X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fcfq-iosched.c;h=5ff4f4850e717ddb319423e9678e0e44cd7f265c;hb=c86d1b8ae622e1ea5d20e98bd72fbd7d9dd69016;hp=55d2a21f7f0678cf9404ea801cb77c88dfb0ad83;hpb=dae739ebc4c590630039533a5bbd05865966094f;p=safe%2Fjmp%2Flinux-2.6

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 55d2a21..5ff4f48 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -7,6 +7,7 @@
  *  Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
  */
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
 #include <linux/jiffies.h>
@@ -19,7 +20,7 @@
  * tunables
  */
 /* max queue in one round of service */
-static const int cfq_quantum = 4;
+static const int cfq_quantum = 8;
 static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
 /* maximum backwards seek, in KiB */
 static const int cfq_back_max = 16 * 1024;
@@ -42,19 +43,19 @@ static const int cfq_hist_divisor = 4;
  */
 #define CFQ_MIN_TT		(2)
 
-/*
- * Allow merged cfqqs to perform this amount of seeky I/O before
- * deciding to break the queues up again.
- */
-#define CFQQ_COOP_TOUT		(HZ)
-
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
 #define CFQ_SERVICE_SHIFT       12
 
+#define CFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define CFQQ_CLOSE_THR		(sector_t)(8 * 1024)
+#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
+
 #define RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
 #define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
+#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private3)
 
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
@@ -63,6 +64,9 @@ static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 
+static DEFINE_SPINLOCK(cic_index_lock);
+static DEFINE_IDA(cic_index_ida);
+
 #define CFQ_PRIO_LISTS		IOPRIO_BE_NR
 #define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
 #define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
@@ -80,11 +84,12 @@ struct cfq_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
 	unsigned count;
+	unsigned total_weight;
 	u64 min_vdisktime;
 	struct rb_node *active;
-	unsigned total_weight;
 };
-#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, 0, 0, }
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
+			.count = 0, .min_vdisktime = 0, }
 
 /*
  * Per process-grouping structure
@@ -117,11 +122,12 @@ struct cfq_queue {
 
 	/* time when queue got scheduled in to dispatch first request. */
 	unsigned long dispatch_start;
+	unsigned int allocated_slice;
+	unsigned int slice_dispatch;
 	/* time when first request from queue completed and slice started. */
 	unsigned long slice_start;
 	unsigned long slice_end;
 	long slice_resid;
-	unsigned int slice_dispatch;
 
 	/* pending metadata requests */
 	int meta_pending;
@@ -132,17 +138,15 @@ struct cfq_queue {
 	unsigned short ioprio, org_ioprio;
 	unsigned short ioprio_class, org_ioprio_class;
 
-	unsigned int seek_samples;
-	u64 seek_total;
-	sector_t seek_mean;
-	sector_t last_request_pos;
-	unsigned long seeky_start;
-
 	pid_t pid;
 
+	u32 seek_history;
+	sector_t last_request_pos;
+
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
+	struct cfq_group *orig_cfqg;
 };
 
 /*
@@ -189,6 +193,11 @@ struct cfq_group {
 	unsigned long saved_workload_slice;
 	enum wl_type_t saved_workload;
 	enum wl_prio_t saved_serving_prio;
+	struct blkio_group blkg;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	struct hlist_node cfqd_node;
+	atomic_t ref;
+#endif
 };
 
 /*
@@ -199,8 +208,6 @@ struct cfq_data {
 	/* Root service tree for cfq_groups */
 	struct cfq_rb_root grp_service_tree;
 	struct cfq_group root_group;
-	/* Number of active cfq groups on group service tree */
-	int nr_groups;
 
 	/*
 	 * The priority currently being served
@@ -220,8 +227,8 @@ struct cfq_data {
 
 	unsigned int busy_queues;
 
-	int rq_in_driver[2];
-	int sync_flight;
+	int rq_in_driver;
+	int rq_in_flight[2];
 
 	/*
 	 * queue-depth detection
@@ -265,7 +272,9 @@ struct cfq_data {
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
 	unsigned int cfq_latency;
+	unsigned int cfq_group_isolation;
 
+	unsigned int cic_index;
 	struct list_head cic_list;
 
 	/*
@@ -273,13 +282,18 @@ struct cfq_data {
 	 */
 	struct cfq_queue oom_cfqq;
 
-	unsigned long last_end_sync_rq;
+	unsigned long last_delayed_sync;
+
+	/* List of cfq groups being managed on this device*/
+	struct hlist_head cfqg_list;
+	struct rcu_head rcu;
 };
 
+static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
+
 static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
 					    enum wl_prio_t prio,
-					    enum wl_type_t type,
-					    struct cfq_data *cfqd)
+					    enum wl_type_t type)
 {
 	if (!cfqg)
 		return NULL;
@@ -301,7 +315,9 @@ enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
 	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
 	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
+	CFQ_CFQQ_FLAG_split_coop,	/* shared cfqq will be splitted */
 	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
+	CFQ_CFQQ_FLAG_wait_busy,	/* Waiting for next request */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -328,11 +344,26 @@ CFQ_CFQQ_FNS(prio_changed);
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(split_coop);
 CFQ_CFQQ_FNS(deep);
+CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
+			cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
+			blkg_path(&(cfqq)->cfqg->blkg), ##args);
+
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)				\
+	blk_add_trace_msg((cfqd)->queue, "%s " fmt,			\
+				blkg_path(&(cfqg)->blkg), ##args);      \
+
+#else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0);
+#endif
 #define cfq_log(cfqd, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
 
@@ -378,17 +409,19 @@ static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
 		+ cfqg->service_trees[wl][SYNC_WORKLOAD].count;
 }
 
+static inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
+					struct cfq_group *cfqg)
+{
+	return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
+		+ cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
+}
+
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
 static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 				       struct io_context *, gfp_t);
 static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
 						struct io_context *);
 
-static inline int rq_in_driver(struct cfq_data *cfqd)
-{
-	return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
-}
-
 static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
 					    bool is_sync)
 {
@@ -401,6 +434,24 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic,
 	cic->cfqq[is_sync] = cfqq;
 }
 
