Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 49f5f58..f16d5f1 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -12,23 +12,19 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_trans.h"
-#include "xfs_inode_item.h"
-#include "xfs_alloc.h"
-#include "xfs_error.h"
 #include "xfs_iomap.h"
 #include "xfs_trace.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
-#include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
-#include <linux/writeback.h>
 
 /*
  * structure owned by writepages passed to individual writepage calls
  */
 struct xfs_writepage_ctx {
 	struct xfs_bmbt_irec    imap;
-	unsigned int		io_type;
+	int			fork;
+	unsigned int		data_seq;
 	unsigned int		cow_seq;
 	struct xfs_ioend	*ioend;
 };
@@ -62,7 +58,7 @@
 static void
 xfs_finish_page_writeback(
 	struct inode		*inode,
-	struct bio_vec		*bvec,
+	struct bio_vec	*bvec,
 	int			error)
 {
 	struct iomap_page	*iop = to_iomap_page(bvec->bv_page);
@@ -97,7 +93,7 @@
 
 	for (bio = &ioend->io_inline_bio; bio; bio = next) {
 		struct bio_vec	*bvec;
-		int		i;
+		struct bvec_iter_all iter_all;
 
 		/*
 		 * For the last bio, bi_private points to the ioend, so we
@@ -109,7 +105,7 @@
 			next = bio->bi_private;
 
 		/* walk each page on bio, ending page IO on them */
-		bio_for_each_segment_all(bvec, bio, i)
+		bio_for_each_segment_all(bvec, bio, iter_all)
 			xfs_finish_page_writeback(inode, bvec, error);
 		bio_put(bio);
 	}
@@ -137,8 +133,7 @@
 	struct xfs_trans	*tp;
 	int			error;
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0,
-				XFS_TRANS_NOFS, &tp);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
 	if (error)
 		return error;
 
@@ -232,17 +227,24 @@
  * IO write completion.
  */
 STATIC void
-xfs_end_io(
-	struct work_struct *work)
+xfs_end_ioend(
+	struct xfs_ioend	*ioend)
 {
-	struct xfs_ioend	*ioend =
-		container_of(work, struct xfs_ioend, io_work);
+	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;
+	unsigned int		nofs_flag;
 	int			error;
 
 	/*
+	 * We can allocate memory here while doing writeback on behalf of
+	 * memory reclaim.  To avoid memory allocation deadlocks set the
+	 * task-wide nofs context for the following operations.
+	 */
+	nofs_flag = memalloc_nofs_save();
+
+	/*
 	 * Just clean up the in-memory strutures if the fs has been shut down.
 	 */
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
@@ -255,35 +257,140 @@
 	 */
 	error = blk_status_to_errno(ioend->io_bio->bi_status);
 	if (unlikely(error)) {
-		switch (ioend->io_type) {
-		case XFS_IO_COW:
+		if (ioend->io_fork == XFS_COW_FORK)
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
-			break;
-		}
-
 		goto done;
 	}
 
 	/*
-	 * Success:  commit the COW or unwritten blocks if needed.
+	 * Success: commit the COW or unwritten blocks if needed.
 	 */
-	switch (ioend->io_type) {
-	case XFS_IO_COW:
+	if (ioend->io_fork == XFS_COW_FORK)
 		error = xfs_reflink_end_cow(ip, offset, size);
-		break;
-	case XFS_IO_UNWRITTEN:
-		/* writeback should never update isize */
+	else if (ioend->io_state == XFS_EXT_UNWRITTEN)
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
-		break;
-	default:
+	else
 		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
-		break;
-	}
 
 done:
 	if (ioend->io_append_trans)
 		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);
+	}
+
+	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)
+{
+	if (!ioend->io_append_trans) {
+		ioend->io_append_trans = next->io_append_trans;
+		next->io_append_trans = 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;
+	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);
+	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);
+		list_del_init(&ioend->io_list);
+		xfs_ioend_try_merge(ioend, &completion_list);
+		xfs_end_ioend(ioend);
+	}
 }
 
 STATIC void
@@ -291,16 +398,92 @@
 	struct bio		*bio)
 {
 	struct xfs_ioend	*ioend = bio->bi_private;
-	struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	unsigned long		flags;
 
-	if (ioend->io_type == XFS_IO_UNWRITTEN || ioend->io_type == XFS_IO_COW)
-		queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
-	else if (ioend->io_append_trans)
-		queue_work(mp->m_data_workqueue, &ioend->io_work);
-	else
+	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));
 }
 
