blkcg: kill policy node and blkg->dev, take#3

index fa8f263..7bfc574 100644
@@ -50,10 +50,7 @@ struct cgroup_subsys blkio_subsys = {
 	.attach = blkiocg_attach,
 	.destroy = blkiocg_destroy,
 	.populate = blkiocg_populate,
-#ifdef CONFIG_BLK_CGROUP
-	/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
 	.subsys_id = blkio_subsys_id,
-#endif
 	.use_id = 1,
 	.module = THIS_MODULE,
 };

@@ -1679,17 +1676,3 @@ void blkio_policy_unregister(struct blkio_policy_type *blkiop)
 	spin_unlock(&blkio_list_lock);
 }
 EXPORT_SYMBOL_GPL(blkio_policy_unregister);
-
-static int __init init_cgroup_blkio(void)
-{
-	return cgroup_load_subsys(&blkio_subsys);
-}
-
-static void __exit exit_cgroup_blkio(void)
-{
-	cgroup_unload_subsys(&blkio_subsys);
-}
-
-module_init(init_cgroup_blkio);
-module_exit(exit_cgroup_blkio);
-MODULE_LICENSE("GPL");

index 6f3ace7..3551687 100644
@@ -24,13 +24,7 @@ enum blkio_policy_id {
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
 
-#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
-
-#ifndef CONFIG_BLK_CGROUP
-/* When blk-cgroup is a module, its subsys_id isn't a compile-time constant */
-extern struct cgroup_subsys blkio_subsys;
-#define blkio_subsys_id blkio_subsys.subsys_id
-#endif
+#ifdef CONFIG_BLK_CGROUP
 
 enum stat_type {
 	/* Total time spent (in ns) between request dispatch to the driver and

@@ -303,7 +297,7 @@ static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {}
 static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 #endif
 
-#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
+#ifdef CONFIG_BLK_CGROUP
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);

index ee55019..529dfba 100644
@@ -3884,8 +3884,6 @@ static struct blkio_policy_type blkio_policy_cfq = {
 	},
 	.plid = BLKIO_POLICY_PROP,
 };
-#else
-static struct blkio_policy_type blkio_policy_cfq;
 #endif
 
 static int __init cfq_init(void)

@@ -3916,14 +3914,17 @@ static int __init cfq_init(void)
 		return ret;
 	}
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 	blkio_policy_register(&blkio_policy_cfq);
-
+#endif
 	return 0;
 }
 
 static void __exit cfq_exit(void)
 {
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 	blkio_policy_unregister(&blkio_policy_cfq);
+#endif
 	elv_unregister(&iosched_cfq);
 	kmem_cache_destroy(cfq_pool);
 }

index 91e18f8..42543e3 100644
@@ -168,11 +168,10 @@ static struct elevator_type *elevator_get(const char *name)
 	return e;
 }
 
-static int elevator_init_queue(struct request_queue *q,
-			       struct elevator_queue *eq)
+static int elevator_init_queue(struct request_queue *q)
 {
-	eq->elevator_data = eq->type->ops.elevator_init_fn(q);
-	if (eq->elevator_data)
+	q->elevator->elevator_data = q->elevator->type->ops.elevator_init_fn(q);
+	if (q->elevator->elevator_data)
 		return 0;
 	return -ENOMEM;
 }

@@ -235,7 +234,6 @@ static void elevator_release(struct kobject *kobj)
 int elevator_init(struct request_queue *q, char *name)
 {
 	struct elevator_type *e = NULL;
-	struct elevator_queue *eq;
 	int err;
 
 	if (unlikely(q->elevator))

@@ -269,17 +267,16 @@ int elevator_init(struct request_queue *q, char *name)
 		}
 	}
 
-	eq = elevator_alloc(q, e);
-	if (!eq)
+	q->elevator = elevator_alloc(q, e);
+	if (!q->elevator)
 		return -ENOMEM;
 
-	err = elevator_init_queue(q, eq);
+	err = elevator_init_queue(q);
 	if (err) {
-		kobject_put(&eq->kobj);
+		kobject_put(&q->elevator->kobj);
 		return err;
 	}
 
-	q->elevator = eq;
 	return 0;
 }
 EXPORT_SYMBOL(elevator_init);

@@ -848,8 +845,9 @@ static struct kobj_type elv_ktype = {
 	.release	= elevator_release,
 };
 
-int __elv_register_queue(struct request_queue *q, struct elevator_queue *e)
+int elv_register_queue(struct request_queue *q)
 {
+	struct elevator_queue *e = q->elevator;
 	int error;
 
 	error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");

@@ -867,11 +865,6 @@ int __elv_register_queue(struct request_queue *q, struct elevator_queue *e)
 	}
 	return error;
 }
-
-int elv_register_queue(struct request_queue *q)
-{
-	return __elv_register_queue(q, q->elevator);
-}
 EXPORT_SYMBOL(elv_register_queue);
 
 void elv_unregister_queue(struct request_queue *q)

@@ -954,39 +947,47 @@ EXPORT_SYMBOL_GPL(elv_unregister);
  */
 static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
-	struct elevator_queue *old_elevator, *e;
+	struct elevator_queue *old = q->elevator;
+	bool registered = old->registered;
 	int err;
 
-	/* allocate new elevator */
-	e = elevator_alloc(q, new_e);
-	if (!e)
-		return -ENOMEM;
-
-	err = elevator_init_queue(q, e);
-	if (err) {
-		kobject_put(&e->kobj);
-		return err;
-	}
-
-	/* turn on BYPASS and drain all requests w/ elevator private data */
+	/*
+	 * Turn on BYPASS and drain all requests w/ elevator private data.
+	 * Block layer doesn't call into a quiesced elevator - all requests
+	 * are directly put on the dispatch list without elevator data
+	 * using INSERT_BACK.  All requests have SOFTBARRIER set and no
+	 * merge happens either.
+	 */
 	elv_quiesce_start(q);
 
-	/* unregister old queue, register new one and kill old elevator */
-	if (q->elevator->registered) {
+	/* unregister and clear all auxiliary data of the old elevator */
+	if (registered)
 		elv_unregister_queue(q);
-		err = __elv_register_queue(q, e);
-		if (err)
-			goto fail_register;
-	}
 
-	/* done, clear io_cq's, switch elevators and turn off BYPASS */
 	spin_lock_irq(q->queue_lock);
 	ioc_clear_queue(q);
-	old_elevator = q->elevator;
-	q->elevator = e;
 	spin_unlock_irq(q->queue_lock);
 
-	elevator_exit(old_elevator);
+	/* allocate, init and register new elevator */
+	err = -ENOMEM;
+	q->elevator = elevator_alloc(q, new_e);
+	if (!q->elevator)
+		goto fail_init;
+
+	err = elevator_init_queue(q);
+	if (err) {
+		kobject_put(&q->elevator->kobj);
+		goto fail_init;
+	}
+
+	if (registered) {
+		err = elv_register_queue(q);
+		if (err)
+			goto fail_register;
+	}
+
+	/* done, kill the old one and finish */
+	elevator_exit(old);
 	elv_quiesce_end(q);
 
 	blk_add_trace_msg(q, "elv switch: %s", e->type->elevator_name);

@@ -994,11 +995,10 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	return 0;
 
 fail_register:
-	/*
-	 * switch failed, exit the new io scheduler and reattach the old
-	 * one again (along with re-adding the sysfs dir)
-	 */
-	elevator_exit(e);
+	elevator_exit(q->elevator);
+fail_init:
+	/* switch failed, restore and re-register old elevator */
+	q->elevator = old;
 	elv_register_queue(q);
 	elv_quiesce_end(q);
 

index 529dfba..f3d6b04 100644
@@ -3662,7 +3662,7 @@ static void cfq_exit_queue(struct elevator_queue *e)
 	kfree(cfqd);
 }
 
-static void *cfq_init_queue(struct request_queue *q)
+static int cfq_init_queue(struct request_queue *q)
 {
 	struct cfq_data *cfqd;
 	int i, j;

@@ -3671,7 +3671,7 @@ static void *cfq_init_queue(struct request_queue *q)
 
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!cfqd)
-		return NULL;
+		return -ENOMEM;
 
 	/* Init root service tree */
 	cfqd->grp_service_tree = CFQ_RB_ROOT;

@@ -3698,7 +3698,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	if (blkio_alloc_blkg_stats(&cfqg->blkg)) {
 		kfree(cfqg);
 		kfree(cfqd);
-		return NULL;
+		return -ENOMEM;
 	}
 
 	rcu_read_lock();

@@ -3729,6 +3729,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);
 
 	cfqd->queue = q;
+	q->elevator->elevator_data = cfqd;
 
 	init_timer(&cfqd->idle_slice_timer);
 	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;

@@ -3753,7 +3754,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	 * second, in order to have larger depth for async operations.
 	 */
 	cfqd->last_delayed_sync = jiffies - HZ;
-	return cfqd;
+	return 0;
 }
 
 /*

index 7bf12d7..599b12e 100644
@@ -337,13 +337,13 @@ static void deadline_exit_queue(struct elevator_queue *e)
 /*
  * initialize elevator private data (deadline_data).
  */
-static void *deadline_init_queue(struct request_queue *q)
+static int deadline_init_queue(struct request_queue *q)
 {
 	struct deadline_data *dd;
 
 	dd = kmalloc_node(sizeof(*dd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!dd)
-		return NULL;
+		return -ENOMEM;
 
 	INIT_LIST_HEAD(&dd->fifo_list[READ]);
 	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);

@@ -354,7 +354,9 @@ static void *deadline_init_queue(struct request_queue *q)
 	dd->writes_starved = writes_starved;
 	dd->front_merges = 1;
 	dd->fifo_batch = fifo_batch;
-	return dd;
+
+	q->elevator->elevator_data = dd;
+	return 0;
 }
 
 /*

index 42543e3..8dc65b1 100644
@@ -168,14 +168,6 @@ static struct elevator_type *elevator_get(const char *name)
 	return e;
 }
 
-static int elevator_init_queue(struct request_queue *q)
-{
-	q->elevator->elevator_data = q->elevator->type->ops.elevator_init_fn(q);
-	if (q->elevator->elevator_data)
-		return 0;
-	return -ENOMEM;
-}
-
 static char chosen_elevator[ELV_NAME_MAX];
 
 static int __init elevator_setup(char *str)

@@ -271,7 +263,7 @@ int elevator_init(struct request_queue *q, char *name)
 	if (!q->elevator)
 		return -ENOMEM;
 
-	err = elevator_init_queue(q);
+	err = e->ops.elevator_init_fn(q);
 	if (err) {
 		kobject_put(&q->elevator->kobj);
 		return err;

@@ -974,7 +966,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	if (!q->elevator)
 		goto fail_init;
 
-	err = elevator_init_queue(q);
+	err = new_e->ops.elevator_init_fn(q);
 	if (err) {
 		kobject_put(&q->elevator->kobj);
 		goto fail_init;

index 413a0b1..5d1bf70 100644
@@ -59,15 +59,17 @@ noop_latter_request(struct request_queue *q, struct request *rq)
 	return list_entry(rq->queuelist.next, struct request, queuelist);
 }
 
-static void *noop_init_queue(struct request_queue *q)
+static int noop_init_queue(struct request_queue *q)
 {
 	struct noop_data *nd;
 
 	nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
 	if (!nd)
-		return NULL;
+		return -ENOMEM;
+
 	INIT_LIST_HEAD(&nd->queue);
-	return nd;
+	q->elevator->elevator_data = nd;
+	return 0;
 }
 
 static void noop_exit_queue(struct elevator_queue *e)

index c24f3d7..d7726c9 100644
@@ -33,7 +33,7 @@ typedef void (elevator_put_req_fn) (struct request *);
 typedef void (elevator_activate_req_fn) (struct request_queue *, struct request *);
 typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *);
 
