Merge branch 'for-3.10/core' of git://git.kernel.dk/linux-block

Pull block core updates from Jens Axboe:

- Major bit is Kents prep work for immutable bio vecs.

- Stable candidate fix for a scheduling-while-atomic in the queue
bypass operation.

- Fix for the hang on exceeded rq->datalen 32-bit unsigned when merging
discard bios.

- Tejuns changes to convert the writeback thread pool to the generic
workqueue mechanism.

- Runtime PM framework, SCSI patches exists on top of these in James'
tree.

- A few random fixes.

* 'for-3.10/core' of git://git.kernel.dk/linux-block: (40 commits)
relay: move remove_buf_file inside relay_close_buf
partitions/efi.c: replace useless kzalloc's by kmalloc's
fs/block_dev.c: fix iov_shorten() criteria in blkdev_aio_read()
block: fix max discard sectors limit
blkcg: fix "scheduling while atomic" in blk_queue_bypass_start
Documentation: cfq-iosched: update documentation help for cfq tunables
writeback: expose the bdi_wq workqueue
writeback: replace custom worker pool implementation with unbound workqueue
writeback: remove unused bdi_pending_list
aoe: Fix unitialized var usage
bio-integrity: Add explicit field for owner of bip_buf
block: Add an explicit bio flag for bios that own their bvec
block: Add bio_alloc_pages()
block: Convert some code to bio_for_each_segment_all()
block: Add bio_for_each_segment_all()
bounce: Refactor __blk_queue_bounce to not use bi_io_vec
raid1: use bio_copy_data()
pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage
pktcdvd: use bio_copy_data()
block: Add bio_copy_data()
...

Documentation/block/cfq-iosched.txt

···
 I/O bandwidth for all the processes which requests an I/O operation.
 
 CFQ maintains the per process queue for the processes which request I/O
-operation(syncronous requests). In case of asynchronous requests, all the
+operation(synchronous requests). In case of asynchronous requests, all the
 requests from all the processes are batched together according to their
 process's I/O priority.
 
···
 value of this is 124ms. In case to favor synchronous requests over asynchronous
 one, this value should be decreased relative to fifo_expire_async.
 
+group_idle
+-----------
+This parameter forces idling at the CFQ group level instead of CFQ
+queue level. This was introduced after after a bottleneck was observed
+in higher end storage due to idle on sequential queue and allow dispatch
+from a single queue. The idea with this parameter is that it can be run with
+slice_idle=0 and group_idle=8, so that idling does not happen on individual
+queues in the group but happens overall on the group and thus still keeps the
+IO controller working.
+Not idling on individual queues in the group will dispatch requests from
+multiple queues in the group at the same time and achieve higher throughput
+on higher end storage.
+
+Default value for this parameter is 8ms.
+
+latency
+-------
+This parameter is used to enable/disable the latency mode of the CFQ
+scheduler. If latency mode (called low_latency) is enabled, CFQ tries
+to recompute the slice time for each process based on the target_latency set
+for the system. This favors fairness over throughput. Disabling low
+latency (setting it to 0) ignores target latency, allowing each process in the
+system to get a full time slice.
+
+By default low latency mode is enabled.
+
+target_latency
+--------------
+This parameter is used to calculate the time slice for a process if cfq's
+latency mode is enabled. It will ensure that sync requests have an estimated
+latency. But if sequential workload is higher(e.g. sequential read),
+then to meet the latency constraints, throughput may decrease because of less
+time for each process to issue I/O request before the cfq queue is switched.
+
+Though this can be overcome by disabling the latency_mode, it may increase
+the read latency for some applications. This parameter allows for changing
+target_latency through the sysfs interface which can provide the balanced
+throughput and read latency.
+
+Default value for target_latency is 300ms.
+
 slice_async
 -----------
 This parameter is same as of slice_sync but for asynchronous queue. The
···
 request.
 
 In case of storage with several disk, this setting can limit the parallel
-processing of request. Therefore, increasing the value can imporve the
-performace although this can cause the latency of some I/O to increase due
+processing of request. Therefore, increasing the value can improve the
+performance although this can cause the latency of some I/O to increase due
 to more number of requests.
 
 CFQ Group scheduling

block/blk-cgroup.c

···
 	if (!new_blkg)
 		return -ENOMEM;
 
-	preloaded = !radix_tree_preload(GFP_KERNEL);
-
 	blk_queue_bypass_start(q);
+
+	preloaded = !radix_tree_preload(GFP_KERNEL);
 
 	/*
 	 * Make sure the root blkg exists and count the existing blkgs.  As

block/blk-core.c

···
 #include <linux/list_sort.h>
 #include <linux/delay.h>
 #include <linux/ratelimit.h>
+#include <linux/pm_runtime.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
···
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
 
-	if (unlikely(nbytes > bio->bi_size)) {
-		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
-		       __func__, nbytes, bio->bi_size);
-		nbytes = bio->bi_size;
-	}
-
 	if (unlikely(rq->cmd_flags & REQ_QUIET))
 		set_bit(BIO_QUIET, &bio->bi_flags);
 
-	bio->bi_size -= nbytes;
-	bio->bi_sector += (nbytes >> 9);
-
-	if (bio_integrity(bio))
-		bio_integrity_advance(bio, nbytes);
+	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
 	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
···
 }
 EXPORT_SYMBOL_GPL(part_round_stats);
 
+#ifdef CONFIG_PM_RUNTIME
+static void blk_pm_put_request(struct request *rq)
+{
+	if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending)
+		pm_runtime_mark_last_busy(rq->q->dev);
+}
+#else
+static inline void blk_pm_put_request(struct request *rq) {}
+#endif
+
 /*
  * queue lock must be held
  */
···
 		return;
 	if (unlikely(--req->ref_count))
 		return;
+
+	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
 
···
 	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
 			bio->bi_rw,
-			(unsigned long long)bio->bi_sector + bio_sectors(bio),
+			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 
 	set_bit(BIO_EOF, &bio->bi_flags);
···
 	}
 }
 
+#ifdef CONFIG_PM_RUNTIME
+/*
+ * Don't process normal requests when queue is suspended
+ * or in the process of suspending/resuming
+ */
+static struct request *blk_pm_peek_request(struct request_queue *q,
+					   struct request *rq)
+{
+	if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
+	    (q->rpm_status != RPM_ACTIVE && !(rq->cmd_flags & REQ_PM))))
+		return NULL;
+	else
+		return rq;
+}
+#else
+static inline struct request *blk_pm_peek_request(struct request_queue *q,
+						  struct request *rq)
+{
+	return rq;
+}
+#endif
+
 /**
  * blk_peek_request - peek at the top of a request queue
  * @q: request queue to peek at
···
 	int ret;
 
 	while ((rq = __elv_next_request(q)) != NULL) {
+
+		rq = blk_pm_peek_request(q, rq);
+		if (!rq)
+			break;
+
 		if (!(rq->cmd_flags & REQ_STARTED)) {
 			/*
 			 * This is the first time the device driver
···
  **/
 bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
-	int total_bytes, bio_nbytes, next_idx = 0;
-	struct bio *bio;
+	int total_bytes;
 
 	if (!req->bio)
 		return false;
···
 
 	blk_account_io_completion(req, nr_bytes);
 
-	total_bytes = bio_nbytes = 0;
-	while ((bio = req->bio) != NULL) {
-		int nbytes;
+	total_bytes = 0;
+	while (req->bio) {
+		struct bio *bio = req->bio;
+		unsigned bio_bytes = min(bio->bi_size, nr_bytes);
 
-		if (nr_bytes >= bio->bi_size) {
+		if (bio_bytes == bio->bi_size)
 			req->bio = bio->bi_next;
-			nbytes = bio->bi_size;
-			req_bio_endio(req, bio, nbytes, error);
-			next_idx = 0;
-			bio_nbytes = 0;
-		} else {
-			int idx = bio->bi_idx + next_idx;
 
-			if (unlikely(idx >= bio->bi_vcnt)) {
-				blk_dump_rq_flags(req, "__end_that");
-				printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
-				       __func__, idx, bio->bi_vcnt);
-				break;
-			}
+		req_bio_endio(req, bio, bio_bytes, error);
 
-			nbytes = bio_iovec_idx(bio, idx)->bv_len;
-			BIO_BUG_ON(nbytes > bio->bi_size);
+		total_bytes += bio_bytes;
+		nr_bytes -= bio_bytes;
 
-			/*
-			 * not a complete bvec done
-			 */
-			if (unlikely(nbytes > nr_bytes)) {
-				bio_nbytes += nr_bytes;
-				total_bytes += nr_bytes;
-				break;
-			}
-
-			/*
-			 * advance to the next vector
-			 */
-			next_idx++;
-			bio_nbytes += nbytes;
-		}
-
-		total_bytes += nbytes;
-		nr_bytes -= nbytes;
-
-		bio = req->bio;
-		if (bio) {
-			/*
-			 * end more in this run, or just return 'not-done'
-			 */
-			if (unlikely(nr_bytes <= 0))
-				break;
-		}
+		if (!nr_bytes)
+			break;
 	}
 
 	/*
···
 		 */
 		req->__data_len = 0;
 		return false;
-	}
-
-	/*
-	 * if the request wasn't completed, update state
-	 */
-	if (bio_nbytes) {
-		req_bio_endio(req, bio, bio_nbytes, error);
-		bio->bi_idx += next_idx;
-		bio_iovec(bio)->bv_offset += nr_bytes;
-		bio_iovec(bio)->bv_len -= nr_bytes;
 	}
 
 	req->__data_len -= total_bytes;
···
 		current->plug = NULL;
 }
 EXPORT_SYMBOL(blk_finish_plug);
+
+#ifdef CONFIG_PM_RUNTIME
+/**
+ * blk_pm_runtime_init - Block layer runtime PM initialization routine
+ * @q: the queue of the device
+ * @dev: the device the queue belongs to
+ *
+ * Description:
+ *    Initialize runtime-PM-related fields for @q and start auto suspend for
+ *    @dev. Drivers that want to take advantage of request-based runtime PM
+ *    should call this function after @dev has been initialized, and its
+ *    request queue @q has been allocated, and runtime PM for it can not happen
+ *    yet(either due to disabled/forbidden or its usage_count > 0). In most
+ *    cases, driver should call this function before any I/O has taken place.
+ *
+ *    This function takes care of setting up using auto suspend for the device,
+ *    the autosuspend delay is set to -1 to make runtime suspend impossible
+ *    until an updated value is either set by user or by driver. Drivers do
+ *    not need to touch other autosuspend settings.
+ *
+ *    The block layer runtime PM is request based, so only works for drivers
+ *    that use request as their IO unit instead of those directly use bio's.
+ */
+void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
+{
+	q->dev = dev;
+	q->rpm_status = RPM_ACTIVE;
+	pm_runtime_set_autosuspend_delay(q->dev, -1);
+	pm_runtime_use_autosuspend(q->dev);
+}
+EXPORT_SYMBOL(blk_pm_runtime_init);
+
+/**
+ * blk_pre_runtime_suspend - Pre runtime suspend check
+ * @q: the queue of the device
+ *
+ * Description:
+ *    This function will check if runtime suspend is allowed for the device
+ *    by examining if there are any requests pending in the queue. If there
+ *    are requests pending, the device can not be runtime suspended; otherwise,
+ *    the queue's status will be updated to SUSPENDING and the driver can
+ *    proceed to suspend the device.
+ *
+ *    For the not allowed case, we mark last busy for the device so that
+ *    runtime PM core will try to autosuspend it some time later.
+ *
+ *    This function should be called near the start of the device's
+ *    runtime_suspend callback.
+ *
+ * Return:
+ *    0		- OK to runtime suspend the device
+ *    -EBUSY	- Device should not be runtime suspended
+ */
+int blk_pre_runtime_suspend(struct request_queue *q)
+{
+	int ret = 0;
+
+	spin_lock_irq(q->queue_lock);
+	if (q->nr_pending) {
+		ret = -EBUSY;
+		pm_runtime_mark_last_busy(q->dev);
+	} else {
+		q->rpm_status = RPM_SUSPENDING;
+	}
+	spin_unlock_irq(q->queue_lock);
+	return ret;
+}
+EXPORT_SYMBOL(blk_pre_runtime_suspend);
+
+/**
+ * blk_post_runtime_suspend - Post runtime suspend processing
+ * @q: the queue of the device
+ * @err: return value of the device's runtime_suspend function
+ *
+ * Description:
+ *    Update the queue's runtime status according to the return value of the
+ *    device's runtime suspend function and mark last busy for the device so
+ *    that PM core will try to auto suspend the device at a later time.
+ *
+ *    This function should be called near the end of the device's
+ *    runtime_suspend callback.
+ */
+void blk_post_runtime_suspend(struct request_queue *q, int err)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!err) {
+		q->rpm_status = RPM_SUSPENDED;
+	} else {
+		q->rpm_status = RPM_ACTIVE;
+		pm_runtime_mark_last_busy(q->dev);
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_post_runtime_suspend);
+
+/**
+ * blk_pre_runtime_resume - Pre runtime resume processing
+ * @q: the queue of the device
+ *
+ * Description:
+ *    Update the queue's runtime status to RESUMING in preparation for the
+ *    runtime resume of the device.
+ *
+ *    This function should be called near the start of the device's
+ *    runtime_resume callback.
+ */
+void blk_pre_runtime_resume(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	q->rpm_status = RPM_RESUMING;
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_pre_runtime_resume);
+
+/**
+ * blk_post_runtime_resume - Post runtime resume processing
+ * @q: the queue of the device
+ * @err: return value of the device's runtime_resume function
+ *
+ * Description:
+ *    Update the queue's runtime status according to the return value of the
+ *    device's runtime_resume function. If it is successfully resumed, process
+ *    the requests that are queued into the device's queue when it is resuming
+ *    and then mark last busy and initiate autosuspend for it.
+ *
+ *    This function should be called near the end of the device's
+ *    runtime_resume callback.
+ */
+void blk_post_runtime_resume(struct request_queue *q, int err)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!err) {
+		q->rpm_status = RPM_ACTIVE;
+		__blk_run_queue(q);
+		pm_runtime_mark_last_busy(q->dev);
+		pm_runtime_autosuspend(q->dev);
+	} else {
+		q->rpm_status = RPM_SUSPENDED;
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_post_runtime_resume);
+#endif
 
 int __init blk_dev_init(void)
 {

block/cfq-iosched.c

···
 		return NULL;
 
