Merge commit 'block/for-next'

53 files changed, 1851 insertions, 760 deletions

diff --git a/block/Makefile b/block/Makefile
index 6c54ed0ff755..ba74ca6bfa14 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			ioctl.o genhd.o scsi_ioctl.o
+			blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
diff --git a/block/blk-core.c b/block/blk-core.c
index e3299a77a0d8..5b59592b8bf7 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -501,6 +501,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
 	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+	q->backing_dev_info.name = "block";
 
 	err = bdi_init(&q->backing_dev_info);
 	if (err) {
@@ -1111,31 +1112,27 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	req->cmd_type = REQ_TYPE_FS;
 
 	/*
-	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+	 * Inherit FAILFAST from bio (for read-ahead, and explicit
+	 * FAILFAST).  FAILFAST flags are identical for req and bio.
 	 */
-	if (bio_rw_ahead(bio))
-		req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-				   REQ_FAILFAST_DRIVER);
-	if (bio_failfast_dev(bio))
-		req->cmd_flags |= REQ_FAILFAST_DEV;
-	if (bio_failfast_transport(bio))
-		req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	if (bio_failfast_driver(bio))
-		req->cmd_flags |= REQ_FAILFAST_DRIVER;
-
-	if (unlikely(bio_discard(bio))) {
+	if (bio_rw_flagged(bio, BIO_RW_AHEAD))
+		req->cmd_flags |= REQ_FAILFAST_MASK;
+	else
+		req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
+
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) {
 		req->cmd_flags |= REQ_DISCARD;
-		if (bio_barrier(bio))
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER))
 			req->cmd_flags |= REQ_SOFTBARRIER;
 		req->q->prepare_discard_fn(req->q, req);
-	} else if (unlikely(bio_barrier(bio)))
+	} else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
 		req->cmd_flags |= REQ_HARDBARRIER;
 
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_rw_meta(bio))
+	if (bio_rw_flagged(bio, BIO_RW_META))
 		req->cmd_flags |= REQ_RW_META;
-	if (bio_noidle(bio))
+	if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
 		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
@@ -1150,7 +1147,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
  */
 static inline bool queue_should_plug(struct request_queue *q)
 {
-	return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+	return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
 }
 
 static int __make_request(struct request_queue *q, struct bio *bio)
@@ -1159,11 +1156,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret;
 	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
-	const int sync = bio_sync(bio);
-	const int unplug = bio_unplug(bio);
+	const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG);
+	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;
 
-	if (bio_barrier(bio) && bio_has_data(bio) &&
+	if (bio_rw_flagged(bio, BIO_RW_BARRIER) && bio_has_data(bio) &&
 	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
@@ -1177,7 +1175,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely(bio_barrier(bio)) || elv_queue_empty(q))
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1190,6 +1188,9 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		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;
@@ -1209,6 +1210,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		trace_block_bio_frontmerge(q, bio);
 
+		if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+			blk_rq_set_mixed_merge(req);
+			req->cmd_flags &= ~REQ_FAILFAST_MASK;
+			req->cmd_flags |= ff;
+		}
+
 		bio->bi_next = req->bio;
 		req->bio = bio;
 
@@ -1464,7 +1471,8 @@ static inline void __generic_make_request(struct bio *bio)
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
-		if (bio_discard(bio) && !q->prepare_discard_fn) {
+		if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+		    !q->prepare_discard_fn) {
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
@@ -1653,6 +1661,50 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ *     A request could be merge of IOs which require different failure
+ *     handling.  This function determines the number of bytes which
+ *     can be failed from the beginning of the request without
+ *     crossing into area which need to be retried further.
+ *
+ * Return:
+ *     The number of bytes to fail.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	unsigned int bytes = 0;
+	struct bio *bio;
+
+	if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+		return blk_rq_bytes(rq);
+
+	/*
+	 * Currently the only 'mixing' which can happen is between
+	 * different fastfail types.  We can safely fail portions
+	 * which have all the failfast bits that the first one has -
+	 * the ones which are at least as eager to fail as the first
+	 * one.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		if ((bio->bi_rw & ff) != ff)
+			break;
+		bytes += bio->bi_size;
+	}
+
+	/* this could lead to infinite loop */
+	BUG_ON(blk_rq_bytes(rq) && !bytes);
+	return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
@@ -1806,8 +1858,15 @@ void blk_dequeue_request(struct request *rq)
 	 * and to it is freed is accounted as io that is in progress at
 	 * the driver side.
 	 */
-	if (blk_account_rq(rq))
+	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]++;
+		/*
+		 * Mark this device as supporting hardware queuing, if
+		 * we have more IOs in flight than 4.
+		 */
+		if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+			set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
+	}
 }
 
 /**
@@ -1999,6 +2058,12 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (blk_fs_request(req) || blk_discard_rq(req))
 		req->__sector += total_bytes >> 9;
 
+	/* mixed attributes always follow the first bio */
+	if (req->cmd_flags & REQ_MIXED_MERGE) {
+		req->cmd_flags &= ~REQ_FAILFAST_MASK;
+		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+	}
+
 	/*
 	 * If total number of sectors is less than the first segment
 	 * size, something has gone terribly wrong.
@@ -2178,6 +2243,25 @@ bool blk_end_request_cur(struct request *rq, int error)
 EXPORT_SYMBOL(blk_end_request_cur);
 
 /**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
+
+/**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
  * @error:    %0 for success, < %0 for error
@@ -2236,12 +2320,31 @@ bool __blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_end_request_cur);
 
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ *     Complete @rq till the next failure boundary.  Must be called
+ *     with queue lock held.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+	WARN_ON(error >= 0);
+	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
+
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and
-	   we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
-	rq->cmd_flags |= (bio->bi_rw & 3);
+	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+	rq->cmd_flags |= bio->bi_rw & REQ_RW;
 
 	if (bio_has_data(bio)) {
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
new file mode 100644
index 000000000000..ca564202ed7a
--- /dev/null
+++ b/block/blk-iopoll.c
@@ -0,0 +1,227 @@
+/*
+ * Functions related to interrupt-poll handling in the block layer. This
+ * is similar to NAPI for network devices.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/blk-iopoll.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+
+int blk_iopoll_enabled = 1;
+EXPORT_SYMBOL(blk_iopoll_enabled);
+
+static unsigned int blk_iopoll_budget __read_mostly = 256;
+
+static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
+
+/**
+ * blk_iopoll_sched - Schedule a run of the iopoll handler
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Add this blk_iopoll structure to the pending poll list and trigger the
+ *     raise of the blk iopoll softirq. The driver must already have gotten a
+ *     succesful return from blk_iopoll_sched_prep() before calling this.
+ **/
+void blk_iopoll_sched(struct blk_iopoll *iop)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll));
+	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(blk_iopoll_sched);
+
+/**
+ * __blk_iopoll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     See blk_iopoll_complete(). This function must be called with interrupts
+ *     disabled.
+ **/
+void __blk_iopoll_complete(struct blk_iopoll *iop)
+{
+	list_del(&iop->list);
+	smp_mb__before_clear_bit();
+	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(__blk_iopoll_complete);
+
+/**
+ * blk_iopoll_complete - Mark this @iop as un-polled again
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     If a driver consumes less than the assigned budget in its run of the
+ *     iopoll handler, it'll end the polled mode by calling this function. The
+ *     iopoll handler will not be invoked again before blk_iopoll_sched_prep()
+ *     is called.
+ **/
+void blk_iopoll_complete(struct blk_iopoll *iopoll)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__blk_iopoll_complete(iopoll);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(blk_iopoll_complete);
+
+static void blk_iopoll_softirq(struct softirq_action *h)
+{
+	struct list_head *list = &__get_cpu_var(blk_cpu_iopoll);
+	int rearm = 0, budget = blk_iopoll_budget;
+	unsigned long start_time = jiffies;
+
+	local_irq_disable();
+
+	while (!list_empty(list)) {
+		struct blk_iopoll *iop;
+		int work, weight;
+
+		/*
+		 * If softirq window is exhausted then punt.
+		 */
+		if (budget <= 0 || time_after(jiffies, start_time)) {
+			rearm = 1;
+			break;
+		}
+
+		local_irq_enable();
+
+		/* Even though interrupts have been re-enabled, this
+		 * access is safe because interrupts can only add new
+		 * entries to the tail of this list, and only ->poll()
+		 * calls can remove this head entry from the list.
+		 */
+		iop = list_entry(list->next, struct blk_iopoll, list);
+
+		weight = iop->weight;
+		work = 0;
+		if (test_bit(IOPOLL_F_SCHED, &iop->state))
+			work = iop->poll(iop, weight);
+
+		budget -= work;
+
+		local_irq_disable();
+
+		/*
+		 * Drivers must not modify the iopoll state, if they
+		 * consume their assigned weight (or more, some drivers can't
+		 * easily just stop processing, they have to complete an
+		 * entire mask of commands).In such cases this code
+		 * still "owns" the iopoll instance and therefore can
+		 * move the instance around on the list at-will.
+		 */
+		if (work >= weight) {
+			if (blk_iopoll_disable_pending(iop))
+				__blk_iopoll_complete(iop);
+			else
+				list_move_tail(&iop->list, list);
+		}
+	}
+
+	if (rearm)
+		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+
+	local_irq_enable();
+}
+
+/**
+ * blk_iopoll_disable - Disable iopoll on this @iop
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Disable io polling and wait for any pending callbacks to have completed.
+ **/
+void blk_iopoll_disable(struct blk_iopoll *iop)
+{
+	set_bit(IOPOLL_F_DISABLE, &iop->state);
+	while (test_and_set_bit(IOPOLL_F_SCHED, &iop->state))
+		msleep(1);
+	clear_bit(IOPOLL_F_DISABLE, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_disable);
+
+/**
+ * blk_iopoll_enable - Enable iopoll on this @iop
+ * @iop:      The parent iopoll structure
+ *
+ * Description:
+ *     Enable iopoll on this @iop. Note that the handler run will not be
+ *     scheduled, it will only mark it as active.
+ **/
+void blk_iopoll_enable(struct blk_iopoll *iop)
+{
+	BUG_ON(!test_bit(IOPOLL_F_SCHED, &iop->state));
+	smp_mb__before_clear_bit();
+	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_enable);
+
+/**
+ * blk_iopoll_init - Initialize this @iop
+ * @iop:      The parent iopoll structure
+ * @weight:   The default weight (or command completion budget)
+ * @poll_fn:  The handler to invoke
+ *
+ * Description:
+ *     Initialize this blk_iopoll structure. Before being actively used, the
+ *     driver must call blk_iopoll_enable().
+ **/
+void blk_iopoll_init(struct blk_iopoll *iop, int weight, blk_iopoll_fn *poll_fn)
+{
+	memset(iop, 0, sizeof(*iop));
+	INIT_LIST_HEAD(&iop->list);
+	iop->weight = weight;
+	iop->poll = poll_fn;
+	set_bit(IOPOLL_F_SCHED, &iop->state);
+}
+EXPORT_SYMBOL(blk_iopoll_init);
+
+static int __cpuinit blk_iopoll_cpu_notify(struct notifier_block *self,
+					  unsigned long action, void *hcpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		int cpu = (unsigned long) hcpu;
+
+		local_irq_disable();
+		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
+				 &__get_cpu_var(blk_cpu_iopoll));
+		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata blk_iopoll_cpu_notifier = {
+	.notifier_call	= blk_iopoll_cpu_notify,
+};
+
+static __init int blk_iopoll_setup(void)
+{
+	int i;
+
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));
+
+	open_softirq(BLOCK_IOPOLL_SOFTIRQ, blk_iopoll_softirq);
+	register_hotcpu_notifier(&blk_iopoll_cpu_notifier);
+	return 0;
+}
+subsys_initcall(blk_iopoll_setup);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index e1999679a4d5..b0de8574fdc8 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -311,6 +311,36 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+/**
+ * blk_rq_set_mixed_merge - mark a request as mixed merge
+ * @rq: request to mark as mixed merge
+ *
+ * Description:
+ *     @rq is about to be mixed merged.  Make sure the attributes
+ *     which can be mixed are set in each bio and mark @rq as mixed
+ *     merged.
+ */
+void blk_rq_set_mixed_merge(struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	struct bio *bio;
+
+	if (rq->cmd_flags & REQ_MIXED_MERGE)
+		return;
+
+	/*
+	 * @rq will no longer represent mixable attributes for all the
+	 * contained bios.  It will just track those of the first one.
+	 * Distributes the attributs to each bio.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
+			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
+		bio->bi_rw |= ff;
+	}
+	rq->cmd_flags |= REQ_MIXED_MERGE;
+}
+
 static void blk_account_io_merge(struct request *req)
 {
 	if (blk_do_io_stat(req)) {
@@ -350,12 +380,6 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_integrity_rq(req) != blk_integrity_rq(next))
 		return 0;
 
-	/* don't merge requests of different failfast settings */
-	if (blk_failfast_dev(req)	!= blk_failfast_dev(next)	||
-	    blk_failfast_transport(req)	!= blk_failfast_transport(next)	||
-	    blk_failfast_driver(req)	!= blk_failfast_driver(next))
-		return 0;
-
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
@@ -366,6 +390,19 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 		return 0;
 
 	/*
+	 * If failfast settings disagree or any of the two is already
+	 * a mixed merge, mark both as mixed before proceeding.  This
+	 * makes sure that all involved bios have mixable attributes
+	 * set properly.
+	 */
+	if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
+	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
+	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
+		blk_rq_set_mixed_merge(req);
+		blk_rq_set_mixed_merge(next);
+	}
+
+	/*
 	 * At this point we have either done a back merge
 	 * or front merge. We need the smaller start_time of
 	 * the merged requests to be the current request
diff --git a/block/blk.h b/block/blk.h
index 3fae6add5430..5ee3d7e72feb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -104,6 +104,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
 void blk_recalc_rq_segments(struct request *rq);
+void blk_rq_set_mixed_merge(struct request *rq);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index fd7080ed7935..f75a54bfc547 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -134,13 +134,8 @@ struct cfq_data {
 	struct rb_root prio_trees[CFQ_PRIO_LISTS];
 
 	unsigned int busy_queues;
-	/*
-	 * Used to track any pending rt requests so we can pre-empt current
-	 * non-RT cfqq in service when this value is non-zero.
-	 */
-	unsigned int busy_rt_queues;
 
-	int rq_in_driver;
+	int rq_in_driver[2];
 	int sync_flight;
 
