X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fcfq-iosched.c;h=71446497d7b6ee544058189559f967cac3556166;hb=464191c65b85a8ec68a6e1a6293af625287c807e;hp=7f909d2f4886d36aaea83836a07a9d255d3e7de5;hpb=07416d29bcf608257f1e5280642dcbe0021518a3;p=safe%2Fjmp%2Flinux-2.6

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7f909d2..7144649 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -9,8 +9,10 @@
 #include <linux/module.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
+#include <linux/jiffies.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
+#include <linux/blktrace_api.h>
 
 /*
  * tunables
@@ -26,6 +28,8 @@ static const int cfq_slice_sync = HZ / 10;
 static int cfq_slice_async = HZ / 25;
 static const int cfq_slice_async_rq = 2;
 static int cfq_slice_idle = HZ / 125;
+static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
+static const int cfq_hist_divisor = 4;
 
 /*
  * offset from end of service tree
@@ -37,25 +41,30 @@ static int cfq_slice_idle = HZ / 125;
  */
 #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 RQ_CIC(rq)		\
 	((struct cfq_io_context *) (rq)->elevator_private)
-#define RQ_CFQQ(rq)		((rq)->elevator_private2)
+#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)
 
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
 
-static DEFINE_PER_CPU(unsigned long, ioc_count);
+static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
 static struct completion *ioc_gone;
+static DEFINE_SPINLOCK(ioc_gone_lock);
 
 #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)
 
-#define ASYNC			(0)
-#define SYNC			(1)
-
 #define sample_valid(samples)	((samples) > 80)
 
 /*
@@ -67,8 +76,83 @@ static struct completion *ioc_gone;
 struct cfq_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
+	unsigned count;
+};
+#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, 0, }
+
+/*
+ * Per process-grouping structure
+ */
+struct cfq_queue {
+	/* reference count */
+	atomic_t ref;
+	/* various state flags, see below */
+	unsigned int flags;
+	/* parent cfq_data */
+	struct cfq_data *cfqd;
+	/* service_tree member */
+	struct rb_node rb_node;
+	/* service_tree key */
+	unsigned long rb_key;
+	/* prio tree member */
+	struct rb_node p_node;
+	/* prio tree root we belong to, if any */
+	struct rb_root *p_root;
+	/* sorted list of pending requests */
+	struct rb_root sort_list;
+	/* if fifo isn't expired, next request to serve */
+	struct request *next_rq;
+	/* requests queued in sort_list */
+	int queued[2];
+	/* currently allocated requests */
+	int allocated[2];
+	/* fifo list of requests in sort_list */
+	struct list_head fifo;
+
+	unsigned long slice_end;
+	long slice_resid;
+	unsigned int slice_dispatch;
+
+	/* pending metadata requests */
+	int meta_pending;
+	/* number of requests that are on the dispatch list or inside driver */
+	int dispatched;
+
+	/* io prio of this group */
+	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;
+
+	struct cfq_rb_root *service_tree;
+	struct cfq_queue *new_cfqq;
+};
+
+/*
+ * First index in the service_trees.
+ * IDLE is handled separately, so it has negative index
+ */
+enum wl_prio_t {
+	IDLE_WORKLOAD = -1,
+	BE_WORKLOAD = 0,
+	RT_WORKLOAD = 1
 };
-#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, }
+
+/*
+ * Second index in the service_trees.
+ */
+enum wl_type_t {
+	ASYNC_WORKLOAD = 0,
+	SYNC_NOIDLE_WORKLOAD = 1,
+	SYNC_WORKLOAD = 2
+};
+
 
 /*
  * Per block device queue structure
@@ -77,14 +161,45 @@ struct cfq_data {
 	struct request_queue *queue;
 
 	/*
-	 * rr list of queues with requests and the count of them
+	 * rr lists of queues with requests, onle rr for each priority class.
+	 * Counts are embedded in the cfq_rb_root
+	 */
+	struct cfq_rb_root service_trees[2][3];
+	struct cfq_rb_root service_tree_idle;
+	/*
+	 * The priority currently being served
+	 */
+	enum wl_prio_t serving_prio;
+	enum wl_type_t serving_type;
+	unsigned long workload_expires;
+	bool noidle_tree_requires_idle;
+
+	/*
+	 * Each priority tree is sorted by next_request position.  These
+	 * trees are used when determining if two or more queues are
+	 * interleaving requests (see cfq_close_cooperator).
 	 */
-	struct cfq_rb_root service_tree;
+	struct rb_root prio_trees[CFQ_PRIO_LISTS];
+
 	unsigned int busy_queues;
+	unsigned int busy_queues_avg[2];
 
-	int rq_in_driver;
+	int rq_in_driver[2];
 	int sync_flight;
+
+	/*
+	 * queue-depth detection
+	 */
+	int rq_queued;
 	int hw_tag;
+	/*
+	 * hw_tag can be
+	 * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection)
+	 *  1 => NCQ is present (hw_tag_est_depth is the estimated max depth)
+	 *  0 => no NCQ
+	 */
+	int hw_tag_est_depth;
+	unsigned int hw_tag_samples;
 
 	/*
 	 * idle window management
@@ -102,7 +217,6 @@ struct cfq_data {
 	struct cfq_queue *async_idle_cfqq;
 
 	sector_t last_position;
-	unsigned long last_end_request;
 
 	/*
 	 * tunables, see top of file
@@ -114,61 +228,40 @@ struct cfq_data {
 	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
+	unsigned int cfq_latency;
 
 	struct list_head cic_list;
-};
-
-/*
- * Per process-grouping structure
- */
-struct cfq_queue {
-	/* reference count */
-	atomic_t ref;
-	/* parent cfq_data */
-	struct cfq_data *cfqd;
-	/* service_tree member */
-	struct rb_node rb_node;
-	/* service_tree key */
-	unsigned long rb_key;
-	/* sorted list of pending requests */
-	struct rb_root sort_list;
-	/* if fifo isn't expired, next request to serve */
-	struct request *next_rq;
-	/* requests queued in sort_list */
-	int queued[2];
-	/* currently allocated requests */
-	int allocated[2];
-	/* pending metadata requests */
-	int meta_pending;
-	/* fifo list of requests in sort_list */
-	struct list_head fifo;
 
-	unsigned long slice_end;
-	long slice_resid;
+	/*
+	 * Fallback dummy cfqq for extreme OOM conditions
+	 */
+	struct cfq_queue oom_cfqq;
 
-	/* number of requests that are on the dispatch list or inside driver */
-	int dispatched;
+	unsigned long last_end_sync_rq;
+};
 
-	/* io prio of this group */
-	unsigned short ioprio, org_ioprio;
-	unsigned short ioprio_class, org_ioprio_class;
+static struct cfq_rb_root *service_tree_for(enum wl_prio_t prio,
+					    enum wl_type_t type,
+					    struct cfq_data *cfqd)
+{
+	if (prio == IDLE_WORKLOAD)
+		return &cfqd->service_tree_idle;
 
-	/* various state flags, see below */
-	unsigned int flags;
-};
+	return &cfqd->service_trees[prio][type];
+}
 
 enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
 	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
-	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
+	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
 	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
-	CFQ_CFQQ_FLAG_must_dispatch,	/* must dispatch, even if expired */
 	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
 	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
 	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
-	CFQ_CFQQ_FLAG_queue_new,	/* queue never been serviced */
 	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_deep,		/* sync cfqq experienced large depth */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -187,45 +280,81 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
 
 CFQ_CFQQ_FNS(on_rr);
 CFQ_CFQQ_FNS(wait_request);
-CFQ_CFQQ_FNS(must_alloc);
-CFQ_CFQQ_FNS(must_alloc_slice);
 CFQ_CFQQ_FNS(must_dispatch);
+CFQ_CFQQ_FNS(must_alloc_slice);
 CFQ_CFQQ_FNS(fifo_expire);
 CFQ_CFQQ_FNS(idle_window);
 CFQ_CFQQ_FNS(prio_changed);
-CFQ_CFQQ_FNS(queue_new);
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
+CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(deep);
 #undef CFQ_CFQQ_FNS
 
