[PATCH v4 0/2] xfs: use new list helpers in writeback code

[PATCH v4 0/2] xfs: use new list helpers in 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 second part
refactors some of XFS's writeback code to use the new helpers introduced
in the first part.

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.

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

--D

[PATCH 1/2] xfs: initialize iomap->flags in xfs_bmbt_to_iomap

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Currently we don't overwrite the flags field in the iomap in
xfs_bmbt_to_iomap.  This works fine with 0-initialized iomaps on stack,
but is harmful once we want to be able to reuse an iomap in the
writeback code.  Replace the shared paramter with a set of initial
flags an thus ensures the flags field is always reinitialized.

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_iomap.c |   28 +++++++++++++++++-----------
 fs/xfs/xfs_iomap.h |    2 +-
 fs/xfs/xfs_pnfs.c  |    2 +-
 3 files changed, 19 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 434ff589f0fc..d340db666c06 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -54,7 +54,7 @@ xfs_bmbt_to_iomap(
 	struct xfs_inode	*ip,
 	struct iomap		*iomap,
 	struct xfs_bmbt_irec	*imap,
-	bool			shared)
+	u16			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
@@ -79,12 +79,11 @@ xfs_bmbt_to_iomap(
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
 	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
 	iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
+	iomap->flags = flags;
 
 	if (xfs_ipincount(ip) &&
 	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 		iomap->flags |= IOMAP_F_DIRTY;
-	if (shared)
-		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
 }
 
@@ -540,6 +539,7 @@ xfs_file_iomap_begin_delay(
 	struct xfs_iext_cursor	icur, ccur;
 	xfs_fsblock_t		prealloc_blocks = 0;
 	bool			eof = false, cow_eof = false, shared = false;
+	u16			iomap_flags = 0;
 	int			whichfork = XFS_DATA_FORK;
 	int			error = 0;
 
@@ -708,7 +708,7 @@ xfs_file_iomap_begin_delay(
 	 * them out if the write happens to fail.
 	 */
 	if (whichfork == XFS_DATA_FORK) {
-		iomap->flags |= IOMAP_F_NEW;
+		iomap_flags |= IOMAP_F_NEW;
 		trace_xfs_iomap_alloc(ip, offset, count, whichfork, &imap);
 	} else {
 		trace_xfs_iomap_alloc(ip, offset, count, whichfork, &cmap);
@@ -718,14 +718,17 @@ xfs_file_iomap_begin_delay(
 		if (imap.br_startoff > offset_fsb) {
 			xfs_trim_extent(&cmap, offset_fsb,
 					imap.br_startoff - offset_fsb);
-			error = xfs_bmbt_to_iomap(ip, iomap, &cmap, true);
+			error = xfs_bmbt_to_iomap(ip, iomap, &cmap,
+					IOMAP_F_SHARED);
 			goto out_unlock;
 		}
 		/* ensure we only report blocks we have a reservation for */
 		xfs_trim_extent(&imap, cmap.br_startoff, cmap.br_blockcount);
 		shared = true;
 	}
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	if (shared)
+		iomap_flags |= IOMAP_F_SHARED;
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -933,6 +936,7 @@ xfs_file_iomap_begin(
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			nimaps = 1, error = 0;
 	bool			shared = false;
+	u16			iomap_flags = 0;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -1048,11 +1052,13 @@ xfs_file_iomap_begin(
 	if (error)
 		return error;
 
-	iomap->flags |= IOMAP_F_NEW;
+	iomap_flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
 
 out_finish:
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	if (shared)
+		iomap_flags |= IOMAP_F_SHARED;
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
 
 out_found:
 	ASSERT(nimaps);
@@ -1196,7 +1202,7 @@ xfs_seek_iomap_begin(
 		if (data_fsb < cow_fsb + cmap.br_blockcount)
 			end_fsb = min(end_fsb, data_fsb);
 		xfs_trim_extent(&cmap, offset_fsb, end_fsb);
-		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, true);
+		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
 		/*
 		 * This is a COW extent, so we must probe the page cache
 		 * because there could be dirty page cache being backed
@@ -1218,7 +1224,7 @@ xfs_seek_iomap_begin(
 	imap.br_state = XFS_EXT_NORM;
 done:
 	xfs_trim_extent(&imap, offset_fsb, end_fsb);
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
@@ -1264,7 +1270,7 @@ xfs_xattr_iomap_begin(
 	if (error)
 		return error;
 	ASSERT(nimaps);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 }
 
