blkcg: factor out blkio_group creation

Currently both blk-throttle and cfq-iosched implement their own
blkio_group creation code in throtl_get_tg() and cfq_get_cfqg().  This
patch factors out the common code into blkg_lookup_create(), which
returns ERR_PTR value so that transitional failures due to queue
bypass can be distinguished from other failures.

* New plkio_policy_ops methods blkio_alloc_group_fn() and
  blkio_link_group_fn added.  Both are transitional and will be
  removed once the blkg management code is fully moved into
  blk-cgroup.c.

* blkio_alloc_group_fn() allocates policy-specific blkg which is
  usually a larger data structure with blkg as the first entry and
  intiailizes it.  Note that initialization of blkg proper, including
  percpu stats, is responsibility of blk-cgroup proper.

  Note that default config (weight, bps...) initialization is done
  from this method; otherwise, we end up violating locking order
  between blkcg and q locks via blkcg_get_CONF() functions.

* blkio_link_group_fn() is called under queue_lock and responsible for
  linking the blkg to the queue.  blkcg side is handled by blk-cgroup
  proper.

* The common blkg creation function is named blkg_lookup_create() and
  blkiocg_lookup_group() is renamed to blkg_lookup() for consistency.
  Also, throtl / cfq related functions are similarly [re]named for
  consistency.

This simplifies blkcg policy implementations and enables further
cleanup.

-v2: Vivek noticed that blkg_lookup_create() incorrectly tested
     blk_queue_dead() instead of blk_queue_bypass() leading a user of
     the function ending up creating a new blkg on bypassing queue.
     This is a bug introduced while relocating bypass patches before
     this one.  Fixed.

-v3: ERR_PTR patch folded into this one.  @for_root added to
     blkg_lookup_create() to allow creating root group on a bypassed
     queue during elevator switch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

5 files changed, 193 insertions, 248 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index f1b08d3cba5..bc989149631 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -465,38 +465,93 @@ 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,
+                                       bool for_root)
+        __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, *new_blkg;
 
-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 bypassing queue.
+         * The following can be removed if blkg lookup is guaranteed to
+         * fail on a bypassing queue.
+         */
+        if (unlikely(blk_queue_bypass(q)) && !for_root)
+                return ERR_PTR(blk_queue_dead(q) ? -EINVAL : -EBUSY);
+
+        blkg = blkg_lookup(blkcg, q, plid);
+        if (blkg)
+                return blkg;
+
+        if (!css_tryget(&blkcg->css))
+                return ERR_PTR(-EINVAL);
+
+        /*
+         * 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 bypass get turned on inbetween? */
+        if (unlikely(blk_queue_bypass(q)) && !for_root) {
+                blkg = ERR_PTR(blk_queue_dead(q) ? -EINVAL : -EBUSY);
+                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)) {
+                blkg = ERR_PTR(-ENOMEM);
+                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 +588,9 @@ 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 +600,7 @@ 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);
 
 void blkg_destroy_all(struct request_queue *q)
 {
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 562fa55d97b..2600ae7e6f6 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -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;
@@ -307,14 +313,14 @@ 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,
+                                       bool for_root);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
                                         unsigned long time,
                                         unsigned long unaccounted_time);
@@ -335,17 +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)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index aeeb798d1cd..2ae637b9e80 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -181,17 +181,25 @@ static void throtl_put_tg(struct throtl_grp *tg)
         call_rcu(&tg->rcu_head, throtl_free_tg);
 }
 
-static void throtl_init_group(struct throtl_grp *tg)
+static struct blkio_group *throtl_alloc_blkio_group(struct request_queue *q,
+                                                    struct blkio_cgroup *blkcg)
 {
+        struct throtl_grp *tg;
+
+        tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, q->node);
+        if (!tg)
+                return NULL;
+
         INIT_HLIST_NODE(&tg->tg_node);
         RB_CLEAR_NODE(&tg->rb_node);
         bio_list_init(&tg->bio_lists[0]);
         bio_list_init(&tg->bio_lists[1]);
         tg->limits_changed = false;
 
-        /* Practically unlimited BW */
-        tg->bps[0] = tg->bps[1] = -1;
-        tg->iops[0] = tg->iops[1] = -1;
+        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);
 
         /*
          * Take the initial reference that will be released on destroy
@@ -200,14 +208,8 @@ static void throtl_init_group(struct throtl_grp *tg)
          * exit or cgroup deletion path depending on who is exiting first.
          */
         atomic_set(&tg->ref, 1);
-}
 
