Merge remote-tracking branch 'block/for-next'

Conflicts:
	fs/btrfs/extent_io.c
	fs/f2fs/data.c
	fs/f2fs/segment.c
	include/trace/events/f2fs.h

10 files changed, 237 insertions, 161 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 060ff695085c..70654521dab6 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -61,25 +61,87 @@
  * various member access, note that bio_data should of course not be used
  * on highmem page vectors
  */
-#define bio_iovec_idx(bio, idx)	(&((bio)->bi_io_vec[(idx)]))
-#define bio_iovec(bio)		bio_iovec_idx((bio), (bio)->bi_idx)
-#define bio_page(bio)		bio_iovec((bio))->bv_page
-#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)))
+#define __bvec_iter_bvec(bvec, iter)	(&(bvec)[(iter).bi_idx])
+
+#define bvec_iter_page(bvec, iter)				\
+	(__bvec_iter_bvec((bvec), (iter))->bv_page)
+
+#define bvec_iter_len(bvec, iter)				\
+	min((iter).bi_size,					\
+	    __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done)
+
+#define bvec_iter_offset(bvec, iter)				\
+	(__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done)
+
+#define bvec_iter_bvec(bvec, iter)				\
+((struct bio_vec) {						\
+	.bv_page	= bvec_iter_page((bvec), (iter)),	\
+	.bv_len		= bvec_iter_len((bvec), (iter)),	\
+	.bv_offset	= bvec_iter_offset((bvec), (iter)),	\
+})
+
+#define bio_iter_iovec(bio, iter)				\
+	bvec_iter_bvec((bio)->bi_io_vec, (iter))
+
+#define bio_iter_page(bio, iter)				\
+	bvec_iter_page((bio)->bi_io_vec, (iter))
+#define bio_iter_len(bio, iter)					\
+	bvec_iter_len((bio)->bi_io_vec, (iter))
+#define bio_iter_offset(bio, iter)				\
+	bvec_iter_offset((bio)->bi_io_vec, (iter))
+
+#define bio_page(bio)		bio_iter_page((bio), (bio)->bi_iter)
+#define bio_offset(bio)		bio_iter_offset((bio), (bio)->bi_iter)
+#define bio_iovec(bio)		bio_iter_iovec((bio), (bio)->bi_iter)
+
+#define bio_multiple_segments(bio)				\
+	((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len)
+#define bio_sectors(bio)	((bio)->bi_iter.bi_size >> 9)
+#define bio_end_sector(bio)	((bio)->bi_iter.bi_sector + bio_sectors((bio)))
+
+/*
+ * Check whether this bio carries any data or not. A NULL bio is allowed.
+ */
+static inline bool bio_has_data(struct bio *bio)
+{
+	if (bio &&
+	    bio->bi_iter.bi_size &&
+	    !(bio->bi_rw & REQ_DISCARD))
+		return true;
+
+	return false;
+}
+
+static inline bool bio_is_rw(struct bio *bio)
+{
+	if (!bio_has_data(bio))
+		return false;
+
+	if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
+		return false;
+
+	return true;
+}
+
+static inline bool bio_mergeable(struct bio *bio)
+{
+	if (bio->bi_rw & REQ_NOMERGE_FLAGS)
+		return false;
+
+	return true;
+}
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
-	if (bio->bi_vcnt)
-		return bio_iovec(bio)->bv_len;
+	if (bio_has_data(bio))
+		return bio_iovec(bio).bv_len;
 	else /* dataless requests such as discard */
-		return bio->bi_size;
+		return bio->bi_iter.bi_size;
 }
 
 static inline void *bio_data(struct bio *bio)
 {
-	if (bio->bi_vcnt)
+	if (bio_has_data(bio))
 		return page_address(bio_page(bio)) + bio_offset(bio);
 
 	return NULL;
@@ -97,19 +159,16 @@ static inline void *bio_data(struct bio *bio)
  * permanent PIO fall back, user is probably better off disabling highmem
  * I/O completely on that queue (see ide-dma for example)
  */
-#define __bio_kmap_atomic(bio, idx)				\
-	(kmap_atomic(bio_iovec_idx((bio), (idx))->bv_page) +	\
-		bio_iovec_idx((bio), (idx))->bv_offset)
+#define __bio_kmap_atomic(bio, iter)				\
+	(kmap_atomic(bio_iter_iovec((bio), (iter)).bv_page) +	\
+		bio_iter_iovec((bio), (iter)).bv_offset)
 