 	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
-	if (cfqq) {
-		sector_t sector = bio->bi_sector + bio_sectors(bio);
-
-		return elv_rb_find(&cfqq->sort_list, sector);
-	}
+	if (cfqq)
+		return elv_rb_find(&cfqq->sort_list, bio_end_sector(bio));
 
 	return NULL;
 }

block/deadline-iosched.c

···
 	 * check for front merge
 	 */
 	if (dd->front_merges) {
-		sector_t sector = bio->bi_sector + bio_sectors(bio);
+		sector_t sector = bio_end_sector(bio);
 
 		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
 		if (__rq) {

block/elevator.c

···
 #include <linux/blktrace_api.h>
 #include <linux/hash.h>
 #include <linux/uaccess.h>
+#include <linux/pm_runtime.h>
 
 #include <trace/events/block.h>
 
···
 		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
 }
 
+#ifdef CONFIG_PM_RUNTIME
+static void blk_pm_requeue_request(struct request *rq)
+{
+	if (rq->q->dev && !(rq->cmd_flags & REQ_PM))
+		rq->q->nr_pending--;
+}
+
+static void blk_pm_add_request(struct request_queue *q, struct request *rq)
+{
+	if (q->dev && !(rq->cmd_flags & REQ_PM) && q->nr_pending++ == 0 &&
+	    (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
+		pm_request_resume(q->dev);
+}
+#else
+static inline void blk_pm_requeue_request(struct request *rq) {}
+static inline void blk_pm_add_request(struct request_queue *q,
+				      struct request *rq)
+{
+}
+#endif
+
 void elv_requeue_request(struct request_queue *q, struct request *rq)
 {
 	/*
···
 	}
 
 	rq->cmd_flags &= ~REQ_STARTED;
+
+	blk_pm_requeue_request(rq);
 
 	__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
 }
···
 void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	trace_block_rq_insert(q, rq);
+
+	blk_pm_add_request(q, rq);
 
 	rq->q = q;
 

block/partitions/efi.c

···
                 le32_to_cpu(gpt->sizeof_partition_entry);
 	if (!count)
 		return NULL;
-	pte = kzalloc(count, GFP_KERNEL);
+	pte = kmalloc(count, GFP_KERNEL);
 	if (!pte)
 		return NULL;
 
···
 	gpt_header *gpt;
 	unsigned ssz = bdev_logical_block_size(state->bdev);
 
-	gpt = kzalloc(ssz, GFP_KERNEL);
+	gpt = kmalloc(ssz, GFP_KERNEL);
 	if (!gpt)
 		return NULL;
 

drivers/block/aoe/aoecmd.c

···
 	buf->resid = bio->bi_size;
 	buf->sector = bio->bi_sector;
 	bio_pageinc(bio);
-	buf->bv = bv = &bio->bi_io_vec[bio->bi_idx];
+	buf->bv = bv = bio_iovec(bio);
 	buf->bv_resid = bv->bv_len;
 	WARN_ON(buf->bv_resid == 0);
 }

drivers/block/brd.c

···
 	int err = -EIO;
 
 	sector = bio->bi_sector;
-	if (sector + (bio->bi_size >> SECTOR_SHIFT) >
-						get_capacity(bdev->bd_disk))
+	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
 		goto out;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {

drivers/block/floppy.c

···
 	bio_vec.bv_len = size;
 	bio_vec.bv_offset = 0;
 	bio.bi_vcnt = 1;
-	bio.bi_idx = 0;
 	bio.bi_size = size;
 	bio.bi_bdev = bdev;
 	bio.bi_sector = 0;

drivers/block/pktcdvd.c

···
 			pd->iosched.successive_reads += bio->bi_size >> 10;
 		else {
 			pd->iosched.successive_reads = 0;
-			pd->iosched.last_write = bio->bi_sector + bio_sectors(bio);
+			pd->iosched.last_write = bio_end_sector(bio);
 		}
 		if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
 			if (pd->read_speed == pd->write_speed) {
···
 	} else {
 		printk(DRIVER_NAME": cdrom max_phys_segments too small\n");
 		return -EIO;
-	}
-}
-
-/*
- * Copy CD_FRAMESIZE bytes from src_bio into a destination page
- */
-static void pkt_copy_bio_data(struct bio *src_bio, int seg, int offs, struct page *dst_page, int dst_offs)
-{
-	unsigned int copy_size = CD_FRAMESIZE;
-
-	while (copy_size > 0) {
-		struct bio_vec *src_bvl = bio_iovec_idx(src_bio, seg);
-		void *vfrom = kmap_atomic(src_bvl->bv_page) +
-			src_bvl->bv_offset + offs;
-		void *vto = page_address(dst_page) + dst_offs;
-		int len = min_t(int, copy_size, src_bvl->bv_len - offs);
-
-		BUG_ON(len < 0);
-		memcpy(vto, vfrom, len);
-		kunmap_atomic(vfrom);
-
-		seg++;
-		offs = 0;
-		dst_offs += len;
-		copy_size -= len;
 	}
 }
 
···
 	new_sector = new_block * (CD_FRAMESIZE >> 9);
 	pkt->sector = new_sector;
 
+	bio_reset(pkt->bio);
+	pkt->bio->bi_bdev = pd->bdev;
+	pkt->bio->bi_rw = REQ_WRITE;
 	pkt->bio->bi_sector = new_sector;
-	pkt->bio->bi_next = NULL;
-	pkt->bio->bi_flags = 1 << BIO_UPTODATE;
-	pkt->bio->bi_idx = 0;
+	pkt->bio->bi_size = pkt->frames * CD_FRAMESIZE;
+	pkt->bio->bi_vcnt = pkt->frames;
 
-	BUG_ON(pkt->bio->bi_rw != REQ_WRITE);
-	BUG_ON(pkt->bio->bi_vcnt != pkt->frames);
-	BUG_ON(pkt->bio->bi_size != pkt->frames * CD_FRAMESIZE);
-	BUG_ON(pkt->bio->bi_end_io != pkt_end_io_packet_write);
-	BUG_ON(pkt->bio->bi_private != pkt);
+	pkt->bio->bi_end_io = pkt_end_io_packet_write;
+	pkt->bio->bi_private = pkt;
 
 	drop_super(sb);
 	return 1;
···
  */
 static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 {
-	struct bio *bio;
 	int f;
-	int frames_write;
 	struct bio_vec *bvec = pkt->w_bio->bi_io_vec;
 
+	bio_reset(pkt->w_bio);
+	pkt->w_bio->bi_sector = pkt->sector;
+	pkt->w_bio->bi_bdev = pd->bdev;
+	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
+	pkt->w_bio->bi_private = pkt;
+
+	/* XXX: locking? */
 	for (f = 0; f < pkt->frames; f++) {
 		bvec[f].bv_page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
 		bvec[f].bv_offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+		if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset))
+			BUG();
 	}
+	VPRINTK(DRIVER_NAME": vcnt=%d\n", pkt->w_bio->bi_vcnt);
 
 	/*
 	 * Fill-in bvec with data from orig_bios.
 	 */
-	frames_write = 0;
 	spin_lock(&pkt->lock);
-	bio_list_for_each(bio, &pkt->orig_bios) {
-		int segment = bio->bi_idx;
-		int src_offs = 0;
-		int first_frame = (bio->bi_sector - pkt->sector) / (CD_FRAMESIZE >> 9);
-		int num_frames = bio->bi_size / CD_FRAMESIZE;
-		BUG_ON(first_frame < 0);
-		BUG_ON(first_frame + num_frames > pkt->frames);
-		for (f = first_frame; f < first_frame + num_frames; f++) {
-			struct bio_vec *src_bvl = bio_iovec_idx(bio, segment);
+	bio_copy_data(pkt->w_bio, pkt->orig_bios.head);
 
-			while (src_offs >= src_bvl->bv_len) {
-				src_offs -= src_bvl->bv_len;
-				segment++;
-				BUG_ON(segment >= bio->bi_vcnt);
-				src_bvl = bio_iovec_idx(bio, segment);
-			}
-
-			if (src_bvl->bv_len - src_offs >= CD_FRAMESIZE) {
-				bvec[f].bv_page = src_bvl->bv_page;
-				bvec[f].bv_offset = src_bvl->bv_offset + src_offs;
-			} else {
-				pkt_copy_bio_data(bio, segment, src_offs,
-						  bvec[f].bv_page, bvec[f].bv_offset);
-			}
-			src_offs += CD_FRAMESIZE;
-			frames_write++;
-		}
-	}
 	pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
 	spin_unlock(&pkt->lock);
 
 	VPRINTK("pkt_start_write: Writing %d frames for zone %llx\n",
-		frames_write, (unsigned long long)pkt->sector);
-	BUG_ON(frames_write != pkt->write_size);
+		pkt->write_size, (unsigned long long)pkt->sector);
 
 	if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) {
 		pkt_make_local_copy(pkt, bvec);
···
 	}
 
 	/* Start the write request */
-	bio_reset(pkt->w_bio);
-	pkt->w_bio->bi_sector = pkt->sector;
-	pkt->w_bio->bi_bdev = pd->bdev;
-	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
-	pkt->w_bio->bi_private = pkt;
-	for (f = 0; f < pkt->frames; f++)
-		if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset))
-			BUG();
-	VPRINTK(DRIVER_NAME": vcnt=%d\n", pkt->w_bio->bi_vcnt);
-
 	atomic_set(&pkt->io_wait, 1);
 	pkt->w_bio->bi_rw = WRITE;
 	pkt_queue_bio(pd, pkt->w_bio);
···
 		cloned_bio->bi_bdev = pd->bdev;
 		cloned_bio->bi_private = psd;
 		cloned_bio->bi_end_io = pkt_end_io_read_cloned;
-		pd->stats.secs_r += bio->bi_size >> 9;
+		pd->stats.secs_r += bio_sectors(bio);
 		pkt_queue_bio(pd, cloned_bio);
 		return;
 	}
···
 	zone = ZONE(bio->bi_sector, pd);
 	VPRINTK("pkt_make_request: start = %6llx stop = %6llx\n",
 		(unsigned long long)bio->bi_sector,
-		(unsigned long long)(bio->bi_sector + bio_sectors(bio)));
+		(unsigned long long)bio_end_sector(bio));
 
 	/* Check if we have to split the bio */
 	{
···
 		sector_t last_zone;
 		int first_sectors;
 
-		last_zone = ZONE(bio->bi_sector + bio_sectors(bio) - 1, pd);
+		last_zone = ZONE(bio_end_sector(bio) - 1, pd);
 		if (last_zone != zone) {
 			BUG_ON(last_zone != zone + pd->settings.size);
 			first_sectors = last_zone - bio->bi_sector;

drivers/block/rbd.c

···
 	/* Find first affected segment... */
 
 	resid = offset;
-	__bio_for_each_segment(bv, bio_src, idx, 0) {
+	bio_for_each_segment(bv, bio_src, idx) {
 		if (resid < bv->bv_len)
 			break;
 		resid -= bv->bv_len;

drivers/md/dm-crypt.c

···
 	unsigned int i;
 	struct bio_vec *bv;
 
-	for (i = 0; i < clone->bi_vcnt; i++) {
-		bv = bio_iovec_idx(clone, i);
+	bio_for_each_segment_all(bv, clone, i) {
 		BUG_ON(!bv->bv_page);
 		mempool_free(bv->bv_page, cc->page_pool);
 		bv->bv_page = NULL;

drivers/md/dm-raid1.c

···
 {
 	io->bdev = m->dev->bdev;
 	io->sector = map_sector(m, bio);
-	io->count = bio->bi_size >> 9;
+	io->count = bio_sectors(bio);
 }
 
 static void hold_bio(struct mirror_set *ms, struct bio *bio)

drivers/md/dm-stripe.c

···
 	sector_t begin, end;
 
 	stripe_map_range_sector(sc, bio->bi_sector, target_stripe, &begin);
-	stripe_map_range_sector(sc, bio->bi_sector + bio_sectors(bio),
+	stripe_map_range_sector(sc, bio_end_sector(bio),
 				target_stripe, &end);
 	if (begin < end) {
 		bio->bi_bdev = sc->stripe[target_stripe].dev->bdev;

drivers/md/dm-verity.c

···
 		return -EIO;
 	}
 
-	if ((bio->bi_sector + bio_sectors(bio)) >>
+	if (bio_end_sector(bio) >>
 	    (v->data_dev_block_bits - SECTOR_SHIFT) > v->data_blocks) {
 		DMERR_LIMIT("io out of range");
 		return -EIO;
···
 
 	bio->bi_end_io = verity_end_io;
 	bio->bi_private = io;
-	io->io_vec_size = bio->bi_vcnt - bio->bi_idx;
+	io->io_vec_size = bio_segments(bio);
 	if (io->io_vec_size < DM_VERITY_IO_VEC_INLINE)
 		io->io_vec = io->io_vec_inline;
 	else

drivers/md/faulty.c

···
 			return;
 		}
 
-		if (check_sector(conf, bio->bi_sector, bio->bi_sector+(bio->bi_size>>9),
-				 WRITE))
+		if (check_sector(conf, bio->bi_sector, bio_end_sector(bio), WRITE))
 			failit = 1;
 		if (check_mode(conf, WritePersistent)) {
 			add_sector(conf, bio->bi_sector, WritePersistent);
···
 			failit = 1;
 	} else {
 		/* read request */
-		if (check_sector(conf, bio->bi_sector, bio->bi_sector + (bio->bi_size>>9),
-				 READ))
+		if (check_sector(conf, bio->bi_sector, bio_end_sector(bio), READ))
 			failit = 1;
 		if (check_mode(conf, ReadTransient))
 			failit = 1;

drivers/md/linear.c

···
 		bio_io_error(bio);
 		return;
 	}
-	if (unlikely(bio->bi_sector + (bio->bi_size >> 9) >
-		     tmp_dev->end_sector)) {
+	if (unlikely(bio_end_sector(bio) > tmp_dev->end_sector)) {
 		/* This bio crosses a device boundary, so we have to
 		 * split it.
 		 */

drivers/md/md.c

···
 	if (offset == 0 && size == bio->bi_size)
 		return;
 