-typedef void *(elevator_init_fn) (struct request_queue *);
+typedef int (elevator_init_fn) (struct request_queue *);
 typedef void (elevator_exit_fn) (struct elevator_queue *);
 
 struct elevator_ops

index e6c05a9..c2e39de 100644
@@ -403,6 +403,42 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
 }
 
 /**
+ * blk_queue_bypass_start - enter queue bypass mode
+ * @q: queue of interest
+ *
+ * In bypass mode, only the dispatch FIFO queue of @q is used.  This
+ * function makes @q enter bypass mode and drains all requests which were
+ * issued before.  On return, it's guaranteed that no request has ELVPRIV
+ * set.
+ */
+void blk_queue_bypass_start(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	q->bypass_depth++;
+	queue_flag_set(QUEUE_FLAG_BYPASS, q);
+	spin_unlock_irq(q->queue_lock);
+
+	blk_drain_queue(q, false);
+}
+EXPORT_SYMBOL_GPL(blk_queue_bypass_start);
+
+/**
+ * blk_queue_bypass_end - leave queue bypass mode
+ * @q: queue of interest
+ *
+ * Leave bypass mode and restore the normal queueing behavior.
+ */
+void blk_queue_bypass_end(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!--q->bypass_depth)
+		queue_flag_clear(QUEUE_FLAG_BYPASS, q);
+	WARN_ON_ONCE(q->bypass_depth < 0);
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
+
+/**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
  *

@@ -859,8 +895,7 @@ retry:
 	 * Also, lookup icq while holding queue_lock.  If it doesn't exist,
 	 * it will be created after releasing queue_lock.
 	 */
-	if (blk_rq_should_init_elevator(bio) &&
-	    !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags)) {
+	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
 		rw_flags |= REQ_ELVPRIV;
 		rl->elvpriv++;
 		if (et->icq_cache && ioc)

index 7efd772..33897f6 100644
@@ -23,7 +23,8 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		      struct bio *bio);
-void blk_drain_queue(struct request_queue *q, bool drain_all);
+void blk_queue_bypass_start(struct request_queue *q);
+void blk_queue_bypass_end(struct request_queue *q);
 void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 bool __blk_end_bidi_request(struct request *rq, int error,

@@ -142,9 +143,6 @@ void blk_queue_congestion_threshold(struct request_queue *q);
 
 int blk_dev_init(void);
 
-void elv_quiesce_start(struct request_queue *q);
-void elv_quiesce_end(struct request_queue *q);
-
 
 /*
  * Return the threshold (number of used requests) at which the queue is

index 8dc65b1..078a491 100644
@@ -600,25 +600,6 @@ void elv_drain_elevator(struct request_queue *q)
 	}
 }
 
-void elv_quiesce_start(struct request_queue *q)
-{
-	if (!q->elevator)
-		return;
-
-	spin_lock_irq(q->queue_lock);
-	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
-	spin_unlock_irq(q->queue_lock);
-
-	blk_drain_queue(q, false);
-}
-
-void elv_quiesce_end(struct request_queue *q)
-{
-	spin_lock_irq(q->queue_lock);
-	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
-	spin_unlock_irq(q->queue_lock);
-}
-
 void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	trace_block_rq_insert(q, rq);

@@ -950,7 +931,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * using INSERT_BACK.  All requests have SOFTBARRIER set and no
 	 * merge happens either.
 	 */
-	elv_quiesce_start(q);
+	blk_queue_bypass_start(q);
 
 	/* unregister and clear all auxiliary data of the old elevator */
 	if (registered)

@@ -980,7 +961,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
 	/* done, kill the old one and finish */
 	elevator_exit(old);
-	elv_quiesce_end(q);
+	blk_queue_bypass_end(q);
 
 	blk_add_trace_msg(q, "elv switch: %s", e->type->elevator_name);
 

@@ -992,7 +973,7 @@ fail_init:
 	/* switch failed, restore and re-register old elevator */
 	q->elevator = old;
 	elv_register_queue(q);
-	elv_quiesce_end(q);
+	blk_queue_bypass_end(q);
 
 	return err;
 }

index 6c6a1f0..f10958b 100644
@@ -389,6 +389,8 @@ struct request_queue {
 
 	struct mutex		sysfs_lock;
 
+	int			bypass_depth;
+
 #if defined(CONFIG_BLK_DEV_BSG)
 	bsg_job_fn		*bsg_job_fn;
 	int			bsg_job_size;

@@ -409,7 +411,7 @@ struct request_queue {
 #define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
 #define QUEUE_FLAG_ASYNCFULL	4	/* write queue has been filled */
 #define QUEUE_FLAG_DEAD		5	/* queue being torn down */
-#define QUEUE_FLAG_ELVSWITCH	6	/* don't use elevator, just do FIFO */
+#define QUEUE_FLAG_BYPASS	6	/* act as dumb FIFO queue */
 #define QUEUE_FLAG_BIDI		7	/* queue supports bidi requests */
 #define QUEUE_FLAG_NOMERGES     8	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP	9	/* complete on same CPU-group */

@@ -497,6 +499,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
+#define blk_queue_bypass(q)	test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)

index c2e39de..c6c61c0 100644
@@ -366,8 +366,7 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
 		spin_lock_irq(q->queue_lock);
 
 		elv_drain_elevator(q);
-		if (drain_all)
-			blk_throtl_drain(q);
+		blk_throtl_drain(q);
 
 		/*
 		 * This function might be called on a queue which failed

@@ -408,8 +407,8 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
  *
  * In bypass mode, only the dispatch FIFO queue of @q is used.  This
  * function makes @q enter bypass mode and drains all requests which were
- * issued before.  On return, it's guaranteed that no request has ELVPRIV
- * set.
+ * throttled or issued before.  On return, it's guaranteed that no request
+ * is being throttled or has ELVPRIV set.
  */
 void blk_queue_bypass_start(struct request_queue *q)
 {

@@ -454,6 +453,11 @@ void blk_cleanup_queue(struct request_queue *q)
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 
 	spin_lock_irq(lock);
+
+	/* dead queue is permanently in bypass mode till released */
+	q->bypass_depth++;
+	queue_flag_set(QUEUE_FLAG_BYPASS, q);
+
 	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	queue_flag_set(QUEUE_FLAG_DEAD, q);

index 5eed6a7..702c0e6 100644
@@ -310,7 +310,7 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	struct request_queue *q = td->queue;
 
 	/* no throttling for dead queue */
-	if (unlikely(blk_queue_dead(q)))
+	if (unlikely(blk_queue_bypass(q)))
 		return NULL;
 
 	rcu_read_lock();

@@ -335,7 +335,7 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	spin_lock_irq(q->queue_lock);
 
 	/* Make sure @q is still alive */
-	if (unlikely(blk_queue_dead(q))) {
+	if (unlikely(blk_queue_bypass(q))) {
 		kfree(tg);
 		return NULL;
 	}

index 7bfc574..ff34543 100644
@@ -17,8 +17,9 @@
 #include <linux/err.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
-#include "blk-cgroup.h"
 #include <linux/genhd.h>
+#include <linux/delay.h>
+#include "blk-cgroup.h"
 
 #define MAX_KEY_LEN 100
 

@@ -1619,6 +1620,37 @@ done:
 	return &blkcg->css;
 }
 
+void blkcg_clear_queue(struct request_queue *q)
+{
+	struct blkio_policy_type *pol;
+
+	while (true) {
+		bool done = true;
+
+		spin_lock(&blkio_list_lock);
+		spin_lock_irq(q->queue_lock);
+
+		/*
+		 * clear_queue_fn() might return with non-empty group list
+		 * if it raced cgroup removal and lost.  cgroup removal is
+		 * guaranteed to make forward progress and retrying after a
+		 * while is enough.  This ugliness is scheduled to be
+		 * removed after locking update.
+		 */
+		list_for_each_entry(pol, &blkio_list, list)
+			if (!pol->ops.blkio_clear_queue_fn(q))
+				done = false;
+
+		spin_unlock_irq(q->queue_lock);
+		spin_unlock(&blkio_list_lock);
+
+		if (done)
+			break;
+
+		msleep(10);	/* just some random duration I like */
+	}
+}
+
 /*
  * We cannot support shared io contexts, as we have no mean to support
  * two tasks with the same ioc in two different groups without major rework

index 3551687..bd7427b 100644
@@ -203,7 +203,7 @@ extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 
 typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
-
+typedef bool (blkio_clear_queue_fn)(struct request_queue *q);
 typedef void (blkio_update_group_weight_fn) (void *key,
 			struct blkio_group *blkg, unsigned int weight);
 typedef void (blkio_update_group_read_bps_fn) (void * key,

@@ -217,6 +217,7 @@ typedef void (blkio_update_group_write_iops_fn) (void *key,
 
 struct blkio_policy_ops {
 	blkio_unlink_group_fn *blkio_unlink_group_fn;
+	blkio_clear_queue_fn *blkio_clear_queue_fn;
 	blkio_update_group_weight_fn *blkio_update_group_weight_fn;
 	blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn;
 	blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn;

@@ -230,6 +231,8 @@ struct blkio_policy_type {
 	enum blkio_policy_id plid;
 };
 
+extern void blkcg_clear_queue(struct request_queue *q);
+
 /* Blkio controller policy registration */
 extern void blkio_policy_register(struct blkio_policy_type *);
 extern void blkio_policy_unregister(struct blkio_policy_type *);

@@ -247,6 +250,7 @@ struct blkio_group {
 struct blkio_policy_type {
 };
 
+static inline void blkcg_clear_queue(struct request_queue *q) { }
 static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
 static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
 

index 702c0e6..3699ab4 100644
@@ -989,12 +989,17 @@ throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
 	td->nr_undestroyed_grps--;
 }
 
-static void throtl_release_tgs(struct throtl_data *td)
+static bool throtl_release_tgs(struct throtl_data *td, bool release_root)
 {
 	struct hlist_node *pos, *n;
 	struct throtl_grp *tg;
+	bool empty = true;
 
 	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
+		/* skip root? */
+		if (!release_root && tg == td->root_tg)
+			continue;
+
 		/*
 		 * If cgroup removal path got to blk_group first and removed
 		 * it from cgroup list, then it will take care of destroying

@@ -1002,7 +1007,10 @@ static void throtl_release_tgs(struct throtl_data *td)
 		 */
 		if (!blkiocg_del_blkio_group(&tg->blkg))
 			throtl_destroy_tg(td, tg);
+		else
+			empty = false;
 	}
+	return empty;
 }
 
 /*

@@ -1029,6 +1037,20 @@ void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg)
 	spin_unlock_irqrestore(td->queue->queue_lock, flags);
 }
 
+static bool throtl_clear_queue(struct request_queue *q)
+{
+	lockdep_assert_held(q->queue_lock);
+
+	/*
+	 * Clear tgs but leave the root one alone.  This is necessary
+	 * because root_tg is expected to be persistent and safe because
+	 * blk-throtl can never be disabled while @q is alive.  This is a
+	 * kludge to prepare for unified blkg.  This whole function will be
+	 * removed soon.
+	 */
+	return throtl_release_tgs(q->td, false);
+}
+
 static void throtl_update_blkio_group_common(struct throtl_data *td,
 				struct throtl_grp *tg)
 {

@@ -1097,6 +1119,7 @@ static void throtl_shutdown_wq(struct request_queue *q)
 static struct blkio_policy_type blkio_policy_throtl = {
 	.ops = {
 		.blkio_unlink_group_fn = throtl_unlink_blkio_group,
+		.blkio_clear_queue_fn = throtl_clear_queue,
 		.blkio_update_group_read_bps_fn =
 					throtl_update_blkio_group_read_bps,
 		.blkio_update_group_write_bps_fn =

@@ -1282,7 +1305,7 @@ void blk_throtl_exit(struct request_queue *q)
 	throtl_shutdown_wq(q);
 
 	spin_lock_irq(q->queue_lock);
-	throtl_release_tgs(td);
+	throtl_release_tgs(td, true);
 
 	/* If there are other groups */
 	if (td->nr_undestroyed_grps > 0)

index f3d6b04..37831d8 100644
@@ -1225,10 +1225,11 @@ static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	cfq_put_cfqg(cfqg);
 }
 
-static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+static bool cfq_release_cfq_groups(struct cfq_data *cfqd)
 {
 	struct hlist_node *pos, *n;
 	struct cfq_group *cfqg;
+	bool empty = true;
 
 	hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
 		/*

@@ -1238,7 +1239,10 @@ static void cfq_release_cfq_groups(struct cfq_data *cfqd)
 		 */
 		if (!cfq_blkiocg_del_blkio_group(&cfqg->blkg))
 			cfq_destroy_cfqg(cfqd, cfqg);
+		else
+			empty = false;
 	}
+	return empty;
 }
 
 /*

@@ -1265,6 +1269,20 @@ static void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
 }
 
+static struct elevator_type iosched_cfq;
+
+static bool cfq_clear_queue(struct request_queue *q)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+
+	lockdep_assert_held(q->queue_lock);
+
+	/* shoot down blkgs iff the current elevator is cfq */
+	if (q->elevator->type == &iosched_cfq)
+		return cfq_release_cfq_groups(cfqd);
+	return true;
+}
+
 #else /* GROUP_IOSCHED */
 static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 {

@@ -3881,6 +3899,7 @@ static struct elevator_type iosched_cfq = {
 static struct blkio_policy_type blkio_policy_cfq = {
 	.ops = {
 		.blkio_unlink_group_fn =	cfq_unlink_blkio_group,
+		.blkio_clear_queue_fn = cfq_clear_queue,
 		.blkio_update_group_weight_fn =	cfq_update_blkio_group_weight,
 	},
 	.plid = BLKIO_POLICY_PROP,

index 078a491..725995d 100644
@@ -38,6 +38,7 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-cgroup.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);

@@ -941,6 +942,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	ioc_clear_queue(q);
 	spin_unlock_irq(q->queue_lock);
 
+	blkcg_clear_queue(q);
+
 	/* allocate, init and register new elevator */
 	err = -ENOMEM;
 	q->elevator = elevator_alloc(q, new_e);

index 3699ab4..9beaac7 100644
@@ -313,25 +313,23 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	if (unlikely(blk_queue_bypass(q)))
 		return NULL;
 
-	rcu_read_lock();
 	blkcg = task_blkio_cgroup(current);
 	tg = throtl_find_tg(td, blkcg);
-	if (tg) {
-		rcu_read_unlock();
+	if (tg)
 		return tg;
-	}
 
 	/*
 	 * Need to allocate a group. Allocation of group also needs allocation
 	 * of per cpu stats which in-turn takes a mutex() and can block. Hence
 	 * we need to drop rcu lock and queue_lock before we call alloc.
 	 */
-	rcu_read_unlock();
 	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
 
 	tg = throtl_alloc_tg(td);
 
 	/* Group allocated and queue is still alive. take the lock */
+	rcu_read_lock();
 	spin_lock_irq(q->queue_lock);
 
 	/* Make sure @q is still alive */

@@ -343,7 +341,6 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	/*
 	 * Initialize the new group. After sleeping, read the blkcg again.
 	 */
-	rcu_read_lock();
 	blkcg = task_blkio_cgroup(current);
 
 	/*

@@ -354,7 +351,6 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 
 	if (__tg) {
 		kfree(tg);
-		rcu_read_unlock();
 		return __tg;
 	}
 

@@ -365,7 +361,6 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	}
 
 	throtl_init_add_tg_lists(td, tg, blkcg);
-	rcu_read_unlock();
 	return tg;
 }
 

@@ -1150,7 +1145,6 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 	 * basic fields like stats and io rates. If a group has no rules,
 	 * just update the dispatch stats in lockless manner and return.
 	 */
-
 	rcu_read_lock();
 	blkcg = task_blkio_cgroup(current);
 	tg = throtl_find_tg(td, blkcg);

@@ -1160,11 +1154,9 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 		if (tg_no_rule_group(tg, rw)) {
 			blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
 					rw, rw_is_sync(bio->bi_rw));
-			rcu_read_unlock();
-			goto out;
+			goto out_unlock_rcu;
 		}
 	}
-	rcu_read_unlock();
 
 	/*
 	 * Either group has not been allocated yet or it is not an unlimited

@@ -1222,6 +1214,8 @@ queue_bio:
 
 out_unlock:
 	spin_unlock_irq(q->queue_lock);
+out_unlock_rcu:
+	rcu_read_unlock();
 out:
 	return throttled;
 }

index 37831d8..c3f2348 100644
@@ -1128,13 +1128,10 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 	struct cfq_group *cfqg = NULL, *__cfqg = NULL;
 	struct request_queue *q = cfqd->queue;
 
-	rcu_read_lock();
 	blkcg = task_blkio_cgroup(current);
 	cfqg = cfq_find_cfqg(cfqd, blkcg);
-	if (cfqg) {
-		rcu_read_unlock();
+	if (cfqg)
 		return cfqg;
-	}
 
 	/*
 	 * Need to allocate a group. Allocation of group also needs allocation

@@ -1164,7 +1161,6 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 
 	if (__cfqg) {
 		kfree(cfqg);
-		rcu_read_unlock();
 		return __cfqg;
 	}
 

@@ -1172,7 +1168,6 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 		cfqg = &cfqd->root_group;
 
 	cfq_init_add_cfqg_lists(cfqd, cfqg, blkcg);
-	rcu_read_unlock();
 	return cfqg;
 }
 

@@ -2878,6 +2873,8 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 	struct cfq_group *cfqg;
 
 retry:
+	rcu_read_lock();
+
 	cfqg = cfq_get_cfqg(cfqd);
 	cic = cfq_cic_lookup(cfqd, ioc);
 	/* cic always exists here */

@@ -2893,6 +2890,7 @@ retry:
 			cfqq = new_cfqq;
 			new_cfqq = NULL;
 		} else if (gfp_mask & __GFP_WAIT) {
+			rcu_read_unlock();
 			spin_unlock_irq(cfqd->queue->queue_lock);
 			new_cfqq = kmem_cache_alloc_node(cfq_pool,
 					gfp_mask | __GFP_ZERO,

@@ -2918,6 +2916,7 @@ retry:
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 
+	rcu_read_unlock();
 	return cfqq;
 }
 

index 9beaac7..c252df9 100644
@@ -303,21 +303,23 @@ throtl_grp *throtl_find_tg(struct throtl_data *td, struct blkio_cgroup *blkcg)
 	return tg;
 }
 
-static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+static struct throtl_grp *throtl_get_tg(struct throtl_data *td,
+					struct blkio_cgroup *blkcg)
 {
 	struct throtl_grp *tg = NULL, *__tg = NULL;
-	struct blkio_cgroup *blkcg;
 	struct request_queue *q = td->queue;
 
 	/* no throttling for dead queue */
 	if (unlikely(blk_queue_bypass(q)))
 		return NULL;
 
-	blkcg = task_blkio_cgroup(current);
 	tg = throtl_find_tg(td, blkcg);
 	if (tg)
 		return tg;
 
+	if (!css_tryget(&blkcg->css))
+		return NULL;
+
 	/*
 	 * Need to allocate a group. Allocation of group also needs allocation
 	 * of per cpu stats which in-turn takes a mutex() and can block. Hence

@@ -331,6 +333,7 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	/* Group allocated and queue is still alive. take the lock */
 	rcu_read_lock();
 	spin_lock_irq(q->queue_lock);
+	css_put(&blkcg->css);
 
 	/* Make sure @q is still alive */
 	if (unlikely(blk_queue_bypass(q))) {

@@ -339,11 +342,6 @@ static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
 	}
 
 	/*
-	 * Initialize the new group. After sleeping, read the blkcg again.
-	 */
-	blkcg = task_blkio_cgroup(current);
-
-	/*
 	 * If some other thread already allocated the group while we were
 	 * not holding queue lock, free up the group
 	 */

@@ -1163,7 +1161,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 	 * IO group
 	 */
 	spin_lock_irq(q->queue_lock);
-	tg = throtl_get_tg(td);
+	tg = throtl_get_tg(td, blkcg);
 	if (unlikely(!tg))
 		goto out_unlock;
 

index c3f2348..fcdb0e2 100644
@@ -1122,17 +1122,19 @@ cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
  * Search for the cfq group current task belongs to. request_queue lock must
  * be held.
  */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd,
+				      struct blkio_cgroup *blkcg)
 {
-	struct blkio_cgroup *blkcg;
 	struct cfq_group *cfqg = NULL, *__cfqg = NULL;
 	struct request_queue *q = cfqd->queue;
 
-	blkcg = task_blkio_cgroup(current);
 	cfqg = cfq_find_cfqg(cfqd, blkcg);
 	if (cfqg)
 		return cfqg;
 
+	if (!css_tryget(&blkcg->css))
+		return NULL;
+
 	/*
 	 * Need to allocate a group. Allocation of group also needs allocation
 	 * of per cpu stats which in-turn takes a mutex() and can block. Hence

@@ -1142,16 +1144,14 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 	 * around by the time we return. CFQ queue allocation code does
 	 * the same. It might be racy though.
 	 */
-
 	rcu_read_unlock();
 	spin_unlock_irq(q->queue_lock);
 
 	cfqg = cfq_alloc_cfqg(cfqd);
 
 	spin_lock_irq(q->queue_lock);
-
 	rcu_read_lock();
-	blkcg = task_blkio_cgroup(current);
+	css_put(&blkcg->css);
 
 	/*
 	 * If some other thread already allocated the group while we were

@@ -1279,7 +1279,8 @@ static bool cfq_clear_queue(struct request_queue *q)
 }
 
 #else /* GROUP_IOSCHED */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd,
+				      struct blkio_cgroup *blkcg)
 {
 	return &cfqd->root_group;
 }

@@ -2868,6 +2869,7 @@ static struct cfq_queue *
 cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 		     struct io_context *ioc, gfp_t gfp_mask)
 {
+	struct blkio_cgroup *blkcg;
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
 	struct cfq_io_cq *cic;
 	struct cfq_group *cfqg;

@@ -2875,7 +2877,9 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 retry:
 	rcu_read_lock();
 
-	cfqg = cfq_get_cfqg(cfqd);
+	blkcg = task_blkio_cgroup(current);
+
+	cfqg = cfq_get_cfqg(cfqd, blkcg);
 	cic = cfq_cic_lookup(cfqd, ioc);
 	/* cic always exists here */
 	cfqq = cic_to_cfqq(cic, is_sync);

index ff34543..d90e9e8 100644
@@ -129,7 +129,7 @@ blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
 		if (blkiop->plid != blkg->plid)
 			continue;
 		if (blkiop->ops.blkio_update_group_weight_fn)
-			blkiop->ops.blkio_update_group_weight_fn(blkg->key,
+			blkiop->ops.blkio_update_group_weight_fn(blkg->q,
 							blkg, weight);
 	}
 }