 	/*
@@ -191,7 +186,6 @@ enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
 	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
 	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
-	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
 	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
 	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
 	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
@@ -218,7 +212,6 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
 CFQ_CFQQ_FNS(on_rr);
 CFQ_CFQQ_FNS(wait_request);
 CFQ_CFQQ_FNS(must_dispatch);
-CFQ_CFQQ_FNS(must_alloc);
 CFQ_CFQQ_FNS(must_alloc_slice);
 CFQ_CFQQ_FNS(fifo_expire);
 CFQ_CFQQ_FNS(idle_window);
@@ -239,6 +232,11 @@ static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
 static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
 						struct io_context *);
 
+static inline int rq_in_driver(struct cfq_data *cfqd)
+{
+	return cfqd->rq_in_driver[0] + cfqd->rq_in_driver[1];
+}
+
 static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
 					    int is_sync)
 {
@@ -257,7 +255,7 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic,
  */
 static inline int cfq_bio_sync(struct bio *bio)
 {
-	if (bio_data_dir(bio) == READ || bio_sync(bio))
+	if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		return 1;
 
 	return 0;
@@ -648,8 +646,6 @@ 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_class_rt(cfqq))
-		cfqd->busy_rt_queues++;
 
 	cfq_resort_rr_list(cfqd, cfqq);
 }
@@ -673,8 +669,6 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
-	if (cfq_class_rt(cfqq))
-		cfqd->busy_rt_queues--;
 }
 
 /*
@@ -760,9 +754,9 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 
-	cfqd->rq_in_driver++;
+	cfqd->rq_in_driver[rq_is_sync(rq)]++;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
-						cfqd->rq_in_driver);
+						rq_in_driver(cfqd));
 
 	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
@@ -770,11 +764,12 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
+	const int sync = rq_is_sync(rq);
 
-	WARN_ON(!cfqd->rq_in_driver);
-	cfqd->rq_in_driver--;
+	WARN_ON(!cfqd->rq_in_driver[sync]);
+	cfqd->rq_in_driver[sync]--;
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
-						cfqd->rq_in_driver);
+						rq_in_driver(cfqd));
 }
 
 static void cfq_remove_request(struct request *rq)
@@ -1080,7 +1075,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	/*
 	 * still requests with the driver, don't idle
 	 */
-	if (cfqd->rq_in_driver)
+	if (rq_in_driver(cfqd))
 		return;
 
 	/*
@@ -1179,20 +1174,6 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 		goto expire;
 
 	/*
-	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
-	 * cfqq.
-	 */
-	if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
-		/*
-		 * We simulate this as cfqq timed out so that it gets to bank
-		 * the remaining of its time slice.
-		 */
-		cfq_log_cfqq(cfqd, cfqq, "preempt");
-		cfq_slice_expired(cfqd, 1);
-		goto new_queue;
-	}
-
-	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
 	 */
@@ -1312,6 +1293,12 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 		return 0;
 
 	/*
+	 * Drain async requests before we start sync IO
+	 */
+	if (cfq_cfqq_idle_window(cfqq) && cfqd->rq_in_driver[BLK_RW_ASYNC])
+		return 0;
+
+	/*
 	 * If this is an async queue and we have sync IO in flight, let it wait
 	 */
 	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
@@ -2130,11 +2117,11 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
  */
 static void cfq_update_hw_tag(struct cfq_data *cfqd)
 {
-	if (cfqd->rq_in_driver > cfqd->rq_in_driver_peak)
-		cfqd->rq_in_driver_peak = cfqd->rq_in_driver;
+	if (rq_in_driver(cfqd) > cfqd->rq_in_driver_peak)
+		cfqd->rq_in_driver_peak = rq_in_driver(cfqd);
 
 	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
-	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
+	    rq_in_driver(cfqd) <= CFQ_HW_QUEUE_MIN)
 		return;
 
 	if (cfqd->hw_tag_samples++ < 50)
@@ -2161,9 +2148,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 
 	cfq_update_hw_tag(cfqd);
 
-	WARN_ON(!cfqd->rq_in_driver);
+	WARN_ON(!cfqd->rq_in_driver[sync]);
 	WARN_ON(!cfqq->dispatched);
-	cfqd->rq_in_driver--;
+	cfqd->rq_in_driver[sync]--;
 	cfqq->dispatched--;
 
 	if (cfq_cfqq_sync(cfqq))
@@ -2197,7 +2184,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			cfq_arm_slice_timer(cfqd);
 	}
 
-	if (!cfqd->rq_in_driver)
+	if (!rq_in_driver(cfqd))
 		cfq_schedule_dispatch(cfqd);
 }
 
@@ -2229,8 +2216,7 @@ static void cfq_prio_boost(struct cfq_queue *cfqq)
 
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 {
-	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
-	    !cfq_cfqq_must_alloc_slice(cfqq)) {
+	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
 		cfq_mark_cfqq_must_alloc_slice(cfqq);
 		return ELV_MQUEUE_MUST;
 	}
@@ -2317,7 +2303,6 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
 	}
 
 	cfqq->allocated[rw]++;
-	cfq_clear_cfqq_must_alloc(cfqq);
 	atomic_inc(&cfqq->ref);
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
diff --git a/block/elevator.c b/block/elevator.c
index 2d511f9105e1..51bb66236ebb 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -79,7 +79,8 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 	/*
 	 * Don't merge file system requests and discard requests
 	 */
-	if (bio_discard(bio) != bio_discard(rq->bio))
+	if (bio_rw_flagged(bio, BIO_RW_DISCARD) !=
+	    bio_rw_flagged(rq->bio, BIO_RW_DISCARD))
 		return 0;
 
 	/*
@@ -101,16 +102,11 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 		return 0;
 
 	/*
-	 * Don't merge if failfast settings don't match.
-	 *
-	 * FIXME: The negation in front of each condition is necessary
-	 * because bio and request flags use different bit positions
-	 * and the accessors return those bits directly.  This
-	 * ugliness will soon go away.
+	 * Don't merge if failfast settings don't match. Just check the
+	 * first four bits, they have identical mappings in the bio->bi_rw
+	 * and rq->cmd_flags bits.
 	 */
-	if (!bio_failfast_dev(bio)	 != !blk_failfast_dev(rq)	||
-	    !bio_failfast_transport(bio) != !blk_failfast_transport(rq)	||
-	    !bio_failfast_driver(bio)	 != !blk_failfast_driver(rq))
+	if ((bio->bi_rw & BIO_RW_RQ_MASK) != (rq->cmd_flags & BIO_RW_RQ_MASK))
 		return 0;
 
 	if (!elv_iosched_allow_merge(rq, bio))
diff --git a/block/genhd.c b/block/genhd.c
index f4c64c2b303a..b89328eceee2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1215,6 +1215,16 @@ void put_disk(struct gendisk *disk)
 
 EXPORT_SYMBOL(put_disk);
 
+static void set_disk_ro_uevent(struct gendisk *gd, int ro)
+{
+	char event[] = "DISK_RO=1";
+	char *envp[] = { event, NULL };
+
+	if (!ro)
+		event[8] = '0';
+	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
+}
+
 void set_device_ro(struct block_device *bdev, int flag)
 {
 	bdev->bd_part->policy = flag;
@@ -1227,8 +1237,12 @@ void set_disk_ro(struct gendisk *disk, int flag)
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
-	disk_part_iter_init(&piter, disk,
-			    DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0);
+	if (disk->part0.policy != flag) {
+		set_disk_ro_uevent(disk, flag);
+		disk->part0.policy = flag;
+	}
+
+	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
 		part->policy = flag;
 	disk_part_iter_exit(&piter);
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 2307a271bdc9..0efb8fccb619 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -265,6 +265,7 @@ aoeblk_gdalloc(void *vp)
 	}
 
 	blk_queue_make_request(&d->blkq, aoeblk_make_request);
+	d->blkq.backing_dev_info.name = "aoe";
 	if (bdi_init(&d->blkq.backing_dev_info))
 		goto err_mempool;
 	spin_lock_irqsave(&d->lock, flags);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 5757188cd1fb..bbb79441d895 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -475,7 +475,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
-		int barrier = bio_barrier(bio);
+		bool barrier = bio_rw_flagged(bio, BIO_RW_BARRIER);
 		struct file *file = lo->lo_backing_file;
 
 		if (barrier) {
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 13c1aee6aa3f..28f1f25f0f63 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -442,7 +442,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev)
 	 * sleep when allocating a lower-request and therefore cannot be
 	 * bouncing.
 	 */
-	blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
+	blk_stack_limits(&q->limits, &osd_request_queue(osdev->osd)->limits, 0);
 
 	blk_queue_prep_rq(q, blk_queue_start_tag);
 	blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, osdblk_prepare_flush);
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index afa8813e737a..645237bda682 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -822,6 +822,7 @@ static const struct file_operations zero_fops = {
  * - permits private mappings, "copies" are taken of the source of zeros
  */
 static struct backing_dev_info zero_bdi = {
+	.name		= "char/mem",
 	.capabilities	= BDI_CAP_MAP_COPY,
 };
 
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9726577cde49..76811fd94e9e 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1123,7 +1123,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	if (error == -EOPNOTSUPP)
 		goto out;
 
-	if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+	if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
 		goto out;
 
 	if (unlikely(error)) {
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4e0e5937e42a..5aa30d1b2d6e 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -285,7 +285,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
 	if (!error)
 		return 0; /* I/O complete */
 
-	if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio))
+	if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD))
 		return error;
 
 	if (error == -EOPNOTSUPP)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8a311ea0d441..82350f590d98 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -586,7 +586,7 @@ static void dec_pending(struct dm_io *io, int error)
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
 			if (__noflush_suspending(md)) {
-				if (!bio_barrier(io->bio))
+				if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER))
 					bio_list_add_head(&md->deferred,
 							  io->bio);
 			} else
@@ -598,7 +598,7 @@ static void dec_pending(struct dm_io *io, int error)
 		io_error = io->error;
 		bio = io->bio;
 
-		if (bio_barrier(bio)) {
+		if (bio_rw_flagged(bio, BIO_RW_BARRIER)) {
 			/*
 			 * There can be just one barrier request so we use
 			 * a per-device variable for error reporting.
@@ -1204,7 +1204,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 
 	ci.map = dm_get_table(md);
 	if (unlikely(!ci.map)) {
-		if (!bio_barrier(bio))
+		if (!bio_rw_flagged(bio, BIO_RW_BARRIER))
 			bio_io_error(bio);
 		else
 			if (!md->barrier_error)
@@ -1316,7 +1316,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio)
 	 * we have to queue this io for later.
 	 */
 	if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
-	    unlikely(bio_barrier(bio))) {
+	    unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		up_read(&md->io_lock);
 
 		if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
@@ -1339,7 +1339,7 @@ static int dm_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct mapped_device *md = q->queuedata;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
@@ -2159,7 +2159,7 @@ static void dm_wq_work(struct work_struct *work)
 		if (dm_request_based(md))
 			generic_make_request(c);
 		else {
-			if (bio_barrier(c))
+			if (bio_rw_flagged(c, BIO_RW_BARRIER))
 				process_barrier(md, c);
 			else
 				__split_and_process_bio(md, c);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 5fe39c2a3d2b..ea4842905444 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -288,7 +288,7 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 	sector_t start_sector;
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 7140909f6662..89e76819f61f 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -90,7 +90,7 @@ static void multipath_end_request(struct bio *bio, int error)
 
 	if (uptodate)
 		multipath_end_bh_io(mp_bh, 0);
-	else if (!bio_rw_ahead(bio)) {
+	else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) {
 		/*
 		 * oops, IO error:
 		 */
@@ -144,7 +144,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	const int rw = bio_data_dir(bio);
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 898e2bdfee47..f845ed98fec9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -448,7 +448,7 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio)
 	const int rw = bio_data_dir(bio);
 	int cpu;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8726fd7ebce5..ff7ed3335995 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -782,8 +782,9 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	struct bio_list bl;
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
-	const int do_sync = bio_sync(bio);
-	int cpu, do_barriers;
+	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+	int cpu;
+	bool do_barriers;
 	mdk_rdev_t *blocked_rdev;
 
 	/*
@@ -797,7 +798,8 @@ static int make_request(struct request_queue *q, struct bio * bio)
 
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
-	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+	if (unlikely(!mddev->barriers_work &&
+		     bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		if (rw == WRITE)
 			md_write_end(mddev);
 		bio_endio(bio, -EOPNOTSUPP);
@@ -925,7 +927,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	atomic_set(&r1_bio->remaining, 0);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
-	do_barriers = bio_barrier(bio);
+	do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER);
 	if (do_barriers)
 		set_bit(R1BIO_Barrier, &r1_bio->state);
 
@@ -1600,7 +1602,7 @@ static void raid1d(mddev_t *mddev)
 			 * We already have a nr_pending reference on these rdevs.
 			 */
 			int i;
-			const int do_sync = bio_sync(r1_bio->master_bio);
+			const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
 			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
 			clear_bit(R1BIO_Barrier, &r1_bio->state);
 			for (i=0; i < conf->raid_disks; i++)
@@ -1654,7 +1656,7 @@ static void raid1d(mddev_t *mddev)
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
 			} else {
-				const int do_sync = bio_sync(r1_bio->master_bio);
+				const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
 				r1_bio->bios[r1_bio->read_disk] =
 					mddev->ro ? IO_BLOCKED : NULL;
 				r1_bio->read_disk = disk;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3d9020cf6f6e..d0a2152e064f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -796,12 +796,12 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
-	const int do_sync = bio_sync(bio);
+	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
 	struct bio_list bl;
 	unsigned long flags;
 	mdk_rdev_t *blocked_rdev;
 
-	if (unlikely(bio_barrier(bio))) {
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
@@ -1610,7 +1610,7 @@ static void raid10d(mddev_t *mddev)
 				raid_end_bio_io(r10_bio);
 				bio_put(bio);
 			} else {
-				const int do_sync = bio_sync(r10_bio->master_bio);
+				const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO);
 				bio_put(bio);
 				rdev = conf->mirrors[mirror].rdev;
 				if (printk_ratelimit())
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2b521ee67dfa..3233b98bdd9d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3606,7 +3606,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	const int rw = bio_data_dir(bi);
 	int cpu, remaining;
 
