From: Dave Chinner <dchinner@redhat.com>

When forced allocation alignment is specified, the extent will
be aligned to the extent size hint size rather than stripe
alignment. If aligned allocation cannot be done, then the allocation
is failed rather than attempting non-aligned fallbacks.

Note: none of the per-inode force align configuration is present
yet, so this just triggers off an "always false" wrapper function
for the moment.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
[jpg: Set XFS_ALLOC_FORCEALIGN in xfs_bmap_alloc_userdata(), rather than
      xfs_bmap_compute_alignments()]
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.h |  1 +
 fs/xfs/libxfs/xfs_bmap.c  | 28 +++++++++++++++++++++++-----
 fs/xfs/xfs_inode.h        |  5 +++++
 3 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 473822a5d4e9..17b062e8b925 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -66,6 +66,7 @@ typedef struct xfs_alloc_arg {
 #define XFS_ALLOC_USERDATA		(1 << 0)/* allocation is for user data*/
 #define XFS_ALLOC_INITIAL_USER_DATA	(1 << 1)/* special case start of file */
 #define XFS_ALLOC_NOBUSY		(1 << 2)/* Busy extents not allowed */
+#define XFS_ALLOC_FORCEALIGN		(1 << 3)/* forced extent alignment */
 
 /* freespace limit calculations */
 unsigned int xfs_alloc_set_aside(struct xfs_mount *mp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 42a75d257b35..602a5a50bcca 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3401,9 +3401,10 @@ xfs_bmap_alloc_account(
  * Calculate the extent start alignment and the extent length adjustments that
  * constrain this allocation.
  *
- * Extent start alignment is currently determined by stripe configuration and is
- * carried in args->alignment, whilst extent length adjustment is determined by
- * extent size hints and is carried by args->prod and args->mod.
+ * Extent start alignment is currently determined by forced inode alignment or
+ * stripe configuration and is carried in args->alignment, whilst extent length
+ * adjustment is determined by extent size hints and is carried by args->prod
+ * and args->mod.
  *
  * Low level allocation code is free to either ignore or override these values
  * as required.
@@ -3416,8 +3417,13 @@ xfs_bmap_compute_alignments(
 	struct xfs_mount	*mp = args->mp;
 	xfs_extlen_t		align = 0; /* minimum allocation alignment */
 
-	/* stripe alignment for allocation is determined by mount parameters */
-	if (mp->m_swidth && xfs_has_swalloc(mp))
+	/*
+	 * Forced inode alignment takes preference over stripe alignment.
+	 * Stripe alignment for allocation is determined by mount parameters.
+	 */
+	if (xfs_inode_has_forcealign(ap->ip))
+		args->alignment = xfs_get_extsz_hint(ap->ip);
+	else if (mp->m_swidth && xfs_has_swalloc(mp))
 		args->alignment = mp->m_swidth;
 	else if (mp->m_dalign)
 		args->alignment = mp->m_dalign;
@@ -3607,6 +3613,11 @@ xfs_bmap_btalloc_low_space(
 {
 	int			error;
 
+	if (args->alignment > 1 && (args->datatype & XFS_ALLOC_FORCEALIGN)) {
+		args->fsbno = NULLFSBLOCK;
+		return 0;
+	}
+
 	args->alignment = 1;
 	if (args->minlen > ap->minlen) {
 		args->minlen = ap->minlen;
@@ -3658,6 +3669,8 @@ xfs_bmap_btalloc_filestreams(
 
 	/* Attempt non-aligned allocation if we haven't already. */
 	if (!error && args->fsbno == NULLFSBLOCK && args->alignment > 1)  {
+		if (args->datatype & XFS_ALLOC_FORCEALIGN)
+			return error;
 		args->alignment = 1;
 		error = xfs_alloc_vextent_near_bno(args, ap->blkno);
 	}
@@ -3716,6 +3729,8 @@ xfs_bmap_btalloc_best_length(
 
 	/* Attempt non-aligned allocation if we haven't already. */
 	if (!error && args->fsbno == NULLFSBLOCK && args->alignment > 1)  {
+		if (args->datatype & XFS_ALLOC_FORCEALIGN)
+			return error;
 		args->alignment = 1;
 		error = xfs_alloc_vextent_start_ag(args, ap->blkno);
 	}
@@ -4151,6 +4166,9 @@ xfs_bmap_alloc_userdata(
 		if (bma->offset == 0)
 			bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;
 
+		if (xfs_inode_has_forcealign(bma->ip))
+			bma->datatype |= XFS_ALLOC_FORCEALIGN;
+
 		if (mp->m_dalign && bma->length >= mp->m_dalign) {
 			error = xfs_bmap_isaeof(bma, whichfork);
 			if (error)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 51defdebef30..bf0f4f8b9e64 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -310,6 +310,11 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_NREXT64;
 }
 
+static inline bool xfs_inode_has_forcealign(struct xfs_inode *ip)
+{
+	return false;
+}
+
 /*
  * Decide if this file is a realtime file whose data allocation unit is larger
  * than a single filesystem block.
-- 
2.31.1