-/* Should be called with rcu read lock held (needed for blkcg) */
-static void
-throtl_add_group_to_td_list(struct throtl_data *td, struct throtl_grp *tg)
-{
-        hlist_add_head(&tg->tg_node, &td->tg_list);
-        td->nr_undestroyed_grps++;
+        return &tg->blkg;
 }
 
 static void
@@ -246,119 +248,62 @@ throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
         spin_unlock_irq(td->queue->queue_lock);
 }
 
-static void throtl_init_add_tg_lists(struct throtl_data *td,
-                        struct throtl_grp *tg, struct blkio_cgroup *blkcg)
+static void throtl_link_blkio_group(struct request_queue *q,
+                                    struct blkio_group *blkg)
 {
-        __throtl_tg_fill_dev_details(td, tg);
-
-        /* Add group onto cgroup list */
-        blkiocg_add_blkio_group(blkcg, &tg->blkg, td->queue,
-                                tg->blkg.dev, BLKIO_POLICY_THROTL);
-
-        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);
-
-        throtl_add_group_to_td_list(td, tg);
-}
-
-/* Should be called without queue lock and outside of rcu period */
-static struct throtl_grp *throtl_alloc_tg(struct throtl_data *td)
-{
-        struct throtl_grp *tg = NULL;
-        int ret;
-
-        tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
-        if (!tg)
-                return NULL;
-
-        ret = blkio_alloc_blkg_stats(&tg->blkg);
+        struct throtl_data *td = q->td;
+        struct throtl_grp *tg = tg_of_blkg(blkg);
 
-        if (ret) {
-                kfree(tg);
-                return NULL;
-        }
+        __throtl_tg_fill_dev_details(td, tg);
 
-        throtl_init_group(tg);
-        return tg;
+        hlist_add_head(&tg->tg_node, &td->tg_list);
+        td->nr_undestroyed_grps++;
 }
 
 static struct
-throtl_grp *throtl_find_tg(struct throtl_data *td, struct blkio_cgroup *blkcg)
+throtl_grp *throtl_lookup_tg(struct throtl_data *td, struct blkio_cgroup *blkcg)
 {
         struct throtl_grp *tg = NULL;
 
         /*
          * This is the common case when there are no blkio cgroups.
-         * Avoid lookup in this case
-         */
+         * Avoid lookup in this case
+         */
         if (blkcg == &blkio_root_cgroup)
                 tg = td->root_tg;
         else
-                tg = tg_of_blkg(blkiocg_lookup_group(blkcg, td->queue,
-                                                     BLKIO_POLICY_THROTL));
+                tg = tg_of_blkg(blkg_lookup(blkcg, td->queue,
+                                            BLKIO_POLICY_THROTL));
 
         __throtl_tg_fill_dev_details(td, tg);
         return tg;
 }
 
-static struct throtl_grp *throtl_get_tg(struct throtl_data *td,
-                                        struct blkio_cgroup *blkcg)
+static struct throtl_grp *throtl_lookup_create_tg(struct throtl_data *td,
+                                                  struct blkio_cgroup *blkcg)
 {
-        struct throtl_grp *tg = NULL, *__tg = NULL;
         struct request_queue *q = td->queue;
-
-        /* no throttling for dead queue */
-        if (unlikely(blk_queue_bypass(q)))
-                return NULL;
-
-        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
-         * we need to drop rcu lock and queue_lock before we call alloc.
-         */
-        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);
-        css_put(&blkcg->css);
-
-        /* Make sure @q is still alive */
-        if (unlikely(blk_queue_bypass(q))) {
-                kfree(tg);
-                return NULL;
-        }
+        struct throtl_grp *tg = NULL;
 
         /*
-         * If some other thread already allocated the group while we were
-         * not holding queue lock, free up the group
+         * This is the common case when there are no blkio cgroups.
+         * Avoid lookup in this case
          */
-        __tg = throtl_find_tg(td, blkcg);
+        if (blkcg == &blkio_root_cgroup) {
+                tg = td->root_tg;
+        } else {
+                struct blkio_group *blkg;
 
-        if (__tg) {
-                kfree(tg);
-                return __tg;
-        }
+                blkg = blkg_lookup_create(blkcg, q, BLKIO_POLICY_THROTL, false);
 
-        /* Group allocation failed. Account the IO to root group */
-        if (!tg) {
-                tg = td->root_tg;
-                return tg;
+                /* if %NULL and @q is alive, fall back to root_tg */
+                if (!IS_ERR(blkg))
+                        tg = tg_of_blkg(blkg);
+                else if (!blk_queue_dead(q))
+                        tg = td->root_tg;
         }
 