@@ -147,12 +147,12 @@ static inline void blkio_update_group_bps(struct blkio_group *blkg, u64 bps,
 
 		if (fileid == BLKIO_THROTL_read_bps_device
 		    && blkiop->ops.blkio_update_group_read_bps_fn)
-			blkiop->ops.blkio_update_group_read_bps_fn(blkg->key,
+			blkiop->ops.blkio_update_group_read_bps_fn(blkg->q,
 								blkg, bps);
 
 		if (fileid == BLKIO_THROTL_write_bps_device
 		    && blkiop->ops.blkio_update_group_write_bps_fn)
-			blkiop->ops.blkio_update_group_write_bps_fn(blkg->key,
+			blkiop->ops.blkio_update_group_write_bps_fn(blkg->q,
 								blkg, bps);
 	}
 }

@@ -170,12 +170,12 @@ static inline void blkio_update_group_iops(struct blkio_group *blkg,
 
 		if (fileid == BLKIO_THROTL_read_iops_device
 		    && blkiop->ops.blkio_update_group_read_iops_fn)
-			blkiop->ops.blkio_update_group_read_iops_fn(blkg->key,
+			blkiop->ops.blkio_update_group_read_iops_fn(blkg->q,
 								blkg, iops);
 
 		if (fileid == BLKIO_THROTL_write_iops_device
 		    && blkiop->ops.blkio_update_group_write_iops_fn)
-			blkiop->ops.blkio_update_group_write_iops_fn(blkg->key,
+			blkiop->ops.blkio_update_group_write_iops_fn(blkg->q,
 								blkg,iops);
 	}
 }

@@ -478,14 +478,14 @@ int blkio_alloc_blkg_stats(struct blkio_group *blkg)
 EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
 
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, void *key, dev_t dev,
+		struct blkio_group *blkg, struct request_queue *q, dev_t dev,
 		enum blkio_policy_id plid)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&blkcg->lock, flags);
 	spin_lock_init(&blkg->stats_lock);
-	rcu_assign_pointer(blkg->key, key);
+	rcu_assign_pointer(blkg->q, q);
 	blkg->blkcg_id = css_id(&blkcg->css);
 	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
 	blkg->plid = plid;

@@ -531,18 +531,16 @@ int blkiocg_del_blkio_group(struct blkio_group *blkg)
 EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
 
 /* called under rcu_read_lock(). */
-struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
+struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
+					 struct request_queue *q,
+					 enum blkio_policy_id plid)
 {
 	struct blkio_group *blkg;
 	struct hlist_node *n;
-	void *__key;
 
-	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
-		__key = blkg->key;
-		if (__key == key)
+	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node)
+		if (blkg->q == q && blkg->plid == plid)
 			return blkg;
-	}
-
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(blkiocg_lookup_group);

@@ -1551,7 +1549,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
 	unsigned long flags;
 	struct blkio_group *blkg;
-	void *key;
+	struct request_queue *q;
 	struct blkio_policy_type *blkiop;
 	struct blkio_policy_node *pn, *pntmp;
 

@@ -1566,7 +1564,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 
 		blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
 					blkcg_node);
-		key = rcu_dereference(blkg->key);
+		q = rcu_dereference(blkg->q);
 		__blkiocg_del_blkio_group(blkg);
 
 		spin_unlock_irqrestore(&blkcg->lock, flags);

@@ -1580,7 +1578,7 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 		list_for_each_entry(blkiop, &blkio_list, list) {
 			if (blkiop->plid != blkg->plid)
 				continue;
-			blkiop->ops.blkio_unlink_group_fn(key, blkg);
+			blkiop->ops.blkio_unlink_group_fn(q, blkg);
 		}
 		spin_unlock(&blkio_list_lock);
 	} while (1);

index bd7427b..a19b265 100644
@@ -153,8 +153,8 @@ struct blkio_group_stats_cpu {
 };
 
 struct blkio_group {
-	/* An rcu protected unique identifier for the group */
-	void *key;
+	/* Pointer to the associated request_queue, RCU protected */
+	struct request_queue __rcu *q;
 	struct hlist_node blkcg_node;
 	unsigned short blkcg_id;
 	/* Store cgroup path */

@@ -202,17 +202,18 @@ extern unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg,
 extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 
-typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
+typedef void (blkio_unlink_group_fn)(struct request_queue *q,
+			struct blkio_group *blkg);
 typedef bool (blkio_clear_queue_fn)(struct request_queue *q);
-typedef void (blkio_update_group_weight_fn) (void *key,
+typedef void (blkio_update_group_weight_fn)(struct request_queue *q,
 			struct blkio_group *blkg, unsigned int weight);
-typedef void (blkio_update_group_read_bps_fn) (void * key,
+typedef void (blkio_update_group_read_bps_fn)(struct request_queue *q,
 			struct blkio_group *blkg, u64 read_bps);
-typedef void (blkio_update_group_write_bps_fn) (void *key,
+typedef void (blkio_update_group_write_bps_fn)(struct request_queue *q,
 			struct blkio_group *blkg, u64 write_bps);
-typedef void (blkio_update_group_read_iops_fn) (void *key,
+typedef void (blkio_update_group_read_iops_fn)(struct request_queue *q,
 			struct blkio_group *blkg, unsigned int read_iops);
-typedef void (blkio_update_group_write_iops_fn) (void *key,
+typedef void (blkio_update_group_write_iops_fn)(struct request_queue *q,
 			struct blkio_group *blkg, unsigned int write_iops);
 
 struct blkio_policy_ops {

@@ -306,12 +307,13 @@ extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-	struct blkio_group *blkg, void *key, dev_t dev,
+	struct blkio_group *blkg, struct request_queue *q, dev_t dev,
 	enum blkio_policy_id plid);
 extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
-						void *key);
+						struct request_queue *q,
+						enum blkio_policy_id plid);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 					unsigned long time,
 					unsigned long unaccounted_time);

125 lines not on this page · raw message

index fcdb0e2..f063557 100644
@@ -1020,7 +1020,8 @@ static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
 	return NULL;
 }
 
-static void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
+static void cfq_update_blkio_group_weight(struct request_queue *q,
+					  struct blkio_group *blkg,
 					  unsigned int weight)
 {
 	struct cfq_group *cfqg = cfqg_of_blkg(blkg);

@@ -1043,10 +1044,10 @@ static void cfq_init_add_cfqg_lists(struct cfq_data *cfqd,
 	if (bdi->dev) {
 		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
 		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
-					(void *)cfqd, MKDEV(major, minor));
+					cfqd->queue, MKDEV(major, minor));
 	} else
 		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
-					(void *)cfqd, 0);
+					cfqd->queue, 0);
 
 	cfqd->nr_blkcg_linked_grps++;
 	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);

@@ -1097,7 +1098,6 @@ static struct cfq_group *
 cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
 {
 	struct cfq_group *cfqg = NULL;
-	void *key = cfqd;
 	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
 	unsigned int major, minor;
 

@@ -1108,7 +1108,8 @@ cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
 	if (blkcg == &blkio_root_cgroup)
 		cfqg = &cfqd->root_group;
 	else
-		cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+		cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, cfqd->queue,
+							 BLKIO_POLICY_PROP));
 
 	if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
 		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);

@@ -1247,21 +1248,22 @@ static bool cfq_release_cfq_groups(struct cfq_data *cfqd)
  * any pending IO in the group is finished.
  *
  * This function is called under rcu_read_lock(). key is the rcu protected
- * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu
- * read lock.
+ * pointer. That means @q is a valid request_queue pointer as long as we
+ * are rcu read lock.
  *
- * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * @q was fetched from blkio_group under blkio_cgroup->lock. That means
  * it should not be NULL as even if elevator was exiting, cgroup deltion
  * path got to it first.
  */
-static void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
+static void cfq_unlink_blkio_group(struct request_queue *q,
+				   struct blkio_group *blkg)
 {
-	unsigned long  flags;
-	struct cfq_data *cfqd = key;
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	unsigned long flags;
 
-	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+	spin_lock_irqsave(q->queue_lock, flags);
 	cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
-	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 static struct elevator_type iosched_cfq;

@@ -3725,7 +3727,7 @@ static int cfq_init_queue(struct request_queue *q)
 	rcu_read_lock();
 
 	cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
-					(void *)cfqd, 0);
+				    cfqd->queue, 0);
 	rcu_read_unlock();
 	cfqd->nr_blkcg_linked_grps++;
 

index 2a15592..343b78a 100644
@@ -68,8 +68,9 @@ static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg,
 }
 
 static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev) {
-	blkiocg_add_blkio_group(blkcg, blkg, key, dev, BLKIO_POLICY_PROP);
+		struct blkio_group *blkg, struct request_queue *q, dev_t dev)
+{
+	blkiocg_add_blkio_group(blkcg, blkg, q, dev, BLKIO_POLICY_PROP);
 }
 
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)

@@ -105,7 +106,7 @@ static inline void cfq_blkiocg_update_dispatch_stats(struct blkio_group *blkg,
 static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) {}
 
 static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev) {}
+		struct blkio_group *blkg, struct request_queue *q, dev_t dev) {}
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return 0;

index d90e9e8..fab2800 100644
@@ -29,6 +29,8 @@ static LIST_HEAD(blkio_list);
 struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
 EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
+static struct blkio_policy_type *blkio_policy[BLKIO_NR_POLICIES];
+
 static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
 						  struct cgroup *);
 static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,

@@ -1694,7 +1696,11 @@ static void blkiocg_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 void blkio_policy_register(struct blkio_policy_type *blkiop)
 {
 	spin_lock(&blkio_list_lock);
+
+	BUG_ON(blkio_policy[blkiop->plid]);
+	blkio_policy[blkiop->plid] = blkiop;
 	list_add_tail(&blkiop->list, &blkio_list);
+
 	spin_unlock(&blkio_list_lock);
 }
 EXPORT_SYMBOL_GPL(blkio_policy_register);

@@ -1702,7 +1708,11 @@ EXPORT_SYMBOL_GPL(blkio_policy_register);
 void blkio_policy_unregister(struct blkio_policy_type *blkiop)
 {
 	spin_lock(&blkio_list_lock);
+
+	BUG_ON(blkio_policy[blkiop->plid] != blkiop);
+	blkio_policy[blkiop->plid] = NULL;
 	list_del_init(&blkiop->list);
+
 	spin_unlock(&blkio_list_lock);
 }
 EXPORT_SYMBOL_GPL(blkio_policy_unregister);

index a19b265..aa66d49 100644
@@ -19,6 +19,8 @@
 enum blkio_policy_id {
 	BLKIO_POLICY_PROP = 0,		/* Proportional Bandwidth division */
 	BLKIO_POLICY_THROTL,		/* Throttling */
+
+	BLKIO_NR_POLICIES,
 };
 
 /* Max limits for throttle policy */

index c6c61c0..1b73d06 100644
@@ -538,9 +538,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (err)
 		goto fail_id;
 
-	if (blk_throtl_init(q))
-		goto fail_id;
-
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);

@@ -562,6 +559,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	 */
 	q->queue_lock = &q->__queue_lock;
 
+	if (blk_throtl_init(q))
+		goto fail_id;
+
 	return q;
 
 fail_id:

index 6613de7..aeeb798 100644
@@ -1252,7 +1252,6 @@ void blk_throtl_drain(struct request_queue *q)
 int blk_throtl_init(struct request_queue *q)
 {
 	struct throtl_data *td;
-	struct throtl_grp *tg;
 
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
 	if (!td)

@@ -1265,19 +1264,20 @@ int blk_throtl_init(struct request_queue *q)
 
 	/* alloc and Init root group. */
 	td->queue = q;
-	tg = throtl_alloc_tg(td);
 
