bump refcnt on io_context

 * @cfqd: cfqd to setup cic for

 * @gfp_mask: allocation mask

 *

 * Return cfq_io_context associating @cfqd and %current->io_context and

 * Return cfq_io_cq associating @cfqd and %current->io_context and

 * bump refcnt on io_context.  If ioc or cic doesn't exist, they're created

 * using @gfp_mask.

 *

 * Must be called under queue_lock which may be released and re-acquired.

 * This function also may sleep depending on @gfp_mask.

 */

static struct cfq_io_context *

cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)

static struct cfq_io_cq *cfq_get_cic(struct cfq_data *cfqd, gfp_t gfp_mask)

{

	struct request_queue *q = cfqd->queue;

	struct cfq_io_context *cic = NULL;

	struct cfq_io_cq *cic = NULL;

	struct io_context *ioc;

	int err;
@@ -3095,11 +3113,11 @@ cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) 
	/* bump @ioc's refcnt and handle changed notifications */

	get_io_context(ioc);



	if (unlikely(cic->changed)) {

		if (test_and_clear_bit(CIC_IOPRIO_CHANGED, &cic->changed))

	if (unlikely(cic->icq.changed)) {

		if (test_and_clear_bit(ICQ_IOPRIO_CHANGED, &cic->icq.changed))

			changed_ioprio(cic);

#ifdef CONFIG_CFQ_GROUP_IOSCHED

		if (test_and_clear_bit(CIC_CGROUP_CHANGED, &cic->changed))

		if (test_and_clear_bit(ICQ_CGROUP_CHANGED, &cic->icq.changed))

			changed_cgroup(cic);

#endif

	}
@@ -3120,7 +3138,7 @@ __cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle) 


static void

cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_queue *cfqq,

	struct cfq_io_context *cic)

			struct cfq_io_cq *cic)

{

	if (cfq_cfqq_sync(cfqq)) {

		__cfq_update_io_thinktime(&cic->ttime, cfqd->cfq_slice_idle);
@@ -3158,7 +3176,7 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq, 
 */

static void

cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,

		       struct cfq_io_context *cic)

		       struct cfq_io_cq *cic)

{

	int old_idle, enable_idle;
@@ -3175,7 +3193,8 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, 


	if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE))

		enable_idle = 0;

	else if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||

	else if (!atomic_read(&cic->icq.ioc->nr_tasks) ||

		 !cfqd->cfq_slice_idle ||

		 (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))

		enable_idle = 0;

	else if (sample_valid(cic->ttime.ttime_samples)) {
@@ -3308,7 +3327,7 @@ static void 
cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,

		struct request *rq)

{

	struct cfq_io_context *cic = RQ_CIC(rq);

	struct cfq_io_cq *cic = RQ_CIC(rq);



	cfqd->rq_queued++;

	if (rq->cmd_flags & REQ_PRIO)
@@ -3361,7 +3380,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) 
	struct cfq_queue *cfqq = RQ_CFQQ(rq);



	cfq_log_cfqq(cfqd, cfqq, "insert_request");

	cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);

	cfq_init_prio_data(cfqq, RQ_CIC(rq)->icq.ioc);



	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);

	list_add_tail(&rq->queuelist, &cfqq->fifo);
@@ -3411,7 +3430,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd) 


static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)

{

	struct cfq_io_context *cic = cfqd->active_cic;

	struct cfq_io_cq *cic = cfqd->active_cic;



	/* If the queue already has requests, don't wait */

	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
@@ -3548,7 +3567,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) 
{

	struct cfq_data *cfqd = q->elevator->elevator_data;

	struct task_struct *tsk = current;

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;

	struct cfq_queue *cfqq;



	/*
@@ -3563,7 +3582,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) 


	cfqq = cic_to_cfqq(cic, rw_is_sync(rw));

	if (cfqq) {

		cfq_init_prio_data(cfqq, cic->ioc);

		cfq_init_prio_data(cfqq, cic->icq.ioc);



		return __cfq_may_queue(cfqq);

	}
@@ -3584,7 +3603,7 @@ static void cfq_put_request(struct request *rq) 
		BUG_ON(!cfqq->allocated[rw]);

		cfqq->allocated[rw]--;



		put_io_context(RQ_CIC(rq)->ioc, cfqq->cfqd->queue);

		put_io_context(RQ_CIC(rq)->icq.ioc, cfqq->cfqd->queue);



		rq->elevator_private[0] = NULL;

		rq->elevator_private[1] = NULL;
@@ -3598,7 +3617,7 @@ static void cfq_put_request(struct request *rq) 
}



static struct cfq_queue *

cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,

cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_cq *cic,

		struct cfq_queue *cfqq)

{

	cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq);
@@ -3613,7 +3632,7 @@ cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic, 
 * was the last process referring to said cfqq.

