Merge branch 'for-4.2/core' into for-4.2/drivers

We need the blkdev_reread_part() changes for drivers to adapt.

block/blk-core.c

@@ -1522,7 +1522,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
  * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    unsigned int *request_count)
+			    unsigned int *request_count,
+			    struct request **same_queue_rq)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1542,8 +1543,16 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	list_for_each_entry_reverse(rq, plug_list, queuelist) {
 		int el_ret;
 
-		if (rq->q == q)
+		if (rq->q == q) {
 			(*request_count)++;
+			/*
+			 * Only blk-mq multiple hardware queues case checks the
+			 * rq in the same queue, there should be only one such
+			 * rq in a queue
+			 **/
+			if (same_queue_rq)
+				*same_queue_rq = rq;
+		}
 
 		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
 			continue;
@@ -1608,7 +1617,7 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * any locks.
 	 */
 	if (!blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count))
+	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1716,8 +1725,6 @@ static void handle_bad_sector(struct bio *bio)
 			bio->bi_rw,
 			(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_FAIL_MAKE_REQUEST
@@ -3032,21 +3039,20 @@ void blk_start_plug(struct blk_plug *plug)
 {
 	struct task_struct *tsk = current;
 
+	/*
+	 * If this is a nested plug, don't actually assign it.
+	 */
+	if (tsk->plug)
+		return;
+
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->mq_list);
 	INIT_LIST_HEAD(&plug->cb_list);
-
-	/*
-	 * If this is a nested plug, don't actually assign it. It will be
-	 * flushed on its own.
-	 */
-	if (!tsk->plug) {
 	/*
 	 * Store ordering should not be needed here, since a potential
 	 * preempt will imply a full memory barrier
 	 */
 	tsk->plug = plug;
-	}
 }
 EXPORT_SYMBOL(blk_start_plug);
 
@@ -3193,9 +3199,10 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 
 void blk_finish_plug(struct blk_plug *plug)
 {
+	if (plug != current->plug)
+		return;
 	blk_flush_plug_list(plug, false);
 
-	if (plug == current->plug)
 	current->plug = NULL;
 }
 EXPORT_SYMBOL(blk_finish_plug);

block/blk-mq.c

@@ -89,7 +89,8 @@ static int blk_mq_queue_enter(struct request_queue *q, gfp_t gfp)
 			return -EBUSY;
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!q->mq_freeze_depth || blk_queue_dying(q));
+				!atomic_read(&q->mq_freeze_depth) ||
+				blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
 		if (ret)
@@ -112,13 +113,10 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref)
 
 void blk_mq_freeze_queue_start(struct request_queue *q)
 {
-	bool freeze;
+	int freeze_depth;
 
-	spin_lock_irq(q->queue_lock);
-	freeze = !q->mq_freeze_depth++;
-	spin_unlock_irq(q->queue_lock);
-
-	if (freeze) {
+	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
+	if (freeze_depth == 1) {
 		percpu_ref_kill(&q->mq_usage_counter);
 		blk_mq_run_hw_queues(q, false);
 	}
@@ -143,13 +141,11 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	bool wake;
+	int freeze_depth;
 
-	spin_lock_irq(q->queue_lock);
-	wake = !--q->mq_freeze_depth;
-	WARN_ON_ONCE(q->mq_freeze_depth < 0);
-	spin_unlock_irq(q->queue_lock);
-	if (wake) {
+	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
+	WARN_ON_ONCE(freeze_depth < 0);
+	if (!freeze_depth) {
 		percpu_ref_reinit(&q->mq_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
@@ -1224,6 +1220,38 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	return rq;
 }
 