-	if (!tg) {
-		kfree(td);
-		return -ENOMEM;
-	}
+	rcu_read_lock();
+	spin_lock_irq(q->queue_lock);
 
-	td->root_tg = tg;
+	td->root_tg = throtl_get_tg(td, &blkio_root_cgroup);
 
-	rcu_read_lock();
-	throtl_init_add_tg_lists(td, tg, &blkio_root_cgroup);
+	spin_unlock_irq(q->queue_lock);
 	rcu_read_unlock();
 
+	if (!td->root_tg) {
+		kfree(td);
+		return -ENOMEM;
+	}
+
 	/* Attach throtl data to request queue */
 	q->td = td;
 	return 0;

188 lines not on this page · raw message

index fab2800..2e6a043 100644
@@ -465,38 +465,89 @@ void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
-/*
- * This function allocates the per cpu stats for blkio_group. Should be called
- * from sleepable context as alloc_per_cpu() requires that.
- */
-int blkio_alloc_blkg_stats(struct blkio_group *blkg)
+struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid)
+	__releases(q->queue_lock) __acquires(q->queue_lock)
 {
-	/* Allocate memory for per cpu stats */
-	blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
-	if (!blkg->stats_cpu)
-		return -ENOMEM;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
+	struct blkio_policy_type *pol = blkio_policy[plid];
+	struct blkio_group *blkg = NULL;
+	struct blkio_group *new_blkg = NULL;
 
-void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev,
-		enum blkio_policy_id plid)
-{
-	unsigned long flags;
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	lockdep_assert_held(q->queue_lock);
 
-	spin_lock_irqsave(&blkcg->lock, flags);
-	spin_lock_init(&blkg->stats_lock);
-	rcu_assign_pointer(blkg->q, q);
-	blkg->blkcg_id = css_id(&blkcg->css);
+	/*
+	 * This could be the first entry point of blkcg implementation and
+	 * we shouldn't allow anything to go through for a dead queue.  The
+	 * following can be removed if blkg lookup is guaranteed to fail on
+	 * a dead queue.
+	 */
+	if (unlikely(blk_queue_dead(q)))
+		return NULL;
+
+	blkg = blkg_lookup(blkcg, q, plid);
+	if (blkg)
+		return blkg;
+
+	if (!css_tryget(&blkcg->css))
+		return NULL;
+
+	/*
+	 * Allocate and initialize.
+	 *
+	 * FIXME: The following is broken.  Percpu memory allocation
+	 * requires %GFP_KERNEL context and can't be performed from IO
+	 * path.  Allocation here should inherently be atomic and the
+	 * following lock dancing can be removed once the broken percpu
+	 * allocation is fixed.
+	 */
+	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
+
+	new_blkg = pol->ops.blkio_alloc_group_fn(q, blkcg);
+	if (new_blkg) {
+		new_blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
+
+		spin_lock_init(&new_blkg->stats_lock);
+		rcu_assign_pointer(new_blkg->q, q);
+		new_blkg->blkcg_id = css_id(&blkcg->css);
+		new_blkg->plid = plid;
+		cgroup_path(blkcg->css.cgroup, new_blkg->path,
+			    sizeof(new_blkg->path));
+	}
+
+	rcu_read_lock();
+	spin_lock_irq(q->queue_lock);
+	css_put(&blkcg->css);
+
+	/* did the device die inbetween? */
+	if (unlikely(blk_queue_dead(q)))
+		goto out;
+
+	/* did someone beat us to it? */
+	blkg = blkg_lookup(blkcg, q, plid);
+	if (unlikely(blkg))
+		goto out;
+
+	/* did alloc fail? */
+	if (unlikely(!new_blkg || !new_blkg->stats_cpu))
+		goto out;
+
+	/* insert */
+	spin_lock(&blkcg->lock);
+	swap(blkg, new_blkg);
 	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
-	blkg->plid = plid;
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-	/* Need to take css reference ? */
-	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
-	blkg->dev = dev;
+	pol->ops.blkio_link_group_fn(q, blkg);
+	spin_unlock(&blkcg->lock);
+out:
+	if (new_blkg) {
+		free_percpu(new_blkg->stats_cpu);
+		kfree(new_blkg);
+	}
+	return blkg;
 }
-EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
+EXPORT_SYMBOL_GPL(blkg_lookup_create);
 
 static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
 {

@@ -533,9 +584,9 @@ int blkiocg_del_blkio_group(struct blkio_group *blkg)
 EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
 
 /* called under rcu_read_lock(). */
-struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
-					 struct request_queue *q,
-					 enum blkio_policy_id plid)
+struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+				struct request_queue *q,
+				enum blkio_policy_id plid)
 {
 	struct blkio_group *blkg;
 	struct hlist_node *n;

@@ -545,7 +596,7 @@ struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 			return blkg;
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
+EXPORT_SYMBOL_GPL(blkg_lookup);
 
 static void blkio_reset_stats_cpu(struct blkio_group *blkg)
 {

index aa66d49..f4057b7 100644
@@ -204,6 +204,10 @@ extern unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg,
 extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 
+typedef struct blkio_group *(blkio_alloc_group_fn)(struct request_queue *q,
+						   struct blkio_cgroup *blkcg);
+typedef void (blkio_link_group_fn)(struct request_queue *q,
+			struct blkio_group *blkg);
 typedef void (blkio_unlink_group_fn)(struct request_queue *q,
 			struct blkio_group *blkg);
 typedef bool (blkio_clear_queue_fn)(struct request_queue *q);

@@ -219,6 +223,8 @@ typedef void (blkio_update_group_write_iops_fn)(struct request_queue *q,
 			struct blkio_group *blkg, unsigned int write_iops);
 
 struct blkio_policy_ops {
+	blkio_alloc_group_fn *blkio_alloc_group_fn;
+	blkio_link_group_fn *blkio_link_group_fn;
 	blkio_unlink_group_fn *blkio_unlink_group_fn;
 	blkio_clear_queue_fn *blkio_clear_queue_fn;
 	blkio_update_group_weight_fn *blkio_update_group_weight_fn;

@@ -308,14 +314,13 @@ static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
-extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-	struct blkio_group *blkg, struct request_queue *q, dev_t dev,
-	enum blkio_policy_id plid);
-extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
-extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
-						struct request_queue *q,
-						enum blkio_policy_id plid);
+extern struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid);
+struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 					unsigned long time,
 					unsigned long unaccounted_time);

@@ -336,17 +341,11 @@ cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
 static inline struct blkio_cgroup *
 task_blkio_cgroup(struct task_struct *tsk) { return NULL; }
 
-static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, void *key, dev_t dev,
-		enum blkio_policy_id plid) {}
-
-static inline int blkio_alloc_blkg_stats(struct blkio_group *blkg) { return 0; }
-
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 
-static inline struct blkio_group *
-blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
+static inline struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+					      void *key) { return NULL; }
 static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 						unsigned long time,
 						unsigned long unaccounted_time)

228 lines not on this page · raw message

205 lines not on this page · raw message

index 343b78a..3987601 100644
@@ -67,12 +67,6 @@ static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg,
 				direction, sync);
 }
 
-static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev)
-{
-	blkiocg_add_blkio_group(blkcg, blkg, q, dev, BLKIO_POLICY_PROP);
-}
-
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return blkiocg_del_blkio_group(blkg);

@@ -105,8 +99,6 @@ static inline void cfq_blkiocg_update_dispatch_stats(struct blkio_group *blkg,
 				uint64_t bytes, bool direction, bool sync) {}
 static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) {}
 
-static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev) {}
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return 0;

Index: work/block/blk-cgroup.h
===================================================================
@@ -204,6 +204,10 @@ extern unsigned int blkcg_get_read_iops(
 extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 
+typedef struct blkio_group *(blkio_alloc_group_fn)(struct request_queue *q,
+						   struct blkio_cgroup *blkcg);
+typedef void (blkio_link_group_fn)(struct request_queue *q,
+			struct blkio_group *blkg);
 typedef void (blkio_unlink_group_fn)(struct request_queue *q,
 			struct blkio_group *blkg);
 typedef bool (blkio_clear_queue_fn)(struct request_queue *q);

@@ -219,6 +223,8 @@ typedef void (blkio_update_group_write_i
 			struct blkio_group *blkg, unsigned int write_iops);
 
 struct blkio_policy_ops {
+	blkio_alloc_group_fn *blkio_alloc_group_fn;
+	blkio_link_group_fn *blkio_link_group_fn;
 	blkio_unlink_group_fn *blkio_unlink_group_fn;
 	blkio_clear_queue_fn *blkio_clear_queue_fn;
 	blkio_update_group_weight_fn *blkio_update_group_weight_fn;

@@ -308,14 +314,13 @@ static inline void blkiocg_set_start_emp
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
-extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-	struct blkio_group *blkg, struct request_queue *q, dev_t dev,
-	enum blkio_policy_id plid);
-extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
-extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
-						struct request_queue *q,
-						enum blkio_policy_id plid);
+extern struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid);
+struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 					unsigned long time,
 					unsigned long unaccounted_time);

@@ -336,17 +341,11 @@ cgroup_to_blkio_cgroup(struct cgroup *cg
 static inline struct blkio_cgroup *
 task_blkio_cgroup(struct task_struct *tsk) { return NULL; }
 
-static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, void *key, dev_t dev,
-		enum blkio_policy_id plid) {}
-
-static inline int blkio_alloc_blkg_stats(struct blkio_group *blkg) { return 0; }
-
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 
-static inline struct blkio_group *
-blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
+static inline struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+					      void *key) { return NULL; }
 static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 						unsigned long time,
 						unsigned long unaccounted_time)

228 lines not on this page · raw message

137 lines not on this page · raw message

205 lines not on this page · raw message

Index: work/block/cfq.h
===================================================================
@@ -67,12 +67,6 @@ static inline void cfq_blkiocg_update_co
 				direction, sync);
 }
 
-static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev)
-{
-	blkiocg_add_blkio_group(blkcg, blkg, q, dev, BLKIO_POLICY_PROP);
-}
-
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return blkiocg_del_blkio_group(blkg);

@@ -105,8 +99,6 @@ static inline void cfq_blkiocg_update_di
 				uint64_t bytes, bool direction, bool sync) {}
 static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) {}
 
-static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev) {}
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return 0;

Index: work/block/blk-cgroup.h
===================================================================
@@ -204,6 +204,10 @@ extern unsigned int blkcg_get_read_iops(
 extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
 				     dev_t dev);
 
+typedef struct blkio_group *(blkio_alloc_group_fn)(struct request_queue *q,
+						   struct blkio_cgroup *blkcg);
+typedef void (blkio_link_group_fn)(struct request_queue *q,
+			struct blkio_group *blkg);
 typedef void (blkio_unlink_group_fn)(struct request_queue *q,
 			struct blkio_group *blkg);
 typedef bool (blkio_clear_queue_fn)(struct request_queue *q);

@@ -219,6 +223,8 @@ typedef void (blkio_update_group_write_i
 			struct blkio_group *blkg, unsigned int write_iops);
 
 struct blkio_policy_ops {
+	blkio_alloc_group_fn *blkio_alloc_group_fn;
+	blkio_link_group_fn *blkio_link_group_fn;
 	blkio_unlink_group_fn *blkio_unlink_group_fn;
 	blkio_clear_queue_fn *blkio_clear_queue_fn;
 	blkio_update_group_weight_fn *blkio_update_group_weight_fn;