+#define CIC_DEAD_KEY	1ul
+#define CIC_DEAD_INDEX_SHIFT	1
+
+static inline void *cfqd_dead_key(struct cfq_data *cfqd)
+{
+	return (void *)(cfqd->cic_index << CIC_DEAD_INDEX_SHIFT | CIC_DEAD_KEY);
+}
+
+static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic)
+{
+	struct cfq_data *cfqd = cic->key;
+
+	if (unlikely((unsigned long) cfqd & CIC_DEAD_KEY))
+		return NULL;
+
+	return cfqd;
+}
+
 /*
  * We regard a request as SYNC, if it's either a read or has the SYNC bit
  * set (in which case it could also be direct WRITE).
@@ -553,6 +604,7 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	}
 	cfqq->slice_start = jiffies;
 	cfqq->slice_end = jiffies + slice;
+	cfqq->allocated_slice = slice;
 	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
 }
 
@@ -803,7 +855,6 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
 	__cfq_group_service_tree_add(st, cfqg);
 	cfqg->on_st = true;
-	cfqd->nr_groups++;
 	st->total_weight += cfqg->weight;
 }
 
@@ -822,17 +873,18 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	if (cfqg->nr_cfqq)
 		return;
 
+	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
 	cfqg->on_st = false;
-	cfqd->nr_groups--;
 	st->total_weight -= cfqg->weight;
 	if (!RB_EMPTY_NODE(&cfqg->rb_node))
 		cfq_rb_erase(&cfqg->rb_node, st);
 	cfqg->saved_workload_slice = 0;
+	blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }
 
 static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
 {
-	unsigned int slice_used, allocated_slice;
+	unsigned int slice_used;
 
 	/*
 	 * Queue got expired before even a single request completed or
@@ -849,9 +901,8 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
 					1);
 	} else {
 		slice_used = jiffies - cfqq->slice_start;
-		allocated_slice = cfqq->slice_end - cfqq->slice_start;
-		if (slice_used > allocated_slice)
-			slice_used = allocated_slice;
+		if (slice_used > cfqq->allocated_slice)
+			slice_used = cfqq->allocated_slice;
 	}
 
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used);
@@ -862,13 +913,19 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl;
+	unsigned int used_sl, charge_sl;
+	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
+			- cfqg->service_tree_idle.count;
+
+	BUG_ON(nr_sync < 0);
+	used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
 
-	used_sl = cfq_cfqq_slice_usage(cfqq);
+	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+		charge_sl = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
 	cfq_rb_erase(&cfqg->rb_node, st);
-	cfqg->vdisktime += cfq_scale_slice(used_sl, cfqg);
+	cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
@@ -879,9 +936,200 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 		cfqg->saved_serving_prio = cfqd->serving_prio;
 	} else
 		cfqg->saved_workload_slice = 0;
+
+	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
+					st->min_vdisktime);
+	blkiocg_update_timeslice_used(&cfqg->blkg, used_sl);
+	blkiocg_set_start_empty_time(&cfqg->blkg);
+}
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
+{
+	if (blkg)
+		return container_of(blkg, struct cfq_group, blkg);
+	return NULL;
+}
+
+void
+cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
+{
+	cfqg_of_blkg(blkg)->weight = weight;
+}
+
+static struct cfq_group *
+cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+{
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+	struct cfq_group *cfqg = NULL;
+	void *key = cfqd;
+	int i, j;
+	struct cfq_rb_root *st;
+	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+	unsigned int major, minor;
+
+	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+	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);
+		goto done;
+	}
+	if (cfqg || !create)
+		goto done;
+
+	cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
+	if (!cfqg)
+		goto done;
+
+	for_each_cfqg_st(cfqg, i, j, st)
+		*st = CFQ_RB_ROOT;
+	RB_CLEAR_NODE(&cfqg->rb_node);
+
+	/*
+	 * Take the initial reference that will be released on destroy
+	 * This can be thought of a joint reference by cgroup and
+	 * elevator which will be dropped by either elevator exit
+	 * or cgroup deletion path depending on who is exiting first.
+	 */
+	atomic_set(&cfqg->ref, 1);
+
+	/* Add group onto cgroup list */
+	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+	blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+					MKDEV(major, minor));
+	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+
+	/* Add group on cfqd list */
+	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+
+done:
+	return cfqg;
 }
 
 /*
+ * Search for the cfq group current task belongs to. If create = 1, then also
+ * create the cfq group if it does not exist. request_queue lock must be held.
+ */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+	struct cgroup *cgroup;
+	struct cfq_group *cfqg = NULL;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(current, blkio_subsys_id);
+	cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
+	if (!cfqg && create)
+		cfqg = &cfqd->root_group;
+	rcu_read_unlock();
+	return cfqg;
+}
+
+static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
+{
+	atomic_inc(&cfqg->ref);
+	return cfqg;
+}
+
+static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
+{
+	/* Currently, all async queues are mapped to root group */
+	if (!cfq_cfqq_sync(cfqq))
+		cfqg = &cfqq->cfqd->root_group;
+
+	cfqq->cfqg = cfqg;
+	/* cfqq reference on cfqg */
+	atomic_inc(&cfqq->cfqg->ref);
+}
+
+static void cfq_put_cfqg(struct cfq_group *cfqg)
+{
+	struct cfq_rb_root *st;
+	int i, j;
+
+	BUG_ON(atomic_read(&cfqg->ref) <= 0);
+	if (!atomic_dec_and_test(&cfqg->ref))
+		return;
+	for_each_cfqg_st(cfqg, i, j, st)
+		BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+	kfree(cfqg);
+}
+
+static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+	/* Something wrong if we are trying to remove same group twice */
+	BUG_ON(hlist_unhashed(&cfqg->cfqd_node));
+
+	hlist_del_init(&cfqg->cfqd_node);
+
+	/*
+	 * Put the reference taken at the time of creation so that when all
+	 * queues are gone, group can be destroyed.
+	 */
+	cfq_put_cfqg(cfqg);
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+{
+	struct hlist_node *pos, *n;
+	struct cfq_group *cfqg;
+
+	hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
+		/*
+		 * If cgroup removal path got to blk_group first and removed
+		 * it from cgroup list, then it will take care of destroying
+		 * cfqg also.
+		 */
+		if (!blkiocg_del_blkio_group(&cfqg->blkg))
+			cfq_destroy_cfqg(cfqd, cfqg);
+	}
+}
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * 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.
+ *
+ * "key" 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.
+ */
+void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+	unsigned long  flags;
+	struct cfq_data *cfqd = key;
+
+	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+	cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
+	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+}
+
+#else /* GROUP_IOSCHED */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+	return &cfqd->root_group;
+}
+
+static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
+{
+	return cfqg;
+}
+
+static inline void
+cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
+	cfqq->cfqg = cfqg;
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd) {}
+static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
+
+#endif /* GROUP_IOSCHED */
+
+/*
  * The cfqd->service_trees holds all pending cfq_queue's that have
  * requests waiting to be processed. It is sorted in the order that
  * we will service the queues.
@@ -895,9 +1143,36 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_rb_root *service_tree;
 	int left;
 	int new_cfqq = 1;
+	int group_changed = 0;
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (!cfqd->cfq_group_isolation
+	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
+	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
+		/* Move this cfq to root group */
+		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
+		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+		cfqq->orig_cfqg = cfqq->cfqg;
+		cfqq->cfqg = &cfqd->root_group;
+		atomic_inc(&cfqd->root_group.ref);
+		group_changed = 1;
+	} else if (!cfqd->cfq_group_isolation
+		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
+		/* cfqq is sequential now needs to go to its original group */
+		BUG_ON(cfqq->cfqg != &cfqd->root_group);
+		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+		cfq_put_cfqg(cfqq->cfqg);
+		cfqq->cfqg = cfqq->orig_cfqg;
+		cfqq->orig_cfqg = NULL;
+		group_changed = 1;
+		cfq_log_cfqq(cfqd, cfqq, "moved to origin group");
+	}
+#endif
 
 	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
-						cfqq_type(cfqq), cfqd);
+						cfqq_type(cfqq));
 	if (cfq_class_idle(cfqq)) {
 		rb_key = CFQ_IDLE_DELAY;
 		parent = rb_last(&service_tree->rb);
@@ -965,7 +1240,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	rb_link_node(&cfqq->rb_node, parent, p);
 	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
 	service_tree->count++;
-	if (add_front || !new_cfqq)
+	if ((add_front || !new_cfqq) && !group_changed)
 		return;
 	cfq_group_service_tree_add(cfqd, cfqq->cfqg);
 }
@@ -1146,7 +1421,12 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
+	blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq),
+						rq_is_sync(rq));
 	cfq_add_rq_rb(rq);
+	blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg,
+			&cfqq->cfqd->serving_group->blkg, rq_data_dir(rq),
+			rq_is_sync(rq));
 }
 
 static struct request *
@@ -1174,9 +1454,9 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver[rq_is_sync(rq)]++;
+	cfqd->rq_in_driver++;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 
 	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
@@ -1184,12 +1464,11 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
-	const int sync = rq_is_sync(rq);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
-	cfqd->rq_in_driver[sync]--;
+	WARN_ON(!cfqd->rq_in_driver);
+	cfqd->rq_in_driver--;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
-						rq_in_driver(cfqd));
+						cfqd->rq_in_driver);
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -1203,6 +1482,8 @@ static void cfq_remove_request(struct request *rq)
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
+	blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq),
+						rq_is_sync(rq));
 	if (rq_is_meta(rq)) {
 		WARN_ON(!cfqq->meta_pending);
 		cfqq->meta_pending--;
@@ -1234,6 +1515,13 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 	}
 }
 
+static void cfq_bio_merged(struct request_queue *q, struct request *req,
+				struct bio *bio)
+{
+	blkiocg_update_io_merged_stats(&(RQ_CFQG(req))->blkg, bio_data_dir(bio),
+					cfq_bio_sync(bio));
+}
+
 static void
 cfq_merged_requests(struct request_queue *q, struct request *rq,
 		    struct request *next)
@@ -1251,6 +1539,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
+	blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(next),
+					rq_is_sync(next));
 }
 
 static int cfq_allow_merge(struct request_queue *q, struct request *rq,
@@ -1278,13 +1568,22 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	return cfqq == RQ_CFQQ(rq);
 }
 
+static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	del_timer(&cfqd->idle_slice_timer);
+	blkiocg_update_idle_time_stats(&cfqq->cfqg->blkg);
+}
+
 static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				   struct cfq_queue *cfqq)
 {
 	if (cfqq) {
-		cfq_log_cfqq(cfqd, cfqq, "set_active");
+		cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
+				cfqd->serving_prio, cfqd->serving_type);
+		blkiocg_update_avg_queue_size_stats(&cfqq->cfqg->blkg);
 		cfqq->slice_start = 0;
 		cfqq->dispatch_start = jiffies;
+		cfqq->allocated_slice = 0;
 		cfqq->slice_end = 0;
 		cfqq->slice_dispatch = 0;
 
@@ -1294,7 +1593,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 		cfq_clear_cfqq_fifo_expire(cfqq);
 		cfq_mark_cfqq_slice_new(cfqq);
 
-		del_timer(&cfqd->idle_slice_timer);
+		cfq_del_timer(cfqd, cfqq);
 	}
 
 	cfqd->active_queue = cfqq;
@@ -1310,9 +1609,19 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
 
 	if (cfq_cfqq_wait_request(cfqq))
-		del_timer(&cfqd->idle_slice_timer);
+		cfq_del_timer(cfqd, cfqq);
 
 	cfq_clear_cfqq_wait_request(cfqq);
+	cfq_clear_cfqq_wait_busy(cfqq);
+
+	/*
+	 * If this cfqq is shared between multiple processes, check to
+	 * make sure that those processes are still issuing I/Os within
+	 * the mean seek distance.  If not, it may be time to break the
+	 * queues apart again.
+	 */
+	if (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq))
+		cfq_mark_cfqq_split_coop(cfqq);
 
 	/*
 	 * store what was left of this slice, if the queue idled/timed out
@@ -1357,7 +1666,7 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 {
 	struct cfq_rb_root *service_tree =
 		service_tree_for(cfqd->serving_group, cfqd->serving_prio,
-					cfqd->serving_type, cfqd);
+					cfqd->serving_type);
 
 	if (!cfqd->rq_queued)
 		return NULL;
@@ -1372,7 +1681,7 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 
 static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 {
-	struct cfq_group *cfqg = &cfqd->root_group;
+	struct cfq_group *cfqg;
 	struct cfq_queue *cfqq;
 	int i, j;
 	struct cfq_rb_root *st;
@@ -1380,6 +1689,10 @@ static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 	if (!cfqd->rq_queued)
 		return NULL;
 
