[PATCH v4 0/5] xfs: use the iomap writeback code

[PATCH v4 0/5] xfs: use the iomap writeback code

[Darrick J. Wong]

Hi all,

>From Christoph:

This series cleans up the xfs writepage code and then lifts it to
fs/iomap/ so that it could be use by other file systems.  I've been
wanting to [do] this for a while so that I could eventually convert gfs2
over to it, but I never got to it.  Now Damien has a new zonefs file
system for semi-raw access to zoned block devices that would like to use
the iomap code instead of reinventing it, so I finally had to do the
work.

>From Darrick:

For v4, split the series into smaller pieces.  This third part converts
XFS to use the iomap writeback code.

Changes since v2:
 - rebased to v5.3-rc1
 - folded in a few changes from the gfs2 enablement series

Changes since v1:
 - rebased to the latest xfs for-next tree
 - keep the preallocated transactions for size updates
 - rename list_pop to list_pop_entry and related cleanups
 - better document the nofs context handling
 - document that the iomap tracepoints are not a stable API
This series breaks up fs/iomap.c by grouping the functions by major
functional area (swapfiles, fiemap, seek hole/data, directio, buffered
io, and page migration) in separate source code files under fs/iomap/.
No functional changes have been made.  Please check the copyrights to
make sure the attribution is correct.

If you're going to start using this mess, you probably ought to just
pull from my git trees, which are linked below.

This has been lightly tested with fstests.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git/log/?h=xfs-iomap-writeback

[PATCH 1/5] xfs: use a struct iomap in xfs_writepage_ctx

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

In preparation for moving the XFS writeback code to fs/iomap.c, switch
it to use struct iomap instead of the XFS-specific struct xfs_bmbt_irec.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c |   14 ++++++--
 fs/xfs/libxfs/xfs_bmap.h |    3 +-
 fs/xfs/xfs_aops.c        |   82 +++++++++++++++++++++-------------------------
 fs/xfs/xfs_aops.h        |    2 +
 4 files changed, 50 insertions(+), 51 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index baf0b72c0a37..2a0d9427a9e2 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;
@@ -4452,16 +4453,21 @@ 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.
@@ -4491,7 +4497,7 @@ 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;
 	}
@@ -4524,7 +4530,7 @@ 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 8f597f9abdbe..3c3470f11648 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -220,8 +220,7 @@ 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 4e4a4d7df5ac..8a1cd562a358 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -22,7 +22,7 @@
  * structure owned by writepages passed to individual writepage calls
  */
 struct xfs_writepage_ctx {
-	struct xfs_bmbt_irec    imap;
+	struct iomap		iomap;
 	int			fork;
 	unsigned int		data_seq;
 	unsigned int		cow_seq;
@@ -279,7 +279,7 @@ xfs_end_ioend(
 	 */
 	if (ioend->io_fork == XFS_COW_FORK)
 		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);
@@ -303,8 +303,8 @@ xfs_ioend_can_merge(
 		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))
+	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
+	    (next->io_type == IOMAP_UNWRITTEN))
 		return false;
 	if (ioend->io_offset + ioend->io_size != next->io_offset)
 		return false;
@@ -409,7 +409,7 @@ xfs_end_bio(
 	unsigned long		flags;
 
 	if (ioend->io_fork == XFS_COW_FORK ||
-	    ioend->io_state == XFS_EXT_UNWRITTEN ||
+	    ioend->io_type == IOMAP_UNWRITTEN ||
 	    ioend->io_append_trans != NULL) {
 		spin_lock_irqsave(&ip->i_ioend_lock, flags);
 		if (list_empty(&ip->i_ioend_list))
@@ -429,10 +429,10 @@ static bool
 xfs_imap_valid(
 	struct xfs_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
@@ -459,7 +459,7 @@ xfs_imap_valid(
 
 /*
  * 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
@@ -469,23 +469,23 @@ static int
 xfs_convert_blocks(
 	struct xfs_writepage_ctx *wpc,
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		offset_fsb)
+	loff_t			offset)
 {
 	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.
+	 * Attempt to allocate whatever delalloc extent currently backs offset
+	 * 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 ?
+		error = xfs_bmapi_convert_delalloc(ip, wpc->fork, offset,
+				&wpc->iomap, 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);
+	} while (wpc->iomap.offset + wpc->iomap.length <= offset);
 
 	return 0;
 }
@@ -525,7 +525,7 @@ 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;
 
 	/*
@@ -558,7 +558,7 @@ xfs_map_blocks(
 	 * 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;
 	}
@@ -598,11 +598,11 @@ xfs_map_blocks(
 	    isnullstartblock(imap.br_startblock))
 		goto allocate_blocks;
 
-	wpc->imap = imap;
+	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
 	trace_xfs_map_blocks_found(ip, offset, count, wpc->fork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_convert_blocks(wpc, ip, offset_fsb);
+	error = xfs_convert_blocks(wpc, ip, offset);
 	if (error) {
 		/*
 		 * If we failed to find the extent in the COW fork we might have
@@ -622,12 +622,15 @@ xfs_map_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 (wpc->fork != 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);
+	ASSERT(wpc->iomap.offset <= offset);
+	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
 	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->fork, &imap);
 	return 0;
 }
@@ -670,7 +673,7 @@ xfs_submit_ioend(
 	/* 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_type != IOMAP_UNWRITTEN) &&
 	    xfs_ioend_is_append(ioend) &&
 	    !ioend->io_append_trans)
 		status = xfs_setfilesize_trans_alloc(ioend);
@@ -699,10 +702,8 @@ xfs_submit_ioend(
 static struct xfs_ioend *
 xfs_alloc_ioend(
 	struct inode		*inode,
-	int			fork,
-	xfs_exntst_t		state,
+	struct xfs_writepage_ctx *wpc,
 	xfs_off_t		offset,
-	struct block_device	*bdev,
 	sector_t		sector,
 	struct writeback_control *wbc)
 {
@@ -710,7 +711,7 @@ xfs_alloc_ioend(
 	struct bio		*bio;
 
 	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
-	bio_set_dev(bio, bdev);
+	bio_set_dev(bio, wpc->iomap.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;
@@ -718,8 +719,8 @@ xfs_alloc_ioend(
 
 	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_fork = wpc->fork;
+	ioend->io_type = wpc->iomap.type;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
 	ioend->io_offset = offset;
@@ -767,26 +768,19 @@ xfs_add_to_ioend(
 	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);
+	sector_t		sector = iomap_sector(&wpc->iomap, offset);
 	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 ||
+	    wpc->iomap.type != wpc->ioend->io_type ||
 	    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);
+		wpc->ioend = xfs_alloc_ioend(inode, wpc, offset, sector, wbc);
 	}
 
 	merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff,
@@ -900,7 +894,7 @@ xfs_writepage_map(
 		error = xfs_map_blocks(wpc, inode, file_offset);
 		if (error)
 			break;
-		if (wpc->imap.br_startblock == HOLESTARTBLOCK)
+		if (wpc->iomap.type == IOMAP_HOLE)
 			continue;
 		xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
 				 &submit_list);
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 45a1ea240cbb..4af8ec0115cd 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -14,7 +14,7 @@ extern struct bio_set xfs_ioend_bioset;
 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 */
+	u16			io_type;
 	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 */