@@ -308,14 +314,13 @@ static inline void blkiocg_set_start_emp
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
-extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-	struct blkio_group *blkg, struct request_queue *q, dev_t dev,
-	enum blkio_policy_id plid);
-extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
-extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
-						struct request_queue *q,
-						enum blkio_policy_id plid);
+extern struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid);
+struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
+				       struct request_queue *q,
+				       enum blkio_policy_id plid);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 					unsigned long time,
 					unsigned long unaccounted_time);

@@ -336,17 +341,11 @@ cgroup_to_blkio_cgroup(struct cgroup *cg
 static inline struct blkio_cgroup *
 task_blkio_cgroup(struct task_struct *tsk) { return NULL; }
 
-static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, void *key, dev_t dev,
-		enum blkio_policy_id plid) {}
-
-static inline int blkio_alloc_blkg_stats(struct blkio_group *blkg) { return 0; }
-
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 
-static inline struct blkio_group *
-blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
+static inline struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+					      void *key) { return NULL; }
 static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
 						unsigned long time,
 						unsigned long unaccounted_time)

228 lines not on this page · raw message

137 lines not on this page · raw message

205 lines not on this page · raw message

Index: work/block/cfq.h
===================================================================
@@ -67,12 +67,6 @@ static inline void cfq_blkiocg_update_co
 				direction, sync);
 }
 
-static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev)
-{
-	blkiocg_add_blkio_group(blkcg, blkg, q, dev, BLKIO_POLICY_PROP);
-}
-
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return blkiocg_del_blkio_group(blkg);

@@ -105,8 +99,6 @@ static inline void cfq_blkiocg_update_di
 				uint64_t bytes, bool direction, bool sync) {}
 static inline void cfq_blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) {}
 
-static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct request_queue *q, dev_t dev) {}
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
 {
 	return 0;

index 2e6a043..c1793e2 100644
@@ -820,9 +820,12 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg,
 }
 
 static int blkio_policy_parse_and_set(char *buf,
-	struct blkio_policy_node *newpn, enum blkio_policy_id plid, int fileid)
+				      struct blkio_policy_node *newpn,
+				      enum blkio_policy_id plid, int fileid,
+				      struct blkio_cgroup *blkcg)
 {
 	struct gendisk *disk = NULL;
+	struct blkio_group *blkg = NULL;
 	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
 	unsigned long major, minor;
 	int i = 0, ret = -EINVAL;

@@ -868,12 +871,19 @@ static int blkio_policy_parse_and_set(char *buf,
 		goto out;
 
 	/* For rule removal, do not check for device presence. */
-	if (temp) {
-		disk = get_gendisk(dev, &part);
-		if (!disk || part) {
-			ret = -ENODEV;
-			goto out;
-		}
+	disk = get_gendisk(dev, &part);
+
+	if ((!disk || part) && temp) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	rcu_read_lock();
+
+	if (disk && !part) {
+		spin_lock_irq(disk->queue->queue_lock);
+		blkg = blkg_lookup_create(blkcg, disk->queue, plid);
+		spin_unlock_irq(disk->queue->queue_lock);
 	}
 
 	newpn->dev = dev;

@@ -882,25 +892,46 @@ static int blkio_policy_parse_and_set(char *buf,
 	case BLKIO_POLICY_PROP:
 		if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
 		     temp > BLKIO_WEIGHT_MAX)
-			goto out;
+			goto out_unlock;
 
 		newpn->plid = plid;
 		newpn->fileid = fileid;
 		newpn->val.weight = temp;
+		if (blkg)
+			blkg->conf.weight = temp;
 		break;
 	case BLKIO_POLICY_THROTL:
 		switch(fileid) {
 		case BLKIO_THROTL_read_bps_device:
+			if (blkg)
+				blkg->conf.bps[READ] = temp;
+			newpn->plid = plid;
+			newpn->fileid = fileid;
+			newpn->val.bps = temp;
+			break;
 		case BLKIO_THROTL_write_bps_device:
+			if (blkg)
+				blkg->conf.bps[WRITE] = temp;
 			newpn->plid = plid;
 			newpn->fileid = fileid;
 			newpn->val.bps = temp;
 			break;
 		case BLKIO_THROTL_read_iops_device:
+			if (temp > THROTL_IOPS_MAX)
+				goto out_unlock;
+
+			if (blkg)
+				blkg->conf.iops[READ] = temp;
+			newpn->plid = plid;
+			newpn->fileid = fileid;
+			newpn->val.iops = (unsigned int)temp;
+			break;
 		case BLKIO_THROTL_write_iops_device:
 			if (temp > THROTL_IOPS_MAX)
-				goto out;
+				goto out_unlock;
 
+			if (blkg)
+				blkg->conf.iops[WRITE] = temp;
 			newpn->plid = plid;
 			newpn->fileid = fileid;
 			newpn->val.iops = (unsigned int)temp;

@@ -911,6 +942,8 @@ static int blkio_policy_parse_and_set(char *buf,
 		BUG();
 	}
 	ret = 0;
+out_unlock:
+	rcu_read_unlock();
 out:
 	put_disk(disk);
 	return ret;

@@ -1060,26 +1093,29 @@ static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
 static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, struct blkio_policy_node *pn)
 {
-	unsigned int weight, iops;
-	u64 bps;
+	struct blkio_group_conf *conf = &blkg->conf;
 
 	switch(pn->plid) {
 	case BLKIO_POLICY_PROP:
-		weight = pn->val.weight ? pn->val.weight :
-				blkcg->weight;
-		blkio_update_group_weight(blkg, weight);
+		blkio_update_group_weight(blkg, conf->weight ?: blkcg->weight);
 		break;
 	case BLKIO_POLICY_THROTL:
 		switch(pn->fileid) {
 		case BLKIO_THROTL_read_bps_device:
+			blkio_update_group_bps(blkg, conf->bps[READ] ?: -1,
+					       pn->fileid);
+			break;
 		case BLKIO_THROTL_write_bps_device:
-			bps = pn->val.bps ? pn->val.bps : (-1);
-			blkio_update_group_bps(blkg, bps, pn->fileid);
+			blkio_update_group_bps(blkg, conf->bps[WRITE] ?: -1,
+					       pn->fileid);
 			break;
 		case BLKIO_THROTL_read_iops_device:
+			blkio_update_group_iops(blkg, conf->iops[READ] ?: -1,
+						pn->fileid);
+			break;
 		case BLKIO_THROTL_write_iops_device:
-			iops = pn->val.iops ? pn->val.iops : (-1);
-			blkio_update_group_iops(blkg, iops, pn->fileid);
+			blkio_update_group_iops(blkg, conf->iops[WRITE] ?: -1,
+						pn->fileid);
 			break;
 		}
 		break;

@@ -1117,7 +1153,7 @@ static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
 	int ret = 0;
 	char *buf;
 	struct blkio_policy_node *newpn, *pn;
-	struct blkio_cgroup *blkcg;
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgrp);
 	int keep_newpn = 0;
 	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
 	int fileid = BLKIOFILE_ATTR(cft->private);

@@ -1132,12 +1168,10 @@ static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
 		goto free_buf;
 	}
 
-	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid);
+	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid, blkcg);
 	if (ret)
 		goto free_newpn;
 
-	blkcg = cgroup_to_blkio_cgroup(cgrp);
-
 	spin_lock_irq(&blkcg->lock);
 
 	pn = blkio_policy_search_node(blkcg, newpn->dev, plid, fileid);

index f4057b7..3bbbe80 100644
@@ -154,6 +154,12 @@ struct blkio_group_stats_cpu {
 	struct u64_stats_sync syncp;
 };
 
+struct blkio_group_conf {
+	unsigned int weight;
+	unsigned int iops[2];
+	u64 bps[2];
+};
+
 struct blkio_group {
 	/* Pointer to the associated request_queue, RCU protected */
 	struct request_queue __rcu *q;

@@ -166,6 +172,9 @@ struct blkio_group {
 	/* policy which owns this blk group */
 	enum blkio_policy_id plid;
 
+	/* Configuration */
+	struct blkio_group_conf conf;
+
 	/* Need to serialize the stats in the case of reset/update */
 	spinlock_t stats_lock;
 	struct blkio_group_stats stats;

index 9da1ad4..f02eaf67 100644
@@ -196,10 +196,10 @@ static struct blkio_group *throtl_alloc_blkio_group(struct request_queue *q,
 	bio_list_init(&tg->bio_lists[1]);
 	tg->limits_changed = false;
 
-	tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
-	tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
-	tg->iops[READ] = blkcg_get_read_iops(blkcg, tg->blkg.dev);
-	tg->iops[WRITE] = blkcg_get_write_iops(blkcg, tg->blkg.dev);
+	tg->bps[READ] = -1;
+	tg->bps[WRITE] = -1;
+	tg->iops[READ] = -1;
+	tg->iops[WRITE] = -1;
 
 	/*
 	 * Take the initial reference that will be released on destroy

index 37a9660..0ee04b5 100644
@@ -1083,7 +1083,7 @@ static struct blkio_group *cfq_alloc_blkio_group(struct request_queue *q,
 		return NULL;
 
 	cfq_init_cfqg_base(cfqg);
-	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+	cfqg->weight = blkcg->weight;
 
 	/*
 	 * Take the initial reference that will be released on destroy

Index: work/block/blk-cgroup.c
===================================================================
@@ -823,9 +823,12 @@ static uint64_t blkio_get_stat(struct bl
 }
 
 static int blkio_policy_parse_and_set(char *buf,
-	struct blkio_policy_node *newpn, enum blkio_policy_id plid, int fileid)
+				      struct blkio_policy_node *newpn,
+				      enum blkio_policy_id plid, int fileid,
+				      struct blkio_cgroup *blkcg)
 {
 	struct gendisk *disk = NULL;
+	struct blkio_group *blkg = NULL;
 	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
 	unsigned long major, minor;
 	int i = 0, ret = -EINVAL;

@@ -871,11 +874,25 @@ static int blkio_policy_parse_and_set(ch
 		goto out;
 
 	/* For rule removal, do not check for device presence. */
-	if (temp) {
-		disk = get_gendisk(dev, &part);
-		if (!disk || part) {
-			ret = -ENODEV;
-			goto out;
+	disk = get_gendisk(dev, &part);
+
+	if ((!disk || part) && temp) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	rcu_read_lock();
+
+	if (disk && !part) {
+		spin_lock_irq(disk->queue->queue_lock);
+		blkg = blkg_lookup_create(blkcg, disk->queue, plid);
+		spin_unlock_irq(disk->queue->queue_lock);
+
+		if (IS_ERR(blkg)) {
+			ret = PTR_ERR(blkg);
+			if (ret == -EBUSY)
+				goto out_unlock;
+			blkg = NULL;
 		}
 	}
 

@@ -885,25 +902,46 @@ static int blkio_policy_parse_and_set(ch
 	case BLKIO_POLICY_PROP:
 		if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
 		     temp > BLKIO_WEIGHT_MAX)
-			goto out;
+			goto out_unlock;
 
 		newpn->plid = plid;
 		newpn->fileid = fileid;
 		newpn->val.weight = temp;
+		if (blkg)
+			blkg->conf.weight = temp;
 		break;
 	case BLKIO_POLICY_THROTL:
 		switch(fileid) {
 		case BLKIO_THROTL_read_bps_device:
+			if (blkg)
+				blkg->conf.bps[READ] = temp;
+			newpn->plid = plid;
+			newpn->fileid = fileid;
+			newpn->val.bps = temp;
+			break;
 		case BLKIO_THROTL_write_bps_device:
+			if (blkg)
+				blkg->conf.bps[WRITE] = temp;
 			newpn->plid = plid;
 			newpn->fileid = fileid;
 			newpn->val.bps = temp;
 			break;
 		case BLKIO_THROTL_read_iops_device:
+			if (temp > THROTL_IOPS_MAX)
+				goto out_unlock;
+
+			if (blkg)
+				blkg->conf.iops[READ] = temp;
+			newpn->plid = plid;
+			newpn->fileid = fileid;
+			newpn->val.iops = (unsigned int)temp;
+			break;
 		case BLKIO_THROTL_write_iops_device:
 			if (temp > THROTL_IOPS_MAX)
-				goto out;
+				goto out_unlock;
 