-#define __bio_kunmap_atomic(addr) kunmap_atomic(addr)
+#define __bio_kunmap_atomic(addr)	kunmap_atomic(addr)
 
 /*
  * merge helpers etc
  */
 
-#define __BVEC_END(bio)		bio_iovec_idx((bio), (bio)->bi_vcnt - 1)
-#define __BVEC_START(bio)	bio_iovec_idx((bio), (bio)->bi_idx)
-
 /* Default implementation of BIOVEC_PHYS_MERGEABLE */
 #define __BIOVEC_PHYS_MERGEABLE(vec1, vec2)	\
 	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
@@ -126,33 +185,76 @@ static inline void *bio_data(struct bio *bio)
 	(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
 	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
-#define BIO_SEG_BOUNDARY(q, b1, b2) \
-	BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2)))
 
 #define bio_io_error(bio) bio_endio((bio), -EIO)
 
 /*
- * 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++)
+	for (i = 0, bvl = (bio)->bi_io_vec; i < (bio)->bi_vcnt; i++, bvl++)
+
+static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
+				     unsigned bytes)
+{
+	WARN_ONCE(bytes > iter->bi_size,
+		  "Attempted to advance past end of bvec iter\n");
+
+	while (bytes) {
+		unsigned len = min(bytes, bvec_iter_len(bv, *iter));
+
+		bytes -= len;
+		iter->bi_size -= len;
+		iter->bi_bvec_done += len;
+
+		if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) {
+			iter->bi_bvec_done = 0;
+			iter->bi_idx++;
+		}
+	}
+}
+
+#define for_each_bvec(bvl, bio_vec, iter, start)			\
+	for ((iter) = start;						\
+	     (bvl) = bvec_iter_bvec((bio_vec), (iter)),			\
+		(iter).bi_size;						\
+	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
+
+
+static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
+				    unsigned bytes)
+{
+	iter->bi_sector += bytes >> 9;
+
+	if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
+		iter->bi_size -= bytes;
+	else
+		bvec_iter_advance(bio->bi_io_vec, iter, bytes);
+}
 
-#define bio_for_each_segment(bvl, bio, i)				\
-	for (i = (bio)->bi_idx;						\
-	     bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt;	\
-	     i++)
+#define __bio_for_each_segment(bvl, bio, iter, start)			\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = bio_iter_iovec((bio), (iter))), 1);		\
+	     bio_advance_iter((bio), &(iter), (bvl).bv_len))
+
+#define bio_for_each_segment(bvl, bio, iter)				\
+	__bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter)
+
+#define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len)
+
+static inline unsigned bio_segments(struct bio *bio)
+{
+	unsigned segs = 0;
+	struct bio_vec bv;
+	struct bvec_iter iter;
+
+	bio_for_each_segment(bv, bio, iter)
+		segs++;
+
+	return segs;
+}
 
 /*
  * get a reference to a bio, so it won't disappear. the intended use is
@@ -177,16 +279,15 @@ static inline void *bio_data(struct bio *bio)
 struct bio_integrity_payload {
 	struct bio		*bip_bio;	/* parent bio */
 
-	sector_t		bip_sector;	/* virtual start sector */
+	struct bvec_iter	bip_iter;
 
+	/* kill - should just use bip_vec */
 	void			*bip_buf;	/* generated integrity data */
-	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
 
-	unsigned int		bip_size;
+	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
 
