xfs: Add support FALLOC_FL_INSERT_RANGE for fallocate

This patch implements fallocate's FALLOC_FL_INSERT_RANGE for XFS.

1) Make sure that both offset and len are block size aligned.
2) Update the i_size of inode by len bytes.
3) Compute the file's logical block number against offset. If the computed
   block number is not the starting block of the extent, split the extent
   such that the block number is the starting block of the extent.
4) Shift all the extents which are lying bewteen [offset, last allocated extent]
   towards right by len bytes. This step will make a hole of len bytes
   at offset.

Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com>
Signed-off-by: Ashish Sangwan <a.sangwan@samsung.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

2 files changed, 323 insertions, 46 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 60cfa90163b8..e8696f5a8041 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5526,52 +5526,92 @@ xfs_bmse_shift_one(
 	int				*current_ext,
 	struct xfs_bmbt_rec_host	*gotp,
 	struct xfs_btree_cur		*cur,
-	int				*logflags)
+	int				*logflags,
+	enum shift_direction		direction)
 {
 	struct xfs_ifork		*ifp;
 	struct xfs_mount		*mp;
 	xfs_fileoff_t			startoff;
-	struct xfs_bmbt_rec_host	*leftp;
+	struct xfs_bmbt_rec_host	*adj_irecp;
 	struct xfs_bmbt_irec		got;
-	struct xfs_bmbt_irec		left;
+	struct xfs_bmbt_irec		adj_irec;
 	int				error;
 	int				i;
+	int				total_extents;
 
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
+	total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
 
 	xfs_bmbt_get_all(gotp, &got);
-	startoff = got.br_startoff - offset_shift_fsb;
 
 	/* delalloc extents should be prevented by caller */
 	XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got.br_startblock));
 
-	/*
-	 * Check for merge if we've got an extent to the left, otherwise make
-	 * sure there's enough room at the start of the file for the shift.
-	 */
-	if (*current_ext) {
-		/* grab the left extent and check for a large enough hole */
-		leftp = xfs_iext_get_ext(ifp, *current_ext - 1);
-		xfs_bmbt_get_all(leftp, &left);
+	if (direction == SHIFT_LEFT) {
+		startoff = got.br_startoff - offset_shift_fsb;
+
+		/*
+		 * Check for merge if we've got an extent to the left,
+		 * otherwise make sure there's enough room at the start
+		 * of the file for the shift.
+		 */
+		if (!*current_ext) {
+			if (got.br_startoff < offset_shift_fsb)
+				return -EINVAL;
+			goto update_current_ext;
+		}
+		/*
+		 * grab the left extent and check for a large
+		 * enough hole.
+		 */
+		adj_irecp = xfs_iext_get_ext(ifp, *current_ext - 1);
+		xfs_bmbt_get_all(adj_irecp, &adj_irec);
 
-		if (startoff < left.br_startoff + left.br_blockcount)
+		if (startoff <
+		    adj_irec.br_startoff + adj_irec.br_blockcount)
 			return -EINVAL;
 
 		/* check whether to merge the extent or shift it down */
-		if (xfs_bmse_can_merge(&left, &got, offset_shift_fsb)) {
+		if (xfs_bmse_can_merge(&adj_irec, &got,
+				       offset_shift_fsb)) {
 			return xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
-					      *current_ext, gotp, leftp, cur,
-					      logflags);
+					      *current_ext, gotp, adj_irecp,
+					      cur, logflags);
 		}
-	} else if (got.br_startoff < offset_shift_fsb)
-		return -EINVAL;
-
+	} else {
+		startoff = got.br_startoff + offset_shift_fsb;
+		/* nothing to move if this is the last extent */
+		if (*current_ext >= (total_extents - 1))
+			goto update_current_ext;
+		/*
+		 * If this is not the last extent in the file, make sure there
+		 * is enough room between current extent and next extent for
+		 * accommodating the shift.
+		 */
+		adj_irecp = xfs_iext_get_ext(ifp, *current_ext + 1);
+		xfs_bmbt_get_all(adj_irecp, &adj_irec);
+		if (startoff + got.br_blockcount > adj_irec.br_startoff)
+			return -EINVAL;
+		/*
+		 * Unlike a left shift (which involves a hole punch),
+		 * a right shift does not modify extent neighbors
+		 * in any way. We should never find mergeable extents
+		 * in this scenario. Check anyways and warn if we
+		 * encounter two extents that could be one.
+		 */
+		if (xfs_bmse_can_merge(&got, &adj_irec, offset_shift_fsb))
+			WARN_ON_ONCE(1);
+	}
 	/*
 	 * Increment the extent index for the next iteration, update the start
 	 * offset of the in-core extent and update the btree if applicable.
 	 */
-	(*current_ext)++;
+update_current_ext:
+	if (direction == SHIFT_LEFT)
+		(*current_ext)++;
+	else
+		(*current_ext)--;
 	xfs_bmbt_set_startoff(gotp, startoff);
 	*logflags |= XFS_ILOG_CORE;
 	if (!cur) {
@@ -5587,14 +5627,14 @@ xfs_bmse_shift_one(
 
 	got.br_startoff = startoff;
 	return xfs_bmbt_update(cur, got.br_startoff, got.br_startblock,
-				got.br_blockcount, got.br_state);
+			       got.br_blockcount, got.br_state);
 }
 
 /*
- * Shift extent records to the left to cover a hole.
+ * Shift extent records to the left/right to cover/create a hole.
  *
  * The maximum number of extents to be shifted in a single operation is
- * @num_exts. @start_fsb specifies the file offset to start the shift and the
+ * @num_exts. @stop_fsb specifies the file offset at which to stop shift and the
  * file offset where we've left off is returned in @next_fsb. @offset_shift_fsb
  * is the length by which each extent is shifted. If there is no hole to shift
  * the extents into, this will be considered invalid operation and we abort
@@ -5604,12 +5644,13 @@ int
 xfs_bmap_shift_extents(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		start_fsb,
+	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
 	int			*done,
-	xfs_fileoff_t		*next_fsb,
+	xfs_fileoff_t		stop_fsb,
 	xfs_fsblock_t		*firstblock,
 	struct xfs_bmap_free	*flist,
+	enum shift_direction	direction,
 	int			num_exts)
 {
 	struct xfs_btree_cur		*cur = NULL;
@@ -5619,10 +5660,11 @@ xfs_bmap_shift_extents(
 	struct xfs_ifork		*ifp;
 	xfs_extnum_t			nexts = 0;
 	xfs_extnum_t			current_ext;
+	xfs_extnum_t			total_extents;
+	xfs_extnum_t			stop_extent;
 	int				error = 0;
 	int				whichfork = XFS_DATA_FORK;
 	int				logflags = 0;
-	int				total_extents;
 
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
@@ -5638,6 +5680,8 @@ xfs_bmap_shift_extents(
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT);
+	ASSERT(*next_fsb != NULLFSBLOCK || direction == SHIFT_RIGHT);
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
@@ -5655,43 +5699,83 @@ xfs_bmap_shift_extents(
 	}
 
 	/*
+	 * There may be delalloc extents in the data fork before the range we
+	 * are collapsing out, so we cannot use the count of real extents here.
+	 * Instead we have to calculate it from the incore fork.
+	 */
+	total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+	if (total_extents == 0) {
+		*done = 1;
+		goto del_cursor;
+	}
+
+	/*
+	 * In case of first right shift, we need to initialize next_fsb
+	 */
+	if (*next_fsb == NULLFSBLOCK) {
+		gotp = xfs_iext_get_ext(ifp, total_extents - 1);
+		xfs_bmbt_get_all(gotp, &got);
+		*next_fsb = got.br_startoff;
+		if (stop_fsb > *next_fsb) {
+			*done = 1;
+			goto del_cursor;
+		}
+	}
+
+	/* Lookup the extent index at which we have to stop */
+	if (direction == SHIFT_RIGHT) {
+		gotp = xfs_iext_bno_to_ext(ifp, stop_fsb, &stop_extent);
+		/* Make stop_extent exclusive of shift range */
+		stop_extent--;
+	} else
+		stop_extent = total_extents;
+
+	/*
 	 * Look up the extent index for the fsb where we start shifting. We can
 	 * henceforth iterate with current_ext as extent list changes are locked
 	 * out via ilock.
 	 *
 	 * gotp can be null in 2 cases: 1) if there are no extents or 2)
-	 * start_fsb lies in a hole beyond which there are no extents. Either
+	 * *next_fsb lies in a hole beyond which there are no extents. Either
 	 * way, we are done.
 	 */
-	gotp = xfs_iext_bno_to_ext(ifp, start_fsb, &current_ext);
+	gotp = xfs_iext_bno_to_ext(ifp, *next_fsb, &current_ext);
 	if (!gotp) {
 		*done = 1;
 		goto del_cursor;
 	}
 