 */

static struct cfq_queue *

split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)

split_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq)

{

	if (cfqq_process_refs(cfqq) == 1) {

		cfqq->pid = current->pid;
@@ -3636,7 +3655,7 @@ static int 
cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)

{

	struct cfq_data *cfqd = q->elevator->elevator_data;

	struct cfq_io_context *cic;

	struct cfq_io_cq *cic;

	const int rw = rq_data_dir(rq);

	const bool is_sync = rq_is_sync(rq);

	struct cfq_queue *cfqq;
@@ -3644,14 +3663,14 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) 
	might_sleep_if(gfp_mask & __GFP_WAIT);



	spin_lock_irq(q->queue_lock);

	cic = cfq_get_io_context(cfqd, gfp_mask);

	cic = cfq_get_cic(cfqd, gfp_mask);

	if (!cic)

		goto queue_fail;



new_queue:

	cfqq = cic_to_cfqq(cic, is_sync);

	if (!cfqq || cfqq == &cfqd->oom_cfqq) {

		cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);

		cfqq = cfq_get_queue(cfqd, is_sync, cic->icq.ioc, gfp_mask);

		cic_set_cfqq(cic, cfqq, is_sync);

	} else {

		/*
@@ -3677,7 +3696,7 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) 
	cfqq->allocated[rw]++;



	cfqq->ref++;

	rq->elevator_private[0] = cic;

	rq->elevator_private[0] = &cic->icq;

	rq->elevator_private[1] = cfqq;

	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);

	spin_unlock_irq(q->queue_lock);
@@ -3791,15 +3810,14 @@ static void cfq_exit_queue(struct elevator_queue *e) 
	if (cfqd->active_queue)

		__cfq_slice_expired(cfqd, cfqd->active_queue, 0);



	while (!list_empty(&cfqd->cic_list)) {

		struct cfq_io_context *cic = list_entry(cfqd->cic_list.next,

							struct cfq_io_context,

							queue_list);

		struct io_context *ioc = cic->ioc;

	while (!list_empty(&cfqd->icq_list)) {

		struct io_cq *icq = list_entry(cfqd->icq_list.next,

					       struct io_cq, q_node);

		struct io_context *ioc = icq->ioc;



		spin_lock(&ioc->lock);

		cfq_exit_cic(cic);

		cfq_release_cic(cic);

		cfq_exit_icq(icq);

		cfq_release_icq(icq);

		spin_unlock(&ioc->lock);

	}
@@ -3904,7 +3922,7 @@ static void *cfq_init_queue(struct request_queue *q) 
	cfqd->oom_cfqq.ref++;

	cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);



	INIT_LIST_HEAD(&cfqd->cic_list);

	INIT_LIST_HEAD(&cfqd->icq_list);



	cfqd->queue = q;
@@ -3942,8 +3960,8 @@ static void cfq_slab_kill(void) 
	 */

	if (cfq_pool)

		kmem_cache_destroy(cfq_pool);

	if (cfq_ioc_pool)

		kmem_cache_destroy(cfq_ioc_pool);

	if (cfq_icq_pool)

		kmem_cache_destroy(cfq_icq_pool);

}



static int __init cfq_slab_setup(void)
@@ -3952,8 +3970,8 @@ static int __init cfq_slab_setup(void) 
	if (!cfq_pool)

		goto fail;



	cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0);

	if (!cfq_ioc_pool)

	cfq_icq_pool = KMEM_CACHE(cfq_io_cq, 0);

	if (!cfq_icq_pool)

		goto fail;



	return 0;

include/linux/iocontext.h

+14 −29
Original line number Diff line number Diff line
@@ -5,38 +5,23 @@ 
#include <linux/rcupdate.h>

#include <linux/workqueue.h>



struct cfq_queue;

struct cfq_ttime {

	unsigned long last_end_request;



	unsigned long ttime_total;

	unsigned long ttime_samples;

	unsigned long ttime_mean;

};



enum {

	CIC_IOPRIO_CHANGED,

	CIC_CGROUP_CHANGED,

	ICQ_IOPRIO_CHANGED,

	ICQ_CGROUP_CHANGED,

};



struct cfq_io_context {

struct io_cq {

	struct request_queue	*q;



	struct cfq_queue *cfqq[2];



	struct io_context	*ioc;



	struct cfq_ttime ttime;



	struct list_head queue_list;

	struct hlist_node cic_list;

	struct list_head	q_node;

	struct hlist_node	ioc_node;



	unsigned long		changed;



	void (*exit)(struct cfq_io_context *);

	void (*release)(struct cfq_io_context *);



	struct rcu_head		rcu_head;



	void (*exit)(struct io_cq *);

	void (*release)(struct io_cq *);

};



/*
@@ -58,9 +43,9 @@ struct io_context { 
	int nr_batch_requests;     /* Number of requests left in the batch */

	unsigned long last_waited; /* Time last woken after wait for request */



	struct radix_tree_root radix_root;

	struct hlist_head cic_list;

	void __rcu *ioc_data;

	struct radix_tree_root	icq_tree;

	struct io_cq __rcu	*icq_hint;

	struct hlist_head	icq_list;



	struct work_struct release_work;

};