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log(cfqd, fmt, args...)	\
+	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
+
+static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
+{
+	if (cfq_class_idle(cfqq))
+		return IDLE_WORKLOAD;
+	if (cfq_class_rt(cfqq))
+		return RT_WORKLOAD;
+	return BE_WORKLOAD;
+}
+
+
+static enum wl_type_t cfqq_type(struct cfq_queue *cfqq)
+{
+	if (!cfq_cfqq_sync(cfqq))
+		return ASYNC_WORKLOAD;
+	if (!cfq_cfqq_idle_window(cfqq))
+		return SYNC_NOIDLE_WORKLOAD;
+	return SYNC_WORKLOAD;
+}
+
+static inline int cfq_busy_queues_wl(enum wl_prio_t wl, struct cfq_data *cfqd)
+{
+	if (wl == IDLE_WORKLOAD)
+		return cfqd->service_tree_idle.count;
+
+	return cfqd->service_trees[wl][ASYNC_WORKLOAD].count
+		+ cfqd->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count
+		+ cfqd->service_trees[wl][SYNC_WORKLOAD].count;
+}
+
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
-static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
+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,
-					    int is_sync)
+					    bool is_sync)
 {
-	return cic->cfqq[!!is_sync];
+	return cic->cfqq[is_sync];
 }
 
 static inline void cic_set_cfqq(struct cfq_io_context *cic,
-				struct cfq_queue *cfqq, int is_sync)
+				struct cfq_queue *cfqq, bool is_sync)
 {
-	cic->cfqq[!!is_sync] = cfqq;
+	cic->cfqq[is_sync] = cfqq;
 }
 
 /*
  * 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).
  */
-static inline int cfq_bio_sync(struct bio *bio)
+static inline bool cfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || bio_sync(bio))
-		return 1;
-
-	return 0;
+	return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO);
 }
 
 /*
@@ -234,8 +363,10 @@ static inline int cfq_bio_sync(struct bio *bio)
  */
 static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 {
-	if (cfqd->busy_queues)
-		kblockd_schedule_work(&cfqd->unplug_work);
+	if (cfqd->busy_queues) {
+		cfq_log(cfqd, "schedule dispatch");
+		kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
+	}
 }
 
 static int cfq_queue_empty(struct request_queue *q)
@@ -250,7 +381,7 @@ static int cfq_queue_empty(struct request_queue *q)
  * if a queue is marked sync and has sync io queued. A sync queue with async
  * io only, should not get full sync slice length.
  */
-static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync,
+static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
 				 unsigned short prio)
 {
 	const int base_slice = cfqd->cfq_slice[sync];
@@ -266,10 +397,50 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
 }
 
+/*
+ * get averaged number of queues of RT/BE priority.
+ * average is updated, with a formula that gives more weight to higher numbers,
+ * to quickly follows sudden increases and decrease slowly
+ */
+
+static inline unsigned cfq_get_avg_queues(struct cfq_data *cfqd, bool rt)
+{
+	unsigned min_q, max_q;
+	unsigned mult  = cfq_hist_divisor - 1;
+	unsigned round = cfq_hist_divisor / 2;
+	unsigned busy = cfq_busy_queues_wl(rt, cfqd);
+
+	min_q = min(cfqd->busy_queues_avg[rt], busy);
+	max_q = max(cfqd->busy_queues_avg[rt], busy);
+	cfqd->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
+		cfq_hist_divisor;
+	return cfqd->busy_queues_avg[rt];
+}
+
 static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
+	if (cfqd->cfq_latency) {
+		/* interested queues (we consider only the ones with the same
+		 * priority class) */
+		unsigned iq = cfq_get_avg_queues(cfqd, cfq_class_rt(cfqq));
+		unsigned sync_slice = cfqd->cfq_slice[1];
+		unsigned expect_latency = sync_slice * iq;
+		if (expect_latency > cfq_target_latency) {
+			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
+			/* scale low_slice according to IO priority
+			 * and sync vs async */
+			unsigned low_slice =
+				min(slice, base_low_slice * slice / sync_slice);
+			/* the adapted slice value is scaled to fit all iqs
+			 * into the target latency */
+			slice = max(slice * cfq_target_latency / expect_latency,
+				    low_slice);
+		}
+	}
+	cfqq->slice_end = jiffies + slice;
+	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
 }
 
 /*
@@ -277,7 +448,7 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  * isn't valid until the first request from the dispatch is activated
  * and the slice time set.
  */
-static inline int cfq_slice_used(struct cfq_queue *cfqq)
+static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
 		return 0;
@@ -293,9 +464,9 @@ static inline int cfq_slice_used(struct cfq_queue *cfqq)
  * behind the head is penalized and only allowed to a certain extent.
  */
 static struct request *
-cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
+cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last)
 {
-	sector_t last, s1, s2, d1 = 0, d2 = 0;
+	sector_t s1, s2, d1 = 0, d2 = 0;
 	unsigned long back_max;
 #define CFQ_RQ1_WRAP	0x01 /* request 1 wraps */
 #define CFQ_RQ2_WRAP	0x02 /* request 2 wraps */
@@ -315,10 +486,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
 	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
 		return rq2;
 
-	s1 = rq1->sector;
-	s2 = rq2->sector;
-
-	last = cfqd->last_position;
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
 
 	/*
 	 * by definition, 1KiB is 2 sectors
@@ -396,13 +565,18 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
 	return NULL;
 }
 
+static void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+
 static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
 {
 	if (root->left == n)
 		root->left = NULL;
-
-	rb_erase(n, &root->rb);
-	RB_CLEAR_NODE(n);
+	rb_erase_init(n, &root->rb);
+	--root->count;
 }
 
 /*
@@ -429,7 +603,7 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			next = rb_entry_rq(rbnext);
 	}
 
-	return cfq_choose_req(cfqd, next, prev);
+	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
 static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
@@ -443,46 +617,60 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
 }
 
 /*
- * The cfqd->service_tree holds all pending cfq_queue's that have
+ * 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.
  */
-static void cfq_service_tree_add(struct cfq_data *cfqd,
-				    struct cfq_queue *cfqq, int add_front)
+static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+				 bool add_front)
 {
 	struct rb_node **p, *parent;
 	struct cfq_queue *__cfqq;
 	unsigned long rb_key;
+	struct cfq_rb_root *service_tree;
 	int left;
 
+	service_tree = service_tree_for(cfqq_prio(cfqq), cfqq_type(cfqq), cfqd);
 	if (cfq_class_idle(cfqq)) {
 		rb_key = CFQ_IDLE_DELAY;
-		parent = rb_last(&cfqd->service_tree.rb);
+		parent = rb_last(&service_tree->rb);
 		if (parent && parent != &cfqq->rb_node) {
 			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 			rb_key += __cfqq->rb_key;
 		} else
 			rb_key += jiffies;
 	} else if (!add_front) {
+		/*
+		 * Get our rb key offset. Subtract any residual slice
+		 * value carried from last service. A negative resid
+		 * count indicates slice overrun, and this should position
+		 * the next service time further away in the tree.
+		 */
 		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
-		rb_key += cfqq->slice_resid;
+		rb_key -= cfqq->slice_resid;
 		cfqq->slice_resid = 0;
-	} else
-		rb_key = 0;
+	} else {
+		rb_key = -HZ;
+		__cfqq = cfq_rb_first(service_tree);
+		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+	}
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
 		/*
 		 * same position, nothing more to do
 		 */
-		if (rb_key == cfqq->rb_key)
+		if (rb_key == cfqq->rb_key &&
+		    cfqq->service_tree == service_tree)
 			return;
 
-		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
+		cfqq->service_tree = NULL;
 	}
 
 	left = 1;
 	parent = NULL;
-	p = &cfqd->service_tree.rb.rb_node;
+	cfqq->service_tree = service_tree;
+	p = &service_tree->rb.rb_node;
 	while (*p) {
 		struct rb_node **n;
 
@@ -490,35 +678,86 @@ static void cfq_service_tree_add(struct cfq_data *cfqd,
 		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 
 		/*
-		 * sort RT queues first, we always want to give
-		 * preference to them. IDLE queues goes to the back.
-		 * after that, sort on the next service time.
+		 * sort by key, that represents service time.
 		 */
-		if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq))
-			n = &(*p)->rb_left;
-		else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq))
-			n = &(*p)->rb_right;
-		else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq))
-			n = &(*p)->rb_left;
-		else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq))
-			n = &(*p)->rb_right;
-		else if (rb_key < __cfqq->rb_key)
+		if (time_before(rb_key, __cfqq->rb_key))
 			n = &(*p)->rb_left;
-		else
+		else {
 			n = &(*p)->rb_right;
-
-		if (n == &(*p)->rb_right)
 			left = 0;
+		}
 
 		p = n;
 	}
 
 	if (left)
-		cfqd->service_tree.left = &cfqq->rb_node;
+		service_tree->left = &cfqq->rb_node;
 
 	cfqq->rb_key = rb_key;
 	rb_link_node(&cfqq->rb_node, parent, p);
-	rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
+	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
+	service_tree->count++;
+}
+
+static struct cfq_queue *
+cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct cfq_queue *cfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		cfqq = rb_entry(parent, struct cfq_queue, p_node);
+
+		/*
+		 * Sort strictly based on sector.  Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(cfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(cfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		cfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+	return cfqq;
+}
+
+static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct rb_node **p, *parent;
+	struct cfq_queue *__cfqq;
+
+	if (cfqq->p_root) {
+		rb_erase(&cfqq->p_node, cfqq->p_root);
+		cfqq->p_root = NULL;
+	}
+
+	if (cfq_class_idle(cfqq))
+		return;
+	if (!cfqq->next_rq)
+		return;
+
+	cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
+	__cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root,
+				      blk_rq_pos(cfqq->next_rq), &parent, &p);
+	if (!__cfqq) {
+		rb_link_node(&cfqq->p_node, parent, p);
+		rb_insert_color(&cfqq->p_node, cfqq->p_root);
+	} else
+		cfqq->p_root = NULL;
 }
 