Re: [PATCH 1/5] xfs: use a struct iomap in xfs_writepage_ctx

[Carlos Maiolino]

On Mon, Jul 29, 2019 at 06:18:43PM -0700, Darrick J. Wong wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> In preparation for moving the XFS writeback code to fs/iomap.c, switch
> it to use struct iomap instead of the XFS-specific struct xfs_bmbt_irec.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
>  fs/xfs/libxfs/xfs_bmap.c |   14 ++++++--
>  fs/xfs/libxfs/xfs_bmap.h |    3 +-
>  fs/xfs/xfs_aops.c        |   82 +++++++++++++++++++++-------------------------
>  fs/xfs/xfs_aops.h        |    2 +
>  4 files changed, 50 insertions(+), 51 deletions(-)
> 
> 
> diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
> index baf0b72c0a37..2a0d9427a9e2 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;
> @@ -4452,16 +4453,21 @@ 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.
> @@ -4491,7 +4497,7 @@ 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;
>  	}
> @@ -4524,7 +4530,7 @@ 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 8f597f9abdbe..3c3470f11648 100644
> --- a/fs/xfs/libxfs/xfs_bmap.h
> +++ b/fs/xfs/libxfs/xfs_bmap.h
> @@ -220,8 +220,7 @@ 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 4e4a4d7df5ac..8a1cd562a358 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -22,7 +22,7 @@
>   * structure owned by writepages passed to individual writepage calls
>   */
>  struct xfs_writepage_ctx {
> -	struct xfs_bmbt_irec    imap;
> +	struct iomap		iomap;
>  	int			fork;
>  	unsigned int		data_seq;
>  	unsigned int		cow_seq;
> @@ -279,7 +279,7 @@ xfs_end_ioend(
>  	 */
>  	if (ioend->io_fork == XFS_COW_FORK)
>  		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);
> @@ -303,8 +303,8 @@ xfs_ioend_can_merge(
>  		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))
> +	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
> +	    (next->io_type == IOMAP_UNWRITTEN))
>  		return false;
>  	if (ioend->io_offset + ioend->io_size != next->io_offset)
>  		return false;
> @@ -409,7 +409,7 @@ xfs_end_bio(
>  	unsigned long		flags;
>  
>  	if (ioend->io_fork == XFS_COW_FORK ||
> -	    ioend->io_state == XFS_EXT_UNWRITTEN ||
> +	    ioend->io_type == IOMAP_UNWRITTEN ||
>  	    ioend->io_append_trans != NULL) {
>  		spin_lock_irqsave(&ip->i_ioend_lock, flags);
>  		if (list_empty(&ip->i_ioend_list))
> @@ -429,10 +429,10 @@ static bool
>  xfs_imap_valid(
>  	struct xfs_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
> @@ -459,7 +459,7 @@ xfs_imap_valid(
>  
>  /*
>   * 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
> @@ -469,23 +469,23 @@ static int
>  xfs_convert_blocks(
>  	struct xfs_writepage_ctx *wpc,
>  	struct xfs_inode	*ip,
> -	xfs_fileoff_t		offset_fsb)
> +	loff_t			offset)
>  {
>  	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.
> +	 * Attempt to allocate whatever delalloc extent currently backs offset
> +	 * and put the result into wpc->imap.  Allocate in a loop because it may
				     ^^^^
			And put the result into wpc->iomap?

> +	 * take several attempts to allocate real blocks for a contiguous
> +	 * delalloc extent if free space is sufficiently fragmented.
>  	 */


Other than the comment nitpick above, patch looks good and you can add:

Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>

-- 
Carlos

Re: [PATCH 1/5] xfs: use a struct iomap in xfs_writepage_ctx

[Christoph Hellwig]

On Mon, Aug 05, 2019 at 02:38:26PM +0200, Carlos Maiolino wrote:
> > -	 * 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->imap.  Allocate in a loop because it may
> 				     ^^^^
> 			And put the result into wpc->iomap?

Yes.  Darrick, can you fix this up when applying?

[PATCH 2/5] xfs: turn io_append_trans into an io_private void pointer

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

In preparation for moving the ioend structure to common code we need
to get rid of the xfs-specific xfs_trans type.  Just make it a file
system private void pointer instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c |   26 +++++++++++++-------------
 fs/xfs/xfs_aops.h |    2 +-
 2 files changed, 14 insertions(+), 14 deletions(-)


diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8a1cd562a358..12f42922251c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -150,7 +150,7 @@ 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
@@ -217,7 +217,7 @@ xfs_setfilesize_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,
@@ -282,10 +282,10 @@ xfs_end_ioend(
 	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);
 	xfs_destroy_ioends(ioend, error);
 	memalloc_nofs_restore(nofs_flag);
@@ -318,13 +318,13 @@ xfs_ioend_can_merge(
  * as it is guaranteed to be clean.
  */
 static void
-xfs_ioend_merge_append_transactions(
+xfs_ioend_merge_private(
 	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;
+	if (!ioend->io_private) {
+		ioend->io_private = next->io_private;
+		next->io_private = NULL;
 	} else {
 		xfs_setfilesize_ioend(next, -ECANCELED);
 	}
@@ -346,8 +346,8 @@ xfs_ioend_try_merge(
 			break;
 		list_move_tail(&next->io_list, &ioend->io_list);
 		ioend->io_size += next->io_size;
-		if (next->io_append_trans)
-			xfs_ioend_merge_append_transactions(ioend, next);
+		if (next->io_private)
+			xfs_ioend_merge_private(ioend, next);
 	}
 }
 
@@ -410,7 +410,7 @@ xfs_end_bio(
 
 	if (ioend->io_fork == XFS_COW_FORK ||
 	    ioend->io_type == IOMAP_UNWRITTEN ||
-	    ioend->io_append_trans != NULL) {
+	    ioend->io_private) {
 		spin_lock_irqsave(&ip->i_ioend_lock, flags);
 		if (list_empty(&ip->i_ioend_list))
 			WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
@@ -675,7 +675,7 @@ xfs_submit_ioend(
 	    (ioend->io_fork == XFS_COW_FORK ||
 	     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);
@@ -724,7 +724,7 @@ xfs_alloc_ioend(
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
 	ioend->io_offset = offset;
-	ioend->io_append_trans = NULL;
+	ioend->io_private = NULL;
 	ioend->io_bio = bio;
 	return ioend;
 }
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 4af8ec0115cd..6a45d675dcba 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -18,7 +18,7 @@ struct xfs_ioend {
 	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 */
+	void			*io_private;	/* file system private data */
 	struct bio		*io_bio;	/* bio being built */
 	struct bio		io_inline_bio;	/* MUST BE LAST! */
 };

Re: [PATCH 2/5] xfs: turn io_append_trans into an io_private void pointer

[Carlos Maiolino]

On Mon, Jul 29, 2019 at 06:18:53PM -0700, Darrick J. Wong wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> In preparation for moving the ioend structure to common code we need
> to get rid of the xfs-specific xfs_trans type.  Just make it a file
> system private void pointer instead.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
>  fs/xfs/xfs_aops.c |   26 +++++++++++++-------------
>  fs/xfs/xfs_aops.h |    2 +-
>  2 files changed, 14 insertions(+), 14 deletions(-)
> 


Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>

> 
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 8a1cd562a358..12f42922251c 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -150,7 +150,7 @@ 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
> @@ -217,7 +217,7 @@ xfs_setfilesize_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,
> @@ -282,10 +282,10 @@ xfs_end_ioend(
>  	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);
>  	xfs_destroy_ioends(ioend, error);
>  	memalloc_nofs_restore(nofs_flag);
> @@ -318,13 +318,13 @@ xfs_ioend_can_merge(
>   * as it is guaranteed to be clean.
>   */
>  static void
> -xfs_ioend_merge_append_transactions(
> +xfs_ioend_merge_private(
>  	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;
> +	if (!ioend->io_private) {
> +		ioend->io_private = next->io_private;
> +		next->io_private = NULL;
>  	} else {
>  		xfs_setfilesize_ioend(next, -ECANCELED);
>  	}
> @@ -346,8 +346,8 @@ xfs_ioend_try_merge(
>  			break;
>  		list_move_tail(&next->io_list, &ioend->io_list);
>  		ioend->io_size += next->io_size;
> -		if (next->io_append_trans)
> -			xfs_ioend_merge_append_transactions(ioend, next);
> +		if (next->io_private)
> +			xfs_ioend_merge_private(ioend, next);
>  	}
>  }
>  
> @@ -410,7 +410,7 @@ xfs_end_bio(
>  
>  	if (ioend->io_fork == XFS_COW_FORK ||
>  	    ioend->io_type == IOMAP_UNWRITTEN ||
> -	    ioend->io_append_trans != NULL) {
> +	    ioend->io_private) {
>  		spin_lock_irqsave(&ip->i_ioend_lock, flags);
>  		if (list_empty(&ip->i_ioend_list))
>  			WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
> @@ -675,7 +675,7 @@ xfs_submit_ioend(
>  	    (ioend->io_fork == XFS_COW_FORK ||
>  	     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);
> @@ -724,7 +724,7 @@ xfs_alloc_ioend(
>  	ioend->io_inode = inode;
>  	ioend->io_size = 0;
>  	ioend->io_offset = offset;
> -	ioend->io_append_trans = NULL;
> +	ioend->io_private = NULL;
>  	ioend->io_bio = bio;
>  	return ioend;
>  }
> diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
> index 4af8ec0115cd..6a45d675dcba 100644
> --- a/fs/xfs/xfs_aops.h
> +++ b/fs/xfs/xfs_aops.h
> @@ -18,7 +18,7 @@ struct xfs_ioend {
>  	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 */
> +	void			*io_private;	/* file system private data */
>  	struct bio		*io_bio;	/* bio being built */
>  	struct bio		io_inline_bio;	/* MUST BE LAST! */
>  };
> 

-- 
Carlos

[PATCH 3/5] xfs: remove the fork fields in the writepage_ctx and ioend

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

In preparation for moving the writeback code to iomap.c, replace the
XFS-specific COW fork concept with the iomap IOMAP_F_SHARED flag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c |   42 ++++++++++++++++++++++--------------------
 fs/xfs/xfs_aops.h |    2 +-
 2 files changed, 23 insertions(+), 21 deletions(-)


diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 12f42922251c..93f1bf315585 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -23,7 +23,6 @@
  */
 struct xfs_writepage_ctx {
 	struct iomap		iomap;
-	int			fork;
 	unsigned int		data_seq;
 	unsigned int		cow_seq;
 	struct xfs_ioend	*ioend;
@@ -269,7 +268,7 @@ 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;
 	}
@@ -277,7 +276,7 @@ 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_type == IOMAP_UNWRITTEN)
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
@@ -301,7 +300,8 @@ xfs_ioend_can_merge(
 {
 	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))
+	if ((ioend->io_flags & IOMAP_F_SHARED) ^
+	    (next->io_flags & IOMAP_F_SHARED))
 		return false;
 	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
 	    (next->io_type == IOMAP_UNWRITTEN))
@@ -408,7 +408,7 @@ xfs_end_bio(
 	struct xfs_mount	*mp = ip->i_mount;
 	unsigned long		flags;
 
-	if (ioend->io_fork == XFS_COW_FORK ||
+	if ((ioend->io_flags & IOMAP_F_SHARED) ||
 	    ioend->io_type == IOMAP_UNWRITTEN ||
 	    ioend->io_private) {
 		spin_lock_irqsave(&ip->i_ioend_lock, flags);
@@ -439,7 +439,7 @@ xfs_imap_valid(
 	 * 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;
 
 	/*
@@ -469,6 +469,7 @@ static int
 xfs_convert_blocks(
 	struct xfs_writepage_ctx *wpc,
 	struct xfs_inode	*ip,
+	int			whichfork,
 	loff_t			offset)
 {
 	int			error;
@@ -480,8 +481,8 @@ xfs_convert_blocks(
 	 * delalloc extent if free space is sufficiently fragmented.
 	 */
 	do {
-		error = xfs_bmapi_convert_delalloc(ip, wpc->fork, offset,
-				&wpc->iomap, wpc->fork == XFS_COW_FORK ?
+		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
+				&wpc->iomap, whichfork == XFS_COW_FORK ?
 					&wpc->cow_seq : &wpc->data_seq);
 		if (error)
 			return error;
@@ -502,6 +503,7 @@ 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;
@@ -550,7 +552,7 @@ xfs_map_blocks(
 		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;
 	}
 
@@ -573,8 +575,6 @@ xfs_map_blocks(
 	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;
@@ -599,10 +599,10 @@ xfs_map_blocks(
 		goto allocate_blocks;
 
 	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
-	trace_xfs_map_blocks_found(ip, offset, count, wpc->fork, &imap);
+	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_convert_blocks(wpc, ip, offset);
+	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
 	if (error) {
 		/*
 		 * If we failed to find the extent in the COW fork we might have
@@ -611,7 +611,8 @@ xfs_map_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 && (wpc->iomap.flags & IOMAP_F_SHARED) &&
+		    !retries++)
 			goto retry;
 		ASSERT(error != -EAGAIN);
 		return error;
@@ -622,7 +623,7 @@ xfs_map_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) {
+	if (!(wpc->iomap.flags & IOMAP_F_SHARED) && cow_fsb != NULLFILEOFF) {
 		loff_t		cow_offset = XFS_FSB_TO_B(mp, cow_fsb);
 
 		if (cow_offset < wpc->iomap.offset + wpc->iomap.length)
@@ -631,7 +632,7 @@ xfs_map_blocks(
 
 	ASSERT(wpc->iomap.offset <= offset);
 	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
-	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->fork, &imap);
+	trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap);
 	return 0;
 }
 
@@ -665,14 +666,14 @@ 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_flags & IOMAP_F_SHARED) ||
 	     ioend->io_type != IOMAP_UNWRITTEN) &&
 	    xfs_ioend_is_append(ioend) &&
 	    !ioend->io_private)
@@ -719,8 +720,8 @@ xfs_alloc_ioend(
 