-	if (unlikely(bio_barrier(bi))) {
+	if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
 		bio_endio(bi, -EOPNOTSUPP);
 		return 0;
 	}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 662024d86949..5987da857103 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -898,8 +898,10 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				scsi_print_sense("", cmd);
 			scsi_print_command(cmd);
 		}
-		blk_end_request_all(req, -EIO);
-		scsi_next_command(cmd);
+		if (blk_end_request_err(req, -EIO))
+			scsi_requeue_command(q, cmd);
+		else
+			scsi_next_command(cmd);
 		break;
 	case ACTION_REPREP:
 		/* Unprep the request and put it back at the head of the queue.
diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c
index 84724187ec3e..ac8577358ba0 100644
--- a/drivers/staging/dst/dcore.c
+++ b/drivers/staging/dst/dcore.c
@@ -112,8 +112,9 @@ static int dst_request(struct request_queue *q, struct bio *bio)
 		 * I worked with.
 		 *
 		 * Empty barriers are not allowed anyway, see 51fd77bd9f512
-		 * for example, although later it was changed to bio_discard()
-		 * only, which does not work in this case.
+		 * for example, although later it was changed to
+		 * bio_rw_flagged(bio, BIO_RW_DISCARD) only, which does not
+		 * work in this case.
 		 */
 		//err = -EOPNOTSUPP;
 		err = 0;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e83be2e4602c..15831d5c7367 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1352,6 +1352,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
 	int err;
 
+	bdi->name = "btrfs";
 	bdi->capabilities = BDI_CAP_MAP_COPY;
 	err = bdi_init(bdi);
 	if (err)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5dbefd11b4af..5cf405b0828d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -260,7 +260,7 @@ loop_lock:
 		num_run++;
 		batch_run++;
 
-		if (bio_sync(cur))
+		if (bio_rw_flagged(cur, BIO_RW_SYNCIO))
 			num_sync_run++;
 
 		if (need_resched()) {
@@ -2903,7 +2903,7 @@ static noinline int schedule_bio(struct btrfs_root *root,
 	bio->bi_rw |= rw;
 
 	spin_lock(&device->io_lock);
-	if (bio_sync(bio))
+	if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
 		pending_bios = &device->pending_sync_bios;
 	else
 		pending_bios = &device->pending_bios;
diff --git a/fs/buffer.c b/fs/buffer.c
index a3ef091a45bd..2a01b2bc27ba 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -281,7 +281,7 @@ static void free_more_memory(void)
 	struct zone *zone;
 	int nid;
 
-	wakeup_pdflush(1024);
+	wakeup_flusher_threads(1024);
 	yield();
 
 	for_each_online_node(nid) {
diff --git a/fs/char_dev.c b/fs/char_dev.c
index a173551e19d7..7c27a8ebef6a 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -31,6 +31,7 @@
  * - no readahead or I/O queue unplugging required
  */
 struct backing_dev_info directly_mappable_cdev_bdi = {
+	.name = "char",
 	.capabilities	= (
 #ifdef CONFIG_MMU
 		/* permit private copies of the data to be taken */
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 4921e7426d95..a2f746066c5d 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -51,6 +51,7 @@ static const struct address_space_operations configfs_aops = {
 };
 
 static struct backing_dev_info configfs_backing_dev_info = {
+	.name		= "configfs",
 	.ra_pages	= 0,	/* No readahead */
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c54226be5294..dfb4767d7ca4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -19,49 +19,507 @@
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include "internal.h"
 
+#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
 
-/**
- * writeback_acquire - attempt to get exclusive writeback access to a device
- * @bdi: the device's backing_dev_info structure
- *
- * It is a waste of resources to have more than one pdflush thread blocked on
- * a single request queue.  Exclusion at the request_queue level is obtained
- * via a flag in the request_queue's backing_dev_info.state.
- *
- * Non-request_queue-backed address_spaces will share default_backing_dev_info,
- * unless they implement their own.  Which is somewhat inefficient, as this
- * may prevent concurrent writeback against multiple devices.
+static void generic_sync_wb_inodes(struct bdi_writeback *wb,
+				   struct super_block *sb,
+				   struct writeback_control *wbc);
+
+/*
+ * We don't actually have pdflush, but this one is exported though /proc...
  */
-static int writeback_acquire(struct backing_dev_info *bdi)
+int nr_pdflush_threads;
+
+static void generic_sync_wb_inodes(struct bdi_writeback *wb,
+				   struct super_block *sb,
+				   struct writeback_control *wbc);
+
+/*
+ * Work items for the bdi_writeback threads
+ */
+struct bdi_work {
+	struct list_head list;
+	struct list_head wait_list;
+	struct rcu_head rcu_head;
+
+	unsigned long seen;
+	atomic_t pending;
+
+	unsigned long sb_data;
+	unsigned long nr_pages;
+	enum writeback_sync_modes sync_mode;
+
+	unsigned long state;
+};
+
+static struct super_block *bdi_work_sb(struct bdi_work *work)
+{
+	return (struct super_block *) (work->sb_data & ~1UL);
+}
+
+static inline bool bdi_work_on_stack(struct bdi_work *work)
+{
+	return work->sb_data & 1UL;
+}
+
+static inline void bdi_work_init(struct bdi_work *work, struct super_block *sb,
+				 unsigned long nr_pages,
+				 enum writeback_sync_modes sync_mode)
 {
-	return !test_and_set_bit(BDI_pdflush, &bdi->state);
+	INIT_RCU_HEAD(&work->rcu_head);
+	work->sb_data = (unsigned long) sb;
+	work->nr_pages = nr_pages;
+	work->sync_mode = sync_mode;
+	work->state = 1;
+}
+
+static inline void bdi_work_init_on_stack(struct bdi_work *work,
+					  struct super_block *sb,
+					  unsigned long nr_pages,
+					  enum writeback_sync_modes sync_mode)
+{
+	bdi_work_init(work, sb, nr_pages, sync_mode);
+	work->sb_data |= 1UL;
 }
 
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
  *
- * Determine whether there is writeback in progress against a backing device.
+ * Determine whether there is writeback waiting to be handled against a
+ * backing device.
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
-	return test_bit(BDI_pdflush, &bdi->state);
+	return !list_empty(&bdi->work_list);
 }
 
-/**
- * writeback_release - relinquish exclusive writeback access against a device.
- * @bdi: the device's backing_dev_info structure
+static void bdi_work_clear(struct bdi_work *work)
+{
+	clear_bit(0, &work->state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&work->state, 0);
+}
+
+static void bdi_work_free(struct rcu_head *head)
+{
+	struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
+
+	if (!bdi_work_on_stack(work))
+		kfree(work);
+	else
+		bdi_work_clear(work);
+}
+
+static void wb_work_complete(struct bdi_work *work)
+{
+	const enum writeback_sync_modes sync_mode = work->sync_mode;
+
+	/*
+	 * For allocated work, we can clear the done/seen bit right here.
+	 * For on-stack work, we need to postpone both the clear and free
+	 * to after the RCU grace period, since the stack could be invalidated
+	 * as soon as bdi_work_clear() has done the wakeup.
+	 */
+	if (!bdi_work_on_stack(work))
+		bdi_work_clear(work);
+	if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work))
+		call_rcu(&work->rcu_head, bdi_work_free);
+}
+
+static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
+{
+	/*
+	 * The caller has retrieved the work arguments from this work,
+	 * drop our reference. If this is the last ref, delete and free it
+	 */
+	if (atomic_dec_and_test(&work->pending)) {
+		struct backing_dev_info *bdi = wb->bdi;
+
+		spin_lock(&bdi->wb_lock);
+		list_del_rcu(&work->list);
+		spin_unlock(&bdi->wb_lock);
+
+		wb_work_complete(work);
+	}
+}
+
+static void wb_start_writeback(struct bdi_writeback *wb, struct bdi_work *work)
+{
+	/*
+	 * If we failed allocating the bdi work item, wake up the wb thread
+	 * always. As a safety precaution, it'll flush out everything
+	 */
+	if (!wb_has_dirty_io(wb) && work)
+		wb_clear_pending(wb, work);
+	else if (wb->task)
+		wake_up_process(wb->task);
+}
+
+static void bdi_sched_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+	if (!bdi_wblist_needs_lock(bdi))
+		wb_start_writeback(&bdi->wb, work);
+	else {
+		struct bdi_writeback *wb;
+		int idx;
+
+		idx = srcu_read_lock(&bdi->srcu);
+
+		list_for_each_entry_rcu(wb, &bdi->wb_list, list)
+			wb_start_writeback(wb, work);
+
+		srcu_read_unlock(&bdi->srcu, idx);
+	}
+}
+
+static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+	if (work) {
+		work->seen = bdi->wb_mask;
+		BUG_ON(!work->seen);
+		atomic_set(&work->pending, bdi->wb_cnt);
+		BUG_ON(!bdi->wb_cnt);
+
+		/*
+		 * Make sure stores are seen before it appears on the list
+		 */
+		smp_mb();
+
+		spin_lock(&bdi->wb_lock);
+		list_add_tail_rcu(&work->list, &bdi->work_list);
+		spin_unlock(&bdi->wb_lock);
+	}
+
+	/*
+	 * If the default thread isn't there, make sure we add it. When
+	 * it gets created and wakes up, we'll run this work.
+	 */
+	if (unlikely(list_empty_careful(&bdi->wb_list)))
+		wake_up_process(default_backing_dev_info.wb.task);
+	else
+		bdi_sched_work(bdi, work);
+}
+
+/*
+ * Used for on-stack allocated work items. The caller needs to wait until
+ * the wb threads have acked the work before it's safe to continue.
+ */
+static void bdi_wait_on_work_clear(struct bdi_work *work)
+{
+	wait_on_bit(&work->state, 0, bdi_sched_wait, TASK_UNINTERRUPTIBLE);
+}
+
+static struct bdi_work *bdi_alloc_work(struct super_block *sb, long nr_pages,
+				       enum writeback_sync_modes sync_mode)
+{
+	struct bdi_work *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work)
+		bdi_work_init(work, sb, nr_pages, sync_mode);
+
+	return work;
+}
+
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+			 long nr_pages, enum writeback_sync_modes sync_mode)
+{
+	const bool must_wait = sync_mode == WB_SYNC_ALL;
+	struct bdi_work work_stack, *work = NULL;
+
+	if (!must_wait)
+		work = bdi_alloc_work(sb, nr_pages, sync_mode);
+
+	if (!work) {
+		work = &work_stack;
+		bdi_work_init_on_stack(work, sb, nr_pages, sync_mode);
+	}
+
+	bdi_queue_work(bdi, work);
+
+	/*
+	 * If the sync mode is WB_SYNC_ALL, block waiting for the work to
+	 * complete. If not, we only need to wait for the work to be started,
+	 * if we allocated it on-stack. We use the same mechanism, if the
+	 * wait bit is set in the bdi_work struct, then threads will not
+	 * clear pending until after they are done.
+	 *
+	 * Note that work == &work_stack if must_wait is true, so we don't
+	 * need to do call_rcu() here ever, since the completion path will
+	 * have done that for us.
+	 */
+	if (must_wait || work == &work_stack) {
+		bdi_wait_on_work_clear(work);
+		if (work != &work_stack)
+			call_rcu(&work->rcu_head, bdi_work_free);
+	}
+}
+
+/*
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation.  We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode.  Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES     1024
+
+static inline bool over_bground_thresh(void)
+{
+	unsigned long background_thresh, dirty_thresh;
+
+	get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+
+	return (global_page_state(NR_FILE_DIRTY) +
+		global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
+}
+
+/*
+ * Explicit flushing or periodic writeback of "old" data.
+ *
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in the inode's address_space.  So this periodic writeback code
+ * just walks the superblock inode list, writing back any inodes which are
+ * older than a specific point in time.
+ *
+ * Try to run once per dirty_writeback_interval.  But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
+ * one-second gap.
+ *
+ * older_than_this takes precedence over nr_to_write.  So we'll only write back
+ * all dirty pages if they are all attached to "old" mappings.
+ */
+static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
+			 struct super_block *sb,
+			 enum writeback_sync_modes sync_mode, int for_kupdate)
+{
+	struct writeback_control wbc = {
+		.bdi			= wb->bdi,
+		.sync_mode		= sync_mode,
+		.older_than_this	= NULL,
+		.for_kupdate		= for_kupdate,
+		.range_cyclic		= 1,
+	};
+	unsigned long oldest_jif;
+	long wrote = 0;
+
+	if (wbc.for_kupdate) {
+		wbc.older_than_this = &oldest_jif;
+		oldest_jif = jiffies -
+				msecs_to_jiffies(dirty_expire_interval * 10);
+	}
+
+	for (;;) {
+		if (sync_mode == WB_SYNC_NONE && nr_pages <= 0 &&
+		    !over_bground_thresh())
+			break;
+
+		wbc.more_io = 0;
+		wbc.encountered_congestion = 0;
+		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+		wbc.pages_skipped = 0;
+		generic_sync_wb_inodes(wb, sb, &wbc);
+		nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+		wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+		/*
+		 * If we ran out of stuff to write, bail unless more_io got set
+		 */
+		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
+			if (wbc.more_io && !wbc.for_kupdate)
+				continue;
+			break;
+		}
+	}
+
+	return wrote;
+}
+
+/*
+ * Return the next bdi_work struct that hasn't been processed by this
+ * wb thread yet
+ */
+static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi,
+					   struct bdi_writeback *wb)
+{
+	struct bdi_work *work, *ret = NULL;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(work, &bdi->work_list, list) {
+		if (!test_and_clear_bit(wb->nr, &work->seen))
+			continue;
+
+		ret = work;
+		break;
+	}
+
+	rcu_read_unlock();
+	return ret;
+}
+
+/*
+ * Retrieve work items and do the writeback they describe
+ */
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+{
+	struct backing_dev_info *bdi = wb->bdi;
+	struct bdi_work *work;
+	long nr_pages, wrote = 0;
+
+	while ((work = get_next_work_item(bdi, wb)) != NULL) {
+		struct super_block *sb = bdi_work_sb(work);
+		enum writeback_sync_modes sync_mode;
+
+		nr_pages = work->nr_pages;
+
+		/*
+		 * Override sync mode, in case we must wait for completion
+		 */
+		if (force_wait)
+			work->sync_mode = sync_mode = WB_SYNC_ALL;
+		else
+			sync_mode = work->sync_mode;
+
+		/*
+		 * If this isn't a data integrity operation, just notify
+		 * that we have seen this work and we are now starting it.
+		 */
+		if (sync_mode == WB_SYNC_NONE)
+			wb_clear_pending(wb, work);
+
+		wrote += wb_writeback(wb, nr_pages, sb, sync_mode, 0);
+
+		/*
+		 * This is a data integrity writeback, so only do the
+		 * notification when we have completed the work.
+		 */
+		if (sync_mode == WB_SYNC_ALL)
+			wb_clear_pending(wb, work);
+	}
+
+	/*
+	 * Check for periodic writeback, kupdated() style
+	 */
+	if (!wrote) {
+		nr_pages = global_page_state(NR_FILE_DIRTY) +
+				global_page_state(NR_UNSTABLE_NFS) +
+				(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+		wrote = wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
+	}
+
+	return wrote;
+}
+
+/*
+ * Handle writeback of dirty data for the device backed by this bdi. Also
+ * wakes up periodically and does kupdated style flushing.
  */
-static void writeback_release(struct backing_dev_info *bdi)
+int bdi_writeback_task(struct bdi_writeback *wb)
 {
-	BUG_ON(!writeback_in_progress(bdi));
-	clear_bit(BDI_pdflush, &bdi->state);
+	unsigned long last_active = jiffies;
+	unsigned long wait_jiffies = -1UL;
+	long pages_written;
+
+	while (!kthread_should_stop()) {
+		pages_written = wb_do_writeback(wb, 0);
+
+		if (pages_written)
+			last_active = jiffies;
+		else if (wait_jiffies != -1UL) {
+			unsigned long max_idle;
+
+			/*
+			 * Longest period of inactivity that we tolerate. If we
+			 * see dirty data again later, the task will get
+			 * recreated automatically.
+			 */
+			max_idle = max(5UL * 60 * HZ, wait_jiffies);
+			if (time_after(jiffies, max_idle + last_active) &&
+			    wb_is_default_task(wb))
+				break;
+		}
+
+		wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(wait_jiffies);
+		try_to_freeze();
+	}
+
+	return 0;
+}
+
+/*
+ * Schedule writeback for all backing devices. Expensive! If this is a data
+ * integrity operation, writeback will be complete when this returns. If
+ * we are simply called for WB_SYNC_NONE, then writeback will merely be
+ * scheduled to run.
+ */
+void bdi_writeback_all(struct super_block *sb, struct writeback_control *wbc)
+{
+	const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+	struct backing_dev_info *bdi;
+	struct bdi_work *work;
+	LIST_HEAD(list);
+
+restart:
+	spin_lock(&bdi_lock);
+
+	list_for_each_entry(bdi, &bdi_list, bdi_list) {
+		struct bdi_work *work;
+
+		if (!bdi_has_dirty_io(bdi))
+			continue;
+
+		/*
+		 * If work allocation fails, do the writes inline. We drop
+		 * the lock and restart the list writeout. This should be OK,
+		 * since this happens rarely and because the writeout should
+		 * eventually make more free memory available.
+		 */
+		work = bdi_alloc_work(sb, wbc->nr_to_write, wbc->sync_mode);
+		if (!work) {
+			struct writeback_control __wbc = *wbc;
+
+			/*
+			 * Not a data integrity writeout, just continue
+			 */
+			if (!must_wait)
+				continue;
+
+			spin_unlock(&bdi_lock);
+			__wbc = *wbc;
+			__wbc.bdi = bdi;
+			generic_sync_bdi_inodes(sb, &__wbc);
+			goto restart;
+		}
+		if (must_wait)
+			list_add_tail(&work->wait_list, &list);
+
+		bdi_queue_work(bdi, work);
+	}
+
+	spin_unlock(&bdi_lock);
+
+	/*
+	 * If this is for WB_SYNC_ALL, wait for pending work to complete
+	 * before returning.
+	 */
+	while (!list_empty(&list)) {
+		work = list_entry(list.next, struct bdi_work, wait_list);
+		list_del(&work->wait_list);
+		bdi_wait_on_work_clear(work);
+		call_rcu(&work->rcu_head, bdi_work_free);
+	}
 }
 
