/*
* Get a buffer for the bitmap or summary file block specified.
* The buffer is returned read and locked.
*/
int
xfs_rtbuf_get(
xfs_mount_t *mp, /* file system mount structure */
xfs_trans_t *tp, /* transaction pointer */
xfs_rtblock_t block, /* block number in bitmap or summary */
int issum, /* is summary not bitmap */
xfs_buf_t **bpp) /* output: buffer for the block */
{
xfs_buf_t *bp; /* block buffer, result */
xfs_inode_t *ip; /* bitmap or summary inode */
xfs_bmbt_irec_t map;
int nmap = 1;
int error; /* error value */
ip = issum ? mp->m_rsumip : mp->m_rbmip;
error = xfs_bmapi_read(ip, block, 1, &map, &nmap, XFS_DATA_FORK);
if (error)
return error;
if (nmap == 0 || !xfs_bmap_is_real_extent(&map))
return -EFSCORRUPTED;
ASSERT(map.br_startblock != NULLFSBLOCK);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map.br_startblock),
mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
if (error)
return error;
xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF
: XFS_BLFT_RTBITMAP_BUF);
*bpp = bp;
return 0;
}
/*
* Trim the mapping to the next block where there's a change in the
* shared/unshared status. More specifically, this means that we
* find the lowest-numbered extent of shared blocks that coincides with
* the given block mapping. If the shared extent overlaps the start of
* the mapping, trim the mapping to the end of the shared extent. If
* the shared region intersects the mapping, trim the mapping to the
* start of the shared extent. If there are no shared regions that
* overlap, just return the original extent.
*/
int
xfs_reflink_trim_around_shared(
struct xfs_inode *ip,
struct xfs_bmbt_irec *irec,
bool *shared,
bool *trimmed)
{
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t fbno;
xfs_extlen_t flen;
int error = 0;
/* Holes, unwritten, and delalloc extents cannot be shared */
if (!xfs_is_reflink_inode(ip) || !xfs_bmap_is_real_extent(irec)) {
*shared = false;
return 0;
}
trace_xfs_reflink_trim_around_shared(ip, irec);
agno = XFS_FSB_TO_AGNO(ip->i_mount, irec->br_startblock);
agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock);
aglen = irec->br_blockcount;
error = xfs_reflink_find_shared(ip->i_mount, NULL, agno, agbno,
aglen, &fbno, &flen, true);
if (error)
return error;
*shared = *trimmed = false;
if (fbno == NULLAGBLOCK) {
/* No shared blocks at all. */
return 0;
} else if (fbno == agbno) {
/*
* The start of this extent is shared. Truncate the
* mapping at the end of the shared region so that a
* subsequent iteration starts at the start of the
* unshared region.
*/
irec->br_blockcount = flen;
*shared = true;
if (flen != aglen)
*trimmed = true;
return 0;
} else {
/*
* There's a shared extent midway through this extent.
* Truncate the mapping at the start of the shared
* extent so that a subsequent iteration starts at the
* start of the shared region.
*/
irec->br_blockcount = fbno - agbno;
*trimmed = true;
return 0;
}
}
/*
* The user wants to preemptively CoW all shared blocks in this file,
* which enables us to turn off the reflink flag. Iterate all
* extents which are not prealloc/delalloc to see which ranges are
* mentioned in the refcount tree, then read those blocks into the
* pagecache, dirty them, fsync them back out, and then we can update
* the inode flag. What happens if we run out of memory? :)
*/
STATIC int
xfs_reflink_dirty_extents(
struct xfs_inode *ip,
xfs_fileoff_t fbno,
xfs_filblks_t end,
xfs_off_t isize)
{
struct xfs_mount *mp = ip->i_mount;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t rbno;
xfs_extlen_t rlen;
xfs_off_t fpos;
xfs_off_t flen;
struct xfs_bmbt_irec map[2];
int nmaps;
int error = 0;
while (end - fbno > 0) {
nmaps = 1;
/*
* Look for extents in the file. Skip holes, delalloc, or
* unwritten extents; they can't be reflinked.
*/
error = xfs_bmapi_read(ip, fbno, end - fbno, map, &nmaps, 0);
if (error)
goto out;
if (nmaps == 0)
break;
if (!xfs_bmap_is_real_extent(&map[0]))
goto next;
map[1] = map[0];
while (map[1].br_blockcount) {
agno = XFS_FSB_TO_AGNO(mp, map[1].br_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, map[1].br_startblock);
aglen = map[1].br_blockcount;
error = xfs_reflink_find_shared(mp, NULL, agno, agbno,
aglen, &rbno, &rlen, true);
if (error)
goto out;
if (rbno == NULLAGBLOCK)
break;
/* Dirty the pages */
xfs_iunlock(ip, XFS_ILOCK_EXCL);
fpos = XFS_FSB_TO_B(mp, map[1].br_startoff +
(rbno - agbno));
flen = XFS_FSB_TO_B(mp, rlen);
if (fpos + flen > isize)
flen = isize - fpos;
error = iomap_file_dirty(VFS_I(ip), fpos, flen,
&xfs_iomap_ops);
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (error)
goto out;
map[1].br_blockcount -= (rbno - agbno + rlen);
map[1].br_startoff += (rbno - agbno + rlen);
map[1].br_startblock += (rbno - agbno + rlen);
}
next:
fbno = map[0].br_startoff + map[0].br_blockcount;
}
out:
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;
}
/* Clear the inode reflink flag if there are no shared extents. */
int
xfs_reflink_clear_inode_flag(
struct xfs_inode *ip,
struct xfs_trans **tpp)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t fbno;
xfs_filblks_t end;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t rbno;
xfs_extlen_t rlen;
struct xfs_bmbt_irec map;
int nmaps;
int error = 0;
ASSERT(xfs_is_reflink_inode(ip));
fbno = 0;
end = XFS_B_TO_FSB(mp, i_size_read(VFS_I(ip)));
while (end - fbno > 0) {
nmaps = 1;
/*
* Look for extents in the file. Skip holes, delalloc, or
* unwritten extents; they can't be reflinked.
*/
error = xfs_bmapi_read(ip, fbno, end - fbno, &map, &nmaps, 0);
if (error)
return error;
if (nmaps == 0)
break;
if (!xfs_bmap_is_real_extent(&map))
goto next;
agno = XFS_FSB_TO_AGNO(mp, map.br_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock);
aglen = map.br_blockcount;
error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
&rbno, &rlen, false);
if (error)
return error;
/* Is there still a shared block here? */
if (rbno != NULLAGBLOCK)
return 0;
next:
fbno = map.br_startoff + map.br_blockcount;
}
/*
* We didn't find any shared blocks so turn off the reflink flag.
* First, get rid of any leftover CoW mappings.
*/
error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
if (error)
return error;
/* Clear the inode flag. */
trace_xfs_reflink_unset_inode_flag(ip);
ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
xfs_inode_clear_cowblocks_tag(ip);
xfs_trans_ijoin(*tpp, ip, 0);
xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
return 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;
}
