xfs: introduce new file range exchange ioctl

Introduce a new ioctl to handle exchanging ranges of bytes
between files.  The goal here is to perform the exchange atomically with
respect to applications -- either they see the file contents before the
exchange or they see that A-B is now B-A, even if the kernel crashes.

My original goal with all this code was to make it so that online repair
can build a replacement directory or xattr structure in a temporary file
and commit the repair by atomically exchanging all the data blocks
between the two files.  However, I needed a way to test this mechanism
thoroughly, so I've been evolving an ioctl interface since then.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 41 insertions, 0 deletions

diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index ca1b17d01437..8a1e30cf4dc8 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -772,6 +772,46 @@ struct xfs_scrub_metadata {
 #  define XFS_XATTR_LIST_MAX 65536
 #endif
 
+/*
+ * Exchange part of file1 with part of the file that this ioctl that is being
+ * called against (which we'll call file2).  Filesystems must be able to
+ * restart and complete the operation even after the system goes down.
+ */
+struct xfs_exchange_range {
+	__s32		file1_fd;
+	__u32		pad;		/* must be zeroes */
+	__u64		file1_offset;	/* file1 offset, bytes */
+	__u64		file2_offset;	/* file2 offset, bytes */
+	__u64		length;		/* bytes to exchange */
+
+	__u64		flags;		/* see XFS_EXCHANGE_RANGE_* below */
+};
+
+/*
+ * Exchange file data all the way to the ends of both files, and then exchange
+ * the file sizes.  This flag can be used to replace a file's contents with a
+ * different amount of data.  length will be ignored.
+ */
+#define XFS_EXCHANGE_RANGE_TO_EOF	(1ULL << 0)
+
+/* Flush all changes in file data and file metadata to disk before returning. */
+#define XFS_EXCHANGE_RANGE_DSYNC	(1ULL << 1)
+
+/* Dry run; do all the parameter verification but do not change anything. */
+#define XFS_EXCHANGE_RANGE_DRY_RUN	(1ULL << 2)
+
+/*
+ * Exchange only the parts of the two files where the file allocation units
+ * mapped to file1's range have been written to.  This can accelerate
+ * scatter-gather atomic writes with a temp file if all writes are aligned to
+ * the file allocation unit.
+ */
+#define XFS_EXCHANGE_RANGE_FILE1_WRITTEN (1ULL << 3)
+
+#define XFS_EXCHANGE_RANGE_ALL_FLAGS	(XFS_EXCHANGE_RANGE_TO_EOF | \
+					 XFS_EXCHANGE_RANGE_DSYNC | \
+					 XFS_EXCHANGE_RANGE_DRY_RUN | \
+					 XFS_EXCHANGE_RANGE_FILE1_WRITTEN)
 
 /*
  * ioctl commands that are used by Linux filesystems
@@ -843,6 +883,7 @@ struct xfs_scrub_metadata {
 #define XFS_IOC_FSGEOMETRY	     _IOR ('X', 126, struct xfs_fsop_geom)
 #define XFS_IOC_BULKSTAT	     _IOR ('X', 127, struct xfs_bulkstat_req)
 #define XFS_IOC_INUMBERS	     _IOR ('X', 128, struct xfs_inumbers_req)
+#define XFS_IOC_EXCHANGE_RANGE	     _IOWR('X', 129, struct xfs_exchange_range)
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */