STATIC int
xfs_map_blocks(
struct inode *inode,
loff_t offset,
struct xfs_bmbt_irec *imap,
int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t count = 1 << inode->i_blkbits;
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (type == XFS_IO_UNWRITTEN)
bmapi_flags |= XFS_BMAPI_IGSTATE;
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
ASSERT(offset <= mp->m_super->s_maxbytes);
if (offset + count > mp->m_super->s_maxbytes)
count = mp->m_super->s_maxbytes - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
imap, &nimaps, bmapi_flags);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
return error;
if (type == XFS_IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
error = xfs_iomap_write_allocate(ip, offset, imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return error;
}
#ifdef DEBUG
if (type == XFS_IO_UNWRITTEN) {
ASSERT(nimaps);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
}
#endif
if (nimaps)
trace_xfs_map_blocks_found(ip, offset, count, type, imap);
return 0;
}
/* Does this inode need the reflink flag? */
int
xfs_reflink_inode_has_shared_extents(
struct xfs_trans *tp,
struct xfs_inode *ip,
bool *has_shared)
{
struct xfs_bmbt_irec got;
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t rbno;
xfs_extlen_t rlen;
xfs_extnum_t idx;
bool found;
int error;
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
if (error)
return error;
}
*has_shared = false;
found = xfs_iext_lookup_extent(ip, ifp, 0, &idx, &got);
while (found) {
if (isnullstartblock(got.br_startblock) ||
got.br_state != XFS_EXT_NORM)
goto next;
agno = XFS_FSB_TO_AGNO(mp, got.br_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock);
aglen = got.br_blockcount;
error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen,
&rbno, &rlen, false);
if (error)
return error;
/* Is there still a shared block here? */
if (rbno != NULLAGBLOCK) {
*has_shared = true;
return 0;
}
next:
found = xfs_iext_get_extent(ifp, ++idx, &got);
}
return 0;
}
bool
xfs_inode_need_cow(
struct xfs_inode *ip,
struct xfs_bmbt_irec *imap,
bool *shared)
{
/* We can't update any real extents in always COW mode. */
if (xfs_is_always_cow_inode(ip) &&
!isnullstartblock(imap->br_startblock)) {
*shared = true;
return 0;
}
/* Trim the mapping to the nearest shared extent boundary. */
return xfs_reflink_trim_around_shared(ip, imap, shared);
}
/*
* Find the extent that maps the given range in the COW fork. Even if the extent
* is not shared we might have a preallocation for it in the COW fork. If so we
* use it that rather than trigger a new allocation.
*/
static int
xfs_find_trim_cow_extent(
struct xfs_inode *ip,
struct xfs_bmbt_irec *imap,
bool *shared,
bool *found)
{
xfs_fileoff_t offset_fsb = imap->br_startoff;
xfs_filblks_t count_fsb = imap->br_blockcount;
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec got;
*found = false;
/*
* If we don't find an overlapping extent, trim the range we need to
* allocate to fit the hole we found.
*/
if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got))
got.br_startoff = offset_fsb + count_fsb;
if (got.br_startoff > offset_fsb) {
xfs_trim_extent(imap, imap->br_startoff,
got.br_startoff - imap->br_startoff);
return xfs_inode_need_cow(ip, imap, shared);
}
*shared = true;
if (isnullstartblock(got.br_startblock)) {
xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
return 0;
}
/* real extent found - no need to allocate */
xfs_trim_extent(&got, offset_fsb, count_fsb);
*imap = got;
*found = true;
return 0;
}
static int
xfs_reflink_convert_cow_locked(
struct xfs_inode *ip,
xfs_fileoff_t offset_fsb,
xfs_filblks_t count_fsb)
{
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec got;
struct xfs_btree_cur *dummy_cur = NULL;
int dummy_logflags;
int error = 0;
if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got))
return 0;
do {
if (got.br_startoff >= offset_fsb + count_fsb)
break;
if (got.br_state == XFS_EXT_NORM)
continue;
if (WARN_ON_ONCE(isnullstartblock(got.br_startblock)))
return -EIO;
xfs_trim_extent(&got, offset_fsb, count_fsb);
if (!got.br_blockcount)
continue;
got.br_state = XFS_EXT_NORM;
error = xfs_bmap_add_extent_unwritten_real(NULL, ip,
XFS_COW_FORK, &icur, &dummy_cur, &got,
&dummy_logflags);
if (error)
return error;
} while (xfs_iext_next_extent(ip->i_cowfp, &icur, &got));
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;
}
/*
* Cancel CoW reservations for some block range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb,
bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
xfs_extnum_t idx;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error = 0;
if (!xfs_is_reflink_inode(ip))
return 0;
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return 0;
while (got.br_startoff < end_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
