Merge tag 'iomap-5.5-merge-11' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "In this release, we hoisted as much of XFS' writeback code into iomap
  as was practicable, refactored the unshare file data function, added
  the ability to perform buffered io copy on write, and tweaked various
  parts of the directio implementation as needed to port ext4's directio
  code (that will be a separate pull).

  Summary:

   - Make iomap_dio_rw callers explicitly tell us if they want us to
     wait

   - Port the xfs writeback code to iomap to complete the buffered io
     library functions

   - Refactor the unshare code to share common pieces

   - Add support for performing copy on write with buffered writes

   - Other minor fixes

   - Fix unchecked return in iomap_bmap

   - Fix a type casting bug in a ternary statement in
     iomap_dio_bio_actor

   - Improve tracepoints for easier diagnostic ability

   - Fix pipe page leakage in directio reads"

* tag 'iomap-5.5-merge-11' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (31 commits)
  iomap: Fix pipe page leakage during splicing
  iomap: trace iomap_appply results
  iomap: fix return value of iomap_dio_bio_actor on 32bit systems
  iomap: iomap_bmap should check iomap_apply return value
  iomap: Fix overflow in iomap_page_mkwrite
  fs/iomap: remove redundant check in iomap_dio_rw()
  iomap: use a srcmap for a read-modify-write I/O
  iomap: renumber IOMAP_HOLE to 0
  iomap: use write_begin to read pages to unshare
  iomap: move the zeroing case out of iomap_read_page_sync
  iomap: ignore non-shared or non-data blocks in xfs_file_dirty
  iomap: always use AOP_FLAG_NOFS in iomap_write_begin
  iomap: remove the unused iomap argument to __iomap_write_end
  iomap: better document the IOMAP_F_* flags
  iomap: enhance writeback error message
  iomap: pass a struct page to iomap_finish_page_writeback
  iomap: cleanup iomap_ioend_compare
  iomap: move struct iomap_page out of iomap.h
  iomap: warn on inline maps in iomap_writepage_map
  iomap: lift the xfs writeback code to iomap
  ...

11 files changed, 172 insertions, 762 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 02469d59c787..ef75e223cb70 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -34,6 +34,7 @@
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
 #include "xfs_icache.h"
+#include "xfs_iomap.h"
 
 
 kmem_zone_t		*xfs_bmap_free_item_zone;
@@ -4456,16 +4457,21 @@ int
 xfs_bmapi_convert_delalloc(
 	struct xfs_inode	*ip,
 	int			whichfork,
-	xfs_fileoff_t		offset_fsb,
-	struct xfs_bmbt_irec	*imap,
+	xfs_off_t		offset,
+	struct iomap		*iomap,
 	unsigned int		*seq)
 {
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	struct xfs_bmalloca	bma = { NULL };
+	u16			flags = 0;
 	struct xfs_trans	*tp;
 	int			error;
 
+	if (whichfork == XFS_COW_FORK)
+		flags |= IOMAP_F_SHARED;
+
 	/*
 	 * Space for the extent and indirect blocks was reserved when the
 	 * delalloc extent was created so there's no need to do so here.
@@ -4495,7 +4501,7 @@ xfs_bmapi_convert_delalloc(
 	 * the extent.  Just return the real extent at this offset.
 	 */
 	if (!isnullstartblock(bma.got.br_startblock)) {
-		*imap = bma.got;
+		xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
 		*seq = READ_ONCE(ifp->if_seq);
 		goto out_trans_cancel;
 	}
@@ -4528,7 +4534,7 @@ xfs_bmapi_convert_delalloc(
 	XFS_STATS_INC(mp, xs_xstrat_quick);
 
 	ASSERT(!isnullstartblock(bma.got.br_startblock));
-	*imap = bma.got;
+	xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
 	*seq = READ_ONCE(ifp->if_seq);
 
 	if (whichfork == XFS_COW_FORK)
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e2798c6f3a5f..14d25e0b7d9c 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -228,8 +228,7 @@ int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
 		int eof);
 int	xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork,
-		xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap,
-		unsigned int *seq);
+		xfs_off_t offset, struct iomap *iomap, unsigned int *seq);
 int	xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp,
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f16d5f196c6b..5936507c6f50 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -18,17 +18,18 @@
 #include "xfs_bmap_util.h"
 #include "xfs_reflink.h"
 
-/*
- * structure owned by writepages passed to individual writepage calls
- */
 struct xfs_writepage_ctx {
-	struct xfs_bmbt_irec    imap;
-	int			fork;
+	struct iomap_writepage_ctx ctx;
 	unsigned int		data_seq;
 	unsigned int		cow_seq;
-	struct xfs_ioend	*ioend;
 };
 
+static inline struct xfs_writepage_ctx *
+XFS_WPC(struct iomap_writepage_ctx *ctx)
+{
+	return container_of(ctx, struct xfs_writepage_ctx, ctx);
+}
+
 struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
@@ -55,71 +56,10 @@ xfs_find_daxdev_for_inode(
 		return mp->m_ddev_targp->bt_daxdev;
 }
 
-static void
-xfs_finish_page_writeback(
-	struct inode		*inode,
-	struct bio_vec	*bvec,
-	int			error)
-{
-	struct iomap_page	*iop = to_iomap_page(bvec->bv_page);
-
-	if (error) {
-		SetPageError(bvec->bv_page);
-		mapping_set_error(inode->i_mapping, -EIO);
-	}
-
-	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
-	ASSERT(!iop || atomic_read(&iop->write_count) > 0);
-
-	if (!iop || atomic_dec_and_test(&iop->write_count))
-		end_page_writeback(bvec->bv_page);
-}
-
-/*
- * We're now finished for good with this ioend structure.  Update the page
- * state, release holds on bios, and finally free up memory.  Do not use the
- * ioend after this.
- */
-STATIC void
-xfs_destroy_ioend(
-	struct xfs_ioend	*ioend,
-	int			error)
-{
-	struct inode		*inode = ioend->io_inode;
-	struct bio		*bio = &ioend->io_inline_bio;
-	struct bio		*last = ioend->io_bio, *next;
-	u64			start = bio->bi_iter.bi_sector;
-	bool			quiet = bio_flagged(bio, BIO_QUIET);
-
-	for (bio = &ioend->io_inline_bio; bio; bio = next) {
-		struct bio_vec	*bvec;
-		struct bvec_iter_all iter_all;
-
-		/*
-		 * For the last bio, bi_private points to the ioend, so we
-		 * need to explicitly end the iteration here.
-		 */
-		if (bio == last)
-			next = NULL;
-		else
-			next = bio->bi_private;
-
-		/* walk each page on bio, ending page IO on them */
-		bio_for_each_segment_all(bvec, bio, iter_all)
-			xfs_finish_page_writeback(inode, bvec, error);
-		bio_put(bio);
-	}
-
-	if (unlikely(error && !quiet)) {
-		xfs_err_ratelimited(XFS_I(inode)->i_mount,
-			"writeback error on sector %llu", start);
-	}
-}
-
 /*
  * Fast and loose check if this write could update the on-disk inode size.
  */
-static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend)
+static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend)
 {
 	return ioend->io_offset + ioend->io_size >
 		XFS_I(ioend->io_inode)->i_d.di_size;
@@ -127,7 +67,7 @@ static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend)
 