+	cfqg = cfq_get_next_cfqg(cfqd);
+	if (!cfqg)
+		return NULL;
+
 	for_each_cfqg_st(cfqg, i, j, st)
 		if ((cfqq = cfq_rb_first(st)) != NULL)
 			return cfqq;
@@ -1408,18 +1721,10 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 		return cfqd->last_position - blk_rq_pos(rq);
 }
 
-#define CFQQ_SEEK_THR		8 * 1024
-#define CFQQ_SEEKY(cfqq)	((cfqq)->seek_mean > CFQQ_SEEK_THR)
-
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			       struct request *rq)
 {
-	sector_t sdist = cfqq->seek_mean;
-
-	if (!sample_valid(cfqq->seek_samples))
-		sdist = CFQQ_SEEK_THR;
-
-	return cfq_dist_from_last(cfqd, rq) <= sdist;
+	return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1478,12 +1783,20 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 {
 	struct cfq_queue *cfqq;
 
+	if (cfq_class_idle(cur_cfqq))
+		return NULL;
 	if (!cfq_cfqq_sync(cur_cfqq))
 		return NULL;
 	if (CFQQ_SEEKY(cur_cfqq))
 		return NULL;
 
 	/*
+	 * Don't search priority tree if it's the only queue in the group.
+	 */
+	if (cur_cfqq->cfqg->nr_cfqq == 1)
+		return NULL;
+
+	/*
 	 * We should notice if some of the queues are cooperating, eg
 	 * working closely on the same area of the disk. In that case,
 	 * we can group them together and don't waste time idling.
@@ -1492,6 +1805,10 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 	if (!cfqq)
 		return NULL;
 
+	/* If new queue belongs to different cfq_group, don't choose it */
+	if (cur_cfqq->cfqg != cfqq->cfqg)
+		return NULL;
+
 	/*
 	 * It only makes sense to merge sync queues.
 	 */
@@ -1526,14 +1843,19 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		return false;
 
 	/* We do for queues that were marked with idle window flag. */
-	if (cfq_cfqq_idle_window(cfqq))
+	if (cfq_cfqq_idle_window(cfqq) &&
+	   !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag))
 		return true;
 
 	/*
 	 * Otherwise, we do only if they are the last ones
 	 * in their service tree.
 	 */
-	return service_tree->count == 1;
+	if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
+		return 1;
+	cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
+			service_tree->count);
+	return 0;
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -1578,14 +1900,18 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime_mean))
+	    (cfqq->slice_end - jiffies < cic->ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
+				cic->ttime_mean);
 		return;
+	}
 
 	cfq_mark_cfqq_wait_request(cfqq);
 
 	sl = cfqd->cfq_slice_idle;
 
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg);
 	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
 }
 
@@ -1604,8 +1930,9 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight++;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
+	blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq),
+					rq_data_dir(rq), rq_is_sync(rq));
 }
 
 /*
@@ -1688,8 +2015,7 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 }
 
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
-				struct cfq_group *cfqg, enum wl_prio_t prio,
-				bool prio_changed)
+				struct cfq_group *cfqg, enum wl_prio_t prio)
 {
 	struct cfq_queue *queue;
 	int i;
@@ -1697,24 +2023,9 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 	unsigned long lowest_key = 0;
 	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
-	if (prio_changed) {
-		/*
-		 * When priorities switched, we prefer starting
-		 * from SYNC_NOIDLE (first choice), or just SYNC
-		 * over ASYNC
-		 */
-		if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
-			return cur_best;
-		cur_best = SYNC_WORKLOAD;
-		if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
-			return cur_best;
-
-		return ASYNC_WORKLOAD;
-	}
-
-	for (i = 0; i < 3; ++i) {
-		/* otherwise, select the one with lowest rb_key */
-		queue = cfq_rb_first(service_tree_for(cfqg, prio, i, cfqd));
+	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
+		/* select the one with lowest rb_key */
+		queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
 		if (queue &&
 		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
 			lowest_key = queue->rb_key;
@@ -1728,8 +2039,6 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 
 static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
-	enum wl_prio_t previous_prio = cfqd->serving_prio;
-	bool prio_changed;
 	unsigned slice;
 	unsigned count;
 	struct cfq_rb_root *st;
@@ -1757,24 +2066,19 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
 	 * expiration time
 	 */
-	prio_changed = (cfqd->serving_prio != previous_prio);
-	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
-				cfqd);
+	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
 	count = st->count;
 
 	/*
-	 * If priority didn't change, check workload expiration,
-	 * and that we still have other queues ready
+	 * check workload expiration, and that we still have other queues ready
 	 */
-	if (!prio_changed && count &&
-	    !time_after(jiffies, cfqd->workload_expires))
+	if (count && !time_after(jiffies, cfqd->workload_expires))
 		return;
 
 	/* otherwise select new workload type */
 	cfqd->serving_type =
-		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio, prio_changed);
-	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
-				cfqd);
+		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
+	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
 	count = st->count;
 
 	/*
@@ -1788,15 +2092,29 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio],
 		      cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg));
 
-	if (cfqd->serving_type == ASYNC_WORKLOAD)
+	if (cfqd->serving_type == ASYNC_WORKLOAD) {
+		unsigned int tmp;
+
+		/*
+		 * Async queues are currently system wide. Just taking
+		 * proportion of queues with-in same group will lead to higher
+		 * async ratio system wide as generally root group is going
+		 * to have higher weight. A more accurate thing would be to
+		 * calculate system wide asnc/sync ratio.
+		 */
+		tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg);
+		tmp = tmp/cfqd->busy_queues;
+		slice = min_t(unsigned, slice, tmp);
+
 		/* async workload slice is scaled down according to
 		 * the sync/async slice ratio. */
 		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
-	else
+	} else
 		/* sync workload slice is at least 2 * cfq_slice_idle */
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
 	slice = max_t(unsigned, slice, CFQ_MIN_TT);
+	cfq_log(cfqd, "workload slice:%d", slice);
 	cfqd->workload_expires = jiffies + slice;
 	cfqd->noidle_tree_requires_idle = false;
 }
@@ -1825,7 +2143,9 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
 		cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
 		cfqd->serving_type = cfqg->saved_workload;
 		cfqd->serving_prio = cfqg->saved_serving_prio;
-	}
+	} else
+		cfqd->workload_expires = jiffies - 1;
+
 	choose_service_tree(cfqd, cfqg);
 }
 
