/*
* Remap parts of a file's data fork after a successful CoW.
*/
int
xfs_reflink_end_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
int error = 0;
trace_xfs_reflink_end_cow(ip, offset, count);
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/*
* Walk backwards until we're out of the I/O range. The loop function
* repeatedly cycles the ILOCK to allocate one transaction per remapped
* extent.
*
* If we're being called by writeback then the the pages will still
* have PageWriteback set, which prevents races with reflink remapping
* and truncate. Reflink remapping prevents races with writeback by
* taking the iolock and mmaplock before flushing the pages and
* remapping, which means there won't be any further writeback or page
* cache dirtying until the reflink completes.
*
* We should never have two threads issuing writeback for the same file
* region. There are also have post-eof checks in the writeback
* preparation code so that we don't bother writing out pages that are
* about to be truncated.
*
* If we're being called as part of directio write completion, the dio
* count is still elevated, which reflink and truncate will wait for.
* Reflink remapping takes the iolock and mmaplock and waits for
* pending dio to finish, which should prevent any directio until the
* remap completes. Multiple concurrent directio writes to the same
* region are handled by end_cow processing only occurring for the
* threads which succeed; the outcome of multiple overlapping direct
* writes is not well defined anyway.
*
* It's possible that a buffered write and a direct write could collide
* here (the buffered write stumbles in after the dio flushes and
* invalidates the page cache and immediately queues writeback), but we
* have never supported this 100%. If either disk write succeeds the
* blocks will be remapped.
*/
while (end_fsb > offset_fsb && !error)
error = xfs_reflink_end_cow_extent(ip, offset_fsb, &end_fsb);
if (error)
trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
return error;
}
/*
* Remap parts of a file's data fork after a successful CoW.
*/
int
xfs_reflink_end_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error;
unsigned int resblks;
xfs_filblks_t rlen;
xfs_extnum_t idx;
trace_xfs_reflink_end_cow(ip, offset, count);
/* No COW extents? That's easy! */
if (ifp->if_bytes == 0)
return 0;
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/*
* Start a rolling transaction to switch the mappings. We're
* unlikely ever to have to remap 16T worth of single-block
* extents, so just cap the worst case extent count to 2^32-1.
* Stick a warning in just in case, and avoid 64-bit division.
*/
BUILD_BUG_ON(MAX_RW_COUNT > UINT_MAX);
if (end_fsb - offset_fsb > UINT_MAX) {
error = -EFSCORRUPTED;
xfs_force_shutdown(ip->i_mount, SHUTDOWN_CORRUPT_INCORE);
ASSERT(0);
goto out;
}
resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount,
(unsigned int)(end_fsb - offset_fsb),
XFS_DATA_FORK);
error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
resblks, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* If there is a hole at end_fsb - 1 go to the previous extent */
if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
got.br_startoff > end_fsb) {
/*
* In case of racing, overlapping AIO writes no COW extents
* might be left by the time I/O completes for the loser of
* the race. In that case we are done.
*/
if (idx <= 0)
goto out_cancel;
xfs_iext_get_extent(ifp, --idx, &got);
}
/* Walk backwards until we're out of the I/O range... */
while (got.br_startoff + got.br_blockcount > offset_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
/* Extent delete may have bumped idx forward */
if (!del.br_blockcount) {
idx--;
goto next_extent;
}
ASSERT(!isnullstartblock(got.br_startblock));
/*
* Don't remap unwritten extents; these are
* speculatively preallocated CoW extents that have been
* allocated but have not yet been involved in a write.
*/
if (got.br_state == XFS_EXT_UNWRITTEN) {
idx--;
goto next_extent;
}
/* Unmap the old blocks in the data fork. */
xfs_defer_init(&dfops, &firstfsb);
rlen = del.br_blockcount;
error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
&firstfsb, &dfops);
if (error)
goto out_defer;
/* Trim the extent to whatever got unmapped. */
if (rlen) {
xfs_trim_extent(&del, del.br_startoff + rlen,
del.br_blockcount - rlen);
}
trace_xfs_reflink_cow_remap(ip, &del);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
del.br_startblock, del.br_blockcount);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
if (error)
goto out_defer;
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto out_defer;
next_extent:
if (!xfs_iext_get_extent(ifp, idx, &got))
break;
}
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
goto out;
return 0;
out_defer:
xfs_defer_cancel(&dfops);
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
return error;
}