 	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
 	INIT_LIST_HEAD(&ioend->io_list);
-	ioend->io_fork = wpc->fork;
 	ioend->io_type = wpc->iomap.type;
+	ioend->io_flags = wpc->iomap.flags;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
 	ioend->io_offset = offset;
@@ -774,7 +775,8 @@ xfs_add_to_ioend(
 	bool			merged, same_page = false;
 
 	if (!wpc->ioend ||
-	    wpc->fork != wpc->ioend->io_fork ||
+	    (wpc->iomap.flags & IOMAP_F_SHARED) !=
+	    (wpc->ioend->io_flags & IOMAP_F_SHARED) ||
 	    wpc->iomap.type != wpc->ioend->io_type ||
 	    sector != bio_end_sector(wpc->ioend->io_bio) ||
 	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 6a45d675dcba..4a0226cdad4f 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -13,8 +13,8 @@ extern struct bio_set xfs_ioend_bioset;
  */
 struct xfs_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
-	int			io_fork;	/* inode fork written back */
 	u16			io_type;
+	u16			io_flags;	/* IOMAP_F_* */
 	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 */

Re: [PATCH 3/5] xfs: remove the fork fields in the writepage_ctx and ioend

[Carlos Maiolino]

On Mon, Jul 29, 2019 at 06:19:00PM -0700, Darrick J. Wong wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> In preparation for moving the writeback code to iomap.c, replace the
> XFS-specific COW fork concept with the iomap IOMAP_F_SHARED flag.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>

> ---
>  fs/xfs/xfs_aops.c |   42 ++++++++++++++++++++++--------------------
>  fs/xfs/xfs_aops.h |    2 +-
>  2 files changed, 23 insertions(+), 21 deletions(-)
> 
> 
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 12f42922251c..93f1bf315585 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -23,7 +23,6 @@
>   */
>  struct xfs_writepage_ctx {
>  	struct iomap		iomap;
> -	int			fork;
>  	unsigned int		data_seq;
>  	unsigned int		cow_seq;
>  	struct xfs_ioend	*ioend;
> @@ -269,7 +268,7 @@ 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;
>  	}
> @@ -277,7 +276,7 @@ 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_type == IOMAP_UNWRITTEN)
>  		error = xfs_iomap_write_unwritten(ip, offset, size, false);
> @@ -301,7 +300,8 @@ xfs_ioend_can_merge(
>  {
>  	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))
> +	if ((ioend->io_flags & IOMAP_F_SHARED) ^
> +	    (next->io_flags & IOMAP_F_SHARED))
>  		return false;
>  	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
>  	    (next->io_type == IOMAP_UNWRITTEN))
> @@ -408,7 +408,7 @@ xfs_end_bio(
>  	struct xfs_mount	*mp = ip->i_mount;
>  	unsigned long		flags;
>  
> -	if (ioend->io_fork == XFS_COW_FORK ||
> +	if ((ioend->io_flags & IOMAP_F_SHARED) ||
>  	    ioend->io_type == IOMAP_UNWRITTEN ||
>  	    ioend->io_private) {
>  		spin_lock_irqsave(&ip->i_ioend_lock, flags);
> @@ -439,7 +439,7 @@ xfs_imap_valid(
>  	 * 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;
>  
>  	/*
> @@ -469,6 +469,7 @@ static int
>  xfs_convert_blocks(
>  	struct xfs_writepage_ctx *wpc,
>  	struct xfs_inode	*ip,
> +	int			whichfork,
>  	loff_t			offset)
>  {
>  	int			error;
> @@ -480,8 +481,8 @@ xfs_convert_blocks(
>  	 * delalloc extent if free space is sufficiently fragmented.
>  	 */
>  	do {
> -		error = xfs_bmapi_convert_delalloc(ip, wpc->fork, offset,
> -				&wpc->iomap, wpc->fork == XFS_COW_FORK ?
> +		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
> +				&wpc->iomap, whichfork == XFS_COW_FORK ?
>  					&wpc->cow_seq : &wpc->data_seq);
>  		if (error)
>  			return error;
> @@ -502,6 +503,7 @@ 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;
> @@ -550,7 +552,7 @@ xfs_map_blocks(
>  		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;
>  	}
>  
> @@ -573,8 +575,6 @@ xfs_map_blocks(
>  	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;
> @@ -599,10 +599,10 @@ xfs_map_blocks(
>  		goto allocate_blocks;
>  
>  	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
> -	trace_xfs_map_blocks_found(ip, offset, count, wpc->fork, &imap);
> +	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
>  	return 0;
>  allocate_blocks:
> -	error = xfs_convert_blocks(wpc, ip, offset);
> +	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
>  	if (error) {
>  		/*
>  		 * If we failed to find the extent in the COW fork we might have
> @@ -611,7 +611,8 @@ xfs_map_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 && (wpc->iomap.flags & IOMAP_F_SHARED) &&
> +		    !retries++)
>  			goto retry;
>  		ASSERT(error != -EAGAIN);
>  		return error;
> @@ -622,7 +623,7 @@ xfs_map_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) {
> +	if (!(wpc->iomap.flags & IOMAP_F_SHARED) && cow_fsb != NULLFILEOFF) {
>  		loff_t		cow_offset = XFS_FSB_TO_B(mp, cow_fsb);
>  
>  		if (cow_offset < wpc->iomap.offset + wpc->iomap.length)
> @@ -631,7 +632,7 @@ xfs_map_blocks(
>  
>  	ASSERT(wpc->iomap.offset <= offset);
>  	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
> -	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->fork, &imap);
> +	trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap);
>  	return 0;
>  }
>  
> @@ -665,14 +666,14 @@ 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_flags & IOMAP_F_SHARED) ||
>  	     ioend->io_type != IOMAP_UNWRITTEN) &&
>  	    xfs_ioend_is_append(ioend) &&
>  	    !ioend->io_private)
> @@ -719,8 +720,8 @@ xfs_alloc_ioend(
>  
>  	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
>  	INIT_LIST_HEAD(&ioend->io_list);
> -	ioend->io_fork = wpc->fork;
>  	ioend->io_type = wpc->iomap.type;
> +	ioend->io_flags = wpc->iomap.flags;
>  	ioend->io_inode = inode;
>  	ioend->io_size = 0;
>  	ioend->io_offset = offset;
> @@ -774,7 +775,8 @@ xfs_add_to_ioend(
>  	bool			merged, same_page = false;
>  
>  	if (!wpc->ioend ||
> -	    wpc->fork != wpc->ioend->io_fork ||
> +	    (wpc->iomap.flags & IOMAP_F_SHARED) !=
> +	    (wpc->ioend->io_flags & IOMAP_F_SHARED) ||
>  	    wpc->iomap.type != wpc->ioend->io_type ||
>  	    sector != bio_end_sector(wpc->ioend->io_bio) ||
>  	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
> diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
> index 6a45d675dcba..4a0226cdad4f 100644
> --- a/fs/xfs/xfs_aops.h
> +++ b/fs/xfs/xfs_aops.h
> @@ -13,8 +13,8 @@ extern struct bio_set xfs_ioend_bioset;
>   */
>  struct xfs_ioend {
>  	struct list_head	io_list;	/* next ioend in chain */
> -	int			io_fork;	/* inode fork written back */
>  	u16			io_type;
> +	u16			io_flags;	/* IOMAP_F_* */
>  	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 */
> 

-- 
Carlos

[PATCH 4/5] xfs: convert the xfs writeback code to iomap writeback

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Converts the xfs writeback code to use iomap writeback.  A new structure
with three methods is added as the abstraction from the generic
writeback code to the file system.  These methods are used to map
blocks, submit an ioend, and cancel a page that encountered an error
before it was added to an ioend.