-	/*
-	 * There may be delalloc extents in the data fork before the range we
-	 * are collapsing out, so we cannot use the count of real extents here.
-	 * Instead we have to calculate it from the incore fork.
-	 */
-	total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
-	while (nexts++ < num_exts && current_ext < total_extents) {
+	/* some sanity checking before we finally start shifting extents */
+	if ((direction == SHIFT_LEFT && current_ext >= stop_extent) ||
+	     (direction == SHIFT_RIGHT && current_ext <= stop_extent)) {
+		error = -EIO;
+		goto del_cursor;
+	}
+
+	while (nexts++ < num_exts) {
 		error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb,
-					&current_ext, gotp, cur, &logflags);
+					   &current_ext, gotp, cur, &logflags,
+					   direction);
 		if (error)
 			goto del_cursor;
+		/*
+		 * If there was an extent merge during the shift, the extent
+		 * count can change. Update the total and grade the next record.
+		 */
+		if (direction == SHIFT_LEFT) {
+			total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+			stop_extent = total_extents;
+		}
 
-		/* update total extent count and grab the next record */
-		total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
-		if (current_ext >= total_extents)
+		if (current_ext == stop_extent) {
+			*done = 1;
+			*next_fsb = NULLFSBLOCK;
 			break;
+		}
 		gotp = xfs_iext_get_ext(ifp, current_ext);
 	}
 
-	/* Check if we are done */
-	if (current_ext == total_extents) {
-		*done = 1;
-	} else if (next_fsb) {
+	if (!*done) {
 		xfs_bmbt_get_all(gotp, &got);
 		*next_fsb = got.br_startoff;
 	}
@@ -5706,3 +5790,189 @@ del_cursor:
 