+			if (blkg)
+				blkg->conf.iops[WRITE] = temp;
 			newpn->plid = plid;
 			newpn->fileid = fileid;
 			newpn->val.iops = (unsigned int)temp;

@@ -914,8 +952,21 @@ static int blkio_policy_parse_and_set(ch
 		BUG();
 	}
 	ret = 0;
+out_unlock:
+	rcu_read_unlock();
 out:
 	put_disk(disk);
+
+	/*
+	 * If queue was bypassing, we should retry.  Do so after a short
+	 * msleep().  It isn't strictly necessary but queue can be
+	 * bypassing for some time and it's always nice to avoid busy
+	 * looping.
+	 */
+	if (ret == -EBUSY) {
+		msleep(10);
+		return restart_syscall();
+	}
 	return ret;
 }
 

@@ -1063,26 +1114,29 @@ static void blkio_update_policy_rule(str
 static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, struct blkio_policy_node *pn)
 {
-	unsigned int weight, iops;
-	u64 bps;
+	struct blkio_group_conf *conf = &blkg->conf;
 
 	switch(pn->plid) {
 	case BLKIO_POLICY_PROP:
-		weight = pn->val.weight ? pn->val.weight :
-				blkcg->weight;
-		blkio_update_group_weight(blkg, weight);
+		blkio_update_group_weight(blkg, conf->weight ?: blkcg->weight);
 		break;
 	case BLKIO_POLICY_THROTL:
 		switch(pn->fileid) {
 		case BLKIO_THROTL_read_bps_device:
+			blkio_update_group_bps(blkg, conf->bps[READ] ?: -1,
+					       pn->fileid);
+			break;
 		case BLKIO_THROTL_write_bps_device:
-			bps = pn->val.bps ? pn->val.bps : (-1);
-			blkio_update_group_bps(blkg, bps, pn->fileid);
+			blkio_update_group_bps(blkg, conf->bps[WRITE] ?: -1,
+					       pn->fileid);
 			break;
 		case BLKIO_THROTL_read_iops_device:
+			blkio_update_group_iops(blkg, conf->iops[READ] ?: -1,
+						pn->fileid);
+			break;
 		case BLKIO_THROTL_write_iops_device:
-			iops = pn->val.iops ? pn->val.iops : (-1);
-			blkio_update_group_iops(blkg, iops, pn->fileid);
+			blkio_update_group_iops(blkg, conf->iops[WRITE] ?: -1,
+						pn->fileid);
 			break;
 		}
 		break;

@@ -1120,7 +1174,7 @@ static int blkiocg_file_write(struct cgr
 	int ret = 0;
 	char *buf;
 	struct blkio_policy_node *newpn, *pn;
-	struct blkio_cgroup *blkcg;
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgrp);
 	int keep_newpn = 0;
 	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
 	int fileid = BLKIOFILE_ATTR(cft->private);

@@ -1135,12 +1189,10 @@ static int blkiocg_file_write(struct cgr
 		goto free_buf;
 	}
 
-	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid);
+	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid, blkcg);
 	if (ret)
 		goto free_newpn;
 
-	blkcg = cgroup_to_blkio_cgroup(cgrp);
-
 	spin_lock_irq(&blkcg->lock);
 
 	pn = blkio_policy_search_node(blkcg, newpn->dev, plid, fileid);

Index: work/block/blk-cgroup.h
===================================================================
@@ -154,6 +154,12 @@ struct blkio_group_stats_cpu {
 	struct u64_stats_sync syncp;
 };
 
+struct blkio_group_conf {
+	unsigned int weight;
+	unsigned int iops[2];
+	u64 bps[2];
+};
+
 struct blkio_group {
 	/* Pointer to the associated request_queue, RCU protected */
 	struct request_queue __rcu *q;

@@ -166,6 +172,9 @@ struct blkio_group {
 	/* policy which owns this blk group */
 	enum blkio_policy_id plid;
 
+	/* Configuration */
+	struct blkio_group_conf conf;
+
 	/* Need to serialize the stats in the case of reset/update */
 	spinlock_t stats_lock;
 	struct blkio_group_stats stats;

Index: work/block/blk-throttle.c
===================================================================
@@ -196,10 +196,10 @@ static struct blkio_group *throtl_alloc_
 	bio_list_init(&tg->bio_lists[1]);
 	tg->limits_changed = false;
 
-	tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
-	tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
-	tg->iops[READ] = blkcg_get_read_iops(blkcg, tg->blkg.dev);
-	tg->iops[WRITE] = blkcg_get_write_iops(blkcg, tg->blkg.dev);
+	tg->bps[READ] = -1;
+	tg->bps[WRITE] = -1;
+	tg->iops[READ] = -1;
+	tg->iops[WRITE] = -1;
 
 	/*
 	 * Take the initial reference that will be released on destroy

Index: work/block/cfq-iosched.c
===================================================================
@@ -1083,7 +1083,7 @@ static struct blkio_group *cfq_alloc_blk
 		return NULL;
 
 	cfq_init_cfqg_base(cfqg);
-	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+	cfqg->weight = blkcg->weight;
 
 	/*
 	 * Take the initial reference that will be released on destroy

index c1793e2..efb159c 100644
@@ -59,54 +59,6 @@ struct cgroup_subsys blkio_subsys = {
 };
 EXPORT_SYMBOL_GPL(blkio_subsys);
 
-static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
-					    struct blkio_policy_node *pn)
-{
-	list_add(&pn->node, &blkcg->policy_list);
-}
-
-static inline bool cftype_blkg_same_policy(struct cftype *cft,
-			struct blkio_group *blkg)
-{
-	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
-
-	if (blkg->plid == plid)
-		return 1;
-
-	return 0;
-}
-
-/* Determines if policy node matches cgroup file being accessed */
-static inline bool pn_matches_cftype(struct cftype *cft,
-			struct blkio_policy_node *pn)
-{
-	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
-	int fileid = BLKIOFILE_ATTR(cft->private);
-
-	return (plid == pn->plid && fileid == pn->fileid);
-}
-
-/* Must be called with blkcg->lock held */
-static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
-{
-	list_del(&pn->node);
-}
-
-/* Must be called with blkcg->lock held */
-static struct blkio_policy_node *
-blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev,
-		enum blkio_policy_id plid, int fileid)
-{
-	struct blkio_policy_node *pn;
-
-	list_for_each_entry(pn, &blkcg->policy_list, node) {
-		if (pn->dev == dev && pn->plid == plid && pn->fileid == fileid)
-			return pn;
-	}
-
-	return NULL;
-}
-
 struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 {
 	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),

@@ -819,10 +771,8 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg,
 	return disk_total;
 }
 
-static int blkio_policy_parse_and_set(char *buf,
-				      struct blkio_policy_node *newpn,
-				      enum blkio_policy_id plid, int fileid,
-				      struct blkio_cgroup *blkcg)
+static int blkio_policy_parse_and_set(char *buf, enum blkio_policy_id plid,
+				      int fileid, struct blkio_cgroup *blkcg)
 {
 	struct gendisk *disk = NULL;
 	struct blkio_group *blkg = NULL;

@@ -870,23 +820,18 @@ static int blkio_policy_parse_and_set(char *buf,
 	if (strict_strtoull(s[1], 10, &temp))
 		goto out;
 
-	/* For rule removal, do not check for device presence. */
 	disk = get_gendisk(dev, &part);
-
-	if ((!disk || part) && temp) {
-		ret = -ENODEV;
+	if (!disk || part)
 		goto out;
-	}
 
 	rcu_read_lock();
 
-	if (disk && !part) {
-		spin_lock_irq(disk->queue->queue_lock);
-		blkg = blkg_lookup_create(blkcg, disk->queue, plid);
-		spin_unlock_irq(disk->queue->queue_lock);
-	}
+	spin_lock_irq(disk->queue->queue_lock);
+	blkg = blkg_lookup_create(blkcg, disk->queue, plid);
+	spin_unlock_irq(disk->queue->queue_lock);
 
-	newpn->dev = dev;
+	if (!blkg)
+		goto out_unlock;
 
 	switch (plid) {
 	case BLKIO_POLICY_PROP:

@@ -894,47 +839,30 @@ static int blkio_policy_parse_and_set(char *buf,
 		     temp > BLKIO_WEIGHT_MAX)
 			goto out_unlock;
 
-		newpn->plid = plid;
-		newpn->fileid = fileid;
-		newpn->val.weight = temp;
-		if (blkg)
-			blkg->conf.weight = temp;
+		blkg->conf.weight = temp;
+		blkio_update_group_weight(blkg, temp ?: blkcg->weight);
 		break;
 	case BLKIO_POLICY_THROTL:
 		switch(fileid) {
 		case BLKIO_THROTL_read_bps_device:
-			if (blkg)
-				blkg->conf.bps[READ] = temp;
-			newpn->plid = plid;
-			newpn->fileid = fileid;
-			newpn->val.bps = temp;
+			blkg->conf.bps[READ] = temp;
+			blkio_update_group_bps(blkg, temp ?: -1, fileid);
 			break;
 		case BLKIO_THROTL_write_bps_device:
-			if (blkg)
-				blkg->conf.bps[WRITE] = temp;
-			newpn->plid = plid;
-			newpn->fileid = fileid;
-			newpn->val.bps = temp;
+			blkg->conf.bps[WRITE] = temp;
+			blkio_update_group_bps(blkg, temp ?: -1, fileid);
 			break;
 		case BLKIO_THROTL_read_iops_device:
 			if (temp > THROTL_IOPS_MAX)
 				goto out_unlock;
-
-			if (blkg)
-				blkg->conf.iops[READ] = temp;
-			newpn->plid = plid;
-			newpn->fileid = fileid;
-			newpn->val.iops = (unsigned int)temp;
+			blkg->conf.iops[READ] = temp;
+			blkio_update_group_iops(blkg, temp ?: -1, fileid);
 			break;
 		case BLKIO_THROTL_write_iops_device:
 			if (temp > THROTL_IOPS_MAX)
 				goto out_unlock;
-
-			if (blkg)
-				blkg->conf.iops[WRITE] = temp;
-			newpn->plid = plid;
-			newpn->fileid = fileid;
-			newpn->val.iops = (unsigned int)temp;
+			blkg->conf.iops[WRITE] = temp;
+			blkio_update_group_iops(blkg, temp ?: -1, fileid);
 			break;
 		}
 		break;