 static noinline void block_dump___mark_inode_dirty(struct inode *inode)
@@ -86,6 +544,21 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 	}
 }
 
+/*
+ * If the filesystem didn't provide a way to map an inode to a dedicated
+ * flusher thread, it doesn't support more than 1 thread. So we know it's
+ * the default thread, return that.
+ */
+static inline struct bdi_writeback *inode_get_wb(struct inode *inode)
+{
+	const struct super_operations *sop = inode->i_sb->s_op;
+
+	if (!sop->inode_get_wb)
+		return &inode_to_bdi(inode)->wb;
+
+	return sop->inode_get_wb(inode);
+}
+
 /**
  *	__mark_inode_dirty -	internal function
  *	@inode: inode to mark
@@ -165,12 +638,21 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			goto out;
 
 		/*
-		 * If the inode was already on s_dirty/s_io/s_more_io, don't
-		 * reposition it (that would break s_dirty time-ordering).
+		 * If the inode was already on b_dirty/b_io/b_more_io, don't
+		 * reposition it (that would break b_dirty time-ordering).
 		 */
 		if (!was_dirty) {
+			struct bdi_writeback *wb = inode_get_wb(inode);
+			struct backing_dev_info *bdi = wb->bdi;
+
+			if (bdi_cap_writeback_dirty(bdi) &&
+			    !test_bit(BDI_registered, &bdi->state)) {
+				WARN_ON(1);
+				printk("bdi-%s not registered\n", bdi->name);
+			}
+
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &sb->s_dirty);
+			list_move(&inode->i_list, &wb->b_dirty);
 		}
 	}
 out:
@@ -191,31 +673,32 @@ static int write_inode(struct inode *inode, int sync)
  * furthest end of its superblock's dirty-inode list.
  *
  * Before stamping the inode's ->dirtied_when, we check to see whether it is
- * already the most-recently-dirtied inode on the s_dirty list.  If that is
+ * already the most-recently-dirtied inode on the b_dirty list.  If that is
  * the case then the inode must have been redirtied while it was being written
  * out and we don't reset its dirtied_when.
  */
 static void redirty_tail(struct inode *inode)
 {
-	struct super_block *sb = inode->i_sb;
+	struct bdi_writeback *wb = inode_get_wb(inode);
 
-	if (!list_empty(&sb->s_dirty)) {
-		struct inode *tail_inode;
+	if (!list_empty(&wb->b_dirty)) {
+		struct inode *tail;
 
-		tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
-		if (time_before(inode->dirtied_when,
-				tail_inode->dirtied_when))
+		tail = list_entry(wb->b_dirty.next, struct inode, i_list);
+		if (time_before(inode->dirtied_when, tail->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
-	list_move(&inode->i_list, &sb->s_dirty);
+	list_move(&inode->i_list, &wb->b_dirty);
 }
 
 /*
- * requeue inode for re-scanning after sb->s_io list is exhausted.
+ * requeue inode for re-scanning after bdi->b_io list is exhausted.
  */
 static void requeue_io(struct inode *inode)
 {
-	list_move(&inode->i_list, &inode->i_sb->s_more_io);
+	struct bdi_writeback *wb = inode_get_wb(inode);
+
+	list_move(&inode->i_list, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
@@ -262,21 +745,12 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 /*
  * Queue all expired dirty inodes for io, eldest first.
  */
-static void queue_io(struct super_block *sb,
-				unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
-	list_splice_init(&sb->s_more_io, sb->s_io.prev);
-	move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
+	list_splice_init(&wb->b_more_io, wb->b_io.prev);
+	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
 }
 
-int sb_has_dirty_inodes(struct super_block *sb)
-{
-	return !list_empty(&sb->s_dirty) ||
-	       !list_empty(&sb->s_io) ||
-	       !list_empty(&sb->s_more_io);
-}
-EXPORT_SYMBOL(sb_has_dirty_inodes);
-
 /*
  * Wait for writeback on an inode to complete.
  */
@@ -322,11 +796,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	if (inode->i_state & I_SYNC) {
 		/*
 		 * If this inode is locked for writeback and we are not doing
-		 * writeback-for-data-integrity, move it to s_more_io so that
+		 * writeback-for-data-integrity, move it to b_more_io so that
 		 * writeback can proceed with the other inodes on s_io.
 		 *
 		 * We'll have another go at writing back this inode when we
-		 * completed a full scan of s_io.
+		 * completed a full scan of b_io.
 		 */
 		if (!wait) {
 			requeue_io(inode);
@@ -371,11 +845,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			/*
 			 * We didn't write back all the pages.  nfs_writepages()
 			 * sometimes bales out without doing anything. Redirty
-			 * the inode; Move it from s_io onto s_more_io/s_dirty.
+			 * the inode; Move it from b_io onto b_more_io/b_dirty.
 			 */
 			/*
 			 * akpm: if the caller was the kupdate function we put
-			 * this inode at the head of s_dirty so it gets first
+			 * this inode at the head of b_dirty so it gets first
 			 * consideration.  Otherwise, move it to the tail, for
 			 * the reasons described there.  I'm not really sure
 			 * how much sense this makes.  Presumably I had a good
@@ -385,7 +859,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			if (wbc->for_kupdate) {
 				/*
 				 * For the kupdate function we move the inode
-				 * to s_more_io so it will get more writeout as
+				 * to b_more_io so it will get more writeout as
 				 * soon as the queue becomes uncongested.
 				 */
 				inode->i_state |= I_DIRTY_PAGES;
@@ -433,51 +907,34 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	return ret;
 }
 
-/*
- * Write out a superblock's list of dirty inodes.  A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If we're a pdflush thread, then implement pdflush collision avoidance
- * against the entire list.
- *
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched.  For other superblocks,
- * assume that all inodes are backed by the same queue.
- *
- * FIXME: this linear search could get expensive with many fileystems.  But
- * how to fix?  We need to go from an address_space to all inodes which share
- * a queue with that address_space.  (Easy: have a global "dirty superblocks"
- * list).
- *
- * The inodes to be written are parked on sb->s_io.  They are moved back onto
- * sb->s_dirty as they are selected for writing.  This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
- */
-void generic_sync_sb_inodes(struct super_block *sb,
-				struct writeback_control *wbc)
+static void generic_sync_wb_inodes(struct bdi_writeback *wb,
+				   struct super_block *sb,
+				   struct writeback_control *wbc)
 {
+	const int is_blkdev_sb = sb_is_blkdev_sb(sb);
 	const unsigned long start = jiffies;	/* livelock avoidance */
-	int sync = wbc->sync_mode == WB_SYNC_ALL;
 
 	spin_lock(&inode_lock);
-	if (!wbc->for_kupdate || list_empty(&sb->s_io))
-		queue_io(sb, wbc->older_than_this);
 
-	while (!list_empty(&sb->s_io)) {
-		struct inode *inode = list_entry(sb->s_io.prev,
+	if (!wbc->for_kupdate || list_empty(&wb->b_io))
+		queue_io(wb, wbc->older_than_this);
+
+	while (!list_empty(&wb->b_io)) {
+		struct inode *inode = list_entry(wb->b_io.prev,
 						struct inode, i_list);
-		struct address_space *mapping = inode->i_mapping;
-		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		long pages_skipped;
 
-		if (!bdi_cap_writeback_dirty(bdi)) {
+		/*
+		 * super block given and doesn't match, skip this inode
+		 */
+		if (sb && sb != inode->i_sb) {
 			redirty_tail(inode);
-			if (sb_is_blkdev_sb(sb)) {
+			continue;
+		}
+
+		if (!bdi_cap_writeback_dirty(wb->bdi)) {
+			redirty_tail(inode);
+			if (is_blkdev_sb) {
 				/*
 				 * Dirty memory-backed blockdev: the ramdisk
 				 * driver does this.  Skip just this inode
@@ -497,21 +954,14 @@ void generic_sync_sb_inodes(struct super_block *sb,
 			continue;
 		}
 
-		if (wbc->nonblocking && bdi_write_congested(bdi)) {
+		if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
 			wbc->encountered_congestion = 1;
-			if (!sb_is_blkdev_sb(sb))
+			if (!is_blkdev_sb)
 				break;		/* Skip a congested fs */
 			requeue_io(inode);
 			continue;		/* Skip a congested blockdev */
 		}
 
-		if (wbc->bdi && bdi != wbc->bdi) {
-			if (!sb_is_blkdev_sb(sb))
-				break;		/* fs has the wrong queue */
-			requeue_io(inode);
-			continue;		/* blockdev has wrong queue */
-		}
-
 		/*
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
@@ -519,16 +969,10 @@ void generic_sync_sb_inodes(struct super_block *sb,
 		if (inode_dirtied_after(inode, start))
 			break;
 
-		/* Is another pdflush already flushing this queue? */
-		if (current_is_pdflush() && !writeback_acquire(bdi))
-			break;
-
 		BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		writeback_single_inode(inode, wbc);
-		if (current_is_pdflush())
-			writeback_release(bdi);
 		if (wbc->pages_skipped != pages_skipped) {
 			/*
 			 * writeback is not making progress due to locked
@@ -544,13 +988,71 @@ void generic_sync_sb_inodes(struct super_block *sb,
 			wbc->more_io = 1;
 			break;
 		}
-		if (!list_empty(&sb->s_more_io))
+		if (!list_empty(&wb->b_more_io))
 			wbc->more_io = 1;
 	}
 
-	if (sync) {
+	spin_unlock(&inode_lock);
+	/* Leave any unwritten inodes on b_io */
+}
+
+void generic_sync_bdi_inodes(struct super_block *sb,
+			     struct writeback_control *wbc)
+{
+	struct backing_dev_info *bdi = wbc->bdi;
+	struct bdi_writeback *wb;
+
+	/*
+	 * Common case is just a single wb thread and that is embedded in
+	 * the bdi, so it doesn't need locking
+	 */
+	if (!bdi_wblist_needs_lock(bdi))
+		generic_sync_wb_inodes(&bdi->wb, sb, wbc);
+	else {
+		int idx;
+
+		idx = srcu_read_lock(&bdi->srcu);
+
+		list_for_each_entry_rcu(wb, &bdi->wb_list, list)
+			generic_sync_wb_inodes(wb, sb, wbc);
+
+		srcu_read_unlock(&bdi->srcu, idx);
+	}
+}
+
+/*
+ * Write out a superblock's list of dirty inodes.  A wait will be performed
+ * upon no inodes, all inodes or the final one, depending upon sync_mode.
+ *
+ * If older_than_this is non-NULL, then only write out inodes which
+ * had their first dirtying at a time earlier than *older_than_this.
+ *
+ * If we're a pdlfush thread, then implement pdflush collision avoidance
+ * against the entire list.
+ *
+ * If `bdi' is non-zero then we're being asked to writeback a specific queue.
+ * This function assumes that the blockdev superblock's inodes are backed by
+ * a variety of queues, so all inodes are searched.  For other superblocks,
+ * assume that all inodes are backed by the same queue.
+ *
+ * The inodes to be written are parked on bdi->b_io.  They are moved back onto
+ * bdi->b_dirty as they are selected for writing.  This way, none can be missed
+ * on the writer throttling path, and we get decent balancing between many
+ * throttled threads: we don't want them all piling up on inode_sync_wait.
+ */
+void generic_sync_sb_inodes(struct super_block *sb,
+				struct writeback_control *wbc)
+{
+	if (wbc->bdi)
+		bdi_start_writeback(wbc->bdi, sb, wbc->nr_to_write, wbc->sync_mode);
+	else
+		bdi_writeback_all(sb, wbc);
+
+	if (wbc->sync_mode == WB_SYNC_ALL) {
 		struct inode *inode, *old_inode = NULL;
 