 const struct iomap_ops xfs_xattr_iomap_ops = {
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 5c2f6aa6d78f..71d0ae460c44 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -16,7 +16,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
-		struct xfs_bmbt_irec *, bool shared);
+		struct xfs_bmbt_irec *, u16);
 xfs_extlen_t xfs_eof_alignment(struct xfs_inode *ip, xfs_extlen_t extsize);
 
 static inline xfs_filblks_t
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 0c954cad7449..d1e293b62902 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -178,7 +178,7 @@ xfs_fs_map_blocks(
 	}
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, false);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
 	*device_generation = mp->m_generation;
 	return error;
 out_unlock:

[PATCH 2/2] xfs: refactor the ioend merging code

[Darrick J. Wong]

From: Christoph Hellwig <hch@lst.de>

Introduce two nicely abstracted helper, which can be moved to the
iomap code later.  Also use list_pop_entry and list_first_entry_or_null
to simplify the code a bit.

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 |   70 +++++++++++++++++++++++++++++------------------------
 1 file changed, 38 insertions(+), 32 deletions(-)


diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f16d5f196c6b..4e4a4d7df5ac 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -116,6 +116,19 @@ xfs_destroy_ioend(
 	}
 }
 
+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.
  */
@@ -230,7 +243,6 @@ STATIC void
 xfs_end_ioend(
 	struct xfs_ioend	*ioend)
 {
-	struct list_head	ioend_list;
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	xfs_off_t		offset = ioend->io_offset;
 	size_t			size = ioend->io_size;
@@ -275,16 +287,7 @@ xfs_end_ioend(
 done:
 	if (ioend->io_append_trans)
 		error = xfs_setfilesize_ioend(ioend, error);
-	list_replace_init(&ioend->io_list, &ioend_list);
-	xfs_destroy_ioend(ioend, error);
-
-	while (!list_empty(&ioend_list)) {
-		ioend = list_first_entry(&ioend_list, struct xfs_ioend,
-				io_list);
-		list_del_init(&ioend->io_list);
-		xfs_destroy_ioend(ioend, error);
-	}
-
+	xfs_destroy_ioends(ioend, error);
 	memalloc_nofs_restore(nofs_flag);
 }
 
@@ -333,17 +336,18 @@ xfs_ioend_try_merge(
 	struct xfs_ioend	*ioend,
 	struct list_head	*more_ioends)
 {
-	struct xfs_ioend	*next_ioend;
+	struct xfs_ioend	*next;
 
-	while (!list_empty(more_ioends)) {
-		next_ioend = list_first_entry(more_ioends, struct xfs_ioend,
-				io_list);
-		if (!xfs_ioend_can_merge(ioend, next_ioend))
+	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_ioend->io_list, &ioend->io_list);
-		ioend->io_size += next_ioend->io_size;
-		if (next_ioend->io_append_trans)
-			xfs_ioend_merge_append_transactions(ioend, next_ioend);
+		list_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);
 	}
 }
 
@@ -366,29 +370,31 @@ xfs_ioend_compare(
 	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(
 	struct work_struct	*work)
 {
-	struct xfs_inode	*ip;
+	struct xfs_inode	*ip =
+		container_of(work, struct xfs_inode, i_ioend_work);
 	struct xfs_ioend	*ioend;
-	struct list_head	completion_list;
+	struct list_head	tmp;
 	unsigned long		flags;
 
-	ip = container_of(work, struct xfs_inode, i_ioend_work);
-
 	spin_lock_irqsave(&ip->i_ioend_lock, flags);
-	list_replace_init(&ip->i_ioend_list, &completion_list);
+	list_replace_init(&ip->i_ioend_list, &tmp);
 	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
 
-	list_sort(NULL, &completion_list, xfs_ioend_compare);
-
-	while (!list_empty(&completion_list)) {
-		ioend = list_first_entry(&completion_list, struct xfs_ioend,
-				io_list);
-		list_del_init(&ioend->io_list);
-		xfs_ioend_try_merge(ioend, &completion_list);
+	xfs_sort_ioends(&tmp);
+	while ((ioend = list_pop_entry(&tmp, struct xfs_ioend, io_list))) {
+		xfs_ioend_try_merge(ioend, &tmp);
 		xfs_end_ioend(ioend);
 	}
 }