 	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 */
@@ -196,29 +297,28 @@ struct bio_integrity_payload {
 };
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-/*
- * A bio_pair is used when we need to split a bio.
- * This can only happen for a bio that refers to just one
- * page of data, and in the unusual situation when the
- * page crosses a chunk/device boundary
+extern void bio_trim(struct bio *bio, int offset, int size);
+extern struct bio *bio_split(struct bio *bio, int sectors,
+			     gfp_t gfp, struct bio_set *bs);
+
+/**
+ * bio_next_split - get next @sectors from a bio, splitting if necessary
+ * @bio:	bio to split
+ * @sectors:	number of sectors to split from the front of @bio
+ * @gfp:	gfp mask
+ * @bs:		bio set to allocate from
  *
- * The address of the master bio is stored in bio1.bi_private
- * The address of the pool the pair was allocated from is stored
- *   in bio2.bi_private
+ * Returns a bio representing the next @sectors of @bio - if the bio is smaller
+ * than @sectors, returns the original bio unchanged.
  */
-struct bio_pair {
-	struct bio			bio1, bio2;
-	struct bio_vec			bv1, bv2;
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	struct bio_integrity_payload	bip1, bip2;
-	struct bio_vec			iv1, iv2;
-#endif
-	atomic_t			cnt;
-	int				error;
-};
-extern struct bio_pair *bio_split(struct bio *bi, int first_sectors);
-extern void bio_pair_release(struct bio_pair *dbio);
-extern void bio_trim(struct bio *bio, int offset, int size);
+static inline struct bio *bio_next_split(struct bio *bio, int sectors,
+					 gfp_t gfp, struct bio_set *bs)
+{
+	if (sectors >= bio_sectors(bio))
+		return bio;
+
+	return bio_split(bio, sectors, gfp, bs);
+}
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
@@ -227,7 +327,8 @@ 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_clone(struct bio *, struct bio *);
+extern void __bio_clone_fast(struct bio *, struct bio *);
+extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set *fs_bio_set;
@@ -254,6 +355,7 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
 }
 
 extern void bio_endio(struct bio *, int);
+extern void bio_endio_nodec(struct bio *, int);
 struct request_queue;
 extern int bio_phys_segments(struct request_queue *, struct bio *);
 
@@ -262,12 +364,12 @@ extern void bio_advance(struct bio *, unsigned);
 
 extern void bio_init(struct bio *);
 extern void bio_reset(struct bio *);
+void bio_chain(struct bio *, struct bio *);
 
 extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 extern int bio_get_nr_vecs(struct block_device *);
-extern sector_t bio_sector_offset(struct bio *, unsigned short, unsigned int);
 extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
 				unsigned long, unsigned int, int, gfp_t);
 struct sg_iovec;
@@ -357,48 +459,18 @@ static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
 }
 #endif
 
-static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
+static inline char *__bio_kmap_irq(struct bio *bio, struct bvec_iter iter,
 				   unsigned long *flags)
 {
-	return bvec_kmap_irq(bio_iovec_idx(bio, idx), flags);
+	return bvec_kmap_irq(&bio_iter_iovec(bio, iter), flags);
 }
 #define __bio_kunmap_irq(buf, flags)	bvec_kunmap_irq(buf, flags)
 
 #define bio_kmap_irq(bio, flags) \
-	__bio_kmap_irq((bio), (bio)->bi_idx, (flags))
+	__bio_kmap_irq((bio), (bio)->bi_iter, (flags))
 #define bio_kunmap_irq(buf,flags)	__bio_kunmap_irq(buf, flags)
 
 /*
- * Check whether this bio carries any data or not. A NULL bio is allowed.
- */
-static inline bool bio_has_data(struct bio *bio)
-{
-	if (bio && bio->bi_vcnt)
-		return true;
-
-	return false;
-}
-
-static inline bool bio_is_rw(struct bio *bio)
-{
-	if (!bio_has_data(bio))
-		return false;
-
-	if (bio->bi_rw & REQ_WRITE_SAME)
-		return false;
-
-	return true;
-}
-
-static inline bool bio_mergeable(struct bio *bio)
-{
-	if (bio->bi_rw & REQ_NOMERGE_FLAGS)
-		return false;
-
-	return true;
-}
-
-/*
  * BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
  *
  * A bio_list anchors a singly-linked list of bios chained through the bi_next
@@ -559,16 +631,12 @@ struct biovec_slab {
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
-#define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
-#define bip_vec(bip)		bip_vec_idx(bip, 0)
 
-#define __bip_for_each_vec(bvl, bip, i, start_idx)			\
-	for (bvl = bip_vec_idx((bip), (start_idx)), i = (start_idx);	\
-	     i < (bip)->bip_vcnt;					\
-	     bvl++, i++)
 
-#define bip_for_each_vec(bvl, bip, i)					\
-	__bip_for_each_vec(bvl, bip, i, (bip)->bip_idx)
+#define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
+
+#define bip_for_each_vec(bvl, bip, iter)				\
+	for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
 
 #define bio_for_each_integrity_vec(_bvl, _bio, _iter)			\
 	for_each_bio(_bio)						\
@@ -586,7 +654,6 @@ extern int bio_integrity_prep(struct bio *);
 extern void bio_integrity_endio(struct bio *, int);
 extern void bio_integrity_advance(struct bio *, unsigned int);
 extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
-extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
 extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
 extern int bioset_integrity_create(struct bio_set *, int);
 extern void bioset_integrity_free(struct bio_set *);
@@ -630,12 +697,6 @@ static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 	return 0;
 }
 
-static inline void bio_integrity_split(struct bio *bio, struct bio_pair *bp,
-				       int sectors)
-{
-	return;
-}
-
 static inline void bio_integrity_advance(struct bio *bio,
 					 unsigned int bytes_done)
 {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ab0e9b2025b3..1a14f29c6fb5 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -36,12 +36,15 @@ struct blk_mq_hw_ctx {
 	struct list_head	page_list;
 	struct blk_mq_tags	*tags;
 
+	atomic_t		pending_flush;
+
 	unsigned long		queued;
 	unsigned long		run;
 #define BLK_MQ_MAX_DISPATCH_ORDER	10
 	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
 
 	unsigned int		queue_depth;
+	unsigned int		reserved_tags;
 	unsigned int		numa_node;
 	unsigned int		cmd_size;	/* per-request extra data */
 
@@ -113,7 +116,6 @@ enum {
 };
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_reg *, void *);
-void blk_mq_free_queue(struct request_queue *);
 int blk_mq_register_disk(struct gendisk *);
 void blk_mq_unregister_disk(struct gendisk *);
 void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struct blk_mq_hw_ctx *, struct request *, unsigned int), void *data);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 238ef0ed62f8..bbc3a6c88fce 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -28,13 +28,22 @@ struct bio_vec {
 	unsigned int	bv_offset;
 };
 
+struct bvec_iter {
+	sector_t		bi_sector;	/* device address in 512 byte
+						   sectors */
+	unsigned int		bi_size;	/* residual I/O count */
+
+	unsigned int		bi_idx;		/* current index into bvl_vec */
+
+	unsigned int            bi_bvec_done;	/* number of bytes completed in
+						   current bvec */
+};
+
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
  * stacking drivers)
  */
 struct bio {
-	sector_t		bi_sector;	/* device address in 512 byte
-						   sectors */
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
 	unsigned long		bi_flags;	/* status, command, etc */
@@ -42,16 +51,13 @@ struct bio {
 						 * top bits priority
 						 */
 
-	unsigned short		bi_vcnt;	/* how many bio_vec's */
-	unsigned short		bi_idx;		/* current index into bvl_vec */
+	struct bvec_iter	bi_iter;
 
 	/* Number of segments in this BIO after
 	 * physical address coalescing is performed.
 	 */
 	unsigned int		bi_phys_segments;
 
-	unsigned int		bi_size;	/* residual I/O count */
-
 	/*
 	 * To keep track of the max segment size, we account for the
 	 * sizes of the first and last mergeable segments in this bio.
@@ -59,6 +65,8 @@ struct bio {
 	unsigned int		bi_seg_front_size;
 	unsigned int		bi_seg_back_size;
 
+	atomic_t		bi_remaining;
+
 	bio_end_io_t		*bi_end_io;
 
 	void			*bi_private;
@@ -74,11 +82,13 @@ struct bio {
 	struct bio_integrity_payload *bi_integrity;  /* data integrity */
 #endif
 
+	unsigned short		bi_vcnt;	/* how many bio_vec's */
+
 	/*
 	 * Everything starting with bi_max_vecs will be preserved by bio_reset()
 	 */
 
-	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */
+	unsigned short		bi_max_vecs;	/* max bvl_vecs we can hold */
 
 	atomic_t		bi_cnt;		/* pin count */
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1b135d49b279..0375654adb28 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -291,6 +291,7 @@ struct queue_limits {
 	unsigned char		discard_misaligned;
 	unsigned char		cluster;
 	unsigned char		discard_zeroes_data;
+	unsigned char		raid_partial_stripes_expensive;
 };
 
 struct request_queue {
@@ -735,7 +736,7 @@ struct rq_map_data {
 };
 
 struct req_iterator {
-	int i;
+	struct bvec_iter iter;
 	struct bio *bio;
 };
 
@@ -748,10 +749,11 @@ struct req_iterator {
 
 #define rq_for_each_segment(bvl, _rq, _iter)			\
 	__rq_for_each_bio(_iter.bio, _rq)			\
-		bio_for_each_segment(bvl, _iter.bio, _iter.i)
+		bio_for_each_segment(bvl, _iter.bio, _iter.iter)
 
-#define rq_iter_last(rq, _iter)					\
-		(_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1)
+#define rq_iter_last(bvec, _iter)				\
+		(_iter.bio->bi_next == NULL &&			\
+		 bio_iter_last(bvec, _iter.iter))
 
 #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 # error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 7c1420bb1dce..091fdb600d55 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -1,6 +1,7 @@
 #ifndef __FS_CEPH_MESSENGER_H
 #define __FS_CEPH_MESSENGER_H
 
+#include <linux/blk_types.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
 #include <linux/net.h>
@@ -119,8 +120,7 @@ struct ceph_msg_data_cursor {
 #ifdef CONFIG_BLOCK
 		struct {				/* bio */
 			struct bio	*bio;		/* bio from list */
-			unsigned int	vector_index;	/* vector from bio */
-			unsigned int	vector_offset;	/* bytes from vector */
+			struct bvec_iter bvec_iter;
 		};
 #endif /* CONFIG_BLOCK */
 		struct {				/* pages */
diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h
index f4b0aa3126f5..a68cbe59e6ad 100644
--- a/include/linux/dm-io.h
+++ b/include/linux/dm-io.h
@@ -29,7 +29,7 @@ typedef void (*io_notify_fn)(unsigned long error, void *context);
 
 enum dm_io_mem_type {
 	DM_IO_PAGE_LIST,/* Page list */
-	DM_IO_BVEC,	/* Bio vector */
+	DM_IO_BIO,	/* Bio vector */
 	DM_IO_VMA,	/* Virtual memory area */
 	DM_IO_KMEM,	/* Kernel memory */
 };
@@ -41,7 +41,7 @@ struct dm_io_memory {
 
 	union {
 		struct page_list *pl;
-		struct bio_vec *bvec;
+		struct bio *bio;
 		void *vma;
 		void *addr;
 	} ptr;
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index e2b9576d00e2..7110897c3dfa 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -24,10 +24,10 @@ DECLARE_EVENT_CLASS(bcache_request,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->orig_major	= d->disk->major;
 		__entry->orig_minor	= d->disk->first_minor;
-		__entry->sector		= bio->bi_sector;
-		__entry->orig_sector	= bio->bi_sector - 16;
-		__entry->nr_sector	= bio->bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->orig_sector	= bio->bi_iter.bi_sector - 16;
+		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u (from %d,%d @ %llu)",
@@ -99,9 +99,9 @@ DECLARE_EVENT_CLASS(bcache_bio,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d  %s %llu + %u",
@@ -134,9 +134,9 @@ TRACE_EVENT(bcache_read,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 		__entry->cache_hit = hit;
 		__entry->bypass = bypass;
 	),
@@ -162,9 +162,9 @@ TRACE_EVENT(bcache_write,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
-		__entry->nr_sector	= bio->bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 		__entry->writeback = writeback;
 		__entry->bypass = bypass;
 	),
@@ -247,7 +247,7 @@ TRACE_EVENT(bcache_btree_write,
 	TP_fast_assign(
 		__entry->bucket	= PTR_BUCKET_NR(b->c, &b->key, 0);
 		__entry->block	= b->written;
-		__entry->keys	= b->sets[b->nsets].data->keys;
+		__entry->keys	= b->keys.set[b->keys.nsets].data->keys;
 	),
 
 	TP_printk("bucket %zu", __entry->bucket)
@@ -411,7 +411,7 @@ TRACE_EVENT(bcache_alloc_invalidate,
 	),
 
 	TP_fast_assign(
-		__entry->free		= fifo_used(&ca->free);
+		__entry->free		= fifo_used(&ca->free[RESERVE_NONE]);
 		__entry->free_inc	= fifo_used(&ca->free_inc);
 		__entry->free_inc_size	= ca->free_inc.size;
 		__entry->unused		= fifo_used(&ca->unused);
@@ -422,8 +422,8 @@ TRACE_EVENT(bcache_alloc_invalidate,
 );
 
 TRACE_EVENT(bcache_alloc_fail,
-	TP_PROTO(struct cache *ca),
-	TP_ARGS(ca),
+	TP_PROTO(struct cache *ca, unsigned reserve),
+	TP_ARGS(ca, reserve),
 
 	TP_STRUCT__entry(
 		__field(unsigned,	free			)
@@ -433,7 +433,7 @@ TRACE_EVENT(bcache_alloc_fail,
 	),
 
 	TP_fast_assign(
-		__entry->free		= fifo_used(&ca->free);
+		__entry->free		= fifo_used(&ca->free[reserve]);
 		__entry->free_inc	= fifo_used(&ca->free_inc);
 		__entry->unused		= fifo_used(&ca->unused);
 		__entry->blocked	= atomic_read(&ca->set->prio_blocked);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 4c2301d2ef1a..e76ae19a8d6f 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -243,9 +243,9 @@ TRACE_EVENT(block_bio_bounce,
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev ?
 					  bio->bi_bdev->bd_dev : 0;
-		__entry->sector		= bio->bi_sector;
+		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -280,10 +280,10 @@ TRACE_EVENT(block_bio_complete,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
+		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->error		= error;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u [%d]",
@@ -308,9 +308,9 @@ DECLARE_EVENT_CLASS(block_bio_merge,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
+		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -375,9 +375,9 @@ TRACE_EVENT(block_bio_queue,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
+		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -403,7 +403,7 @@ DECLARE_EVENT_CLASS(block_get_rq,
 
 	TP_fast_assign(
 		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
-		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->sector		= bio ? bio->bi_iter.bi_sector : 0;
 		__entry->nr_sector	= bio ? bio_sectors(bio) : 0;
 		blk_fill_rwbs(__entry->rwbs,
 			      bio ? bio->bi_rw : 0, __entry->nr_sector);
@@ -538,9 +538,9 @@ TRACE_EVENT(block_split,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
+		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->new_sector	= new_sector;
-		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
@@ -579,11 +579,11 @@ TRACE_EVENT(block_bio_remap,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->sector		= bio->bi_sector;
+		__entry->sector		= bio->bi_iter.bi_sector;
 		__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);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 3b9f28dfc849..67f38faac589 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -629,8 +629,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 		__entry->dev		= sb->s_dev;
 		__entry->rw		= rw;
 		__entry->type		= type;
-		__entry->sector		= bio->bi_sector;
-		__entry->size		= bio->bi_size;
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->size		= bio->bi_iter.bi_size;
 	),
 
 	TP_printk("dev = (%d,%d), %s%s, %s, sector = %lld, size = %u",
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 164a7e263988..22b6ad31c706 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -39,6 +39,7 @@ static inline void SET_##name(struct bkey *k, unsigned i, __u64 v)	\
 }
 
 #define KEY_SIZE_BITS		16
+#define KEY_MAX_U64S		8
 
 KEY_FIELD(KEY_PTRS,	high, 60, 3)
 KEY_FIELD(HEADER_SIZE,	high, 58, 2)
@@ -118,7 +119,7 @@ static inline struct bkey *bkey_next(const struct bkey *k)
 	return (struct bkey *) (d + bkey_u64s(k));
 }
 
-static inline struct bkey *bkey_last(const struct bkey *k, unsigned nr_keys)
+static inline struct bkey *bkey_idx(const struct bkey *k, unsigned nr_keys)
 {
 	__u64 *d = (void *) k;
 	return (struct bkey *) (d + nr_keys);