+static int blk_mq_direct_issue_request(struct request *rq)
+{
+	int ret;
+	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
+			rq->mq_ctx->cpu);
+	struct blk_mq_queue_data bd = {
+		.rq = rq,
+		.list = NULL,
+		.last = 1
+	};
+
+	/*
+	 * For OK queue, we are done. For error, kill it. Any other
+	 * error (busy), just add it to our list as we previously
+	 * would have done
+	 */
+	ret = q->mq_ops->queue_rq(hctx, &bd);
+	if (ret == BLK_MQ_RQ_QUEUE_OK)
+		return 0;
+	else {
+		__blk_mq_requeue_request(rq);
+
+		if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+			return 0;
+		}
+		return -1;
+	}
+}
+
 /*
  * Multiple hardware queue variant. This will not use per-process plugs,
  * but will attempt to bypass the hctx queueing if we can go straight to
@@ -1235,6 +1263,9 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
+	unsigned int request_count = 0;
+	struct blk_plug *plug;
+	struct request *same_queue_rq = NULL;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1243,6 +1274,10 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return;
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
@@ -1253,38 +1288,42 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto run_queue;
 	}
 
+	plug = current->plug;
 	/*
 	 * If the driver supports defer issued based on 'last', then
 	 * queue it up like normal since we can potentially save some
 	 * CPU this way.
 	 */
-	if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
-		struct blk_mq_queue_data bd = {
-			.rq = rq,
-			.list = NULL,
-			.last = 1
-		};
-		int ret;
+	if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
+	    !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
+		struct request *old_rq = NULL;
 
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * For OK queue, we are done. For error, kill it. Any other
-		 * error (busy), just add it to our list as we previously
-		 * would have done
+		 * we do limited pluging. If bio can be merged, do merge.
+		 * Otherwise the existing request in the plug list will be
+		 * issued. So the plug list will have one request at most
 		 */
-		ret = q->mq_ops->queue_rq(data.hctx, &bd);
-		if (ret == BLK_MQ_RQ_QUEUE_OK)
-			goto done;
-		else {
-			__blk_mq_requeue_request(rq);
-
-			if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
-				rq->errors = -EIO;
-				blk_mq_end_request(rq, rq->errors);
-				goto done;
-			}
+		if (plug) {
+			/*
+			 * The plug list might get flushed before this. If that
+			 * happens, same_queue_rq is invalid and plug list is empty
+			 **/
+			if (same_queue_rq && !list_empty(&plug->mq_list)) {
+				old_rq = same_queue_rq;
+				list_del_init(&old_rq->queuelist);
 			}
+			list_add_tail(&rq->queuelist, &plug->mq_list);
+		} else /* is_sync */
+			old_rq = rq;
+		blk_mq_put_ctx(data.ctx);
+		if (!old_rq)
+			return;
+		if (!blk_mq_direct_issue_request(old_rq))
+			return;
+		blk_mq_insert_request(old_rq, false, true, true);
+		return;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1297,7 +1336,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
-done:
 	blk_mq_put_ctx(data.ctx);
 }
 
@@ -1309,16 +1347,11 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = rw_is_sync(bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
-	unsigned int use_plug, request_count = 0;
+	struct blk_plug *plug;
+	unsigned int request_count = 0;
 	struct blk_map_ctx data;
 	struct request *rq;
 
-	/*
-	 * If we have multiple hardware queues, just go directly to
-	 * one of those for sync IO.
-	 */
-	use_plug = !is_flush_fua && !is_sync;
-
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
@@ -1326,8 +1359,8 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
-	if (use_plug && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count))
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
 	rq = blk_mq_map_request(q, bio, &data);
@@ -1345,9 +1378,7 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	 * utilize that to temporarily store requests until the task is
 	 * either done or scheduled away.
 	 */
-	if (use_plug) {
-		struct blk_plug *plug = current->plug;
-
+	plug = current->plug;
 	if (plug) {
 		blk_mq_bio_to_request(rq, bio);
 		if (list_empty(&plug->mq_list))
@@ -1360,7 +1391,6 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		return;
 	}
-	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
@@ -2047,7 +2077,7 @@ void blk_mq_free_queue(struct request_queue *q)
 /* Basically redo blk_mq_init_queue with queue frozen */
 static void blk_mq_queue_reinit(struct request_queue *q)
 {
-	WARN_ON_ONCE(!q->mq_freeze_depth);
+	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
 
 	blk_mq_sysfs_unregister(q);
 

block/blk.h

@@ -78,7 +78,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    unsigned int *request_count);
+			    unsigned int *request_count,
+			    struct request **same_queue_rq);
 
 void blk_account_io_start(struct request *req, bool new_io);
 void blk_account_io_completion(struct request *req, unsigned int bytes);

block/bounce.c

@@ -128,9 +128,6 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
 	struct bio_vec *bvec, *org_vec;
 	int i;
 
