[PATCH v3 3/6] fs, xfs: introduce FALLOC_FL_UNSEAL_BLOCK_MAP

[Dan Williams]

Provide an explicit fallocate operation type for clearing the
S_IOMAP_IMMUTABLE flag. Like the enable case it requires CAP_IMMUTABLE
and it can only be performed while no process has the file mapped.

Cc: Jan Kara <jack@xxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: "Darrick J. Wong" <darrick.wong@xxxxxxxxxx>
Suggested-by: Dave Chinner <david@xxxxxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
 fs/open.c                   |   20 ++++++++++++------
 fs/xfs/xfs_bmap_util.c      |   47 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_bmap_util.h      |    3 +++
 fs/xfs/xfs_file.c           |    4 +++-
 include/linux/falloc.h      |    3 ++-
 include/uapi/linux/falloc.h |    1 +
 6 files changed, 69 insertions(+), 9 deletions(-)

diff --git a/fs/open.c b/fs/open.c
index 76f57f7465c4..3075599f1c55 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -274,13 +274,17 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		return -EINVAL;
 
 	/*
-	 * Seal block map operation should only be used exclusively, and
-	 * with the IMMUTABLE capability.
+	 * Seal/unseal block map operations should only be used
+	 * exclusively, and with the IMMUTABLE capability.
 	 */
-	if (mode & FALLOC_FL_SEAL_BLOCK_MAP) {
+	if (mode & (FALLOC_FL_SEAL_BLOCK_MAP | FALLOC_FL_UNSEAL_BLOCK_MAP)) {
 		if (!capable(CAP_LINUX_IMMUTABLE))
 			return -EPERM;
-		if (mode & ~FALLOC_FL_SEAL_BLOCK_MAP)
+		if (mode == (FALLOC_FL_SEAL_BLOCK_MAP
+					| FALLOC_FL_UNSEAL_BLOCK_MAP))
+			return -EINVAL;
+		if (mode & ~(FALLOC_FL_SEAL_BLOCK_MAP
+					| FALLOC_FL_UNSEAL_BLOCK_MAP))
 			return -EINVAL;
 	}
 
@@ -303,10 +307,12 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		return -ETXTBSY;
 
 	/*
-	 * We cannot allow any allocation changes on an iomap immutable file,
-	 * but we can allow the fs to validate if this request is redundant.
+	 * We cannot allow any allocation changes on an iomap immutable
+	 * file, but we can allow the fs to validate if this request is
+	 * redundant, or unseal the block map.
 	 */
-	if (IS_IOMAP_IMMUTABLE(inode) && !(mode & FALLOC_FL_SEAL_BLOCK_MAP))
+	if (IS_IOMAP_IMMUTABLE(inode) && !(mode & (FALLOC_FL_SEAL_BLOCK_MAP
+					| FALLOC_FL_UNSEAL_BLOCK_MAP)))
 		return -ETXTBSY;
 
 	/*
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 2ac8f4ed5723..888bae801961 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1462,6 +1462,53 @@ xfs_seal_file_space(
 	return error;
 }
 
+int
+xfs_unseal_file_space(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_off_t		len)
+{
+	struct inode		*inode = VFS_I(ip);
+	struct address_space	*mapping = inode->i_mapping;
+	int			error;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL));
+
+	if (offset)
+		return -EINVAL;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	/*
+	 * It does not make sense to unseal less than the full range of
+	 * the file.
+	 */
+	error = -EINVAL;
+	if (len != i_size_read(inode))
+		goto out_unlock;
+
+	/* Are we already unsealed? */
+	error = 0;
+	if (!IS_IOMAP_IMMUTABLE(inode))
+		goto out_unlock;
+
+	/*
+	 * Provide safety against one thread changing the policy of not
+	 * requiring fsync/msync (for block allocations) behind another
+	 * thread's back.
+	 */
+	error = -EBUSY;
+	if (mapping_mapped(mapping))
+		goto out_unlock;
+
+	error = 0;
+	inode->i_flags &= ~S_IOMAP_IMMUTABLE;
+
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	return error;
+}
+
 /*
  * @next_fsb will keep track of the extent currently undergoing shift.
  * @stop_fsb will keep track of the extent at which we have to stop.
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 5115a32a2483..b64653a75942 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -62,6 +62,9 @@ int	xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
 				xfs_off_t len);
 int	xfs_seal_file_space(struct xfs_inode *, xfs_off_t offset,
 				xfs_off_t len);
+int	xfs_unseal_file_space(struct xfs_inode *, xfs_off_t offset,
+				xfs_off_t len);
+
 
 /* EOF block manipulation functions */
 bool	xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e21121530a90..833f77700be2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -740,7 +740,7 @@ xfs_file_write_iter(
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
 		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
 		 FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE |	\
-		 FALLOC_FL_SEAL_BLOCK_MAP)
+		 FALLOC_FL_SEAL_BLOCK_MAP | FALLOC_FL_UNSEAL_BLOCK_MAP)
 
 STATIC long
 xfs_file_fallocate(
@@ -840,6 +840,8 @@ xfs_file_fallocate(
 						XFS_BMAPI_PREALLOC);
 			} else if (mode & FALLOC_FL_SEAL_BLOCK_MAP) {
 				error = xfs_seal_file_space(ip, offset, len);
+			} else if (mode & FALLOC_FL_UNSEAL_BLOCK_MAP) {
+				error = xfs_unseal_file_space(ip, offset, len);
 			} else
 				error = xfs_alloc_file_space(ip, offset, len,
 						XFS_BMAPI_PREALLOC);
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
index 48546c6fbec7..b22c1368ed1e 100644
--- a/include/linux/falloc.h
+++ b/include/linux/falloc.h
@@ -27,6 +27,7 @@ struct space_resv {
 					 FALLOC_FL_ZERO_RANGE |		\
 					 FALLOC_FL_INSERT_RANGE |	\
 					 FALLOC_FL_UNSHARE_RANGE |	\
-					 FALLOC_FL_SEAL_BLOCK_MAP)
+					 FALLOC_FL_SEAL_BLOCK_MAP |	\
+					 FALLOC_FL_UNSEAL_BLOCK_MAP)
 
 #endif /* _FALLOC_H_ */
diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h
index e3867cfe31d5..5509e6216448 100644
--- a/include/uapi/linux/falloc.h
+++ b/include/uapi/linux/falloc.h
@@ -93,4 +93,5 @@
  * with the punch, zero, collapse, or insert range modes.
  */
 #define FALLOC_FL_SEAL_BLOCK_MAP	0x080
+#define FALLOC_FL_UNSEAL_BLOCK_MAP	0x100
 #endif /* _UAPI_FALLOC_H_ */