/*
* Process a bmap update intent item that was recovered from the log.
* We need to update some inode's bmbt.
*/
int
xfs_bui_recover(
struct xfs_mount *mp,
struct xfs_bui_log_item *buip,
struct xfs_defer_ops *dfops)
{
int error = 0;
unsigned int bui_type;
struct xfs_map_extent *bmap;
xfs_fsblock_t startblock_fsb;
xfs_fsblock_t inode_fsb;
xfs_filblks_t count;
bool op_ok;
struct xfs_bud_log_item *budp;
enum xfs_bmap_intent_type type;
int whichfork;
xfs_exntst_t state;
struct xfs_trans *tp;
struct xfs_inode *ip = NULL;
struct xfs_bmbt_irec irec;
ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
/* Only one mapping operation per BUI... */
if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
xfs_bui_release(buip);
return -EIO;
}
/*
* First check the validity of the extent described by the
* BUI. If anything is bad, then toss the BUI.
*/
bmap = &buip->bui_format.bui_extents[0];
startblock_fsb = XFS_BB_TO_FSB(mp,
XFS_FSB_TO_DADDR(mp, bmap->me_startblock));
inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp,
XFS_INO_TO_FSB(mp, bmap->me_owner)));
switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) {
case XFS_BMAP_MAP:
case XFS_BMAP_UNMAP:
op_ok = true;
break;
default:
op_ok = false;
break;
}
if (!op_ok || startblock_fsb == 0 ||
bmap->me_len == 0 ||
inode_fsb == 0 ||
startblock_fsb >= mp->m_sb.sb_dblocks ||
bmap->me_len >= mp->m_sb.sb_agblocks ||
inode_fsb >= mp->m_sb.sb_dblocks ||
(bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS)) {
/*
* This will pull the BUI from the AIL and
* free the memory associated with it.
*/
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
xfs_bui_release(buip);
return -EIO;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
if (error)
return error;
budp = xfs_trans_get_bud(tp, buip);
/* Grab the inode. */
error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip);
if (error)
goto err_inode;
if (VFS_I(ip)->i_nlink == 0)
xfs_iflags_set(ip, XFS_IRECOVERY);
/* Process deferred bmap item. */
state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
XFS_ATTR_FORK : XFS_DATA_FORK;
bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
switch (bui_type) {
case XFS_BMAP_MAP:
case XFS_BMAP_UNMAP:
type = bui_type;
break;
default:
error = -EFSCORRUPTED;
goto err_inode;
}
xfs_trans_ijoin(tp, ip, 0);
count = bmap->me_len;
error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type,
ip, whichfork, bmap->me_startoff,
bmap->me_startblock, &count, state);
if (error)
goto err_inode;
if (count > 0) {
ASSERT(type == XFS_BMAP_UNMAP);
irec.br_startblock = bmap->me_startblock;
irec.br_blockcount = count;
irec.br_startoff = bmap->me_startoff;
irec.br_state = state;
error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec);
if (error)
goto err_inode;
}
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
return error;
err_inode:
xfs_trans_cancel(tp);
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
}
return error;
}
/*
* Unmap a range of blocks from a file, then map other blocks into the hole.
* The range to unmap is (destoff : destoff + srcioff + irec->br_blockcount).
* The extent irec is mapped into dest at irec->br_startoff.
*/
STATIC int
xfs_reflink_remap_extent(
struct xfs_inode *ip,
struct xfs_bmbt_irec *irec,
xfs_fileoff_t destoff,
xfs_off_t new_isize)
{
struct xfs_mount *mp = ip->i_mount;
bool real_extent = xfs_bmap_is_real_extent(irec);
struct xfs_trans *tp;
xfs_fsblock_t firstfsb;
unsigned int resblks;
struct xfs_defer_ops dfops;
struct xfs_bmbt_irec uirec;
xfs_filblks_t rlen;
xfs_filblks_t unmap_len;
xfs_off_t newlen;
int error;
unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
trace_xfs_reflink_punch_range(ip, destoff, unmap_len);
/* No reflinking if we're low on space */
if (real_extent) {
error = xfs_reflink_ag_has_free_space(mp,
XFS_FSB_TO_AGNO(mp, irec->br_startblock));
if (error)
goto out;
}
/* Start a rolling transaction to switch the mappings */
resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* If we're not just clearing space, then do we have enough quota? */
if (real_extent) {
error = xfs_trans_reserve_quota_nblks(tp, ip,
irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
if (error)
goto out_cancel;
}
trace_xfs_reflink_remap(ip, irec->br_startoff,
irec->br_blockcount, irec->br_startblock);
/* Unmap the old blocks in the data fork. */
rlen = unmap_len;
while (rlen) {
xfs_defer_init(&dfops, &firstfsb);
error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
&firstfsb, &dfops);
if (error)
goto out_defer;
/*
* Trim the extent to whatever got unmapped.
