xfs: create delalloc extents in CoW fork

Wire up iomap_begin to detect shared extents and create delayed allocation
extents in the CoW fork:

 1) Check if we already have an extent in the COW fork for the area.
    If so nothing to do, we can move along.
 2) Look up block number for the current extent, and if there is none
    it's not shared move along.
 3) Unshare the current extent as far as we are going to write into it.
    For this we avoid an additional COW fork lookup and use the
    information we set aside in step 1) above.
 4) Goto 1) unless we've covered the whole range.

Last but not least, this updates the xfs_reflink_reserve_cow_range calling
convention to pass a byte offset and length, as that is what both callers
expect anyway.  This patch has been refactored considerably as part of the
iomap transition.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 216 insertions, 0 deletions

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 7adbb83df040..5d796b7f23d7 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -51,6 +51,7 @@
 #include "xfs_btree.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_iomap.h"
 
 /*
  * Copy on Write of Shared Blocks
@@ -112,3 +113,218 @@
  * ioend structure.  Better yet, the more ground we can cover with one
  * ioend, the better.
  */
+
+/*
+ * Given an AG extent, find the lowest-numbered run of shared blocks
+ * within that range and return the range in fbno/flen.  If
+ * find_end_of_shared is true, return the longest contiguous extent of
+ * shared blocks.  If there are no shared extents, fbno and flen will
+ * be set to NULLAGBLOCK and 0, respectively.
+ */
+int
+xfs_reflink_find_shared(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		aglen,
+	xfs_agblock_t		*fbno,
+	xfs_extlen_t		*flen,
+	bool			find_end_of_shared)
+{
+	struct xfs_buf		*agbp;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	if (error)
+		return error;
+
+	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
+
+	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
+			find_end_of_shared);
+
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+
+	xfs_buf_relse(agbp);
+	return error;
+}
+
+/*
+ * Trim the mapping to the next block where there's a change in the
+ * shared/unshared status.  More specifically, this means that we
+ * find the lowest-numbered extent of shared blocks that coincides with
+ * the given block mapping.  If the shared extent overlaps the start of
+ * the mapping, trim the mapping to the end of the shared extent.  If
+ * the shared region intersects the mapping, trim the mapping to the
+ * start of the shared extent.  If there are no shared regions that
+ * overlap, just return the original extent.
+ */
+int
+xfs_reflink_trim_around_shared(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*irec,
+	bool			*shared,
+	bool			*trimmed)
+{
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		aglen;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	int			error = 0;
+
+	/* Holes, unwritten, and delalloc extents cannot be shared */
+	if (!xfs_is_reflink_inode(ip) ||
+	    ISUNWRITTEN(irec) ||
+	    irec->br_startblock == HOLESTARTBLOCK ||
+	    irec->br_startblock == DELAYSTARTBLOCK) {
+		*shared = false;
+		return 0;
+	}
+
+	trace_xfs_reflink_trim_around_shared(ip, irec);
+
+	agno = XFS_FSB_TO_AGNO(ip->i_mount, irec->br_startblock);
+	agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock);
+	aglen = irec->br_blockcount;
+
+	error = xfs_reflink_find_shared(ip->i_mount, agno, agbno,
+			aglen, &fbno, &flen, true);
+	if (error)
+		return error;
+
+	*shared = *trimmed = false;
+	if (fbno == NULLAGBLOCK) {
+		/* No shared blocks at all. */
+		return 0;
+	} else if (fbno == agbno) {
+		/*
+		 * The start of this extent is shared.  Truncate the
+		 * mapping at the end of the shared region so that a
+		 * subsequent iteration starts at the start of the
+		 * unshared region.
+		 */
+		irec->br_blockcount = flen;
+		*shared = true;
+		if (flen != aglen)
+			*trimmed = true;
+		return 0;
+	} else {
+		/*
+		 * There's a shared extent midway through this extent.
+		 * Truncate the mapping at the start of the shared
+		 * extent so that a subsequent iteration starts at the
+		 * start of the shared region.
+		 */
+		irec->br_blockcount = fbno - agbno;
+		*trimmed = true;
+		return 0;
+	}
+}
+
+/* Create a CoW reservation for a range of blocks within a file. */
+static int
+__xfs_reflink_reserve_cow(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		*offset_fsb,
+	xfs_fileoff_t		end_fsb)
+{
+	struct xfs_bmbt_irec	got, prev, imap;
+	xfs_fileoff_t		orig_end_fsb;
+	int			nimaps, eof = 0, error = 0;
+	bool			shared = false, trimmed = false;
+	xfs_extnum_t		idx;
+
+	/* Already reserved?  Skip the refcount btree access. */
+	xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx,
+			&got, &prev);
+	if (!eof && got.br_startoff <= *offset_fsb) {
+		end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount;
+		trace_xfs_reflink_cow_found(ip, &got);
+		goto done;
+	}
+
+	/* Read extent from the source file. */
+	nimaps = 1;
+	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
+			&imap, &nimaps, 0);
+	if (error)
+		goto out_unlock;
+	ASSERT(nimaps == 1);
+
+	/* Trim the mapping to the nearest shared extent boundary. */
+	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
+	if (error)
+		goto out_unlock;
+
+	end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount;
+
+	/* Not shared?  Just report the (potentially capped) extent. */
+	if (!shared)
+		goto done;
+
+	/*
+	 * Fork all the shared blocks from our write offset until the end of
+	 * the extent.
+	 */
+	error = xfs_qm_dqattach_locked(ip, 0);
+	if (error)
+		goto out_unlock;
+
+retry:
+	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb,
+			end_fsb - *offset_fsb, &got,
+			&prev, &idx, eof);
+	switch (error) {
+	case 0:
+		break;
+	case -ENOSPC:
+	case -EDQUOT:
+		/* retry without any preallocation */
+		trace_xfs_reflink_cow_enospc(ip, &imap);
+		if (end_fsb != orig_end_fsb) {
+			end_fsb = orig_end_fsb;
+			goto retry;
+		}
+		/*FALLTHRU*/
+	default:
+		goto out_unlock;
+	}
+
+	trace_xfs_reflink_cow_alloc(ip, &got);
+done:
+	*offset_fsb = end_fsb;
+out_unlock:
+	return error;
+}
+
+/* Create a CoW reservation for part of a file. */
+int
+xfs_reflink_reserve_cow_range(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_off_t		count)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb, end_fsb;
+	int			error;
+
+	trace_xfs_reflink_reserve_cow_range(ip, offset, count);
+
+	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	end_fsb = XFS_B_TO_FSB(mp, offset + count);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	while (offset_fsb < end_fsb) {
+		error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb);
+		if (error) {
+			trace_xfs_reflink_reserve_cow_range_error(ip, error,
+				_RET_IP_);
+			break;
+		}
+	}
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	return error;
+}