Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus-1

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6: (9356 commits) [media] rc: update for bitop name changes fs: simplify iget & friends fs: pull inode->i_lock up out of writeback_single_inode fs: rename inode_lock to inode_hash_lock fs: move i_wb_list out from under inode_lock fs: move i_sb_list out from under inode_lock fs: remove inode_lock from iput_final and prune_icache fs: Lock the inode LRU list separately fs: factor inode disposal fs: protect inode->i_state with inode->i_lock lib, arch: add filter argument to show_mem and fix private implementations SLUB: Write to per cpu data when allocating it slub: Fix debugobjects with lockless fastpath autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd() autofs4 - remove autofs4_lock autofs4 - fix d_manage() return on rcu-walk autofs4 - fix autofs4_expire_indirect() traversal autofs4 - fix dentry leak in autofs4_expire_direct() autofs4 - reinstate last used update on access vfs - check non-mountpoint dentry might block in __follow_mount_rcu() ... NOTE! This merge commit was created to fix compilation error. The block tree was merged upstream and removed the 'elv_queue_empty()' function which the new 'mtdswap' driver is using. So a simple merge of the mtd tree with upstream does not compile. And the mtd tree has already be published, so re-basing it is not an option. To fix this unfortunate situation, I had to merge upstream into the mtd-2.6.git tree without committing, put the fixup patch on top of this, and then commit this. The result is that we do not have commits which do not compile. In other words, this merge commit "merges" 3 things: the MTD tree, the upstream tree, and the fixup patch.
author: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> 2011-03-25 17:41:20 +0200
committer: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> 2011-03-25 17:41:20 +0200
commit: 7bf7e370d5919112c223a269462cd0b546903829 (patch)
tree: 03ccc715239df14ae168277dbccc9d9cf4d8a2c8 /block
parent: 68b1a1e786f29c900fa1c516a402e24f0ece622a (diff)
parent: d39dd11c3e6a7af5c20bfac40594db36cf270f42 (diff)
18 files changed, 1027 insertions, 699 deletions
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 455768a3eb9e..2bef5705ce24 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -371,12 +371,14 @@ void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
 
-void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
+void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time,
+				unsigned long unaccounted_time)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&blkg->stats_lock, flags);
 	blkg->stats.time += time;
+	blkg->stats.unaccounted_time += unaccounted_time;
 	spin_unlock_irqrestore(&blkg->stats_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
@@ -604,6 +606,9 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg,
 		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
 					blkg->stats.sectors, cb, dev);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
+	if (type == BLKIO_STAT_UNACCOUNTED_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.unaccounted_time, cb, dev);
 	if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {
 		uint64_t sum = blkg->stats.avg_queue_size_sum;
 		uint64_t samples = blkg->stats.avg_queue_size_samples;
@@ -1125,6 +1130,9 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
 			return blkio_read_blkg_stats(blkcg, cft, cb,
 						BLKIO_STAT_QUEUED, 1);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
+		case BLKIO_PROP_unaccounted_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_UNACCOUNTED_TIME, 0);
 		case BLKIO_PROP_dequeue:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
 						BLKIO_STAT_DEQUEUE, 0);
@@ -1382,6 +1390,12 @@ struct cftype blkio_files[] = {
 				BLKIO_PROP_dequeue),
 		.read_map = blkiocg_file_read_map,
 	},
+	{
+		.name = "unaccounted_time",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_unaccounted_time),
+		.read_map = blkiocg_file_read_map,
+	},
 #endif
 };
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index ea4861bdd549..10919fae2d3a 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -49,6 +49,8 @@ enum stat_type {
 	/* All the single valued stats go below this */
 	BLKIO_STAT_TIME,
 	BLKIO_STAT_SECTORS,
+	/* Time not charged to this cgroup */
+	BLKIO_STAT_UNACCOUNTED_TIME,
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	BLKIO_STAT_AVG_QUEUE_SIZE,
 	BLKIO_STAT_IDLE_TIME,
@@ -81,6 +83,7 @@ enum blkcg_file_name_prop {
 	BLKIO_PROP_io_serviced,
 	BLKIO_PROP_time,
 	BLKIO_PROP_sectors,
+	BLKIO_PROP_unaccounted_time,
 	BLKIO_PROP_io_service_time,
 	BLKIO_PROP_io_wait_time,
 	BLKIO_PROP_io_merged,
@@ -114,6 +117,8 @@ struct blkio_group_stats {
 	/* total disk time and nr sectors dispatched by this group */
 	uint64_t time;
 	uint64_t sectors;
+	/* Time not charged to this cgroup */
+	uint64_t unaccounted_time;
 	uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* Sum of number of IOs queued across all samples */
@@ -240,7 +245,7 @@ static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
 
 #endif
 
-#define BLKIO_WEIGHT_MIN	100
+#define BLKIO_WEIGHT_MIN	10
 #define BLKIO_WEIGHT_MAX	1000
 #define BLKIO_WEIGHT_DEFAULT	500
 
@@ -293,7 +298,8 @@ extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 						void *key);
 void blkiocg_update_timeslice_used(struct blkio_group *blkg,
-					unsigned long time);
+					unsigned long time,
+					unsigned long unaccounted_time);
 void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes,
 						bool direction, bool sync);
 void blkiocg_update_completion_stats(struct blkio_group *blkg,
@@ -319,7 +325,9 @@ blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 static inline struct blkio_group *
 blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; }
 static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
-						unsigned long time) {}
+						unsigned long time,
+						unsigned long unaccounted_time)
+{}
 static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
 				uint64_t bytes, bool direction, bool sync) {}
 static inline void blkiocg_update_completion_stats(struct blkio_group *blkg,
diff --git a/block/blk-core.c b/block/blk-core.c
index 2f4002f79a24..59b5c00c0126 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -27,6 +27,7 @@
 #include <linux/writeback.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/fault-inject.h>
+#include <linux/list_sort.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -149,39 +150,29 @@ EXPORT_SYMBOL(blk_rq_init);
 static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
 {
-	struct request_queue *q = rq->q;
-
-	if (&q->flush_rq != rq) {
-		if (error)
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
-		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-			error = -EIO;
+	if (error)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		error = -EIO;
 
-		if (unlikely(nbytes > bio->bi_size)) {
-			printk(KERN_ERR "%s: want %u bytes done, %u left\n",
-			       __func__, nbytes, bio->bi_size);
-			nbytes = bio->bi_size;
-		}
+	if (unlikely(nbytes > bio->bi_size)) {
+		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
+		       __func__, nbytes, bio->bi_size);
+		nbytes = bio->bi_size;
+	}
 
-		if (unlikely(rq->cmd_flags & REQ_QUIET))
-			set_bit(BIO_QUIET, &bio->bi_flags);
+	if (unlikely(rq->cmd_flags & REQ_QUIET))
+		set_bit(BIO_QUIET, &bio->bi_flags);
 
-		bio->bi_size -= nbytes;
-		bio->bi_sector += (nbytes >> 9);
+	bio->bi_size -= nbytes;
+	bio->bi_sector += (nbytes >> 9);
 
-		if (bio_integrity(bio))
-			bio_integrity_advance(bio, nbytes);
+	if (bio_integrity(bio))
+		bio_integrity_advance(bio, nbytes);
 
-		if (bio->bi_size == 0)
-			bio_endio(bio, error);
-	} else {
-		/*
-		 * Okay, this is the sequenced flush request in
-		 * progress, just record the error;
-		 */
-		if (error && !q->flush_err)
-			q->flush_err = error;
-	}
+	/* don't actually finish bio if it's part of flush sequence */
+	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+		bio_endio(bio, error);
 }
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
@@ -208,135 +199,43 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
 /*
- * "plug" the device if there are no outstanding requests: this will
- * force the transfer to start only after we have put all the requests
- * on the list.
- *
- * This is called with interrupts off and no requests on the queue and
- * with the queue lock held.
- */
-void blk_plug_device(struct request_queue *q)
+ * Make sure that plugs that were pending when this function was entered,
+ * are now complete and requests pushed to the queue.
+*/
+static inline void queue_sync_plugs(struct request_queue *q)
 {
-	WARN_ON(!irqs_disabled());
-
 	/*
-	 * don't plug a stopped queue, it must be paired with blk_start_queue()
-	 * which will restart the queueing
+	 * If the current process is plugged and has barriers submitted,
+	 * we will livelock if we don't unplug first.
 	 */
-	if (blk_queue_stopped(q))
-		return;
-
-	if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) {
-		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
-		trace_block_plug(q);
-	}
-}
-EXPORT_SYMBOL(blk_plug_device);
-
-/**
- * blk_plug_device_unlocked - plug a device without queue lock held
- * @q:    The &struct request_queue to plug
- *
- * Description:
- *   Like @blk_plug_device(), but grabs the queue lock and disables
- *   interrupts.
- **/
-void blk_plug_device_unlocked(struct request_queue *q)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	blk_plug_device(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-EXPORT_SYMBOL(blk_plug_device_unlocked);
-
-/*
- * remove the queue from the plugged list, if present. called with
- * queue lock held and interrupts disabled.
- */
-int blk_remove_plug(struct request_queue *q)
-{
-	WARN_ON(!irqs_disabled());
-
-	if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q))
-		return 0;
-
-	del_timer(&q->unplug_timer);
-	return 1;
+	blk_flush_plug(current);
 }
-EXPORT_SYMBOL(blk_remove_plug);
 
-/*
- * remove the plug and let it rip..
- */
-void __generic_unplug_device(struct request_queue *q)
+static void blk_delay_work(struct work_struct *work)
 {
-	if (unlikely(blk_queue_stopped(q)))
-		return;
-	if (!blk_remove_plug(q) && !blk_queue_nonrot(q))
-		return;
+	struct request_queue *q;
 
-	q->request_fn(q);
+	q = container_of(work, struct request_queue, delay_work.work);
+	spin_lock_irq(q->queue_lock);
+	__blk_run_queue(q, false);
+	spin_unlock_irq(q->queue_lock);
 }
 
 /**
- * generic_unplug_device - fire a request queue
- * @q:    The &struct request_queue in question
+ * blk_delay_queue - restart queueing after defined interval
+ * @q:		The &struct request_queue in question
+ * @msecs:	Delay in msecs
  *
  * Description:
- *   Linux uses plugging to build bigger requests queues before letting
- *   the device have at them. If a queue is plugged, the I/O scheduler
- *   is still adding and merging requests on the queue. Once the queue
- *   gets unplugged, the request_fn defined for the queue is invoked and
- *   transfers started.
- **/
-void generic_unplug_device(struct request_queue *q)
-{
-	if (blk_queue_plugged(q)) {
-		spin_lock_irq(q->queue_lock);
-		__generic_unplug_device(q);
-		spin_unlock_irq(q->queue_lock);
-	}
-}
-EXPORT_SYMBOL(generic_unplug_device);
-
-static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
-				   struct page *page)
-{
-	struct request_queue *q = bdi->unplug_io_data;
-
-	blk_unplug(q);
-}
-
-void blk_unplug_work(struct work_struct *work)
-{
-	struct request_queue *q =
-		container_of(work, struct request_queue, unplug_work);
-
-	trace_block_unplug_io(q);
-	q->unplug_fn(q);
-}
-
-void blk_unplug_timeout(unsigned long data)
-{
-	struct request_queue *q = (struct request_queue *)data;
-
-	trace_block_unplug_timer(q);
-	kblockd_schedule_work(q, &q->unplug_work);
-}
-
-void blk_unplug(struct request_queue *q)
+ *   Sometimes queueing needs to be postponed for a little while, to allow
+ *   resources to come back. This function will make sure that queueing is
+ *   restarted around the specified time.
+ */
+void blk_delay_queue(struct request_queue *q, unsigned long msecs)
 {
-	/*
-	 * devices don't necessarily have an ->unplug_fn defined
-	 */
-	if (q->unplug_fn) {
-		trace_block_unplug_io(q);
-		q->unplug_fn(q);
-	}
+	schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs));
 }
-EXPORT_SYMBOL(blk_unplug);
+EXPORT_SYMBOL(blk_delay_queue);
 
 /**
  * blk_start_queue - restart a previously stopped queue
@@ -352,7 +251,7 @@ void blk_start_queue(struct request_queue *q)
 	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-	__blk_run_queue(q);
+	__blk_run_queue(q, false);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -372,7 +271,7 @@ EXPORT_SYMBOL(blk_start_queue);
  **/
 void blk_stop_queue(struct request_queue *q)
 {
-	blk_remove_plug(q);
+	cancel_delayed_work(&q->delay_work);
 	queue_flag_set(QUEUE_FLAG_STOPPED, q);
 }
 EXPORT_SYMBOL(blk_stop_queue);
@@ -390,46 +289,43 @@ EXPORT_SYMBOL(blk_stop_queue);
  *     that its ->make_request_fn will not re-add plugging prior to calling
  *     this function.
  *
+ *     This function does not cancel any asynchronous activity arising
+ *     out of elevator or throttling code. That would require elevaotor_exit()
+ *     and blk_throtl_exit() to be called with queue lock initialized.
+ *
  */
 void blk_sync_queue(struct request_queue *q)
 {
-	del_timer_sync(&q->unplug_timer);
 	del_timer_sync(&q->timeout);
-	cancel_work_sync(&q->unplug_work);
-	throtl_shutdown_timer_wq(q);
+	cancel_delayed_work_sync(&q->delay_work);
+	queue_sync_plugs(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
 /**
  * __blk_run_queue - run a single device queue
  * @q:	The queue to run
+ * @force_kblockd: Don't run @q->request_fn directly.  Use kblockd.
  *
  * Description:
  *    See @blk_run_queue. This variant must be called with the queue lock
  *    held and interrupts disabled.
  *
  */
-void __blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q, bool force_kblockd)
 {
-	blk_remove_plug(q);
-
 	if (unlikely(blk_queue_stopped(q)))
 		return;
 
-	if (elv_queue_empty(q))
-		return;
-
 	/*
 	 * Only recurse once to avoid overrunning the stack, let the unplug
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
-	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+	if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
 		q->request_fn(q);
 		queue_flag_clear(QUEUE_FLAG_REENTER, q);
-	} else {
-		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
-		kblockd_schedule_work(q, &q->unplug_work);
-	}
+	} else
+		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
@@ -446,7 +342,7 @@ void blk_run_queue(struct request_queue *q)
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_run_queue(q);
+	__blk_run_queue(q, false);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -456,6 +352,11 @@ void blk_put_queue(struct request_queue *q)
 	kobject_put(&q->kobj);
 }
 
+/*
+ * Note: If a driver supplied the queue lock, it should not zap that lock
+ * unexpectedly as some queue cleanup components like elevator_exit() and
+ * blk_throtl_exit() need queue lock.
+ */
 void blk_cleanup_queue(struct request_queue *q)
 {
 	/*
@@ -474,6 +375,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	if (q->elevator)
 		elevator_exit(q->elevator);
 
+	blk_throtl_exit(q);
+
 	blk_put_queue(q);
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
@@ -516,8 +419,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q)
 		return NULL;
 
-	q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
-	q->backing_dev_info.unplug_io_data = q;
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
@@ -537,17 +438,24 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
-	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
-	INIT_LIST_HEAD(&q->pending_flushes);
-	INIT_WORK(&q->unplug_work, blk_unplug_work);
+	INIT_LIST_HEAD(&q->flush_queue[0]);
+	INIT_LIST_HEAD(&q->flush_queue[1]);
+	INIT_LIST_HEAD(&q->flush_data_in_flight);
+	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
 	mutex_init(&q->sysfs_lock);
 	spin_lock_init(&q->__queue_lock);
 
+	/*
+	 * By default initialize queue_lock to internal lock and driver can
+	 * override it later if need be.
+	 */
+	q->queue_lock = &q->__queue_lock;
+
 	return q;
 }
 EXPORT_SYMBOL(blk_alloc_queue_node);
@@ -630,9 +538,11 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
-	q->unplug_fn		= generic_unplug_device;
 	q->queue_flags		= QUEUE_FLAG_DEFAULT;
-	q->queue_lock		= lock;
+
+	/* Override internal queue lock with supplied lock pointer */
+	if (lock)
+		q->queue_lock		= lock;
 
 	/*
 	 * This also sets hw/phys segments, boundary and size
@@ -665,6 +575,8 @@ int blk_get_queue(struct request_queue *q)
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
+	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
+
 	if (rq->cmd_flags & REQ_ELVPRIV)
 		elv_put_request(q, rq);
 	mempool_free(rq, q->rq.rq_pool);
@@ -761,6 +673,25 @@ static void freed_request(struct request_queue *q, int sync, int priv)
 }
 
 /*
+ * Determine if elevator data should be initialized when allocating the
+ * request associated with @bio.
+ */
+static bool blk_rq_should_init_elevator(struct bio *bio)
+{
+	if (!bio)
+		return true;
+
+	/*
+	 * Flush requests do not use the elevator so skip initialization.
+	 * This allows a request to share the flush and elevator data.
+	 */
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+		return false;
+
+	return true;
+}
+
+/*
  * Get a free request, queue_lock must be held.
  * Returns NULL on failure, with queue_lock held.
  * Returns !NULL on success, with queue_lock *not held*.
@@ -772,7 +703,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	struct request_list *rl = &q->rq;
 	struct io_context *ioc = NULL;
 	const bool is_sync = rw_is_sync(rw_flags) != 0;
-	int may_queue, priv;
+	int may_queue, priv = 0;
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
@@ -816,9 +747,11 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	rl->count[is_sync]++;
 	rl->starved[is_sync] = 0;
 
-	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
-	if (priv)
-		rl->elvpriv++;
+	if (blk_rq_should_init_elevator(bio)) {
+		priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+		if (priv)
+			rl->elvpriv++;
+	}
 
 	if (blk_queue_io_stat(q))
 		rw_flags |= REQ_IO_STAT;
@@ -865,8 +798,8 @@ out:
 }
 
 /*
- * No available requests for this queue, unplug the device and wait for some
- * requests to become available.
+ * No available requests for this queue, wait for some requests to become
+ * available.
  *
  * Called with q->queue_lock held, and returns with it unlocked.
  */
@@ -887,7 +820,6 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags,
 
 		trace_block_sleeprq(q, bio, rw_flags & 1);
 
-		__generic_unplug_device(q);
 		spin_unlock_irq(q->queue_lock);
 		io_schedule();
 
@@ -1009,6 +941,13 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_requeue_request);
 
+static void add_acct_request(struct request_queue *q, struct request *rq,
+			     int where)
+{
+	drive_stat_acct(rq, 1);
+	__elv_add_request(q, rq, where);
+}
+
 /**
  * blk_insert_request - insert a special request into a request queue
  * @q:		request queue where request should be inserted
@@ -1051,9 +990,8 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 	if (blk_rq_tagged(rq))
 		blk_queue_end_tag(q, rq);
 
-	drive_stat_acct(rq, 1);
-	__elv_add_request(q, rq, where, 0);
-	__blk_run_queue(q);
+	add_acct_request(q, rq, where);
+	__blk_run_queue(q, false);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
@@ -1173,6 +1111,113 @@ void blk_add_request_payload(struct request *rq, struct page *page,
 }
 EXPORT_SYMBOL_GPL(blk_add_request_payload);
 
+static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
+				   struct bio *bio)
+{
+	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+
+	/*
+	 * Debug stuff, kill later
+	 */
+	if (!rq_mergeable(req)) {
+		blk_dump_rq_flags(req, "back");
+		return false;
+	}
+
+	if (!ll_back_merge_fn(q, req, bio))
+		return false;
+
+	trace_block_bio_backmerge(q, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+
+	drive_stat_acct(req, 0);
+	return true;
+}
+
+static bool bio_attempt_front_merge(struct request_queue *q,
+				    struct request *req, struct bio *bio)
+{
+	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	sector_t sector;
+
+	/*
+	 * Debug stuff, kill later
+	 */
+	if (!rq_mergeable(req)) {
+		blk_dump_rq_flags(req, "front");
+		return false;
+	}
+
+	if (!ll_front_merge_fn(q, req, bio))
+		return false;
+
+	trace_block_bio_frontmerge(q, bio);
+
+	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+		blk_rq_set_mixed_merge(req);
+
+	sector = bio->bi_sector;
+
+	bio->bi_next = req->bio;
+	req->bio = bio;
+
+	/*
+	 * may not be valid. if the low level driver said
+	 * it didn't need a bounce buffer then it better
+	 * not touch req->buffer either...
+	 */
+	req->buffer = bio_data(bio);
+	req->__sector = bio->bi_sector;
+	req->__data_len += bio->bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+
+	drive_stat_acct(req, 0);
+	return true;
+}
+
+/*
+ * Attempts to merge with the plugged list in the current process. Returns
+ * true if merge was succesful, otherwise false.
+ */
+static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
+			       struct bio *bio)
+{
+	struct blk_plug *plug;
+	struct request *rq;
+	bool ret = false;
+
+	plug = tsk->plug;
+	if (!plug)
+		goto out;
+
+	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
+		int el_ret;
+
+		if (rq->q != q)
+			continue;
+
+		el_ret = elv_try_merge(rq, bio);
+		if (el_ret == ELEVATOR_BACK_MERGE) {
+			ret = bio_attempt_back_merge(q, rq, bio);
+			if (ret)
+				break;
+		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+			ret = bio_attempt_front_merge(q, rq, bio);
+			if (ret)
+				break;
+		}
+	}
+out:
+	return ret;
+}
+
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cpu = bio->bi_comp_cpu;
@@ -1188,26 +1233,12 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
-/*
- * Only disabling plugging for non-rotational devices if it does tagging
- * as well, otherwise we do need the proper merging
- */
-static inline bool queue_should_plug(struct request_queue *q)
-{
-	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
-}
-
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
-	struct request *req;
-	int el_ret;
-	unsigned int bytes = bio->bi_size;
-	const unsigned short prio = bio_prio(bio);
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
-	const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
-	const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
-	int where = ELEVATOR_INSERT_SORT;
-	int rw_flags;
+	struct blk_plug *plug;
+	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
+	struct request *req;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1216,78 +1247,36 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	 */
 	blk_queue_bounce(q, &bio);
 
-	spin_lock_irq(q->queue_lock);
-
 	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
-		where = ELEVATOR_INSERT_FRONT;
+		spin_lock_irq(q->queue_lock);
+		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
 	}
 
-	if (elv_queue_empty(q))
-		goto get_rq;
-
-	el_ret = elv_merge(q, &req, bio);
-	switch (el_ret) {
-	case ELEVATOR_BACK_MERGE:
-		BUG_ON(!rq_mergeable(req));
-
-		if (!ll_back_merge_fn(q, req, bio))
-			break;
-
-		trace_block_bio_backmerge(q, bio);
-
-		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
-			blk_rq_set_mixed_merge(req);
-
-		req->biotail->bi_next = bio;
-		req->biotail = bio;
-		req->__data_len += bytes;
-		req->ioprio = ioprio_best(req->ioprio, prio);
-		if (!blk_rq_cpu_valid(req))
-			req->cpu = bio->bi_comp_cpu;
-		drive_stat_acct(req, 0);
-		elv_bio_merged(q, req, bio);
-		if (!attempt_back_merge(q, req))
-			elv_merged_request(q, req, el_ret);
+	/*
+	 * Check if we can merge with the plugged list before grabbing
+	 * any locks.
+	 */
+	if (attempt_plug_merge(current, q, bio))
 		goto out;
 
-	case ELEVATOR_FRONT_MERGE:
-		BUG_ON(!rq_mergeable(req));
-
-		if (!ll_front_merge_fn(q, req, bio))
-			break;
-
-		trace_block_bio_frontmerge(q, bio);
+	spin_lock_irq(q->queue_lock);
 
-		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
-			blk_rq_set_mixed_merge(req);
-			req->cmd_flags &= ~REQ_FAILFAST_MASK;
-			req->cmd_flags |= ff;
+	el_ret = elv_merge(q, &req, bio);
+	if (el_ret == ELEVATOR_BACK_MERGE) {
+		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
+		if (bio_attempt_back_merge(q, req, bio)) {
+			if (!attempt_back_merge(q, req))
+				elv_merged_request(q, req, el_ret);
+			goto out_unlock;
+		}
+	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
+		if (bio_attempt_front_merge(q, req, bio)) {
+			if (!attempt_front_merge(q, req))
+				elv_merged_request(q, req, el_ret);
+			goto out_unlock;
 		}
-
-		bio->bi_next = req->bio;
-		req->bio = bio;
-
-		/*
-		 * may not be valid. if the low level driver said
-		 * it didn't need a bounce buffer then it better
-		 * not touch req->buffer either...
-		 */
-		req->buffer = bio_data(bio);
-		req->__sector = bio->bi_sector;
-		req->__data_len += bytes;
-		req->ioprio = ioprio_best(req->ioprio, prio);
-		if (!blk_rq_cpu_valid(req))
-			req->cpu = bio->bi_comp_cpu;
-		drive_stat_acct(req, 0);
-		elv_bio_merged(q, req, bio);
-		if (!attempt_front_merge(q, req))
-			elv_merged_request(q, req, el_ret);
-		goto out;
-
-	/* ELV_NO_MERGE: elevator says don't/can't merge. */
-	default:
-		;
 	}
 
 get_rq:
@@ -1314,20 +1303,35 @@ get_rq:
 	 */
 	init_request_from_bio(req, bio);
 
-	spin_lock_irq(q->queue_lock);
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
-	    bio_flagged(bio, BIO_CPU_AFFINE))
-		req->cpu = blk_cpu_to_group(smp_processor_id());
-	if (queue_should_plug(q) && elv_queue_empty(q))
-		blk_plug_device(q);
-
-	/* insert the request into the elevator */
-	drive_stat_acct(req, 1);
-	__elv_add_request(q, req, where, 0);
+	    bio_flagged(bio, BIO_CPU_AFFINE)) {
+		req->cpu = blk_cpu_to_group(get_cpu());
+		put_cpu();
+	}
+
+	plug = current->plug;
+	if (plug) {
+		if (!plug->should_sort && !list_empty(&plug->list)) {
+			struct request *__rq;
+
+			__rq = list_entry_rq(plug->list.prev);
+			if (__rq->q != q)
+				plug->should_sort = 1;
+		}
+		/*
+		 * Debug flag, kill later
+		 */
+		req->cmd_flags |= REQ_ON_PLUG;
+		list_add_tail(&req->queuelist, &plug->list);
+		drive_stat_acct(req, 1);
+	} else {
+		spin_lock_irq(q->queue_lock);
+		add_acct_request(q, req, where);
+		__blk_run_queue(q, false);
+out_unlock:
+		spin_unlock_irq(q->queue_lock);
+	}
 out:
-	if (unplug || !queue_should_plug(q))
-		__generic_unplug_device(q);
-	spin_unlock_irq(q->queue_lock);
 	return 0;
 }
 
@@ -1730,9 +1734,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	drive_stat_acct(rq, 1);
-	__elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
-
+	add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
@@ -1804,7 +1806,7 @@ static void blk_account_io_done(struct request *req)
 	 * normal IO on queueing nor completion.  Accounting the
 	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
+	if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
@@ -2044,9 +2046,26 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 
 	if (error && req->cmd_type == REQ_TYPE_FS &&
 	    !(req->cmd_flags & REQ_QUIET)) {
-		printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
-				req->rq_disk ? req->rq_disk->disk_name : "?",
-				(unsigned long long)blk_rq_pos(req));
+		char *error_type;
+
+		switch (error) {
+		case -ENOLINK:
+			error_type = "recoverable transport";
+			break;
+		case -EREMOTEIO:
+			error_type = "critical target";
+			break;
+		case -EBADE:
+			error_type = "critical nexus";
+			break;
+		case -EIO:
+		default:
+			error_type = "I/O";
+			break;
+		}
+		printk(KERN_ERR "end_request: %s error, dev %s, sector %llu\n",
+		       error_type, req->rq_disk ? req->rq_disk->disk_name : "?",
+		       (unsigned long long)blk_rq_pos(req));
 	}
 
 	blk_account_io_completion(req, nr_bytes);
@@ -2617,6 +2636,106 @@ int kblockd_schedule_delayed_work(struct request_queue *q,
 }
 EXPORT_SYMBOL(kblockd_schedule_delayed_work);
 
+#define PLUG_MAGIC	0x91827364
+
+void blk_start_plug(struct blk_plug *plug)
+{
+	struct task_struct *tsk = current;
+
+	plug->magic = PLUG_MAGIC;
+	INIT_LIST_HEAD(&plug->list);
+	plug->should_sort = 0;
+
+	/*
+	 * If this is a nested plug, don't actually assign it. It will be
+	 * flushed on its own.
+	 */
+	if (!tsk->plug) {
+		/*
+		 * Store ordering should not be needed here, since a potential
+		 * preempt will imply a full memory barrier
+		 */
+		tsk->plug = plug;
+	}
+}
+EXPORT_SYMBOL(blk_start_plug);
+
+static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct request *rqa = container_of(a, struct request, queuelist);
+	struct request *rqb = container_of(b, struct request, queuelist);
+
+	return !(rqa->q == rqb->q);
+}
+
+static void flush_plug_list(struct blk_plug *plug)
+{
+	struct request_queue *q;
+	unsigned long flags;
+	struct request *rq;
+
+	BUG_ON(plug->magic != PLUG_MAGIC);
+
+	if (list_empty(&plug->list))
+		return;
+
+	if (plug->should_sort)
+		list_sort(NULL, &plug->list, plug_rq_cmp);
+
+	q = NULL;
+	local_irq_save(flags);
+	while (!list_empty(&plug->list)) {
+		rq = list_entry_rq(plug->list.next);
+		list_del_init(&rq->queuelist);
+		BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
+		BUG_ON(!rq->q);
+		if (rq->q != q) {
+			if (q) {
+				__blk_run_queue(q, false);
+				spin_unlock(q->queue_lock);
+			}
+			q = rq->q;
+			spin_lock(q->queue_lock);
+		}
+		rq->cmd_flags &= ~REQ_ON_PLUG;
+
+		/*
+		 * rq is already accounted, so use raw insert
+		 */
+		__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
+	}
+
+	if (q) {
+		__blk_run_queue(q, false);
+		spin_unlock(q->queue_lock);
+	}
+
+	BUG_ON(!list_empty(&plug->list));
+	local_irq_restore(flags);
+}
+
+static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug)
+{
+	flush_plug_list(plug);
+
+	if (plug == tsk->plug)
+		tsk->plug = NULL;
+}
+
+void blk_finish_plug(struct blk_plug *plug)
+{
+	if (plug)
+		__blk_finish_plug(current, plug);
+}
+EXPORT_SYMBOL(blk_finish_plug);
+
+void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug)
+{
+	__blk_finish_plug(tsk, plug);
+	tsk->plug = plug;
+}
+EXPORT_SYMBOL(__blk_flush_plug);
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
diff --git a/block/blk-exec.c b/block/blk-exec.c
index cf1456a02acd..7482b7fa863b 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -54,8 +54,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->end_io = done;
 	WARN_ON(irqs_disabled());
 	spin_lock_irq(q->queue_lock);
-	__elv_add_request(q, rq, where, 1);
-	__generic_unplug_device(q);
+	__elv_add_request(q, rq, where);
+	__blk_run_queue(q, false);
 	/* the queue is stopped so it won't be plugged+unplugged */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 54b123d6563e..93d5fd8e51eb 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -1,6 +1,69 @@
 /*
  * Functions to sequence FLUSH and FUA writes.
+ *
+ * Copyright (C) 2011		Max Planck Institute for Gravitational Physics
+ * Copyright (C) 2011		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * REQ_{FLUSH|FUA} requests are decomposed to sequences consisted of three
+ * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
+ * properties and hardware capability.
+ *
+ * If a request doesn't have data, only REQ_FLUSH makes sense, which
+ * indicates a simple flush request.  If there is data, REQ_FLUSH indicates
+ * that the device cache should be flushed before the data is executed, and
+ * REQ_FUA means that the data must be on non-volatile media on request
+ * completion.
+ *
+ * If the device doesn't have writeback cache, FLUSH and FUA don't make any
+ * difference.  The requests are either completed immediately if there's no
+ * data or executed as normal requests otherwise.
+ *
+ * If the device has writeback cache and supports FUA, REQ_FLUSH is
+ * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
+ *
+ * If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
+ * translated to PREFLUSH and REQ_FUA to POSTFLUSH.
+ *
+ * The actual execution of flush is double buffered.  Whenever a request
+ * needs to execute PRE or POSTFLUSH, it queues at
+ * q->flush_queue[q->flush_pending_idx].  Once certain criteria are met, a
+ * flush is issued and the pending_idx is toggled.  When the flush
+ * completes, all the requests which were pending are proceeded to the next
+ * step.  This allows arbitrary merging of different types of FLUSH/FUA
+ * requests.
+ *
+ * Currently, the following conditions are used to determine when to issue
+ * flush.
+ *
+ * C1. At any given time, only one flush shall be in progress.  This makes
+ *     double buffering sufficient.
+ *
+ * C2. Flush is deferred if any request is executing DATA of its sequence.
+ *     This avoids issuing separate POSTFLUSHes for requests which shared
+ *     PREFLUSH.
+ *
+ * C3. The second condition is ignored if there is a request which has
+ *     waited longer than FLUSH_PENDING_TIMEOUT.  This is to avoid
+ *     starvation in the unlikely case where there are continuous stream of
+ *     FUA (without FLUSH) requests.
+ *
+ * For devices which support FUA, it isn't clear whether C2 (and thus C3)
+ * is beneficial.
+ *
+ * Note that a sequenced FLUSH/FUA request with DATA is completed twice.
+ * Once while executing DATA and again after the whole sequence is
+ * complete.  The first completion updates the contained bio but doesn't
+ * finish it so that the bio submitter is notified only after the whole
+ * sequence is complete.  This is implemented by testing REQ_FLUSH_SEQ in
+ * req_bio_endio().
+ *
+ * The above peculiarity requires that each FLUSH/FUA request has only one
+ * bio attached to it, which is guaranteed as they aren't allowed to be
+ * merged in the usual way.
  */
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/bio.h>
@@ -11,184 +74,296 @@
 
 /* FLUSH/FUA sequences */
 enum {
-	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
-	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
-	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
-	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
-	QUEUE_FSEQ_DONE		= (1 << 4),
+	REQ_FSEQ_PREFLUSH	= (1 << 0), /* pre-flushing in progress */
+	REQ_FSEQ_DATA		= (1 << 1), /* data write in progress */
+	REQ_FSEQ_POSTFLUSH	= (1 << 2), /* post-flushing in progress */
+	REQ_FSEQ_DONE		= (1 << 3),
+
+	REQ_FSEQ_ACTIONS	= REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA |
+				  REQ_FSEQ_POSTFLUSH,
+
+	/*
+	 * If flush has been pending longer than the following timeout,
+	 * it's issued even if flush_data requests are still in flight.
+	 */
+	FLUSH_PENDING_TIMEOUT	= 5 * HZ,
 };
 
-static struct request *queue_next_fseq(struct request_queue *q);
+static bool blk_kick_flush(struct request_queue *q);
 
-unsigned blk_flush_cur_seq(struct request_queue *q)
+static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
 {
-	if (!q->flush_seq)
-		return 0;
-	return 1 << ffz(q->flush_seq);
+	unsigned int policy = 0;
+
+	if (fflags & REQ_FLUSH) {
+		if (rq->cmd_flags & REQ_FLUSH)
+			policy |= REQ_FSEQ_PREFLUSH;
+		if (blk_rq_sectors(rq))
+			policy |= REQ_FSEQ_DATA;
+		if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
+			policy |= REQ_FSEQ_POSTFLUSH;
+	}
+	return policy;
 }
 
-static struct request *blk_flush_complete_seq(struct request_queue *q,
-					      unsigned seq, int error)
+static unsigned int blk_flush_cur_seq(struct request *rq)
 {
-	struct request *next_rq = NULL;
-
-	if (error && !q->flush_err)
-		q->flush_err = error;
-
-	BUG_ON(q->flush_seq & seq);
-	q->flush_seq |= seq;
-
-	if (blk_flush_cur_seq(q) != QUEUE_FSEQ_DONE) {
-		/* not complete yet, queue the next flush sequence */
-		next_rq = queue_next_fseq(q);
-	} else {
-		/* complete this flush request */
-		__blk_end_request_all(q->orig_flush_rq, q->flush_err);
-		q->orig_flush_rq = NULL;
-		q->flush_seq = 0;
-
-		/* dispatch the next flush if there's one */
-		if (!list_empty(&q->pending_flushes)) {
-			next_rq = list_entry_rq(q->pending_flushes.next);
-			list_move(&next_rq->queuelist, &q->queue_head);
-		}
+	return 1 << ffz(rq->flush.seq);
+}
+
+static void blk_flush_restore_request(struct request *rq)
+{
+	/*
+	 * After flush data completion, @rq->bio is %NULL but we need to
+	 * complete the bio again.  @rq->biotail is guaranteed to equal the
+	 * original @rq->bio.  Restore it.
+	 */
+	rq->bio = rq->biotail;
+
+	/* make @rq a normal request */
+	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
+	rq->end_io = NULL;
+}
+
+/**
+ * blk_flush_complete_seq - complete flush sequence
+ * @rq: FLUSH/FUA request being sequenced
+ * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero)
+ * @error: whether an error occurred
+ *
+ * @rq just completed @seq part of its flush sequence, record the
+ * completion and trigger the next step.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ *
+ * RETURNS:
+ * %true if requests were added to the dispatch queue, %false otherwise.
+ */
+static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
+				   int error)
+{
+	struct request_queue *q = rq->q;
+	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	bool queued = false;
+
+	BUG_ON(rq->flush.seq & seq);
+	rq->flush.seq |= seq;
+
+	if (likely(!error))
+		seq = blk_flush_cur_seq(rq);
+	else
+		seq = REQ_FSEQ_DONE;
+
+	switch (seq) {
+	case REQ_FSEQ_PREFLUSH:
+	case REQ_FSEQ_POSTFLUSH:
+		/* queue for flush */
+		if (list_empty(pending))
+			q->flush_pending_since = jiffies;
+		list_move_tail(&rq->flush.list, pending);
+		break;
+
+	case REQ_FSEQ_DATA:
+		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
+		list_add(&rq->queuelist, &q->queue_head);
+		queued = true;
+		break;
+
+	case REQ_FSEQ_DONE:
+		/*
+		 * @rq was previously adjusted by blk_flush_issue() for
+		 * flush sequencing and may already have gone through the
+		 * flush data request completion path.  Restore @rq for
+		 * normal completion and end it.
+		 */
+		BUG_ON(!list_empty(&rq->queuelist));
+		list_del_init(&rq->flush.list);
+		blk_flush_restore_request(rq);
+		__blk_end_request_all(rq, error);
+		break;
+
+	default:
+		BUG();
 	}
-	return next_rq;
+
+	return blk_kick_flush(q) | queued;
 }
 
-static void blk_flush_complete_seq_end_io(struct request_queue *q,
-					  unsigned seq, int error)
+static void flush_end_io(struct request *flush_rq, int error)
 {
-	bool was_empty = elv_queue_empty(q);
-	struct request *next_rq;
+	struct request_queue *q = flush_rq->q;
+	struct list_head *running = &q->flush_queue[q->flush_running_idx];
+	bool queued = false;
+	struct request *rq, *n;
+
+	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
+
+	/* account completion of the flush request */
+	q->flush_running_idx ^= 1;
+	elv_completed_request(q, flush_rq);
 
-	next_rq = blk_flush_complete_seq(q, seq, error);
+	/* and push the waiting requests to the next stage */
+	list_for_each_entry_safe(rq, n, running, flush.list) {
+		unsigned int seq = blk_flush_cur_seq(rq);
+
+		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
+		queued |= blk_flush_complete_seq(rq, seq, error);
+	}
 
 	/*
 	 * Moving a request silently to empty queue_head may stall the
-	 * queue.  Kick the queue in those cases.
+	 * queue.  Kick the queue in those cases.  This function is called
+	 * from request completion path and calling directly into
+	 * request_fn may confuse the driver.  Always use kblockd.
 	 */
-	if (was_empty && next_rq)
-		__blk_run_queue(q);
+	if (queued)
+		__blk_run_queue(q, true);
 }
 
-static void pre_flush_end_io(struct request *rq, int error)
+/**
+ * blk_kick_flush - consider issuing flush request
+ * @q: request_queue being kicked
+ *
+ * Flush related states of @q have changed, consider issuing flush request.
+ * Please read the comment at the top of this file for more info.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ *
+ * RETURNS:
+ * %true if flush was issued, %false otherwise.
+ */
+static bool blk_kick_flush(struct request_queue *q)
 {
-	elv_completed_request(rq->q, rq);
-	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_PREFLUSH, error);
+	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	struct request *first_rq =
+		list_first_entry(pending, struct request, flush.list);
+
+	/* C1 described at the top of this file */
+	if (q->flush_pending_idx != q->flush_running_idx || list_empty(pending))
+		return false;
+
+	/* C2 and C3 */
+	if (!list_empty(&q->flush_data_in_flight) &&
+	    time_before(jiffies,
+			q->flush_pending_since + FLUSH_PENDING_TIMEOUT))
+		return false;
+
+	/*
+	 * Issue flush and toggle pending_idx.  This makes pending_idx
+	 * different from running_idx, which means flush is in flight.
+	 */
+	blk_rq_init(q, &q->flush_rq);
+	q->flush_rq.cmd_type = REQ_TYPE_FS;
+	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	q->flush_rq.rq_disk = first_rq->rq_disk;
+	q->flush_rq.end_io = flush_end_io;
+
+	q->flush_pending_idx ^= 1;
+	elv_insert(q, &q->flush_rq, ELEVATOR_INSERT_REQUEUE);
+	return true;
 }
 
 static void flush_data_end_io(struct request *rq, int error)
 {
-	elv_completed_request(rq->q, rq);
-	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_DATA, error);
-}
+	struct request_queue *q = rq->q;
 
-static void post_flush_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
+	/*
+	 * After populating an empty queue, kick it to avoid stall.  Read
+	 * the comment in flush_end_io().
+	 */
+	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
+		__blk_run_queue(q, true);
 }
 
-static void init_flush_request(struct request *rq, struct gendisk *disk)
+/**
+ * blk_insert_flush - insert a new FLUSH/FUA request
+ * @rq: request to insert
+ *
+ * To be called from elv_insert() for %ELEVATOR_INSERT_FLUSH insertions.
+ * @rq is being submitted.  Analyze what needs to be done and put it on the
+ * right queue.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ */
+void blk_insert_flush(struct request *rq)
 {
-	rq->cmd_type = REQ_TYPE_FS;
-	rq->cmd_flags = WRITE_FLUSH;
-	rq->rq_disk = disk;
-}
+	struct request_queue *q = rq->q;
+	unsigned int fflags = q->flush_flags;	/* may change, cache */
+	unsigned int policy = blk_flush_policy(fflags, rq);
 
-static struct request *queue_next_fseq(struct request_queue *q)
-{
-	struct request *orig_rq = q->orig_flush_rq;
-	struct request *rq = &q->flush_rq;
+	BUG_ON(rq->end_io);
+	BUG_ON(!rq->bio || rq->bio != rq->biotail);
 
-	blk_rq_init(q, rq);
+	/*
+	 * @policy now records what operations need to be done.  Adjust
+	 * REQ_FLUSH and FUA for the driver.
+	 */
+	rq->cmd_flags &= ~REQ_FLUSH;
+	if (!(fflags & REQ_FUA))
+		rq->cmd_flags &= ~REQ_FUA;
 
-	switch (blk_flush_cur_seq(q)) {
-	case QUEUE_FSEQ_PREFLUSH:
-		init_flush_request(rq, orig_rq->rq_disk);
-		rq->end_io = pre_flush_end_io;
-		break;
-	case QUEUE_FSEQ_DATA:
-		init_request_from_bio(rq, orig_rq->bio);
-		/*
-		 * orig_rq->rq_disk may be different from
-		 * bio->bi_bdev->bd_disk if orig_rq got here through
-		 * remapping drivers.  Make sure rq->rq_disk points
-		 * to the same one as orig_rq.
-		 */
-		rq->rq_disk = orig_rq->rq_disk;
-		rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA);
-		rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA);
-		rq->end_io = flush_data_end_io;
-		break;
-	case QUEUE_FSEQ_POSTFLUSH:
-		init_flush_request(rq, orig_rq->rq_disk);
-		rq->end_io = post_flush_end_io;
-		break;
-	default:
-		BUG();
+	/*
+	 * If there's data but flush is not necessary, the request can be
+	 * processed directly without going through flush machinery.  Queue
+	 * for normal execution.
+	 */
+	if ((policy & REQ_FSEQ_DATA) &&
+	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
+		list_add(&rq->queuelist, &q->queue_head);
+		return;
 	}
 