* Remember, bunmapi works backwards.
*/
uirec.br_startblock = irec->br_startblock + rlen;
uirec.br_startoff = irec->br_startoff + rlen;
uirec.br_blockcount = unmap_len - rlen;
unmap_len = rlen;
/* If this isn't a real mapping, we're done. */
if (!real_extent || uirec.br_blockcount == 0)
goto next_extent;
trace_xfs_reflink_remap(ip, uirec.br_startoff,
uirec.br_blockcount, uirec.br_startblock);
/* Update the refcount tree */
error = xfs_refcount_increase_extent(mp, &dfops, &uirec);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(mp, &dfops, ip, &uirec);
if (error)
goto out_defer;
/* Update quota accounting. */
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
uirec.br_blockcount);
/* Update dest isize if needed. */
newlen = XFS_FSB_TO_B(mp,
uirec.br_startoff + uirec.br_blockcount);
newlen = min_t(xfs_off_t, newlen, new_isize);
if (newlen > i_size_read(VFS_I(ip))) {
trace_xfs_reflink_update_inode_size(ip, newlen);
i_size_write(VFS_I(ip), newlen);
ip->i_d.di_size = newlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
next_extent:
/* Process all the deferred stuff. */
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto out_defer;
}
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_remap_extent_error(ip, error, _RET_IP_);
return error;
}
/*
* Pass in a delayed allocate extent, convert it to real extents;
* return to the caller the extent we create which maps on top of
* the originating callers request.
*
* Called without a lock on the inode.
*
* We no longer bother to look at the incoming map - all we have to
* guarantee is that whatever we allocate fills the required range.
*/
int
xfs_iomap_write_allocate(
xfs_inode_t *ip,
xfs_off_t offset,
size_t count,
xfs_bmbt_irec_t *map,
int *retmap)
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t offset_fsb, last_block;
xfs_fileoff_t end_fsb, map_start_fsb;
xfs_fsblock_t first_block;
xfs_bmap_free_t free_list;
xfs_filblks_t count_fsb;
xfs_bmbt_irec_t imap;
xfs_trans_t *tp;
int nimaps, committed;
int error = 0;
int nres;
*retmap = 0;
/*
* Make sure that the dquots are there.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return XFS_ERROR(error);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
count_fsb = map->br_blockcount;
map_start_fsb = map->br_startoff;
XFS_STATS_ADD(xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb));
while (count_fsb != 0) {
/*
* Set up a transaction with which to allocate the
* backing store for the file. Do allocations in a
* loop until we get some space in the range we are
* interested in. The other space that might be allocated
* is in the delayed allocation extent on which we sit
* but before our buffer starts.
*/
nimaps = 0;
while (nimaps == 0) {
tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
tp->t_flags |= XFS_TRANS_RESERVE;
nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
error = xfs_trans_reserve(tp, nres,
XFS_WRITE_LOG_RES(mp),
0, XFS_TRANS_PERM_LOG_RES,
XFS_WRITE_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
return XFS_ERROR(error);
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
xfs_bmap_init(&free_list, &first_block);
/*
* it is possible that the extents have changed since
* we did the read call as we dropped the ilock for a
* while. We have to be careful about truncates or hole
* punchs here - we are not allowed to allocate
* non-delalloc blocks here.
*
* The only protection against truncation is the pages
* for the range we are being asked to convert are
* locked and hence a truncate will block on them
* first.
*
* As a result, if we go beyond the range we really
* need and hit an delalloc extent boundary followed by
* a hole while we have excess blocks in the map, we
* will fill the hole incorrectly and overrun the
* transaction reservation.
*
* Using a single map prevents this as we are forced to
* check each map we look for overlap with the desired
* range and abort as soon as we find it. Also, given
* that we only return a single map, having one beyond
* what we can return is probably a bit silly.