@@ -1843,13 +2163,35 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 
 	if (!cfqd->rq_queued)
 		return NULL;
+
 	/*
-	 * The active queue has run out of time, expire it and select new.
+	 * We were waiting for group to get backlogged. Expire the queue
 	 */
-	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
+	if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
 		goto expire;
 
 	/*
+	 * The active queue has run out of time, expire it and select new.
+	 */
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
+		/*
+		 * If slice had not expired at the completion of last request
+		 * we might not have turned on wait_busy flag. Don't expire
+		 * the queue yet. Allow the group to get backlogged.
+		 *
+		 * The very fact that we have used the slice, that means we
+		 * have been idling all along on this queue and it should be
+		 * ok to wait for this request to complete.
+		 */
+		if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
+		    && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+			cfqq = NULL;
+			goto keep_queue;
+		} else
+			goto expire;
+	}
+
+	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
 	 */
@@ -1920,16 +2262,32 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq;
 	int dispatched = 0;
 
-	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
+	/* Expire the timeslice of the current active queue first */
+	cfq_slice_expired(cfqd, 0);
+	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
+		__cfq_set_active_queue(cfqd, cfqq);
 		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+	}
 
-	cfq_slice_expired(cfqd, 0);
 	BUG_ON(cfqd->busy_queues);
 
 	cfq_log(cfqd, "forced_dispatch=%d", dispatched);
 	return dispatched;
 }
 
+static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
+	struct cfq_queue *cfqq)
+{
+	/* the queue hasn't finished any request, can't estimate */
+	if (cfq_cfqq_slice_new(cfqq))
+		return 1;
+	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
+		cfqq->slice_end))
+		return 1;
+
+	return 0;
+}
+
 static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned int max_dispatch;
@@ -1937,16 +2295,16 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	/*
 	 * Drain async requests before we start sync IO
 	 */
-	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC])
 		return false;
 
 	/*
 	 * If this is an async queue and we have sync IO in flight, let it wait
 	 */
-	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+	if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq))
 		return false;
 
-	max_dispatch = cfqd->cfq_quantum;
+	max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1);
 	if (cfq_class_idle(cfqq))
 		max_dispatch = 1;
 
@@ -1963,13 +2321,22 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		/*
 		 * We have other queues, don't allow more IO from this one
 		 */
-		if (cfqd->busy_queues > 1)
+		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq))
 			return false;
 
 		/*
 		 * Sole queue user, no limit
 		 */
-		max_dispatch = -1;
+		if (cfqd->busy_queues == 1)
+			max_dispatch = -1;
+		else
+			/*
+			 * Normally we start throttling cfqq when cfq_quantum/2
+			 * requests have been dispatched. But we can drive
+			 * deeper queue depths at the beginning of slice
+			 * subjected to upper limit of cfq_quantum.
+			 * */
+			max_dispatch = cfqd->cfq_quantum;
 	}
 
 	/*
@@ -1978,7 +2345,7 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * based on the last sync IO we serviced
 	 */
 	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
-		unsigned long last_sync = jiffies - cfqd->last_end_sync_rq;
+		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
 		unsigned int depth;
 
 		depth = last_sync / cfqd->cfq_slice[1];
@@ -2076,11 +2443,13 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
  * task holds one reference to the queue, dropped when task exits. each rq
  * in-flight on this queue also holds a reference, dropped when rq is freed.
  *
+ * Each cfq queue took a reference on the parent group. Drop it now.
  * queue lock must be held here.
  */
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
+	struct cfq_group *cfqg, *orig_cfqg;
 
 	BUG_ON(atomic_read(&cfqq->ref) <= 0);
 
@@ -2090,6 +2459,8 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	cfq_log_cfqq(cfqd, cfqq, "put_queue");
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
+	cfqg = cfqq->cfqg;
+	orig_cfqg = cfqq->orig_cfqg;
 
 	if (unlikely(cfqd->active_queue == cfqq)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
@@ -2098,6 +2469,9 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	kmem_cache_free(cfq_pool, cfqq);
+	cfq_put_cfqg(cfqg);
+	if (orig_cfqg)
+		cfq_put_cfqg(orig_cfqg);
 }
 
 /*
@@ -2158,11 +2532,12 @@ static void cfq_cic_free(struct cfq_io_context *cic)
 static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
 {
 	unsigned long flags;
+	unsigned long dead_key = (unsigned long) cic->key;
 
-	BUG_ON(!cic->dead_key);
+	BUG_ON(!(dead_key & CIC_DEAD_KEY));
 
 	spin_lock_irqsave(&ioc->lock, flags);
-	radix_tree_delete(&ioc->radix_root, cic->dead_key);
+	radix_tree_delete(&ioc->radix_root, dead_key >> CIC_DEAD_INDEX_SHIFT);
 	hlist_del_rcu(&cic->cic_list);
 	spin_unlock_irqrestore(&ioc->lock, flags);
 
@@ -2185,15 +2560,10 @@ static void cfq_free_io_context(struct io_context *ioc)
 	__call_for_each_cic(ioc, cic_free_func);
 }
 
-static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static void cfq_put_cooperator(struct cfq_queue *cfqq)
 {
 	struct cfq_queue *__cfqq, *next;
 
-	if (unlikely(cfqq == cfqd->active_queue)) {
-		__cfq_slice_expired(cfqd, cfqq, 0);
-		cfq_schedule_dispatch(cfqd);
-	}
-
 	/*
 	 * If this queue was scheduled to merge with another queue, be
 	 * sure to drop the reference taken on that queue (and others in
@@ -2209,6 +2579,16 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		cfq_put_queue(__cfqq);
 		__cfqq = next;
 	}
+}
+
+static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	if (unlikely(cfqq == cfqd->active_queue)) {
+		__cfq_slice_expired(cfqd, cfqq, 0);
+		cfq_schedule_dispatch(cfqd);
+	}
+
+	cfq_put_cooperator(cfqq);
 
 	cfq_put_queue(cfqq);
 }
@@ -2221,11 +2601,10 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 	list_del_init(&cic->queue_list);
 