+		spin_lock(&inode_lock);
+
 		/*
 		 * Data integrity sync. Must wait for all pages under writeback,
 		 * because there may have been pages dirtied before our sync
@@ -588,10 +1090,8 @@ void generic_sync_sb_inodes(struct super_block *sb,
 		}
 		spin_unlock(&inode_lock);
 		iput(old_inode);
-	} else
-		spin_unlock(&inode_lock);
+	}
 
-	return;		/* Leave any unwritten inodes on s_io */
 }
 EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
 
@@ -602,58 +1102,6 @@ static void sync_sb_inodes(struct super_block *sb,
 }
 
 /*
- * Start writeback of dirty pagecache data against all unlocked inodes.
- *
- * Note:
- * We don't need to grab a reference to superblock here. If it has non-empty
- * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
- * empty. Since __sync_single_inode() regains inode_lock before it finally moves
- * inode from superblock lists we are OK.
- *
- * If `older_than_this' is non-zero then only flush inodes which have a
- * flushtime older than *older_than_this.
- *
- * If `bdi' is non-zero then we will scan the first inode against each
- * superblock until we find the matching ones.  One group will be the dirty
- * inodes against a filesystem.  Then when we hit the dummy blockdev superblock,
- * sync_sb_inodes will seekout the blockdev which matches `bdi'.  Maybe not
- * super-efficient but we're about to do a ton of I/O...
- */
-void
-writeback_inodes(struct writeback_control *wbc)
-{
-	struct super_block *sb;
-
-	might_sleep();
-	spin_lock(&sb_lock);
-restart:
-	list_for_each_entry_reverse(sb, &super_blocks, s_list) {
-		if (sb_has_dirty_inodes(sb)) {
-			/* we're making our own get_super here */
-			sb->s_count++;
-			spin_unlock(&sb_lock);
-			/*
-			 * If we can't get the readlock, there's no sense in
-			 * waiting around, most of the time the FS is going to
-			 * be unmounted by the time it is released.
-			 */
-			if (down_read_trylock(&sb->s_umount)) {
-				if (sb->s_root)
-					sync_sb_inodes(sb, wbc);
-				up_read(&sb->s_umount);
-			}
-			spin_lock(&sb_lock);
-			if (__put_super_and_need_restart(sb))
-				goto restart;
-		}
-		if (wbc->nr_to_write <= 0)
-			break;
-	}
-	spin_unlock(&sb_lock);
-}
-
-/*
  * writeback and wait upon the filesystem's dirty inodes.  The caller will
  * do this in two passes - one to write, and one to wait.
  *
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 9aa6f46d0c32..a9a9cfff30ca 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -815,6 +815,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 {
 	int err;
 
+	fc->bdi.name = "fuse";
 	fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	fc->bdi.unplug_io_fn = default_unplug_io_fn;
 	/* fuse does it's own writeback accounting */
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 941c8425c10b..2d8abaf3b8a8 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -44,6 +44,7 @@ static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
 static struct backing_dev_info hugetlbfs_backing_dev_info = {
+	.name		= "hugetlbfs",
 	.ra_pages	= 0,	/* No readahead */
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index d36925f9b952..e350bd6a2334 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -882,6 +882,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 		server->rsize = NFS_MAX_FILE_IO_SIZE;
 	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
+	server->backing_dev_info.name = "nfs";
 	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
 
 	if (server->wsize > max_rpc_payload)
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index 1c9efb406a96..02bf17808bdc 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -325,6 +325,7 @@ clear_fields:
 }
 
 static struct backing_dev_info dlmfs_backing_dev_info = {
+	.name		= "ocfs2-dlmfs",
 	.ra_pages	= 0,	/* No readahead */
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 0ff7566c767c..a7f0110fca4c 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -46,6 +46,7 @@ static const struct super_operations ramfs_ops;
 static const struct inode_operations ramfs_dir_inode_operations;
 
 static struct backing_dev_info ramfs_backing_dev_info = {
+	.name		= "ramfs",
 	.ra_pages	= 0,	/* No readahead */
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK |
 			  BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
diff --git a/fs/super.c b/fs/super.c
index 2761d3e22ed9..0d22ce3be4aa 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -62,9 +62,6 @@ static struct super_block *alloc_super(struct file_system_type *type)
 			s = NULL;
 			goto out;
 		}
-		INIT_LIST_HEAD(&s->s_dirty);
-		INIT_LIST_HEAD(&s->s_io);
-		INIT_LIST_HEAD(&s->s_more_io);
 		INIT_LIST_HEAD(&s->s_files);
 		INIT_LIST_HEAD(&s->s_instances);
 		INIT_HLIST_HEAD(&s->s_anon);
diff --git a/fs/sync.c b/fs/sync.c
index 3422ba61d86d..bf03fc75b392 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -118,7 +118,7 @@ restart:
  */
 SYSCALL_DEFINE0(sync)
 {
-	wakeup_pdflush(0);
+	wakeup_flusher_threads(0);
 	sync_filesystems(0);
 	sync_filesystems(1);
 	if (unlikely(laptop_mode))
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 555f0ff988df..e57f98e54fce 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -29,6 +29,7 @@ static const struct address_space_operations sysfs_aops = {
 };
 
 static struct backing_dev_info sysfs_backing_dev_info = {
+	.name		= "sysfs",
 	.ra_pages	= 0,	/* No readahead */
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index b541bd75bd1f..22b2db3cad23 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1950,6 +1950,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	 *
 	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
 	 */
+	c->bdi.name = "ubifs",
 	c->bdi.capabilities = BDI_CAP_MAP_COPY;
 	c->bdi.unplug_io_fn = default_unplug_io_fn;
 	err  = bdi_init(&c->bdi);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1d52425a6118..47ed0f22d020 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,9 @@
 #include <linux/proportions.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/srcu.h>
+#include <linux/writeback.h>
 #include <asm/atomic.h>
 
 struct page;
@@ -23,9 +26,12 @@ struct dentry;
  * Bits in backing_dev_info.state
  */
 enum bdi_state {
-	BDI_pdflush,		/* A pdflush thread is working this device */
+	BDI_pending,		/* On its way to being activated */
+	BDI_wb_alloc,		/* Default embedded wb allocated */
+	BDI_wblist_lock,	/* bdi->wb_list now needs locking */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
+	BDI_registered,		/* bdi_register() was done */
 	BDI_unused,		/* Available bits start here */
 };
 
@@ -39,7 +45,23 @@ enum bdi_stat_item {
 
 #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
+struct bdi_writeback {
+	struct list_head list;			/* hangs off the bdi */
+
+	struct backing_dev_info *bdi;		/* our parent bdi */
+	unsigned int nr;
+
+	struct task_struct	*task;		/* writeback task */
+	struct list_head	b_dirty;	/* dirty inodes */
+	struct list_head	b_io;		/* parked for writeback */
+	struct list_head	b_more_io;	/* parked for more writeback */
+};
+
+#define BDI_MAX_FLUSHERS	32
+
 struct backing_dev_info {
+	struct srcu_struct srcu; /* for wb_list read side protection */
+	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
 	unsigned long state;	/* Always use atomic bitops on this */
 	unsigned int capabilities; /* Device capabilities */
@@ -48,6 +70,8 @@ struct backing_dev_info {
 	void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
 	void *unplug_io_data;
 
+	char *name;
+
 	struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
 
 	struct prop_local_percpu completions;
@@ -56,6 +80,14 @@ struct backing_dev_info {
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;
 
+	struct bdi_writeback wb;  /* default writeback info for this bdi */
+	spinlock_t wb_lock;	  /* protects update side of wb_list */
+	struct list_head wb_list; /* the flusher threads hanging off this bdi */
+	unsigned long wb_mask;	  /* bitmask of registered tasks */
+	unsigned int wb_cnt;	  /* number of registered tasks */
+
+	struct list_head work_list;
+
 	struct device *dev;
 
 #ifdef CONFIG_DEBUG_FS
@@ -71,6 +103,32 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+			 long nr_pages, enum writeback_sync_modes sync_mode);
+int bdi_writeback_task(struct bdi_writeback *wb);
+void bdi_writeback_all(struct super_block *sb, struct writeback_control *wbc);
+void bdi_add_flusher_task(struct backing_dev_info *bdi);
+int bdi_has_dirty_io(struct backing_dev_info *bdi);
+
+extern spinlock_t bdi_lock;
+extern struct list_head bdi_list;
+
+static inline int wb_is_default_task(struct bdi_writeback *wb)
+{
+	return wb == &wb->bdi->wb;
+}
+
+static inline int bdi_wblist_needs_lock(struct backing_dev_info *bdi)
+{
+	return test_bit(BDI_wblist_lock, &bdi->state);
+}
+
+static inline int wb_has_dirty_io(struct bdi_writeback *wb)
+{
+	return !list_empty(&wb->b_dirty) ||
+	       !list_empty(&wb->b_io) ||
+	       !list_empty(&wb->b_more_io);
+}
 
 static inline void __add_bdi_stat(struct backing_dev_info *bdi,
 		enum bdi_stat_item item, s64 amount)
@@ -261,6 +319,11 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
 	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
 }
 
+static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
+{
+	return bdi == &default_backing_dev_info;
+}
+
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -276,4 +339,10 @@ static inline bool mapping_cap_swap_backed(struct address_space *mapping)
 	return bdi_cap_swap_backed(mapping->backing_dev_info);
 }
 
+static inline int bdi_sched_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
 #endif		/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2892b710771c..5be93f18d842 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -142,56 +142,51 @@ struct bio {
  *
  * bit 0 -- data direction
  *	If not set, bio is a read from device. If set, it's a write to device.
- * bit 1 -- rw-ahead when set
- * bit 2 -- barrier
+ * bit 1 -- fail fast device errors
+ * bit 2 -- fail fast transport errors
+ * bit 3 -- fail fast driver errors
+ * bit 4 -- rw-ahead when set
+ * bit 5 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
  *	submitted IO to be completed before this one is issued.
- * bit 3 -- synchronous I/O hint.
- * bit 4 -- Unplug the device immediately after submitting this bio.
- * bit 5 -- metadata request
+ * bit 6 -- synchronous I/O hint.
+ * bit 7 -- Unplug the device immediately after submitting this bio.
+ * bit 8 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 6 -- discard sectors
+ * bit 9 -- discard sectors
  *	Informs the lower level device that this range of sectors is no longer
  *	used by the file system and may thus be freed by the device. Used
  *	for flash based storage.
- * bit 7 -- fail fast device errors
- * bit 8 -- fail fast transport errors
- * bit 9 -- fail fast driver errors
  *	Don't want driver retries for any fast fail whatever the reason.
  * bit 10 -- Tell the IO scheduler not to wait for more requests after this
 	one has been submitted, even if it is a SYNC request.
  */
-#define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
-#define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
-#define BIO_RW_BARRIER	2
-#define BIO_RW_SYNCIO	3
-#define BIO_RW_UNPLUG	4
-#define BIO_RW_META	5
-#define BIO_RW_DISCARD	6
-#define BIO_RW_FAILFAST_DEV		7
-#define BIO_RW_FAILFAST_TRANSPORT	8
-#define BIO_RW_FAILFAST_DRIVER		9
-#define BIO_RW_NOIDLE	10
-
-#define bio_rw_flagged(bio, flag)	((bio)->bi_rw & (1 << (flag)))
+enum bio_rw_flags {
+	BIO_RW,
+	BIO_RW_FAILFAST_DEV,
+	BIO_RW_FAILFAST_TRANSPORT,
+	BIO_RW_FAILFAST_DRIVER,
+	/* above flags must match REQ_* */
+	BIO_RW_AHEAD,
+	BIO_RW_BARRIER,
+	BIO_RW_SYNCIO,
+	BIO_RW_UNPLUG,
+	BIO_RW_META,
+	BIO_RW_DISCARD,
+	BIO_RW_NOIDLE,
+};
 