 /*
@@ -529,8 +768,10 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	/*
 	 * Resorting requires the cfqq to be on the RR list already.
 	 */
-	if (cfq_cfqq_on_rr(cfqq))
+	if (cfq_cfqq_on_rr(cfqq)) {
 		cfq_service_tree_add(cfqd, cfqq, 0);
+		cfq_prio_tree_add(cfqd, cfqq);
+	}
 }
 
 /*
@@ -539,6 +780,7 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
@@ -552,11 +794,18 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  */
 static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
 	BUG_ON(!cfq_cfqq_on_rr(cfqq));
 	cfq_clear_cfqq_on_rr(cfqq);
 
-	if (!RB_EMPTY_NODE(&cfqq->rb_node))
-		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
+	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
+		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
+		cfqq->service_tree = NULL;
+	}
+	if (cfqq->p_root) {
+		rb_erase(&cfqq->p_node, cfqq->p_root);
+		cfqq->p_root = NULL;
+	}
 
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
@@ -584,7 +833,7 @@ static void cfq_add_rq_rb(struct request *rq)
 {
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 	struct cfq_data *cfqd = cfqq->cfqd;
-	struct request *__alias;
+	struct request *__alias, *prev;
 
 	cfqq->queued[rq_is_sync(rq)]++;
 
@@ -601,7 +850,15 @@ static void cfq_add_rq_rb(struct request *rq)
 	/*
 	 * check if this request is a better next-serve candidate
 	 */
-	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
+	prev = cfqq->next_rq;
+	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position);
+
+	/*
+	 * adjust priority tree position, if ->next_rq changes
+	 */
+	if (prev != cfqq->next_rq)
+		cfq_prio_tree_add(cfqd, cfqq);
+
 	BUG_ON(!cfqq->next_rq);
 }
 
@@ -637,26 +894,22 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver++;
-
-	/*
-	 * If the depth is larger 1, it really could be queueing. But lets
-	 * make the mark a little higher - idling could still be good for
-	 * low queueing, and a low queueing number could also just indicate
-	 * a SCSI mid layer like behaviour where limit+1 is often seen.
-	 */
-	if (!cfqd->hw_tag && cfqd->rq_in_driver > 4)
-		cfqd->hw_tag = 1;
+	cfqd->rq_in_driver[rq_is_sync(rq)]++;
+	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
+						rq_in_driver(cfqd));
 
-	cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors;
+	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(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);
-	cfqd->rq_in_driver--;
+	WARN_ON(!cfqd->rq_in_driver[sync]);
+	cfqd->rq_in_driver[sync]--;
+	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
+						rq_in_driver(cfqd));
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -669,6 +922,7 @@ static void cfq_remove_request(struct request *rq)
 	list_del_init(&rq->queuelist);
 	cfq_del_rq_rb(rq);
 
+	cfqq->cfqd->rq_queued--;
 	if (rq_is_meta(rq)) {
 		WARN_ON(!cfqq->meta_pending);
 		cfqq->meta_pending--;
@@ -704,13 +958,18 @@ static void
 cfq_merged_requests(struct request_queue *q, struct request *rq,
 		    struct request *next)
 {
+	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 	/*
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->start_time, rq->start_time))
+	    time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
 		list_move(&rq->queuelist, &next->queuelist);
+		rq_set_fifo_time(rq, rq_fifo_time(next));
+	}
 
+	if (cfqq->next_rq == next)
+		cfqq->next_rq = rq;
 	cfq_remove_request(next);
 }
 
@@ -725,7 +984,7 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	 * Disallow merge of a sync bio into an async request.
 	 */
 	if (cfq_bio_sync(bio) && !rq_is_sync(rq))
-		return 0;
+		return false;
 
 	/*
 	 * Lookup the cfqq that this bio will be queued with. Allow
@@ -733,24 +992,27 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	 */
 	cic = cfq_cic_lookup(cfqd, current->io_context);
 	if (!cic)
-		return 0;
+		return false;
 
 	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
-	if (cfqq == RQ_CFQQ(rq))
-		return 1;
-
-	return 0;
+	return cfqq == RQ_CFQQ(rq);
 }
 
 static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				   struct cfq_queue *cfqq)
 {
 	if (cfqq) {
+		cfq_log_cfqq(cfqd, cfqq, "set_active");
 		cfqq->slice_end = 0;
+		cfqq->slice_dispatch = 0;
+
+		cfq_clear_cfqq_wait_request(cfqq);
+		cfq_clear_cfqq_must_dispatch(cfqq);
 		cfq_clear_cfqq_must_alloc_slice(cfqq);
 		cfq_clear_cfqq_fifo_expire(cfqq);
 		cfq_mark_cfqq_slice_new(cfqq);
-		cfq_clear_cfqq_queue_new(cfqq);
+
+		del_timer(&cfqd->idle_slice_timer);
 	}
 
 	cfqd->active_queue = cfqq;
@@ -761,19 +1023,22 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
  */
 static void
 __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-		    int timed_out)
+		    bool timed_out)
 {
+	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
+
 	if (cfq_cfqq_wait_request(cfqq))
 		del_timer(&cfqd->idle_slice_timer);
 
-	cfq_clear_cfqq_must_dispatch(cfqq);
 	cfq_clear_cfqq_wait_request(cfqq);
 
 	/*
 	 * store what was left of this slice, if the queue idled/timed out
 	 */
-	if (timed_out && !cfq_cfqq_slice_new(cfqq))
+	if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
 		cfqq->slice_resid = cfqq->slice_end - jiffies;
+		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+	}
 
 	cfq_resort_rr_list(cfqd, cfqq);
 
@@ -786,7 +1051,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	}
 }
 
-static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
+static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 
@@ -800,20 +1065,23 @@ static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
  */
 static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 {
-	if (RB_EMPTY_ROOT(&cfqd->service_tree.rb))
-		return NULL;
+	struct cfq_rb_root *service_tree =
+		service_tree_for(cfqd->serving_prio, cfqd->serving_type, cfqd);
 
-	return cfq_rb_first(&cfqd->service_tree);
+	if (RB_EMPTY_ROOT(&service_tree->rb))
+		return NULL;
+	return cfq_rb_first(service_tree);
 }
 
 /*
  * Get and set a new active queue for service.
  */
-static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
+static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
+					      struct cfq_queue *cfqq)
 {
-	struct cfq_queue *cfqq;
+	if (!cfqq)
+		cfqq = cfq_get_next_queue(cfqd);
 
-	cfqq = cfq_get_next_queue(cfqd);
 	__cfq_set_active_queue(cfqd, cfqq);
 	return cfqq;
 }
@@ -821,34 +1089,142 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
 static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 					  struct request *rq)
 {
-	if (rq->sector >= cfqd->last_position)
-		return rq->sector - cfqd->last_position;
+	if (blk_rq_pos(rq) >= cfqd->last_position)
+		return blk_rq_pos(rq) - cfqd->last_position;
 	else
-		return cfqd->last_position - rq->sector;
+		return cfqd->last_position - blk_rq_pos(rq);
 }
 
-static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *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)
 {
-	struct cfq_io_context *cic = cfqd->active_cic;
+	sector_t sdist = cfqq->seek_mean;
 
-	if (!sample_valid(cic->seek_samples))
-		return 0;
+	if (!sample_valid(cfqq->seek_samples))
+		sdist = CFQQ_SEEK_THR;
 
-	return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean;
+	return cfq_dist_from_last(cfqd, rq) <= sdist;
 }
 