trace_xfs_reflink_cancel_cow(ip, &del);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&idx, &got, &del);
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(ip->i_mount,
&dfops, del.br_startblock,
del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(ip->i_mount, &dfops,
del.br_startblock, del.br_blockcount,
NULL);
/* Update quota accounting */
xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-(long)del.br_blockcount);
/* Roll the transaction */
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(tpp, &dfops);
if (error) {
xfs_defer_cancel(&dfops);
break;
}
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
}
if (!xfs_iext_get_extent(ifp, ++idx, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
/* Allocate all CoW reservations covering a range of blocks in a file. */
int
xfs_reflink_allocate_cow(
struct xfs_inode *ip,
struct xfs_bmbt_irec *imap,
bool *shared,
uint *lockmode)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = imap->br_startoff;
xfs_filblks_t count_fsb = imap->br_blockcount;
struct xfs_bmbt_irec got;
struct xfs_defer_ops dfops;
struct xfs_trans *tp = NULL;
xfs_fsblock_t first_block;
int nimaps, error = 0;
bool trimmed;
xfs_filblks_t resaligned;
xfs_extlen_t resblks = 0;
xfs_extnum_t idx;
retry:
ASSERT(xfs_is_reflink_inode(ip));
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
/*
* Even if the extent is not shared we might have a preallocation for
* it in the COW fork. If so use it.
*/
if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &idx, &got) &&
got.br_startoff <= offset_fsb) {
*shared = true;
/* If we have a real allocation in the COW fork we're done. */
if (!isnullstartblock(got.br_startblock)) {
xfs_trim_extent(&got, offset_fsb, count_fsb);
*imap = got;
goto convert;
}
xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
} else {
error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
if (error || !*shared)
goto out;
}
if (!tp) {
resaligned = xfs_aligned_fsb_count(imap->br_startoff,
imap->br_blockcount, xfs_get_cowextsz_hint(ip));
resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
xfs_iunlock(ip, *lockmode);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
*lockmode = XFS_ILOCK_EXCL;
xfs_ilock(ip, *lockmode);
if (error)
return error;
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out;
goto retry;
}
error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0,
XFS_QMOPT_RES_REGBLKS);
if (error)
goto out;
xfs_trans_ijoin(tp, ip, 0);
xfs_defer_init(&dfops, &first_block);
nimaps = 1;
/* Allocate the entire reservation as unwritten blocks. */
error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
resblks, imap, &nimaps, &dfops);
if (error)
goto out_bmap_cancel;
/* Finish up. */
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto out_bmap_cancel;
error = xfs_trans_commit(tp);
if (error)
return error;
convert:
return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb,
&dfops);
out_bmap_cancel:
xfs_defer_cancel(&dfops);
xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
XFS_QMOPT_RES_REGBLKS);
out:
if (tp)
xfs_trans_cancel(tp);
return error;
}
/*
* Cancel CoW reservations for some block range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb,
bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error = 0;
if (!xfs_is_reflink_inode(ip))
return 0;
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
return 0;
/* 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 ext forward */
if (!del.br_blockcount) {
xfs_iext_prev(ifp, &icur);
goto next_extent;
}
trace_xfs_reflink_cancel_cow(ip, &del);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&icur, &got, &del);
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(ip->i_mount,
&dfops, del.br_startblock,
del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(ip->i_mount, &dfops,
del.br_startblock, del.br_blockcount,
NULL);
/* Update quota accounting */
xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-(long)del.br_blockcount);
/* Roll the transaction */
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(tpp, &dfops);
if (error) {
xfs_defer_cancel(&dfops);
break;
}
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
} else {
/* Didn't do anything, push cursor back. */
xfs_iext_prev(ifp, &icur);
}
next_extent:
if (!xfs_iext_get_extent(ifp, &icur, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
STATIC loff_t
xfs_seek_data(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a data extent */
if (map[i].br_startblock == DELAYSTARTBLOCK ||
(map[i].br_state == XFS_EXT_NORM &&
!isnullstartblock(map[i].br_startblock)))
goto out;
/*
* Landed in an unwritten extent, try to search data
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
DATA_OFF, &offset))
goto out;
}
}
/*
* map[0] is hole or its an unwritten extent but
* without data in page cache. Probably means that
* we are reading after EOF if nothing in map[1].