*
* We also need to check that we don't go beyond EOF;
* this is a truncate optimisation as a truncate sets
* the new file size before block on the pages we
* currently have locked under writeback. Because they
* are about to be tossed, we don't need to write them
* back....
*/
nimaps = 1;
end_fsb = XFS_B_TO_FSB(mp, ip->i_size);
error = xfs_bmap_last_offset(NULL, ip, &last_block,
XFS_DATA_FORK);
if (error)
goto trans_cancel;
last_block = XFS_FILEOFF_MAX(last_block, end_fsb);
if ((map_start_fsb + count_fsb) > last_block) {
count_fsb = last_block - map_start_fsb;
if (count_fsb == 0) {
error = EAGAIN;
goto trans_cancel;
}
}
/* Go get the actual blocks */
error = xfs_bmapi(tp, ip, map_start_fsb, count_fsb,
XFS_BMAPI_WRITE, &first_block, 1,
&imap, &nimaps, &free_list, NULL);
if (error)
goto trans_cancel;
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error)
goto trans_cancel;
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
if (error)
goto error0;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
/*
* See if we were able to allocate an extent that
* covers at least part of the callers request
*/
if (!(imap.br_startblock || XFS_IS_REALTIME_INODE(ip)))
return xfs_cmn_err_fsblock_zero(ip, &imap);
if ((offset_fsb >= imap.br_startoff) &&
(offset_fsb < (imap.br_startoff +
imap.br_blockcount))) {
*map = imap;
*retmap = 1;
XFS_STATS_INC(xs_xstrat_quick);
return 0;
}
/*
* So far we have not mapped the requested part of the
* file, just surrounding data, try again.
*/
count_fsb -= imap.br_blockcount;
map_start_fsb = imap.br_startoff + imap.br_blockcount;
}
trans_cancel:
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
error0:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return XFS_ERROR(error);
}
/*
* Remap part of the CoW fork into the data fork.
*
* We aim to remap the range starting at @offset_fsb and ending at @end_fsb
* into the data fork; this function will remap what it can (at the end of the
* range) and update @end_fsb appropriately. Each remap gets its own
* transaction because we can end up merging and splitting bmbt blocks for
* every remap operation and we'd like to keep the block reservation
* requirements as low as possible.
*/
STATIC int
xfs_reflink_end_cow_extent(
struct xfs_inode *ip,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t *end_fsb)
{
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_filblks_t rlen;
unsigned int resblks;
int error;
/* No COW extents? That's easy! */
if (ifp->if_bytes == 0) {
*end_fsb = offset_fsb;
return 0;
}
resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp);
if (error)
return error;
/*
* Lock the inode. We have to ijoin without automatic unlock because
* the lead transaction is the refcountbt record deletion; the data
* fork update follows as a deferred log item.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* 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 (!xfs_iext_lookup_extent_before(ip, ifp, end_fsb, &icur, &got) ||
got.br_startoff + got.br_blockcount <= offset_fsb) {
*end_fsb = offset_fsb;
goto out_cancel;
}
/*
* Structure copy @got into @del, then trim @del to the range that we
* were asked to remap. We preserve @got for the eventual CoW fork
* deletion; from now on @del represents the mapping that we're
* actually remapping.
*/
del = got;
xfs_trim_extent(&del, offset_fsb, *end_fsb - offset_fsb);
ASSERT(del.br_blockcount > 0);
/*
* Only remap real extents that contain data. With AIO, speculative
* preallocations can leak into the range we are called upon, and we
* need to skip them.
*/
if (!xfs_bmap_is_real_extent(&got)) {
*end_fsb = del.br_startoff;
goto out_cancel;
}
/* Unmap the old blocks in the data fork. */
rlen = del.br_blockcount;
error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
if (error)
goto out_cancel;
/* Trim the extent to whatever got unmapped. */
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, del.br_startblock,
del.br_blockcount);
if (error)
goto out_cancel;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp, ip, &del);
if (error)
goto out_cancel;
/* Charge this new data fork mapping to the on-disk quota. */
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
(long)del.br_blockcount);
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
/* Update the caller about how much progress we made. */
*end_fsb = del.br_startoff;
return 0;
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* Pass in a delayed allocate extent, convert it to real extents;
* return to the caller the extent we create which maps on top of
* the originating callers request.
*
* Called without a lock on the inode.
*/
int
xfs_iomap_write_allocate(
xfs_inode_t *ip,
xfs_off_t offset,
size_t count,
xfs_bmbt_irec_t *map,
int *retmap)
{
xfs_mount_t *mp = ip->i_mount;
xfs_iocore_t *io = &ip->i_iocore;
xfs_fileoff_t offset_fsb, last_block;
xfs_fileoff_t end_fsb, map_start_fsb;
xfs_fsblock_t first_block;
xfs_bmap_free_t free_list;
xfs_filblks_t count_fsb;
xfs_bmbt_irec_t imap[XFS_STRAT_WRITE_IMAPS];
xfs_trans_t *tp;
int i, nimaps, committed;
int error = 0;
int nres;
*retmap = 0;
/*
* Make sure that the dquots are there.
*/
if ((error = XFS_QM_DQATTACH(mp, ip, 0)))
return XFS_ERROR(error);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
count_fsb = map->br_blockcount;
map_start_fsb = map->br_startoff;
XFS_STATS_ADD(xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb));
while (count_fsb != 0) {
/*
* Set up a transaction with which to allocate the
* backing store for the file. Do allocations in a
* loop until we get some space in the range we are
* interested in. The other space that might be allocated
* is in the delayed allocation extent on which we sit
* but before our buffer starts.
*/
nimaps = 0;
while (nimaps == 0) {
tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
error = xfs_trans_reserve(tp, nres,
XFS_WRITE_LOG_RES(mp),
0, XFS_TRANS_PERM_LOG_RES,
XFS_WRITE_LOG_COUNT);
if (error == ENOSPC) {
error = xfs_trans_reserve(tp, 0,
XFS_WRITE_LOG_RES(mp),
0,
XFS_TRANS_PERM_LOG_RES,
XFS_WRITE_LOG_COUNT);
}
if (error) {
xfs_trans_cancel(tp, 0);
return XFS_ERROR(error);
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, ip);
XFS_BMAP_INIT(&free_list, &first_block);
nimaps = XFS_STRAT_WRITE_IMAPS;
/*
* Ensure we don't go beyond eof - it is possible
* the extents changed since we did the read call,
* we dropped the ilock in the interim.
*/
end_fsb = XFS_B_TO_FSB(mp, ip->i_d.di_size);
xfs_bmap_last_offset(NULL, ip, &last_block,
XFS_DATA_FORK);
last_block = XFS_FILEOFF_MAX(last_block, end_fsb);
if ((map_start_fsb + count_fsb) > last_block) {
count_fsb = last_block - map_start_fsb;
if (count_fsb == 0) {
error = EAGAIN;
goto trans_cancel;
}
}
/* Go get the actual blocks */
error = XFS_BMAPI(mp, tp, io, map_start_fsb, count_fsb,
XFS_BMAPI_WRITE, &first_block, 1,
imap, &nimaps, &free_list, NULL);
if (error)
goto trans_cancel;
error = xfs_bmap_finish(&tp, &free_list,
first_block, &committed);
if (error)
goto trans_cancel;
error = xfs_trans_commit(tp,
XFS_TRANS_RELEASE_LOG_RES, NULL);
if (error)
goto error0;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
/*
* See if we were able to allocate an extent that
* covers at least part of the callers request
*/
for (i = 0; i < nimaps; i++) {
if (unlikely(!imap[i].br_startblock &&
!(io->io_flags & XFS_IOCORE_RT)))
return xfs_cmn_err_fsblock_zero(ip, &imap[i]);
if ((offset_fsb >= imap[i].br_startoff) &&
(offset_fsb < (imap[i].br_startoff +
imap[i].br_blockcount))) {
*map = imap[i];
*retmap = 1;
XFS_STATS_INC(xs_xstrat_quick);
return 0;
}
count_fsb -= imap[i].br_blockcount;
}
/* So far we have not mapped the requested part of the
* file, just surrounding data, try again.
*/
nimaps--;
map_start_fsb = imap[nimaps].br_startoff +
imap[nimaps].br_blockcount;
}
trans_cancel:
xfs_bmap_cancel(&free_list);
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
error0:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return XFS_ERROR(error);
}