 STATIC int
 xfs_setfilesize_trans_alloc(
-	struct xfs_ioend	*ioend)
+	struct iomap_ioend	*ioend)
 {
 	struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
 	struct xfs_trans	*tp;
@@ -137,7 +77,7 @@ xfs_setfilesize_trans_alloc(
 	if (error)
 		return error;
 
-	ioend->io_append_trans = tp;
+	ioend->io_private = tp;
 
 	/*
 	 * We may pass freeze protection with a transaction.  So tell lockdep
@@ -200,11 +140,11 @@ xfs_setfilesize(
 
 STATIC int
 xfs_setfilesize_ioend(
-	struct xfs_ioend	*ioend,
+	struct iomap_ioend	*ioend,
 	int			error)
 {
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	struct xfs_trans	*tp = ioend->io_append_trans;
+	struct xfs_trans	*tp = ioend->io_private;
 
 	/*
 	 * The transaction may have been allocated in the I/O submission thread,
@@ -228,9 +168,8 @@ xfs_setfilesize_ioend(
  */
 STATIC void
 xfs_end_ioend(
-	struct xfs_ioend	*ioend)
+	struct iomap_ioend	*ioend)
 {
-	struct list_head	ioend_list;
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	xfs_off_t		offset = ioend->io_offset;
 	size_t			size = ioend->io_size;
@@ -257,7 +196,7 @@ xfs_end_ioend(
 	 */
 	error = blk_status_to_errno(ioend->io_bio->bi_status);
 	if (unlikely(error)) {
-		if (ioend->io_fork == XFS_COW_FORK)
+		if (ioend->io_flags & IOMAP_F_SHARED)
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
 		goto done;
 	}
@@ -265,154 +204,86 @@ xfs_end_ioend(
 	/*
 	 * Success: commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_fork == XFS_COW_FORK)
+	if (ioend->io_flags & IOMAP_F_SHARED)
 		error = xfs_reflink_end_cow(ip, offset, size);
-	else if (ioend->io_state == XFS_EXT_UNWRITTEN)
+	else if (ioend->io_type == IOMAP_UNWRITTEN)
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
 	else
-		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_private);
 
 done:
-	if (ioend->io_append_trans)
+	if (ioend->io_private)
 		error = xfs_setfilesize_ioend(ioend, error);
-	list_replace_init(&ioend->io_list, &ioend_list);
-	xfs_destroy_ioend(ioend, error);
-
-	while (!list_empty(&ioend_list)) {
-		ioend = list_first_entry(&ioend_list, struct xfs_ioend,
-				io_list);
-		list_del_init(&ioend->io_list);
-		xfs_destroy_ioend(ioend, error);
-	}
-
+	iomap_finish_ioends(ioend, error);
 	memalloc_nofs_restore(nofs_flag);
 }
 
 /*
- * We can merge two adjacent ioends if they have the same set of work to do.
- */
-static bool
-xfs_ioend_can_merge(
-	struct xfs_ioend	*ioend,
-	struct xfs_ioend	*next)
-{
-	if (ioend->io_bio->bi_status != next->io_bio->bi_status)
-		return false;
-	if ((ioend->io_fork == XFS_COW_FORK) ^ (next->io_fork == XFS_COW_FORK))
-		return false;
-	if ((ioend->io_state == XFS_EXT_UNWRITTEN) ^
-	    (next->io_state == XFS_EXT_UNWRITTEN))
-		return false;
-	if (ioend->io_offset + ioend->io_size != next->io_offset)
-		return false;
-	return true;
-}
-
-/*
  * If the to be merged ioend has a preallocated transaction for file
  * size updates we need to ensure the ioend it is merged into also
  * has one.  If it already has one we can simply cancel the transaction
  * as it is guaranteed to be clean.
  */
 static void
-xfs_ioend_merge_append_transactions(
-	struct xfs_ioend	*ioend,
-	struct xfs_ioend	*next)
+xfs_ioend_merge_private(
+	struct iomap_ioend	*ioend,
+	struct iomap_ioend	*next)
 {
-	if (!ioend->io_append_trans) {
-		ioend->io_append_trans = next->io_append_trans;
-		next->io_append_trans = NULL;
+	if (!ioend->io_private) {
+		ioend->io_private = next->io_private;
+		next->io_private = NULL;
 	} else {
 		xfs_setfilesize_ioend(next, -ECANCELED);
 	}
 }
 
-/* Try to merge adjacent completions. */
-STATIC void
-xfs_ioend_try_merge(
-	struct xfs_ioend	*ioend,
-	struct list_head	*more_ioends)
-{
-	struct xfs_ioend	*next_ioend;
-
-	while (!list_empty(more_ioends)) {
-		next_ioend = list_first_entry(more_ioends, struct xfs_ioend,
-				io_list);
-		if (!xfs_ioend_can_merge(ioend, next_ioend))
-			break;
-		list_move_tail(&next_ioend->io_list, &ioend->io_list);
-		ioend->io_size += next_ioend->io_size;
-		if (next_ioend->io_append_trans)
-			xfs_ioend_merge_append_transactions(ioend, next_ioend);
-	}
-}
-
-/* list_sort compare function for ioends */
-static int
-xfs_ioend_compare(
-	void			*priv,
-	struct list_head	*a,
-	struct list_head	*b)
-{
-	struct xfs_ioend	*ia;
-	struct xfs_ioend	*ib;
-
-	ia = container_of(a, struct xfs_ioend, io_list);
-	ib = container_of(b, struct xfs_ioend, io_list);
-	if (ia->io_offset < ib->io_offset)
-		return -1;
-	else if (ia->io_offset > ib->io_offset)
-		return 1;
-	return 0;
-}
-
 /* Finish all pending io completions. */
 void
 xfs_end_io(
 	struct work_struct	*work)
 {
-	struct xfs_inode	*ip;
-	struct xfs_ioend	*ioend;
-	struct list_head	completion_list;
+	struct xfs_inode	*ip =
+		container_of(work, struct xfs_inode, i_ioend_work);
+	struct iomap_ioend	*ioend;
+	struct list_head	tmp;
 	unsigned long		flags;
 