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
 	/*
 	 * free up bounce indirect pages used
 	 */

block/ioctl.c

@@ -150,21 +150,48 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
-static int blkdev_reread_part(struct block_device *bdev)
+/*
+ * This is an exported API for the block driver, and will not
+ * acquire bd_mutex. This API should be used in case that
+ * caller has held bd_mutex already.
+ */
+int __blkdev_reread_part(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	int res;
 
 	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (!mutex_trylock(&bdev->bd_mutex))
-		return -EBUSY;
-	res = rescan_partitions(disk, bdev);
+
+	lockdep_assert_held(&bdev->bd_mutex);
+
+	return rescan_partitions(disk, bdev);
+}
+EXPORT_SYMBOL(__blkdev_reread_part);
+
+/*
+ * This is an exported API for the block driver, and will
+ * try to acquire bd_mutex. If bd_mutex has been held already
+ * in current context, please call __blkdev_reread_part().
+ *
+ * Make sure the held locks in current context aren't required
+ * in open()/close() handler and I/O path for avoiding ABBA deadlock:
+ * - bd_mutex is held before calling block driver's open/close
+ *   handler
+ * - reading partition table may submit I/O to the block device
+ */
+int blkdev_reread_part(struct block_device *bdev)
+{
+	int res;
+
+	mutex_lock(&bdev->bd_mutex);
+	res = __blkdev_reread_part(bdev);
 	mutex_unlock(&bdev->bd_mutex);
+
 	return res;
 }
+EXPORT_SYMBOL(blkdev_reread_part);
 
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len, int secure)

fs/btrfs/disk-io.c

@@ -3269,11 +3269,8 @@ static int write_dev_supers(struct btrfs_device *device,
  */
 static void btrfs_end_empty_barrier(struct bio *bio, int err)
 {
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+	if (err)
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
 	if (bio->bi_private)
 		complete(bio->bi_private);
 	bio_put(bio);
@@ -3301,11 +3298,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 
 		wait_for_completion(&device->flush_wait);
 
-		if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
-			printk_in_rcu("BTRFS: disabling barriers on dev %s\n",
-				      rcu_str_deref(device->name));
-			device->nobarriers = 1;
-		} else if (!bio_flagged(bio, BIO_UPTODATE)) {
+		if (!bio_flagged(bio, BIO_UPTODATE)) {
 			ret = -EIO;
 			btrfs_dev_stat_inc_and_print(device,
 				BTRFS_DEV_STAT_FLUSH_ERRS);

fs/btrfs/extent_io.c

@@ -2767,8 +2767,6 @@ static int __must_check submit_one_bio(int rw, struct bio *bio,
 	else
 		btrfsic_submit_bio(rw, bio);
 
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
 	bio_put(bio);
 	return ret;
 }

fs/buffer.c

@@ -2938,10 +2938,6 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
 {
 	struct buffer_head *bh = bio->bi_private;
 
-	if (err == -EOPNOTSUPP) {
-		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-	}
-
 	if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
 		set_bit(BH_Quiet, &bh->b_state);
 
@@ -3041,13 +3037,7 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	if (buffer_prio(bh))
 		rw |= REQ_PRIO;
 
