STATIC int
xfs_vn_setattr(
struct dentry *dentry,
struct iattr *iattr)
{
struct xfs_inode *ip = XFS_I(d_inode(dentry));
int error;
if (iattr->ia_valid & ATTR_SIZE) {
uint iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(d_inode(dentry), &iolock, true);
if (!error) {
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
error = xfs_setattr_size(ip, iattr);
}
xfs_iunlock(ip, iolock);
} else {
error = xfs_setattr_nonsize(ip, iattr, 0);
}
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;
}
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;
}
/*
* Common pre-write limit and setup checks.
*
* Called with the iolocked held either shared and exclusive according to
* @iolock, and returns with it held. Might upgrade the iolock to exclusive
* if called for a direct write beyond i_size.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct kiocb *iocb,
struct iov_iter *from,
int *iolock)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t error = 0;
size_t count = iov_iter_count(from);
bool drained_dio = false;
restart:
error = generic_write_checks(iocb, from);
if (error <= 0)
return error;
error = xfs_break_layouts(inode, iolock);
if (error)
return error;
/*
* For changing security info in file_remove_privs() we need i_rwsem
* exclusively.
*/
if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
xfs_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
goto restart;
}
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write. If zeroing is needed and we are currently holding the
* iolock shared, we need to update it to exclusive which implies
* having to redo all checks before.
*
* We need to serialise against EOF updates that occur in IO
* completions here. We want to make sure that nobody is changing the
* size while we do this check until we have placed an IO barrier (i.e.
* hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
* The spinlock effectively forms a memory barrier once we have the
* XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
* and hence be able to correctly determine if we need to run zeroing.
*/
spin_lock(&ip->i_flags_lock);
if (iocb->ki_pos > i_size_read(inode)) {
spin_unlock(&ip->i_flags_lock);
if (!drained_dio) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
iov_iter_reexpand(from, count);
}
/*
* We now have an IO submission barrier in place, but
* AIO can do EOF updates during IO completion and hence
* we now need to wait for all of them to drain. Non-AIO
* DIO will have drained before we are given the
* XFS_IOLOCK_EXCL, and so for most cases this wait is a
* no-op.
*/
inode_dio_wait(inode);
drained_dio = true;
goto restart;
}
error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
if (error)
return error;
} else
spin_unlock(&ip->i_flags_lock);
/*
* Updating the timestamps will grab the ilock again from
* xfs_fs_dirty_inode, so we have to call it after dropping the
* lock above. Eventually we should look into a way to avoid
* the pointless lock roundtrip.
*/
if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
error = file_update_time(file);
if (error)
return error;
}
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
if (!IS_NOSEC(inode))
return file_remove_privs(file);
return 0;
}