-	ip = container_of(work, struct xfs_inode, i_ioend_work);
-
 	spin_lock_irqsave(&ip->i_ioend_lock, flags);
-	list_replace_init(&ip->i_ioend_list, &completion_list);
+	list_replace_init(&ip->i_ioend_list, &tmp);
 	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
 
-	list_sort(NULL, &completion_list, xfs_ioend_compare);
-
-	while (!list_empty(&completion_list)) {
-		ioend = list_first_entry(&completion_list, struct xfs_ioend,
-				io_list);
+	iomap_sort_ioends(&tmp);
+	while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
+			io_list))) {
 		list_del_init(&ioend->io_list);
-		xfs_ioend_try_merge(ioend, &completion_list);
+		iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private);
 		xfs_end_ioend(ioend);
 	}
 }
 
+static inline bool xfs_ioend_needs_workqueue(struct iomap_ioend *ioend)
+{
+	return ioend->io_private ||
+		ioend->io_type == IOMAP_UNWRITTEN ||
+		(ioend->io_flags & IOMAP_F_SHARED);
+}
+
 STATIC void
 xfs_end_bio(
 	struct bio		*bio)
 {
-	struct xfs_ioend	*ioend = bio->bi_private;
+	struct iomap_ioend	*ioend = bio->bi_private;
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	struct xfs_mount	*mp = ip->i_mount;
 	unsigned long		flags;
 
-	if (ioend->io_fork == XFS_COW_FORK ||
-	    ioend->io_state == XFS_EXT_UNWRITTEN ||
-	    ioend->io_append_trans != NULL) {
-		spin_lock_irqsave(&ip->i_ioend_lock, flags);
-		if (list_empty(&ip->i_ioend_list))
-			WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
-						 &ip->i_ioend_work));
-		list_add_tail(&ioend->io_list, &ip->i_ioend_list);
-		spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
-	} else
-		xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status));
+	ASSERT(xfs_ioend_needs_workqueue(ioend));
+
+	spin_lock_irqsave(&ip->i_ioend_lock, flags);
+	if (list_empty(&ip->i_ioend_list))
+		WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue,
+					 &ip->i_ioend_work));
+	list_add_tail(&ioend->io_list, &ip->i_ioend_list);
+	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
 }
 
 /*
@@ -421,19 +292,19 @@ xfs_end_bio(
  */
 static bool
 xfs_imap_valid(
-	struct xfs_writepage_ctx	*wpc,
+	struct iomap_writepage_ctx	*wpc,
 	struct xfs_inode		*ip,
-	xfs_fileoff_t			offset_fsb)
+	loff_t				offset)
 {
-	if (offset_fsb < wpc->imap.br_startoff ||
-	    offset_fsb >= wpc->imap.br_startoff + wpc->imap.br_blockcount)
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length)
 		return false;
 	/*
 	 * If this is a COW mapping, it is sufficient to check that the mapping
 	 * covers the offset. Be careful to check this first because the caller
 	 * can revalidate a COW mapping without updating the data seqno.
 	 */
-	if (wpc->fork == XFS_COW_FORK)
+	if (wpc->iomap.flags & IOMAP_F_SHARED)
 		return true;
 
 	/*
@@ -443,17 +314,17 @@ xfs_imap_valid(
 	 * checked (and found nothing at this offset) could have added
 	 * overlapping blocks.
 	 */
-	if (wpc->data_seq != READ_ONCE(ip->i_df.if_seq))
+	if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq))
 		return false;
 	if (xfs_inode_has_cow_data(ip) &&
-	    wpc->cow_seq != READ_ONCE(ip->i_cowfp->if_seq))
+	    XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq))
 		return false;
 	return true;
 }
 
 /*
  * Pass in a dellalloc extent and convert it to real extents, return the real
- * extent that maps offset_fsb in wpc->imap.
+ * extent that maps offset_fsb in wpc->iomap.
  *
  * The current page is held locked so nothing could have removed the block
  * backing offset_fsb, although it could have moved from the COW to the data
@@ -461,32 +332,38 @@ xfs_imap_valid(
  */
 static int
 xfs_convert_blocks(
-	struct xfs_writepage_ctx *wpc,
+	struct iomap_writepage_ctx *wpc,
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		offset_fsb)
+	int			whichfork,
+	loff_t			offset)
 {
 	int			error;
+	unsigned		*seq;
+
+	if (whichfork == XFS_COW_FORK)
+		seq = &XFS_WPC(wpc)->cow_seq;
+	else
+		seq = &XFS_WPC(wpc)->data_seq;
 
 	/*
-	 * Attempt to allocate whatever delalloc extent currently backs
-	 * offset_fsb and put the result into wpc->imap.  Allocate in a loop
-	 * because it may take several attempts to allocate real blocks for a
-	 * contiguous delalloc extent if free space is sufficiently fragmented.
+	 * Attempt to allocate whatever delalloc extent currently backs offset
+	 * and put the result into wpc->iomap.  Allocate in a loop because it
+	 * may take several attempts to allocate real blocks for a contiguous
+	 * delalloc extent if free space is sufficiently fragmented.
 	 */
 	do {
-		error = xfs_bmapi_convert_delalloc(ip, wpc->fork, offset_fsb,
-				&wpc->imap, wpc->fork == XFS_COW_FORK ?
-					&wpc->cow_seq : &wpc->data_seq);
+		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
+				&wpc->iomap, seq);
 		if (error)
 			return error;
-	} while (wpc->imap.br_startoff + wpc->imap.br_blockcount <= offset_fsb);
+	} while (wpc->iomap.offset + wpc->iomap.length <= offset);
 
 	return 0;
 }
 
-STATIC int
+static int
 xfs_map_blocks(
-	struct xfs_writepage_ctx *wpc,
+	struct iomap_writepage_ctx *wpc,
 	struct inode		*inode,
 	loff_t			offset)
 {
@@ -496,6 +373,7 @@ xfs_map_blocks(
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_fileoff_t		cow_fsb = NULLFILEOFF;
+	int			whichfork = XFS_DATA_FORK;
 	struct xfs_bmbt_irec	imap;
 	struct xfs_iext_cursor	icur;
 	int			retries = 0;
@@ -519,7 +397,7 @@ xfs_map_blocks(
 	 * against concurrent updates and provides a memory barrier on the way
 	 * out that ensures that we always see the current value.
 	 */
-	if (xfs_imap_valid(wpc, ip, offset_fsb))
+	if (xfs_imap_valid(wpc, ip, offset))
 		return 0;
 
 	/*
@@ -541,10 +419,10 @@ retry:
 	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
 		cow_fsb = imap.br_startoff;
 	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
-		wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
+		XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-		wpc->fork = XFS_COW_FORK;
+		whichfork = XFS_COW_FORK;
 		goto allocate_blocks;
 	}
 
@@ -552,7 +430,7 @@ retry:
 	 * No COW extent overlap. Revalidate now that we may have updated
 	 * ->cow_seq. If the data mapping is still valid, we're done.
 	 */
-	if (xfs_imap_valid(wpc, ip, offset_fsb)) {
+	if (xfs_imap_valid(wpc, ip, offset)) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		return 0;
 	}
@@ -564,11 +442,9 @@ retry:
 	 */
 	if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
 		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
-	wpc->data_seq = READ_ONCE(ip->i_df.if_seq);
+	XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-	wpc->fork = XFS_DATA_FORK;
-
 	/* landed in a hole or beyond EOF? */
 	if (imap.br_startoff > offset_fsb) {
 		imap.br_blockcount = imap.br_startoff - offset_fsb;
@@ -592,11 +468,11 @@ retry:
 	    isnullstartblock(imap.br_startblock))
 		goto allocate_blocks;
 
-	wpc->imap = imap;
-	trace_xfs_map_blocks_found(ip, offset, count, wpc->fork, &imap);
+	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
+	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_convert_blocks(wpc, ip, offset_fsb);
+	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
 	if (error) {
 		/*
 		 * If we failed to find the extent in the COW fork we might have
@@ -605,7 +481,7 @@ allocate_blocks:
 		 * the former case, but prevent additional retries to avoid
 		 * looping forever for the latter case.
 		 */
-		if (error == -EAGAIN && wpc->fork == XFS_COW_FORK && !retries++)
+		if (error == -EAGAIN && whichfork == XFS_COW_FORK && !retries++)
 			goto retry;
 		ASSERT(error != -EAGAIN);
 		return error;
@@ -616,34 +492,22 @@ allocate_blocks:
 	 * original delalloc one.  Trim the return extent to the next COW
 	 * boundary again to force a re-lookup.
 	 */
-	if (wpc->fork != XFS_COW_FORK && cow_fsb != NULLFILEOFF &&
-	    cow_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount)
-		wpc->imap.br_blockcount = cow_fsb - wpc->imap.br_startoff;
+	if (whichfork != XFS_COW_FORK && cow_fsb != NULLFILEOFF) {
+		loff_t		cow_offset = XFS_FSB_TO_B(mp, cow_fsb);
+
+		if (cow_offset < wpc->iomap.offset + wpc->iomap.length)
+			wpc->iomap.length = cow_offset - wpc->iomap.offset;
+	}
 
-	ASSERT(wpc->imap.br_startoff <= offset_fsb);
-	ASSERT(wpc->imap.br_startoff + wpc->imap.br_blockcount > offset_fsb);
-	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->fork, &imap);
+	ASSERT(wpc->iomap.offset <= offset);
+	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
+	trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap);
 	return 0;
 }
 
-/*
- * Submit the bio for an ioend. We are passed an ioend with a bio attached to
- * it, and we submit that bio. The ioend may be used for multiple bio
- * submissions, so we only want to allocate an append transaction for the ioend
- * once. In the case of multiple bio submission, each bio will take an IO
- * reference to the ioend to ensure that the ioend completion is only done once
- * all bios have been submitted and the ioend is really done.
- *
- * If @status is non-zero, it means that we have a situation where some part of
- * the submission process has failed after we have marked paged for writeback
- * and unlocked them. In this situation, we need to fail the bio and ioend
- * rather than submit it to IO. This typically only happens on a filesystem
- * shutdown.
- */
-STATIC int
-xfs_submit_ioend(
-	struct writeback_control *wbc,
-	struct xfs_ioend	*ioend,
+static int
+xfs_prepare_ioend(
+	struct iomap_ioend	*ioend,
 	int			status)
 {
 	unsigned int		nofs_flag;
@@ -656,157 +520,24 @@ xfs_submit_ioend(
 	nofs_flag = memalloc_nofs_save();
 
 	/* Convert CoW extents to regular */
-	if (!status && ioend->io_fork == XFS_COW_FORK) {
+	if (!status && (ioend->io_flags & IOMAP_F_SHARED)) {
 		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
 				ioend->io_offset, ioend->io_size);
 	}
 
 	/* Reserve log space if we might write beyond the on-disk inode size. */
 	if (!status &&
-	    (ioend->io_fork == XFS_COW_FORK ||
-	     ioend->io_state != XFS_EXT_UNWRITTEN) &&
+	    ((ioend->io_flags & IOMAP_F_SHARED) ||
+	     ioend->io_type != IOMAP_UNWRITTEN) &&
 	    xfs_ioend_is_append(ioend) &&
-	    !ioend->io_append_trans)
+	    !ioend->io_private)
 		status = xfs_setfilesize_trans_alloc(ioend);
 
 	memalloc_nofs_restore(nofs_flag);
 
-	ioend->io_bio->bi_private = ioend;
-	ioend->io_bio->bi_end_io = xfs_end_bio;
-
-	/*
-	 * If we are failing the IO now, just mark the ioend with an
-	 * error and finish it. This will run IO completion immediately
-	 * as there is only one reference to the ioend at this point in
-	 * time.
-	 */
-	if (status) {
-		ioend->io_bio->bi_status = errno_to_blk_status(status);
-		bio_endio(ioend->io_bio);
-		return status;
-	}
-
-	submit_bio(ioend->io_bio);
-	return 0;
-}
-
-static struct xfs_ioend *
-xfs_alloc_ioend(
-	struct inode		*inode,
-	int			fork,
-	xfs_exntst_t		state,
-	xfs_off_t		offset,
-	struct block_device	*bdev,
-	sector_t		sector,
-	struct writeback_control *wbc)
-{
-	struct xfs_ioend	*ioend;
-	struct bio		*bio;
-
-	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
-	bio_set_dev(bio, bdev);
-	bio->bi_iter.bi_sector = sector;
-	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
-	bio->bi_write_hint = inode->i_write_hint;
-	wbc_init_bio(wbc, bio);
-
-	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
-	INIT_LIST_HEAD(&ioend->io_list);
-	ioend->io_fork = fork;
-	ioend->io_state = state;
-	ioend->io_inode = inode;
-	ioend->io_size = 0;
-	ioend->io_offset = offset;
-	ioend->io_append_trans = NULL;
-	ioend->io_bio = bio;
-	return ioend;
-}
-
-/*
- * Allocate a new bio, and chain the old bio to the new one.
- *
- * Note that we have to do perform the chaining in this unintuitive order
- * so that the bi_private linkage is set up in the right direction for the
- * traversal in xfs_destroy_ioend().
- */
-static struct bio *
-xfs_chain_bio(
-	struct bio		*prev)
-{
-	struct bio *new;
-
-	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
-	bio_copy_dev(new, prev);/* also copies over blkcg information */
-	new->bi_iter.bi_sector = bio_end_sector(prev);
-	new->bi_opf = prev->bi_opf;
-	new->bi_write_hint = prev->bi_write_hint;
-
-	bio_chain(prev, new);
-	bio_get(prev);		/* for xfs_destroy_ioend */
-	submit_bio(prev);
-	return new;
-}
-
-/*
- * Test to see if we have an existing ioend structure that we could append to
- * first, otherwise finish off the current ioend and start another.
- */
-STATIC void
-xfs_add_to_ioend(
-	struct inode		*inode,
-	xfs_off_t		offset,
-	struct page		*page,
-	struct iomap_page	*iop,
-	struct xfs_writepage_ctx *wpc,
-	struct writeback_control *wbc,
-	struct list_head	*iolist)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
-	unsigned		len = i_blocksize(inode);
-	unsigned		poff = offset & (PAGE_SIZE - 1);
-	bool			merged, same_page = false;
-	sector_t		sector;
-
-	sector = xfs_fsb_to_db(ip, wpc->imap.br_startblock) +
-		((offset - XFS_FSB_TO_B(mp, wpc->imap.br_startoff)) >> 9);
-
-	if (!wpc->ioend ||
-	    wpc->fork != wpc->ioend->io_fork ||
-	    wpc->imap.br_state != wpc->ioend->io_state ||
-	    sector != bio_end_sector(wpc->ioend->io_bio) ||
-	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
-		if (wpc->ioend)
-			list_add(&wpc->ioend->io_list, iolist);
-		wpc->ioend = xfs_alloc_ioend(inode, wpc->fork,
-				wpc->imap.br_state, offset, bdev, sector, wbc);
-	}
-
-	merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff,
-			&same_page);
-
-	if (iop && !same_page)
-		atomic_inc(&iop->write_count);
-
-	if (!merged) {
-		if (bio_full(wpc->ioend->io_bio, len))
-			wpc->ioend->io_bio = xfs_chain_bio(wpc->ioend->io_bio);
-		bio_add_page(wpc->ioend->io_bio, page, len, poff);
-	}
-
-	wpc->ioend->io_size += len;
-	wbc_account_cgroup_owner(wbc, page, len);
-}
-
-STATIC void
-xfs_vm_invalidatepage(
-	struct page		*page,
-	unsigned int		offset,
-	unsigned int		length)
-{
-	trace_xfs_invalidatepage(page->mapping->host, page, offset, length);
-	iomap_invalidatepage(page, offset, length);
+	if (xfs_ioend_needs_workqueue(ioend))
+		ioend->io_bio->bi_end_io = xfs_end_bio;
+	return status;
 }
 
 /*
@@ -820,8 +551,8 @@ xfs_vm_invalidatepage(
  * transaction as there is no space left for block reservation (typically why we
  * see a ENOSPC in writeback).
  */
-STATIC void
-xfs_aops_discard_page(
+static void
+xfs_discard_page(
 	struct page		*page)
 {
 	struct inode		*inode = page->mapping->host;
@@ -843,246 +574,14 @@ xfs_aops_discard_page(
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
-	xfs_vm_invalidatepage(page, 0, PAGE_SIZE);
+	iomap_invalidatepage(page, 0, PAGE_SIZE);
 }
 