 	/*
-	 * Make sure key == NULL is seen for dead queues
+	 * Make sure dead mark is seen for dead queues
 	 */
 	smp_wmb();
-	cic->dead_key = (unsigned long) cic->key;
-	cic->key = NULL;
+	cic->key = cfqd_dead_key(cfqd);
 
 	if (ioc->ioc_data == cic)
 		rcu_assign_pointer(ioc->ioc_data, NULL);
@@ -2244,7 +2623,7 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 static void cfq_exit_single_io_context(struct io_context *ioc,
 				       struct cfq_io_context *cic)
 {
-	struct cfq_data *cfqd = cic->key;
+	struct cfq_data *cfqd = cic_to_cfqd(cic);
 
 	if (cfqd) {
 		struct request_queue *q = cfqd->queue;
@@ -2257,7 +2636,7 @@ static void cfq_exit_single_io_context(struct io_context *ioc,
 		 * race between exiting task and queue
 		 */
 		smp_read_barrier_depends();
-		if (cic->key)
+		if (cic->key == cfqd)
 			__cfq_exit_single_io_context(cfqd, cic);
 
 		spin_unlock_irqrestore(q->queue_lock, flags);
@@ -2337,7 +2716,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 
 static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
 {
-	struct cfq_data *cfqd = cic->key;
+	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 
@@ -2390,15 +2769,40 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfqq->pid = pid;
 }
 
-static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
 {
-	cfqq->cfqg = cfqg;
+	struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);
+	struct cfq_data *cfqd = cic_to_cfqd(cic);
+	unsigned long flags;
+	struct request_queue *q;
+
+	if (unlikely(!cfqd))
+		return;
+
+	q = cfqd->queue;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (sync_cfqq) {
+		/*
+		 * Drop reference to sync queue. A new sync queue will be
+		 * assigned in new group upon arrival of a fresh request.
+		 */
+		cfq_log_cfqq(cfqd, sync_cfqq, "changed cgroup");
+		cic_set_cfqq(cic, NULL, 1);
+		cfq_put_queue(sync_cfqq);
+	}
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+static void cfq_ioc_set_cgroup(struct io_context *ioc)
 {
-	return &cfqd->root_group;
+	call_for_each_cic(ioc, changed_cgroup);
+	ioc->cgroup_changed = 0;
 }
+#endif  /* CONFIG_CFQ_GROUP_IOSCHED */
 
 static struct cfq_queue *
 cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
@@ -2506,12 +2910,13 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc,
 	unsigned long flags;
 
 	WARN_ON(!list_empty(&cic->queue_list));
+	BUG_ON(cic->key != cfqd_dead_key(cfqd));
 
 	spin_lock_irqsave(&ioc->lock, flags);
 
 	BUG_ON(ioc->ioc_data == cic);
 
-	radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
+	radix_tree_delete(&ioc->radix_root, cfqd->cic_index);
 	hlist_del_rcu(&cic->cic_list);
 	spin_unlock_irqrestore(&ioc->lock, flags);
 
@@ -2523,7 +2928,6 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
 {
 	struct cfq_io_context *cic;
 	unsigned long flags;
-	void *k;
 
 	if (unlikely(!ioc))
 		return NULL;
@@ -2540,13 +2944,11 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
 	}
 
 	do {
-		cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
+		cic = radix_tree_lookup(&ioc->radix_root, cfqd->cic_index);
 		rcu_read_unlock();
 		if (!cic)
 			break;
-		/* ->key must be copied to avoid race with cfq_exit_queue() */
-		k = cic->key;
-		if (unlikely(!k)) {
+		if (unlikely(cic->key != cfqd)) {
 			cfq_drop_dead_cic(cfqd, ioc, cic);
 			rcu_read_lock();
 			continue;
@@ -2579,7 +2981,7 @@ static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
 
 		spin_lock_irqsave(&ioc->lock, flags);
 		ret = radix_tree_insert(&ioc->radix_root,
-						(unsigned long) cfqd, cic);
+						cfqd->cic_index, cic);
 		if (!ret)
 			hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
 		spin_unlock_irqrestore(&ioc->lock, flags);
@@ -2632,6 +3034,10 @@ out:
 	if (unlikely(ioc->ioprio_changed))
 		cfq_ioc_set_ioprio(ioc);
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (unlikely(ioc->cgroup_changed))
+		cfq_ioc_set_cgroup(ioc);
+#endif
 	return cic;
 err_free:
 	cfq_cic_free(cic);
@@ -2655,43 +3061,20 @@ static void
 cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct request *rq)
 {
-	sector_t sdist;
-	u64 total;
-
-	if (!cfqq->last_request_pos)
-		sdist = 0;
-	else if (cfqq->last_request_pos < blk_rq_pos(rq))
-		sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
-	else
-		sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	sector_t sdist = 0;
+	sector_t n_sec = blk_rq_sectors(rq);
+	if (cfqq->last_request_pos) {
+		if (cfqq->last_request_pos < blk_rq_pos(rq))
+			sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
+		else
+			sdist = cfqq->last_request_pos - blk_rq_pos(rq);
+	}
 
-	/*
-	 * Don't allow the seek distance to get too large from the
-	 * odd fragment, pagein, etc
-	 */
-	if (cfqq->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
+	cfqq->seek_history <<= 1;
+	if (blk_queue_nonrot(cfqd->queue))
+		cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT);
 	else
-		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*64);
-
-	cfqq->seek_samples = (7*cfqq->seek_samples + 256) / 8;
-	cfqq->seek_total = (7*cfqq->seek_total + (u64)256*sdist) / 8;
-	total = cfqq->seek_total + (cfqq->seek_samples/2);
-	do_div(total, cfqq->seek_samples);
-	cfqq->seek_mean = (sector_t)total;
-
-	/*
-	 * If this cfqq is shared between multiple processes, check to
-	 * make sure that those processes are still issuing I/Os within
-	 * the mean seek distance.  If not, it may be time to break the
-	 * queues apart again.
-	 */
-	if (cfq_cfqq_coop(cfqq)) {
-		if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start)
-			cfqq->seeky_start = jiffies;
-		else if (!CFQQ_SEEKY(cfqq))
-			cfqq->seeky_start = 0;
-	}
+		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
 }
 
 /*
@@ -2716,8 +3099,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		cfq_mark_cfqq_deep(cfqq);
 
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
-	     && CFQQ_SEEKY(cfqq)))
+	    (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -2749,21 +3131,17 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (!cfqq)
 		return false;
 
-	if (cfq_slice_used(cfqq))
-		return true;
-
 	if (cfq_class_idle(new_cfqq))
 		return false;
 
 	if (cfq_class_idle(cfqq))
 		return true;
 