 	return error;
 }
+
+/*
+ * Splits an extent into two extents at split_fsb block such that it is
+ * the first block of the current_ext. @current_ext is a target extent
+ * to be split. @split_fsb is a block where the extents is split.
+ * If split_fsb lies in a hole or the first block of extents, just return 0.
+ */
+STATIC int
+xfs_bmap_split_extent_at(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		split_fsb,
+	xfs_fsblock_t		*firstfsb,
+	struct xfs_bmap_free	*free_list)
+{
+	int				whichfork = XFS_DATA_FORK;
+	struct xfs_btree_cur		*cur = NULL;
+	struct xfs_bmbt_rec_host	*gotp;
+	struct xfs_bmbt_irec		got;
+	struct xfs_bmbt_irec		new; /* split extent */
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_ifork		*ifp;
+	xfs_fsblock_t			gotblkcnt; /* new block count for got */
+	xfs_extnum_t			current_ext;
+	int				error = 0;
+	int				logflags = 0;
+	int				i = 0;
+
+	if (unlikely(XFS_TEST_ERROR(
+	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
+	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+		XFS_ERROR_REPORT("xfs_bmap_split_extent_at",
+				 XFS_ERRLEVEL_LOW, mp);
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	ifp = XFS_IFORK_PTR(ip, whichfork);
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		/* Read in all the extents */
+		error = xfs_iread_extents(tp, ip, whichfork);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * gotp can be null in 2 cases: 1) if there are no extents
+	 * or 2) split_fsb lies in a hole beyond which there are
+	 * no extents. Either way, we are done.
+	 */
+	gotp = xfs_iext_bno_to_ext(ifp, split_fsb, &current_ext);
+	if (!gotp)
+		return 0;
+
+	xfs_bmbt_get_all(gotp, &got);
+
+	/*
+	 * Check split_fsb lies in a hole or the start boundary offset
+	 * of the extent.
+	 */
+	if (got.br_startoff >= split_fsb)
+		return 0;
+
+	gotblkcnt = split_fsb - got.br_startoff;
+	new.br_startoff = split_fsb;
+	new.br_startblock = got.br_startblock + gotblkcnt;
+	new.br_blockcount = got.br_blockcount - gotblkcnt;
+	new.br_state = got.br_state;
+
+	if (ifp->if_flags & XFS_IFBROOT) {
+		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
+		cur->bc_private.b.firstblock = *firstfsb;
+		cur->bc_private.b.flist = free_list;
+		cur->bc_private.b.flags = 0;
+		error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
+				got.br_startblock,
+				got.br_blockcount,
+				&i);
+		if (error)
+			goto del_cursor;
+		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor);
+	}
+
+	xfs_bmbt_set_blockcount(gotp, gotblkcnt);
+	got.br_blockcount = gotblkcnt;
+
+	logflags = XFS_ILOG_CORE;
+	if (cur) {
+		error = xfs_bmbt_update(cur, got.br_startoff,
+				got.br_startblock,
+				got.br_blockcount,
+				got.br_state);
+		if (error)
+			goto del_cursor;
+	} else
+		logflags |= XFS_ILOG_DEXT;
+
+	/* Add new extent */
+	current_ext++;
+	xfs_iext_insert(ip, current_ext, 1, &new, 0);
+	XFS_IFORK_NEXT_SET(ip, whichfork,
+			   XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
+
+	if (cur) {
+		error = xfs_bmbt_lookup_eq(cur, new.br_startoff,
+				new.br_startblock, new.br_blockcount,
+				&i);
+		if (error)
+			goto del_cursor;
+		XFS_WANT_CORRUPTED_GOTO(mp, i == 0, del_cursor);
+		cur->bc_rec.b.br_state = new.br_state;
+
+		error = xfs_btree_insert(cur, &i);
+		if (error)
+			goto del_cursor;
+		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor);
+	}
+
+	/*
+	 * Convert to a btree if necessary.
+	 */
+	if (xfs_bmap_needs_btree(ip, whichfork)) {
+		int tmp_logflags; /* partial log flag return val */
+
+		ASSERT(cur == NULL);
+		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, free_list,
+				&cur, 0, &tmp_logflags, whichfork);
+		logflags |= tmp_logflags;
+	}
+
+del_cursor:
+	if (cur) {
+		cur->bc_private.b.allocated = 0;
+		xfs_btree_del_cursor(cur,
+				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	}
+
+	if (logflags)
+		xfs_trans_log_inode(tp, ip, logflags);
+	return error;
+}
+
+int
+xfs_bmap_split_extent(
+	struct xfs_inode        *ip,
+	xfs_fileoff_t           split_fsb)
+{
+	struct xfs_mount        *mp = ip->i_mount;
+	struct xfs_trans        *tp;
+	struct xfs_bmap_free    free_list;
+	xfs_fsblock_t           firstfsb;
+	int                     committed;
+	int                     error;
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
+			XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	xfs_bmap_init(&free_list, &firstfsb);
+
+	error = xfs_bmap_split_extent_at(tp, ip, split_fsb,
+			&firstfsb, &free_list);
+	if (error)
+		goto out;
+
+	error = xfs_bmap_finish(&tp, &free_list, &committed);
+	if (error)
+		goto out;
+
+	return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+
+
+out:
+	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index b9d8a499d2c4..6aaa0c1c7200 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -166,6 +166,11 @@ static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp)
  */
 #define XFS_BMAP_MAX_SHIFT_EXTENTS	1
 
+enum shift_direction {
+	SHIFT_LEFT = 0,
+	SHIFT_RIGHT,
+};
+
 #ifdef DEBUG
 void	xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
 		int whichfork, unsigned long caller_ip);
@@ -211,8 +216,10 @@ int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
 		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t start_fsb, xfs_fileoff_t offset_shift_fsb,
-		int *done, xfs_fileoff_t *next_fsb, xfs_fsblock_t *firstblock,
-		struct xfs_bmap_free *flist, int num_exts);
+		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
+		int *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
+		struct xfs_bmap_free *flist, enum shift_direction direction,
+		int num_exts);
+int	xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
 
 #endif	/* __XFS_BMAP_H__ */