-	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-	return rq;
+	/*
+	 * @rq should go through flush machinery.  Mark it part of flush
+	 * sequence and submit for further processing.
+	 */
+	memset(&rq->flush, 0, sizeof(rq->flush));
+	INIT_LIST_HEAD(&rq->flush.list);
+	rq->cmd_flags |= REQ_FLUSH_SEQ;
+	rq->end_io = flush_data_end_io;
+
+	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
 }
 
-struct request *blk_do_flush(struct request_queue *q, struct request *rq)
+/**
+ * blk_abort_flushes - @q is being aborted, abort flush requests
+ * @q: request_queue being aborted
+ *
+ * To be called from elv_abort_queue().  @q is being aborted.  Prepare all
+ * FLUSH/FUA requests for abortion.
+ *
+ * CONTEXT:
+ * spin_lock_irq(q->queue_lock)
+ */
+void blk_abort_flushes(struct request_queue *q)
 {
-	unsigned int fflags = q->flush_flags; /* may change, cache it */
-	bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA;
-	bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH);
-	bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA);
-	unsigned skip = 0;
+	struct request *rq, *n;
+	int i;
 
 	/*
-	 * Special case.  If there's data but flush is not necessary,
-	 * the request can be issued directly.
-	 *
-	 * Flush w/o data should be able to be issued directly too but
-	 * currently some drivers assume that rq->bio contains
-	 * non-zero data if it isn't NULL and empty FLUSH requests
-	 * getting here usually have bio's without data.
+	 * Requests in flight for data are already owned by the dispatch
+	 * queue or the device driver.  Just restore for normal completion.
 	 */
-	if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) {
-		rq->cmd_flags &= ~REQ_FLUSH;
-		if (!has_fua)
-			rq->cmd_flags &= ~REQ_FUA;
-		return rq;
+	list_for_each_entry_safe(rq, n, &q->flush_data_in_flight, flush.list) {
+		list_del_init(&rq->flush.list);
+		blk_flush_restore_request(rq);
 	}
 
 	/*
-	 * Sequenced flushes can't be processed in parallel.  If
-	 * another one is already in progress, queue for later
-	 * processing.
+	 * We need to give away requests on flush queues.  Restore for
+	 * normal completion and put them on the dispatch queue.
 	 */
-	if (q->flush_seq) {
-		list_move_tail(&rq->queuelist, &q->pending_flushes);
-		return NULL;
+	for (i = 0; i < ARRAY_SIZE(q->flush_queue); i++) {
+		list_for_each_entry_safe(rq, n, &q->flush_queue[i],
+					 flush.list) {
+			list_del_init(&rq->flush.list);
+			blk_flush_restore_request(rq);
+			list_add_tail(&rq->queuelist, &q->queue_head);
+		}
 	}
-
-	/*
-	 * Start a new flush sequence
-	 */
-	q->flush_err = 0;
-	q->flush_seq |= QUEUE_FSEQ_STARTED;
-
-	/* adjust FLUSH/FUA of the original request and stash it away */
-	rq->cmd_flags &= ~REQ_FLUSH;
-	if (!has_fua)
-		rq->cmd_flags &= ~REQ_FUA;
-	blk_dequeue_request(rq);
-	q->orig_flush_rq = rq;
-
-	/* skip unneded sequences and return the first one */
-	if (!do_preflush)
-		skip |= QUEUE_FSEQ_PREFLUSH;
-	if (!blk_rq_sectors(rq))
-		skip |= QUEUE_FSEQ_DATA;
-	if (!do_postflush)
-		skip |= QUEUE_FSEQ_POSTFLUSH;
-	return blk_flush_complete_seq(q, skip, 0);
 }
 
 static void bio_end_flush(struct bio *bio, int err)
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 1a320d2406b0..25de73e4759b 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -109,7 +109,6 @@ struct bio_batch
 	atomic_t 		done;
 	unsigned long 		flags;
 	struct completion 	*wait;
-	bio_end_io_t		*end_io;
 };
 
 static void bio_batch_end_io(struct bio *bio, int err)
@@ -122,17 +121,14 @@ static void bio_batch_end_io(struct bio *bio, int err)
 		else
 			clear_bit(BIO_UPTODATE, &bb->flags);
 	}
-	if (bb) {
-		if (bb->end_io)
-			bb->end_io(bio, err);
-		atomic_inc(&bb->done);
-		complete(bb->wait);
-	}
+	if (bb)
+		if (atomic_dec_and_test(&bb->done))
+			complete(bb->wait);
 	bio_put(bio);
 }
 
 /**
- * blkdev_issue_zeroout generate number of zero filed write bios
+ * blkdev_issue_zeroout - generate number of zero filed write bios
  * @bdev:	blockdev to issue
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
@@ -140,8 +136,6 @@ static void bio_batch_end_io(struct bio *bio, int err)
  *
  * Description:
  *  Generate and issue number of bios with zerofiled pages.
- *  Send barrier at the beginning and at the end if requested. This guarantie
- *  correct request ordering. Empty barrier allow us to avoid post queue flush.
  */
 
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
@@ -150,13 +144,12 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	int ret;
 	struct bio *bio;
 	struct bio_batch bb;
-	unsigned int sz, issued = 0;
+	unsigned int sz;
 	DECLARE_COMPLETION_ONSTACK(wait);
 
-	atomic_set(&bb.done, 0);
+	atomic_set(&bb.done, 1);
 	bb.flags = 1 << BIO_UPTODATE;
 	bb.wait = &wait;
-	bb.end_io = NULL;
 
 submit:
 	ret = 0;
@@ -185,12 +178,12 @@ submit:
 				break;
 		}
 		ret = 0;
-		issued++;
+		atomic_inc(&bb.done);
 		submit_bio(WRITE, bio);
 	}
 
 	/* Wait for bios in-flight */
-	while (issued != atomic_read(&bb.done))
+	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion(&wait);
 
 	if (!test_bit(BIO_UPTODATE, &bb.flags))
diff --git a/block/blk-merge.c b/block/blk-merge.c
index ea85e20d5e94..cfcc37cb222b 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -465,3 +465,9 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
 
 	return 0;
 }
+
+int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
+			  struct request *next)
+{
+	return attempt_merge(q, rq, next);
+}
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 36c8c1f2af18..1fa769293597 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -164,25 +164,10 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	blk_queue_congestion_threshold(q);
 	q->nr_batching = BLK_BATCH_REQ;
 
-	q->unplug_thresh = 4;		/* hmm */
-	q->unplug_delay = msecs_to_jiffies(3);	/* 3 milliseconds */
-	if (q->unplug_delay == 0)
-		q->unplug_delay = 1;
-
-	q->unplug_timer.function = blk_unplug_timeout;
-	q->unplug_timer.data = (unsigned long)q;
-
 	blk_set_default_limits(&q->limits);
 	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
 
 	/*
-	 * If the caller didn't supply a lock, fall back to our embedded
-	 * per-queue locks
-	 */
-	if (!q->queue_lock)
-		q->queue_lock = &q->__queue_lock;
-
-	/*
 	 * by default assume old behaviour and bounce for any highmem page
 	 */
 	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 41fb69150b4d..261c75c665ae 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -471,8 +471,6 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_sync_queue(q);
 
-	blk_throtl_exit(q);
-
 	if (rl->rq_pool)
 		mempool_destroy(rl->rq_pool);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 381b09bb562b..5352bdafbcf0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -20,6 +20,11 @@ static int throtl_quantum = 32;
 /* Throttling is performed over 100ms slice and after that slice is renewed */
 static unsigned long throtl_slice = HZ/10;	/* 100 ms */
 
+/* A workqueue to queue throttle related work */
+static struct workqueue_struct *kthrotld_workqueue;
+static void throtl_schedule_delayed_work(struct throtl_data *td,
+				unsigned long delay);
+
 struct throtl_rb_root {
 	struct rb_root rb;
 	struct rb_node *left;
@@ -97,7 +102,7 @@ struct throtl_data
 	/* Work for dispatching throttled bios */
 	struct delayed_work throtl_work;
 
-	atomic_t limits_changed;
+	bool limits_changed;
 };
 
 enum tg_state_flags {
@@ -168,7 +173,15 @@ static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
 	 * tree of blkg (instead of traversing through hash list all
 	 * the time.
 	 */
-	tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+	/*
+	 * This is the common case when there are no blkio cgroups.
+ 	 * Avoid lookup in this case
+ 	 */
+	if (blkcg == &blkio_root_cgroup)
+		tg = &td->root_tg;
+	else
+		tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
 
 	/* Fill in device details for root group */
 	if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
@@ -188,6 +201,7 @@ static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
 	RB_CLEAR_NODE(&tg->rb_node);
 	bio_list_init(&tg->bio_lists[0]);
 	bio_list_init(&tg->bio_lists[1]);
+	td->limits_changed = false;
 
 	/*
 	 * Take the initial reference that will be released on destroy
@@ -337,10 +351,9 @@ static void throtl_schedule_next_dispatch(struct throtl_data *td)
 	update_min_dispatch_time(st);
 
 	if (time_before_eq(st->min_disptime, jiffies))
-		throtl_schedule_delayed_work(td->queue, 0);
+		throtl_schedule_delayed_work(td, 0);
 	else
-		throtl_schedule_delayed_work(td->queue,
-				(st->min_disptime - jiffies));
+		throtl_schedule_delayed_work(td, (st->min_disptime - jiffies));
 }
 
 static inline void
@@ -725,34 +738,36 @@ static void throtl_process_limit_change(struct throtl_data *td)
 	struct throtl_grp *tg;
 	struct hlist_node *pos, *n;
 
-	if (!atomic_read(&td->limits_changed))
+	if (!td->limits_changed)
 		return;
 
-	throtl_log(td, "limit changed =%d", atomic_read(&td->limits_changed));
+	xchg(&td->limits_changed, false);
 
-	/*
-	 * Make sure updates from throtl_update_blkio_group_read_bps() group
-	 * of functions to tg->limits_changed are visible. We do not
-	 * want update td->limits_changed to be visible but update to
-	 * tg->limits_changed not being visible yet on this cpu. Hence
-	 * the read barrier.
-	 */
-	smp_rmb();
+	throtl_log(td, "limits changed");
 
 	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
-		if (throtl_tg_on_rr(tg) && tg->limits_changed) {
-			throtl_log_tg(td, tg, "limit change rbps=%llu wbps=%llu"
-				" riops=%u wiops=%u", tg->bps[READ],
-				tg->bps[WRITE], tg->iops[READ],
-				tg->iops[WRITE]);
+		if (!tg->limits_changed)
+			continue;
+
+		if (!xchg(&tg->limits_changed, false))
+			continue;
+
+		throtl_log_tg(td, tg, "limit change rbps=%llu wbps=%llu"
+			" riops=%u wiops=%u", tg->bps[READ], tg->bps[WRITE],
+			tg->iops[READ], tg->iops[WRITE]);
+
+		/*
+		 * Restart the slices for both READ and WRITES. It
+		 * might happen that a group's limit are dropped
+		 * suddenly and we don't want to account recently
+		 * dispatched IO with new low rate
+		 */
+		throtl_start_new_slice(td, tg, 0);
+		throtl_start_new_slice(td, tg, 1);
+
+		if (throtl_tg_on_rr(tg))
 			tg_update_disptime(td, tg);
-			tg->limits_changed = false;
-		}
 	}
-
-	smp_mb__before_atomic_dec();
-	atomic_dec(&td->limits_changed);
-	smp_mb__after_atomic_dec();
 }
 