 /*
- * Old defines, these should eventually be replaced by direct usage of
- * bio_rw_flagged()
+ * First four bits must match between bio->bi_rw and rq->cmd_flags, make
+ * that explicit here.
  */
-#define bio_barrier(bio)	bio_rw_flagged(bio, BIO_RW_BARRIER)
-#define bio_sync(bio)		bio_rw_flagged(bio, BIO_RW_SYNCIO)
-#define bio_unplug(bio)		bio_rw_flagged(bio, BIO_RW_UNPLUG)
-#define bio_failfast_dev(bio)	bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV)
-#define bio_failfast_transport(bio)	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT)
-#define bio_failfast_driver(bio) 	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER)
-#define bio_rw_ahead(bio)	bio_rw_flagged(bio, BIO_RW_AHEAD)
-#define bio_rw_meta(bio)	bio_rw_flagged(bio, BIO_RW_META)
-#define bio_discard(bio)	bio_rw_flagged(bio, BIO_RW_DISCARD)
-#define bio_noidle(bio)		bio_rw_flagged(bio, BIO_RW_NOIDLE)
+#define BIO_RW_RQ_MASK		0xf
+
+static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
+{
+	return (bio->bi_rw & (1 << flag)) != 0;
+}
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -216,7 +211,7 @@ struct bio {
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
-#define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
+#define bio_empty_barrier(bio)	(bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h
new file mode 100644
index 000000000000..308734d3d4a2
--- /dev/null
+++ b/include/linux/blk-iopoll.h
@@ -0,0 +1,48 @@
+#ifndef BLK_IOPOLL_H
+#define BLK_IOPOLL_H
+
+struct blk_iopoll;
+typedef int (blk_iopoll_fn)(struct blk_iopoll *, int);
+
+struct blk_iopoll {
+	struct list_head list;
+	unsigned long state;
+	unsigned long data;
+	int weight;
+	int max;
+	blk_iopoll_fn *poll;
+};
+
+enum {
+	IOPOLL_F_SCHED		= 0,
+	IOPOLL_F_DISABLE	= 1,
+};
+
+/*
+ * Returns 0 if we successfully set the IOPOLL_F_SCHED bit, indicating
+ * that we were the first to acquire this iop for scheduling. If this iop
+ * is currently disabled, return "failure".
+ */
+static inline int blk_iopoll_sched_prep(struct blk_iopoll *iop)
+{
+	if (!test_bit(IOPOLL_F_DISABLE, &iop->state))
+		return test_and_set_bit(IOPOLL_F_SCHED, &iop->state);
+
+	return 1;
+}
+
+static inline int blk_iopoll_disable_pending(struct blk_iopoll *iop)
+{
+	return test_bit(IOPOLL_F_DISABLE, &iop->state);
+}
+
+extern void blk_iopoll_sched(struct blk_iopoll *);
+extern void blk_iopoll_init(struct blk_iopoll *, int, blk_iopoll_fn *);
+extern void blk_iopoll_complete(struct blk_iopoll *);
+extern void __blk_iopoll_complete(struct blk_iopoll *);
+extern void blk_iopoll_enable(struct blk_iopoll *);
+extern void blk_iopoll_disable(struct blk_iopoll *);
+
+extern int blk_iopoll_enabled;
+
+#endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 69103e053c92..4c0f724511f5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -86,13 +86,14 @@ enum {
 };
 
 /*
- * request type modified bits. first two bits match BIO_RW* bits, important
+ * request type modified bits. first four bits match BIO_RW* bits, important
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
 	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
+	/* above flags must match BIO_RW_* */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
@@ -114,6 +115,7 @@ enum rq_flag_bits {
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_IO_STAT,		/* account I/O stat */
+	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -142,6 +144,10 @@ enum rq_flag_bits {
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 #define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 #define REQ_IO_STAT	(1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE	(1 << __REQ_MIXED_MERGE)
+
+#define REQ_FAILFAST_MASK	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
+				 REQ_FAILFAST_DRIVER)
 
 #define BLK_MAX_CDB	16
 
@@ -453,6 +459,7 @@ struct request_queue
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
+#define QUEUE_FLAG_CQ	       16	/* hardware does queuing */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
@@ -575,6 +582,7 @@ enum {
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
+#define blk_queue_queuing(q)	test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
@@ -828,11 +836,13 @@ static inline void blk_run_address_space(struct address_space *mapping)
 }
 
 /*
- * blk_rq_pos()		: the current sector
- * blk_rq_bytes()	: bytes left in the entire request
- * blk_rq_cur_bytes()	: bytes left in the current segment
- * blk_rq_sectors()	: sectors left in the entire request
- * blk_rq_cur_sectors()	: sectors left in the current segment
+ * blk_rq_pos()			: the current sector
+ * blk_rq_bytes()		: bytes left in the entire request
+ * blk_rq_cur_bytes()		: bytes left in the current segment
+ * blk_rq_err_bytes()		: bytes left till the next error boundary
+ * blk_rq_sectors()		: sectors left in the entire request
+ * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_err_sectors()		: sectors left till the next error boundary
  */
 static inline sector_t blk_rq_pos(const struct request *rq)
 {
@@ -849,6 +859,8 @@ static inline int blk_rq_cur_bytes(const struct request *rq)
 	return rq->bio ? bio_cur_bytes(rq->bio) : 0;
 }
 
+extern unsigned int blk_rq_err_bytes(const struct request *rq);
+
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
 	return blk_rq_bytes(rq) >> 9;
@@ -859,6 +871,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> 9;
 }
 
+static inline unsigned int blk_rq_err_sectors(const struct request *rq)
+{
+	return blk_rq_err_bytes(rq) >> 9;
+}
+
 /*
  * Request issue related functions.
  */
@@ -885,10 +902,12 @@ extern bool blk_end_request(struct request *rq, int error,
 			    unsigned int nr_bytes);
 extern void blk_end_request_all(struct request *rq, int error);
 extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool blk_end_request_err(struct request *rq, int error);
 extern bool __blk_end_request(struct request *rq, int error,
 			      unsigned int nr_bytes);
 extern void __blk_end_request_all(struct request *rq, int error);
 extern bool __blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request_err(struct request *rq, int error);
 
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
@@ -921,7 +940,6 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
 extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 			      sector_t offset);
-extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern int blk_queue_dma_drain(struct request_queue *q,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 67888a9e0655..936017fe7214 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -715,7 +715,7 @@ struct posix_acl;
 
 struct inode {
 	struct hlist_node	i_hash;
-	struct list_head	i_list;
+	struct list_head	i_list;		/* backing dev IO list */
 	struct list_head	i_sb_list;
 	struct list_head	i_dentry;
 	unsigned long		i_ino;
@@ -1336,9 +1336,6 @@ struct super_block {
 	struct xattr_handler	**s_xattr;
 
 	struct list_head	s_inodes;	/* all inodes */
-	struct list_head	s_dirty;	/* dirty inodes */
-	struct list_head	s_io;		/* parked for writeback */
-	struct list_head	s_more_io;	/* parked for more writeback */
 	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 	struct list_head	s_files;
 	/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
@@ -1555,11 +1552,14 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
 
+struct bdi_writeback;
+
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
 
    	void (*dirty_inode) (struct inode *);
+	struct bdi_writeback *(*inode_get_wb) (struct inode *);
 	int (*write_inode) (struct inode *, int);
 	void (*drop_inode) (struct inode *);
 	void (*delete_inode) (struct inode *);
@@ -2072,6 +2072,8 @@ extern int invalidate_inode_pages2_range(struct address_space *mapping,
 					 pgoff_t start, pgoff_t end);
 extern void generic_sync_sb_inodes(struct super_block *sb,
 				struct writeback_control *wbc);
+extern void generic_sync_bdi_inodes(struct super_block *sb,
+				struct writeback_control *);
 extern int write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_flush(struct address_space *);
@@ -2186,7 +2188,6 @@ extern int bdev_read_only(struct block_device *);
 extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
-extern int sb_has_dirty_inodes(struct super_block *);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 6967f6aab33a..b7ba6946fa82 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -342,6 +342,7 @@ enum
 	NET_TX_SOFTIRQ,
 	NET_RX_SOFTIRQ,
 	BLOCK_SOFTIRQ,
+	BLOCK_IOPOLL_SOFTIRQ,
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 3224820c8514..e070b91905d6 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -14,17 +14,6 @@ extern struct list_head inode_in_use;
 extern struct list_head inode_unused;
 
 /*
- * Yes, writeback.h requires sched.h
- * No, sched.h is not included from here.
- */
-static inline int task_is_pdflush(struct task_struct *task)
-{
-	return task->flags & PF_FLUSHER;
-}
-
-#define current_is_pdflush()	task_is_pdflush(current)
-
-/*
  * fs/fs-writeback.c
  */
 enum writeback_sync_modes {
@@ -79,6 +68,7 @@ struct writeback_control {
 void writeback_inodes(struct writeback_control *wbc);
 int inode_wait(void *);
 void sync_inodes_sb(struct super_block *, int wait);
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
 
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
@@ -98,7 +88,7 @@ static inline void inode_sync_wait(struct inode *inode)
 /*
  * mm/page-writeback.c
  */
-int wakeup_pdflush(long nr_pages);
+void wakeup_flusher_threads(long nr_pages);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
 void throttle_vm_writeout(gfp_t gfp_mask);
@@ -150,7 +140,6 @@ balance_dirty_pages_ratelimited(struct address_space *mapping)
 typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 				void *data);
 
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc);
 int write_cache_pages(struct address_space *mapping,
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b6eadfe30e7b..c7ece8f027f2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -600,6 +600,7 @@ static struct inode_operations cgroup_dir_inode_operations;
 static struct file_operations proc_cgroupstats_operations;
 
 static struct backing_dev_info cgroup_backing_dev_info = {
+	.name		= "cgroup",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 98e02328c67d..121837ee602a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -91,6 +91,7 @@ extern int sysctl_nr_trim_pages;
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
+extern int blk_iopoll_enabled;
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_DETECT_SOFTLOCKUP
@@ -989,7 +990,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
-
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "blk_iopoll",
+		.data		= &blk_iopoll_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff --git a/mm/Makefile b/mm/Makefile
index 5e0bd6426693..147a7a7873c4 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -8,7 +8,7 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   vmalloc.o
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
-			   maccess.o page_alloc.o page-writeback.o pdflush.o \
+			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o $(mmu-y)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c86edd244294..036b07ba393b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,8 +1,11 @@
 
 #include <linux/wait.h>
 #include <linux/backing-dev.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
+#include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/writeback.h>
@@ -14,6 +17,7 @@ void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
 EXPORT_SYMBOL(default_unplug_io_fn);
 
 struct backing_dev_info default_backing_dev_info = {
+	.name		= "default",
 	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
 	.state		= 0,
 	.capabilities	= BDI_CAP_MAP_COPY,
@@ -22,6 +26,18 @@ struct backing_dev_info default_backing_dev_info = {
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
 static struct class *bdi_class;
+DEFINE_SPINLOCK(bdi_lock);
+LIST_HEAD(bdi_list);
+LIST_HEAD(bdi_pending_list);
+
+static struct task_struct *sync_supers_tsk;
+static struct timer_list sync_supers_timer;
+
+static int bdi_sync_supers(void *);
+static void sync_supers_timer_fn(unsigned long);
+static void arm_supers_timer(void);
+
+static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
 
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
@@ -37,9 +53,29 @@ static void bdi_debug_init(void)
 static int bdi_debug_stats_show(struct seq_file *m, void *v)
 {
 	struct backing_dev_info *bdi = m->private;
+	struct bdi_writeback *wb;
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
+	unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+	struct inode *inode;
+
+	/*
+	 * inode lock is enough here, the bdi->wb_list is protected by
+	 * RCU on the reader side
+	 */
+	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
+	spin_lock(&inode_lock);
+	list_for_each_entry(wb, &bdi->wb_list, list) {
+		nr_wb++;
+		list_for_each_entry(inode, &wb->b_dirty, i_list)
+			nr_dirty++;
+		list_for_each_entry(inode, &wb->b_io, i_list)
+			nr_io++;
+		list_for_each_entry(inode, &wb->b_more_io, i_list)
+			nr_more_io++;
+	}
+	spin_unlock(&inode_lock);
 
 	get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
 
@@ -49,12 +85,22 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "BdiReclaimable:   %8lu kB\n"
 		   "BdiDirtyThresh:   %8lu kB\n"
 		   "DirtyThresh:      %8lu kB\n"
-		   "BackgroundThresh: %8lu kB\n",
+		   "BackgroundThresh: %8lu kB\n"
+		   "WriteBack threads:%8lu\n"
+		   "b_dirty:          %8lu\n"
+		   "b_io:             %8lu\n"
+		   "b_more_io:        %8lu\n"
+		   "bdi_list:         %8u\n"
+		   "state:            %8lx\n"
+		   "wb_mask:          %8lx\n"
+		   "wb_list:          %8u\n"
+		   "wb_cnt:           %8u\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
-		   K(bdi_thresh),
-		   K(dirty_thresh),
-		   K(background_thresh));
+		   K(bdi_thresh), K(dirty_thresh),
+		   K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io,
+		   !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask,
+		   !list_empty(&bdi->wb_list), bdi->wb_cnt);
 #undef K
 
 	return 0;
@@ -185,6 +231,13 @@ static int __init default_bdi_init(void)
 {
 	int err;
 
+	sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
+	BUG_ON(IS_ERR(sync_supers_tsk));
+
+	init_timer(&sync_supers_timer);
+	setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
+	arm_supers_timer();
+
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
@@ -193,6 +246,390 @@ static int __init default_bdi_init(void)
 }
 subsys_initcall(default_bdi_init);
 