-	bio_get(bio);
 	submit_bio(rw, bio);
-
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
-
-	bio_put(bio);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(_submit_bh);

fs/ext4/page-io.c

@@ -359,7 +359,6 @@ void ext4_io_submit(struct ext4_io_submit *io)
 	if (bio) {
 		bio_get(io->io_bio);
 		submit_bio(io->io_op, io->io_bio);
-		BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
 		bio_put(io->io_bio);
 	}
 	io->io_bio = NULL;

fs/nilfs2/segbuf.c

@@ -343,11 +343,6 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct nilfs_segment_buffer *segbuf = bio->bi_private;
 
-	if (err == -EOPNOTSUPP) {
-		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		/* to be detected by nilfs_segbuf_submit_bio() */
-	}
-
 	if (!uptodate)
 		atomic_inc(&segbuf->sb_err);
 
@@ -374,15 +369,8 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
 
 	bio->bi_end_io = nilfs_end_bio_write;
 	bio->bi_private = segbuf;
-	bio_get(bio);
 	submit_bio(mode, bio);
 	segbuf->sb_nbio++;
-	if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
-		bio_put(bio);
-		err = -EOPNOTSUPP;
-		goto failed;
-	}
-	bio_put(bio);
 
 	wi->bio = NULL;
 	wi->rest_blocks -= wi->end - wi->start;

include/linux/blk_types.h

@@ -112,18 +112,15 @@ struct bio {
  * bio flags
  */
 #define BIO_UPTODATE	0	/* ok after I/O completion */
-#define BIO_RW_BLOCK	1	/* RW_AHEAD set, and read/write would block */
-#define BIO_EOF		2	/* out-out-bounds error */
-#define BIO_SEG_VALID	3	/* bi_phys_segments valid */
-#define BIO_CLONED	4	/* doesn't own data */
-#define BIO_BOUNCED	5	/* bio is a bounce bio */
-#define BIO_USER_MAPPED 6	/* contains user pages */
-#define BIO_EOPNOTSUPP	7	/* not supported */
-#define BIO_NULL_MAPPED 8	/* contains invalid user pages */
-#define BIO_QUIET	9	/* Make BIO Quiet */
-#define BIO_SNAP_STABLE	10	/* bio data must be snapshotted during write */
-#define BIO_CHAIN	11	/* chained bio, ->bi_remaining in effect */
-#define BIO_REFFED	12	/* bio has elevated ->bi_cnt */
+#define BIO_SEG_VALID	1	/* bi_phys_segments valid */
+#define BIO_CLONED	2	/* doesn't own data */
+#define BIO_BOUNCED	3	/* bio is a bounce bio */
+#define BIO_USER_MAPPED 4	/* contains user pages */
+#define BIO_NULL_MAPPED 5	/* contains invalid user pages */
+#define BIO_QUIET	6	/* Make BIO Quiet */
+#define BIO_SNAP_STABLE	7	/* bio data must be snapshotted during write */
+#define BIO_CHAIN	8	/* chained bio, ->bi_remaining in effect */
+#define BIO_REFFED	9	/* bio has elevated ->bi_cnt */
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes

include/linux/blkdev.h

@@ -444,7 +444,7 @@ struct request_queue {
 	struct mutex		sysfs_lock;
 
 	int			bypass_depth;
-	int			mq_freeze_depth;
+	atomic_t		mq_freeze_depth;
 
 #if defined(CONFIG_BLK_DEV_BSG)
 	bsg_job_fn		*bsg_job_fn;

include/linux/fs.h

@@ -2279,6 +2279,9 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
 					      void *holder);
 extern void blkdev_put(struct block_device *bdev, fmode_t mode);
+extern int __blkdev_reread_part(struct block_device *bdev);
+extern int blkdev_reread_part(struct block_device *bdev);
+
 #ifdef CONFIG_SYSFS
 extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
 extern void bd_unlink_disk_holder(struct block_device *bdev,

include/linux/swap.h

@@ -377,7 +377,6 @@ extern void end_swap_bio_write(struct bio *bio, int err);
 extern int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	void (*end_write_func)(struct bio *, int));
 extern int swap_set_page_dirty(struct page *page);
-extern void end_swap_bio_read(struct bio *bio, int err);
 
 int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
 		unsigned long nr_pages, sector_t start_block);