 /* Dispatch throttled bios. Should be called without queue lock held. */
@@ -762,6 +777,7 @@ static int throtl_dispatch(struct request_queue *q)
 	unsigned int nr_disp = 0;
 	struct bio_list bio_list_on_stack;
 	struct bio *bio;
+	struct blk_plug plug;
 
 	spin_lock_irq(q->queue_lock);
 
@@ -790,9 +806,10 @@ out:
 	 * immediate dispatch
 	 */
 	if (nr_disp) {
+		blk_start_plug(&plug);
 		while((bio = bio_list_pop(&bio_list_on_stack)))
 			generic_make_request(bio);
-		blk_unplug(q);
+		blk_finish_plug(&plug);
 	}
 	return nr_disp;
 }
@@ -807,24 +824,24 @@ void blk_throtl_work(struct work_struct *work)
 }
 
 /* Call with queue lock held */
-void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
+static void
+throtl_schedule_delayed_work(struct throtl_data *td, unsigned long delay)
 {
 
-	struct throtl_data *td = q->td;
 	struct delayed_work *dwork = &td->throtl_work;
 
-	if (total_nr_queued(td) > 0) {
+	/* schedule work if limits changed even if no bio is queued */
+	if (total_nr_queued(td) > 0 || td->limits_changed) {
 		/*
 		 * We might have a work scheduled to be executed in future.
 		 * Cancel that and schedule a new one.
 		 */
 		__cancel_delayed_work(dwork);
-		kblockd_schedule_delayed_work(q, dwork, delay);
+		queue_delayed_work(kthrotld_workqueue, dwork, delay);
 		throtl_log(td, "schedule work. delay=%lu jiffies=%lu",
 				delay, jiffies);
 	}
 }
-EXPORT_SYMBOL(throtl_schedule_delayed_work);
 
 static void
 throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
@@ -887,6 +904,15 @@ void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg)
 	spin_unlock_irqrestore(td->queue->queue_lock, flags);
 }
 
+static void throtl_update_blkio_group_common(struct throtl_data *td,
+				struct throtl_grp *tg)
+{
+	xchg(&tg->limits_changed, true);
+	xchg(&td->limits_changed, true);
+	/* Schedule a work now to process the limit change */
+	throtl_schedule_delayed_work(td, 0);
+}
+
 /*
  * For all update functions, key should be a valid pointer because these
  * update functions are called under blkcg_lock, that means, blkg is
@@ -900,64 +926,43 @@ static void throtl_update_blkio_group_read_bps(void *key,
 				struct blkio_group *blkg, u64 read_bps)
 {
 	struct throtl_data *td = key;
+	struct throtl_grp *tg = tg_of_blkg(blkg);
 
-	tg_of_blkg(blkg)->bps[READ] = read_bps;
-	/* Make sure read_bps is updated before setting limits_changed */
-	smp_wmb();
-	tg_of_blkg(blkg)->limits_changed = true;
-
-	/* Make sure tg->limits_changed is updated before td->limits_changed */
-	smp_mb__before_atomic_inc();
-	atomic_inc(&td->limits_changed);
-	smp_mb__after_atomic_inc();
-
-	/* Schedule a work now to process the limit change */
-	throtl_schedule_delayed_work(td->queue, 0);
+	tg->bps[READ] = read_bps;
+	throtl_update_blkio_group_common(td, tg);
 }
 
 static void throtl_update_blkio_group_write_bps(void *key,
 				struct blkio_group *blkg, u64 write_bps)
 {
 	struct throtl_data *td = key;
+	struct throtl_grp *tg = tg_of_blkg(blkg);
 
-	tg_of_blkg(blkg)->bps[WRITE] = write_bps;
-	smp_wmb();
-	tg_of_blkg(blkg)->limits_changed = true;
-	smp_mb__before_atomic_inc();
-	atomic_inc(&td->limits_changed);
-	smp_mb__after_atomic_inc();
-	throtl_schedule_delayed_work(td->queue, 0);
+	tg->bps[WRITE] = write_bps;
+	throtl_update_blkio_group_common(td, tg);
 }
 
 static void throtl_update_blkio_group_read_iops(void *key,
 			struct blkio_group *blkg, unsigned int read_iops)
 {
 	struct throtl_data *td = key;
+	struct throtl_grp *tg = tg_of_blkg(blkg);
 
-	tg_of_blkg(blkg)->iops[READ] = read_iops;
-	smp_wmb();
-	tg_of_blkg(blkg)->limits_changed = true;
-	smp_mb__before_atomic_inc();
-	atomic_inc(&td->limits_changed);
-	smp_mb__after_atomic_inc();
-	throtl_schedule_delayed_work(td->queue, 0);
+	tg->iops[READ] = read_iops;
+	throtl_update_blkio_group_common(td, tg);
 }
 
 static void throtl_update_blkio_group_write_iops(void *key,
 			struct blkio_group *blkg, unsigned int write_iops)
 {
 	struct throtl_data *td = key;
+	struct throtl_grp *tg = tg_of_blkg(blkg);
 
-	tg_of_blkg(blkg)->iops[WRITE] = write_iops;
-	smp_wmb();
-	tg_of_blkg(blkg)->limits_changed = true;
-	smp_mb__before_atomic_inc();
-	atomic_inc(&td->limits_changed);
-	smp_mb__after_atomic_inc();
-	throtl_schedule_delayed_work(td->queue, 0);
+	tg->iops[WRITE] = write_iops;
+	throtl_update_blkio_group_common(td, tg);
 }
 
-void throtl_shutdown_timer_wq(struct request_queue *q)
+static void throtl_shutdown_wq(struct request_queue *q)
 {
 	struct throtl_data *td = q->td;
 
@@ -998,20 +1003,28 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 		/*
 		 * There is already another bio queued in same dir. No
 		 * need to update dispatch time.
-		 * Still update the disptime if rate limits on this group
-		 * were changed.
 		 */
-		if (!tg->limits_changed)
-			update_disptime = false;
-		else
-			tg->limits_changed = false;
-
+		update_disptime = false;
 		goto queue_bio;
+
 	}
 
 	/* Bio is with-in rate limit of group */
 	if (tg_may_dispatch(td, tg, bio, NULL)) {
 		throtl_charge_bio(tg, bio);
+
+		/*
+		 * We need to trim slice even when bios are not being queued
+		 * otherwise it might happen that a bio is not queued for
+		 * a long time and slice keeps on extending and trim is not
+		 * called for a long time. Now if limits are reduced suddenly
+		 * we take into account all the IO dispatched so far at new
+		 * low rate and * newly queued IO gets a really long dispatch
+		 * time.
+		 *
+		 * So keep on trimming slice even if bio is not queued.
+		 */
+		throtl_trim_slice(td, tg, rw);
 		goto out;
 	}
 
@@ -1047,7 +1060,7 @@ int blk_throtl_init(struct request_queue *q)
 
 	INIT_HLIST_HEAD(&td->tg_list);
 	td->tg_service_tree = THROTL_RB_ROOT;
-	atomic_set(&td->limits_changed, 0);
+	td->limits_changed = false;
 
 	/* Init root group */
 	tg = &td->root_tg;
@@ -1059,6 +1072,7 @@ int blk_throtl_init(struct request_queue *q)
 	/* Practically unlimited BW */
 	tg->bps[0] = tg->bps[1] = -1;
 	tg->iops[0] = tg->iops[1] = -1;
+	td->limits_changed = false;
 
 	/*
 	 * Set root group reference to 2. One reference will be dropped when
@@ -1091,7 +1105,7 @@ void blk_throtl_exit(struct request_queue *q)
 
 	BUG_ON(!td);
 
-	throtl_shutdown_timer_wq(q);
+	throtl_shutdown_wq(q);
 
 	spin_lock_irq(q->queue_lock);
 	throtl_release_tgs(td);
@@ -1121,12 +1135,16 @@ void blk_throtl_exit(struct request_queue *q)
 	 * update limits through cgroup and another work got queued, cancel
 	 * it.
 	 */
-	throtl_shutdown_timer_wq(q);
+	throtl_shutdown_wq(q);
 	throtl_td_free(td);
 }
 
 static int __init throtl_init(void)
 {
+	kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
+	if (!kthrotld_workqueue)
+		panic("Failed to create kthrotld\n");
+
 	blkio_policy_register(&blkio_policy_throtl);
 	return 0;
 }
diff --git a/block/blk.h b/block/blk.h
index 2db8f32838e7..c8db371a921d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -18,8 +18,6 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 
-void blk_unplug_work(struct work_struct *work);
-void blk_unplug_timeout(unsigned long data);
 void blk_rq_timed_out_timer(unsigned long data);
 void blk_delete_timer(struct request *);
 void blk_add_timer(struct request *);
@@ -51,21 +49,17 @@ static inline void blk_clear_rq_complete(struct request *rq)
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
-struct request *blk_do_flush(struct request_queue *q, struct request *rq);
+void blk_insert_flush(struct request *rq);
+void blk_abort_flushes(struct request_queue *q);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
 
 	while (1) {
-		while (!list_empty(&q->queue_head)) {
+		if (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
-			if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) ||
-			    rq == &q->flush_rq)
-				return rq;
-			rq = blk_do_flush(q, rq);
-			if (rq)
-				return rq;
+			return rq;
 		}
 
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
@@ -109,6 +103,8 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 		      struct bio *bio);
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
+int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
+				struct request *next);
 void blk_recalc_rq_segments(struct request *rq);
 void blk_rq_set_mixed_merge(struct request *rq);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 501ffdf0399c..7785169f3c8f 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -54,9 +54,9 @@ static const int cfq_hist_divisor = 4;
 #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)
+	((struct cfq_io_context *) (rq)->elevator_private[0])
+#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private[1])
+#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private[2])
 
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
@@ -146,7 +146,6 @@ struct cfq_queue {
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
-	struct cfq_group *orig_cfqg;
 	/* Number of sectors dispatched from queue in single dispatch round */
 	unsigned long nr_sectors;
 };
@@ -179,6 +178,8 @@ struct cfq_group {
 	/* group service_tree key */
 	u64 vdisktime;
 	unsigned int weight;
+	unsigned int new_weight;
+	bool needs_update;
 
 	/* number of cfqq currently on this group */
 	int nr_cfqq;
@@ -238,6 +239,7 @@ struct cfq_data {
 	struct rb_root prio_trees[CFQ_PRIO_LISTS];
 
 	unsigned int busy_queues;
+	unsigned int busy_sync_queues;
 
 	int rq_in_driver;
 	int rq_in_flight[2];
@@ -285,7 +287,6 @@ struct cfq_data {
 	unsigned int cfq_slice_idle;
 	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
-	unsigned int cfq_group_isolation;
 
 	unsigned int cic_index;
 	struct list_head cic_list;
@@ -501,13 +502,6 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
 	}
 }
 