Signed-off-by: Christoph Hellwig <hch@lst.de>
[darrick: reduce this patch only to convert the xfs writeback code]
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c  |  649 +++++-----------------------------------------------
 fs/xfs/xfs_aops.h  |   17 -
 fs/xfs/xfs_super.c |   11 -
 fs/xfs/xfs_trace.h |   65 -----
 4 files changed, 60 insertions(+), 682 deletions(-)


diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 93f1bf315585..5f8939f6637a 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -18,16 +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 iomap		iomap;
+	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)
@@ -54,84 +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);
-	}
-}
-
-static void
-xfs_destroy_ioends(
-	struct xfs_ioend	*ioend,
-	int			error)
-{
-	struct list_head	tmp;
-
-	list_replace_init(&ioend->io_list, &tmp);
-	xfs_destroy_ioend(ioend, error);
-	while ((ioend = list_pop_entry(&tmp, struct xfs_ioend, io_list)))
-		xfs_destroy_ioend(ioend, error);
-}
-
 /*
  * 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;
@@ -139,7 +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;
@@ -212,7 +140,7 @@ 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);
@@ -240,7 +168,7 @@ xfs_setfilesize_ioend(
  */
 STATIC void
 xfs_end_ioend(
-	struct xfs_ioend	*ioend)
+	struct iomap_ioend	*ioend)
 {
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	xfs_off_t		offset = ioend->io_offset;
@@ -286,31 +214,10 @@ xfs_end_ioend(
 done:
 	if (ioend->io_private)
 		error = xfs_setfilesize_ioend(ioend, error);
-	xfs_destroy_ioends(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_flags & IOMAP_F_SHARED) ^
-	    (next->io_flags & IOMAP_F_SHARED))
-		return false;
-	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
-	    (next->io_type == IOMAP_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
@@ -319,8 +226,8 @@ xfs_ioend_can_merge(
  */
 static void
 xfs_ioend_merge_private(
-	struct xfs_ioend	*ioend,
-	struct xfs_ioend	*next)
+	struct iomap_ioend	*ioend,
+	struct iomap_ioend	*next)
 {
 	if (!ioend->io_private) {
 		ioend->io_private = next->io_private;
@@ -330,53 +237,6 @@ xfs_ioend_merge_private(
 	}
 }
 
-/* Try to merge adjacent completions. */
-STATIC void
-xfs_ioend_try_merge(
-	struct xfs_ioend	*ioend,
-	struct list_head	*more_ioends)
-{
-	struct xfs_ioend	*next;
-
-	INIT_LIST_HEAD(&ioend->io_list);
-
-	while ((next = list_first_entry_or_null(more_ioends, struct xfs_ioend,
-			io_list))) {
-		if (!xfs_ioend_can_merge(ioend, next))
-			break;
-		list_move_tail(&next->io_list, &ioend->io_list);
-		ioend->io_size += next->io_size;
-		if (next->io_private)
-			xfs_ioend_merge_private(ioend, next);
-	}
-}
-
-/* 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;
-}
-
-static void
-xfs_sort_ioends(
-	struct list_head	*ioend_list)
-{
-	list_sort(NULL, ioend_list, xfs_ioend_compare);
-}
-
 /* Finish all pending io completions. */
 void
 xfs_end_io(
@@ -384,7 +244,7 @@ xfs_end_io(
 {
 	struct xfs_inode	*ip =
 		container_of(work, struct xfs_inode, i_ioend_work);
-	struct xfs_ioend	*ioend;
+	struct iomap_ioend	*ioend;
 	struct list_head	tmp;
 	unsigned long		flags;
 
@@ -392,9 +252,9 @@ xfs_end_io(
 	list_replace_init(&ip->i_ioend_list, &tmp);
 	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
 
-	xfs_sort_ioends(&tmp);
-	while ((ioend = list_pop_entry(&tmp, struct xfs_ioend, io_list))) {
-		xfs_ioend_try_merge(ioend, &tmp);
+	iomap_sort_ioends(&tmp);
+	while ((ioend = list_pop_entry(&tmp, struct iomap_ioend, io_list))) {
+		iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private);
 		xfs_end_ioend(ioend);
 	}
 }
@@ -403,22 +263,16 @@ 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_flags & IOMAP_F_SHARED) ||
-	    ioend->io_type == IOMAP_UNWRITTEN ||
-	    ioend->io_private) {
-		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));
+	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);
 }
 
 /*
@@ -427,7 +281,7 @@ xfs_end_bio(
  */
 static bool
 xfs_imap_valid(
-	struct xfs_writepage_ctx	*wpc,
+	struct iomap_writepage_ctx	*wpc,
 	struct xfs_inode		*ip,
 	loff_t				offset)
 {
@@ -449,10 +303,10 @@ 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;
 }
@@ -467,12 +321,18 @@ xfs_imap_valid(
  */
 static int
 xfs_convert_blocks(
-	struct xfs_writepage_ctx *wpc,
+	struct iomap_writepage_ctx *wpc,
 	struct xfs_inode	*ip,
 	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
@@ -482,8 +342,7 @@ xfs_convert_blocks(
 	 */
 	do {
 		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
-				&wpc->iomap, whichfork == XFS_COW_FORK ?
-					&wpc->cow_seq : &wpc->data_seq);
+				&wpc->iomap, seq);
 		if (error)
 			return error;
 	} while (wpc->iomap.offset + wpc->iomap.length <= offset);
@@ -491,9 +350,9 @@ xfs_convert_blocks(
 	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)
 {
@@ -549,7 +408,7 @@ xfs_map_blocks(
 	    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);
 
 		whichfork = XFS_COW_FORK;
@@ -572,7 +431,7 @@ xfs_map_blocks(
 	 */
 	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);
 
 	/* landed in a hole or beyond EOF? */
@@ -636,24 +495,9 @@ xfs_map_blocks(
 	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
+static int
 xfs_submit_ioend(
-	struct writeback_control *wbc,
-	struct xfs_ioend	*ioend,
+	struct iomap_ioend	*ioend,
 	int			status)
 {
 	unsigned int		nofs_flag;
@@ -680,135 +524,11 @@ xfs_submit_ioend(
 		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,
-	struct xfs_writepage_ctx *wpc,
-	xfs_off_t		offset,
-	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, wpc->iomap.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 = wpc->iomap.type;
-	ioend->io_flags = wpc->iomap.flags;
-	ioend->io_inode = inode;
-	ioend->io_size = 0;
-	ioend->io_offset = offset;
-	ioend->io_private = 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)
-{
-	sector_t		sector = iomap_sector(&wpc->iomap, offset);
-	unsigned		len = i_blocksize(inode);
-	unsigned		poff = offset & (PAGE_SIZE - 1);
-	bool			merged, same_page = false;
-
-	if (!wpc->ioend ||
-	    (wpc->iomap.flags & IOMAP_F_SHARED) !=
-	    (wpc->ioend->io_flags & IOMAP_F_SHARED) ||
-	    wpc->iomap.type != wpc->ioend->io_type ||
-	    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, offset, 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 ((ioend->io_flags & IOMAP_F_SHARED) ||
+	    ioend->io_type == IOMAP_UNWRITTEN ||
+	    ioend->io_private)
+		ioend->io_bio->bi_end_io = xfs_end_bio;
+	return status;
 }
 
