STATIC long
xfs_file_fallocate(
struct file *file,
int mode,
loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct xfs_inode *ip = XFS_I(inode);
long error;
enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL;
loff_t new_size = 0;
bool do_file_insert = false;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (mode & ~XFS_FALLOC_FL_SUPPORTED)
return -EOPNOTSUPP;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(inode, &iolock);
if (error)
goto out_unlock;
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
unsigned int blksize_mask = i_blocksize(inode) - 1;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
/*
* There is no need to overlap collapse range with EOF,
* in which case it is effectively a truncate operation
*/
if (offset + len >= i_size_read(inode)) {
error = -EINVAL;
goto out_unlock;
}
new_size = i_size_read(inode) - len;
error = xfs_collapse_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_INSERT_RANGE) {
unsigned int blksize_mask = i_blocksize(inode) - 1;
new_size = i_size_read(inode) + len;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
/* check the new inode size does not wrap through zero */
if (new_size > inode->i_sb->s_maxbytes) {
error = -EFBIG;
goto out_unlock;
}
/* Offset should be less than i_size */
if (offset >= i_size_read(inode)) {
error = -EINVAL;
goto out_unlock;
}
do_file_insert = true;
} else {
flags |= XFS_PREALLOC_SET;
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;
}
if (mode & FALLOC_FL_ZERO_RANGE)
error = xfs_zero_file_space(ip, offset, len);
else {
if (mode & FALLOC_FL_UNSHARE_RANGE) {
error = xfs_reflink_unshare(ip, offset, len);
if (error)
goto out_unlock;
}
error = xfs_alloc_file_space(ip, offset, len,
XFS_BMAPI_PREALLOC);
}
if (error)
goto out_unlock;
}
if (file->f_flags & O_DSYNC)
flags |= XFS_PREALLOC_SYNC;
error = xfs_update_prealloc_flags(ip, flags);
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_vn_setattr_size(file_dentry(file), &iattr);
if (error)
goto out_unlock;
}
/*
* Perform hole insertion now that the file size has been
* updated so that if we crash during the operation we don't
* leave shifted extents past EOF and hence losing access to
* the data that is contained within them.
*/
if (do_file_insert)
error = xfs_insert_file_space(ip, offset, len);
out_unlock:
xfs_iunlock(ip, iolock);
return error;
}
int
xfs_ioc_space(
struct xfs_inode *ip,
struct inode *inode,
struct file *filp,
int ioflags,
unsigned int cmd,
xfs_flock64_t *bf)
{
struct iattr iattr;
enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL;
int error;
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
return -EPERM;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (filp->f_flags & O_DSYNC)
flags |= XFS_PREALLOC_SYNC;
if (ioflags & XFS_IO_INVIS)
flags |= XFS_PREALLOC_INVISIBLE;
error = mnt_want_write_file(filp);
if (error)
return error;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(inode, &iolock, false);
if (error)
goto out_unlock;
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
switch (bf->l_whence) {
case 0: /*SEEK_SET*/
break;
case 1: /*SEEK_CUR*/
bf->l_start += filp->f_pos;
break;
case 2: /*SEEK_END*/
bf->l_start += XFS_ISIZE(ip);
break;
default:
error = -EINVAL;
goto out_unlock;
}
/*
* length of <= 0 for resv/unresv/zero is invalid. length for
* alloc/free is ignored completely and we have no idea what userspace
* might have set it to, so set it to zero to allow range
* checks to pass.
*/
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
if (bf->l_len <= 0) {
error = -EINVAL;
goto out_unlock;
}
break;
default:
bf->l_len = 0;
break;
}
if (bf->l_start < 0 ||
bf->l_start > inode->i_sb->s_maxbytes ||
bf->l_start + bf->l_len < 0 ||
bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) {
error = -EINVAL;
goto out_unlock;
}
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
flags |= XFS_PREALLOC_SET;
error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
flags |= XFS_PREALLOC_SET;
error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
XFS_BMAPI_PREALLOC);
break;
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_ALLOCSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP:
case XFS_IOC_FREESP64:
flags |= XFS_PREALLOC_CLEAR;
if (bf->l_start > XFS_ISIZE(ip)) {
error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
bf->l_start - XFS_ISIZE(ip), 0);
if (error)
goto out_unlock;
}
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = bf->l_start;
error = xfs_setattr_size(ip, &iattr);
break;
default:
ASSERT(0);
error = -EINVAL;
}
if (error)
goto out_unlock;
error = xfs_update_prealloc_flags(ip, flags);
out_unlock:
xfs_iunlock(ip, iolock);
mnt_drop_write_file(filp);
return error;
}
/*
* Get a layout for the pNFS client.
*/
int
xfs_fs_map_blocks(
struct inode *inode,
loff_t offset,
u64 length,
struct iomap *iomap,
bool write,
u32 *device_generation)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec imap;
xfs_fileoff_t offset_fsb, end_fsb;
loff_t limit;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
uint lock_flags;
int error = 0;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* We can't export inodes residing on the realtime device. The realtime
* device doesn't have a UUID to identify it, so the client has no way
* to find it.
*/
if (XFS_IS_REALTIME_INODE(ip))
return -ENXIO;
/*
* Lock out any other I/O before we flush and invalidate the pagecache,
* and then hand out a layout to the remote system. This is very
* similar to direct I/O, except that the synchronization is much more
* complicated. See the comment near xfs_break_layouts for a detailed
* explanation.
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL);
error = -EINVAL;
limit = mp->m_super->s_maxbytes;
if (!write)
limit = max(limit, round_up(i_size_read(inode),
inode->i_sb->s_blocksize));
if (offset > limit)
goto out_unlock;
if (offset > limit - length)
length = limit - offset;
error = filemap_write_and_wait(inode->i_mapping);
if (error)
goto out_unlock;
error = invalidate_inode_pages2(inode->i_mapping);
if (WARN_ON_ONCE(error))
return error;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
lock_flags = xfs_ilock_data_map_shared(ip);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
&imap, &nimaps, bmapi_flags);
xfs_iunlock(ip, lock_flags);
if (error)
goto out_unlock;
if (write) {
enum xfs_prealloc_flags flags = 0;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) {
/*
* xfs_iomap_write_direct() expects to take ownership of
* the shared ilock.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_iomap_write_direct(ip, offset, length,
&imap, nimaps);
if (error)
goto out_unlock;
/*
* Ensure the next transaction is committed
* synchronously so that the blocks allocated and
* handed out to the client are guaranteed to be
* present even after a server crash.
*/
flags |= XFS_PREALLOC_SET | XFS_PREALLOC_SYNC;
}
error = xfs_update_prealloc_flags(ip, flags);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
xfs_bmbt_to_iomap(ip, iomap, &imap);
*device_generation = mp->m_generation;
return error;
out_unlock:
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}