-        throtl_init_add_tg_lists(td, tg, blkcg);
+        __throtl_tg_fill_dev_details(td, tg);
         return tg;
 }
 
@@ -1107,6 +1052,8 @@ static void throtl_shutdown_wq(struct request_queue *q)
 
 static struct blkio_policy_type blkio_policy_throtl = {
         .ops = {
+                .blkio_alloc_group_fn = throtl_alloc_blkio_group,
+                .blkio_link_group_fn = throtl_link_blkio_group,
                 .blkio_unlink_group_fn = throtl_unlink_blkio_group,
                 .blkio_clear_queue_fn = throtl_clear_queue,
                 .blkio_update_group_read_bps_fn =
@@ -1141,7 +1088,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
          */
         rcu_read_lock();
         blkcg = task_blkio_cgroup(current);
-        tg = throtl_find_tg(td, blkcg);
+        tg = throtl_lookup_tg(td, blkcg);
         if (tg) {
                 throtl_tg_fill_dev_details(td, tg);
 
@@ -1157,7 +1104,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
          * IO group
          */
         spin_lock_irq(q->queue_lock);
-        tg = throtl_get_tg(td, blkcg);
+        tg = throtl_lookup_create_tg(td, blkcg);
         if (unlikely(!tg))
                 goto out_unlock;
 
@@ -1252,6 +1199,7 @@ void blk_throtl_drain(struct request_queue *q)
 int blk_throtl_init(struct request_queue *q)
 {
         struct throtl_data *td;
+        struct blkio_group *blkg;
 
         td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
         if (!td)
@@ -1262,13 +1210,17 @@ int blk_throtl_init(struct request_queue *q)
         td->limits_changed = false;
         INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
 
-        /* alloc and Init root group. */
+        q->td = td;
         td->queue = q;
 
+        /* alloc and init root group. */
         rcu_read_lock();
         spin_lock_irq(q->queue_lock);
 
-        td->root_tg = throtl_get_tg(td, &blkio_root_cgroup);
+        blkg = blkg_lookup_create(&blkio_root_cgroup, q, BLKIO_POLICY_THROTL,
+                                  true);
+        if (!IS_ERR(blkg))
+                td->root_tg = tg_of_blkg(blkg);
 
         spin_unlock_irq(q->queue_lock);
         rcu_read_unlock();
@@ -1277,9 +1229,6 @@ int blk_throtl_init(struct request_queue *q)
                 kfree(td);
                 return -ENOMEM;
         }
-
-        /* Attach throtl data to request queue */
-        q->td = td;
         return 0;
 }
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1c3f41b9d5d..acef564578c 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1048,10 +1048,12 @@ static void cfq_update_blkio_group_weight(struct request_queue *q,
         cfqg->needs_update = true;
 }
 
-static void cfq_init_add_cfqg_lists(struct cfq_data *cfqd,
-                        struct cfq_group *cfqg, struct blkio_cgroup *blkcg)
+static void cfq_link_blkio_group(struct request_queue *q,
+                                 struct blkio_group *blkg)
 {
-        struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+        struct cfq_data *cfqd = q->elevator->elevator_data;
+        struct backing_dev_info *bdi = &q->backing_dev_info;
+        struct cfq_group *cfqg = cfqg_of_blkg(blkg);
         unsigned int major, minor;
 
         /*
@@ -1062,34 +1064,26 @@ 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,
-                                        cfqd->queue, MKDEV(major, minor));
-        } else
-                cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
-                                        cfqd->queue, 0);
+                blkg->dev = MKDEV(major, minor);
+        }
 
         cfqd->nr_blkcg_linked_grps++;
-        cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
 
         /* Add group on cfqd list */
         hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 }
 
-/*
- * Should be called from sleepable context. No request queue lock as per
- * cpu stats are allocated dynamically and alloc_percpu needs to be called
- * from sleepable context.
- */
-static struct cfq_group * cfq_alloc_cfqg(struct cfq_data *cfqd)
+static struct blkio_group *cfq_alloc_blkio_group(struct request_queue *q,
+                                                 struct blkio_cgroup *blkcg)
 {
         struct cfq_group *cfqg;
-        int ret;
 
-        cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
+        cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, q->node);
         if (!cfqg)
                 return NULL;
 
         cfq_init_cfqg_base(cfqg);
+        cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
 
         /*
          * Take the initial reference that will be released on destroy
@@ -1099,90 +1093,38 @@ static struct cfq_group * cfq_alloc_cfqg(struct cfq_data *cfqd)
          */
         cfqg->ref = 1;
 
-        ret = blkio_alloc_blkg_stats(&cfqg->blkg);
-        if (ret) {
-                kfree(cfqg);
-                return NULL;
-        }
-
-        return cfqg;
-}
-
-static struct cfq_group *
-cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
-{
-        struct cfq_group *cfqg = NULL;
-        struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
-        unsigned int major, minor;
-
-        /*
-         * This is the common case when there are no blkio cgroups.
-         * Avoid lookup in this case
-         */
-        if (blkcg == &blkio_root_cgroup)
-                cfqg = cfqd->root_group;
-        else
-                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);
-                cfqg->blkg.dev = MKDEV(major, minor);
-        }
-
-        return cfqg;
+        return &cfqg->blkg;
 }
 
 /*
  * 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,
-                                      struct blkio_cgroup *blkcg)
+static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd,
+                                                struct blkio_cgroup *blkcg)
 {
-        struct cfq_group *cfqg = NULL, *__cfqg = NULL;
         struct request_queue *q = cfqd->queue;
+        struct backing_dev_info *bdi = &q->backing_dev_info;
+        struct cfq_group *cfqg = NULL;
 
-        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
-         * we need to drop rcu lock and queue_lock before we call alloc.
-         *
-         * Not taking any queue reference here and assuming that queue is
-         * 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);
+        /* avoid lookup for the common case where there's no blkio cgroup */
+        if (blkcg == &blkio_root_cgroup) {
+                cfqg = cfqd->root_group;
+        } else {
+                struct blkio_group *blkg;
 
-        spin_lock_irq(q->queue_lock);
-        rcu_read_lock();
-        css_put(&blkcg->css);
+                blkg = blkg_lookup_create(blkcg, q, BLKIO_POLICY_PROP, false);
+                if (!IS_ERR(blkg))
+                        cfqg = cfqg_of_blkg(blkg);
+        }
 
-        /*
-         * If some other thread already allocated the group while we were
-         * not holding queue lock, free up the group
-         */
-        __cfqg = cfq_find_cfqg(cfqd, blkcg);
+        if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+                unsigned int major, minor;
 
-        if (__cfqg) {
-                kfree(cfqg);
-                return __cfqg;
+                sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+                cfqg->blkg.dev = MKDEV(major, minor);
         }
 
-        if (!cfqg)
-                cfqg = cfqd->root_group;
-
-        cfq_init_add_cfqg_lists(cfqd, cfqg, blkcg);
         return cfqg;
 }
 
@@ -1294,8 +1236,8 @@ static bool cfq_clear_queue(struct request_queue *q)
 }
 
 #else /* GROUP_IOSCHED */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd,
-                                      struct blkio_cgroup *blkcg)
+static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd,
+                                                struct blkio_cgroup *blkcg)
 {
         return cfqd->root_group;
 }
@@ -2887,7 +2829,8 @@ retry:
 
         blkcg = task_blkio_cgroup(current);
 
-        cfqg = cfq_get_cfqg(cfqd, blkcg);
+        cfqg = cfq_lookup_create_cfqg(cfqd, blkcg);
+
         cic = cfq_cic_lookup(cfqd, ioc);
         /* cic always exists here */
         cfqq = cic_to_cfqq(cic, is_sync);
@@ -3694,6 +3637,7 @@ static void cfq_exit_queue(struct elevator_queue *e)
 static int cfq_init_queue(struct request_queue *q)
 {
         struct cfq_data *cfqd;
+        struct blkio_group *blkg __maybe_unused;
         int i;
 
         cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
@@ -3711,7 +3655,10 @@ static int cfq_init_queue(struct request_queue *q)
         rcu_read_lock();
         spin_lock_irq(q->queue_lock);
 
-        cfqd->root_group = cfq_get_cfqg(cfqd, &blkio_root_cgroup);
+        blkg = blkg_lookup_create(&blkio_root_cgroup, q, BLKIO_POLICY_PROP,
+                                  true);
+        if (!IS_ERR(blkg))
+                cfqd->root_group = cfqg_of_blkg(blkg);
 
         spin_unlock_irq(q->queue_lock);
         rcu_read_unlock();
@@ -3897,6 +3844,8 @@ static struct elevator_type iosched_cfq = {
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 static struct blkio_policy_type blkio_policy_cfq = {
         .ops = {
+                .blkio_alloc_group_fn =         cfq_alloc_blkio_group,
+                .blkio_link_group_fn =          cfq_link_blkio_group,
                 .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,
diff --git a/block/cfq.h b/block/cfq.h
index 343b78a61df..398760194e1 100644
--- a/block/cfq.h
+++ b/block/cfq.h
@@ -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;