-	bio->bi_sector += offset;
-	bio->bi_size = size;
-	offset <<= 9;
 	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
 
-	while (bio->bi_idx < bio->bi_vcnt &&
-	       bio->bi_io_vec[bio->bi_idx].bv_len <= offset) {
-		/* remove this whole bio_vec */
-		offset -= bio->bi_io_vec[bio->bi_idx].bv_len;
-		bio->bi_idx++;
-	}
-	if (bio->bi_idx < bio->bi_vcnt) {
-		bio->bi_io_vec[bio->bi_idx].bv_offset += offset;
-		bio->bi_io_vec[bio->bi_idx].bv_len -= offset;
-	}
+	bio_advance(bio, offset << 9);
+
+	bio->bi_size = size;
+
 	/* avoid any complications with bi_idx being non-zero*/
 	if (bio->bi_idx) {
 		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,

drivers/md/raid0.c

···
 {
 	if (likely(is_power_of_2(chunk_sects))) {
 		return chunk_sects >= ((bio->bi_sector & (chunk_sects-1))
-					+ (bio->bi_size >> 9));
+					+ bio_sectors(bio));
 	} else{
 		sector_t sector = bio->bi_sector;
 		return chunk_sects >= (sector_div(sector, chunk_sects)
-						+ (bio->bi_size >> 9));
+						+ bio_sectors(bio));
 	}
 }
 
···
 		sector_t sector = bio->bi_sector;
 		struct bio_pair *bp;
 		/* Sanity check -- queue functions should prevent this happening */
-		if ((bio->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
-		    bio->bi_idx != 0)
+		if (bio_segments(bio) > 1)
 			goto bad_map;
 		/* This is a one page bio that upper layers
 		 * refuse to split for us, so we need to split it.
···
 	printk("md/raid0:%s: make_request bug: can't convert block across chunks"
 	       " or bigger than %dk %llu %d\n",
 	       mdname(mddev), chunk_sects / 2,
-	       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
+	       (unsigned long long)bio->bi_sector, bio_sectors(bio) / 2);
 
 	bio_io_error(bio);
 	return;

drivers/md/raid1.c

···
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct pool_info *pi = data;
-	struct page *page;
 	struct r1bio *r1_bio;
 	struct bio *bio;
 	int i, j;
···
 		j = 1;
 	while(j--) {
 		bio = r1_bio->bios[j];
-		for (i = 0; i < RESYNC_PAGES; i++) {
-			page = alloc_page(gfp_flags);
-			if (unlikely(!page))
-				goto out_free_pages;
+		bio->bi_vcnt = RESYNC_PAGES;
 
-			bio->bi_io_vec[i].bv_page = page;
-			bio->bi_vcnt = i+1;
-		}
+		if (bio_alloc_pages(bio, gfp_flags))
+			goto out_free_bio;
 	}
 	/* If not user-requests, copy the page pointers to all bios */
 	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
···
 
 	return r1_bio;
 
-out_free_pages:
-	for (j=0 ; j < pi->raid_disks; j++)
-		for (i=0; i < r1_bio->bios[j]->bi_vcnt ; i++)
-			put_page(r1_bio->bios[j]->bi_io_vec[i].bv_page);
-	j = -1;
 out_free_bio:
 	while (++j < pi->raid_disks)
 		bio_put(r1_bio->bios[j]);
···
 			 (bio_data_dir(bio) == WRITE) ? "write" : "read",
 			 (unsigned long long) bio->bi_sector,
 			 (unsigned long long) bio->bi_sector +
-			 (bio->bi_size >> 9) - 1);
+			 bio_sectors(bio) - 1);
 
 		call_bio_endio(r1_bio);
 	}
···
 					 " %llu-%llu\n",
 					 (unsigned long long) mbio->bi_sector,
 					 (unsigned long long) mbio->bi_sector +
-					 (mbio->bi_size >> 9) - 1);
+					 bio_sectors(mbio) - 1);
 				call_bio_endio(r1_bio);
 			}
 		}
···
 	if (unlikely(!bvecs))
 		return;
 
-	bio_for_each_segment(bvec, bio, i) {
+	bio_for_each_segment_all(bvec, bio, i) {
 		bvecs[i] = *bvec;
 		bvecs[i].bv_page = alloc_page(GFP_NOIO);
 		if (unlikely(!bvecs[i].bv_page))
···
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
 	if (bio_data_dir(bio) == WRITE &&
-	    bio->bi_sector + bio->bi_size/512 > mddev->suspend_lo &&
+	    bio_end_sector(bio) > mddev->suspend_lo &&
 	    bio->bi_sector < mddev->suspend_hi) {
 		/* As the suspend_* range is controlled by
 		 * userspace, we want an interruptible
···
 			flush_signals(current);
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_INTERRUPTIBLE);
-			if (bio->bi_sector + bio->bi_size/512 <= mddev->suspend_lo ||
+			if (bio_end_sector(bio) <= mddev->suspend_lo ||
 			    bio->bi_sector >= mddev->suspend_hi)
 				break;
 			schedule();
···
 	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
 
 	r1_bio->master_bio = bio;
-	r1_bio->sectors = bio->bi_size >> 9;
+	r1_bio->sectors = bio_sectors(bio);
 	r1_bio->state = 0;
 	r1_bio->mddev = mddev;
 	r1_bio->sector = bio->bi_sector;
···
 			r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
 
 			r1_bio->master_bio = bio;
-			r1_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+			r1_bio->sectors = bio_sectors(bio) - sectors_handled;
 			r1_bio->state = 0;
 			r1_bio->mddev = mddev;
 			r1_bio->sector = bio->bi_sector + sectors_handled;
···
 			struct bio_vec *bvec;
 			int j;
 
-			/* Yes, I really want the '__' version so that
-			 * we clear any unused pointer in the io_vec, rather
-			 * than leave them unchanged.  This is important
-			 * because when we come to free the pages, we won't
-			 * know the original bi_idx, so we just free
-			 * them all
+			/*
+			 * We trimmed the bio, so _all is legit
 			 */
-			__bio_for_each_segment(bvec, mbio, j, 0)
+			bio_for_each_segment_all(bvec, mbio, j)
 				bvec->bv_page = r1_bio->behind_bvecs[j].bv_page;
 			if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
 				atomic_inc(&r1_bio->behind_remaining);
···
 	/* Mustn't call r1_bio_write_done before this next test,
 	 * as it could result in the bio being freed.
 	 */
-	if (sectors_handled < (bio->bi_size >> 9)) {
+	if (sectors_handled < bio_sectors(bio)) {
 		r1_bio_write_done(r1_bio);
 		/* We need another r1_bio.  It has already been counted
 		 * in bio->bi_phys_segments
 		 */
 		r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
 		r1_bio->master_bio = bio;
-		r1_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+		r1_bio->sectors = bio_sectors(bio) - sectors_handled;
 		r1_bio->state = 0;
 		r1_bio->mddev = mddev;
 		r1_bio->sector = bio->bi_sector + sectors_handled;
···
 		struct bio *sbio = r1_bio->bios[i];
 		int size;
 
-		if (r1_bio->bios[i]->bi_end_io != end_sync_read)
+		if (sbio->bi_end_io != end_sync_read)
 			continue;
 
 		if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
···
 			continue;
 		}
 		/* fixup the bio for reuse */
+		bio_reset(sbio);
 		sbio->bi_vcnt = vcnt;
 		sbio->bi_size = r1_bio->sectors << 9;
-		sbio->bi_idx = 0;
-		sbio->bi_phys_segments = 0;
-		sbio->bi_flags &= ~(BIO_POOL_MASK - 1);
-		sbio->bi_flags |= 1 << BIO_UPTODATE;
-		sbio->bi_next = NULL;
 		sbio->bi_sector = r1_bio->sector +
 			conf->mirrors[i].rdev->data_offset;
 		sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+		sbio->bi_end_io = end_sync_read;
+		sbio->bi_private = r1_bio;
+
 		size = sbio->bi_size;
 		for (j = 0; j < vcnt ; j++) {
 			struct bio_vec *bi;
···
 			else
 				bi->bv_len = size;
 			size -= PAGE_SIZE;
-			memcpy(page_address(bi->bv_page),
-			       page_address(pbio->bi_io_vec[j].bv_page),
-			       PAGE_SIZE);
 		}
+
+		bio_copy_data(sbio, pbio);
 	}
 	return 0;
 }
···
 		wbio->bi_rw = WRITE;
 		wbio->bi_end_io = end_sync_write;
 		atomic_inc(&r1_bio->remaining);
-		md_sync_acct(conf->mirrors[i].rdev->bdev, wbio->bi_size >> 9);
+		md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
 
 		generic_make_request(wbio);
 	}
···
 	}
 }
 
-static void bi_complete(struct bio *bio, int error)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
-static int submit_bio_wait(int rw, struct bio *bio)
-{
-	struct completion event;
-	rw |= REQ_SYNC;
-
-	init_completion(&event);
-	bio->bi_private = &event;
-	bio->bi_end_io = bi_complete;
-	submit_bio(rw, bio);
-	wait_for_completion(&event);
-
-	return test_bit(BIO_UPTODATE, &bio->bi_flags);
-}
-
 static int narrow_write_error(struct r1bio *r1_bio, int i)
 {
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
 	struct md_rdev *rdev = conf->mirrors[i].rdev;
-	int vcnt, idx;
-	struct bio_vec *vec;
 
 	/* bio has the data to be written to device 'i' where
 	 * we just recently had a write error.
···
 		   & ~(sector_t)(block_sectors - 1))
 		- sector;
 
-	if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
-		vcnt = r1_bio->behind_page_count;
-		vec = r1_bio->behind_bvecs;
-		idx = 0;
-		while (vec[idx].bv_page == NULL)
-			idx++;
-	} else {
-		vcnt = r1_bio->master_bio->bi_vcnt;
-		vec = r1_bio->master_bio->bi_io_vec;
-		idx = r1_bio->master_bio->bi_idx;
-	}
 	while (sect_to_write) {
 		struct bio *wbio;
 		if (sectors > sect_to_write)
 			sectors = sect_to_write;
 		/* Write at 'sector' for 'sectors'*/
 
-		wbio = bio_alloc_mddev(GFP_NOIO, vcnt, mddev);
-		memcpy(wbio->bi_io_vec, vec, vcnt * sizeof(struct bio_vec));
-		wbio->bi_sector = r1_bio->sector;
+		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+			unsigned vcnt = r1_bio->behind_page_count;
+			struct bio_vec *vec = r1_bio->behind_bvecs;
+
+			while (!vec->bv_page) {
+				vec++;
+				vcnt--;
+			}
+
+			wbio = bio_alloc_mddev(GFP_NOIO, vcnt, mddev);
+			memcpy(wbio->bi_io_vec, vec, vcnt * sizeof(struct bio_vec));
+
+			wbio->bi_vcnt = vcnt;
+		} else {
+			wbio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
+		}
+
 		wbio->bi_rw = WRITE;
-		wbio->bi_vcnt = vcnt;
+		wbio->bi_sector = r1_bio->sector;
 		wbio->bi_size = r1_bio->sectors << 9;
-		wbio->bi_idx = idx;
 
 		md_trim_bio(wbio, sector - r1_bio->sector, sectors);
 		wbio->bi_sector += rdev->data_offset;
···
 			r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
 
 			r1_bio->master_bio = mbio;
-			r1_bio->sectors = (mbio->bi_size >> 9)
-					  - sectors_handled;
+			r1_bio->sectors = bio_sectors(mbio) - sectors_handled;
 			r1_bio->state = 0;
 			set_bit(R1BIO_ReadError, &r1_bio->state);
 			r1_bio->mddev = mddev;
···
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		struct md_rdev *rdev;
 		bio = r1_bio->bios[i];
-
-		/* take from bio_init */
-		bio->bi_next = NULL;
-		bio->bi_flags &= ~(BIO_POOL_MASK-1);
-		bio->bi_flags |= 1 << BIO_UPTODATE;
-		bio->bi_rw = READ;
-		bio->bi_vcnt = 0;
-		bio->bi_idx = 0;
-		bio->bi_phys_segments = 0;
-		bio->bi_size = 0;
-		bio->bi_end_io = NULL;
-		bio->bi_private = NULL;
+		bio_reset(bio);
 
 		rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev == NULL ||

drivers/md/raid10.c

···
 	/* If this request crosses a chunk boundary, we need to
 	 * split it.  This will only happen for 1 PAGE (or less) requests.
 	 */
-	if (unlikely((bio->bi_sector & chunk_mask) + (bio->bi_size >> 9)
+	if (unlikely((bio->bi_sector & chunk_mask) + bio_sectors(bio)
 		     > chunk_sects
 		     && (conf->geo.near_copies < conf->geo.raid_disks
 			 || conf->prev.near_copies < conf->prev.raid_disks))) {
 		struct bio_pair *bp;
 		/* Sanity check -- queue functions should prevent this happening */
-		if ((bio->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
-		    bio->bi_idx != 0)
+		if (bio_segments(bio) > 1)
 			goto bad_map;
 		/* This is a one page bio that upper layers
 		 * refuse to split for us, so we need to split it.
···
 	bad_map:
 		printk("md/raid10:%s: make_request bug: can't convert block across chunks"
 		       " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2,
-		       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
+		       (unsigned long long)bio->bi_sector, bio_sectors(bio) / 2);
 
 		bio_io_error(bio);
 		return;
···
 	 */
 	wait_barrier(conf);
 
-	sectors = bio->bi_size >> 9;
+	sectors = bio_sectors(bio);
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_sector < conf->reshape_progress &&
 	    bio->bi_sector + sectors > conf->reshape_progress) {
···
 			r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
 			r10_bio->master_bio = bio;
-			r10_bio->sectors = ((bio->bi_size >> 9)
-					    - sectors_handled);
+			r10_bio->sectors = bio_sectors(bio) - sectors_handled;
 			r10_bio->state = 0;
 			r10_bio->mddev = mddev;
 			r10_bio->sector = bio->bi_sector + sectors_handled;
···
 	 * after checking if we need to go around again.
 	 */
 
-	if (sectors_handled < (bio->bi_size >> 9)) {
+	if (sectors_handled < bio_sectors(bio)) {
 		one_write_done(r10_bio);
 		/* We need another r10_bio.  It has already been counted
 		 * in bio->bi_phys_segments.
···
 		r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
 		r10_bio->master_bio = bio;
-		r10_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+		r10_bio->sectors = bio_sectors(bio) - sectors_handled;
 
 		r10_bio->mddev = mddev;
 		r10_bio->sector = bio->bi_sector + sectors_handled;
···
 		 * First we need to fixup bv_offset, bv_len and
 		 * bi_vecs, as the read request might have corrupted these
 		 */
+		bio_reset(tbio);
+
 		tbio->bi_vcnt = vcnt;
 		tbio->bi_size = r10_bio->sectors << 9;
-		tbio->bi_idx = 0;
-		tbio->bi_phys_segments = 0;
-		tbio->bi_flags &= ~(BIO_POOL_MASK - 1);
-		tbio->bi_flags |= 1 << BIO_UPTODATE;
-		tbio->bi_next = NULL;
 		tbio->bi_rw = WRITE;
 		tbio->bi_private = r10_bio;
 		tbio->bi_sector = r10_bio->devs[i].addr;
···
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		atomic_inc(&r10_bio->remaining);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, tbio->bi_size >> 9);
+		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio));
 
 		tbio->bi_sector += conf->mirrors[d].rdev->data_offset;
 		tbio->bi_bdev = conf->mirrors[d].rdev->bdev;
···
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     tbio->bi_size >> 9);
+			     bio_sectors(tbio));
 		generic_make_request(tbio);
 	}
 
···
 	wbio2 = r10_bio->devs[1].repl_bio;
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, wbio->bi_size >> 9);
+		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
 		generic_make_request(wbio);
 	}
 	if (wbio2 && wbio2->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].replacement->nr_pending);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     wbio2->bi_size >> 9);
+			     bio_sectors(wbio2));
 		generic_make_request(wbio2);
 	}
 }
···
 	}
 }
 
-static void bi_complete(struct bio *bio, int error)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
-static int submit_bio_wait(int rw, struct bio *bio)
-{
-	struct completion event;
-	rw |= REQ_SYNC;
-
-	init_completion(&event);
-	bio->bi_private = &event;
-	bio->bi_end_io = bi_complete;
-	submit_bio(rw, bio);
-	wait_for_completion(&event);
-
-	return test_bit(BIO_UPTODATE, &bio->bi_flags);
-}
-
 static int narrow_write_error(struct r10bio *r10_bio, int i)
 {
 	struct bio *bio = r10_bio->master_bio;
···
 		r10_bio = mempool_alloc(conf->r10bio_pool,
 					GFP_NOIO);
 		r10_bio->master_bio = mbio;
-		r10_bio->sectors = (mbio->bi_size >> 9)
-			- sectors_handled;
+		r10_bio->sectors = bio_sectors(mbio) - sectors_handled;
 		r10_bio->state = 0;
 		set_bit(R10BIO_ReadError,
 			&r10_bio->state);
···
 					}
 				}
 				bio = r10_bio->devs[0].bio;
+				bio_reset(bio);
 				bio->bi_next = biolist;
 				biolist = bio;
 				bio->bi_private = r10_bio;
···
 				rdev = mirror->rdev;
 				if (!test_bit(In_sync, &rdev->flags)) {
 					bio = r10_bio->devs[1].bio;
+					bio_reset(bio);
 					bio->bi_next = biolist;
 					biolist = bio;
 					bio->bi_private = r10_bio;
···
 				if (rdev == NULL || bio == NULL ||
 				    test_bit(Faulty, &rdev->flags))
 					break;
+				bio_reset(bio);
 				bio->bi_next = biolist;
 				biolist = bio;
 				bio->bi_private = r10_bio;
···
 				r10_bio->devs[i].repl_bio->bi_end_io = NULL;
 
 			bio = r10_bio->devs[i].bio;
-			bio->bi_end_io = NULL;
+			bio_reset(bio);
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
···
 
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
+			bio_reset(bio);
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 
 			sector = r10_bio->devs[i].addr;
···
 			biolist = NULL;
 			goto giveup;
 		}
-	}
-
-	for (bio = biolist; bio ; bio=bio->bi_next) {
-
-		bio->bi_flags &= ~(BIO_POOL_MASK - 1);
-		if (bio->bi_end_io)
-			bio->bi_flags |= 1 << BIO_UPTODATE;
-		bio->bi_vcnt = 0;
-		bio->bi_idx = 0;
-		bio->bi_phys_segments = 0;
-		bio->bi_size = 0;
 	}
 
 	nr_sectors = 0;
···
 	read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
 	read_bio->bi_flags |= 1 << BIO_UPTODATE;
 	read_bio->bi_vcnt = 0;
-	read_bio->bi_idx = 0;
 	read_bio->bi_size = 0;
 	r10_bio->master_bio = read_bio;
 	r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum;
···
 		}
 		if (!rdev2 || test_bit(Faulty, &rdev2->flags))
 			continue;
+
+		bio_reset(b);
 		b->bi_bdev = rdev2->bdev;
 		b->bi_sector = r10_bio->devs[s/2].addr + rdev2->new_data_offset;
 		b->bi_private = r10_bio;
 		b->bi_end_io = end_reshape_write;
 		b->bi_rw = WRITE;
-		b->bi_flags &= ~(BIO_POOL_MASK - 1);
-		b->bi_flags |= 1 << BIO_UPTODATE;
 		b->bi_next = blist;
-		b->bi_vcnt = 0;
-		b->bi_idx = 0;
-		b->bi_size = 0;
 		blist = b;
 	}
 

drivers/md/raid5.c

···
  */
 static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 {
-	int sectors = bio->bi_size >> 9;
+	int sectors = bio_sectors(bio);
 	if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
 		return bio->bi_next;
 	else
···
 		bi = &sh->dev[i].req;
 		rbi = &sh->dev[i].rreq; /* For writing to replacement */
 
-		bi->bi_rw = rw;
-		rbi->bi_rw = rw;
-		if (rw & WRITE) {
-			bi->bi_end_io = raid5_end_write_request;
-			rbi->bi_end_io = raid5_end_write_request;
-		} else
-			bi->bi_end_io = raid5_end_read_request;
-
 		rcu_read_lock();
 		rrdev = rcu_dereference(conf->disks[i].replacement);
 		smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
···
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
+			bio_reset(bi);
 			bi->bi_bdev = rdev->bdev;
+			bi->bi_rw = rw;
+			bi->bi_end_io = (rw & WRITE)
+				? raid5_end_write_request
+				: raid5_end_read_request;
+			bi->bi_private = sh;
+
 			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
 				__func__, (unsigned long long)sh->sector,
 				bi->bi_rw, i);
···
 			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 				bi->bi_rw |= REQ_FLUSH;
 
-			bi->bi_flags = 1 << BIO_UPTODATE;
-			bi->bi_idx = 0;
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
 			bi->bi_size = STRIPE_SIZE;
-			bi->bi_next = NULL;
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
···
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
+			bio_reset(rbi);
 			rbi->bi_bdev = rrdev->bdev;
+			rbi->bi_rw = rw;
+			BUG_ON(!(rw & WRITE));
+			rbi->bi_end_io = raid5_end_write_request;
+			rbi->bi_private = sh;
+
 			pr_debug("%s: for %llu schedule op %ld on "
 				 "replacement disc %d\n",
 				__func__, (unsigned long long)sh->sector,
···
 			else
 				rbi->bi_sector = (sh->sector
 						  + rrdev->data_offset);
-			rbi->bi_flags = 1 << BIO_UPTODATE;
-			rbi->bi_idx = 0;
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
 			rbi->bi_size = STRIPE_SIZE;
-			rbi->bi_next = NULL;
 			if (conf->mddev->gendisk)
 				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
 						      rbi, disk_devt(conf->mddev->gendisk),
···
 	} else
 		bip = &sh->dev[dd_idx].toread;
 	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
-		if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
+		if (bio_end_sector(*bip) > bi->bi_sector)
 			goto overlap;
 		bip = & (*bip)->bi_next;
 	}
-	if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
+	if (*bip && (*bip)->bi_sector < bio_end_sector(bi))
 		goto overlap;
 
 	BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
···
 		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
 			     bi && bi->bi_sector <= sector;
 		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
-			if (bi->bi_sector + (bi->bi_size>>9) >= sector)
-				sector = bi->bi_sector + (bi->bi_size>>9);
+			if (bio_end_sector(bi) >= sector)
+				sector = bio_end_sector(bi);
 		}
 		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
 			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
···
 {
 	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
 	unsigned int chunk_sectors = mddev->chunk_sectors;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bio_sectors(bio);
 
 	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
 		chunk_sectors = mddev->new_chunk_sectors;
···
 {
 	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
 
-	if ((bi->bi_size>>9) > queue_max_sectors(q))
+	if (bio_sectors(bi) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
 	if (bi->bi_phys_segments > queue_max_segments(q))
···
 						    0,
 						    &dd_idx, NULL);
 
-	end_sector = align_bi->bi_sector + (align_bi->bi_size >> 9);
+	end_sector = bio_end_sector(align_bi);
 	rcu_read_lock();
 	rdev = rcu_dereference(conf->disks[dd_idx].replacement);
 	if (!rdev || test_bit(Faulty, &rdev->flags) ||
···
 		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 		if (!bio_fits_rdev(align_bi) ||
-		    is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9,
+		    is_badblock(rdev, align_bi->bi_sector, bio_sectors(align_bi),
 				&first_bad, &bad_sectors)) {
 			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
···
 	}
 
 	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	last_sector = bi->bi_sector + (bi->bi_size>>9);
+	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
 
···
 	logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	sector = raid5_compute_sector(conf, logical_sector,
 				      0, &dd_idx, NULL);
-	last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
+	last_sector = bio_end_sector(raid_bio);
 
 	for (; logical_sector < last_sector;
 	     logical_sector += STRIPE_SECTORS,

drivers/message/fusion/mptsas.c

···
 	}
 
 	/* do we need to support multiple segments? */
-	if (req->bio->bi_vcnt > 1 || rsp->bio->bi_vcnt > 1) {
+	if (bio_segments(req->bio) > 1 || bio_segments(rsp->bio) > 1) {
 		printk(MYIOC_s_ERR_FMT "%s: multiple segments req %u %u, rsp %u %u\n",
-		    ioc->name, __func__, req->bio->bi_vcnt, blk_rq_bytes(req),
-		    rsp->bio->bi_vcnt, blk_rq_bytes(rsp));
+		    ioc->name, __func__, bio_segments(req->bio), blk_rq_bytes(req),
+		    bio_segments(rsp->bio), blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 

drivers/s390/block/dcssblk.c

···
 	if ((bio->bi_sector & 7) != 0 || (bio->bi_size & 4095) != 0)
 		/* Request is not page-aligned. */
 		goto fail;
-	if (((bio->bi_size >> 9) + bio->bi_sector)
-			> get_capacity(bio->bi_bdev->bd_disk)) {
+	if (bio_end_sector(bio) > get_capacity(bio->bi_bdev->bd_disk)) {
 		/* Request beyond end of DCSS segment. */
 		goto fail;
 	}

drivers/scsi/libsas/sas_expander.c

···
 	}
 
 	/* do we need to support multiple segments? */
-	if (req->bio->bi_vcnt > 1 || rsp->bio->bi_vcnt > 1) {
+	if (bio_segments(req->bio) > 1 || bio_segments(rsp->bio) > 1) {
 		printk("%s: multiple segments req %u %u, rsp %u %u\n",
-		       __func__, req->bio->bi_vcnt, blk_rq_bytes(req),
-		       rsp->bio->bi_vcnt, blk_rq_bytes(rsp));
+		       __func__, bio_segments(req->bio), blk_rq_bytes(req),
+		       bio_segments(rsp->bio), blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 

drivers/scsi/mpt2sas/mpt2sas_transport.c

···
 	ioc->transport_cmds.status = MPT2_CMD_PENDING;
 
 	/* Check if the request is split across multiple segments */
-	if (req->bio->bi_vcnt > 1) {
+	if (bio_segments(req->bio) > 1) {
 		u32 offset = 0;
 
 		/* Allocate memory and copy the request */
···
 
 	/* Check if the response needs to be populated across
 	 * multiple segments */
-	if (rsp->bio->bi_vcnt > 1) {
+	if (bio_segments(rsp->bio) > 1) {
 		pci_addr_in = pci_alloc_consistent(ioc->pdev, blk_rq_bytes(rsp),
 		    &pci_dma_in);
 		if (!pci_addr_in) {
···
 	sgl_flags = (MPI2_SGE_FLAGS_SIMPLE_ELEMENT |
 	    MPI2_SGE_FLAGS_END_OF_BUFFER | MPI2_SGE_FLAGS_HOST_TO_IOC);
 	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	if (req->bio->bi_vcnt > 1) {
+	if (bio_segments(req->bio) > 1) {
 		ioc->base_add_sg_single(psge, sgl_flags |
 		    (blk_rq_bytes(req) - 4), pci_dma_out);
 	} else {
···
 	    MPI2_SGE_FLAGS_LAST_ELEMENT | MPI2_SGE_FLAGS_END_OF_BUFFER |
 	    MPI2_SGE_FLAGS_END_OF_LIST);
 	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	if (rsp->bio->bi_vcnt > 1) {
+	if (bio_segments(rsp->bio) > 1) {
 		ioc->base_add_sg_single(psge, sgl_flags |
 		    (blk_rq_bytes(rsp) + 4), pci_dma_in);
 	} else {
···
 		    le16_to_cpu(mpi_reply->ResponseDataLength);
 		/* check if the resp needs to be copied from the allocated
 		 * pci mem */
-		if (rsp->bio->bi_vcnt > 1) {
+		if (bio_segments(rsp->bio) > 1) {
 			u32 offset = 0;
 			u32 bytes_to_copy =
 			    le16_to_cpu(mpi_reply->ResponseDataLength);

fs/bio-integrity.c

···
 #include <linux/workqueue.h>
 #include <linux/slab.h>
 
-struct integrity_slab {
-	struct kmem_cache *slab;
-	unsigned short nr_vecs;
-	char name[8];
-};
+#define BIP_INLINE_VECS	4
 
-#define IS(x) { .nr_vecs = x, .name = "bip-"__stringify(x) }
-struct integrity_slab bip_slab[BIOVEC_NR_POOLS] __read_mostly = {
-	IS(1), IS(4), IS(16), IS(64), IS(128), IS(BIO_MAX_PAGES),
-};
-#undef IS
-
+static struct kmem_cache *bip_slab;
 static struct workqueue_struct *kintegrityd_wq;
-
-static inline unsigned int vecs_to_idx(unsigned int nr)
-{
-	switch (nr) {
-	case 1:
-		return 0;
-	case 2 ... 4:
-		return 1;
-	case 5 ... 16:
-		return 2;
-	case 17 ... 64:
-		return 3;
-	case 65 ... 128:
-		return 4;
-	case 129 ... BIO_MAX_PAGES:
-		return 5;
-	default:
-		BUG();
-	}
-}
-
-static inline int use_bip_pool(unsigned int idx)
-{
-	if (idx == BIOVEC_MAX_IDX)
-		return 1;
-
-	return 0;
-}
 
 /**
  * bio_integrity_alloc - Allocate integrity payload and attach it to bio
···
 						  unsigned int nr_vecs)
 {
 	struct bio_integrity_payload *bip;
-	unsigned int idx = vecs_to_idx(nr_vecs);
 	struct bio_set *bs = bio->bi_pool;
+	unsigned long idx = BIO_POOL_NONE;
+	unsigned inline_vecs;
 
-	if (!bs)
-		bs = fs_bio_set;
-
-	BUG_ON(bio == NULL);
-	bip = NULL;
-
-	/* Lower order allocations come straight from slab */
-	if (!use_bip_pool(idx))
-		bip = kmem_cache_alloc(bip_slab[idx].slab, gfp_mask);
-
-	/* Use mempool if lower order alloc failed or max vecs were requested */
-	if (bip == NULL) {
-		idx = BIOVEC_MAX_IDX;  /* so we free the payload properly later */
+	if (!bs) {
+		bip = kmalloc(sizeof(struct bio_integrity_payload) +
+			      sizeof(struct bio_vec) * nr_vecs, gfp_mask);
+		inline_vecs = nr_vecs;
+	} else {
 		bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
-
-		if (unlikely(bip == NULL)) {
-			printk(KERN_ERR "%s: could not alloc bip\n", __func__);
-			return NULL;
-		}
+		inline_vecs = BIP_INLINE_VECS;
 	}
 
+	if (unlikely(!bip))
+		return NULL;
+
 	memset(bip, 0, sizeof(*bip));
+
+	if (nr_vecs > inline_vecs) {
+		bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
+					  bs->bvec_integrity_pool);
+		if (!bip->bip_vec)
+			goto err;
+	} else {
+		bip->bip_vec = bip->bip_inline_vecs;
+	}
 
 	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
 
 	return bip;
+err:
+	mempool_free(bip, bs->bio_integrity_pool);
+	return NULL;
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
···
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct bio_set *bs = bio->bi_pool;
 
-	if (!bs)
-		bs = fs_bio_set;
-
-	BUG_ON(bip == NULL);
-
-	/* A cloned bio doesn't own the integrity metadata */
-	if (!bio_flagged(bio, BIO_CLONED) && !bio_flagged(bio, BIO_FS_INTEGRITY)
-	    && bip->bip_buf != NULL)
+	if (bip->bip_owns_buf)
 		kfree(bip->bip_buf);
 
-	if (use_bip_pool(bip->bip_slab))
+	if (bs) {
+		if (bip->bip_slab != BIO_POOL_NONE)
+			bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
+				  bip->bip_slab);
+
 		mempool_free(bip, bs->bio_integrity_pool);
-	else
-		kmem_cache_free(bip_slab[bip->bip_slab].slab, bip);
+	} else {
+		kfree(bip);
+	}
 
 	bio->bi_integrity = NULL;
 }
···
 		return -EIO;
 	}
 
+	bip->bip_owns_buf = 1;
 	bip->bip_buf = buf;
 	bip->bip_size = len;
 	bip->bip_sector = bio->bi_sector;
···
 	bp->bio1.bi_integrity = &bp->bip1;
 	bp->bio2.bi_integrity = &bp->bip2;
 
-	bp->iv1 = bip->bip_vec[0];
-	bp->iv2 = bip->bip_vec[0];
+	bp->iv1 = bip->bip_vec[bip->bip_idx];
+	bp->iv2 = bip->bip_vec[bip->bip_idx];
 
-	bp->bip1.bip_vec[0] = bp->iv1;
-	bp->bip2.bip_vec[0] = bp->iv2;
+	bp->bip1.bip_vec = &bp->iv1;
+	bp->bip2.bip_vec = &bp->iv2;
 
 	bp->iv1.bv_len = sectors * bi->tuple_size;
 	bp->iv2.bv_offset += sectors * bi->tuple_size;
···
 
 int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
-	unsigned int max_slab = vecs_to_idx(BIO_MAX_PAGES);
-
 	if (bs->bio_integrity_pool)
 		return 0;
 
-	bs->bio_integrity_pool =
-		mempool_create_slab_pool(pool_size, bip_slab[max_slab].slab);
+	bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab);
+
+	bs->bvec_integrity_pool = biovec_create_pool(bs, pool_size);
+	if (!bs->bvec_integrity_pool)
+		return -1;
 
 	if (!bs->bio_integrity_pool)
 		return -1;
···
 {
 	if (bs->bio_integrity_pool)
 		mempool_destroy(bs->bio_integrity_pool);
+
+	if (bs->bvec_integrity_pool)
+		mempool_destroy(bs->bio_integrity_pool);
 }
 EXPORT_SYMBOL(bioset_integrity_free);
 
 void __init bio_integrity_init(void)
 {
-	unsigned int i;
-
 	/*
 	 * kintegrityd won't block much but may burn a lot of CPU cycles.
 	 * Make it highpri CPU intensive wq with max concurrency of 1.
···
 	if (!kintegrityd_wq)
 		panic("Failed to create kintegrityd\n");
 
-	for (i = 0 ; i < BIOVEC_NR_POOLS ; i++) {
-		unsigned int size;
-
-		size = sizeof(struct bio_integrity_payload)
-			+ bip_slab[i].nr_vecs * sizeof(struct bio_vec);
-
-		bip_slab[i].slab =
-			kmem_cache_create(bip_slab[i].name, size, 0,
-					  SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-	}
+	bip_slab = kmem_cache_create("bio_integrity_payload",
+				     sizeof(struct bio_integrity_payload) +
+				     sizeof(struct bio_vec) * BIP_INLINE_VECS,
+				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	if (!bip_slab)
+		panic("Failed to create slab\n");
 }

fs/bio.c

···
 	return bvec_slabs[idx].nr_vecs;
 }
 
-void bvec_free_bs(struct bio_set *bs, struct bio_vec *bv, unsigned int idx)
+void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
 {
 	BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);
 
 	if (idx == BIOVEC_MAX_IDX)
-		mempool_free(bv, bs->bvec_pool);
+		mempool_free(bv, pool);
 	else {
 		struct biovec_slab *bvs = bvec_slabs + idx;
 
···
 	}
 }
 
-struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx,
-			      struct bio_set *bs)
+struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
+			   mempool_t *pool)
 {
 	struct bio_vec *bvl;
 
···
 	 */
 	if (*idx == BIOVEC_MAX_IDX) {
 fallback:
-		bvl = mempool_alloc(bs->bvec_pool, gfp_mask);
+		bvl = mempool_alloc(pool, gfp_mask);
 	} else {
 		struct biovec_slab *bvs = bvec_slabs + *idx;
 		gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
···
 	__bio_free(bio);
 
 	if (bs) {
-		if (bio_has_allocated_vec(bio))
-			bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
+		if (bio_flagged(bio, BIO_OWNS_VEC))
+			bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio));
 
 		/*
 		 * If we have front padding, adjust the bio pointer before freeing
···
 }
 EXPORT_SYMBOL(bio_reset);
 
+static void bio_alloc_rescue(struct work_struct *work)
+{
+	struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
+	struct bio *bio;
+
+	while (1) {
+		spin_lock(&bs->rescue_lock);
+		bio = bio_list_pop(&bs->rescue_list);
+		spin_unlock(&bs->rescue_lock);
+
+		if (!bio)
+			break;
+
+		generic_make_request(bio);
+	}
+}
+
+static void punt_bios_to_rescuer(struct bio_set *bs)
+{
+	struct bio_list punt, nopunt;
+	struct bio *bio;
+
+	/*
+	 * In order to guarantee forward progress we must punt only bios that
+	 * were allocated from this bio_set; otherwise, if there was a bio on
+	 * there for a stacking driver higher up in the stack, processing it
+	 * could require allocating bios from this bio_set, and doing that from
+	 * our own rescuer would be bad.
+	 *
+	 * Since bio lists are singly linked, pop them all instead of trying to
+	 * remove from the middle of the list:
+	 */
+
+	bio_list_init(&punt);
+	bio_list_init(&nopunt);
+
+	while ((bio = bio_list_pop(current->bio_list)))
+		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+
+	*current->bio_list = nopunt;
+
+	spin_lock(&bs->rescue_lock);
+	bio_list_merge(&bs->rescue_list, &punt);
+	spin_unlock(&bs->rescue_lock);
+
+	queue_work(bs->rescue_workqueue, &bs->rescue_work);
+}
+
 /**
  * bio_alloc_bioset - allocate a bio for I/O
  * @gfp_mask:   the GFP_ mask given to the slab allocator
···
  *   previously allocated bio for IO before attempting to allocate a new one.
  *   Failure to do so can cause deadlocks under memory pressure.
  *
+ *   Note that when running under generic_make_request() (i.e. any block
+ *   driver), bios are not submitted until after you return - see the code in
+ *   generic_make_request() that converts recursion into iteration, to prevent
+ *   stack overflows.
+ *
+ *   This would normally mean allocating multiple bios under
+ *   generic_make_request() would be susceptible to deadlocks, but we have
+ *   deadlock avoidance code that resubmits any blocked bios from a rescuer
+ *   thread.
+ *
+ *   However, we do not guarantee forward progress for allocations from other
+ *   mempools. Doing multiple allocations from the same mempool under
+ *   generic_make_request() should be avoided - instead, use bio_set's front_pad
+ *   for per bio allocations.
+ *
  *   RETURNS:
  *   Pointer to new bio on success, NULL on failure.
  */
 struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 {
+	gfp_t saved_gfp = gfp_mask;
 	unsigned front_pad;
 	unsigned inline_vecs;
 	unsigned long idx = BIO_POOL_NONE;
···
 		front_pad = 0;
 		inline_vecs = nr_iovecs;
 	} else {
+		/*
+		 * generic_make_request() converts recursion to iteration; this
+		 * means if we're running beneath it, any bios we allocate and
+		 * submit will not be submitted (and thus freed) until after we
+		 * return.
+		 *
+		 * This exposes us to a potential deadlock if we allocate
+		 * multiple bios from the same bio_set() while running
+		 * underneath generic_make_request(). If we were to allocate
+		 * multiple bios (say a stacking block driver that was splitting
+		 * bios), we would deadlock if we exhausted the mempool's
+		 * reserve.
+		 *
+		 * We solve this, and guarantee forward progress, with a rescuer
+		 * workqueue per bio_set. If we go to allocate and there are
+		 * bios on current->bio_list, we first try the allocation
+		 * without __GFP_WAIT; if that fails, we punt those bios we
+		 * would be blocking to the rescuer workqueue before we retry
+		 * with the original gfp_flags.
+		 */
+
+		if (current->bio_list && !bio_list_empty(current->bio_list))
+			gfp_mask &= ~__GFP_WAIT;
+
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
+		if (!p && gfp_mask != saved_gfp) {
+			punt_bios_to_rescuer(bs);
+			gfp_mask = saved_gfp;
+			p = mempool_alloc(bs->bio_pool, gfp_mask);
+		}
+
 		front_pad = bs->front_pad;
 		inline_vecs = BIO_INLINE_VECS;
 	}
···
 	bio_init(bio);
 
 	if (nr_iovecs > inline_vecs) {
-		bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
+		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
+		if (!bvl && gfp_mask != saved_gfp) {
+			punt_bios_to_rescuer(bs);
+			gfp_mask = saved_gfp;
+			bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
+		}
+
 		if (unlikely(!bvl))
 			goto err_free;
+
+		bio->bi_flags |= 1 << BIO_OWNS_VEC;
 	} else if (nr_iovecs) {
 		bvl = bio->bi_inline_vecs;
 	}
···
 }
 EXPORT_SYMBOL(bio_add_page);
 
+struct submit_bio_ret {
+	struct completion event;
+	int error;
+};
+
+static void submit_bio_wait_endio(struct bio *bio, int error)
+{
+	struct submit_bio_ret *ret = bio->bi_private;
+
+	ret->error = error;
+	complete(&ret->event);
+}
+
+/**
+ * submit_bio_wait - submit a bio, and wait until it completes
+ * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
+ * @bio: The &struct bio which describes the I/O
+ *
+ * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
+ * bio_endio() on failure.
+ */
+int submit_bio_wait(int rw, struct bio *bio)
+{
+	struct submit_bio_ret ret;
+
+	rw |= REQ_SYNC;
+	init_completion(&ret.event);
+	bio->bi_private = &ret;
+	bio->bi_end_io = submit_bio_wait_endio;
+	submit_bio(rw, bio);
+	wait_for_completion(&ret.event);
+
+	return ret.error;
+}
+EXPORT_SYMBOL(submit_bio_wait);
+
+/**
+ * bio_advance - increment/complete a bio by some number of bytes
+ * @bio:	bio to advance
+ * @bytes:	number of bytes to complete
+ *
+ * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
+ * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
+ * be updated on the last bvec as well.
+ *
+ * @bio will then represent the remaining, uncompleted portion of the io.
+ */
+void bio_advance(struct bio *bio, unsigned bytes)
+{
+	if (bio_integrity(bio))
+		bio_integrity_advance(bio, bytes);
+
+	bio->bi_sector += bytes >> 9;
+	bio->bi_size -= bytes;
+
+	if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
+		return;
+
+	while (bytes) {
+		if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
+			WARN_ONCE(1, "bio idx %d >= vcnt %d\n",
+				  bio->bi_idx, bio->bi_vcnt);
+			break;
+		}
+
+		if (bytes >= bio_iovec(bio)->bv_len) {
+			bytes -= bio_iovec(bio)->bv_len;
+			bio->bi_idx++;
+		} else {
+			bio_iovec(bio)->bv_len -= bytes;
+			bio_iovec(bio)->bv_offset += bytes;
+			bytes = 0;
+		}
+	}
+}
+EXPORT_SYMBOL(bio_advance);
+
+/**
+ * bio_alloc_pages - allocates a single page for each bvec in a bio
+ * @bio: bio to allocate pages for
+ * @gfp_mask: flags for allocation
+ *
+ * Allocates pages up to @bio->bi_vcnt.
+ *
+ * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
+ * freed.
+ */
+int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
+{
+	int i;
+	struct bio_vec *bv;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		bv->bv_page = alloc_page(gfp_mask);
+		if (!bv->bv_page) {
+			while (--bv >= bio->bi_io_vec)
+				__free_page(bv->bv_page);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(bio_alloc_pages);
+
+/**
+ * bio_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
+ * @src and @dst as linked lists of bios.
+ *
+ * Stops when it reaches the end of either @src or @dst - that is, copies
+ * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
+ */
+void bio_copy_data(struct bio *dst, struct bio *src)
+{
+	struct bio_vec *src_bv, *dst_bv;
+	unsigned src_offset, dst_offset, bytes;
+	void *src_p, *dst_p;
+
+	src_bv = bio_iovec(src);
+	dst_bv = bio_iovec(dst);
+
+	src_offset = src_bv->bv_offset;
+	dst_offset = dst_bv->bv_offset;
+
+	while (1) {
+		if (src_offset == src_bv->bv_offset + src_bv->bv_len) {
+			src_bv++;
+			if (src_bv == bio_iovec_idx(src, src->bi_vcnt)) {
+				src = src->bi_next;
+				if (!src)
+					break;
+
+				src_bv = bio_iovec(src);
+			}
+
+			src_offset = src_bv->bv_offset;
+		}
+
+		if (dst_offset == dst_bv->bv_offset + dst_bv->bv_len) {
+			dst_bv++;
+			if (dst_bv == bio_iovec_idx(dst, dst->bi_vcnt)) {
+				dst = dst->bi_next;
+				if (!dst)
+					break;
+
+				dst_bv = bio_iovec(dst);
+			}
+
+			dst_offset = dst_bv->bv_offset;
+		}
+
+		bytes = min(dst_bv->bv_offset + dst_bv->bv_len - dst_offset,
+			    src_bv->bv_offset + src_bv->bv_len - src_offset);
+
+		src_p = kmap_atomic(src_bv->bv_page);
+		dst_p = kmap_atomic(dst_bv->bv_page);
+
+		memcpy(dst_p + dst_bv->bv_offset,
+		       src_p + src_bv->bv_offset,
+		       bytes);
+
+		kunmap_atomic(dst_p);
+		kunmap_atomic(src_p);
+
+		src_offset += bytes;
+		dst_offset += bytes;
+	}
+}
+EXPORT_SYMBOL(bio_copy_data);
+
 struct bio_map_data {
 	struct bio_vec *iovecs;
 	struct sg_iovec *sgvecs;
···
 	int iov_idx = 0;
 	unsigned int iov_off = 0;
 
-	__bio_for_each_segment(bvec, bio, i, 0) {
+	bio_for_each_segment_all(bvec, bio, i) {
 		char *bv_addr = page_address(bvec->bv_page);
 		unsigned int bv_len = iovecs[i].bv_len;
 
···
 	return bio;
 cleanup:
 	if (!map_data)
-		bio_for_each_segment(bvec, bio, i)
+		bio_for_each_segment_all(bvec, bio, i)
 			__free_page(bvec->bv_page);
 
 	bio_put(bio);
···
 	/*
 	 * make sure we dirty pages we wrote to
 	 */
-	__bio_for_each_segment(bvec, bio, i, 0) {
+	bio_for_each_segment_all(bvec, bio, i) {
 		if (bio_data_dir(bio) == READ)
 			set_page_dirty_lock(bvec->bv_page);
 
···
 	int i;
 	char *p = bmd->sgvecs[0].iov_base;
 
-	__bio_for_each_segment(bvec, bio, i, 0) {
+	bio_for_each_segment_all(bvec, bio, i) {
 		char *addr = page_address(bvec->bv_page);
 		int len = bmd->iovecs[i].bv_len;
 
···
 	if (!reading) {
 		void *p = data;
 
-		bio_for_each_segment(bvec, bio, i) {
+		bio_for_each_segment_all(bvec, bio, i) {
 			char *addr = page_address(bvec->bv_page);
 
 			memcpy(addr, p, bvec->bv_len);
···
  */
 void bio_set_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec = bio->bi_io_vec;
+	struct bio_vec *bvec;
 	int i;
 
-	for (i = 0; i < bio->bi_vcnt; i++) {
-		struct page *page = bvec[i].bv_page;
+	bio_for_each_segment_all(bvec, bio, i) {
+		struct page *page = bvec->bv_page;
 
 		if (page && !PageCompound(page))
 			set_page_dirty_lock(page);
···
 
 static void bio_release_pages(struct bio *bio)
 {
-	struct bio_vec *bvec = bio->bi_io_vec;
+	struct bio_vec *bvec;
 	int i;
 
-	for (i = 0; i < bio->bi_vcnt; i++) {
-		struct page *page = bvec[i].bv_page;
+	bio_for_each_segment_all(bvec, bio, i) {
+		struct page *page = bvec->bv_page;
 
 		if (page)
 			put_page(page);
···
 
 void bio_check_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec = bio->bi_io_vec;
+	struct bio_vec *bvec;
 	int nr_clean_pages = 0;
 	int i;
 
-	for (i = 0; i < bio->bi_vcnt; i++) {
-		struct page *page = bvec[i].bv_page;
+	bio_for_each_segment_all(bvec, bio, i) {
+		struct page *page = bvec->bv_page;
 
 		if (PageDirty(page) || PageCompound(page)) {
 			page_cache_release(page);
-			bvec[i].bv_page = NULL;
+			bvec->bv_page = NULL;
 		} else {
 			nr_clean_pages++;
 		}
···
 	trace_block_split(bdev_get_queue(bi->bi_bdev), bi,
 				bi->bi_sector + first_sectors);
 
-	BUG_ON(bi->bi_vcnt != 1 && bi->bi_vcnt != 0);
-	BUG_ON(bi->bi_idx != 0);
+	BUG_ON(bio_segments(bi) > 1);
 	atomic_set(&bp->cnt, 3);
 	bp->error = 0;
 	bp->bio1 = *bi;
···
 	bp->bio1.bi_size = first_sectors << 9;
 
 	if (bi->bi_vcnt != 0) {
-		bp->bv1 = bi->bi_io_vec[0];
-		bp->bv2 = bi->bi_io_vec[0];
+		bp->bv1 = *bio_iovec(bi);
+		bp->bv2 = *bio_iovec(bi);
 
 		if (bio_is_rw(bi)) {
 			bp->bv2.bv_offset += first_sectors << 9;
···
 	if (index >= bio->bi_idx)
 		index = bio->bi_vcnt - 1;
 
-	__bio_for_each_segment(bv, bio, i, 0) {
+	bio_for_each_segment_all(bv, bio, i) {
 		if (i == index) {
 			if (offset > bv->bv_offset)
 				sectors += (offset - bv->bv_offset) / sector_sz;
···
  * create memory pools for biovec's in a bio_set.
  * use the global biovec slabs created for general use.
  */
-static int biovec_create_pools(struct bio_set *bs, int pool_entries)
+mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries)
 {
 	struct biovec_slab *bp = bvec_slabs + BIOVEC_MAX_IDX;
 
-	bs->bvec_pool = mempool_create_slab_pool(pool_entries, bp->slab);
-	if (!bs->bvec_pool)
-		return -ENOMEM;
-
-	return 0;
-}
-
-static void biovec_free_pools(struct bio_set *bs)
-{
-	mempool_destroy(bs->bvec_pool);
+	return mempool_create_slab_pool(pool_entries, bp->slab);
 }
 
 void bioset_free(struct bio_set *bs)
 {
+	if (bs->rescue_workqueue)
+		destroy_workqueue(bs->rescue_workqueue);
+
 	if (bs->bio_pool)
 		mempool_destroy(bs->bio_pool);
 
+	if (bs->bvec_pool)
+		mempool_destroy(bs->bvec_pool);
+
 	bioset_integrity_free(bs);
-	biovec_free_pools(bs);
 	bio_put_slab(bs);
 
 	kfree(bs);
···
 
 	bs->front_pad = front_pad;
 
+	spin_lock_init(&bs->rescue_lock);
+	bio_list_init(&bs->rescue_list);
+	INIT_WORK(&bs->rescue_work, bio_alloc_rescue);
+
 	bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad);
 	if (!bs->bio_slab) {
 		kfree(bs);
···
 	if (!bs->bio_pool)
 		goto bad;
 
-	if (!biovec_create_pools(bs, pool_size))
-		return bs;
+	bs->bvec_pool = biovec_create_pool(bs, pool_size);
+	if (!bs->bvec_pool)
+		goto bad;
 
+	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
+	if (!bs->rescue_workqueue)
+		goto bad;
+
+	return bs;
 bad:
 	bioset_free(bs);
 	return NULL;

fs/block_dev.c

···
 		return 0;
 
 	size -= pos;
-	if (size < INT_MAX)
+	if (size < iocb->ki_left)
 		nr_segs = iov_shorten((struct iovec *)iov, nr_segs, size);
 	return generic_file_aio_read(iocb, iov, nr_segs, pos);
 }

fs/btrfs/extent_io.c

···
 		if (old_compressed)
 			contig = bio->bi_sector == sector;
 		else
-			contig = bio->bi_sector + (bio->bi_size >> 9) ==
-				sector;
+			contig = bio_end_sector(bio) == sector;
 
 		if (prev_bio_flags != bio_flags || !contig ||
 		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||

fs/btrfs/volumes.c

···
 	}
 
 	prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
-	if ((bio->bi_size >> 9) > max_sectors)
+	if (bio_sectors(bio) > max_sectors)
 		return 0;
 
 	if (!q->merge_bvec_fn)

fs/buffer.c

···
 	bio->bi_io_vec[0].bv_offset = bh_offset(bh);
 
 	bio->bi_vcnt = 1;
-	bio->bi_idx = 0;
 	bio->bi_size = bh->b_size;
 
 	bio->bi_end_io = end_bio_bh_io_sync;

fs/direct-io.c

···
 static int dio_bio_complete(struct dio *dio, struct bio *bio)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct bio_vec *bvec = bio->bi_io_vec;
-	int page_no;
+	struct bio_vec *bvec;
+	unsigned i;
 
 	if (!uptodate)
 		dio->io_error = -EIO;
···
 	if (dio->is_async && dio->rw == READ) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
-		for (page_no = 0; page_no < bio->bi_vcnt; page_no++) {
-			struct page *page = bvec[page_no].bv_page;
+		bio_for_each_segment_all(bvec, bio, i) {
+			struct page *page = bvec->bv_page;
 
 			if (dio->rw == READ && !PageCompound(page))
 				set_page_dirty_lock(page);

fs/exofs/ore.c

···
 	struct bio_vec *bv;
 	unsigned i;
 
-	__bio_for_each_segment(bv, bio, i, 0) {
+	bio_for_each_segment_all(bv, bio, i) {
 		unsigned this_count = bv->bv_len;
 
 		if (likely(PAGE_SIZE == this_count))

fs/exofs/ore_raid.c

···
 		if (!bio)
 			continue;
 
-		__bio_for_each_segment(bv, bio, i, 0) {
+		bio_for_each_segment_all(bv, bio, i) {
 			struct page *page = bv->bv_page;
 
 			SetPageUptodate(page);

fs/fs-writeback.c

···
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/kthread.h>
-#include <linux/freezer.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
···
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
-/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
-static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
-{
-	if (bdi->wb.task) {
-		wake_up_process(bdi->wb.task);
-	} else {
-		/*
-		 * The bdi thread isn't there, wake up the forker thread which
-		 * will create and run it.
-		 */
-		wake_up_process(default_backing_dev_info.wb.task);
-	}
-}
-
 static void bdi_queue_work(struct backing_dev_info *bdi,
 			   struct wb_writeback_work *work)
 {
···
 
 	spin_lock_bh(&bdi->wb_lock);
 	list_add_tail(&work->list, &bdi->work_list);
-	if (!bdi->wb.task)
-		trace_writeback_nothread(bdi, work);
-	bdi_wakeup_flusher(bdi);
 	spin_unlock_bh(&bdi->wb_lock);
+
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 }
 
 static void
···
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		if (bdi->wb.task) {
-			trace_writeback_nowork(bdi);
-			wake_up_process(bdi->wb.task);
-		}
+		trace_writeback_nowork(bdi);
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 		return;
 	}
 
···
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	spin_lock_bh(&bdi->wb_lock);
-	bdi_wakeup_flusher(bdi);
-	spin_unlock_bh(&bdi->wb_lock);
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 }
 
 /*
···
 
 /*
  * Handle writeback of dirty data for the device backed by this bdi. Also
- * wakes up periodically and does kupdated style flushing.
+ * reschedules periodically and does kupdated style flushing.
  */
-int bdi_writeback_thread(void *data)
+void bdi_writeback_workfn(struct work_struct *work)
 {
-	struct bdi_writeback *wb = data;
+	struct bdi_writeback *wb = container_of(to_delayed_work(work),
+						struct bdi_writeback, dwork);
 	struct backing_dev_info *bdi = wb->bdi;
 	long pages_written;
 
 	set_worker_desc("flush-%s", dev_name(bdi->dev));
 	current->flags |= PF_SWAPWRITE;
-	set_freezable();
-	wb->last_active = jiffies;
 
