[PATCH v5 3/9] xfs: refuse a pNFS LAYOUTCOMMIT of a range without blocks

[Daejun Park via B4 Relay]

From: Daejun Park <daejun7.park@xxxxxxxxxxx>

A client can commit a hole in a LAYOUTCOMMIT, because nfsd does not
check the extents against its layouts. xfs_iomap_write_unwritten() then
allocates written blocks there. A large hole overruns the block
reservation and shuts XFS down. A small one exposes stale data.

Refuse such a range with -EIO, using XFS_BMAPI_CONVERT_ONLY.

Link: https://lore.kernel.org/r/20261014130834.GB15773@xxxxxx
Fixes: 527851124d10 ("xfs: implement pNFS export operations")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Daejun Park <daejun7.park@xxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
---
Tested with pynfs: committing a 64 KiB hole shut XFS down, and a 4 KiB
hole got NFS4_OK and a new block. Both now get NFS4ERR_IO, no block.
---
 fs/xfs/xfs_file.c  |  2 +-
 fs/xfs/xfs_ioend.c |  2 +-
 fs/xfs/xfs_iomap.c | 20 +++++++++++++++++---
 fs/xfs/xfs_iomap.h |  3 ++-
 fs/xfs/xfs_pnfs.c  |  9 ++++++++-
 5 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7d0c8a1975..720f4a9b40 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -666,7 +666,7 @@ xfs_dio_write_end_io(
 	 * they are converted.
 	 */
 	if (flags & IOMAP_DIO_UNWRITTEN) {
-		error = xfs_iomap_write_unwritten(ip, offset, size, true);
+		error = xfs_iomap_write_unwritten(ip, offset, size, true, 0);
 		goto out;
 	}
 
diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c
index 48becc3bf6..7f4a4a95af 100644
--- a/fs/xfs/xfs_ioend.c
+++ b/fs/xfs/xfs_ioend.c
@@ -237,7 +237,7 @@ xfs_end_ioend_write(
 	if (ioend->io_flags & IOMAP_IOEND_SHARED)
 		error = xfs_reflink_end_cow(ip, offset, size);
 	else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN)
-		error = xfs_iomap_write_unwritten(ip, offset, size, false);
+		error = xfs_iomap_write_unwritten(ip, offset, size, false, 0);
 
 	if (!error &&
 	    !(ioend->io_flags & IOMAP_IOEND_DIRECT) &&
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 329c745e31..99d48081c5 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -614,7 +614,8 @@ xfs_iomap_write_unwritten(
 	xfs_inode_t	*ip,
 	xfs_off_t	offset,
 	xfs_off_t	count,
-	bool		update_isize)
+	bool		update_isize,
+	uint32_t	bmapi_flags)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb;
@@ -676,8 +677,21 @@ xfs_iomap_write_unwritten(
 		 */
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-					XFS_BMAPI_CONVERT, resblks, &imap,
-					&nimaps);
+					XFS_BMAPI_CONVERT | bmapi_flags,
+					resblks, &imap, &nimaps);
+		if (error == -ENOSR && (bmapi_flags & XFS_BMAPI_CONVERT_ONLY)) {
+			/*
+			 * Nothing was mapped: the rest of the range starts
+			 * with a hole or a delalloc extent. Nothing was
+			 * changed either, but xfs_iext_count_extend() may
+			 * have logged the inode, and cancelling a dirty
+			 * transaction shuts the filesystem down. Commit it,
+			 * as xfs_alloc_file_space() does on -ENOSR.
+			 */
+			error = xfs_trans_commit(tp);
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+			return error ? error : -EIO;
+		}
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index f2520a9b3a..8fc0c6fc8b 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -15,7 +15,8 @@ struct xfs_zone_alloc_ctx;
 int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb,
 		xfs_fileoff_t count_fsb, unsigned int flags,
 		struct xfs_bmbt_irec *imap, u64 *sequence);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
+int xfs_iomap_write_unwritten(struct xfs_inode *ip, xfs_off_t offset,
+		xfs_off_t count, bool update_isize, uint32_t bmapi_flags);
 xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
 		xfs_fileoff_t end_fsb);
 
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index a9f0b472f3..7ff83274a5 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -344,7 +344,14 @@ xfs_fs_commit_blocks(
 					(end - 1) >> PAGE_SHIFT);
 		WARN_ON_ONCE(error);
 
-		error = xfs_iomap_write_unwritten(ip, start, length, false);
+		/*
+		 * A client may only write to blocks that a layout handed out,
+		 * and xfs_fs_map_blocks() allocates blocks for any hole in a
+		 * write layout, so refuse to allocate blocks for a hole or a
+		 * delalloc extent in the committed range.
+		 */
+		error = xfs_iomap_write_unwritten(ip, start, length, false,
+				XFS_BMAPI_CONVERT_ONLY);
 		if (error)
 			goto out_drop_iolock;
 	}

-- 
2.43.0