-/*
- * We implement an immediate ioend submission policy here to avoid needing to
- * chain multiple ioends and hence nest mempool allocations which can violate
- * forward progress guarantees we need to provide. The current ioend we are
- * adding blocks to is cached on the writepage context, and if the new block
- * does not append to the cached ioend it will create a new ioend and cache that
- * instead.
- *
- * If a new ioend is created and cached, the old ioend is returned and queued
- * locally for submission once the entire page is processed or an error has been
- * detected.  While ioends are submitted immediately after they are completed,
- * batching optimisations are provided by higher level block plugging.
- *
- * At the end of a writeback pass, there will be a cached ioend remaining on the
- * writepage context that the caller will need to submit.
- */
-static int
-xfs_writepage_map(
-	struct xfs_writepage_ctx *wpc,
-	struct writeback_control *wbc,
-	struct inode		*inode,
-	struct page		*page,
-	uint64_t		end_offset)
-{
-	LIST_HEAD(submit_list);
-	struct iomap_page	*iop = to_iomap_page(page);
-	unsigned		len = i_blocksize(inode);
-	struct xfs_ioend	*ioend, *next;
-	uint64_t		file_offset;	/* file offset of page */
-	int			error = 0, count = 0, i;
-
-	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
-	ASSERT(!iop || atomic_read(&iop->write_count) == 0);
-
-	/*
-	 * Walk through the page to find areas to write back. If we run off the
-	 * end of the current map or find the current map invalid, grab a new
-	 * one.
-	 */
-	for (i = 0, file_offset = page_offset(page);
-	     i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset;
-	     i++, file_offset += len) {
-		if (iop && !test_bit(i, iop->uptodate))
-			continue;
-
-		error = xfs_map_blocks(wpc, inode, file_offset);
-		if (error)
-			break;
-		if (wpc->imap.br_startblock == HOLESTARTBLOCK)
-			continue;
-		xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
-				 &submit_list);
-		count++;
-	}
-
-	ASSERT(wpc->ioend || list_empty(&submit_list));
-	ASSERT(PageLocked(page));
-	ASSERT(!PageWriteback(page));
-
-	/*
-	 * On error, we have to fail the ioend here because we may have set
-	 * pages under writeback, we have to make sure we run IO completion to
-	 * mark the error state of the IO appropriately, so we can't cancel the
-	 * ioend directly here.  That means we have to mark this page as under
-	 * writeback if we included any blocks from it in the ioend chain so
-	 * that completion treats it correctly.
-	 *
-	 * If we didn't include the page in the ioend, the on error we can
-	 * simply discard and unlock it as there are no other users of the page
-	 * now.  The caller will still need to trigger submission of outstanding
-	 * ioends on the writepage context so they are treated correctly on
-	 * error.
-	 */
-	if (unlikely(error)) {
-		if (!count) {
-			xfs_aops_discard_page(page);
-			ClearPageUptodate(page);
-			unlock_page(page);
-			goto done;
-		}
-
-		/*
-		 * If the page was not fully cleaned, we need to ensure that the
-		 * higher layers come back to it correctly.  That means we need
-		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
-		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
-		 * so another attempt to write this page in this writeback sweep
-		 * will be made.
-		 */
-		set_page_writeback_keepwrite(page);
-	} else {
-		clear_page_dirty_for_io(page);
-		set_page_writeback(page);
-	}
-
-	unlock_page(page);
-
-	/*
-	 * Preserve the original error if there was one, otherwise catch
-	 * submission errors here and propagate into subsequent ioend
-	 * submissions.
-	 */
-	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
-		int error2;
-
-		list_del_init(&ioend->io_list);
-		error2 = xfs_submit_ioend(wbc, ioend, error);
-		if (error2 && !error)
-			error = error2;
-	}
-
-	/*
-	 * We can end up here with no error and nothing to write only if we race
-	 * with a partial page truncate on a sub-page block sized filesystem.
-	 */
-	if (!count)
-		end_page_writeback(page);
-done:
-	mapping_set_error(page->mapping, error);
-	return error;
-}
-
-/*
- * Write out a dirty page.
- *
- * For delalloc space on the page we need to allocate space and flush it.
- * For unwritten space on the page we need to start the conversion to
- * regular allocated space.
- */
-STATIC int
-xfs_do_writepage(
-	struct page		*page,
-	struct writeback_control *wbc,
-	void			*data)
-{
-	struct xfs_writepage_ctx *wpc = data;
-	struct inode		*inode = page->mapping->host;
-	loff_t			offset;
-	uint64_t              end_offset;
-	pgoff_t                 end_index;
-
-	trace_xfs_writepage(inode, page, 0, 0);
-
-	/*
-	 * Refuse to write the page out if we are called from reclaim context.
-	 *
-	 * This avoids stack overflows when called from deeply used stacks in
-	 * random callers for direct reclaim or memcg reclaim.  We explicitly
-	 * allow reclaim from kswapd as the stack usage there is relatively low.
-	 *
-	 * This should never happen except in the case of a VM regression so
-	 * warn about it.
-	 */
-	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
-			PF_MEMALLOC))
-		goto redirty;
-
-	/*
-	 * Given that we do not allow direct reclaim to call us, we should
-	 * never be called while in a filesystem transaction.
-	 */
-	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
-		goto redirty;
-
-	/*
-	 * Is this page beyond the end of the file?
-	 *
-	 * The page index is less than the end_index, adjust the end_offset
-	 * to the highest offset that this page should represent.
-	 * -----------------------------------------------------
-	 * |			file mapping	       | <EOF> |
-	 * -----------------------------------------------------
-	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
-	 * ^--------------------------------^----------|--------
-	 * |     desired writeback range    |      see else    |
-	 * ---------------------------------^------------------|
-	 */
-	offset = i_size_read(inode);
-	end_index = offset >> PAGE_SHIFT;
-	if (page->index < end_index)
-		end_offset = (xfs_off_t)(page->index + 1) << PAGE_SHIFT;
-	else {
-		/*
-		 * Check whether the page to write out is beyond or straddles
-		 * i_size or not.
-		 * -------------------------------------------------------
-		 * |		file mapping		        | <EOF>  |
-		 * -------------------------------------------------------
-		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
-		 * ^--------------------------------^-----------|---------
-		 * |				    |      Straddles     |
-		 * ---------------------------------^-----------|--------|
-		 */
-		unsigned offset_into_page = offset & (PAGE_SIZE - 1);
-
-		/*
-		 * Skip the page if it is fully outside i_size, e.g. due to a
-		 * truncate operation that is in progress. We must redirty the
-		 * page so that reclaim stops reclaiming it. Otherwise
-		 * xfs_vm_releasepage() is called on it and gets confused.
-		 *
-		 * Note that the end_index is unsigned long, it would overflow
-		 * if the given offset is greater than 16TB on 32-bit system
-		 * and if we do check the page is fully outside i_size or not
-		 * via "if (page->index >= end_index + 1)" as "end_index + 1"
-		 * will be evaluated to 0.  Hence this page will be redirtied
-		 * and be written out repeatedly which would result in an
-		 * infinite loop, the user program that perform this operation
-		 * will hang.  Instead, we can verify this situation by checking
-		 * if the page to write is totally beyond the i_size or if it's
-		 * offset is just equal to the EOF.
-		 */
-		if (page->index > end_index ||
-		    (page->index == end_index && offset_into_page == 0))
-			goto redirty;
-
-		/*
-		 * The page straddles i_size.  It must be zeroed out on each
-		 * and every writepage invocation because it may be mmapped.
-		 * "A file is mapped in multiples of the page size.  For a file
-		 * that is not a multiple of the page size, the remaining
-		 * memory is zeroed when mapped, and writes to that region are
-		 * not written out to the file."
-		 */
-		zero_user_segment(page, offset_into_page, PAGE_SIZE);
-
-		/* Adjust the end_offset to the end of file */
-		end_offset = offset;
-	}
-
-	return xfs_writepage_map(wpc, wbc, inode, page, end_offset);
-
-redirty:
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-	return 0;
-}
+static const struct iomap_writeback_ops xfs_writeback_ops = {
+	.map_blocks		= xfs_map_blocks,
+	.prepare_ioend		= xfs_prepare_ioend,
+	.discard_page		= xfs_discard_page,
+};
 
 STATIC int
 xfs_vm_writepage(
@@ -1090,12 +589,8 @@ xfs_vm_writepage(
 	struct writeback_control *wbc)
 {
 	struct xfs_writepage_ctx wpc = { };
-	int			ret;
 
-	ret = xfs_do_writepage(page, wbc, &wpc);
-	if (wpc.ioend)
-		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
-	return ret;
+	return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
 
 STATIC int
@@ -1104,13 +599,9 @@ xfs_vm_writepages(
 	struct writeback_control *wbc)
 {
 	struct xfs_writepage_ctx wpc = { };
-	int			ret;
 
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
-	ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc);
-	if (wpc.ioend)
-		ret = xfs_submit_ioend(wbc, wpc.ioend, ret);
-	return ret;
+	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
 
