Merge patch series "Subject: sort out the fallocate mode mess"

Christoph Hellwig <hch@lst.de> says:

I've recently been looking at the XFS fallocate implementation and got
upset about the messing parsing of the mode argument, which mixes modes
and an optional flag in a really confusing way.

This series tries to clean this up by better defining what is the
operation mode and what is an optional flag, so that both the core
code and file systems can use switch statements to switch on the mode.

* patches from https://lore.kernel.org/r/20240827065123.1762168-1-hch@lst.de:
  xfs: refactor xfs_file_fallocate
  xfs: move the xfs_is_always_cow_inode check into xfs_alloc_file_space
  xfs: call xfs_flush_unmap_range from xfs_free_file_space
  fs: sort out the fallocate mode vs flag mess
  ext4: remove tracing for FALLOC_FL_NO_HIDE_STALE
  block: remove checks for FALLOC_FL_NO_HIDE_STALE

Link: https://lore.kernel.org/r/20240827065123.1762168-1-hch@lst.deSigned-off-by: Christian Brauner <brauner@kernel.org>

block/fops.c

@@ -771,7 +771,7 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 #define	BLKDEV_FALLOC_FL_SUPPORTED					\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
-		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
+		 FALLOC_FL_ZERO_RANGE)
 
 static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
@@ -830,14 +830,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 					     len >> SECTOR_SHIFT, GFP_KERNEL,
 					     BLKDEV_ZERO_NOFALLBACK);
 		break;
-	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
-		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
-		if (error)
-			goto fail;
-
-		error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
-					     len >> SECTOR_SHIFT, GFP_KERNEL);
-		break;
 	default:
 		error = -EOPNOTSUPP;
 	}

fs/open.c

@@ -252,40 +252,39 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (offset < 0 || len <= 0)
 		return -EINVAL;
 
-	/* Return error if mode is not supported */
-	if (mode & ~FALLOC_FL_SUPPORTED_MASK)
+	if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE))
 		return -EOPNOTSUPP;
 
-	/* Punch hole and zero range are mutually exclusive */
-	if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
-	    (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
+	/*
+	 * Modes are exclusive, even if that is not obvious from the encoding
+	 * as bit masks and the mix with the flag in the same namespace.
+	 *
+	 * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is
+	 * encoded as no bit set.
+	 */
+	switch (mode & FALLOC_FL_MODE_MASK) {
+	case FALLOC_FL_ALLOCATE_RANGE:
+	case FALLOC_FL_UNSHARE_RANGE:
+	case FALLOC_FL_ZERO_RANGE:
+		break;
+	case FALLOC_FL_PUNCH_HOLE:
+		if (!(mode & FALLOC_FL_KEEP_SIZE))
 			return -EOPNOTSUPP;
-
-	/* Punch hole must have keep size set */
-	if ((mode & FALLOC_FL_PUNCH_HOLE) &&
-	    !(mode & FALLOC_FL_KEEP_SIZE))
+		break;
+	case FALLOC_FL_COLLAPSE_RANGE:
+	case FALLOC_FL_INSERT_RANGE:
+		if (mode & FALLOC_FL_KEEP_SIZE)
 			return -EOPNOTSUPP;
-
-	/* Collapse range should only be used exclusively. */
-	if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
-	    (mode & ~FALLOC_FL_COLLAPSE_RANGE))
-		return -EINVAL;
-
-	/* Insert range should only be used exclusively. */
-	if ((mode & FALLOC_FL_INSERT_RANGE) &&
-	    (mode & ~FALLOC_FL_INSERT_RANGE))
-		return -EINVAL;
-
-	/* Unshare range should only be used with allocate mode. */
-	if ((mode & FALLOC_FL_UNSHARE_RANGE) &&
-	    (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE)))
-		return -EINVAL;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 
 	/*
-	 * We can only allow pure fallocate on append only files
+	 * On append-only files only space preallocation is supported.
 	 */
 	if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
 		return -EPERM;

fs/xfs/xfs_bmap_util.c

@@ -653,6 +653,9 @@ xfs_alloc_file_space(
 	xfs_bmbt_irec_t		imaps[1], *imapp;
 	int			error;
 
+	if (xfs_is_always_cow_inode(ip))
+		return 0;
+
 	trace_xfs_alloc_file_space(ip);
 
 	if (xfs_is_shutdown(mp))
@@ -848,6 +851,14 @@ xfs_free_file_space(
 	if (len <= 0)	/* if nothing being freed */
 		return 0;
 
+	/*
+	 * Now AIO and DIO has drained we flush and (if necessary) invalidate
+	 * the cached range over the first operation we are about to run.
+	 */
+	error = xfs_flush_unmap_range(ip, offset, len);
+	if (error)
+		return error;
+
 	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 

include/linux/falloc.h

@@ -25,7 +25,13 @@ struct space_resv {
 #define FS_IOC_UNRESVSP64	_IOW('X', 43, struct space_resv)
 #define FS_IOC_ZERO_RANGE	_IOW('X', 57, struct space_resv)
 
-#define	FALLOC_FL_SUPPORTED_MASK	(FALLOC_FL_KEEP_SIZE |		\
+/*
+ * Mask of all supported fallocate modes.  Only one can be set at a time.
+ *
+ * In addition to the mode bit, the mode argument can also encode flags.
+ * FALLOC_FL_KEEP_SIZE is the only supported flag so far.
+ */
+#define FALLOC_FL_MODE_MASK	(FALLOC_FL_ALLOCATE_RANGE |	\
 				 FALLOC_FL_PUNCH_HOLE |		\
 				 FALLOC_FL_COLLAPSE_RANGE |	\
 				 FALLOC_FL_ZERO_RANGE |		\

include/trace/events/ext4.h

@@ -91,7 +91,6 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 #define show_falloc_mode(mode) __print_flags(mode, "|",		\
 	{ FALLOC_FL_KEEP_SIZE,		"KEEP_SIZE"},		\
 	{ FALLOC_FL_PUNCH_HOLE,		"PUNCH_HOLE"},		\
-	{ FALLOC_FL_NO_HIDE_STALE,	"NO_HIDE_STALE"},	\
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 

include/uapi/linux/falloc.h

@@ -2,6 +2,7 @@
 #ifndef _UAPI_FALLOC_H_
 #define _UAPI_FALLOC_H_
 
+#define FALLOC_FL_ALLOCATE_RANGE 0x00 /* allocate range */
 #define FALLOC_FL_KEEP_SIZE	0x01 /* default is extend size */
 #define FALLOC_FL_PUNCH_HOLE	0x02 /* de-allocates range */
 #define FALLOC_FL_NO_HIDE_STALE	0x04 /* reserved codepoint */