kernel/power/Makefile

@@ -7,8 +7,7 @@ obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
-				   block_io.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
 obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 

kernel/power/block_io.c

-/*
- * This file provides functions for block I/O operations on swap/file.
- *
- * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
- * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- *
- * This file is released under the GPLv2.
- */
-
-#include <linux/bio.h>
-#include <linux/kernel.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-
-#include "power.h"
-
-/**
- *	submit - submit BIO request.
- *	@rw:	READ or WRITE.
- *	@off	physical offset of page.
- *	@page:	page we're reading or writing.
- *	@bio_chain: list of pending biod (for async reading)
- *
- *	Straight from the textbook - allocate and initialize the bio.
- *	If we're reading, make sure the page is marked as dirty.
- *	Then submit it and, if @bio_chain == NULL, wait.
- */
-static int submit(int rw, struct block_device *bdev, sector_t sector,
-		struct page *page, struct bio **bio_chain)
-{
-	const int bio_rw = rw | REQ_SYNC;
-	struct bio *bio;
-
-	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
-	bio->bi_iter.bi_sector = sector;
-	bio->bi_bdev = bdev;
-	bio->bi_end_io = end_swap_bio_read;
-
-	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
-		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
-			(unsigned long long)sector);
-		bio_put(bio);
-		return -EFAULT;
-	}
-
-	lock_page(page);
-	bio_get(bio);
-
-	if (bio_chain == NULL) {
-		submit_bio(bio_rw, bio);
-		wait_on_page_locked(page);
-		if (rw == READ)
-			bio_set_pages_dirty(bio);
-		bio_put(bio);
-	} else {
-		if (rw == READ)
-			get_page(page);	/* These pages are freed later */
-		bio->bi_private = *bio_chain;
-		*bio_chain = bio;
-		submit_bio(bio_rw, bio);
-	}
-	return 0;
-}
-
-int hib_bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(READ, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
-			virt_to_page(addr), bio_chain);
-}
-
-int hib_bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
-{
-	return submit(WRITE, hib_resume_bdev, page_off * (PAGE_SIZE >> 9),
-			virt_to_page(addr), bio_chain);
-}
-
-int hib_wait_on_bio_chain(struct bio **bio_chain)
-{
-	struct bio *bio;
-	struct bio *next_bio;
-	int ret = 0;
-
-	if (bio_chain == NULL)
-		return 0;
-
-	bio = *bio_chain;
-	if (bio == NULL)
-		return 0;
-	while (bio) {
-		struct page *page;
-
-		next_bio = bio->bi_private;
-		page = bio->bi_io_vec[0].bv_page;
-		wait_on_page_locked(page);
-		if (!PageUptodate(page) || PageError(page))
-			ret = -EIO;
-		put_page(page);
-		bio_put(bio);
-		bio = next_bio;
-	}
-	*bio_chain = NULL;
-	return ret;
-}

kernel/power/power.h

@@ -163,15 +163,6 @@ extern void swsusp_close(fmode_t);
 extern int swsusp_unmark(void);
 #endif
 
-/* kernel/power/block_io.c */
-extern struct block_device *hib_resume_bdev;
-
-extern int hib_bio_read_page(pgoff_t page_off, void *addr,
-		struct bio **bio_chain);
-extern int hib_bio_write_page(pgoff_t page_off, void *addr,
-		struct bio **bio_chain);
-extern int hib_wait_on_bio_chain(struct bio **bio_chain);
-
 struct timeval;
 /* kernel/power/swsusp.c */
 extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *);