+static int wb_assign_nr(struct backing_dev_info *bdi, struct bdi_writeback *wb)
+{
+	unsigned long mask = BDI_MAX_FLUSHERS - 1;
+	unsigned int nr;
+
+	do {
+		if ((bdi->wb_mask & mask) == mask)
+			return 1;
+
+		nr = find_first_zero_bit(&bdi->wb_mask, BDI_MAX_FLUSHERS);
+	} while (test_and_set_bit(nr, &bdi->wb_mask));
+
+	wb->nr = nr;
+
+	spin_lock(&bdi->wb_lock);
+	bdi->wb_cnt++;
+	spin_unlock(&bdi->wb_lock);
+
+	return 0;
+}
+
+static void bdi_put_wb(struct backing_dev_info *bdi, struct bdi_writeback *wb)
+{
+	/*
+	 * If this is the default wb thread exiting, leave the bit set
+	 * in the wb mask as we set that before it's created as well. This
+	 * is done to make sure that assigned work with no thread has at
+	 * least one receipient.
+	 */
+	if (wb == &bdi->wb)
+		clear_bit(BDI_wb_alloc, &bdi->state);
+	else {
+		clear_bit(wb->nr, &bdi->wb_mask);
+		kfree(wb);
+		spin_lock(&bdi->wb_lock);
+		bdi->wb_cnt--;
+		spin_unlock(&bdi->wb_lock);
+	}
+}
+
+static int bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+	memset(wb, 0, sizeof(*wb));
+
+	wb->bdi = bdi;
+	INIT_LIST_HEAD(&wb->b_dirty);
+	INIT_LIST_HEAD(&wb->b_io);
+	INIT_LIST_HEAD(&wb->b_more_io);
+
+	return wb_assign_nr(bdi, wb);
+}
+
+static struct bdi_writeback *bdi_new_wb(struct backing_dev_info *bdi)
+{
+	struct bdi_writeback *wb;
+
+	/*
+	 * Default bdi->wb is already assigned, so just return it
+	 */
+	if (!test_and_set_bit(BDI_wb_alloc, &bdi->state))
+		wb = &bdi->wb;
+	else {
+		wb = kmalloc(sizeof(struct bdi_writeback), GFP_KERNEL);
+		if (wb) {
+			if (bdi_wb_init(wb, bdi)) {
+				kfree(wb);
+				wb = NULL;
+			}
+		}
+	}
+
+	return wb;
+}
+
+static void bdi_task_init(struct backing_dev_info *bdi,
+			  struct bdi_writeback *wb)
+{
+	struct task_struct *tsk = current;
+	int was_empty;
+
+	/*
+	 * Add us to the active bdi_list. If we are adding threads beyond
+	 * the default embedded bdi_writeback, then we need to start using
+	 * proper locking. Check the list for empty first, then set the
+	 * BDI_wblist_lock flag if there's > 1 entry on the list now
+	 */
+	spin_lock(&bdi->wb_lock);
+
+	was_empty = list_empty(&bdi->wb_list);
+	list_add_tail_rcu(&wb->list, &bdi->wb_list);
+	if (!was_empty)
+		set_bit(BDI_wblist_lock, &bdi->state);
+
+	spin_unlock(&bdi->wb_lock);
+
+	tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
+	set_freezable();
+
+	/*
+	 * Our parent may run at a different priority, just set us to normal
+	 */
+	set_user_nice(tsk, 0);
+}
+
+static int bdi_start_fn(void *ptr)
+{
+	struct bdi_writeback *wb = ptr;
+	struct backing_dev_info *bdi = wb->bdi;
+	int ret;
+
+	/*
+	 * Add us to the active bdi_list
+	 */
+	spin_lock(&bdi_lock);
+	list_add(&bdi->bdi_list, &bdi_list);
+	spin_unlock(&bdi_lock);
+
+	bdi_task_init(bdi, wb);
+
+	/*
+	 * Clear pending bit and wakeup anybody waiting to tear us down
+	 */
+	clear_bit(BDI_pending, &bdi->state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&bdi->state, BDI_pending);
+
+	ret = bdi_writeback_task(wb);
+
+	/*
+	 * Remove us from the list
+	 */
+	spin_lock(&bdi->wb_lock);
+	list_del_rcu(&wb->list);
+	spin_unlock(&bdi->wb_lock);
+
+	/*
+	 * wait for rcu grace period to end, so we can free wb
+	 */
+	synchronize_srcu(&bdi->srcu);
+
+	/*
+	 * Flush any work that raced with us exiting. No new work
+	 * will be added, since this bdi isn't discoverable anymore.
+	 */
+	if (!list_empty(&bdi->work_list))
+		wb_do_writeback(wb, 1);
+
+	wb->task = NULL;
+	bdi_put_wb(bdi, wb);
+	return ret;
+}
+
+int bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+	struct bdi_writeback *wb;
+	int ret = 0;
+
+	if (!bdi_wblist_needs_lock(bdi))
+		ret = wb_has_dirty_io(&bdi->wb);
+	else {
+		int idx;
+
+		idx = srcu_read_lock(&bdi->srcu);
+
+		list_for_each_entry_rcu(wb, &bdi->wb_list, list) {
+			ret = wb_has_dirty_io(wb);
+			if (ret)
+				break;
+		}
+
+		srcu_read_unlock(&bdi->srcu, idx);
+	}
+
+	return ret;
+}
+
+static void bdi_flush_io(struct backing_dev_info *bdi)
+{
+	struct writeback_control wbc = {
+		.bdi			= bdi,
+		.sync_mode		= WB_SYNC_NONE,
+		.older_than_this	= NULL,
+		.range_cyclic		= 1,
+		.nr_to_write		= 1024,
+	};
+
+	generic_sync_bdi_inodes(NULL, &wbc);
+}
+
+/*
+ * kupdated() used to do this. We cannot do it from the bdi_forker_task()
+ * or we risk deadlocking on ->s_umount. The longer term solution would be
+ * to implement sync_supers_bdi() or similar and simply do it from the
+ * bdi writeback tasks individually.
+ */
+static int bdi_sync_supers(void *unused)
+{
+	set_user_nice(current, 0);
+
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+
+		/*
+		 * Do this periodically, like kupdated() did before.
+		 */
+		sync_supers();
+	}
+
+	return 0;
+}
+
+static void arm_supers_timer(void)
+{
+	unsigned long next;
+
+	next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies;
+	mod_timer(&sync_supers_timer, round_jiffies_up(next));
+}
+
+static void sync_supers_timer_fn(unsigned long unused)
+{
+	wake_up_process(sync_supers_tsk);
+	arm_supers_timer();
+}
+
+static int bdi_forker_task(void *ptr)
+{
+	struct bdi_writeback *me = ptr;
+
+	bdi_task_init(me->bdi, me);
+
+	for (;;) {
+		struct backing_dev_info *bdi, *tmp;
+		struct bdi_writeback *wb;
+
+		/*
+		 * Temporary measure, we want to make sure we don't see
+		 * dirty data on the default backing_dev_info
+		 */
+		if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+			wb_do_writeback(me, 0);
+
+		spin_lock(&bdi_lock);
+
+		/*
+		 * Check if any existing bdi's have dirty data without
+		 * a thread registered. If so, set that up.
+		 */
+		list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
+			if (bdi->wb.task)
+				continue;
+			if (list_empty(&bdi->work_list) &&
+			    !bdi_has_dirty_io(bdi))
+				continue;
+
+			bdi_add_default_flusher_task(bdi);
+		}
+
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (list_empty(&bdi_pending_list)) {
+			unsigned long wait;
+
+			spin_unlock(&bdi_lock);
+			wait = msecs_to_jiffies(dirty_writeback_interval * 10);
+			schedule_timeout(wait);
+			try_to_freeze();
+			continue;
+		}
+
+		__set_current_state(TASK_RUNNING);
+
+		/*
+		 * This is our real job - check for pending entries in
+		 * bdi_pending_list, and create the tasks that got added
+		 */
+		bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
+				 bdi_list);
+		list_del_init(&bdi->bdi_list);
+		spin_unlock(&bdi_lock);
+
+		wb = bdi_new_wb(bdi);
+		if (!wb)
+			goto readd_flush;
+
+		wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
+					dev_name(bdi->dev));
+		/*
+		 * If task creation fails, then readd the bdi to
+		 * the pending list and force writeout of the bdi
+		 * from this forker thread. That will free some memory
+		 * and we can try again.
+		 */
+		if (IS_ERR(wb->task)) {
+			wb->task = NULL;
+			bdi_put_wb(bdi, wb);
+readd_flush:
+			/*
+			 * Add this 'bdi' to the back, so we get
+			 * a chance to flush other bdi's to free
+			 * memory.
+			 */
+			spin_lock(&bdi_lock);
+			list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+			spin_unlock(&bdi_lock);
+
+			bdi_flush_io(bdi);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * bdi_lock held on entry
+ */
+static void bdi_add_one_flusher_task(struct backing_dev_info *bdi,
+				     int(*func)(struct backing_dev_info *))
+{
+	if (!bdi_cap_writeback_dirty(bdi))
+		return;
+
+	if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
+		printk("bdi %p/%s is not registered!\n", bdi, bdi->name);
+		return;
+	}
+
+	/*
+	 * Check with the helper whether to proceed adding a task. Will only
+	 * abort if we two or more simultanous calls to
+	 * bdi_add_default_flusher_task() occured, further additions will block
+	 * waiting for previous additions to finish.
+	 */
+	if (!func(bdi)) {
+		list_move_tail(&bdi->bdi_list, &bdi_pending_list);
+
+		/*
+		 * We are now on the pending list, wake up bdi_forker_task()
+		 * to finish the job and add us back to the active bdi_list
+		 */
+		wake_up_process(default_backing_dev_info.wb.task);
+	}
+}
+
+static int flusher_add_helper_block(struct backing_dev_info *bdi)
+{
+	spin_unlock(&bdi_lock);
+	wait_on_bit_lock(&bdi->state, BDI_pending, bdi_sched_wait,
+				TASK_UNINTERRUPTIBLE);
+	spin_lock(&bdi_lock);
+	return 0;
+}
+
+static int flusher_add_helper_test(struct backing_dev_info *bdi)
+{
+	return test_and_set_bit(BDI_pending, &bdi->state);
+}
+
+/*
+ * Add the default flusher task that gets created for any bdi
+ * that has dirty data pending writeout
+ */
+void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
+{
+	bdi_add_one_flusher_task(bdi, flusher_add_helper_test);
+}
+
+/**
+ * bdi_add_flusher_task - add one more flusher task to this @bdi
+ *  @bdi:	the bdi
+ *
+ * Add an additional flusher task to this @bdi. Will block waiting on
+ * previous additions, if any.
+ *
+ */
+void bdi_add_flusher_task(struct backing_dev_info *bdi)
+{
+	spin_lock(&bdi_lock);
+	bdi_add_one_flusher_task(bdi, flusher_add_helper_block);
+	spin_unlock(&bdi_lock);
+}
+EXPORT_SYMBOL(bdi_add_flusher_task);
+
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
 {
@@ -211,9 +648,42 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		goto exit;
 	}
 
+	spin_lock(&bdi_lock);
+	list_add_tail(&bdi->bdi_list, &bdi_list);
+	spin_unlock(&bdi_lock);
+
 	bdi->dev = dev;
-	bdi_debug_register(bdi, dev_name(dev));
 
+	/*
+	 * Just start the forker thread for our default backing_dev_info,
+	 * and add other bdi's to the list. They will get a thread created
+	 * on-demand when they need it.
+	 */
+	if (bdi_cap_flush_forker(bdi)) {
+		struct bdi_writeback *wb;
+
+		wb = bdi_new_wb(bdi);
+		if (!wb) {
+			ret = -ENOMEM;
+			goto remove_err;
+		}
+
+		wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
+						dev_name(dev));
+		if (IS_ERR(wb->task)) {
+			wb->task = NULL;
+			bdi_put_wb(bdi, wb);
+			ret = -ENOMEM;
+remove_err:
+			spin_lock(&bdi_lock);
+			list_del(&bdi->bdi_list);
+			spin_unlock(&bdi_lock);
+			goto exit;
+		}
+	}
+
+	bdi_debug_register(bdi, dev_name(dev));
+	set_bit(BDI_registered, &bdi->state);
 exit:
 	return ret;
 }
@@ -225,9 +695,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
 }
 EXPORT_SYMBOL(bdi_register_dev);
 
+/*
+ * Remove bdi from the global list and shutdown any threads we have running
+ */
+static void bdi_wb_shutdown(struct backing_dev_info *bdi)
+{
+	struct bdi_writeback *wb;
+
+	if (!bdi_cap_writeback_dirty(bdi))
+		return;
+
+	/*
+	 * If setup is pending, wait for that to complete first
+	 */
+	wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+			TASK_UNINTERRUPTIBLE);
+
+	/*
+	 * Make sure nobody finds us on the bdi_list anymore
+	 */
+	spin_lock(&bdi_lock);
+	list_del(&bdi->bdi_list);
+	spin_unlock(&bdi_lock);
+
+	/*
+	 * Finally, kill the kernel threads. We don't need to be RCU
+	 * safe anymore, since the bdi is gone from visibility.
+	 */
+	list_for_each_entry(wb, &bdi->wb_list, list)
+		kthread_stop(wb->task);
+}
+
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		if (!bdi_cap_flush_forker(bdi))
+			bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
@@ -237,14 +740,21 @@ EXPORT_SYMBOL(bdi_unregister);
 
 int bdi_init(struct backing_dev_info *bdi)
 {
-	int i;
-	int err;
+	int i, err;
 
 	bdi->dev = NULL;
 
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = PROP_FRAC_BASE;
+	spin_lock_init(&bdi->wb_lock);
+	bdi->wb_mask = 0;
+	bdi->wb_cnt = 0;
+	INIT_LIST_HEAD(&bdi->bdi_list);
+	INIT_LIST_HEAD(&bdi->wb_list);
+	INIT_LIST_HEAD(&bdi->work_list);
+
+	bdi_wb_init(&bdi->wb, bdi);
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -252,10 +762,15 @@ int bdi_init(struct backing_dev_info *bdi)
 			goto err;
 	}
 
+	err = init_srcu_struct(&bdi->srcu);
+	if (err)
+		goto err;
+
 	bdi->dirty_exceeded = 0;
 	err = prop_local_init_percpu(&bdi->completions);
 
 	if (err) {
+		cleanup_srcu_struct(&bdi->srcu);
 err:
 		while (i--)
 			percpu_counter_destroy(&bdi->bdi_stat[i]);
@@ -269,8 +784,12 @@ void bdi_destroy(struct backing_dev_info *bdi)
 {
 	int i;
 
+	WARN_ON(bdi_has_dirty_io(bdi));
+
 	bdi_unregister(bdi);
 
+	cleanup_srcu_struct(&bdi->srcu);
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 81627ebcd313..a727af9904e1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,15 +36,6 @@
 #include <linux/pagevec.h>
 
 /*
- * The maximum number of pages to writeout in a single bdflush/kupdate
- * operation.  We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode.  Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES	1024
-
-/*
  * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
  * will look to see if it needs to force writeback or throttling.
  */
@@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode);
 /* End of sysctl-exported parameters */
 
 
-static void background_writeout(unsigned long _min_pages);
-
 /*
  * Scale the writeback cache size proportional to the relative writeout speeds.
  *
@@ -320,15 +309,13 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
 /*
  *
  */
-static DEFINE_SPINLOCK(bdi_lock);
 static unsigned int bdi_min_ratio;
 
 int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
 {
 	int ret = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&bdi_lock, flags);
+	spin_lock(&bdi_lock);
 	if (min_ratio > bdi->max_ratio) {
 		ret = -EINVAL;
 	} else {
@@ -340,27 +327,26 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
 			ret = -EINVAL;
 		}
 	}
-	spin_unlock_irqrestore(&bdi_lock, flags);
+	spin_unlock(&bdi_lock);
 
 	return ret;
 }
 
 int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
 {
-	unsigned long flags;
 	int ret = 0;
 
 	if (max_ratio > 100)
 		return -EINVAL;
 