-	/*
-	 * Our parent may run at a different priority, just set us to normal
-	 */
-	set_user_nice(current, 0);
-
-	trace_writeback_thread_start(bdi);
-
-	while (!kthread_freezable_should_stop(NULL)) {
+	if (likely(!current_is_workqueue_rescuer() ||
+		   list_empty(&bdi->bdi_list))) {
 		/*
-		 * Remove own delayed wake-up timer, since we are already awake
-		 * and we'll take care of the periodic write-back.
+		 * The normal path.  Keep writing back @bdi until its
+		 * work_list is empty.  Note that this path is also taken
+		 * if @bdi is shutting down even when we're running off the
+		 * rescuer as work_list needs to be drained.
 		 */
-		del_timer(&wb->wakeup_timer);
-
-		pages_written = wb_do_writeback(wb, 0);
-
+		do {
+			pages_written = wb_do_writeback(wb, 0);
+			trace_writeback_pages_written(pages_written);
+		} while (!list_empty(&bdi->work_list));
+	} else {
+		/*
+		 * bdi_wq can't get enough workers and we're running off
+		 * the emergency worker.  Don't hog it.  Hopefully, 1024 is
+		 * enough for efficient IO.
+		 */
+		pages_written = writeback_inodes_wb(&bdi->wb, 1024,
+						    WB_REASON_FORKER_THREAD);
 		trace_writeback_pages_written(pages_written);
-
-		if (pages_written)
-			wb->last_active = jiffies;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (!list_empty(&bdi->work_list) || kthread_should_stop()) {
-			__set_current_state(TASK_RUNNING);
-			continue;
-		}
-
-		if (wb_has_dirty_io(wb) && dirty_writeback_interval)
-			schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
-		else {
-			/*
-			 * We have nothing to do, so can go sleep without any
-			 * timeout and save power. When a work is queued or
-			 * something is made dirty - we will be woken up.
-			 */
-			schedule();
-		}
 	}
 
-	/* Flush any work that raced with us exiting */
-	if (!list_empty(&bdi->work_list))
-		wb_do_writeback(wb, 1);
+	if (!list_empty(&bdi->work_list) ||
+	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
+		queue_delayed_work(bdi_wq, &wb->dwork,
+			msecs_to_jiffies(dirty_writeback_interval * 10));
 
-	trace_writeback_thread_stop(bdi);
-	return 0;
+	current->flags &= ~PF_SWAPWRITE;
 }
-
 
 /*
  * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back

fs/gfs2/lops.c

···
 	u64 nblk;
 
 	if (bio) {
-		nblk = bio->bi_sector + bio_sectors(bio);
+		nblk = bio_end_sector(bio);
 		nblk >>= sdp->sd_fsb2bb_shift;
 		if (blkno == nblk)
 			return bio;

fs/jfs/jfs_logmgr.c

···
 	bio->bi_io_vec[0].bv_offset = bp->l_offset;
 
 	bio->bi_vcnt = 1;
-	bio->bi_idx = 0;
 	bio->bi_size = LOGPSIZE;
 
 	bio->bi_end_io = lbmIODone;
···
 	bio->bi_io_vec[0].bv_offset = bp->l_offset;
 
 	bio->bi_vcnt = 1;
-	bio->bi_idx = 0;
 	bio->bi_size = LOGPSIZE;
 
 	bio->bi_end_io = lbmIODone;

fs/logfs/dev_bdev.c

···
 	bio_vec.bv_len = PAGE_SIZE;
 	bio_vec.bv_offset = 0;
 	bio.bi_vcnt = 1;
-	bio.bi_idx = 0;
 	bio.bi_size = PAGE_SIZE;
 	bio.bi_bdev = bdev;
 	bio.bi_sector = page->index * (PAGE_SIZE >> 9);
···
 		if (i >= max_pages) {
 			/* Block layer cannot split bios :( */
 			bio->bi_vcnt = i;
-			bio->bi_idx = 0;
 			bio->bi_size = i * PAGE_SIZE;
 			bio->bi_bdev = super->s_bdev;
 			bio->bi_sector = ofs >> 9;
···
 		unlock_page(page);
 	}
 	bio->bi_vcnt = nr_pages;
-	bio->bi_idx = 0;
 	bio->bi_size = nr_pages * PAGE_SIZE;
 	bio->bi_bdev = super->s_bdev;
 	bio->bi_sector = ofs >> 9;
···
 		if (i >= max_pages) {
 			/* Block layer cannot split bios :( */
 			bio->bi_vcnt = i;
-			bio->bi_idx = 0;
 			bio->bi_size = i * PAGE_SIZE;
 			bio->bi_bdev = super->s_bdev;
 			bio->bi_sector = ofs >> 9;
···
 		bio->bi_io_vec[i].bv_offset = 0;
 	}
 	bio->bi_vcnt = nr_pages;
-	bio->bi_idx = 0;
 	bio->bi_size = nr_pages * PAGE_SIZE;
 	bio->bi_bdev = super->s_bdev;
 	bio->bi_sector = ofs >> 9;

include/linux/backing-dev.h

···
 #include <linux/writeback.h>
 #include <linux/atomic.h>
 #include <linux/sysctl.h>
+#include <linux/workqueue.h>
 
 struct page;
 struct device;
···
  * Bits in backing_dev_info.state
  */
 enum bdi_state {
-	BDI_pending,		/* On its way to being activated */
 	BDI_wb_alloc,		/* Default embedded wb allocated */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
···
 	unsigned int nr;
 
 	unsigned long last_old_flush;	/* last old data flush */
-	unsigned long last_active;	/* last time bdi thread was active */
 
-	struct task_struct *task;	/* writeback thread */
-	struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
+	struct delayed_work dwork;	/* work item used for writeback */
 	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 */
···
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
-int bdi_writeback_thread(void *data);
+void bdi_writeback_workfn(struct work_struct *work);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
 void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
-extern struct list_head bdi_pending_list;
+
+extern struct workqueue_struct *bdi_wq;
 
 static inline int wb_has_dirty_io(struct bdi_writeback *wb)
 {
···
 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)

include/linux/bio.h

···
 #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_end_sector(bio)	((bio)->bi_sector + bio_sectors((bio)))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
···
 		return page_address(bio_page(bio)) + bio_offset(bio);
 
 	return NULL;
-}
-
-static inline int bio_has_allocated_vec(struct bio *bio)
-{
-	return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs;
 }
 
 /*
···
 #define bio_io_error(bio) bio_endio((bio), -EIO)
 
 /*
- * drivers should not use the __ version unless they _really_ want to
- * run through the entire bio and not just pending pieces
+ * drivers should not use the __ version unless they _really_ know what
+ * they're doing
  */
 #define __bio_for_each_segment(bvl, bio, i, start_idx)			\
 	for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx);	\
 	     i < (bio)->bi_vcnt;					\
 	     bvl++, i++)
 
+/*
+ * drivers should _never_ use the all version - the bio may have been split
+ * before it got to the driver and the driver won't own all of it
+ */
+#define bio_for_each_segment_all(bvl, bio, i)				\
+	for (i = 0;							\
+	     bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt;	\
+	     i++)
+
 #define bio_for_each_segment(bvl, bio, i)				\
-	__bio_for_each_segment(bvl, bio, i, (bio)->bi_idx)
+	for (i = (bio)->bi_idx;						\
+	     bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt;	\
+	     i++)
 
 /*
  * get a reference to a bio, so it won't disappear. the intended use is
···
 	unsigned short		bip_slab;	/* slab the bip came from */
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_idx;	/* current bip_vec index */
+	unsigned		bip_owns_buf:1;	/* should free bip_buf */
 
 	struct work_struct	bip_work;	/* I/O completion */
-	struct bio_vec		bip_vec[0];	/* embedded bvec array */
+
+	struct bio_vec		*bip_vec;
+	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
···
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
+extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries);
 
 extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
 extern void bio_put(struct bio *);
···
 extern void bio_endio(struct bio *, int);
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
+
+extern int submit_bio_wait(int rw, struct bio *bio);
+extern void bio_advance(struct bio *, unsigned);
 
 extern void bio_init(struct bio *);
 extern void bio_reset(struct bio *);
···
 }
 #endif
 
+extern void bio_copy_data(struct bio *dst, struct bio *src);
+extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
+
 extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
 				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
···
 				     int, int, gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
-extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
-extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int);
+extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
+extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 #ifdef CONFIG_BLK_CGROUP
···
 static inline int bio_associate_current(struct bio *bio) { return -ENOENT; }
 static inline void bio_disassociate_task(struct bio *bio) { }
 #endif	/* CONFIG_BLK_CGROUP */
-
-/*
- * bio_set is used to allow other portions of the IO system to
- * allocate their own private memory pools for bio and iovec structures.
- * These memory pools in turn all allocate from the bio_slab
- * and the bvec_slabs[].
- */
-#define BIO_POOL_SIZE 2
-#define BIOVEC_NR_POOLS 6
-#define BIOVEC_MAX_IDX	(BIOVEC_NR_POOLS - 1)
-
-struct bio_set {
-	struct kmem_cache *bio_slab;
-	unsigned int front_pad;
-
-	mempool_t *bio_pool;
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	mempool_t *bio_integrity_pool;
-#endif
-	mempool_t *bvec_pool;
-};
-
-struct biovec_slab {
-	int nr_vecs;
-	char *name;
-	struct kmem_cache *slab;
-};
-
-/*
- * a small number of entries is fine, not going to be performance critical.
- * basically we just need to survive
- */
-#define BIO_SPLIT_ENTRIES 2
 
 #ifdef CONFIG_HIGHMEM
 /*
···
 
 	return bio;
 }
+
+/*
+ * bio_set is used to allow other portions of the IO system to
+ * allocate their own private memory pools for bio and iovec structures.
+ * These memory pools in turn all allocate from the bio_slab
+ * and the bvec_slabs[].
+ */
+#define BIO_POOL_SIZE 2
+#define BIOVEC_NR_POOLS 6
+#define BIOVEC_MAX_IDX	(BIOVEC_NR_POOLS - 1)
+
+struct bio_set {
+	struct kmem_cache *bio_slab;
+	unsigned int front_pad;
+
+	mempool_t *bio_pool;
+	mempool_t *bvec_pool;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	mempool_t *bio_integrity_pool;
+	mempool_t *bvec_integrity_pool;
+#endif
+
+	/*
+	 * Deadlock avoidance for stacking block drivers: see comments in
+	 * bio_alloc_bioset() for details
+	 */
+	spinlock_t		rescue_lock;
+	struct bio_list		rescue_list;
+	struct work_struct	rescue_work;
+	struct workqueue_struct	*rescue_workqueue;
+};
+
+struct biovec_slab {
+	int nr_vecs;
+	char *name;
+	struct kmem_cache *slab;
+};
+
+/*
+ * a small number of entries is fine, not going to be performance critical.
+ * basically we just need to survive
+ */
+#define BIO_SPLIT_ENTRIES 2
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 

include/linux/blk_types.h

···
  * BIO_POOL_IDX()
  */
 #define BIO_RESET_BITS	13
+#define BIO_OWNS_VEC	13	/* bio_free() should free bvec */
 
 #define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
···
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
+	__REQ_PM,		/* runtime pm request */
 	__REQ_NR_BITS,		/* stops here */
 };
 
···
 	 REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
 	 REQ_SECURE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
+
+#define BIO_NO_ADVANCE_ITER_MASK	(REQ_DISCARD|REQ_WRITE_SAME)
 
 /* This mask is used for both bio and request merge checking */
 #define REQ_NOMERGE_FLAGS \
···
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
 #define REQ_KERNEL		(1 << __REQ_KERNEL)
+#define REQ_PM			(1 << __REQ_PM)
 
 #endif /* __LINUX_BLK_TYPES_H */

include/linux/blkdev.h

···
 	 */
 	struct kobject kobj;
 
+#ifdef CONFIG_PM_RUNTIME
+	struct device		*dev;
+	int			rpm_status;
+	unsigned int		nr_pending;
+#endif
+
 	/*
 	 * queue settings
 	 */
···
 						     unsigned int cmd_flags)
 {
 	if (unlikely(cmd_flags & REQ_DISCARD))
-		return q->limits.max_discard_sectors;
+		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
 	if (unlikely(cmd_flags & REQ_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
···
 struct request_queue *blk_alloc_queue(gfp_t);
 struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
+
+/*
+ * block layer runtime pm functions
+ */
+#ifdef CONFIG_PM_RUNTIME
+extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev);
+extern int blk_pre_runtime_suspend(struct request_queue *q);
+extern void blk_post_runtime_suspend(struct request_queue *q, int err);
+extern void blk_pre_runtime_resume(struct request_queue *q);
+extern void blk_post_runtime_resume(struct request_queue *q, int err);
+#else
+static inline void blk_pm_runtime_init(struct request_queue *q,
+	struct device *dev) {}
+static inline int blk_pre_runtime_suspend(struct request_queue *q)
+{
+	return -ENOSYS;
+}
+static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {}
+static inline void blk_pre_runtime_resume(struct request_queue *q) {}
+static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
+#endif
 
 /*
  * blk_plug permits building a queue of related requests by holding the I/O

include/trace/events/block.h

···
 		__entry->dev		= bio->bi_bdev ?
 					  bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
···
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		__entry->error		= error;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 	),
···
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
···
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
···
 	TP_fast_assign(
 		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio ? bio->bi_sector : 0;
-		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		__entry->nr_sector	= bio ? bio_sectors(bio) : 0;
 		blk_fill_rwbs(__entry->rwbs,
 			      bio ? bio->bi_rw : 0, __entry->nr_sector);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
···
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->nr_sector	= bio_sectors(bio);
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);

include/trace/events/writeback.h

···
 DEFINE_EVENT(writeback_work_class, name, \
 	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \
 	TP_ARGS(bdi, work))
-DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_start);
···
 