kernel/power/swap.c

@@ -212,7 +212,84 @@ int swsusp_swap_in_use(void)
  */
 
 static unsigned short root_swap = 0xffff;
-struct block_device *hib_resume_bdev;
+static struct block_device *hib_resume_bdev;
+
+struct hib_bio_batch {
+	atomic_t		count;
+	wait_queue_head_t	wait;
+	int			error;
+};
+
+static void hib_init_batch(struct hib_bio_batch *hb)
+{
+	atomic_set(&hb->count, 0);
+	init_waitqueue_head(&hb->wait);
+	hb->error = 0;
+}
+
+static void hib_end_io(struct bio *bio, int error)
+{
+	struct hib_bio_batch *hb = bio->bi_private;
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct page *page = bio->bi_io_vec[0].bv_page;
+
+	if (!uptodate || error) {
+		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
+				imajor(bio->bi_bdev->bd_inode),
+				iminor(bio->bi_bdev->bd_inode),
+				(unsigned long long)bio->bi_iter.bi_sector);
+
+		if (!error)
+			error = -EIO;
+	}
+
+	if (bio_data_dir(bio) == WRITE)
+		put_page(page);
+
+	if (error && !hb->error)
+		hb->error = error;
+	if (atomic_dec_and_test(&hb->count))
+		wake_up(&hb->wait);
+
+	bio_put(bio);
+}
+
+static int hib_submit_io(int rw, pgoff_t page_off, void *addr,
+		struct hib_bio_batch *hb)
+{
+	struct page *page = virt_to_page(addr);
+	struct bio *bio;
+	int error = 0;
+
+	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
+	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
+	bio->bi_bdev = hib_resume_bdev;
+
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
+			(unsigned long long)bio->bi_iter.bi_sector);
+		bio_put(bio);
+		return -EFAULT;
+	}
+
+	if (hb) {
+		bio->bi_end_io = hib_end_io;
+		bio->bi_private = hb;
+		atomic_inc(&hb->count);
+		submit_bio(rw, bio);
+	} else {
+		error = submit_bio_wait(rw, bio);
+		bio_put(bio);
+	}
+
+	return error;
+}
+
+static int hib_wait_io(struct hib_bio_batch *hb)
+{
+	wait_event(hb->wait, atomic_read(&hb->count) == 0);
+	return hb->error;
+}
 
 /*
  * Saving part
@@ -222,7 +299,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
@@ -231,7 +308,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 		swsusp_header->flags = flags;
 		if (flags & SF_CRC32_MODE)
 			swsusp_header->crc32 = handle->crc32;
-		error = hib_bio_write_page(swsusp_resume_block,
+		error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Swap header not found!\n");
@@ -271,10 +348,10 @@ static int swsusp_swap_check(void)
  *	write_page - Write one page to given swap location.
  *	@buf:		Address we're writing.
  *	@offset:	Offset of the swap page we're writing to.
- *	@bio_chain:	Link the next write BIO here
+ *	@hb:		bio completion batch
  */
 
-static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
+static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 {
 	void *src;
 	int ret;
@@ -282,13 +359,13 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 	if (!offset)
 		return -ENOSPC;
 
-	if (bio_chain) {
+	if (hb) {
 		src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN |
 		                              __GFP_NORETRY);
 		if (src) {
 			copy_page(src, buf);
 		} else {
-			ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
+			ret = hib_wait_io(hb); /* Free pages */
 			if (ret)
 				return ret;
 			src = (void *)__get_free_page(__GFP_WAIT |
@@ -298,14 +375,14 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 				copy_page(src, buf);
 			} else {
 				WARN_ON_ONCE(1);
-				bio_chain = NULL;	/* Go synchronous */
+				hb = NULL;	/* Go synchronous */
 				src = buf;
 			}
 		}
 	} else {
 		src = buf;
 	}
-	return hib_bio_write_page(offset, src, bio_chain);
+	return hib_submit_io(WRITE_SYNC, offset, src, hb);
 }
 
 static void release_swap_writer(struct swap_map_handle *handle)
@@ -348,7 +425,7 @@ static int get_swap_writer(struct swap_map_handle *handle)
 }
 