+/*
+ * Fast revalidation of the cached writeback mapping. Return true if the current
+ * mapping is valid, false otherwise.
+ */
+static bool
+xfs_imap_valid(
+	struct xfs_writepage_ctx	*wpc,
+	struct xfs_inode		*ip,
+	xfs_fileoff_t			offset_fsb)
+{
+	if (offset_fsb < wpc->imap.br_startoff ||
+	    offset_fsb >= wpc->imap.br_startoff + wpc->imap.br_blockcount)
+		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)
+		return true;
+
+	/*
+	 * This is not a COW mapping. Check the sequence number of the data fork
+	 * because concurrent changes could have invalidated the extent. Check
+	 * the COW fork because concurrent changes since the last time we
+	 * checked (and found nothing at this offset) could have added
+	 * overlapping blocks.
+	 */
+	if (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))
+		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.
+ *
+ * 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
+ * fork by another thread.
+ */
+static int
+xfs_convert_blocks(
+	struct xfs_writepage_ctx *wpc,
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		offset_fsb)
+{
+	int			error;
+
+	/*
+	 * 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.
+	 */
+	do {
+		error = xfs_bmapi_convert_delalloc(ip, wpc->fork, offset_fsb,
+				&wpc->imap, wpc->fork == XFS_COW_FORK ?
+					&wpc->cow_seq : &wpc->data_seq);
+		if (error)
+			return error;
+	} while (wpc->imap.br_startoff + wpc->imap.br_blockcount <= offset_fsb);
+
+	return 0;
+}
+
 STATIC int
 xfs_map_blocks(
 	struct xfs_writepage_ctx *wpc,
@@ -310,26 +493,16 @@
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
-	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
+	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;
 	struct xfs_bmbt_irec	imap;
-	int			whichfork = XFS_DATA_FORK;
 	struct xfs_iext_cursor	icur;
-	bool			imap_valid;
+	int			retries = 0;
 	int			error = 0;
 
-	/*
-	 * We have to make sure the cached mapping is within EOF to protect
-	 * against eofblocks trimming on file release leaving us with a stale
-	 * mapping. Otherwise, a page for a subsequent file extending buffered
-	 * write could get picked up by this writeback cycle and written to the
-	 * wrong blocks.
-	 *
-	 * Note that what we really want here is a generic mapping invalidation
-	 * mechanism to protect us from arbitrary extent modifying contexts, not
-	 * just eofblocks.
-	 */
-	xfs_trim_extent_eof(&wpc->imap, ip);
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
 
 	/*
 	 * COW fork blocks can overlap data fork blocks even if the blocks
@@ -346,31 +519,19 @@
 	 * against concurrent updates and provides a memory barrier on the way
 	 * out that ensures that we always see the current value.
 	 */
-	imap_valid = offset_fsb >= wpc->imap.br_startoff &&
-		     offset_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount;
-	if (imap_valid &&
-	    (!xfs_inode_has_cow_data(ip) ||
-	     wpc->io_type == XFS_IO_COW ||
-	     wpc->cow_seq == READ_ONCE(ip->i_cowfp->if_seq)))
+	if (xfs_imap_valid(wpc, ip, offset_fsb))
 		return 0;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
 	/*
 	 * If we don't have a valid map, now it's time to get a new one for this
 	 * offset.  This will convert delayed allocations (including COW ones)
 	 * into real extents.  If we return without a valid map, it means we
 	 * landed in a hole and we skip the block.
 	 */
+retry:
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
-	ASSERT(offset <= mp->m_super->s_maxbytes);
-
-	if (offset > mp->m_super->s_maxbytes - count)
-		count = mp->m_super->s_maxbytes - offset;
-	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
 
 	/*
 	 * Check if this is offset is covered by a COW extents, and if yes use
@@ -382,30 +543,16 @@
 	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
 		wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		/*
-		 * Truncate can race with writeback since writeback doesn't
-		 * take the iolock and truncate decreases the file size before
-		 * it starts truncating the pages between new_size and old_size.
-		 * Therefore, we can end up in the situation where writeback
-		 * gets a CoW fork mapping but the truncate makes the mapping
-		 * invalid and we end up in here trying to get a new mapping.
-		 * bail out here so that we simply never get a valid mapping
-		 * and so we drop the write altogether.  The page truncation
-		 * will kill the contents anyway.
-		 */
-		if (offset > i_size_read(inode)) {
-			wpc->io_type = XFS_IO_HOLE;
-			return 0;
-		}
-		whichfork = XFS_COW_FORK;
-		wpc->io_type = XFS_IO_COW;
+
+		wpc->fork = XFS_COW_FORK;
 		goto allocate_blocks;
 	}
 