-static int cfq_queue_empty(struct request_queue *q)
-{
-	struct cfq_data *cfqd = q->elevator->elevator_data;
-
-	return !cfqd->rq_queued;
-}
-
 /*
  * Scale schedule slice based on io priority. Use the sync time slice only
  * if a queue is marked sync and has sync io queued. A sync queue with async
@@ -558,15 +552,13 @@ static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
 
 static void update_min_vdisktime(struct cfq_rb_root *st)
 {
-	u64 vdisktime = st->min_vdisktime;
 	struct cfq_group *cfqg;
 
 	if (st->left) {
 		cfqg = rb_entry_cfqg(st->left);
-		vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
+		st->min_vdisktime = max_vdisktime(st->min_vdisktime,
+						  cfqg->vdisktime);
 	}
-
-	st->min_vdisktime = max_vdisktime(st->min_vdisktime, vdisktime);
 }
 
 /*
@@ -599,7 +591,7 @@ cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
 }
 
 static inline unsigned
-cfq_scaled_group_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
 	if (cfqd->cfq_latency) {
@@ -631,7 +623,7 @@ cfq_scaled_group_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_scaled_group_slice(cfqd, cfqq);
+	unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
 
 	cfqq->slice_start = jiffies;
 	cfqq->slice_end = jiffies + slice;
@@ -863,7 +855,27 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 }
 
 static void
-cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
+cfq_update_group_weight(struct cfq_group *cfqg)
+{
+	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
+	if (cfqg->needs_update) {
+		cfqg->weight = cfqg->new_weight;
+		cfqg->needs_update = false;
+	}
+}
+
+static void
+cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
+{
+	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
+
+	cfq_update_group_weight(cfqg);
+	__cfq_group_service_tree_add(st, cfqg);
+	st->total_weight += cfqg->weight;
+}
+
+static void
+cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
 	struct cfq_group *__cfqg;
@@ -884,13 +896,19 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
 	} else
 		cfqg->vdisktime = st->min_vdisktime;
+	cfq_group_service_tree_add(st, cfqg);
+}
 
-	__cfq_group_service_tree_add(st, cfqg);
-	st->total_weight += cfqg->weight;
+static void
+cfq_group_service_tree_del(struct cfq_rb_root *st, struct cfq_group *cfqg)
+{
+	st->total_weight -= cfqg->weight;
+	if (!RB_EMPTY_NODE(&cfqg->rb_node))
+		cfq_rb_erase(&cfqg->rb_node, st);
 }
 
 static void
-cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
+cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
 
@@ -902,14 +920,13 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		return;
 
 	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
-	st->total_weight -= cfqg->weight;
-	if (!RB_EMPTY_NODE(&cfqg->rb_node))
-		cfq_rb_erase(&cfqg->rb_node, st);
+	cfq_group_service_tree_del(st, cfqg);
 	cfqg->saved_workload_slice = 0;
 	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
 }
 
-static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
+static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
+						unsigned int *unaccounted_time)
 {
 	unsigned int slice_used;
 
@@ -928,8 +945,13 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
 					1);
 	} else {
 		slice_used = jiffies - cfqq->slice_start;
-		if (slice_used > cfqq->allocated_slice)
+		if (slice_used > cfqq->allocated_slice) {
+			*unaccounted_time = slice_used - cfqq->allocated_slice;
 			slice_used = cfqq->allocated_slice;
+		}
+		if (time_after(cfqq->slice_start, cfqq->dispatch_start))
+			*unaccounted_time += cfqq->slice_start -
+					cfqq->dispatch_start;
 	}
 
 	return slice_used;
@@ -939,12 +961,12 @@ 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, charge;
+	unsigned int used_sl, charge, unaccounted_sl = 0;
 	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 = cfq_cfqq_slice_usage(cfqq);
+	used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl);
 
 	if (iops_mode(cfqd))
 		charge = cfqq->slice_dispatch;
@@ -952,9 +974,10 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 		charge = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
-	cfq_rb_erase(&cfqg->rb_node, st);
+	cfq_group_service_tree_del(st, cfqg);
 	cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
-	__cfq_group_service_tree_add(st, cfqg);
+	/* If a new weight was requested, update now, off tree */
+	cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
 	if (time_after(cfqd->workload_expires, jiffies)) {
@@ -970,7 +993,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
 			" sect=%u", used_sl, cfqq->slice_dispatch, charge,
 			iops_mode(cfqd), cfqq->nr_sectors);
-	cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl);
+	cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl,
+					  unaccounted_sl);
 	cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
 }
 
@@ -985,7 +1009,9 @@ static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
 void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
 					unsigned int weight)
 {
-	cfqg_of_blkg(blkg)->weight = weight;
+	struct cfq_group *cfqg = cfqg_of_blkg(blkg);
+	cfqg->new_weight = weight;
+	cfqg->needs_update = true;
 }
 
 static struct cfq_group *
@@ -1187,32 +1213,6 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	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;
-		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));
 	if (cfq_class_idle(cfqq)) {
@@ -1284,7 +1284,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	service_tree->count++;
 	if ((add_front || !new_cfqq) && !group_changed)
 		return;
-	cfq_group_service_tree_add(cfqd, cfqq->cfqg);
+	cfq_group_notify_queue_add(cfqd, cfqq->cfqg);
 }
 
 static struct cfq_queue *
@@ -1372,6 +1372,8 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
+	if (cfq_cfqq_sync(cfqq))
+		cfqd->busy_sync_queues++;
 
 	cfq_resort_rr_list(cfqd, cfqq);
 }
@@ -1395,9 +1397,11 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		cfqq->p_root = NULL;
 	}
 
-	cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+	cfq_group_notify_queue_del(cfqd, cfqq->cfqg);
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
+	if (cfq_cfqq_sync(cfqq))
+		cfqd->busy_sync_queues--;
 }
 
 /*
@@ -1671,7 +1675,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	 */
 	if (timed_out) {
 		if (cfq_cfqq_slice_new(cfqq))
-			cfqq->slice_resid = cfq_scaled_group_slice(cfqd, cfqq);
+			cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
 		else
 			cfqq->slice_resid = cfqq->slice_end - jiffies;
 		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
@@ -2405,6 +2409,7 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * Does this cfqq already have too much IO in flight?
 	 */
 	if (cfqq->dispatched >= max_dispatch) {
+		bool promote_sync = false;
 		/*
 		 * idle queue must always only have a single IO in flight
 		 */
@@ -2412,15 +2417,26 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 			return false;
 
 		/*
+		 * If there is only one sync queue
+		 * we can ignore async queue here and give the sync
+		 * queue no dispatch limit. The reason is a sync queue can
+		 * preempt async queue, limiting the sync queue doesn't make
+		 * sense. This is useful for aiostress test.
+		 */
+		if (cfq_cfqq_sync(cfqq) && cfqd->busy_sync_queues == 1)
+			promote_sync = true;
+
+		/*
 		 * We have other queues, don't allow more IO from this one
 		 */
-		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq))
+		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq) &&
+				!promote_sync)
 			return false;
 
 		/*
 		 * Sole queue user, no limit
 		 */
-		if (cfqd->busy_queues == 1)
+		if (cfqd->busy_queues == 1 || promote_sync)
 			max_dispatch = -1;
 		else
 			/*
@@ -2542,7 +2558,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
-	struct cfq_group *cfqg, *orig_cfqg;
+	struct cfq_group *cfqg;
 
 	BUG_ON(cfqq->ref <= 0);
 
@@ -2554,7 +2570,6 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	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);
@@ -2564,8 +2579,6 @@ 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);
 }
 
 /*
@@ -3355,7 +3368,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			    cfqd->busy_queues > 1) {
 				cfq_del_timer(cfqd, cfqq);
 				cfq_clear_cfqq_wait_request(cfqq);
-				__blk_run_queue(cfqd->queue);
+				__blk_run_queue(cfqd->queue, false);
 			} else {
 				cfq_blkiocg_update_idle_time_stats(
 						&cfqq->cfqg->blkg);
@@ -3370,7 +3383,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		__blk_run_queue(cfqd->queue);
+		__blk_run_queue(cfqd->queue, false);
 	}
 }
 
@@ -3432,6 +3445,10 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_io_context *cic = cfqd->active_cic;
 
+	/* If the queue already has requests, don't wait */
+	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
+		return false;
+
 	/* If there are other queues in the group, don't wait */
 	if (cfqq->cfqg->nr_cfqq > 1)
 		return false;
@@ -3609,12 +3626,12 @@ static void cfq_put_request(struct request *rq)
 
 		put_io_context(RQ_CIC(rq)->ioc);
 
-		rq->elevator_private = NULL;
-		rq->elevator_private2 = NULL;
+		rq->elevator_private[0] = NULL;
+		rq->elevator_private[1] = NULL;
 
 		/* Put down rq reference on cfqg */
 		cfq_put_cfqg(RQ_CFQG(rq));
-		rq->elevator_private3 = NULL;
+		rq->elevator_private[2] = NULL;
 
 		cfq_put_queue(cfqq);
 	}
@@ -3701,13 +3718,12 @@ new_queue:
 	}
 
 	cfqq->allocated[rw]++;
-	cfqq->ref++;
-	rq->elevator_private = cic;
-	rq->elevator_private2 = cfqq;
-	rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
 
+	cfqq->ref++;
+	rq->elevator_private[0] = cic;
+	rq->elevator_private[1] = cfqq;
+	rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
 	spin_unlock_irqrestore(q->queue_lock, flags);
-
 	return 0;
 
 queue_fail:
@@ -3727,7 +3743,7 @@ static void cfq_kick_queue(struct work_struct *work)
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(cfqd->queue);
+	__blk_run_queue(cfqd->queue, false);
 	spin_unlock_irq(q->queue_lock);
 }
 
@@ -3949,7 +3965,6 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_slice_idle = cfq_slice_idle;
 	cfqd->cfq_group_idle = cfq_group_idle;
 	cfqd->cfq_latency = 1;
-	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
 	/*
 	 * we optimistically start assuming sync ops weren't delayed in last
@@ -4025,7 +4040,6 @@ 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)			\
@@ -4059,7 +4073,6 @@ 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) \
@@ -4077,7 +4090,6 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_idle),
 	CFQ_ATTR(group_idle),
 	CFQ_ATTR(low_latency),
-	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
 };
 
@@ -4092,7 +4104,6 @@ static struct elevator_type iosched_cfq = {
 		.elevator_add_req_fn =		cfq_insert_request,
 		.elevator_activate_req_fn =	cfq_activate_request,
 		.elevator_deactivate_req_fn =	cfq_deactivate_request,
-		.elevator_queue_empty_fn =	cfq_queue_empty,
 		.elevator_completed_req_fn =	cfq_completed_request,
 		.elevator_former_req_fn =	elv_rb_former_request,
 		.elevator_latter_req_fn =	elv_rb_latter_request,
diff --git a/block/cfq.h b/block/cfq.h
index 54a6d90f8e8c..2a155927e37c 100644
--- a/block/cfq.h
+++ b/block/cfq.h
@@ -16,9 +16,9 @@ static inline void cfq_blkiocg_update_dequeue_stats(struct blkio_group *blkg,
 }
 
 static inline void cfq_blkiocg_update_timeslice_used(struct blkio_group *blkg,
-			unsigned long time)
+			unsigned long time, unsigned long unaccounted_time)
 {
-	blkiocg_update_timeslice_used(blkg, time);
+	blkiocg_update_timeslice_used(blkg, time, unaccounted_time);
 }
 
 static inline void cfq_blkiocg_set_start_empty_time(struct blkio_group *blkg)
@@ -85,7 +85,7 @@ static inline void cfq_blkiocg_update_dequeue_stats(struct blkio_group *blkg,
 			unsigned long dequeue) {}
 
 static inline void cfq_blkiocg_update_timeslice_used(struct blkio_group *blkg,
-			unsigned long time) {}
+			unsigned long time, unsigned long unaccounted_time) {}
 static inline void cfq_blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 static inline void cfq_blkiocg_update_io_remove_stats(struct blkio_group *blkg,
 				bool direction, bool sync) {}
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index b547cbca7b23..5139c0ea1864 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -326,14 +326,6 @@ dispatch_request:
 	return 1;
 }
 