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
-				struct bio **bio_chain)
+		struct hib_bio_batch *hb)
 {
 	int error = 0;
 	sector_t offset;
@@ -356,7 +433,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 	if (!handle->cur)
 		return -EINVAL;
 	offset = alloc_swapdev_block(root_swap);
-	error = write_page(buf, offset, bio_chain);
+	error = write_page(buf, offset, hb);
 	if (error)
 		return error;
 	handle->cur->entries[handle->k++] = offset;
@@ -365,15 +442,15 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		if (!offset)
 			return -ENOSPC;
 		handle->cur->next_swap = offset;
-		error = write_page(handle->cur, handle->cur_swap, bio_chain);
+		error = write_page(handle->cur, handle->cur_swap, hb);
 		if (error)
 			goto out;
 		clear_page(handle->cur);
 		handle->cur_swap = offset;
 		handle->k = 0;
 
-		if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
-			error = hib_wait_on_bio_chain(bio_chain);
+		if (hb && low_free_pages() <= handle->reqd_free_pages) {
+			error = hib_wait_io(hb);
 			if (error)
 				goto out;
 			/*
@@ -445,23 +522,24 @@ static int save_image(struct swap_map_handle *handle,
 	int ret;
 	int nr_pages;
 	int err2;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	ktime_t start;
 	ktime_t stop;
 
+	hib_init_batch(&hb);
+
 	printk(KERN_INFO "PM: Saving image data pages (%u pages)...\n",
 		nr_to_write);
 	m = nr_to_write / 10;
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 	while (1) {
 		ret = snapshot_read_next(snapshot);
 		if (ret <= 0)
 			break;
-		ret = swap_write_page(handle, data_of(*snapshot), &bio);
+		ret = swap_write_page(handle, data_of(*snapshot), &hb);
 		if (ret)
 			break;
 		if (!(nr_pages % m))
@@ -469,7 +547,7 @@ static int save_image(struct swap_map_handle *handle,
 			       nr_pages / m * 10);
 		nr_pages++;
 	}
-	err2 = hib_wait_on_bio_chain(&bio);
+	err2 = hib_wait_io(&hb);
 	stop = ktime_get();
 	if (!ret)
 		ret = err2;
@@ -580,7 +658,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	int ret = 0;
 	int nr_pages;
 	int err2;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	ktime_t start;
 	ktime_t stop;
 	size_t off;
@@ -589,6 +667,8 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	struct cmp_data *data = NULL;
 	struct crc_data *crc = NULL;
 
+	hib_init_batch(&hb);
+
 	/*
 	 * We'll limit the number of threads for compression to limit memory
 	 * footprint.
@@ -674,7 +754,6 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 	for (;;) {
 		for (thr = 0; thr < nr_threads; thr++) {
@@ -748,7 +827,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			     off += PAGE_SIZE) {
 				memcpy(page, data[thr].cmp + off, PAGE_SIZE);
 
-				ret = swap_write_page(handle, page, &bio);
+				ret = swap_write_page(handle, page, &hb);
 				if (ret)
 					goto out_finish;
 			}
@@ -759,7 +838,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	}
 
 out_finish:
-	err2 = hib_wait_on_bio_chain(&bio);
+	err2 = hib_wait_io(&hb);
 	stop = ktime_get();
 	if (!ret)
 		ret = err2;
@@ -906,7 +985,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 			return -ENOMEM;
 		}
 
-		error = hib_bio_read_page(offset, tmp->map, NULL);
+		error = hib_submit_io(READ_SYNC, offset, tmp->map, NULL);
 		if (error) {
 			release_swap_reader(handle);
 			return error;
@@ -919,7 +998,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 }
 
 static int swap_read_page(struct swap_map_handle *handle, void *buf,
-				struct bio **bio_chain)
+		struct hib_bio_batch *hb)
 {
 	sector_t offset;
 	int error;
@@ -930,7 +1009,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = hib_bio_read_page(offset, buf, bio_chain);
+	error = hib_submit_io(READ_SYNC, offset, buf, hb);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
@@ -968,27 +1047,28 @@ static int load_image(struct swap_map_handle *handle,
 	int ret = 0;
 	ktime_t start;
 	ktime_t stop;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	int err2;
 	unsigned nr_pages;
 