-static int cfq_close_cooperator(struct cfq_data *cfq_data,
-				struct cfq_queue *cfqq)
+static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
+				    struct cfq_queue *cur_cfqq)
 {
+	struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio];
+	struct rb_node *parent, *node;
+	struct cfq_queue *__cfqq;
+	sector_t sector = cfqd->last_position;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL);
+	if (__cfqq)
+		return __cfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector.
+	 */
+	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
+		return __cfqq;
+
+	if (blk_rq_pos(__cfqq->next_rq) < sector)
+		node = rb_next(&__cfqq->p_node);
+	else
+		node = rb_prev(&__cfqq->p_node);
+	if (!node)
+		return NULL;
+
+	__cfqq = rb_entry(node, struct cfq_queue, p_node);
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
+		return __cfqq;
+
+	return NULL;
+}
+
+/*
+ * cfqd - obvious
+ * cur_cfqq - passed in so that we don't decide that the current queue is
+ * 	      closely cooperating with itself.
+ *
+ * So, basically we're assuming that that cur_cfqq has dispatched at least
+ * one request, and that cfqd->last_position reflects a position on the disk
+ * associated with the I/O issued by cur_cfqq.  I'm not sure this is a valid
+ * assumption.
+ */
+static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
+					      struct cfq_queue *cur_cfqq)
+{
+	struct cfq_queue *cfqq;
+
+	if (!cfq_cfqq_sync(cur_cfqq))
+		return NULL;
+	if (CFQQ_SEEKY(cur_cfqq))
+		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.
 	 */
-	return 0;
+	cfqq = cfqq_close(cfqd, cur_cfqq);
+	if (!cfqq)
+		return NULL;
+
+	/*
+	 * It only makes sense to merge sync queues.
+	 */
+	if (!cfq_cfqq_sync(cfqq))
+		return NULL;
+	if (CFQQ_SEEKY(cfqq))
+		return NULL;
+
+	/*
+	 * Do not merge queues of different priority classes
+	 */
+	if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq))
+		return NULL;
+
+	return cfqq;
 }
 
-#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024))
+/*
+ * Determine whether we should enforce idle window for this queue.
+ */
+
+static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	enum wl_prio_t prio = cfqq_prio(cfqq);
+	struct cfq_rb_root *service_tree = cfqq->service_tree;
+
+	/* We never do for idle class queues. */
+	if (prio == IDLE_WORKLOAD)
+		return false;
+
+	/* We do for queues that were marked with idle window flag. */
+	if (cfq_cfqq_idle_window(cfqq))
+		return true;
+
+	/*
+	 * Otherwise, we do only if they are the last ones
+	 * in their service tree.
+	 */
+	if (!service_tree)
+		service_tree = service_tree_for(prio, cfqq_type(cfqq), cfqd);
+
+	if (service_tree->count == 0)
+		return true;
+
+	return (service_tree->count == 1 && cfq_rb_first(service_tree) == cfqq);
+}
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
@@ -856,13 +1232,27 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	struct cfq_io_context *cic;
 	unsigned long sl;
 
+	/*
+	 * SSD device without seek penalty, disable idling. But only do so
+	 * for devices that support queuing, otherwise we still have a problem
+	 * with sync vs async workloads.
+	 */
+	if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag)
+		return;
+
 	WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
 	WARN_ON(cfq_cfqq_slice_new(cfqq));
 
 	/*
 	 * idle is disabled, either manually or by past process history
 	 */
-	if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq))
+	if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
+		return;
+
+	/*
+	 * still active requests from this queue, don't idle
+	 */
+	if (cfqq->dispatched)
 		return;
 
 	/*
@@ -873,25 +1263,20 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		return;
 
 	/*
-	 * See if this prio level has a good candidate
+	 * If our average think time is larger than the remaining time
+	 * slice, then don't idle. This avoids overrunning the allotted
+	 * time slice.
 	 */
-	if (cfq_close_cooperator(cfqd, cfqq) &&
-	    (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2))
+	if (sample_valid(cic->ttime_samples) &&
+	    (cfqq->slice_end - jiffies < cic->ttime_mean))
 		return;
 
-	cfq_mark_cfqq_must_dispatch(cfqq);
 	cfq_mark_cfqq_wait_request(cfqq);
 
-	/*
-	 * we don't want to idle for seeks, but we do want to allow
-	 * fair distribution of slice time for a process doing back-to-back
-	 * seeks. so allow a little bit of time for him to submit a new rq
-	 */
 	sl = cfqd->cfq_slice_idle;
-	if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
-		sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
 
 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
 }
 
 /*
@@ -902,6 +1287,9 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 
+	cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+
+	cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
 	cfq_remove_request(rq);
 	cfqq->dispatched++;
 	elv_dispatch_sort(q, rq);
@@ -915,9 +1303,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
  */
 static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 {
-	struct cfq_data *cfqd = cfqq->cfqd;
-	struct request *rq;
-	int fifo;
+	struct request *rq = NULL;
 
 	if (cfq_cfqq_fifo_expire(cfqq))
 		return NULL;
@@ -927,12 +1313,11 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 	if (list_empty(&cfqq->fifo))
 		return NULL;
 
-	fifo = cfq_cfqq_sync(cfqq);
 	rq = rq_entry_fifo(cfqq->fifo.next);
+	if (time_before(jiffies, rq_fifo_time(rq)))
+		rq = NULL;
 
-	if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
-		return NULL;
-
+	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
 	return rq;
 }
 
@@ -947,12 +1332,159 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 }
 
 /*
+ * Must be called with the queue_lock held.
+ */
+static int cfqq_process_refs(struct cfq_queue *cfqq)
+{
+	int process_refs, io_refs;
+
+	io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
+	process_refs = atomic_read(&cfqq->ref) - io_refs;
+	BUG_ON(process_refs < 0);
+	return process_refs;
+}
+
+static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
+{
+	int process_refs, new_process_refs;
+	struct cfq_queue *__cfqq;
+
+	/* Avoid a circular list and skip interim queue merges */
+	while ((__cfqq = new_cfqq->new_cfqq)) {
+		if (__cfqq == cfqq)
+			return;
+		new_cfqq = __cfqq;
+	}
+
+	process_refs = cfqq_process_refs(cfqq);
+	/*
+	 * If the process for the cfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0)
+		return;
+
+	/*
+	 * Merge in the direction of the lesser amount of work.
+	 */
+	new_process_refs = cfqq_process_refs(new_cfqq);
+	if (new_process_refs >= process_refs) {
+		cfqq->new_cfqq = new_cfqq;
+		atomic_add(process_refs, &new_cfqq->ref);
+	} else {
+		new_cfqq->new_cfqq = cfqq;
+		atomic_add(new_process_refs, &cfqq->ref);
+	}
+}
+
+static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd, enum wl_prio_t prio,
+				    bool prio_changed)
+{
+	struct cfq_queue *queue;
+	int i;
+	bool key_valid = false;
+	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(prio, cur_best, cfqd)->count)
+			return cur_best;
+		cur_best = SYNC_WORKLOAD;
+		if (service_tree_for(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(prio, i, cfqd));
+		if (queue &&
+		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
+			lowest_key = queue->rb_key;
+			cur_best = i;
+			key_valid = true;
+		}
+	}
+
+	return cur_best;
+}
+
+static void choose_service_tree(struct cfq_data *cfqd)
+{
+	enum wl_prio_t previous_prio = cfqd->serving_prio;
+	bool prio_changed;
+	unsigned slice;
+	unsigned count;
+
+	/* Choose next priority. RT > BE > IDLE */
+	if (cfq_busy_queues_wl(RT_WORKLOAD, cfqd))
+		cfqd->serving_prio = RT_WORKLOAD;
+	else if (cfq_busy_queues_wl(BE_WORKLOAD, cfqd))
+		cfqd->serving_prio = BE_WORKLOAD;
+	else {
+		cfqd->serving_prio = IDLE_WORKLOAD;
+		cfqd->workload_expires = jiffies + 1;
+		return;
+	}
+
+	/*
+	 * For RT and BE, we have to choose also the type
+	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
+	 * expiration time
+	 */
+	prio_changed = (cfqd->serving_prio != previous_prio);
+	count = service_tree_for(cfqd->serving_prio, cfqd->serving_type, cfqd)
+		->count;
+
+	/*
+	 * If priority didn't change, check workload expiration,
+	 * and that we still have other queues ready
+	 */
+	if (!prio_changed && count &&
+	    !time_after(jiffies, cfqd->workload_expires))
+		return;
+
+	/* otherwise select new workload type */
+	cfqd->serving_type =
+		cfq_choose_wl(cfqd, cfqd->serving_prio, prio_changed);
+	count = service_tree_for(cfqd->serving_prio, cfqd->serving_type, cfqd)
+		->count;
+
+	/*
+	 * the workload slice is computed as a fraction of target latency
+	 * proportional to the number of queues in that workload, over
+	 * all the queues in the same priority class
+	 */
+	slice = cfq_target_latency * count /
+		max_t(unsigned, cfqd->busy_queues_avg[cfqd->serving_prio],
+		      cfq_busy_queues_wl(cfqd->serving_prio, cfqd));
+
+	if (cfqd->serving_type == ASYNC_WORKLOAD)
+		/* async workload slice is scaled down according to
+		 * the sync/async slice ratio. */
+		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
+	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);
+	cfqd->workload_expires = jiffies + slice;
+	cfqd->noidle_tree_requires_idle = false;
+}
+
+/*
  * Select a queue for service. If we have a current active queue,
  * check whether to continue servicing it, or retrieve and set a new one.
  */
 static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 {
-	struct cfq_queue *cfqq;
+	struct cfq_queue *cfqq, *new_cfqq = NULL;
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
@@ -961,7 +1493,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	/*
 	 * The active queue has run out of time, expire it and select new.
 	 */
-	if (cfq_slice_used(cfqq))
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
 		goto expire;
 