-	/* Allow preemption only if we are idling on sync-noidle tree */
-	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
-	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
-	    new_cfqq->service_tree->count == 2 &&
-	    RB_EMPTY_ROOT(&cfqq->sort_list))
-		return true;
+	/*
+	 * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
+		return false;
 
 	/*
 	 * if the new request is sync, but the currently running queue is
@@ -2772,6 +3150,19 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
 		return true;
 
+	if (new_cfqq->cfqg != cfqq->cfqg)
+		return false;
+
+	if (cfq_slice_used(cfqq))
+		return true;
+
+	/* Allow preemption only if we are idling on sync-noidle tree */
+	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
+	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
+	    new_cfqq->service_tree->count == 2 &&
+	    RB_EMPTY_ROOT(&cfqq->sort_list))
+		return true;
+
 	/*
 	 * So both queues are sync. Let the new request get disk time if
 	 * it's a metadata request and the current queue is doing regular IO.
@@ -2853,10 +3244,14 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (cfq_cfqq_wait_request(cfqq)) {
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
-				del_timer(&cfqd->idle_slice_timer);
+				cfq_del_timer(cfqd, cfqq);
+				cfq_clear_cfqq_wait_request(cfqq);
 				__blk_run_queue(cfqd->queue);
-			} else
+			} else {
+				blkiocg_update_idle_time_stats(
+						&cfqq->cfqg->blkg);
 				cfq_mark_cfqq_must_dispatch(cfqq);
+			}
 		}
 	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
 		/*
@@ -2881,7 +3276,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
-
+	blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg,
+			&cfqd->serving_group->blkg, rq_data_dir(rq),
+			rq_is_sync(rq));
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
 
@@ -2893,14 +3290,14 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
-	if (rq_in_driver(cfqd) > cfqd->hw_tag_est_depth)
-		cfqd->hw_tag_est_depth = rq_in_driver(cfqd);
+	if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth)
+		cfqd->hw_tag_est_depth = cfqd->rq_in_driver;
 
 	if (cfqd->hw_tag == 1)
 		return;
 
 	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
-	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
+	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
 		return;
 
 	/*
@@ -2910,7 +3307,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 	 */
 	if (cfqq && cfq_cfqq_idle_window(cfqq) &&
 	    cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
-	    CFQ_HW_QUEUE_MIN && rq_in_driver(cfqd) < CFQ_HW_QUEUE_MIN)
+	    CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN)
 		return;
 
 	if (cfqd->hw_tag_samples++ < 50)
@@ -2922,6 +3319,35 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 		cfqd->hw_tag = 0;
 }
 
+static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct cfq_io_context *cic = cfqd->active_cic;
+
+	/* If there are other queues in the group, don't wait */
+	if (cfqq->cfqg->nr_cfqq > 1)
+		return false;
+
+	if (cfq_slice_used(cfqq))
+		return true;
+
+	/* if slice left is less than think time, wait busy */
+	if (cic && sample_valid(cic->ttime_samples)
+	    && (cfqq->slice_end - jiffies < cic->ttime_mean))
+		return true;
+
+	/*
+	 * If think times is less than a jiffy than ttime_mean=0 and above
+	 * will not be true. It might happen that slice has not expired yet
+	 * but will expire soon (4-5 ns) during select_queue(). To cover the
+	 * case where think time is less than a jiffy, mark the queue wait
+	 * busy if only 1 jiffy is left in the slice.
+	 */
+	if (cfqq->slice_end - jiffies == 1)
+		return true;
+
+	return false;
+}
+
 static void cfq_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
@@ -2930,21 +3356,24 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	unsigned long now;
 
 	now = jiffies;
-	cfq_log_cfqq(cfqd, cfqq, "complete");
+	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq));
 
 	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver[sync]);
+	WARN_ON(!cfqd->rq_in_driver);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver[sync]--;
+	cfqd->rq_in_driver--;
 	cfqq->dispatched--;
+	blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq),
+			rq_io_start_time_ns(rq), rq_data_dir(rq),
+			rq_is_sync(rq));
 
-	if (cfq_cfqq_sync(cfqq))
-		cfqd->sync_flight--;
+	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
 	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
-		cfqd->last_end_sync_rq = now;
+		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+			cfqd->last_delayed_sync = now;
 	}
 
 	/*
@@ -2958,6 +3387,17 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			cfq_set_prio_slice(cfqd, cfqq);
 			cfq_clear_cfqq_slice_new(cfqq);
 		}
+
+		/*
+		 * Should we wait for next request to come in before we expire
+		 * the queue.
+		 */
+		if (cfq_should_wait_busy(cfqd, cfqq)) {
+			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+			cfq_mark_cfqq_wait_busy(cfqq);
+			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
+		}
+
 		/*
 		 * Idling is not enabled on:
 		 * - expired queues
@@ -2977,12 +3417,13 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			 * only if we processed at least one !rq_noidle request
 			 */
 			if (cfqd->serving_type == SYNC_WORKLOAD
-			    || cfqd->noidle_tree_requires_idle)
+			    || cfqd->noidle_tree_requires_idle
+			    || cfqq->cfqg->nr_cfqq == 1)
 				cfq_arm_slice_timer(cfqd);
 		}
 	}
 
-	if (!rq_in_driver(cfqd))
+	if (!cfqd->rq_in_driver)
 		cfq_schedule_dispatch(cfqd);
 }
 
@@ -3066,6 +3507,10 @@ static void cfq_put_request(struct request *rq)
 		rq->elevator_private = NULL;
 		rq->elevator_private2 = NULL;
 
+		/* Put down rq reference on cfqg */
+		cfq_put_cfqg(RQ_CFQG(rq));
+		rq->elevator_private3 = NULL;
+
 		cfq_put_queue(cfqq);
 	}
 }
@@ -3081,14 +3526,6 @@ cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
 	return cic_to_cfqq(cic, 1);
 }
 