-	spin_lock_irqsave(&bdi_lock, flags);
+	spin_lock(&bdi_lock);
 	if (bdi->min_ratio > max_ratio) {
 		ret = -EINVAL;
 	} else {
 		bdi->max_ratio = max_ratio;
 		bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
 	}
-	spin_unlock_irqrestore(&bdi_lock, flags);
+	spin_unlock(&bdi_lock);
 
 	return ret;
 }
@@ -546,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 		 * up.
 		 */
 		if (bdi_nr_reclaimable > bdi_thresh) {
-			writeback_inodes(&wbc);
+			generic_sync_bdi_inodes(NULL, &wbc);
 			pages_written += write_chunk - wbc.nr_to_write;
 			get_dirty_limits(&background_thresh, &dirty_thresh,
 				       &bdi_thresh, bdi);
@@ -597,7 +583,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 			(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
 					  + global_page_state(NR_UNSTABLE_NFS)
 					  > background_thresh)))
-		pdflush_operation(background_writeout, 0);
+		bdi_start_writeback(bdi, NULL, 0, WB_SYNC_NONE);
 }
 
 void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -682,152 +668,53 @@ void throttle_vm_writeout(gfp_t gfp_mask)
 }
 
 /*
- * writeback at least _min_pages, and keep writing until the amount of dirty
- * memory is less than the background threshold, or until we're all clean.
+ * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
+ * the whole world.
  */
-static void background_writeout(unsigned long _min_pages)
+void wakeup_flusher_threads(long nr_pages)
 {
-	long min_pages = _min_pages;
 	struct writeback_control wbc = {
-		.bdi		= NULL,
 		.sync_mode	= WB_SYNC_NONE,
 		.older_than_this = NULL,
-		.nr_to_write	= 0,
-		.nonblocking	= 1,
 		.range_cyclic	= 1,
 	};
 
-	for ( ; ; ) {
-		unsigned long background_thresh;
-		unsigned long dirty_thresh;
-
-		get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
-		if (global_page_state(NR_FILE_DIRTY) +
-			global_page_state(NR_UNSTABLE_NFS) < background_thresh
-				&& min_pages <= 0)
-			break;
-		wbc.more_io = 0;
-		wbc.encountered_congestion = 0;
-		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
-		wbc.pages_skipped = 0;
-		writeback_inodes(&wbc);
-		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
-		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
-			/* Wrote less than expected */
-			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(BLK_RW_ASYNC, HZ/10);
-			else
-				break;
-		}
-	}
-}
-
-/*
- * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
- * the whole world.  Returns 0 if a pdflush thread was dispatched.  Returns
- * -1 if all pdflush threads were busy.
- */
-int wakeup_pdflush(long nr_pages)
-{
 	if (nr_pages == 0)
 		nr_pages = global_page_state(NR_FILE_DIRTY) +
 				global_page_state(NR_UNSTABLE_NFS);
-	return pdflush_operation(background_writeout, nr_pages);
+	wbc.nr_to_write = nr_pages;
+	bdi_writeback_all(NULL, &wbc);
 }
 
-static void wb_timer_fn(unsigned long unused);
 static void laptop_timer_fn(unsigned long unused);
 
-static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
 static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
 
 /*
- * Periodic writeback of "old" data.
- *
- * Define "old": the first time one of an inode's pages is dirtied, we mark the
- * dirtying-time in the inode's address_space.  So this periodic writeback code
- * just walks the superblock inode list, writing back any inodes which are
- * older than a specific point in time.
- *
- * Try to run once per dirty_writeback_interval.  But if a writeback event
- * takes longer than a dirty_writeback_interval interval, then leave a
- * one-second gap.
- *
- * older_than_this takes precedence over nr_to_write.  So we'll only write back
- * all dirty pages if they are all attached to "old" mappings.
- */
-static void wb_kupdate(unsigned long arg)
-{
-	unsigned long oldest_jif;
-	unsigned long start_jif;
-	unsigned long next_jif;
-	long nr_to_write;
-	struct writeback_control wbc = {
-		.bdi		= NULL,
-		.sync_mode	= WB_SYNC_NONE,
-		.older_than_this = &oldest_jif,
-		.nr_to_write	= 0,
-		.nonblocking	= 1,
-		.for_kupdate	= 1,
-		.range_cyclic	= 1,
-	};
-
-	sync_supers();
-
-	oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10);
-	start_jif = jiffies;
-	next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
-	nr_to_write = global_page_state(NR_FILE_DIRTY) +
-			global_page_state(NR_UNSTABLE_NFS) +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
-	while (nr_to_write > 0) {
-		wbc.more_io = 0;
-		wbc.encountered_congestion = 0;
-		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
-		writeback_inodes(&wbc);
-		if (wbc.nr_to_write > 0) {
-			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(BLK_RW_ASYNC, HZ/10);
-			else
-				break;	/* All the old data is written */
-		}
-		nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
-	}
-	if (time_before(next_jif, jiffies + HZ))
-		next_jif = jiffies + HZ;
-	if (dirty_writeback_interval)
-		mod_timer(&wb_timer, next_jif);
-}
-
-/*
  * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
  */
 int dirty_writeback_centisecs_handler(ctl_table *table, int write,
 	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
 {
 	proc_dointvec(table, write, file, buffer, length, ppos);
-	if (dirty_writeback_interval)
-		mod_timer(&wb_timer, jiffies +
-			msecs_to_jiffies(dirty_writeback_interval * 10));
-	else
-		del_timer(&wb_timer);
 	return 0;
 }
 
-static void wb_timer_fn(unsigned long unused)
+static void do_laptop_sync(struct work_struct *work)
 {
-	if (pdflush_operation(wb_kupdate, 0) < 0)
-		mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
-}
-
-static void laptop_flush(unsigned long unused)
-{
-	sys_sync();
+	wakeup_flusher_threads(0);
+	kfree(work);
 }
 
 static void laptop_timer_fn(unsigned long unused)
 {
-	pdflush_operation(laptop_flush, 0);
+	struct work_struct *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work) {
+		INIT_WORK(work, do_laptop_sync);
+		schedule_work(work);
+	}
 }
 
 /*
@@ -910,8 +797,6 @@ void __init page_writeback_init(void)
 {
 	int shift;
 
-	mod_timer(&wb_timer,
-		  jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
 
diff --git a/mm/pdflush.c b/mm/pdflush.c
deleted file mode 100644
index 235ac440c44e..000000000000
--- a/mm/pdflush.c
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * mm/pdflush.c - worker threads for writing back filesystem data
- *
- * Copyright (C) 2002, Linus Torvalds.
- *
- * 09Apr2002	Andrew Morton
- *		Initial version
- * 29Feb2004	kaos@sgi.com
- *		Move worker thread creation to kthread to avoid chewing
- *		up stack space with nested calls to kernel_thread.
- */
-
-#include <linux/sched.h>
-#include <linux/list.h>
-#include <linux/signal.h>
-#include <linux/spinlock.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/fs.h>		/* Needed by writeback.h	  */
-#include <linux/writeback.h>	/* Prototypes pdflush_operation() */
-#include <linux/kthread.h>
-#include <linux/cpuset.h>
-#include <linux/freezer.h>
-
-
-/*
- * Minimum and maximum number of pdflush instances
- */
-#define MIN_PDFLUSH_THREADS	2
-#define MAX_PDFLUSH_THREADS	8
-
-static void start_one_pdflush_thread(void);
-
-
-/*
- * The pdflush threads are worker threads for writing back dirty data.
- * Ideally, we'd like one thread per active disk spindle.  But the disk
- * topology is very hard to divine at this level.   Instead, we take
- * care in various places to prevent more than one pdflush thread from
- * performing writeback against a single filesystem.  pdflush threads
- * have the PF_FLUSHER flag set in current->flags to aid in this.
- */
-
-/*
- * All the pdflush threads.  Protected by pdflush_lock
- */
-static LIST_HEAD(pdflush_list);
-static DEFINE_SPINLOCK(pdflush_lock);
-
-/*
- * The count of currently-running pdflush threads.  Protected
- * by pdflush_lock.
- *
- * Readable by sysctl, but not writable.  Published to userspace at
- * /proc/sys/vm/nr_pdflush_threads.
- */
-int nr_pdflush_threads = 0;
-
-/*
- * The time at which the pdflush thread pool last went empty
- */
-static unsigned long last_empty_jifs;
-
-/*
- * The pdflush thread.
- *
- * Thread pool management algorithm:
- * 
- * - The minimum and maximum number of pdflush instances are bound
- *   by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
- * 
- * - If there have been no idle pdflush instances for 1 second, create
- *   a new one.
- * 
- * - If the least-recently-went-to-sleep pdflush thread has been asleep
- *   for more than one second, terminate a thread.
- */
-
-/*
- * A structure for passing work to a pdflush thread.  Also for passing
- * state information between pdflush threads.  Protected by pdflush_lock.
- */
-struct pdflush_work {
-	struct task_struct *who;	/* The thread */
-	void (*fn)(unsigned long);	/* A callback function */
-	unsigned long arg0;		/* An argument to the callback */
-	struct list_head list;		/* On pdflush_list, when idle */
-	unsigned long when_i_went_to_sleep;
-};
-
-static int __pdflush(struct pdflush_work *my_work)
-{
-	current->flags |= PF_FLUSHER | PF_SWAPWRITE;
-	set_freezable();
-	my_work->fn = NULL;
-	my_work->who = current;
-	INIT_LIST_HEAD(&my_work->list);
-
-	spin_lock_irq(&pdflush_lock);
-	for ( ; ; ) {
-		struct pdflush_work *pdf;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		list_move(&my_work->list, &pdflush_list);
-		my_work->when_i_went_to_sleep = jiffies;
-		spin_unlock_irq(&pdflush_lock);
-		schedule();
-		try_to_freeze();
-		spin_lock_irq(&pdflush_lock);
-		if (!list_empty(&my_work->list)) {
-			/*
-			 * Someone woke us up, but without removing our control
-			 * structure from the global list.  swsusp will do this
-			 * in try_to_freeze()->refrigerator().  Handle it.
-			 */
-			my_work->fn = NULL;
-			continue;
-		}
-		if (my_work->fn == NULL) {
-			printk("pdflush: bogus wakeup\n");
-			continue;
-		}
-		spin_unlock_irq(&pdflush_lock);
-
-		(*my_work->fn)(my_work->arg0);
-
-		spin_lock_irq(&pdflush_lock);
-
-		/*
-		 * Thread creation: For how long have there been zero
-		 * available threads?
-		 *
-		 * To throttle creation, we reset last_empty_jifs.
-		 */
-		if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
-			if (list_empty(&pdflush_list)) {
-				if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) {
-					last_empty_jifs = jiffies;
-					nr_pdflush_threads++;
-					spin_unlock_irq(&pdflush_lock);
-					start_one_pdflush_thread();
-					spin_lock_irq(&pdflush_lock);
-				}
-			}
-		}
-
-		my_work->fn = NULL;
-
-		/*
-		 * Thread destruction: For how long has the sleepiest
-		 * thread slept?
-		 */
-		if (list_empty(&pdflush_list))
-			continue;
-		if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
-			continue;
-		pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
-		if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
-			/* Limit exit rate */
-			pdf->when_i_went_to_sleep = jiffies;
-			break;					/* exeunt */
-		}
-	}
-	nr_pdflush_threads--;
-	spin_unlock_irq(&pdflush_lock);
-	return 0;
-}
-
-/*
- * Of course, my_work wants to be just a local in __pdflush().  It is
- * separated out in this manner to hopefully prevent the compiler from
- * performing unfortunate optimisations against the auto variables.  Because
- * these are visible to other tasks and CPUs.  (No problem has actually
- * been observed.  This is just paranoia).
- */
-static int pdflush(void *dummy)
-{
-	struct pdflush_work my_work;
-	cpumask_var_t cpus_allowed;
-
-	/*
-	 * Since the caller doesn't even check kthread_run() worked, let's not
-	 * freak out too much if this fails.
-	 */
-	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
-		printk(KERN_WARNING "pdflush failed to allocate cpumask\n");
-		return 0;
-	}
-
-	/*
-	 * pdflush can spend a lot of time doing encryption via dm-crypt.  We
-	 * don't want to do that at keventd's priority.
-	 */
-	set_user_nice(current, 0);
-
-	/*
-	 * Some configs put our parent kthread in a limited cpuset,
-	 * which kthread() overrides, forcing cpus_allowed == cpu_all_mask.
-	 * Our needs are more modest - cut back to our cpusets cpus_allowed.
-	 * This is needed as pdflush's are dynamically created and destroyed.
-	 * The boottime pdflush's are easily placed w/o these 2 lines.
-	 */
-	cpuset_cpus_allowed(current, cpus_allowed);
-	set_cpus_allowed_ptr(current, cpus_allowed);
-	free_cpumask_var(cpus_allowed);
-
-	return __pdflush(&my_work);
-}
-
-/*
- * Attempt to wake up a pdflush thread, and get it to do some work for you.
- * Returns zero if it indeed managed to find a worker thread, and passed your
- * payload to it.
- */
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	BUG_ON(fn == NULL);	/* Hard to diagnose if it's deferred */
-
-	spin_lock_irqsave(&pdflush_lock, flags);
-	if (list_empty(&pdflush_list)) {
-		ret = -1;
-	} else {
-		struct pdflush_work *pdf;
-
-		pdf = list_entry(pdflush_list.next, struct pdflush_work, list);
-		list_del_init(&pdf->list);
-		if (list_empty(&pdflush_list))
-			last_empty_jifs = jiffies;
-		pdf->fn = fn;
-		pdf->arg0 = arg0;
-		wake_up_process(pdf->who);
-	}
-	spin_unlock_irqrestore(&pdflush_lock, flags);
-
-	return ret;
-}
-
-static void start_one_pdflush_thread(void)
-{
-	struct task_struct *k;
-
-	k = kthread_run(pdflush, NULL, "pdflush");
-	if (unlikely(IS_ERR(k))) {
-		spin_lock_irq(&pdflush_lock);
-		nr_pdflush_threads--;
-		spin_unlock_irq(&pdflush_lock);
-	}
-}
-
-static int __init pdflush_init(void)
-{
-	int i;
-
-	/*
-	 * Pre-set nr_pdflush_threads...  If we fail to create,
-	 * the count will be decremented.
-	 */
-	nr_pdflush_threads = MIN_PDFLUSH_THREADS;
-
-	for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
-		start_one_pdflush_thread();
-	return 0;
-}
-
-module_init(pdflush_init);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 42cd38eba79f..5ae6b8b78c80 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -34,6 +34,7 @@ static const struct address_space_operations swap_aops = {
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
+	.name		= "swap",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 	.unplug_io_fn	= swap_unplug_io_fn,
 };
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dea7abd31098..fe8e986bb6a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1715,7 +1715,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 */
 		if (total_scanned > sc->swap_cluster_max +
 					sc->swap_cluster_max / 2) {
-			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
 			sc->may_writepage = 1;
 		}