 DEFINE_WRITEBACK_EVENT(writeback_nowork);
 DEFINE_WRITEBACK_EVENT(writeback_wake_background);
-DEFINE_WRITEBACK_EVENT(writeback_wake_thread);
-DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread);
 DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
 DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
-DEFINE_WRITEBACK_EVENT(writeback_thread_start);
-DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
 
 DECLARE_EVENT_CLASS(wbc_class,
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),

kernel/relay.c

···
 static void relay_remove_buf(struct kref *kref)
 {
 	struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref);
-	buf->chan->cb->remove_buf_file(buf->dentry);
 	relay_destroy_buf(buf);
 }
 
···
 {
 	buf->finalized = 1;
 	del_timer_sync(&buf->timer);
+	buf->chan->cb->remove_buf_file(buf->dentry);
 	kref_put(&buf->kref, relay_remove_buf);
 }
 

mm/backing-dev.c

···
 static struct class *bdi_class;
 
 /*
- * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as
- * reader side protection for bdi_pending_list. bdi_list has RCU reader side
+ * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side
  * locking.
  */
 DEFINE_SPINLOCK(bdi_lock);
 LIST_HEAD(bdi_list);
-LIST_HEAD(bdi_pending_list);
+
+/* bdi_wq serves all asynchronous writeback tasks */
+struct workqueue_struct *bdi_wq;
 
 void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
 {
···
 {
 	int err;
 
+	bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE |
+					      WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!bdi_wq)
+		return -ENOMEM;
+
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
···
 int bdi_has_dirty_io(struct backing_dev_info *bdi)
 {
 	return wb_has_dirty_io(&bdi->wb);
-}
-
-static void wakeup_timer_fn(unsigned long data)
-{
-	struct backing_dev_info *bdi = (struct backing_dev_info *)data;
-
-	spin_lock_bh(&bdi->wb_lock);
-	if (bdi->wb.task) {
-		trace_writeback_wake_thread(bdi);
-		wake_up_process(bdi->wb.task);
-	} else if (bdi->dev) {
-		/*
-		 * When bdi tasks are inactive for long time, they are killed.
-		 * In this case we have to wake-up the forker thread which
-		 * should create and run the bdi thread.
-		 */
-		trace_writeback_wake_forker_thread(bdi);
-		wake_up_process(default_backing_dev_info.wb.task);
-	}
-	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
···
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
-}
-
-/*
- * Calculate the longest interval (jiffies) bdi threads are allowed to be
- * inactive.
- */
-static unsigned long bdi_longest_inactive(void)
-{
-	unsigned long interval;
-
-	interval = msecs_to_jiffies(dirty_writeback_interval * 10);
-	return max(5UL * 60 * HZ, interval);
-}
-
-/*
- * Clear pending bit and wakeup anybody waiting for flusher thread creation or
- * shutdown
- */
-static void bdi_clear_pending(struct backing_dev_info *bdi)
-{
-	clear_bit(BDI_pending, &bdi->state);
-	smp_mb__after_clear_bit();
-	wake_up_bit(&bdi->state, BDI_pending);
-}
-
-static int bdi_forker_thread(void *ptr)
-{
-	struct bdi_writeback *me = ptr;
-
-	current->flags |= PF_SWAPWRITE;
-	set_freezable();
-
-	/*
-	 * Our parent may run at a different priority, just set us to normal
-	 */
-	set_user_nice(current, 0);
-
-	for (;;) {
-		struct task_struct *task = NULL;
-		struct backing_dev_info *bdi;
-		enum {
-			NO_ACTION,   /* Nothing to do */
-			FORK_THREAD, /* Fork bdi thread */
-			KILL_THREAD, /* Kill inactive bdi thread */
-		} action = NO_ACTION;
-
-		/*
-		 * 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)) {
-			del_timer(&me->wakeup_timer);
-			wb_do_writeback(me, 0);
-		}
-
-		spin_lock_bh(&bdi_lock);
-		/*
-		 * In the following loop we are going to check whether we have
-		 * some work to do without any synchronization with tasks
-		 * waking us up to do work for them. Set the task state here
-		 * so that we don't miss wakeups after verifying conditions.
-		 */
-		set_current_state(TASK_INTERRUPTIBLE);
-
-		list_for_each_entry(bdi, &bdi_list, bdi_list) {
-			bool have_dirty_io;
-
-			if (!bdi_cap_writeback_dirty(bdi) ||
-			     bdi_cap_flush_forker(bdi))
-				continue;
-
-			WARN(!test_bit(BDI_registered, &bdi->state),
-			     "bdi %p/%s is not registered!\n", bdi, bdi->name);
-
-			have_dirty_io = !list_empty(&bdi->work_list) ||
-					wb_has_dirty_io(&bdi->wb);
-
-			/*
-			 * If the bdi has work to do, but the thread does not
-			 * exist - create it.
-			 */
-			if (!bdi->wb.task && have_dirty_io) {
-				/*
-				 * Set the pending bit - if someone will try to
-				 * unregister this bdi - it'll wait on this bit.
-				 */
-				set_bit(BDI_pending, &bdi->state);
-				action = FORK_THREAD;
-				break;
-			}
-
-			spin_lock(&bdi->wb_lock);
-
-			/*
-			 * If there is no work to do and the bdi thread was
-			 * inactive long enough - kill it. The wb_lock is taken
-			 * to make sure no-one adds more work to this bdi and
-			 * wakes the bdi thread up.
-			 */
-			if (bdi->wb.task && !have_dirty_io &&
-			    time_after(jiffies, bdi->wb.last_active +
-						bdi_longest_inactive())) {
-				task = bdi->wb.task;
-				bdi->wb.task = NULL;
-				spin_unlock(&bdi->wb_lock);
-				set_bit(BDI_pending, &bdi->state);
-				action = KILL_THREAD;
-				break;
-			}
-			spin_unlock(&bdi->wb_lock);
-		}
-		spin_unlock_bh(&bdi_lock);
-
-		/* Keep working if default bdi still has things to do */
-		if (!list_empty(&me->bdi->work_list))
-			__set_current_state(TASK_RUNNING);
-
-		switch (action) {
-		case FORK_THREAD:
-			__set_current_state(TASK_RUNNING);
-			task = kthread_create(bdi_writeback_thread, &bdi->wb,
-					      "flush-%s", dev_name(bdi->dev));
-			if (IS_ERR(task)) {
-				/*
-				 * If thread creation fails, force writeout of
-				 * the bdi from the thread. Hopefully 1024 is
-				 * large enough for efficient IO.
-				 */
-				writeback_inodes_wb(&bdi->wb, 1024,
-						    WB_REASON_FORKER_THREAD);
-			} else {
-				/*
-				 * The spinlock makes sure we do not lose
-				 * wake-ups when racing with 'bdi_queue_work()'.
-				 * And as soon as the bdi thread is visible, we
-				 * can start it.
-				 */
-				spin_lock_bh(&bdi->wb_lock);
-				bdi->wb.task = task;
-				spin_unlock_bh(&bdi->wb_lock);
-				wake_up_process(task);
-			}
-			bdi_clear_pending(bdi);
-			break;
-
-		case KILL_THREAD:
-			__set_current_state(TASK_RUNNING);
-			kthread_stop(task);
-			bdi_clear_pending(bdi);
-			break;
-
-		case NO_ACTION:
-			if (!wb_has_dirty_io(me) || !dirty_writeback_interval)
-				/*
-				 * There are no dirty data. The only thing we
-				 * should now care about is checking for
-				 * inactive bdi threads and killing them. Thus,
-				 * let's sleep for longer time, save energy and
-				 * be friendly for battery-driven devices.
-				 */
-				schedule_timeout(bdi_longest_inactive());
-			else
-				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
-			try_to_freeze();
-			break;
-		}
-	}
-
-	return 0;
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
 }
 
 /*
···
 	spin_unlock_bh(&bdi_lock);
 
 	synchronize_rcu_expedited();
+
+	/* bdi_list is now unused, clear it to mark @bdi dying */
+	INIT_LIST_HEAD(&bdi->bdi_list);
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
···
 		return PTR_ERR(dev);
 
 	bdi->dev = 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 = &bdi->wb;
-
-		wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
-						dev_name(dev));
-		if (IS_ERR(wb->task))
-			return PTR_ERR(wb->task);
-	}
 
 	bdi_debug_register(bdi, dev_name(dev));
 	set_bit(BDI_registered, &bdi->state);
···
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
-	struct task_struct *task;
-
 	if (!bdi_cap_writeback_dirty(bdi))
 		return;
 
···
 	bdi_remove_from_list(bdi);
 
 	/*
-	 * If setup is pending, wait for that to complete first
+	 * Drain work list and shutdown the delayed_work.  At this point,
+	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
+	 * is dying and its work_list needs to be drained no matter what.
 	 */
-	wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
-			TASK_UNINTERRUPTIBLE);
+	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	flush_delayed_work(&bdi->wb.dwork);
+	WARN_ON(!list_empty(&bdi->work_list));
 
 	/*
-	 * Finally, kill the kernel thread. We don't need to be RCU
-	 * safe anymore, since the bdi is gone from visibility.
+	 * This shouldn't be necessary unless @bdi for some reason has
+	 * unflushed dirty IO after work_list is drained.  Do it anyway
+	 * just in case.
 	 */
-	spin_lock_bh(&bdi->wb_lock);
-	task = bdi->wb.task;
-	bdi->wb.task = NULL;
-	spin_unlock_bh(&bdi->wb_lock);
-
-	if (task)
-		kthread_stop(task);
+	cancel_delayed_work_sync(&bdi->wb.dwork);
 }
 
 /*
···
 		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
-		del_timer_sync(&bdi->wb.wakeup_timer);
 
-		if (!bdi_cap_flush_forker(bdi))
-			bdi_wb_shutdown(bdi);
+		bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
 
 		spin_lock_bh(&bdi->wb_lock);
···
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
 	spin_lock_init(&wb->list_lock);
-	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+	INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
 }
 
 /*
···
 	bdi_unregister(bdi);
 
 	/*
-	 * If bdi_unregister() had already been called earlier, the
-	 * wakeup_timer could still be armed because bdi_prune_sb()
-	 * can race with the bdi_wakeup_thread_delayed() calls from
-	 * __mark_inode_dirty().
+	 * If bdi_unregister() had already been called earlier, the dwork
+	 * could still be pending because bdi_prune_sb() can race with the
+	 * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty().
 	 */
-	del_timer_sync(&bdi->wb.wakeup_timer);
+	cancel_delayed_work_sync(&bdi->wb.dwork);
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);

mm/bounce.c

···
 	struct bio_vec *tovec, *fromvec;
 	int i;
 
-	__bio_for_each_segment(tovec, to, i, 0) {
+	bio_for_each_segment(tovec, to, i) {
 		fromvec = from->bi_io_vec + i;
 
 		/*
···
 	/*
 	 * free up bounce indirect pages used
 	 */
-	__bio_for_each_segment(bvec, bio, i, 0) {
+	bio_for_each_segment_all(bvec, bio, i) {
 		org_vec = bio_orig->bi_io_vec + i;
 		if (bvec->bv_page == org_vec->bv_page)
 			continue;
···
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 			       mempool_t *pool, int force)
 {
-	struct page *page;
-	struct bio *bio = NULL;
-	int i, rw = bio_data_dir(*bio_orig);
+	struct bio *bio;
+	int rw = bio_data_dir(*bio_orig);
 	struct bio_vec *to, *from;
+	unsigned i;
 
-	bio_for_each_segment(from, *bio_orig, i) {
-		page = from->bv_page;
+	bio_for_each_segment(from, *bio_orig, i)
+		if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q))
+			goto bounce;
 
-		/*
-		 * is destination page below bounce pfn?
-		 */
+	return;
+bounce:
+	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
+
+	bio_for_each_segment_all(to, bio, i) {
+		struct page *page = to->bv_page;
+
 		if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
 			continue;
 
-		/*
-		 * irk, bounce it
-		 */
-		if (!bio) {
-			unsigned int cnt = (*bio_orig)->bi_vcnt;
-
-			bio = bio_alloc(GFP_NOIO, cnt);
-			memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec));
-		}
-			
-
-		to = bio->bi_io_vec + i;
-
-		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
-		to->bv_len = from->bv_len;
-		to->bv_offset = from->bv_offset;
 		inc_zone_page_state(to->bv_page, NR_BOUNCE);
+		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
 
 		if (rw == WRITE) {
 			char *vto, *vfrom;
 
-			flush_dcache_page(from->bv_page);
+			flush_dcache_page(page);
+
 			vto = page_address(to->bv_page) + to->bv_offset;
-			vfrom = kmap(from->bv_page) + from->bv_offset;
+			vfrom = kmap_atomic(page) + to->bv_offset;
 			memcpy(vto, vfrom, to->bv_len);
-			kunmap(from->bv_page);
+			kunmap_atomic(vfrom);
 		}
 	}
-
-	/*
-	 * no pages bounced
-	 */
-	if (!bio)
-		return;
 
 	trace_block_bio_bounce(q, *bio_orig);
 
-	/*
-	 * at least one page was bounced, fill in possible non-highmem
-	 * pages
-	 */
-	__bio_for_each_segment(from, *bio_orig, i, 0) {
-		to = bio_iovec_idx(bio, i);
-		if (!to->bv_page) {
-			to->bv_page = from->bv_page;
-			to->bv_len = from->bv_len;
-			to->bv_offset = from->bv_offset;
-		}
-	}
-
-	bio->bi_bdev = (*bio_orig)->bi_bdev;
 	bio->bi_flags |= (1 << BIO_BOUNCED);
-	bio->bi_sector = (*bio_orig)->bi_sector;
-	bio->bi_rw = (*bio_orig)->bi_rw;
-
-	bio->bi_vcnt = (*bio_orig)->bi_vcnt;
-	bio->bi_idx = (*bio_orig)->bi_idx;
-	bio->bi_size = (*bio_orig)->bi_size;
 
 	if (pool == page_pool) {
 		bio->bi_end_io = bounce_end_io_write;

mm/page_io.c

···
 		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
 		bio->bi_io_vec[0].bv_offset = 0;
 		bio->bi_vcnt = 1;
-		bio->bi_idx = 0;
 		bio->bi_size = PAGE_SIZE;
 		bio->bi_end_io = end_io;
 	}