fallocate should be a file operation

Currently all filesystems except XFS implement fallocate asynchronously,
while XFS forced a commit.  Both of these are suboptimal - in case of O_SYNC
I/O we really want our allocation on disk, especially for the !KEEP_SIZE
case where we actually grow the file with user-visible zeroes.  On the
other hand always commiting the transaction is a bad idea for fast-path
uses of fallocate like for example in recent Samba versions.   Given
that block allocation is a data plane operation anyway change it from
an inode operation to a file operation so that we have the file structure
available that lets us check for O_SYNC.

This also includes moving the code around for a few of the filesystems,
and remove the already unnedded S_ISDIR checks given that we only wire
up fallocate for regular files.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 56 insertions, 0 deletions

diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index ef51eb43e137..a55c1b46b219 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -37,6 +37,7 @@
 #include "xfs_trace.h"
 
 #include <linux/dcache.h>
+#include <linux/falloc.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 
@@ -882,6 +883,60 @@ out_unlock:
 	return ret;
 }
 
+STATIC long
+xfs_file_fallocate(
+	struct file	*file,
+	int		mode,
+	loff_t		offset,
+	loff_t		len)
+{
+	struct inode	*inode = file->f_path.dentry->d_inode;
+	long		error;
+	loff_t		new_size = 0;
+	xfs_flock64_t	bf;
+	xfs_inode_t	*ip = XFS_I(inode);
+	int		cmd = XFS_IOC_RESVSP;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	bf.l_whence = 0;
+	bf.l_start = offset;
+	bf.l_len = len;
+
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		cmd = XFS_IOC_UNRESVSP;
+
+	/* check the new inode size is valid before allocating */
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+	    offset + len > i_size_read(inode)) {
+		new_size = offset + len;
+		error = inode_newsize_ok(inode, new_size);
+		if (error)
+			goto out_unlock;
+	}
+
+	error = -xfs_change_file_space(ip, cmd, &bf, 0, XFS_ATTR_NOLOCK);
+	if (error)
+		goto out_unlock;
+
+	/* Change file size if needed */
+	if (new_size) {
+		struct iattr iattr;
+
+		iattr.ia_valid = ATTR_SIZE;
+		iattr.ia_size = new_size;
+		error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
+	}
+
+out_unlock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
+}
+
+
 STATIC int
 xfs_file_open(
 	struct inode	*inode,
@@ -1000,6 +1055,7 @@ const struct file_operations xfs_file_operations = {
 	.open		= xfs_file_open,
 	.release	= xfs_file_release,
 	.fsync		= xfs_file_fsync,
+	.fallocate	= xfs_file_fallocate,
 };
 
 const struct file_operations xfs_dir_file_operations = {