 /*
@@ -822,8 +542,8 @@ 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;
@@ -845,246 +565,14 @@ 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);
-}
-
-/*
- * 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->iomap.type == IOMAP_HOLE)
-			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;
+	iomap_invalidatepage(page, 0, PAGE_SIZE);
 }
 
-/*
- * 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,
+	.submit_ioend		= xfs_submit_ioend,
+	.discard_page		= xfs_discard_page,
+};
 
 STATIC int
 xfs_vm_writepage(
@@ -1092,12 +580,8 @@ 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
@@ -1106,13 +590,9 @@ 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
@@ -1125,15 +605,6 @@ 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,
@@ -1162,7 +633,6 @@ xfs_vm_readpage(
 	struct file		*unused,
 	struct page		*page)
 {
-	trace_xfs_vm_readpage(page->mapping->host, 1);
 	return iomap_readpage(page, &xfs_iomap_ops);
 }
 
@@ -1173,7 +643,6 @@ 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);
 }
 
@@ -1193,8 +662,8 @@ 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 4a0226cdad4f..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 */
-	u16			io_type;
-	u16			io_flags;	/* IOMAP_F_* */
-	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 */
-	void			*io_private;	/* file system private data */
-	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_super.c b/fs/xfs/xfs_super.c
index f9450235533c..659540cc2fbe 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
@@ -1850,15 +1849,10 @@ 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),
@@ -1993,8 +1987,6 @@ 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;
 }
@@ -2025,7 +2017,6 @@ 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 8094b1920eef..d1d0ec1c44ad 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1153,71 +1153,6 @@ 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),

Re: [PATCH 4/5] xfs: convert the xfs writeback code to iomap writeback

[Carlos Maiolino]

On Mon, Jul 29, 2019 at 06:19:06PM -0700, Darrick J. Wong wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> Converts the xfs writeback code to use iomap writeback.  A new structure
> with three methods is added as the abstraction from the generic
> writeback code to the file system.  These methods are used to map
> blocks, submit an ioend, and cancel a page that encountered an error
> before it was added to an ioend.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> [darrick: reduce this patch only to convert the xfs writeback code]
> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>


Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>

> ---
>  fs/xfs/xfs_aops.c  |  649 +++++-----------------------------------------------
>  fs/xfs/xfs_aops.h  |   17 -
>  fs/xfs/xfs_super.c |   11 -
>  fs/xfs/xfs_trace.h |   65 -----
>  4 files changed, 60 insertions(+), 682 deletions(-)
> 
> 
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 93f1bf315585..5f8939f6637a 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -18,16 +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 iomap		iomap;
> +	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)
> @@ -54,84 +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);
> -	}
> -}
> -
> -static void
> -xfs_destroy_ioends(
> -	struct xfs_ioend	*ioend,
> -	int			error)
> -{
> -	struct list_head	tmp;
> -
> -	list_replace_init(&ioend->io_list, &tmp);
> -	xfs_destroy_ioend(ioend, error);
> -	while ((ioend = list_pop_entry(&tmp, struct xfs_ioend, io_list)))
> -		xfs_destroy_ioend(ioend, error);
> -}
> -
>  /*
>   * 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;
> @@ -139,7 +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;
> @@ -212,7 +140,7 @@ 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);
> @@ -240,7 +168,7 @@ xfs_setfilesize_ioend(
>   */
>  STATIC void
>  xfs_end_ioend(
> -	struct xfs_ioend	*ioend)
> +	struct iomap_ioend	*ioend)
>  {
>  	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
>  	xfs_off_t		offset = ioend->io_offset;
> @@ -286,31 +214,10 @@ xfs_end_ioend(
>  done:
>  	if (ioend->io_private)
>  		error = xfs_setfilesize_ioend(ioend, error);
> -	xfs_destroy_ioends(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_flags & IOMAP_F_SHARED) ^
> -	    (next->io_flags & IOMAP_F_SHARED))
> -		return false;
> -	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
> -	    (next->io_type == IOMAP_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
> @@ -319,8 +226,8 @@ xfs_ioend_can_merge(
>   */
>  static void
>  xfs_ioend_merge_private(
> -	struct xfs_ioend	*ioend,
> -	struct xfs_ioend	*next)
> +	struct iomap_ioend	*ioend,
> +	struct iomap_ioend	*next)
>  {
>  	if (!ioend->io_private) {
>  		ioend->io_private = next->io_private;
> @@ -330,53 +237,6 @@ xfs_ioend_merge_private(
>  	}
>  }
>  
> -/* Try to merge adjacent completions. */
> -STATIC void
> -xfs_ioend_try_merge(
> -	struct xfs_ioend	*ioend,
> -	struct list_head	*more_ioends)
> -{
> -	struct xfs_ioend	*next;
> -
> -	INIT_LIST_HEAD(&ioend->io_list);
> -
> -	while ((next = list_first_entry_or_null(more_ioends, struct xfs_ioend,
> -			io_list))) {
> -		if (!xfs_ioend_can_merge(ioend, next))
> -			break;
> -		list_move_tail(&next->io_list, &ioend->io_list);
> -		ioend->io_size += next->io_size;
> -		if (next->io_private)
> -			xfs_ioend_merge_private(ioend, next);
> -	}
> -}
> -
> -/* 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;
> -}
> -
> -static void
> -xfs_sort_ioends(
> -	struct list_head	*ioend_list)
> -{
> -	list_sort(NULL, ioend_list, xfs_ioend_compare);
> -}
> -
>  /* Finish all pending io completions. */
>  void
>  xfs_end_io(
> @@ -384,7 +244,7 @@ xfs_end_io(
>  {
>  	struct xfs_inode	*ip =
>  		container_of(work, struct xfs_inode, i_ioend_work);
> -	struct xfs_ioend	*ioend;
> +	struct iomap_ioend	*ioend;
>  	struct list_head	tmp;
>  	unsigned long		flags;
>  
> @@ -392,9 +252,9 @@ xfs_end_io(
>  	list_replace_init(&ip->i_ioend_list, &tmp);
>  	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
>  
> -	xfs_sort_ioends(&tmp);
> -	while ((ioend = list_pop_entry(&tmp, struct xfs_ioend, io_list))) {
> -		xfs_ioend_try_merge(ioend, &tmp);
> +	iomap_sort_ioends(&tmp);
> +	while ((ioend = list_pop_entry(&tmp, struct iomap_ioend, io_list))) {
> +		iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private);
>  		xfs_end_ioend(ioend);
>  	}
>  }
> @@ -403,22 +263,16 @@ 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_flags & IOMAP_F_SHARED) ||
> -	    ioend->io_type == IOMAP_UNWRITTEN ||
> -	    ioend->io_private) {
> -		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));
> +	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);
>  }
>  
>  /*
> @@ -427,7 +281,7 @@ xfs_end_bio(
>   */
>  static bool
>  xfs_imap_valid(
> -	struct xfs_writepage_ctx	*wpc,
> +	struct iomap_writepage_ctx	*wpc,
>  	struct xfs_inode		*ip,
>  	loff_t				offset)
>  {
> @@ -449,10 +303,10 @@ 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;
>  }
> @@ -467,12 +321,18 @@ xfs_imap_valid(
>   */
>  static int
>  xfs_convert_blocks(
> -	struct xfs_writepage_ctx *wpc,
> +	struct iomap_writepage_ctx *wpc,
>  	struct xfs_inode	*ip,
>  	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
> @@ -482,8 +342,7 @@ xfs_convert_blocks(
>  	 */
>  	do {
>  		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
> -				&wpc->iomap, whichfork == XFS_COW_FORK ?
> -					&wpc->cow_seq : &wpc->data_seq);
> +				&wpc->iomap, seq);
>  		if (error)
>  			return error;
>  	} while (wpc->iomap.offset + wpc->iomap.length <= offset);
> @@ -491,9 +350,9 @@ xfs_convert_blocks(
>  	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)
>  {
> @@ -549,7 +408,7 @@ xfs_map_blocks(
>  	    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);
>  
>  		whichfork = XFS_COW_FORK;
> @@ -572,7 +431,7 @@ xfs_map_blocks(
>  	 */
>  	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);
>  
>  	/* landed in a hole or beyond EOF? */
> @@ -636,24 +495,9 @@ xfs_map_blocks(
>  	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
> +static int
>  xfs_submit_ioend(
> -	struct writeback_control *wbc,
> -	struct xfs_ioend	*ioend,
> +	struct iomap_ioend	*ioend,
>  	int			status)
>  {
>  	unsigned int		nofs_flag;
> @@ -680,135 +524,11 @@ xfs_submit_ioend(
>  		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,
> -	struct xfs_writepage_ctx *wpc,
> -	xfs_off_t		offset,
> -	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, wpc->iomap.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 = wpc->iomap.type;
> -	ioend->io_flags = wpc->iomap.flags;
> -	ioend->io_inode = inode;
> -	ioend->io_size = 0;
> -	ioend->io_offset = offset;
> -	ioend->io_private = 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)
> -{
> -	sector_t		sector = iomap_sector(&wpc->iomap, offset);
> -	unsigned		len = i_blocksize(inode);
> -	unsigned		poff = offset & (PAGE_SIZE - 1);
> -	bool			merged, same_page = false;
> -
> -	if (!wpc->ioend ||
> -	    (wpc->iomap.flags & IOMAP_F_SHARED) !=
> -	    (wpc->ioend->io_flags & IOMAP_F_SHARED) ||
> -	    wpc->iomap.type != wpc->ioend->io_type ||
> -	    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, offset, 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 ((ioend->io_flags & IOMAP_F_SHARED) ||
> +	    ioend->io_type == IOMAP_UNWRITTEN ||
> +	    ioend->io_private)
> +		ioend->io_bio->bi_end_io = xfs_end_bio;
> +	return status;
>  }
>  
>  /*
> @@ -822,8 +542,8 @@ 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;
> @@ -845,246 +565,14 @@ 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);
> -}
> -
> -/*
> - * 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->iomap.type == IOMAP_HOLE)
> -			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;
> +	iomap_invalidatepage(page, 0, PAGE_SIZE);
>  }
>  
> -/*
> - * 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,
> +	.submit_ioend		= xfs_submit_ioend,
> +	.discard_page		= xfs_discard_page,
> +};
>  
>  STATIC int
>  xfs_vm_writepage(
> @@ -1092,12 +580,8 @@ 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
> @@ -1106,13 +590,9 @@ 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
> @@ -1125,15 +605,6 @@ 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,
> @@ -1162,7 +633,6 @@ xfs_vm_readpage(
>  	struct file		*unused,
>  	struct page		*page)
>  {
> -	trace_xfs_vm_readpage(page->mapping->host, 1);
>  	return iomap_readpage(page, &xfs_iomap_ops);
>  }
>  
> @@ -1173,7 +643,6 @@ 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);
>  }
>  
> @@ -1193,8 +662,8 @@ 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 4a0226cdad4f..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 */
> -	u16			io_type;
> -	u16			io_flags;	/* IOMAP_F_* */
> -	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 */
> -	void			*io_private;	/* file system private data */
> -	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_super.c b/fs/xfs/xfs_super.c
> index f9450235533c..659540cc2fbe 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
> @@ -1850,15 +1849,10 @@ 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),
> @@ -1993,8 +1987,6 @@ 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;
>  }
> @@ -2025,7 +2017,6 @@ 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 8094b1920eef..d1d0ec1c44ad 100644
> --- a/fs/xfs/xfs_trace.h
> +++ b/fs/xfs/xfs_trace.h
> @@ -1153,71 +1153,6 @@ 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),
> 