 STATIC int
@@ -1123,15 +614,6 @@ xfs_dax_writepages(
 			xfs_find_bdev_for_inode(mapping->host), wbc);
 }
 
-STATIC int
-xfs_vm_releasepage(
-	struct page		*page,
-	gfp_t			gfp_mask)
-{
-	trace_xfs_releasepage(page->mapping->host, page, 0, 0);
-	return iomap_releasepage(page, gfp_mask);
-}
-
 STATIC sector_t
 xfs_vm_bmap(
 	struct address_space	*mapping,
@@ -1160,7 +642,6 @@ xfs_vm_readpage(
 	struct file		*unused,
 	struct page		*page)
 {
-	trace_xfs_vm_readpage(page->mapping->host, 1);
 	return iomap_readpage(page, &xfs_iomap_ops);
 }
 
@@ -1171,7 +652,6 @@ xfs_vm_readpages(
 	struct list_head	*pages,
 	unsigned		nr_pages)
 {
-	trace_xfs_vm_readpages(mapping->host, nr_pages);
 	return iomap_readpages(mapping, pages, nr_pages, &xfs_iomap_ops);
 }
 
@@ -1191,8 +671,8 @@ const struct address_space_operations xfs_address_space_operations = {
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
 	.set_page_dirty		= iomap_set_page_dirty,
-	.releasepage		= xfs_vm_releasepage,
-	.invalidatepage		= xfs_vm_invalidatepage,
+	.releasepage		= iomap_releasepage,
+	.invalidatepage		= iomap_invalidatepage,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= noop_direct_IO,
 	.migratepage		= iomap_migrate_page,
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 45a1ea240cbb..687b11f34fa2 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -6,23 +6,6 @@
 #ifndef __XFS_AOPS_H__
 #define __XFS_AOPS_H__
 
-extern struct bio_set xfs_ioend_bioset;
-
-/*
- * Structure for buffered I/O completions.
- */
-struct xfs_ioend {
-	struct list_head	io_list;	/* next ioend in chain */
-	int			io_fork;	/* inode fork written back */
-	xfs_exntst_t		io_state;	/* extent state */
-	struct inode		*io_inode;	/* file being written to */
-	size_t			io_size;	/* size of the extent */
-	xfs_off_t		io_offset;	/* offset in the file */
-	struct xfs_trans	*io_append_trans;/* xact. for size update */
-	struct bio		*io_bio;	/* bio being built */
-	struct bio		io_inline_bio;	/* MUST BE LAST! */
-};
-
 extern const struct address_space_operations xfs_address_space_operations;
 extern const struct address_space_operations xfs_dax_aops;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1ffb179f35d2..c0620135a279 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -188,7 +188,7 @@ xfs_file_dio_aio_read(
 	file_accessed(iocb->ki_filp);
 
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL);
+	ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL, is_sync_kiocb(iocb));
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
@@ -547,15 +547,12 @@ xfs_file_dio_aio_write(
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
-	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops);
-
 	/*
-	 * If unaligned, this is the only IO in-flight. If it has not yet
-	 * completed, wait on it before we release the iolock to prevent
-	 * subsequent overlapping IO.
+	 * If unaligned, this is the only IO in-flight. Wait on it before we
+	 * release the iolock to prevent subsequent overlapping IO.
 	 */
-	if (ret == -EIOCBQUEUED && unaligned_io)
-		inode_dio_wait(inode);
+	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops,
+			   is_sync_kiocb(iocb) || unaligned_io);
 out:
 	xfs_iunlock(ip, iolock);
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index f780e223b118..95719e161286 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -54,7 +54,7 @@ xfs_bmbt_to_iomap(
 	struct xfs_inode	*ip,
 	struct iomap		*iomap,
 	struct xfs_bmbt_irec	*imap,
-	bool			shared)
+	u16			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
@@ -79,12 +79,11 @@ xfs_bmbt_to_iomap(
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
 	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
 	iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
+	iomap->flags = flags;
 
 	if (xfs_ipincount(ip) &&
 	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 		iomap->flags |= IOMAP_F_DIRTY;
-	if (shared)
-		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
 }
 
@@ -540,6 +539,7 @@ xfs_file_iomap_begin_delay(
 	struct xfs_iext_cursor	icur, ccur;
 	xfs_fsblock_t		prealloc_blocks = 0;
 	bool			eof = false, cow_eof = false, shared = false;
+	u16			iomap_flags = 0;
 	int			whichfork = XFS_DATA_FORK;
 	int			error = 0;
 
@@ -707,22 +707,28 @@ retry:
 	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
 	 * them out if the write happens to fail.
 	 */
-	iomap->flags |= IOMAP_F_NEW;
-	trace_xfs_iomap_alloc(ip, offset, count, whichfork,
-			whichfork == XFS_DATA_FORK ? &imap : &cmap);
+	if (whichfork == XFS_DATA_FORK) {
+		iomap_flags |= IOMAP_F_NEW;
+		trace_xfs_iomap_alloc(ip, offset, count, whichfork, &imap);
+	} else {
+		trace_xfs_iomap_alloc(ip, offset, count, whichfork, &cmap);
+	}
 done:
 	if (whichfork == XFS_COW_FORK) {
 		if (imap.br_startoff > offset_fsb) {
 			xfs_trim_extent(&cmap, offset_fsb,
 					imap.br_startoff - offset_fsb);
-			error = xfs_bmbt_to_iomap(ip, iomap, &cmap, true);
+			error = xfs_bmbt_to_iomap(ip, iomap, &cmap,
+					IOMAP_F_SHARED);
 			goto out_unlock;
 		}
 		/* ensure we only report blocks we have a reservation for */
 		xfs_trim_extent(&imap, cmap.br_startoff, cmap.br_blockcount);
 		shared = true;
 	}
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	if (shared)
+		iomap_flags |= IOMAP_F_SHARED;
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -922,7 +928,8 @@ xfs_file_iomap_begin(
 	loff_t			offset,
 	loff_t			length,
 	unsigned		flags,
-	struct iomap		*iomap)
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -930,6 +937,7 @@ xfs_file_iomap_begin(
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			nimaps = 1, error = 0;
 	bool			shared = false;
+	u16			iomap_flags = 0;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -1045,11 +1053,20 @@ xfs_file_iomap_begin(
 	if (error)
 		return error;
 