 	/*
@@ -972,75 +1504,42 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 		goto keep_queue;
 
 	/*
+	 * If another queue has a request waiting within our mean seek
+	 * distance, let it run.  The expire code will check for close
+	 * cooperators and put the close queue at the front of the service
+	 * tree.  If possible, merge the expiring queue with the new cfqq.
+	 */
+	new_cfqq = cfq_close_cooperator(cfqd, cfqq);
+	if (new_cfqq) {
+		if (!cfqq->new_cfqq)
+			cfq_setup_merge(cfqq, new_cfqq);
+		goto expire;
+	}
+
+	/*
 	 * No requests pending. If the active queue still has requests in
 	 * flight or is idling for a new request, allow either of these
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
 	if (timer_pending(&cfqd->idle_slice_timer) ||
-	    (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) {
+	    (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
 
 expire:
-	cfq_slice_expired(cfqd, 0);
-new_queue:
-	cfqq = cfq_set_active_queue(cfqd);
-keep_queue:
-	return cfqq;
-}
-
-/*
- * Dispatch some requests from cfqq, moving them to the request queue
- * dispatch list.
- */
-static int
-__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			int max_dispatch)
-{
-	int dispatched = 0;
-
-	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
-
-	do {
-		struct request *rq;
-
-		/*
-		 * follow expired path, else get first next available
-		 */
-		rq = cfq_check_fifo(cfqq);
-		if (rq == NULL)
-			rq = cfqq->next_rq;
-
-		/*
-		 * finally, insert request into driver dispatch list
-		 */
-		cfq_dispatch_insert(cfqd->queue, rq);
-
-		dispatched++;
-
-		if (!cfqd->active_cic) {
-			atomic_inc(&RQ_CIC(rq)->ioc->refcount);
-			cfqd->active_cic = RQ_CIC(rq);
-		}
-
-		if (RB_EMPTY_ROOT(&cfqq->sort_list))
-			break;
-
-	} while (dispatched < max_dispatch);
-
+	cfq_slice_expired(cfqd, 0);
+new_queue:
 	/*
-	 * expire an async queue immediately if it has used up its slice. idle
-	 * queue always expire after 1 dispatch round.
+	 * Current queue expired. Check if we have to switch to a new
+	 * service tree
 	 */
-	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
-	    dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
-	    cfq_class_idle(cfqq))) {
-		cfqq->slice_end = jiffies + 1;
-		cfq_slice_expired(cfqd, 0);
-	}
+	if (!new_cfqq)
+		choose_service_tree(cfqd);
 
-	return dispatched;
+	cfqq = cfq_set_active_queue(cfqd, new_cfqq);
+keep_queue:
+	return cfqq;
 }
 
 static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
@@ -1064,22 +1563,131 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq;
 	int dispatched = 0;
-
-	while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL)
+	int i, j;
+	for (i = 0; i < 2; ++i)
+		for (j = 0; j < 3; ++j)
+			while ((cfqq = cfq_rb_first(&cfqd->service_trees[i][j]))
+				!= NULL)
+				dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+
+	while ((cfqq = cfq_rb_first(&cfqd->service_tree_idle)) != NULL)
 		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 bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	unsigned int max_dispatch;
+
+	/*
+	 * Drain async requests before we start sync IO
+	 */
+	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_driver[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))
+		return false;
+
+	max_dispatch = cfqd->cfq_quantum;
+	if (cfq_class_idle(cfqq))
+		max_dispatch = 1;
+
+	/*
+	 * Does this cfqq already have too much IO in flight?
+	 */
+	if (cfqq->dispatched >= max_dispatch) {
+		/*
+		 * idle queue must always only have a single IO in flight
+		 */
+		if (cfq_class_idle(cfqq))
+			return false;
+
+		/*
+		 * We have other queues, don't allow more IO from this one
+		 */
+		if (cfqd->busy_queues > 1)
+			return false;
+
+		/*
+		 * Sole queue user, allow bigger slice
+		 */
+		max_dispatch *= 4;
+	}
+
+	/*
+	 * Async queues must wait a bit before being allowed dispatch.
+	 * We also ramp up the dispatch depth gradually for async IO,
+	 * 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 int depth;
+
+		depth = last_sync / cfqd->cfq_slice[1];
+		if (!depth && !cfqq->dispatched)
+			depth = 1;
+		if (depth < max_dispatch)
+			max_dispatch = depth;
+	}
+
+	/*
+	 * If we're below the current max, allow a dispatch
+	 */
+	return cfqq->dispatched < max_dispatch;
+}
+
+/*
+ * Dispatch a request from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct request *rq;
+
+	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+	if (!cfq_may_dispatch(cfqd, cfqq))
+		return false;
+
+	/*
+	 * follow expired path, else get first next available
+	 */
+	rq = cfq_check_fifo(cfqq);
+	if (!rq)
+		rq = cfqq->next_rq;
+
+	/*
+	 * insert request into driver dispatch list
+	 */
+	cfq_dispatch_insert(cfqd->queue, rq);
+
+	if (!cfqd->active_cic) {
+		struct cfq_io_context *cic = RQ_CIC(rq);
+
+		atomic_long_inc(&cic->ioc->refcount);
+		cfqd->active_cic = cic;
+	}
+
+	return true;
+}
+
+/*
+ * Find the cfqq that we need to service and move a request from that to the
+ * dispatch list
+ */
 static int cfq_dispatch_requests(struct request_queue *q, int force)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq;
-	int dispatched;
 
 	if (!cfqd->busy_queues)
 		return 0;
@@ -1087,32 +1695,32 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 	if (unlikely(force))
 		return cfq_forced_dispatch(cfqd);
 
-	dispatched = 0;
-	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
-		int max_dispatch;
-
-		max_dispatch = cfqd->cfq_quantum;
-		if (cfq_class_idle(cfqq))
-			max_dispatch = 1;
-
-		if (cfqq->dispatched >= max_dispatch) {
-			if (cfqd->busy_queues > 1)
-				break;
-			if (cfqq->dispatched >= 4 * max_dispatch)
-				break;
-		}
+	cfqq = cfq_select_queue(cfqd);
+	if (!cfqq)
+		return 0;
 
-		if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
-			break;
+	/*
+	 * Dispatch a request from this cfqq, if it is allowed
+	 */
+	if (!cfq_dispatch_request(cfqd, cfqq))
+		return 0;
 
-		cfq_clear_cfqq_must_dispatch(cfqq);
-		cfq_clear_cfqq_wait_request(cfqq);
-		del_timer(&cfqd->idle_slice_timer);
+	cfqq->slice_dispatch++;
+	cfq_clear_cfqq_must_dispatch(cfqq);
 
-		dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
+	/*
+	 * expire an async queue immediately if it has used up its slice. idle
+	 * queue always expire after 1 dispatch round.
+	 */
+	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
+	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+	    cfq_class_idle(cfqq))) {
+		cfqq->slice_end = jiffies + 1;
+		cfq_slice_expired(cfqd, 0);
 	}
 
-	return dispatched;
+	cfq_log_cfqq(cfqd, cfqq, "dispatched a request");
+	return 1;
 }
 
 /*
@@ -1130,6 +1738,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	if (!atomic_dec_and_test(&cfqq->ref))
 		return;
 
+	cfq_log_cfqq(cfqd, cfqq, "put_queue");
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
@@ -1142,6 +1751,9 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	kmem_cache_free(cfq_pool, cfqq);
 }
 
+/*
+ * Must always be called with the rcu_read_lock() held
+ */
 static void
 __call_for_each_cic(struct io_context *ioc,
 		    void (*func)(struct io_context *, struct cfq_io_context *))
@@ -1172,10 +1784,21 @@ static void cfq_cic_free_rcu(struct rcu_head *head)
 	cic = container_of(head, struct cfq_io_context, rcu_head);
 
 	kmem_cache_free(cfq_ioc_pool, cic);
-	elv_ioc_count_dec(ioc_count);
+	elv_ioc_count_dec(cfq_ioc_count);
 
-	if (ioc_gone && !elv_ioc_count_read(ioc_count))
-		complete(ioc_gone);
+	if (ioc_gone) {
+		/*
+		 * CFQ scheduler is exiting, grab exit lock and check
+		 * the pending io context count. If it hits zero,
+		 * complete ioc_gone and set it back to NULL
+		 */
+		spin_lock(&ioc_gone_lock);
+		if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) {
+			complete(ioc_gone);
+			ioc_gone = NULL;
+		}
+		spin_unlock(&ioc_gone_lock);
+	}
 }
 
 static void cfq_cic_free(struct cfq_io_context *cic)
@@ -1197,6 +1820,11 @@ static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
 	cfq_cic_free(cic);
 }
 
