/*
* Zero any on disk space between the current EOF and the new, larger EOF.
*
* This handles the normal case of zeroing the remainder of the last block in
* the file and the unusual case of zeroing blocks out beyond the size of the
* file. This second case only happens with fixed size extents and when the
* system crashes before the inode size was updated but after blocks were
* allocated.
*
* Expects the iolock to be held exclusive, and will take the ilock internally.
*/
int /* error (positive) */
xfs_zero_eof(
struct xfs_inode *ip,
xfs_off_t offset, /* starting I/O offset */
xfs_fsize_t isize, /* current inode size */
bool *did_zeroing)
{
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
trace_xfs_zero_eof(ip, isize, offset - isize);
return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
}
/*
* If we're reflinking to a point past the destination file's EOF, we must
* zero any speculative post-EOF preallocations that sit between the old EOF
* and the destination file offset.
*/
static int
xfs_reflink_zero_posteof(
struct xfs_inode *ip,
loff_t pos)
{
loff_t isize = i_size_read(VFS_I(ip));
if (pos <= isize)
return 0;
trace_xfs_zero_eof(ip, isize, pos - isize);
return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
&xfs_iomap_ops);
}
/*
* 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;
loff_t isize;
restart:
error = generic_write_checks(iocb, from);
if (error <= 0)
return error;
error = xfs_break_layouts(inode, iolock, BREAK_WRITE);
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);
isize = i_size_read(inode);
if (iocb->ki_pos > isize) {
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;
}
trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
NULL, &xfs_iomap_ops);
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;
}
/*
* Zero any on disk space between the current EOF and the new, larger EOF.
*
* This handles the normal case of zeroing the remainder of the last block in
* the file and the unusual case of zeroing blocks out beyond the size of the
* file. This second case only happens with fixed size extents and when the
* system crashes before the inode size was updated but after blocks were
* allocated.
*
* Expects the iolock to be held exclusive, and will take the ilock internally.
*/
int /* error (positive) */
xfs_zero_eof(
struct xfs_inode *ip,
xfs_off_t offset, /* starting I/O offset */
xfs_fsize_t isize, /* current inode size */
bool *did_zeroing)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t start_zero_fsb;
xfs_fileoff_t end_zero_fsb;
xfs_fileoff_t zero_count_fsb;
xfs_fileoff_t last_fsb;
xfs_fileoff_t zero_off;
xfs_fsize_t zero_len;
int nimaps;
int error = 0;
struct xfs_bmbt_irec imap;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
trace_xfs_zero_eof(ip, isize, offset - isize);
/*
* First handle zeroing the block on which isize resides.
*
* We only zero a part of that block so it is handled specially.
*/
if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
if (error)
return error;
}
/*
* Calculate the range between the new size and the old where blocks
* needing to be zeroed may exist.
*
* To get the block where the last byte in the file currently resides,
* we need to subtract one from the size and truncate back to a block
* boundary. We subtract 1 in case the size is exactly on a block
* boundary.
*/
last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
if (last_fsb == end_zero_fsb) {
/*
* The size was only incremented on its last block.
* We took care of that above, so just return.
*/
return 0;
}
ASSERT(start_zero_fsb <= end_zero_fsb);
while (start_zero_fsb <= end_zero_fsb) {
nimaps = 1;
zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
&imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
ASSERT(nimaps > 0);
if (imap.br_state == XFS_EXT_UNWRITTEN ||
imap.br_startblock == HOLESTARTBLOCK) {
start_zero_fsb = imap.br_startoff + imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
continue;
}
/*
* There are blocks we need to zero.
*/
zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
if ((zero_off + zero_len) > offset)
zero_len = offset - zero_off;
error = xfs_iozero(ip, zero_off, zero_len);
if (error)
return error;
*did_zeroing = true;
start_zero_fsb = imap.br_startoff + imap.br_blockcount;
ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
}
return 0;
}