@@ -949,212 +877,12 @@ out:
 	return ret;
 }
 
-unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
-			      dev_t dev)
-{
-	struct blkio_policy_node *pn;
-	unsigned long flags;
-	unsigned int weight;
-
-	spin_lock_irqsave(&blkcg->lock, flags);
-
-	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_PROP,
-				BLKIO_PROP_weight_device);
-	if (pn)
-		weight = pn->val.weight;
-	else
-		weight = blkcg->weight;
-
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-
-	return weight;
-}
-EXPORT_SYMBOL_GPL(blkcg_get_weight);
-
-uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
-{
-	struct blkio_policy_node *pn;
-	unsigned long flags;
-	uint64_t bps = -1;
-
-	spin_lock_irqsave(&blkcg->lock, flags);
-	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
-				BLKIO_THROTL_read_bps_device);
-	if (pn)
-		bps = pn->val.bps;
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-
-	return bps;
-}
-
-uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev)
-{
-	struct blkio_policy_node *pn;
-	unsigned long flags;
-	uint64_t bps = -1;
-
-	spin_lock_irqsave(&blkcg->lock, flags);
-	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
-				BLKIO_THROTL_write_bps_device);
-	if (pn)
-		bps = pn->val.bps;
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-
-	return bps;
-}
-
-unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg, dev_t dev)
-{
-	struct blkio_policy_node *pn;
-	unsigned long flags;
-	unsigned int iops = -1;
-
-	spin_lock_irqsave(&blkcg->lock, flags);
-	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
-				BLKIO_THROTL_read_iops_device);
-	if (pn)
-		iops = pn->val.iops;
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-
-	return iops;
-}
-
-unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg, dev_t dev)
-{
-	struct blkio_policy_node *pn;
-	unsigned long flags;
-	unsigned int iops = -1;
-
-	spin_lock_irqsave(&blkcg->lock, flags);
-	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
-				BLKIO_THROTL_write_iops_device);
-	if (pn)
-		iops = pn->val.iops;
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-
-	return iops;
-}
-
-/* Checks whether user asked for deleting a policy rule */
-static bool blkio_delete_rule_command(struct blkio_policy_node *pn)
-{
-	switch(pn->plid) {
-	case BLKIO_POLICY_PROP:
-		if (pn->val.weight == 0)
-			return 1;
-		break;
-	case BLKIO_POLICY_THROTL:
-		switch(pn->fileid) {
-		case BLKIO_THROTL_read_bps_device:
-		case BLKIO_THROTL_write_bps_device:
-			if (pn->val.bps == 0)
-				return 1;
-			break;
-		case BLKIO_THROTL_read_iops_device:
-		case BLKIO_THROTL_write_iops_device:
-			if (pn->val.iops == 0)
-				return 1;
-		}
-		break;
-	default:
-		BUG();
-	}
-
-	return 0;
-}
-
-static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
-					struct blkio_policy_node *newpn)
-{
-	switch(oldpn->plid) {
-	case BLKIO_POLICY_PROP:
-		oldpn->val.weight = newpn->val.weight;
-		break;
-	case BLKIO_POLICY_THROTL:
-		switch(newpn->fileid) {
-		case BLKIO_THROTL_read_bps_device:
-		case BLKIO_THROTL_write_bps_device:
-			oldpn->val.bps = newpn->val.bps;
-			break;
-		case BLKIO_THROTL_read_iops_device:
-		case BLKIO_THROTL_write_iops_device:
-			oldpn->val.iops = newpn->val.iops;
-		}
-		break;
-	default:
-		BUG();
-	}
-}
-
-/*
- * Some rules/values in blkg have changed. Propagate those to respective
- * policies.
- */
-static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
-		struct blkio_group *blkg, struct blkio_policy_node *pn)
-{
-	struct blkio_group_conf *conf = &blkg->conf;
-
-	switch(pn->plid) {
-	case BLKIO_POLICY_PROP:
-		blkio_update_group_weight(blkg, conf->weight ?: blkcg->weight);
-		break;
-	case BLKIO_POLICY_THROTL:
-		switch(pn->fileid) {
-		case BLKIO_THROTL_read_bps_device:
-			blkio_update_group_bps(blkg, conf->bps[READ] ?: -1,
-					       pn->fileid);
-			break;
-		case BLKIO_THROTL_write_bps_device:
-			blkio_update_group_bps(blkg, conf->bps[WRITE] ?: -1,
-					       pn->fileid);
-			break;
-		case BLKIO_THROTL_read_iops_device:
-			blkio_update_group_iops(blkg, conf->iops[READ] ?: -1,
-						pn->fileid);
-			break;
-		case BLKIO_THROTL_write_iops_device:
-			blkio_update_group_iops(blkg, conf->iops[WRITE] ?: -1,
-						pn->fileid);
-			break;
-		}
-		break;
-	default:
-		BUG();
-	}
-}
-
-/*
- * A policy node rule has been updated. Propagate this update to all the
- * block groups which might be affected by this update.
- */
-static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
-				struct blkio_policy_node *pn)
-{
-	struct blkio_group *blkg;
-	struct hlist_node *n;
-
-	spin_lock(&blkio_list_lock);
-	spin_lock_irq(&blkcg->lock);
-
-	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-		if (pn->dev != blkg->dev || pn->plid != blkg->plid)
-			continue;
-		blkio_update_blkg_policy(blkcg, blkg, pn);
-	}
-
-	spin_unlock_irq(&blkcg->lock);
-	spin_unlock(&blkio_list_lock);
-}
-
 static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
  				       const char *buffer)
 {
 	int ret = 0;
 	char *buf;
-	struct blkio_policy_node *newpn, *pn;
 	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgrp);
-	int keep_newpn = 0;
 	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
 	int fileid = BLKIOFILE_ATTR(cft->private);
 

@@ -1162,69 +890,42 @@ static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
 	if (!buf)
 		return -ENOMEM;
 
-	newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
-	if (!newpn) {
-		ret = -ENOMEM;
-		goto free_buf;
-	}
-
-	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid, blkcg);
-	if (ret)
-		goto free_newpn;
-
-	spin_lock_irq(&blkcg->lock);
-
-	pn = blkio_policy_search_node(blkcg, newpn->dev, plid, fileid);
-	if (!pn) {
-		if (!blkio_delete_rule_command(newpn)) {
-			blkio_policy_insert_node(blkcg, newpn);
-			keep_newpn = 1;
-		}
-		spin_unlock_irq(&blkcg->lock);
-		goto update_io_group;
-	}
-
-	if (blkio_delete_rule_command(newpn)) {
-		blkio_policy_delete_node(pn);
-		kfree(pn);
-		spin_unlock_irq(&blkcg->lock);
-		goto update_io_group;
-	}
-	spin_unlock_irq(&blkcg->lock);
-
-	blkio_update_policy_rule(pn, newpn);
-
-update_io_group:
-	blkio_update_policy_node_blkg(blkcg, newpn);
-
-free_newpn:
-	if (!keep_newpn)
-		kfree(newpn);
-free_buf:
+	ret = blkio_policy_parse_and_set(buf, plid, fileid, blkcg);
 	kfree(buf);
 	return ret;
 }
 
-static void
-blkio_print_policy_node(struct seq_file *m, struct blkio_policy_node *pn)
+static void blkio_print_group_conf(struct cftype *cft, struct blkio_group *blkg,
+				   struct seq_file *m)
 {
-	switch(pn->plid) {
+	int fileid = BLKIOFILE_ATTR(cft->private);
+	int rw = WRITE;
+
+	switch (blkg->plid) {
 		case BLKIO_POLICY_PROP:
-			if (pn->fileid == BLKIO_PROP_weight_device)
-				seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
-					MINOR(pn->dev), pn->val.weight);
+			if (blkg->conf.weight)
+				seq_printf(m, "%u:%u\t%u\n", MAJOR(blkg->dev),
+					MINOR(blkg->dev), blkg->conf.weight);
 			break;
 		case BLKIO_POLICY_THROTL:
-			switch(pn->fileid) {
+			switch (fileid) {
 			case BLKIO_THROTL_read_bps_device:
+				rw = READ;
 			case BLKIO_THROTL_write_bps_device:
-				seq_printf(m, "%u:%u\t%llu\n", MAJOR(pn->dev),
-					MINOR(pn->dev), pn->val.bps);
+				if (blkg->conf.bps[rw])
+					seq_printf(m, "%u:%u\t%llu\n",
+						   MAJOR(blkg->dev),
+						   MINOR(blkg->dev),
+						   blkg->conf.bps[rw]);
 				break;
 			case BLKIO_THROTL_read_iops_device:
+				rw = READ;
 			case BLKIO_THROTL_write_iops_device:
-				seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
-					MINOR(pn->dev), pn->val.iops);
+				if (blkg->conf.iops[rw])
+					seq_printf(m, "%u:%u\t%u\n",
+						   MAJOR(blkg->dev),
+						   MINOR(blkg->dev),
+						   blkg->conf.iops[rw]);
 				break;
 			}
 			break;

@@ -1234,20 +935,17 @@ blkio_print_policy_node(struct seq_file *m, struct blkio_policy_node *pn)
 }
 
 /* cgroup files which read their data from policy nodes end up here */
-static void blkio_read_policy_node_files(struct cftype *cft,
-			struct blkio_cgroup *blkcg, struct seq_file *m)
+static void blkio_read_conf(struct cftype *cft, struct blkio_cgroup *blkcg,
+			    struct seq_file *m)
 {
-	struct blkio_policy_node *pn;
+	struct blkio_group *blkg;
+	struct hlist_node *n;
 
-	if (!list_empty(&blkcg->policy_list)) {
-		spin_lock_irq(&blkcg->lock);
-		list_for_each_entry(pn, &blkcg->policy_list, node) {
-			if (!pn_matches_cftype(cft, pn))
-				continue;
-			blkio_print_policy_node(m, pn);
-		}
-		spin_unlock_irq(&blkcg->lock);
-	}
+	spin_lock_irq(&blkcg->lock);
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node)
+		if (BLKIOFILE_POLICY(cft->private) == blkg->plid)
+			blkio_print_group_conf(cft, blkg, m);
+	spin_unlock_irq(&blkcg->lock);
 }
 
 static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,

@@ -1263,7 +961,7 @@ static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
 	case BLKIO_POLICY_PROP:
 		switch(name) {
 		case BLKIO_PROP_weight_device:
-			blkio_read_policy_node_files(cft, blkcg, m);
+			blkio_read_conf(cft, blkcg, m);
 			return 0;
 		default:
 			BUG();

@@ -1275,7 +973,7 @@ static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
 		case BLKIO_THROTL_write_bps_device:
 		case BLKIO_THROTL_read_iops_device:
 		case BLKIO_THROTL_write_iops_device:
-			blkio_read_policy_node_files(cft, blkcg, m);
+			blkio_read_conf(cft, blkcg, m);
 			return 0;
 		default:
 			BUG();

@@ -1299,7 +997,7 @@ static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
 		if (blkg->dev) {
-			if (!cftype_blkg_same_policy(cft, blkg))
+			if (BLKIOFILE_POLICY(cft->private) != blkg->plid)
 				continue;
 			if (pcpu)
 				cgroup_total += blkio_get_stat_cpu(blkg, cb,

@@ -1398,11 +1096,10 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
 	return 0;
 }
 
-static int blkio_weight_write(struct blkio_cgroup *blkcg, u64 val)
+static int blkio_weight_write(struct blkio_cgroup *blkcg, int plid, u64 val)
 {
 	struct blkio_group *blkg;
 	struct hlist_node *n;
-	struct blkio_policy_node *pn;
 
 	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
 		return -EINVAL;

@@ -1411,14 +1108,10 @@ static int blkio_weight_write(struct blkio_cgroup *blkcg, u64 val)
 	spin_lock_irq(&blkcg->lock);
 	blkcg->weight = (unsigned int)val;
 
-	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-		pn = blkio_policy_search_node(blkcg, blkg->dev,
-				BLKIO_POLICY_PROP, BLKIO_PROP_weight_device);
-		if (pn)
-			continue;
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node)
+		if (blkg->plid == plid && !blkg->conf.weight)
+			blkio_update_group_weight(blkg, blkcg->weight);
 
-		blkio_update_group_weight(blkg, blkcg->weight);
-	}
 	spin_unlock_irq(&blkcg->lock);
 	spin_unlock(&blkio_list_lock);
 	return 0;