*/
if (nmap == 1) {
error = ENXIO;
goto out_unlock;
}
ASSERT(i > 1);
/*
* Nothing was found, proceed to the next round of search
* if reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
}
out:
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return -error;
return offset;
}
/*
* Cancel CoW reservations for some block range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*
* Caller must have already joined the inode to the current transaction. The
* inode will be joined to the transaction returned to the caller.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb,
bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
int error = 0;
if (!xfs_inode_has_cow_data(ip))
return 0;
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
return 0;
/* 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 ext forward */
if (!del.br_blockcount) {
xfs_iext_prev(ifp, &icur);
goto next_extent;
}
trace_xfs_reflink_cancel_cow(ip, &del);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&icur, &got, &del);
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(*tpp,
del.br_startblock, del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(*tpp, del.br_startblock,
del.br_blockcount, NULL);
/* Roll the transaction */
error = xfs_defer_finish(tpp);
if (error)
break;
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
/* Remove the quota reservation */
error = xfs_trans_reserve_quota_nblks(NULL, ip,
-(long)del.br_blockcount, 0,
XFS_QMOPT_RES_REGBLKS);
if (error)
break;
} else {
/* Didn't do anything, push cursor back. */
xfs_iext_prev(ifp, &icur);
}
next_extent:
if (!xfs_iext_get_extent(ifp, &icur, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
int
xfs_iomap(
xfs_inode_t *ip,
xfs_off_t offset,
ssize_t count,
int flags,
xfs_iomap_t *iomapp,
int *niomaps)
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int lockmode = 0;
xfs_bmbt_irec_t imap;
int nimaps = 1;
int bmapi_flags = 0;
int iomap_flags = 0;
ASSERT((ip->i_d.di_mode & S_IFMT) == S_IFREG);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
switch (flags & (BMAPI_READ | BMAPI_WRITE | BMAPI_ALLOCATE)) {
case BMAPI_READ:
xfs_iomap_enter_trace(XFS_IOMAP_READ_ENTER, ip, offset, count);
lockmode = xfs_ilock_map_shared(ip);
bmapi_flags = XFS_BMAPI_ENTIRE;
break;
case BMAPI_WRITE:
xfs_iomap_enter_trace(XFS_IOMAP_WRITE_ENTER, ip, offset, count);
lockmode = XFS_ILOCK_EXCL;
if (flags & BMAPI_IGNSTATE)
bmapi_flags |= XFS_BMAPI_IGSTATE|XFS_BMAPI_ENTIRE;
xfs_ilock(ip, lockmode);
break;
case BMAPI_ALLOCATE:
xfs_iomap_enter_trace(XFS_IOMAP_ALLOC_ENTER, ip, offset, count);
lockmode = XFS_ILOCK_SHARED;
bmapi_flags = XFS_BMAPI_ENTIRE;
/* Attempt non-blocking lock */
if (flags & BMAPI_TRYLOCK) {
if (!xfs_ilock_nowait(ip, lockmode))
return XFS_ERROR(EAGAIN);
} else {
xfs_ilock(ip, lockmode);
}
break;
default:
BUG();
}
ASSERT(offset <= mp->m_maxioffset);
if ((xfs_fsize_t)offset + count > mp->m_maxioffset)
count = mp->m_maxioffset - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi(NULL, ip, offset_fsb,
(xfs_filblks_t)(end_fsb - offset_fsb),
bmapi_flags, NULL, 0, &imap,
&nimaps, NULL, NULL);
if (error)
goto out;
switch (flags & (BMAPI_WRITE|BMAPI_ALLOCATE)) {
case BMAPI_WRITE:
/* If we found an extent, return it */
if (nimaps &&
(imap.br_startblock != HOLESTARTBLOCK) &&
(imap.br_startblock != DELAYSTARTBLOCK)) {
xfs_iomap_map_trace(XFS_IOMAP_WRITE_MAP, ip,
offset, count, iomapp, &imap, flags);
break;
}
if (flags & (BMAPI_DIRECT|BMAPI_MMAP)) {
error = xfs_iomap_write_direct(ip, offset, count, flags,
&imap, &nimaps, nimaps);
} else {
error = xfs_iomap_write_delay(ip, offset, count, flags,
&imap, &nimaps);
}
if (!error) {
xfs_iomap_map_trace(XFS_IOMAP_ALLOC_MAP, ip,
offset, count, iomapp, &imap, flags);
}
iomap_flags = IOMAP_NEW;
break;
case BMAPI_ALLOCATE:
/* If we found an extent, return it */
xfs_iunlock(ip, lockmode);
lockmode = 0;
if (nimaps && !isnullstartblock(imap.br_startblock)) {
xfs_iomap_map_trace(XFS_IOMAP_WRITE_MAP, ip,
offset, count, iomapp, &imap, flags);
break;
}
error = xfs_iomap_write_allocate(ip, offset, count,
&imap, &nimaps);
break;
}
if (nimaps) {
*niomaps = xfs_imap_to_bmap(ip, offset, &imap,
iomapp, nimaps, *niomaps, iomap_flags);
} else if (niomaps) {
*niomaps = 0;
}
out:
if (lockmode)
xfs_iunlock(ip, lockmode);
return XFS_ERROR(error);
}
/*
* caller must lock inode with xfs_ilock_data_map_shared,
* can we craft an appropriate ASSERT?