+/*
+ * Must be called with rcu_read_lock() held or preemption otherwise disabled.
+ * Only two callers of this - ->dtor() which is called with the rcu_read_lock(),
+ * and ->trim() which is called with the task lock held
+ */
 static void cfq_free_io_context(struct io_context *ioc)
 {
 	/*
@@ -1210,11 +1838,29 @@ static void cfq_free_io_context(struct io_context *ioc)
 
 static void cfq_exit_cfqq(struct cfq_data *cfqd, 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
+	 * the merge chain).  See cfq_setup_merge and cfq_merge_cfqqs.
+	 */
+	__cfqq = cfqq->new_cfqq;
+	while (__cfqq) {
+		if (__cfqq == cfqq) {
+			WARN(1, "cfqq->new_cfqq loop detected\n");
+			break;
+		}
+		next = __cfqq->new_cfqq;
+		cfq_put_queue(__cfqq);
+		__cfqq = next;
+	}
+
 	cfq_put_queue(cfqq);
 }
 
@@ -1235,14 +1881,14 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
 	if (ioc->ioc_data == cic)
 		rcu_assign_pointer(ioc->ioc_data, NULL);
 
-	if (cic->cfqq[ASYNC]) {
-		cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
-		cic->cfqq[ASYNC] = NULL;
+	if (cic->cfqq[BLK_RW_ASYNC]) {
+		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
+		cic->cfqq[BLK_RW_ASYNC] = NULL;
 	}
 
-	if (cic->cfqq[SYNC]) {
-		cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]);
-		cic->cfqq[SYNC] = NULL;
+	if (cic->cfqq[BLK_RW_SYNC]) {
+		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]);
+		cic->cfqq[BLK_RW_SYNC] = NULL;
 	}
 }
 
@@ -1256,7 +1902,15 @@ static void cfq_exit_single_io_context(struct io_context *ioc,
 		unsigned long flags;
 
 		spin_lock_irqsave(q->queue_lock, flags);
-		__cfq_exit_single_io_context(cfqd, cic);
+
+		/*
+		 * Ensure we get a fresh copy of the ->key to prevent
+		 * race between exiting task and queue
+		 */
+		smp_read_barrier_depends();
+		if (cic->key)
+			__cfq_exit_single_io_context(cfqd, cic);
+
 		spin_unlock_irqrestore(q->queue_lock, flags);
 	}
 }
@@ -1283,7 +1937,7 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
 		INIT_HLIST_NODE(&cic->cic_list);
 		cic->dtor = cfq_free_io_context;
 		cic->exit = cfq_exit_io_context;
-		elv_ioc_count_inc(ioc_count);
+		elv_ioc_count_inc(cfq_ioc_count);
 	}
 
 	return cic;
@@ -1303,10 +1957,10 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
 		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
 	case IOPRIO_CLASS_NONE:
 		/*
-		 * no prio set, place us in the middle of the BE classes
+		 * no prio set, inherit CPU scheduling settings
 		 */
 		cfqq->ioprio = task_nice_ioprio(tsk);
-		cfqq->ioprio_class = IOPRIO_CLASS_BE;
+		cfqq->ioprio_class = task_nice_ioclass(tsk);
 		break;
 	case IOPRIO_CLASS_RT:
 		cfqq->ioprio = task_ioprio(ioc);
@@ -1343,17 +1997,18 @@ static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
 
 	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
 
-	cfqq = cic->cfqq[ASYNC];
+	cfqq = cic->cfqq[BLK_RW_ASYNC];
 	if (cfqq) {
 		struct cfq_queue *new_cfqq;
-		new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC);
+		new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc,
+						GFP_ATOMIC);
 		if (new_cfqq) {
-			cic->cfqq[ASYNC] = new_cfqq;
+			cic->cfqq[BLK_RW_ASYNC] = new_cfqq;
 			cfq_put_queue(cfqq);
 		}
 	}
 
-	cfqq = cic->cfqq[SYNC];
+	cfqq = cic->cfqq[BLK_RW_SYNC];
 	if (cfqq)
 		cfq_mark_cfqq_prio_changed(cfqq);
 
@@ -1366,8 +2021,28 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc)
 	ioc->ioprio_changed = 0;
 }
 
+static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
+			  pid_t pid, bool is_sync)
+{
+	RB_CLEAR_NODE(&cfqq->rb_node);
+	RB_CLEAR_NODE(&cfqq->p_node);
+	INIT_LIST_HEAD(&cfqq->fifo);
+
+	atomic_set(&cfqq->ref, 0);
+	cfqq->cfqd = cfqd;
+
+	cfq_mark_cfqq_prio_changed(cfqq);
+
+	if (is_sync) {
+		if (!cfq_class_idle(cfqq))
+			cfq_mark_cfqq_idle_window(cfqq);
+		cfq_mark_cfqq_sync(cfqq);
+	}
+	cfqq->pid = pid;
+}
+
 static struct cfq_queue *
-cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
+cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 		     struct io_context *ioc, gfp_t gfp_mask)
 {
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
@@ -1378,54 +2053,40 @@ retry:
 	/* cic always exists here */
 	cfqq = cic_to_cfqq(cic, is_sync);
 
-	if (!cfqq) {
+	/*
+	 * Always try a new alloc if we fell back to the OOM cfqq
+	 * originally, since it should just be a temporary situation.
+	 */
+	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
+		cfqq = NULL;
 		if (new_cfqq) {
 			cfqq = new_cfqq;
 			new_cfqq = NULL;
 		} else if (gfp_mask & __GFP_WAIT) {
-			/*
-			 * Inform the allocator of the fact that we will
-			 * just repeat this allocation if it fails, to allow
-			 * the allocator to do whatever it needs to attempt to
-			 * free memory.
-			 */
 			spin_unlock_irq(cfqd->queue->queue_lock);
 			new_cfqq = kmem_cache_alloc_node(cfq_pool,
-					gfp_mask | __GFP_NOFAIL | __GFP_ZERO,
+					gfp_mask | __GFP_ZERO,
 					cfqd->queue->node);
 			spin_lock_irq(cfqd->queue->queue_lock);
-			goto retry;
+			if (new_cfqq)
+				goto retry;
 		} else {
 			cfqq = kmem_cache_alloc_node(cfq_pool,
 					gfp_mask | __GFP_ZERO,
 					cfqd->queue->node);
-			if (!cfqq)
-				goto out;
 		}
 
-		RB_CLEAR_NODE(&cfqq->rb_node);
-		INIT_LIST_HEAD(&cfqq->fifo);
-
-		atomic_set(&cfqq->ref, 0);
-		cfqq->cfqd = cfqd;
-
-		cfq_mark_cfqq_prio_changed(cfqq);
-		cfq_mark_cfqq_queue_new(cfqq);
-
-		cfq_init_prio_data(cfqq, ioc);
-
-		if (is_sync) {
-			if (!cfq_class_idle(cfqq))
-				cfq_mark_cfqq_idle_window(cfqq);
-			cfq_mark_cfqq_sync(cfqq);
-		}
+		if (cfqq) {
+			cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
+			cfq_init_prio_data(cfqq, ioc);
+			cfq_log_cfqq(cfqd, cfqq, "alloced");
+		} else
+			cfqq = &cfqd->oom_cfqq;
 	}
 
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 
-out:
-	WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
 	return cfqq;
 }
 
@@ -1445,7 +2106,7 @@ cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
 }
 
 static struct cfq_queue *
-cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc,
+cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc,
 	      gfp_t gfp_mask)
 {
 	const int ioprio = task_ioprio(ioc);
@@ -1458,11 +2119,8 @@ cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc,
 		cfqq = *async_cfqq;
 	}
 
-	if (!cfqq) {
+	if (!cfqq)
 		cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask);
-		if (!cfqq)
-			return NULL;
-	}
 
 	/*
 	 * pin the queue now that it's allocated, scheduler exit will prune it
@@ -1502,20 +2160,24 @@ static struct cfq_io_context *
 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;
 
+	rcu_read_lock();
+
 	/*
 	 * we maintain a last-hit cache, to avoid browsing over the tree
 	 */
 	cic = rcu_dereference(ioc->ioc_data);
-	if (cic && cic->key == cfqd)
+	if (cic && cic->key == cfqd) {
+		rcu_read_unlock();
 		return cic;
+	}
 
 	do {
-		rcu_read_lock();
 		cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
 		rcu_read_unlock();
 		if (!cic)
@@ -1524,10 +2186,13 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
 		k = cic->key;
 		if (unlikely(!k)) {
 			cfq_drop_dead_cic(cfqd, ioc, cic);
+			rcu_read_lock();
 			continue;
 		}
 
+		spin_lock_irqsave(&ioc->lock, flags);
 		rcu_assign_pointer(ioc->ioc_data, cic);
+		spin_unlock_irqrestore(&ioc->lock, flags);
 		break;
 	} while (1);
 