-	iomap->flags |= IOMAP_F_NEW;
+	iomap_flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
 
 out_finish:
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	/*
+	 * Writes that span EOF might trigger an IO size update on completion,
+	 * so consider them to be dirty for the purposes of O_DSYNC even if
+	 * there is no other metadata changes pending or have been made here.
+	 */
+	if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode))
+		iomap_flags |= IOMAP_F_DIRTY;
+	if (shared)
+		iomap_flags |= IOMAP_F_SHARED;
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
 
 out_found:
 	ASSERT(nimaps);
@@ -1145,7 +1162,8 @@ xfs_seek_iomap_begin(
 	loff_t			offset,
 	loff_t			length,
 	unsigned		flags,
-	struct iomap		*iomap)
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1193,7 +1211,7 @@ xfs_seek_iomap_begin(
 		if (data_fsb < cow_fsb + cmap.br_blockcount)
 			end_fsb = min(end_fsb, data_fsb);
 		xfs_trim_extent(&cmap, offset_fsb, end_fsb);
-		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, true);
+		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
 		/*
 		 * This is a COW extent, so we must probe the page cache
 		 * because there could be dirty page cache being backed
@@ -1215,7 +1233,7 @@ xfs_seek_iomap_begin(
 	imap.br_state = XFS_EXT_NORM;
 done:
 	xfs_trim_extent(&imap, offset_fsb, end_fsb);
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
@@ -1231,7 +1249,8 @@ xfs_xattr_iomap_begin(
 	loff_t			offset,
 	loff_t			length,
 	unsigned		flags,
-	struct iomap		*iomap)
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1261,7 +1280,7 @@ out_unlock:
 	if (error)
 		return error;
 	ASSERT(nimaps);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 }
 
 const struct iomap_ops xfs_xattr_iomap_ops = {
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 5c2f6aa6d78f..71d0ae460c44 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -16,7 +16,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
-		struct xfs_bmbt_irec *, bool shared);
+		struct xfs_bmbt_irec *, u16);
 xfs_extlen_t xfs_eof_alignment(struct xfs_inode *ip, xfs_extlen_t extsize);
 
 static inline xfs_filblks_t
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index a339bd5fa260..9c96493be9e0 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -178,7 +178,7 @@ xfs_fs_map_blocks(
 	}
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 	*device_generation = mp->m_generation;
 	return error;
 out_unlock:
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 0f08153b4994..a9634110c783 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1442,7 +1442,7 @@ xfs_reflink_dirty_extents(
 			flen = XFS_FSB_TO_B(mp, rlen);
 			if (fpos + flen > isize)
 				flen = isize - fpos;
-			error = iomap_file_dirty(VFS_I(ip), fpos, flen,
+			error = iomap_file_unshare(VFS_I(ip), fpos, flen,
 					&xfs_iomap_ops);
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			if (error)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 8d1df9f8be07..0a8cf6b87a21 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -40,7 +40,6 @@
 #include <linux/parser.h>
 
 static const struct super_operations xfs_super_operations;
-struct bio_set xfs_ioend_bioset;
 
 static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
 #ifdef DEBUG
@@ -1853,15 +1852,10 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
-			offsetof(struct xfs_ioend, io_inline_bio),
-			BIOSET_NEED_BVECS))
-		goto out;
-
 	xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
 						"xfs_log_ticket");
 	if (!xfs_log_ticket_zone)
-		goto out_free_ioend_bioset;
+		goto out;
 
 	xfs_bmap_free_item_zone = kmem_zone_init(
 			sizeof(struct xfs_extent_free_item),
@@ -1996,8 +1990,6 @@ xfs_init_zones(void)
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
  out_destroy_log_ticket_zone:
 	kmem_zone_destroy(xfs_log_ticket_zone);
- out_free_ioend_bioset:
-	bioset_exit(&xfs_ioend_bioset);
  out:
 	return -ENOMEM;
 }
@@ -2028,7 +2020,6 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_btree_cur_zone);
 	kmem_zone_destroy(xfs_bmap_free_item_zone);
 	kmem_zone_destroy(xfs_log_ticket_zone);
-	bioset_exit(&xfs_ioend_bioset);
 }
 
 STATIC int __init
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index eaae275ed430..cbb23d7a3554 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1158,71 +1158,6 @@ DEFINE_RW_EVENT(xfs_file_buffered_write);
 DEFINE_RW_EVENT(xfs_file_direct_write);
 DEFINE_RW_EVENT(xfs_file_dax_write);
 
-DECLARE_EVENT_CLASS(xfs_page_class,
-	TP_PROTO(struct inode *inode, struct page *page, unsigned long off,
-		 unsigned int len),
-	TP_ARGS(inode, page, off, len),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(pgoff_t, pgoff)
-		__field(loff_t, size)
-		__field(unsigned long, offset)
-		__field(unsigned int, length)
-	),
-	TP_fast_assign(
-		__entry->dev = inode->i_sb->s_dev;
-		__entry->ino = XFS_I(inode)->i_ino;
-		__entry->pgoff = page_offset(page);
-		__entry->size = i_size_read(inode);
-		__entry->offset = off;
-		__entry->length = len;
-	),
-	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
-		  "length %x",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->pgoff,
-		  __entry->size,
-		  __entry->offset,
-		  __entry->length)
-)
-
-#define DEFINE_PAGE_EVENT(name)		\
-DEFINE_EVENT(xfs_page_class, name,	\
-	TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \
-		 unsigned int len),	\
-	TP_ARGS(inode, page, off, len))
-DEFINE_PAGE_EVENT(xfs_writepage);
-DEFINE_PAGE_EVENT(xfs_releasepage);
-DEFINE_PAGE_EVENT(xfs_invalidatepage);
-
-DECLARE_EVENT_CLASS(xfs_readpage_class,
-	TP_PROTO(struct inode *inode, int nr_pages),
-	TP_ARGS(inode, nr_pages),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(int, nr_pages)
-	),
-	TP_fast_assign(
-		__entry->dev = inode->i_sb->s_dev;
-		__entry->ino = inode->i_ino;
-		__entry->nr_pages = nr_pages;
-	),
-	TP_printk("dev %d:%d ino 0x%llx nr_pages %d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->nr_pages)
-)
-
-#define DEFINE_READPAGE_EVENT(name)		\
-DEFINE_EVENT(xfs_readpage_class, name,	\
-	TP_PROTO(struct inode *inode, int nr_pages), \
-	TP_ARGS(inode, nr_pages))
-DEFINE_READPAGE_EVENT(xfs_vm_readpage);
-DEFINE_READPAGE_EVENT(xfs_vm_readpages);
-
 DECLARE_EVENT_CLASS(xfs_imap_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,
 		 int whichfork, struct xfs_bmbt_irec *irec),