*
* end is because the VFS-level lseek interface is defined such that any
* offset past i_size shall return -ENXIO, but we use this for quota code
* which does not maintain i_size, and we want to SEEK_DATA past i_size.
*/
loff_t
__xfs_seek_hole_data(
struct inode *inode,
loff_t start,
loff_t end,
int whence)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fileoff_t fsbno;
xfs_filblks_t lastbno;
int error;
if (start >= end) {
error = -ENXIO;
goto out_error;
}
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
fsbno = XFS_B_TO_FSBT(mp, start);
lastbno = XFS_B_TO_FSB(mp, end);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_error;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = -ENXIO;
goto out_error;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in the hole we wanted? */
if (whence == SEEK_HOLE &&
map[i].br_startblock == HOLESTARTBLOCK)
goto out;
/* Landed in the data extent we wanted? */
if (whence == SEEK_DATA &&
(map[i].br_startblock == DELAYSTARTBLOCK ||
(map[i].br_state == XFS_EXT_NORM &&
!isnullstartblock(map[i].br_startblock))))
goto out;
/*
* Landed in an unwritten extent, try to search
* for hole or data from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF,
&offset))
goto out;
}
}
/*
* We only received one extent out of the two requested. This
* means we've hit EOF and didn't find what we are looking for.
*/
if (nmap == 1) {
/*
* If we were looking for a hole, set offset to
* the end of the file (i.e., there is an implicit
* hole at the end of any file).
*/
if (whence == SEEK_HOLE) {
offset = end;
break;
}
/*
* If we were looking for data, it's nowhere to be found
*/
ASSERT(whence == SEEK_DATA);
error = -ENXIO;
goto out_error;
}
ASSERT(i > 1);
/*
* Nothing was found, proceed to the next round of search
* if the next reading offset is not at or beyond EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= end) {
if (whence == SEEK_HOLE) {
offset = end;
break;
}
ASSERT(whence == SEEK_DATA);
error = -ENXIO;
goto out_error;
}
}
out:
/*
* If at this point we have found the hole we wanted, the returned
* offset may be bigger than the file size as it may be aligned to
* page boundary for unwritten extents. We need to deal with this
* situation in particular.
*/
if (whence == SEEK_HOLE)
offset = min_t(loff_t, offset, end);
return offset;
out_error:
return error;
}
STATIC int
xfs_map_blocks(
struct inode *inode,
loff_t offset,
struct xfs_bmbt_irec *imap,
int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t count = 1 << inode->i_blkbits;
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
ASSERT(type != XFS_IO_COW);
if (type == XFS_IO_UNWRITTEN)
bmapi_flags |= XFS_BMAPI_IGSTATE;
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
ASSERT(offset <= mp->m_super->s_maxbytes);
if (offset + count > mp->m_super->s_maxbytes)
count = mp->m_super->s_maxbytes - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
imap, &nimaps, bmapi_flags);
/*
* Truncate an overwrite extent if there's a pending CoW
* reservation before the end of this extent. This forces us
* to come back to writepage to take care of the CoW.
*/
if (nimaps && type == XFS_IO_OVERWRITE)
xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb, imap);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
return error;
if (type == XFS_IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
error = xfs_iomap_write_allocate(ip, XFS_DATA_FORK, offset,
imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return error;
}
#ifdef DEBUG
if (type == XFS_IO_UNWRITTEN) {
ASSERT(nimaps);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
}
#endif
if (nimaps)
trace_xfs_map_blocks_found(ip, offset, count, type, imap);
return 0;
}