@@ -1625,31 +2290,46 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
 }
 
 static void
-cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
+cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct request *rq)
 {
 	sector_t sdist;
 	u64 total;
 
-	if (cic->last_request_pos < rq->sector)
-		sdist = rq->sector - cic->last_request_pos;
+	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 = cic->last_request_pos - rq->sector;
+		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 (cic->seek_samples <= 60) /* second&third seek */
-		sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
+	if (cfqq->seek_samples <= 60) /* second&third seek */
+		sdist = min(sdist, (cfqq->seek_mean * 4) + 2*1024*1024);
 	else
-		sdist = min(sdist, (cic->seek_mean * 4)	+ 2*1024*64);
+		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;
 
-	cic->seek_samples = (7*cic->seek_samples + 256) / 8;
-	cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
-	total = cic->seek_total + (cic->seek_samples/2);
-	do_div(total, cic->seek_samples);
-	cic->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;
+	}
 }
 
 /*
@@ -1660,7 +2340,7 @@ static void
 cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		       struct cfq_io_context *cic)
 {
-	int enable_idle;
+	int old_idle, enable_idle;
 
 	/*
 	 * Don't idle for async or idle io prio class
@@ -1668,10 +2348,14 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
 		return;
 
-	enable_idle = cfq_cfqq_idle_window(cfqq);
+	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
+
+	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
+		cfq_mark_cfqq_deep(cfqq);
 
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (cfqd->hw_tag && CIC_SEEKY(cic)))
+	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
+	     && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -1680,17 +2364,20 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			enable_idle = 1;
 	}
 
-	if (enable_idle)
-		cfq_mark_cfqq_idle_window(cfqq);
-	else
-		cfq_clear_cfqq_idle_window(cfqq);
+	if (old_idle != enable_idle) {
+		cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
+		if (enable_idle)
+			cfq_mark_cfqq_idle_window(cfqq);
+		else
+			cfq_clear_cfqq_idle_window(cfqq);
+	}
 }
 
 /*
  * Check if new_cfqq should preempt the currently active queue. Return 0 for
  * no or if we aren't sure, a 1 will cause a preempt.
  */
-static int
+static bool
 cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 		   struct request *rq)
 {
@@ -1698,42 +2385,53 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
-		return 0;
+		return false;
 
 	if (cfq_slice_used(cfqq))
-		return 1;
+		return true;
 
 	if (cfq_class_idle(new_cfqq))
-		return 0;
+		return false;
 
 	if (cfq_class_idle(cfqq))
-		return 1;
+		return true;
+
+	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
+	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
+	    new_cfqq->service_tree->count == 1)
+		return true;
 
 	/*
 	 * if the new request is sync, but the currently running queue is
 	 * not, let the sync request have priority.
 	 */
 	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
-		return 1;
+		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.
 	 */
 	if (rq_is_meta(rq) && !cfqq->meta_pending)
-		return 1;
+		return true;
+
+	/*
+	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+		return true;
 
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
-		return 0;
+		return false;
 
 	/*
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
-	if (cfq_rq_close(cfqd, rq))
-		return 1;
+	if (cfq_rq_close(cfqd, cfqq, rq))
+		return true;
 
-	return 0;
+	return false;
 }
 
 /*
@@ -1742,6 +2440,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
  */
 static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
+	cfq_log_cfqq(cfqd, cfqq, "preempt");
 	cfq_slice_expired(cfqd, 1);
 
 	/*
@@ -1766,35 +2465,44 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 {
 	struct cfq_io_context *cic = RQ_CIC(rq);
 
+	cfqd->rq_queued++;
 	if (rq_is_meta(rq))
 		cfqq->meta_pending++;
 
 	cfq_update_io_thinktime(cfqd, cic);
-	cfq_update_io_seektime(cfqd, cic, rq);
+	cfq_update_io_seektime(cfqd, cfqq, rq);
 	cfq_update_idle_window(cfqd, cfqq, cic);
 
-	cic->last_request_pos = rq->sector + rq->nr_sectors;
+	cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (cfqq == cfqd->active_queue) {
 		/*
-		 * if we are waiting for a request for this queue, let it rip
-		 * immediately and flag that we must not expire this queue
-		 * just now
+		 * Remember that we saw a request from this process, but
+		 * don't start queuing just yet. Otherwise we risk seeing lots
+		 * of tiny requests, because we disrupt the normal plugging
+		 * and merging. If the request is already larger than a single
+		 * page, let it rip immediately. For that case we assume that
+		 * merging is already done. Ditto for a busy system that
+		 * has other work pending, don't risk delaying until the
+		 * idle timer unplug to continue working.
 		 */
 		if (cfq_cfqq_wait_request(cfqq)) {
+			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
+			    cfqd->busy_queues > 1) {
+				del_timer(&cfqd->idle_slice_timer);
+			__blk_run_queue(cfqd->queue);
+			}
 			cfq_mark_cfqq_must_dispatch(cfqq);
-			del_timer(&cfqd->idle_slice_timer);
-			blk_start_queueing(cfqd->queue);
 		}
 	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
 		/*
 		 * not the active queue - expire current slice if it is
 		 * idle and has expired it's mean thinktime or this new queue
-		 * has some old slice time left and is of higher priority
+		 * has some old slice time left and is of higher priority or
+		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		cfq_mark_cfqq_must_dispatch(cfqq);
-		blk_start_queueing(cfqd->queue);
+		__blk_run_queue(cfqd->queue);
 	}
 }
 
@@ -1803,15 +2511,53 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 
+	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
 
-	cfq_add_rq_rb(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);
 
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
 
+/*
+ * Update hw_tag based on peak queue depth over 50 samples under
+ * sufficient load.
+ */
+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->hw_tag == 1)
+		return;
+
+	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
+	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
+		return;
+
+	/*
+	 * If active queue hasn't enough requests and can idle, cfq might not
+	 * dispatch sufficient requests to hardware. Don't zero hw_tag in this
+	 * case
+	 */
+	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)
+		return;
+
+	if (cfqd->hw_tag_samples++ < 50)
+		return;
+
+	if (cfqd->hw_tag_est_depth >= CFQ_HW_QUEUE_MIN)
+		cfqd->hw_tag = 1;
+	else
+		cfqd->hw_tag = 0;
+}
+
 static void cfq_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
@@ -1820,37 +2566,59 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	unsigned long now;
 
 	now = jiffies;
+	cfq_log_cfqq(cfqd, cfqq, "complete");
+
+	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver);
+	WARN_ON(!cfqd->rq_in_driver[sync]);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver--;
+	cfqd->rq_in_driver[sync]--;
 	cfqq->dispatched--;
 
 	if (cfq_cfqq_sync(cfqq))
 		cfqd->sync_flight--;
 
-	if (!cfq_class_idle(cfqq))
-		cfqd->last_end_request = now;
-
-	if (sync)
+	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
+		cfqd->last_end_sync_rq = now;
+	}
 
 	/*
 	 * If this is the active queue, check if it needs to be expired,
 	 * or if we want to idle in case it has no pending requests.
 	 */
 	if (cfqd->active_queue == cfqq) {
+		const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list);
+
 		if (cfq_cfqq_slice_new(cfqq)) {
 			cfq_set_prio_slice(cfqd, cfqq);
 			cfq_clear_cfqq_slice_new(cfqq);
 		}
+		/*
+		 * Idling is not enabled on:
+		 * - expired queues
+		 * - idle-priority queues
+		 * - async queues
+		 * - queues with still some requests queued
+		 * - when there is a close cooperator
+		 */
 		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
 			cfq_slice_expired(cfqd, 1);
-		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
-			cfq_arm_slice_timer(cfqd);
+		else if (sync && cfqq_empty &&
+			 !cfq_close_cooperator(cfqd, cfqq)) {
+			cfqd->noidle_tree_requires_idle |= !rq_noidle(rq);
+			/*
+			 * Idling is enabled for SYNC_WORKLOAD.
+			 * SYNC_NOIDLE_WORKLOAD idles at the end of the tree
+			 * only if we processed at least one !rq_noidle request
+			 */
+			if (cfqd->serving_type == SYNC_WORKLOAD
+			    || cfqd->noidle_tree_requires_idle)
+				cfq_arm_slice_timer(cfqd);
+		}
 	}
 
-	if (!cfqd->rq_in_driver)
+	if (!rq_in_driver(cfqd))
 		cfq_schedule_dispatch(cfqd);
 }
 
@@ -1871,19 +2639,16 @@ static void cfq_prio_boost(struct cfq_queue *cfqq)
 			cfqq->ioprio = IOPRIO_NORM;
 	} else {
 		/*
-		 * check if we need to unboost the queue
+		 * unboost the queue (if needed)
 		 */
-		if (cfqq->ioprio_class != cfqq->org_ioprio_class)
-			cfqq->ioprio_class = cfqq->org_ioprio_class;
-		if (cfqq->ioprio != cfqq->org_ioprio)
-			cfqq->ioprio = cfqq->org_ioprio;
+		cfqq->ioprio_class = cfqq->org_ioprio_class;
+		cfqq->ioprio = cfqq->org_ioprio;
 	}
 }
 
