Merge branch 'next' into for-linus

Prepare input updates for 6.17 merge window.

1 files changed, 115 insertions, 31 deletions

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index cc3b4df88110..ad3bcb76d805 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -293,7 +293,7 @@ xfs_bmap_trim_cow(
 	return xfs_reflink_trim_around_shared(ip, imap, shared);
 }
 
-static int
+int
 xfs_reflink_convert_cow_locked(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		offset_fsb,
@@ -786,35 +786,19 @@ xfs_reflink_update_quota(
  * requirements as low as possible.
  */
 STATIC int
-xfs_reflink_end_cow_extent(
+xfs_reflink_end_cow_extent_locked(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		*offset_fsb,
 	xfs_fileoff_t		end_fsb)
 {
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_irec	got, del, data;
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_COW_FORK);
-	unsigned int		resblks;
 	int			nmaps;
 	bool			isrt = XFS_IS_REALTIME_INODE(ip);
 	int			error;
 
-	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
-			XFS_TRANS_RESERVE, &tp);
-	if (error)
-		return error;
-
-	/*
-	 * Lock the inode.  We have to ijoin without automatic unlock because
-	 * the lead transaction is the refcountbt record deletion; the data
-	 * fork update follows as a deferred log item.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
-
 	/*
 	 * In case of racing, overlapping AIO writes no COW extents might be
 	 * left by the time I/O completes for the loser of the race.  In that
@@ -823,7 +807,7 @@ xfs_reflink_end_cow_extent(
 	if (!xfs_iext_lookup_extent(ip, ifp, *offset_fsb, &icur, &got) ||
 	    got.br_startoff >= end_fsb) {
 		*offset_fsb = end_fsb;
-		goto out_cancel;
+		return 0;
 	}
 
 	/*
@@ -837,7 +821,7 @@ xfs_reflink_end_cow_extent(
 		if (!xfs_iext_next_extent(ifp, &icur, &got) ||
 		    got.br_startoff >= end_fsb) {
 			*offset_fsb = end_fsb;
-			goto out_cancel;
+			return 0;
 		}
 	}
 	del = got;
@@ -846,14 +830,14 @@ xfs_reflink_end_cow_extent(
 	error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
 			XFS_IEXT_REFLINK_END_COW_CNT);
 	if (error)
-		goto out_cancel;
+		return error;
 
 	/* Grab the corresponding mapping in the data fork. */
 	nmaps = 1;
 	error = xfs_bmapi_read(ip, del.br_startoff, del.br_blockcount, &data,
 			&nmaps, 0);
 	if (error)
-		goto out_cancel;
+		return error;
 
 	/* We can only remap the smaller of the two extent sizes. */
 	data.br_blockcount = min(data.br_blockcount, del.br_blockcount);
@@ -882,7 +866,7 @@ xfs_reflink_end_cow_extent(
 		error = xfs_bunmapi(NULL, ip, data.br_startoff,
 				data.br_blockcount, 0, 1, &done);
 		if (error)
-			goto out_cancel;
+			return error;
 		ASSERT(done);
 	}
 
@@ -899,17 +883,45 @@ xfs_reflink_end_cow_extent(
 	/* Remove the mapping from the CoW fork. */
 	xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
 
-	error = xfs_trans_commit(tp);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		return error;
-
 	/* Update the caller about how much progress we made. */
 	*offset_fsb = del.br_startoff + del.br_blockcount;
 	return 0;
+}
 
-out_cancel:
-	xfs_trans_cancel(tp);
+/*
+ * Remap part of the CoW fork into the data fork.
+ *
+ * We aim to remap the range starting at @offset_fsb and ending at @end_fsb
+ * into the data fork; this function will remap what it can (at the end of the
+ * range) and update @end_fsb appropriately.  Each remap gets its own
+ * transaction because we can end up merging and splitting bmbt blocks for
+ * every remap operation and we'd like to keep the block reservation
+ * requirements as low as possible.
+ */
+STATIC int
+xfs_reflink_end_cow_extent(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		*offset_fsb,
+	xfs_fileoff_t		end_fsb)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	unsigned int		resblks;
+	int			error;
+
+	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
+			XFS_TRANS_RESERVE, &tp);
+	if (error)
+		return error;
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	error = xfs_reflink_end_cow_extent_locked(tp, ip, offset_fsb, end_fsb);
+	if (error)
+		xfs_trans_cancel(tp);
+	else
+		error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -973,6 +985,78 @@ xfs_reflink_end_cow(
 }
 
 /*
+ * Fully remap all of the file's data fork at once, which is the critical part
+ * in achieving atomic behaviour.
+ * The regular CoW end path does not use function as to keep the block
+ * reservation per transaction as low as possible.
+ */
+int
+xfs_reflink_end_atomic_cow(
+	struct xfs_inode		*ip,
+	xfs_off_t			offset,
+	xfs_off_t			count)
+{
+	xfs_fileoff_t			offset_fsb;
+	xfs_fileoff_t			end_fsb;
+	int				error = 0;
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_trans		*tp;
+	unsigned int			resblks;
+
+	trace_xfs_reflink_end_cow(ip, offset, count);
+
+	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	end_fsb = XFS_B_TO_FSB(mp, offset + count);
+
+	/*
+	 * Each remapping operation could cause a btree split, so in the worst
+	 * case that's one for each block.
+	 */
+	resblks = (end_fsb - offset_fsb) *
+			XFS_NEXTENTADD_SPACE_RES(mp, 1, XFS_DATA_FORK);
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_atomic_ioend, resblks, 0,
+			XFS_TRANS_RESERVE, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	while (end_fsb > offset_fsb && !error) {
+		error = xfs_reflink_end_cow_extent_locked(tp, ip, &offset_fsb,
+				end_fsb);
+	}
+	if (error) {
+		trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
+		goto out_cancel;
+	}
+	error = xfs_trans_commit(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+out_cancel:
+	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
+/* Compute the largest atomic write that we can complete through software. */
+xfs_extlen_t
+xfs_reflink_max_atomic_cow(
+	struct xfs_mount	*mp)
+{
+	/* We cannot do any atomic writes without out of place writes. */
+	if (!xfs_can_sw_atomic_write(mp))
+		return 0;
+
+	/*
+	 * Atomic write limits must always be a power-of-2, according to
+	 * generic_atomic_write_valid.
+	 */
+	return rounddown_pow_of_two(xfs_calc_max_atomic_write_fsblocks(mp));
+}
+
+/*
  * Free all CoW staging blocks that are still referenced by the ondisk refcount
  * metadata.  The ondisk metadata does not track which inode created the
  * staging extent, so callers must ensure that there are no cached inodes with