-static int should_split_cfqq(struct cfq_queue *cfqq)
-{
-	if (cfqq->seeky_start &&
-	    time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT))
-		return 1;
-	return 0;
-}
-
 /*
  * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
  * was the last process referring to said cfqq.
@@ -3097,13 +3534,16 @@ static struct cfq_queue *
 split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
 {
 	if (cfqq_process_refs(cfqq) == 1) {
-		cfqq->seeky_start = 0;
 		cfqq->pid = current->pid;
 		cfq_clear_cfqq_coop(cfqq);
+		cfq_clear_cfqq_split_coop(cfqq);
 		return cfqq;
 	}
 
 	cic_set_cfqq(cic, NULL, 1);
+
+	cfq_put_cooperator(cfqq);
+
 	cfq_put_queue(cfqq);
 	return NULL;
 }
@@ -3138,7 +3578,7 @@ new_queue:
 		/*
 		 * If the queue was seeky for too long, break it apart.
 		 */
-		if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
+		if (cfq_cfqq_coop(cfqq) && cfq_cfqq_split_coop(cfqq)) {
 			cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
 			cfqq = split_cfqq(cic, cfqq);
 			if (!cfqq)
@@ -3162,6 +3602,7 @@ new_queue:
 
 	rq->elevator_private = cic;
 	rq->elevator_private2 = cfqq;
+	rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
 	return 0;
 
 queue_fail:
@@ -3262,6 +3703,11 @@ static void cfq_put_async_queues(struct cfq_data *cfqd)
 		cfq_put_queue(cfqd->async_idle_cfqq);
 }
 
+static void cfq_cfqd_free(struct rcu_head *head)
+{
+	kfree(container_of(head, struct cfq_data, rcu));
+}
+
 static void cfq_exit_queue(struct elevator_queue *e)
 {
 	struct cfq_data *cfqd = e->elevator_data;
@@ -3283,12 +3729,37 @@ static void cfq_exit_queue(struct elevator_queue *e)
 	}
 
 	cfq_put_async_queues(cfqd);
+	cfq_release_cfq_groups(cfqd);
+	blkiocg_del_blkio_group(&cfqd->root_group.blkg);
 
 	spin_unlock_irq(q->queue_lock);
 
 	cfq_shutdown_timer_wq(cfqd);
 
-	kfree(cfqd);
+	spin_lock(&cic_index_lock);
+	ida_remove(&cic_index_ida, cfqd->cic_index);
+	spin_unlock(&cic_index_lock);
+
+	/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
+	call_rcu(&cfqd->rcu, cfq_cfqd_free);
+}
+
+static int cfq_alloc_cic_index(void)
+{
+	int index, error;
+
+	do {
+		if (!ida_pre_get(&cic_index_ida, GFP_KERNEL))
+			return -ENOMEM;
+
+		spin_lock(&cic_index_lock);
+		error = ida_get_new(&cic_index_ida, &index);
+		spin_unlock(&cic_index_lock);
+		if (error && error != -EAGAIN)
+			return error;
+	} while (error);
+
+	return index;
 }
 
 static void *cfq_init_queue(struct request_queue *q)
@@ -3298,10 +3769,16 @@ static void *cfq_init_queue(struct request_queue *q)
 	struct cfq_group *cfqg;
 	struct cfq_rb_root *st;
 
+	i = cfq_alloc_cic_index();
+	if (i < 0)
+		return NULL;
+
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!cfqd)
 		return NULL;
 
+	cfqd->cic_index = i;
+
 	/* Init root service tree */
 	cfqd->grp_service_tree = CFQ_RB_ROOT;
 
@@ -3314,6 +3791,17 @@ static void *cfq_init_queue(struct request_queue *q)
 	/* Give preference to root group over other groups */
 	cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	/*
+	 * Take a reference to root group which we never drop. This is just
+	 * to make sure that cfq_put_cfqg() does not try to kfree root group
+	 */
+	atomic_set(&cfqg->ref, 1);
+	rcu_read_lock();
+	blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
+					0);
+	rcu_read_unlock();
+#endif
 	/*
 	 * Not strictly needed (since RB_ROOT just clears the node and we
 	 * zeroed cfqd on alloc), but better be safe in case someone decides
@@ -3351,8 +3839,13 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
 	cfqd->cfq_slice_idle = cfq_slice_idle;
 	cfqd->cfq_latency = 1;
+	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
-	cfqd->last_end_sync_rq = jiffies;
+	/*
+	 * we optimistically start assuming sync ops weren't delayed in last
+	 * second, in order to have larger depth for async operations.
+	 */
+	cfqd->last_delayed_sync = jiffies - HZ;
 	return cfqd;
 }
 
@@ -3421,6 +3914,7 @@ SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
 SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
 SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
 SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
+SHOW_FUNCTION(cfq_group_isolation_show, cfqd->cfq_group_isolation, 0);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
@@ -3453,6 +3947,7 @@ STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
 		UINT_MAX, 0);
 STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
+STORE_FUNCTION(cfq_group_isolation_store, &cfqd->cfq_group_isolation, 0, 1, 0);
 #undef STORE_FUNCTION
 
 #define CFQ_ATTR(name) \
@@ -3469,6 +3964,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
 	CFQ_ATTR(low_latency),
+	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
 };
 
@@ -3478,6 +3974,7 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
 		.elevator_allow_merge_fn =	cfq_allow_merge,
+		.elevator_bio_merged_fn =	cfq_bio_merged,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,
 		.elevator_activate_req_fn =	cfq_activate_request,
@@ -3498,6 +3995,17 @@ static struct elevator_type iosched_cfq = {
 	.elevator_owner =	THIS_MODULE,
 };
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static struct blkio_policy_type blkio_policy_cfq = {
+	.ops = {
+		.blkio_unlink_group_fn =	cfq_unlink_blkio_group,
+		.blkio_update_group_weight_fn =	cfq_update_blkio_group_weight,
+	},
+};
+#else
+static struct blkio_policy_type blkio_policy_cfq;
+#endif
+
 static int __init cfq_init(void)
 {
 	/*
@@ -3512,6 +4020,7 @@ static int __init cfq_init(void)
 		return -ENOMEM;
 
 	elv_register(&iosched_cfq);
+	blkio_policy_register(&blkio_policy_cfq);
 
 	return 0;
 }
@@ -3519,6 +4028,7 @@ static int __init cfq_init(void)
 static void __exit cfq_exit(void)
 {
 	DECLARE_COMPLETION_ONSTACK(all_gone);
+	blkio_policy_unregister(&blkio_policy_cfq);
 	elv_unregister(&iosched_cfq);
 	ioc_gone = &all_gone;
 	/* ioc_gone's update must be visible before reading ioc_count */
@@ -3530,6 +4040,7 @@ static void __exit cfq_exit(void)
 	 */
 	if (elv_ioc_count_read(cfq_ioc_count))
 		wait_for_completion(&all_gone);
+	ida_destroy(&cic_index_ida);
 	cfq_slab_kill();
 }