 	/*
-	 * Map valid and no COW extent in the way?  We're done.
+	 * No COW extent overlap. Revalidate now that we may have updated
+	 * ->cow_seq. If the data mapping is still valid, we're done.
 	 */
-	if (imap_valid) {
+	if (xfs_imap_valid(wpc, ip, offset_fsb)) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		return 0;
 	}
@@ -417,49 +564,65 @@
 	 */
 	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_iunlock(ip, XFS_ILOCK_SHARED);
 
+	wpc->fork = XFS_DATA_FORK;
+
+	/* landed in a hole or beyond EOF? */
 	if (imap.br_startoff > offset_fsb) {
-		/* landed in a hole or beyond EOF */
 		imap.br_blockcount = imap.br_startoff - offset_fsb;
 		imap.br_startoff = offset_fsb;
 		imap.br_startblock = HOLESTARTBLOCK;
-		wpc->io_type = XFS_IO_HOLE;
-	} else {
-		/*
-		 * Truncate to the next COW extent if there is one.  This is the
-		 * only opportunity to do this because we can skip COW fork
-		 * lookups for the subsequent blocks in the mapping; however,
-		 * the requirement to treat the COW range separately remains.
-		 */
-		if (cow_fsb != NULLFILEOFF &&
-		    cow_fsb < imap.br_startoff + imap.br_blockcount)
-			imap.br_blockcount = cow_fsb - imap.br_startoff;
-
-		if (isnullstartblock(imap.br_startblock)) {
-			/* got a delalloc extent */
-			wpc->io_type = XFS_IO_DELALLOC;
-			goto allocate_blocks;
-		}
-
-		if (imap.br_state == XFS_EXT_UNWRITTEN)
-			wpc->io_type = XFS_IO_UNWRITTEN;
-		else
-			wpc->io_type = XFS_IO_OVERWRITE;
+		imap.br_state = XFS_EXT_NORM;
 	}
 
+	/*
+	 * Truncate to the next COW extent if there is one.  This is the only
+	 * opportunity to do this because we can skip COW fork lookups for the
+	 * subsequent blocks in the mapping; however, the requirement to treat
+	 * the COW range separately remains.
+	 */
+	if (cow_fsb != NULLFILEOFF &&
+	    cow_fsb < imap.br_startoff + imap.br_blockcount)
+		imap.br_blockcount = cow_fsb - imap.br_startoff;
+
+	/* got a delalloc extent? */
+	if (imap.br_startblock != HOLESTARTBLOCK &&
+	    isnullstartblock(imap.br_startblock))
+		goto allocate_blocks;
+
 	wpc->imap = imap;
-	trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
+	trace_xfs_map_blocks_found(ip, offset, count, wpc->fork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_iomap_write_allocate(ip, whichfork, offset, &imap,
-			&wpc->cow_seq);
-	if (error)
+	error = xfs_convert_blocks(wpc, ip, offset_fsb);
+	if (error) {
+		/*
+		 * If we failed to find the extent in the COW fork we might have
+		 * raced with a COW to data fork conversion or truncate.
+		 * Restart the lookup to catch the extent in the data fork for
+		 * the former case, but prevent additional retries to avoid
+		 * looping forever for the latter case.
+		 */
+		if (error == -EAGAIN && wpc->fork == XFS_COW_FORK && !retries++)
+			goto retry;
+		ASSERT(error != -EAGAIN);
 		return error;
-	ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF ||
-	       imap.br_startoff + imap.br_blockcount <= cow_fsb);
-	wpc->imap = imap;
-	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap);
+	}
+
+	/*
+	 * Due to merging the return real extent might be larger than the
+	 * 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;
+
+	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);
 	return 0;
 }
 
@@ -471,7 +634,7 @@
  * 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 @fail is non-zero, it means that we have a situation where some part of
+ * 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
@@ -483,33 +646,33 @@
 	struct xfs_ioend	*ioend,
 	int			status)
 {
-	/* Convert CoW extents to regular */
-	if (!status && ioend->io_type == XFS_IO_COW) {
-		/*
-		 * Yuk. This can do memory allocation, but is not a
-		 * transactional operation so everything is done in GFP_KERNEL
-		 * context. That can deadlock, because we hold pages in
-		 * writeback state and GFP_KERNEL allocations can block on them.
-		 * Hence we must operate in nofs conditions here.
-		 */
-		unsigned nofs_flag;
+	unsigned int		nofs_flag;
 
-		nofs_flag = memalloc_nofs_save();
+	/*
+	 * We can allocate memory here while doing writeback on behalf of
+	 * memory reclaim.  To avoid memory allocation deadlocks set the
+	 * task-wide nofs context for the following operations.
+	 */
+	nofs_flag = memalloc_nofs_save();
+
+	/* Convert CoW extents to regular */
+	if (!status && ioend->io_fork == XFS_COW_FORK) {
 		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
 				ioend->io_offset, ioend->io_size);
-		memalloc_nofs_restore(nofs_flag);
 	}
 
 	/* Reserve log space if we might write beyond the on-disk inode size. */
 	if (!status &&
-	    ioend->io_type != XFS_IO_UNWRITTEN &&
+	    (ioend->io_fork == XFS_COW_FORK ||
+	     ioend->io_state != XFS_EXT_UNWRITTEN) &&
 	    xfs_ioend_is_append(ioend) &&
 	    !ioend->io_append_trans)
 		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;
-	ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
 
 	/*
 	 * If we are failing the IO now, just mark the ioend with an
@@ -523,7 +686,6 @@
 		return status;
 	}
 
-	ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint;
 	submit_bio(ioend->io_bio);
 	return 0;
 }
@@ -531,10 +693,12 @@
 static struct xfs_ioend *
 xfs_alloc_ioend(
 	struct inode		*inode,
-	unsigned int		type,
+	int			fork,
+	xfs_exntst_t		state,
 	xfs_off_t		offset,
 	struct block_device	*bdev,
-	sector_t		sector)
+	sector_t		sector,
+	struct writeback_control *wbc)
 {
 	struct xfs_ioend	*ioend;
 	struct bio		*bio;
@@ -542,14 +706,17 @@
 	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_type = type;
+	ioend->io_fork = fork;
+	ioend->io_state = state;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
 	ioend->io_offset = offset;
-	INIT_WORK(&ioend->io_work, xfs_end_io);
 	ioend->io_append_trans = NULL;
 	ioend->io_bio = bio;
 	return ioend;
@@ -562,24 +729,22 @@
  * so that the bi_private linkage is set up in the right direction for the
  * traversal in xfs_destroy_ioend().
  */
-static void
+static struct bio *
 xfs_chain_bio(
-	struct xfs_ioend	*ioend,
-	struct writeback_control *wbc,
-	struct block_device	*bdev,
-	sector_t		sector)
+	struct bio		*prev)
 {
 	struct bio *new;
 
 	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
-	bio_set_dev(new, bdev);
-	new->bi_iter.bi_sector = sector;
-	bio_chain(ioend->io_bio, new);
-	bio_get(ioend->io_bio);		/* for xfs_destroy_ioend */
-	ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
-	ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint;
-	submit_bio(ioend->io_bio);
-	ioend->io_bio = new;
+	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;
 }
 
 /*
@@ -601,29 +766,37 @@
 	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->io_type != wpc->ioend->io_type ||
+	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->io_type, offset,
-				bdev, sector);
+		wpc->ioend = xfs_alloc_ioend(inode, wpc->fork,
+				wpc->imap.br_state, offset, bdev, sector, wbc);
 	}
 
-	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
-		if (iop)
-			atomic_inc(&iop->write_count);
-		if (bio_full(wpc->ioend->io_bio))
-			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
-		__bio_add_page(wpc->ioend->io_bio, page, len, poff);
+	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
@@ -721,7 +894,7 @@
 		error = xfs_map_blocks(wpc, inode, file_offset);
 		if (error)
 			break;
-		if (wpc->io_type == XFS_IO_HOLE)
+		if (wpc->imap.br_startblock == HOLESTARTBLOCK)
 			continue;
 		xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
 				 &submit_list);
@@ -916,9 +1089,7 @@
 	struct page		*page,
 	struct writeback_control *wbc)
 {
-	struct xfs_writepage_ctx wpc = {
-		.io_type = XFS_IO_INVALID,
-	};
+	struct xfs_writepage_ctx wpc = { };
 	int			ret;
 
 	ret = xfs_do_writepage(page, wbc, &wpc);
@@ -932,9 +1103,7 @@
 	struct address_space	*mapping,
 	struct writeback_control *wbc)
 {
-	struct xfs_writepage_ctx wpc = {
-		.io_type = XFS_IO_INVALID,
-	};
+	struct xfs_writepage_ctx wpc = { };
 	int			ret;
 
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
@@ -981,7 +1150,7 @@
 	 * Since we don't pass back blockdev info, we can't return bmap
 	 * information for rt files either.
 	 */
-	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip))
+	if (xfs_is_cow_inode(ip) || XFS_IS_REALTIME_INODE(ip))
 		return 0;
 	return iomap_bmap(mapping, block, &xfs_iomap_ops);
 }