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 {
-	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
-	    !cfq_cfqq_must_alloc_slice(cfqq)) {
+	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
 		cfq_mark_cfqq_must_alloc_slice(cfqq);
 		return ELV_MQUEUE_MUST;
 	}
@@ -1908,7 +2673,7 @@ static int cfq_may_queue(struct request_queue *q, int rw)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC);
+	cfqq = cic_to_cfqq(cic, rw_is_sync(rw));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic->ioc);
 		cfq_prio_boost(cfqq);
@@ -1941,6 +2706,43 @@ static void cfq_put_request(struct request *rq)
 	}
 }
 
+static struct cfq_queue *
+cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
+		struct cfq_queue *cfqq)
+{
+	cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq);
+	cic_set_cfqq(cic, cfqq->new_cfqq, 1);
+	cfq_mark_cfqq_coop(cfqq->new_cfqq);
+	cfq_put_queue(cfqq);
+	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.
+ */
+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);
+		return cfqq;
+	}
+
+	cic_set_cfqq(cic, NULL, 1);
+	cfq_put_queue(cfqq);
+	return NULL;
+}
 /*
  * Allocate cfq data structures associated with this request.
  */
@@ -1950,7 +2752,7 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_context *cic;
 	const int rw = rq_data_dir(rq);
-	const int is_sync = rq_is_sync(rq);
+	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 
@@ -1963,18 +2765,33 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	if (!cic)
 		goto queue_fail;
 
+new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
-	if (!cfqq) {
+	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
 		cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask);
-
-		if (!cfqq)
-			goto queue_fail;
-
 		cic_set_cfqq(cic, cfqq, is_sync);
+	} else {
+		/*
+		 * If the queue was seeky for too long, break it apart.
+		 */
+		if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
+			cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
+			cfqq = split_cfqq(cic, cfqq);
+			if (!cfqq)
+				goto new_queue;
+		}
+
+		/*
+		 * Check to see if this queue is scheduled to merge with
+		 * another, closely cooperating queue.  The merging of
+		 * queues happens here as it must be done in process context.
+		 * The reference on new_cfqq was taken in merge_cfqqs.
+		 */
+		if (cfqq->new_cfqq)
+			cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq);
 	}
 
 	cfqq->allocated[rw]++;
-	cfq_clear_cfqq_must_alloc(cfqq);
 	atomic_inc(&cfqq->ref);
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
@@ -1989,6 +2806,7 @@ queue_fail:
 
 	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
+	cfq_log(cfqd, "set_request fail");
 	return 1;
 }
 
@@ -1997,11 +2815,10 @@ static void cfq_kick_queue(struct work_struct *work)
 	struct cfq_data *cfqd =
 		container_of(work, struct cfq_data, unplug_work);
 	struct request_queue *q = cfqd->queue;
-	unsigned long flags;
 
-	spin_lock_irqsave(q->queue_lock, flags);
-	blk_start_queueing(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	spin_lock_irq(q->queue_lock);
+	__blk_run_queue(cfqd->queue);
+	spin_unlock_irq(q->queue_lock);
 }
 
 /*
@@ -2014,6 +2831,8 @@ static void cfq_idle_slice_timer(unsigned long data)
 	unsigned long flags;
 	int timed_out = 1;
 
+	cfq_log(cfqd, "idle timer fired");
+
 	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
 
 	cfqq = cfqd->active_queue;
@@ -2021,6 +2840,12 @@ static void cfq_idle_slice_timer(unsigned long data)
 		timed_out = 0;
 
 		/*
+		 * We saw a request before the queue expired, let it through
+		 */
+		if (cfq_cfqq_must_dispatch(cfqq))
+			goto out_kick;
+
+		/*
 		 * expired
 		 */
 		if (cfq_slice_used(cfqq))
@@ -2036,10 +2861,13 @@ static void cfq_idle_slice_timer(unsigned long data)
 		/*
 		 * not expired and it has a request pending, let it dispatch
 		 */
-		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
-			cfq_mark_cfqq_must_dispatch(cfqq);
+		if (!RB_EMPTY_ROOT(&cfqq->sort_list))
 			goto out_kick;
-		}
+
+		/*
+		 * Queue depth flag is reset only when the idle didn't succeed
+		 */
+		cfq_clear_cfqq_deep(cfqq);
 	}
 expire:
 	cfq_slice_expired(cfqd, timed_out);
@@ -2052,7 +2880,7 @@ out_cont:
 static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
 {
 	del_timer_sync(&cfqd->idle_slice_timer);
-	kblockd_flush_work(&cfqd->unplug_work);
+	cancel_work_sync(&cfqd->unplug_work);
 }
 
 static void cfq_put_async_queues(struct cfq_data *cfqd)
@@ -2070,7 +2898,7 @@ static void cfq_put_async_queues(struct cfq_data *cfqd)
 		cfq_put_queue(cfqd->async_idle_cfqq);
 }
 
-static void cfq_exit_queue(elevator_t *e)
+static void cfq_exit_queue(struct elevator_queue *e)
 {
 	struct cfq_data *cfqd = e->elevator_data;
 	struct request_queue *q = cfqd->queue;
@@ -2102,12 +2930,33 @@ static void cfq_exit_queue(elevator_t *e)
 static void *cfq_init_queue(struct request_queue *q)
 {
 	struct cfq_data *cfqd;
+	int i, j;
 
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
 	if (!cfqd)
 		return NULL;
 
-	cfqd->service_tree = CFQ_RB_ROOT;
+	for (i = 0; i < 2; ++i)
+		for (j = 0; j < 3; ++j)
+			cfqd->service_trees[i][j] = CFQ_RB_ROOT;
+	cfqd->service_tree_idle = CFQ_RB_ROOT;
+
+	/*
+	 * Not strictly needed (since RB_ROOT just clears the node and we
+	 * zeroed cfqd on alloc), but better be safe in case someone decides
+	 * to add magic to the rb code
+	 */
+	for (i = 0; i < CFQ_PRIO_LISTS; i++)
+		cfqd->prio_trees[i] = RB_ROOT;
+
+	/*
+	 * Our fallback cfqq if cfq_find_alloc_queue() runs into OOM issues.
+	 * Grab a permanent reference to it, so that the normal code flow
+	 * will not attempt to free it.
+	 */
+	cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
+	atomic_inc(&cfqd->oom_cfqq.ref);
+
 	INIT_LIST_HEAD(&cfqd->cic_list);
 
 	cfqd->queue = q;
@@ -2118,7 +2967,6 @@ static void *cfq_init_queue(struct request_queue *q)
 
 	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
 
-	cfqd->last_end_request = jiffies;
 	cfqd->cfq_quantum = cfq_quantum;
 	cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
 	cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
@@ -2128,12 +2976,18 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_slice[1] = cfq_slice_sync;
 	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
 	cfqd->cfq_slice_idle = cfq_slice_idle;
-
+	cfqd->cfq_latency = 1;
+	cfqd->hw_tag = -1;
+	cfqd->last_end_sync_rq = jiffies;
 	return cfqd;
 }
 
 static void cfq_slab_kill(void)
 {
+	/*
+	 * Caller already ensured that pending RCU callbacks are completed,
+	 * so we should have no busy allocations at this point.
+	 */
 	if (cfq_pool)
 		kmem_cache_destroy(cfq_pool);
 	if (cfq_ioc_pool)
@@ -2175,7 +3029,7 @@ cfq_var_store(unsigned int *var, const char *page, size_t count)
 }
 
 #define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
-static ssize_t __FUNC(elevator_t *e, char *page)			\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
 	unsigned int __data = __VAR;					\
@@ -2192,10 +3046,11 @@ SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
 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);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
-static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
 	unsigned int __data;						\
@@ -2223,6 +3078,7 @@ STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
 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);
 #undef STORE_FUNCTION
 
 #define CFQ_ATTR(name) \
@@ -2238,6 +3094,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_async),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(low_latency),
 	__ATTR_NULL
 };
 
@@ -2292,8 +3149,13 @@ static void __exit cfq_exit(void)
 	ioc_gone = &all_gone;
 	/* ioc_gone's update must be visible before reading ioc_count */
 	smp_wmb();
-	if (elv_ioc_count_read(ioc_count))
-		wait_for_completion(ioc_gone);
+
+	/*
+	 * this also protects us from entering cfq_slab_kill() with
+	 * pending RCU callbacks
+	 */
+	if (elv_ioc_count_read(cfq_ioc_count))
+		wait_for_completion(&all_gone);
 	cfq_slab_kill();
 }