-static int deadline_queue_empty(struct request_queue *q)
-{
-	struct deadline_data *dd = q->elevator->elevator_data;
-
-	return list_empty(&dd->fifo_list[WRITE])
-		&& list_empty(&dd->fifo_list[READ]);
-}
-
 static void deadline_exit_queue(struct elevator_queue *e)
 {
 	struct deadline_data *dd = e->elevator_data;
@@ -445,7 +437,6 @@ static struct elevator_type iosched_deadline = {
 		.elevator_merge_req_fn =	deadline_merged_requests,
 		.elevator_dispatch_fn =		deadline_dispatch_requests,
 		.elevator_add_req_fn =		deadline_add_request,
-		.elevator_queue_empty_fn =	deadline_queue_empty,
 		.elevator_former_req_fn =	elv_rb_former_request,
 		.elevator_latter_req_fn =	elv_rb_latter_request,
 		.elevator_init_fn =		deadline_init_queue,
diff --git a/block/elevator.c b/block/elevator.c
index 2569512830d3..c387d3168734 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -113,7 +113,7 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 }
 EXPORT_SYMBOL(elv_rq_merge_ok);
 
-static inline int elv_try_merge(struct request *__rq, struct bio *bio)
+int elv_try_merge(struct request *__rq, struct bio *bio)
 {
 	int ret = ELEVATOR_NO_MERGE;
 
@@ -421,6 +421,8 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	struct list_head *entry;
 	int stop_flags;
 
+	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
+
 	if (q->last_merge == rq)
 		q->last_merge = NULL;
 
@@ -519,6 +521,40 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	return ELEVATOR_NO_MERGE;
 }
 
+/*
+ * Attempt to do an insertion back merge. Only check for the case where
+ * we can append 'rq' to an existing request, so we can throw 'rq' away
+ * afterwards.
+ *
+ * Returns true if we merged, false otherwise
+ */
+static bool elv_attempt_insert_merge(struct request_queue *q,
+				     struct request *rq)
+{
+	struct request *__rq;
+
+	if (blk_queue_nomerges(q))
+		return false;
+
+	/*
+	 * First try one-hit cache.
+	 */
+	if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq))
+		return true;
+
+	if (blk_queue_noxmerges(q))
+		return false;
+
+	/*
+	 * See if our hash lookup can find a potential backmerge.
+	 */
+	__rq = elv_rqhash_find(q, blk_rq_pos(rq));
+	if (__rq && blk_attempt_req_merge(q, __rq, rq))
+		return true;
+
+	return false;
+}
+
 void elv_merged_request(struct request_queue *q, struct request *rq, int type)
 {
 	struct elevator_queue *e = q->elevator;
@@ -536,14 +572,18 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 			     struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
+	const int next_sorted = next->cmd_flags & REQ_SORTED;
 
-	if (e->ops->elevator_merge_req_fn)
+	if (next_sorted && e->ops->elevator_merge_req_fn)
 		e->ops->elevator_merge_req_fn(q, rq, next);
 
 	elv_rqhash_reposition(q, rq);
-	elv_rqhash_del(q, next);
 
-	q->nr_sorted--;
+	if (next_sorted) {
+		elv_rqhash_del(q, next);
+		q->nr_sorted--;
+	}
+
 	q->last_merge = rq;
 }
 
@@ -602,7 +642,7 @@ void elv_quiesce_start(struct request_queue *q)
 	 */
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
-		__blk_run_queue(q);
+		__blk_run_queue(q, false);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
@@ -617,21 +657,12 @@ void elv_quiesce_end(struct request_queue *q)
 
 void elv_insert(struct request_queue *q, struct request *rq, int where)
 {
-	int unplug_it = 1;
-
 	trace_block_rq_insert(q, rq);
 
 	rq->q = q;
 
 	switch (where) {
 	case ELEVATOR_INSERT_REQUEUE:
-		/*
-		 * Most requeues happen because of a busy condition,
-		 * don't force unplug of the queue for that case.
-		 * Clear unplug_it and fall through.
-		 */
-		unplug_it = 0;
-
 	case ELEVATOR_INSERT_FRONT:
 		rq->cmd_flags |= REQ_SOFTBARRIER;
 		list_add(&rq->queuelist, &q->queue_head);
@@ -651,9 +682,17 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
-		__blk_run_queue(q);
+		__blk_run_queue(q, false);
 		break;
 
+	case ELEVATOR_INSERT_SORT_MERGE:
+		/*
+		 * If we succeed in merging this request with one in the
+		 * queue already, we are done - rq has now been freed,
+		 * so no need to do anything further.
+		 */
+		if (elv_attempt_insert_merge(q, rq))
+			break;
 	case ELEVATOR_INSERT_SORT:
 		BUG_ON(rq->cmd_type != REQ_TYPE_FS &&
 		       !(rq->cmd_flags & REQ_DISCARD));
@@ -673,24 +712,21 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		q->elevator->ops->elevator_add_req_fn(q, rq);
 		break;
 
+	case ELEVATOR_INSERT_FLUSH:
+		rq->cmd_flags |= REQ_SOFTBARRIER;
+		blk_insert_flush(rq);
+		break;
 	default:
 		printk(KERN_ERR "%s: bad insertion point %d\n",
 		       __func__, where);
 		BUG();
 	}
-
-	if (unplug_it && blk_queue_plugged(q)) {
-		int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
-				- queue_in_flight(q);
-
-		if (nrq >= q->unplug_thresh)
-			__generic_unplug_device(q);
-	}
 }
 
-void __elv_add_request(struct request_queue *q, struct request *rq, int where,
-		       int plug)
+void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
+	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
+
 	if (rq->cmd_flags & REQ_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||
@@ -702,38 +738,20 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		    where == ELEVATOR_INSERT_SORT)
 		where = ELEVATOR_INSERT_BACK;
 
-	if (plug)
-		blk_plug_device(q);
-
 	elv_insert(q, rq, where);
 }
 EXPORT_SYMBOL(__elv_add_request);
 
-void elv_add_request(struct request_queue *q, struct request *rq, int where,
-		     int plug)
+void elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__elv_add_request(q, rq, where, plug);
+	__elv_add_request(q, rq, where);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(elv_add_request);
 
-int elv_queue_empty(struct request_queue *q)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (!list_empty(&q->queue_head))
-		return 0;
-
-	if (e->ops->elevator_queue_empty_fn)
-		return e->ops->elevator_queue_empty_fn(q);
-
-	return 1;
-}
-EXPORT_SYMBOL(elv_queue_empty);
-
 struct request *elv_latter_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
@@ -759,7 +777,7 @@ int elv_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	if (e->ops->elevator_set_req_fn)
 		return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
 
-	rq->elevator_private = NULL;
+	rq->elevator_private[0] = NULL;
 	return 0;
 }
 
@@ -785,6 +803,8 @@ void elv_abort_queue(struct request_queue *q)
 {
 	struct request *rq;
 
+	blk_abort_flushes(q);
+
 	while (!list_empty(&q->queue_head)) {
 		rq = list_entry_rq(q->queue_head.next);
 		rq->cmd_flags |= REQ_QUIET;
diff --git a/block/genhd.c b/block/genhd.c
index 6a5b772aa201..c91a2dac6b6b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1158,14 +1158,14 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%u %lu %lu %llu %u %u %u %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[0]),
-			   part_stat_read(hd, merges[0]),
-			   (unsigned long long)part_stat_read(hd, sectors[0]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[0])),
-			   part_stat_read(hd, ios[1]),
-			   part_stat_read(hd, merges[1]),
-			   (unsigned long long)part_stat_read(hd, sectors[1]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[1])),
+			   part_stat_read(hd, ios[READ]),
+			   part_stat_read(hd, merges[READ]),
+			   (unsigned long long)part_stat_read(hd, sectors[READ]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
+			   part_stat_read(hd, ios[WRITE]),
+			   part_stat_read(hd, merges[WRITE]),
+			   (unsigned long long)part_stat_read(hd, sectors[WRITE]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
 			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
@@ -1355,7 +1355,7 @@ int invalidate_partition(struct gendisk *disk, int partno)
 	struct block_device *bdev = bdget_disk(disk, partno);
 	if (bdev) {
 		fsync_bdev(bdev);
-		res = __invalidate_device(bdev);
+		res = __invalidate_device(bdev, true);
 		bdput(bdev);
 	}
 	return res;
@@ -1494,7 +1494,7 @@ void disk_block_events(struct gendisk *disk)
 void disk_unblock_events(struct gendisk *disk)
 {
 	if (disk->ev)
-		__disk_unblock_events(disk, true);
+		__disk_unblock_events(disk, false);
 }
 
 /**
diff --git a/block/ioctl.c b/block/ioctl.c
index 9049d460fa89..1124cd297263 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -294,9 +294,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			return -EINVAL;
 		if (get_user(n, (int __user *) arg))
 			return -EFAULT;
-		if (!(mode & FMODE_EXCL) &&
-		    blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
-			return -EBUSY;
+		if (!(mode & FMODE_EXCL)) {
+			bdgrab(bdev);
+			if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+				return -EBUSY;
+		}
 		ret = set_blocksize(bdev, n);
 		if (!(mode & FMODE_EXCL))
 			blkdev_put(bdev, mode | FMODE_EXCL);
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 232c4b38cd37..06389e9ef96d 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -39,13 +39,6 @@ static void noop_add_request(struct request_queue *q, struct request *rq)
 	list_add_tail(&rq->queuelist, &nd->queue);
 }
 
-static int noop_queue_empty(struct request_queue *q)
-{
-	struct noop_data *nd = q->elevator->elevator_data;
-
-	return list_empty(&nd->queue);
-}
-
 static struct request *
 noop_former_request(struct request_queue *q, struct request *rq)
 {
@@ -90,7 +83,6 @@ static struct elevator_type elevator_noop = {
 		.elevator_merge_req_fn		= noop_merged_requests,
 		.elevator_dispatch_fn		= noop_dispatch,
 		.elevator_add_req_fn		= noop_add_request,
-		.elevator_queue_empty_fn	= noop_queue_empty,
 		.elevator_former_req_fn		= noop_former_request,
 		.elevator_latter_req_fn		= noop_latter_request,
 		.elevator_init_fn		= noop_init_queue,
author	Artem Bityutskiy <Artem.Bityutskiy@nokia.com>	2011-03-25 17:41:20 +0200
committer	Artem Bityutskiy <Artem.Bityutskiy@nokia.com>	2011-03-25 17:41:20 +0200
commit	7bf7e370d5919112c223a269462cd0b546903829 (patch)
tree	03ccc715239df14ae168277dbccc9d9cf4d8a2c8 /block
parent	68b1a1e786f29c900fa1c516a402e24f0ece622a (diff)
parent	d39dd11c3e6a7af5c20bfac40594db36cf270f42 (diff)