+	hib_init_batch(&hb);
+
 	printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n",
 		nr_to_read);
 	m = nr_to_read / 10;
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 	for ( ; ; ) {
 		ret = snapshot_write_next(snapshot);
 		if (ret <= 0)
 			break;
-		ret = swap_read_page(handle, data_of(*snapshot), &bio);
+		ret = swap_read_page(handle, data_of(*snapshot), &hb);
 		if (ret)
 			break;
 		if (snapshot->sync_read)
-			ret = hib_wait_on_bio_chain(&bio);
+			ret = hib_wait_io(&hb);
 		if (ret)
 			break;
 		if (!(nr_pages % m))
@@ -996,7 +1076,7 @@ static int load_image(struct swap_map_handle *handle,
 			       nr_pages / m * 10);
 		nr_pages++;
 	}
-	err2 = hib_wait_on_bio_chain(&bio);
+	err2 = hib_wait_io(&hb);
 	stop = ktime_get();
 	if (!ret)
 		ret = err2;
@@ -1067,7 +1147,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	unsigned int m;
 	int ret = 0;
 	int eof = 0;
-	struct bio *bio;
+	struct hib_bio_batch hb;
 	ktime_t start;
 	ktime_t stop;
 	unsigned nr_pages;
@@ -1080,6 +1160,8 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	struct dec_data *data = NULL;
 	struct crc_data *crc = NULL;
 
+	hib_init_batch(&hb);
+
 	/*
 	 * We'll limit the number of threads for decompression to limit memory
 	 * footprint.
@@ -1190,7 +1272,6 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	if (!m)
 		m = 1;
 	nr_pages = 0;
-	bio = NULL;
 	start = ktime_get();
 
 	ret = snapshot_write_next(snapshot);
@@ -1199,7 +1280,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 	for(;;) {
 		for (i = 0; !eof && i < want; i++) {
-			ret = swap_read_page(handle, page[ring], &bio);
+			ret = swap_read_page(handle, page[ring], &hb);
 			if (ret) {
 				/*
 				 * On real read error, finish. On end of data,
@@ -1226,7 +1307,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 			if (!asked)
 				break;
 
-			ret = hib_wait_on_bio_chain(&bio);
+			ret = hib_wait_io(&hb);
 			if (ret)
 				goto out_finish;
 			have += asked;
@@ -1281,7 +1362,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		 * Wait for more data while we are decompressing.
 		 */
 		if (have < LZO_CMP_PAGES && asked) {
-			ret = hib_wait_on_bio_chain(&bio);
+			ret = hib_wait_io(&hb);
 			if (ret)
 				goto out_finish;
 			have += asked;
@@ -1430,7 +1511,7 @@ int swsusp_check(void)
 	if (!IS_ERR(hib_resume_bdev)) {
 		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		clear_page(swsusp_header);
-		error = hib_bio_read_page(swsusp_resume_block,
+		error = hib_submit_io(READ_SYNC, swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
@@ -1438,7 +1519,7 @@ int swsusp_check(void)
 		if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = hib_bio_write_page(swsusp_resume_block,
+			error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
 			error = -EINVAL;
@@ -1482,10 +1563,10 @@ int swsusp_unmark(void)
 {
 	int error;
 
-	hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io(READ_SYNC, swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
-		error = hib_bio_write_page(swsusp_resume_block,
+		error = hib_submit_io(WRITE_SYNC, swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "PM: Cannot find swsusp signature!\n");

kernel/sched/core.c

@@ -4387,10 +4387,7 @@ long __sched io_schedule_timeout(long timeout)
 	long ret;
 
 	current->in_iowait = 1;
-	if (old_iowait)
 	blk_schedule_flush_plug(current);
-	else
-		blk_flush_plug(current);
 
 	delayacct_blkio_start();
 	rq = raw_rq();

mm/page_io.c

@@ -69,7 +69,7 @@ void end_swap_bio_write(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-void end_swap_bio_read(struct bio *bio, int err)
+static void end_swap_bio_read(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;