-- 
Carlos

[PATCH 5/5] iomap: move struct iomap_page out of iomap.h

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Now that all the writepage code is in the iomap code there is no
need to keep this structure public.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap/buffered-io.c |   17 +++++++++++++++++
 include/linux/iomap.h  |   17 -----------------
 2 files changed, 17 insertions(+), 17 deletions(-)


diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 1a7570c441c8..ba0511131868 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -23,6 +23,23 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/iomap.h>
 
+/*
+ * Structure allocated for each page when block size < PAGE_SIZE to track
+ * sub-page uptodate status and I/O completions.
+ */
+struct iomap_page {
+	atomic_t		read_count;
+	atomic_t		write_count;
+	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
+};
+
+static inline struct iomap_page *to_iomap_page(struct page *page)
+{
+	if (page_has_private(page))
+		return (struct iomap_page *)page_private(page);
+	return NULL;
+}
+
 static struct bio_set iomap_ioend_bioset;
 
 static struct iomap_page *
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 834d3923e2f2..38464b8f34b9 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -134,23 +134,6 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
 		unsigned flags, const struct iomap_ops *ops, void *data,
 		iomap_actor_t actor);
 
-/*
- * Structure allocate for each page when block size < PAGE_SIZE to track
- * sub-page uptodate status and I/O completions.
- */
-struct iomap_page {
-	atomic_t		read_count;
-	atomic_t		write_count;
-	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
-};
-
-static inline struct iomap_page *to_iomap_page(struct page *page)
-{
-	if (page_has_private(page))
-		return (struct iomap_page *)page_private(page);
-	return NULL;
-}
-
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
 int iomap_readpage(struct page *page, const struct iomap_ops *ops);

Re: [PATCH 5/5] iomap: move struct iomap_page out of iomap.h

[Carlos Maiolino]

On Mon, Jul 29, 2019 at 06:19:13PM -0700, Darrick J. Wong wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> Now that all the writepage code is in the iomap code there is no
> need to keep this structure public.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---

Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>


>  fs/iomap/buffered-io.c |   17 +++++++++++++++++
>  include/linux/iomap.h  |   17 -----------------
>  2 files changed, 17 insertions(+), 17 deletions(-)
> 
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 1a7570c441c8..ba0511131868 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -23,6 +23,23 @@
>  #define CREATE_TRACE_POINTS
>  #include <trace/events/iomap.h>
>  
> +/*
> + * Structure allocated for each page when block size < PAGE_SIZE to track
> + * sub-page uptodate status and I/O completions.
> + */
> +struct iomap_page {
> +	atomic_t		read_count;
> +	atomic_t		write_count;
> +	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
> +};
> +
> +static inline struct iomap_page *to_iomap_page(struct page *page)
> +{
> +	if (page_has_private(page))
> +		return (struct iomap_page *)page_private(page);
> +	return NULL;
> +}
> +
>  static struct bio_set iomap_ioend_bioset;
>  
>  static struct iomap_page *
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 834d3923e2f2..38464b8f34b9 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -134,23 +134,6 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
>  		unsigned flags, const struct iomap_ops *ops, void *data,
>  		iomap_actor_t actor);
>  
> -/*
> - * Structure allocate for each page when block size < PAGE_SIZE to track
> - * sub-page uptodate status and I/O completions.
> - */
> -struct iomap_page {
> -	atomic_t		read_count;
> -	atomic_t		write_count;
> -	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
> -};
> -
> -static inline struct iomap_page *to_iomap_page(struct page *page)
> -{
> -	if (page_has_private(page))
> -		return (struct iomap_page *)page_private(page);
> -	return NULL;
> -}
> -
>  ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
>  		const struct iomap_ops *ops);
>  int iomap_readpage(struct page *page, const struct iomap_ops *ops);
> 

-- 
Carlos

xfs: use the iomap writeback code v2

[Christoph Hellwig]

This series cleans up the xfs writepage code and then lifts it to
fs/iomap/ so that it could be use by other file systems.  I've been
wanting to [do] this for a while so that I could eventually convert gfs2
over to it, but I never got to it.  Now Damien has a new zonefs file
system for semi-raw access to zoned block devices that would like to use
the iomap code instead of reinventing it, so I finally had to do the
work.

Changes since v1:
 - rebased to latest iomap-for-next
 - fix up a comment to use iomap instead of imap
 - update a commit log

[PATCH 3/5] xfs: remove the fork fields in the writepage_ctx and ioend

[Christoph Hellwig]

In preparation for moving the writeback code to iomap.c, replace the
XFS-specific COW fork concept with the iomap IOMAP_F_SHARED flag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 42 ++++++++++++++++++++++--------------------
 fs/xfs/xfs_aops.h |  2 +-
 2 files changed, 23 insertions(+), 21 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b9255ea91a5c..236dc8371d97 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -23,7 +23,6 @@
  */
 struct xfs_writepage_ctx {
 	struct iomap		iomap;
-	int			fork;
 	unsigned int		data_seq;
 	unsigned int		cow_seq;
 	struct xfs_ioend	*ioend;
@@ -269,7 +268,7 @@ 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;
 	}
@@ -277,7 +276,7 @@ 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_type == IOMAP_UNWRITTEN)
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
@@ -301,7 +300,8 @@ xfs_ioend_can_merge(
 {
 	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))
+	if ((ioend->io_flags & IOMAP_F_SHARED) ^
+	    (next->io_flags & IOMAP_F_SHARED))
 		return false;
 	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
 	    (next->io_type == IOMAP_UNWRITTEN))
@@ -408,7 +408,7 @@ xfs_end_bio(
 	struct xfs_mount	*mp = ip->i_mount;
 	unsigned long		flags;
 
-	if (ioend->io_fork == XFS_COW_FORK ||
+	if ((ioend->io_flags & IOMAP_F_SHARED) ||
 	    ioend->io_type == IOMAP_UNWRITTEN ||
 	    ioend->io_private) {
 		spin_lock_irqsave(&ip->i_ioend_lock, flags);
@@ -439,7 +439,7 @@ xfs_imap_valid(
 	 * 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;
 
 	/*
@@ -469,6 +469,7 @@ static int
 xfs_convert_blocks(
 	struct xfs_writepage_ctx *wpc,
 	struct xfs_inode	*ip,
+	int			whichfork,
 	loff_t			offset)
 {
 	int			error;
@@ -480,8 +481,8 @@ xfs_convert_blocks(
 	 * delalloc extent if free space is sufficiently fragmented.
 	 */
 	do {
-		error = xfs_bmapi_convert_delalloc(ip, wpc->fork, offset,
-				&wpc->iomap, wpc->fork == XFS_COW_FORK ?
+		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
+				&wpc->iomap, whichfork == XFS_COW_FORK ?
 					&wpc->cow_seq : &wpc->data_seq);
 		if (error)
 			return error;
@@ -502,6 +503,7 @@ 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;
@@ -550,7 +552,7 @@ xfs_map_blocks(
 		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;
 	}
 
@@ -573,8 +575,6 @@ xfs_map_blocks(
 	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;
@@ -599,10 +599,10 @@ xfs_map_blocks(
 		goto allocate_blocks;
 
 	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
-	trace_xfs_map_blocks_found(ip, offset, count, wpc->fork, &imap);
+	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_convert_blocks(wpc, ip, offset);
+	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
 	if (error) {
 		/*
 		 * If we failed to find the extent in the COW fork we might have
@@ -611,7 +611,8 @@ xfs_map_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 && (wpc->iomap.flags & IOMAP_F_SHARED) &&
+		    !retries++)
 			goto retry;
 		ASSERT(error != -EAGAIN);
 		return error;
@@ -622,7 +623,7 @@ xfs_map_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) {
+	if (!(wpc->iomap.flags & IOMAP_F_SHARED) && cow_fsb != NULLFILEOFF) {
 		loff_t		cow_offset = XFS_FSB_TO_B(mp, cow_fsb);
 
 		if (cow_offset < wpc->iomap.offset + wpc->iomap.length)
@@ -631,7 +632,7 @@ xfs_map_blocks(
 
 	ASSERT(wpc->iomap.offset <= offset);
 	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
-	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->fork, &imap);
+	trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap);
 	return 0;
 }
 
@@ -665,14 +666,14 @@ 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_flags & IOMAP_F_SHARED) ||
 	     ioend->io_type != IOMAP_UNWRITTEN) &&
 	    xfs_ioend_is_append(ioend) &&
 	    !ioend->io_private)
@@ -719,8 +720,8 @@ xfs_alloc_ioend(
 
 	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
 	INIT_LIST_HEAD(&ioend->io_list);
-	ioend->io_fork = wpc->fork;
 	ioend->io_type = wpc->iomap.type;
+	ioend->io_flags = wpc->iomap.flags;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
 	ioend->io_offset = offset;
@@ -774,7 +775,8 @@ xfs_add_to_ioend(
 	bool			merged, same_page = false;
 
 	if (!wpc->ioend ||
-	    wpc->fork != wpc->ioend->io_fork ||
+	    (wpc->iomap.flags & IOMAP_F_SHARED) !=
+	    (wpc->ioend->io_flags & IOMAP_F_SHARED) ||
 	    wpc->iomap.type != wpc->ioend->io_type ||
 	    sector != bio_end_sector(wpc->ioend->io_bio) ||
 	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 6a45d675dcba..4a0226cdad4f 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -13,8 +13,8 @@ extern struct bio_set xfs_ioend_bioset;
  */
 struct xfs_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
-	int			io_fork;	/* inode fork written back */
 	u16			io_type;
+	u16			io_flags;	/* IOMAP_F_* */
 	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 */
-- 
2.20.1