/*
* Remove a name from the leaf attribute list structure
*
* This leaf block cannot have a "remote" value, we only call this routine
* if bmap_one_block() says there is only one block (ie: no remote blks).
*/
STATIC int
xfs_attr_leaf_removename(xfs_da_args_t *args)
{
xfs_inode_t *dp;
struct xfs_buf *bp;
int error, forkoff;
trace_xfs_attr_leaf_removename(args);
/*
* Remove the attribute.
*/
dp = args->dp;
args->blkno = 0;
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
return error;
error = xfs_attr3_leaf_lookup_int(bp, args);
if (error == -ENOATTR) {
xfs_trans_brelse(args->trans, bp);
return error;
}
xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
}
return 0;
}
/*
* 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;
}
/*
* 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;
}
/*
* Free a symlink that has blocks associated with it.
*/
STATIC int
xfs_inactive_symlink_rmt(
struct xfs_inode *ip)
{
xfs_buf_t *bp;
int done;
int error;
xfs_fsblock_t first_block;
struct xfs_defer_ops dfops;
int i;
xfs_mount_t *mp;
xfs_bmbt_irec_t mval[XFS_SYMLINK_MAPS];
int nmaps;
int size;
xfs_trans_t *tp;
mp = ip->i_mount;
ASSERT(ip->i_df.if_flags & XFS_IFEXTENTS);
/*
* We're freeing a symlink that has some
* blocks allocated to it. Free the
* blocks here. We know that we've got
* either 1 or 2 extents and that we can
* free them all in one bunmapi call.
*/
ASSERT(ip->i_d.di_nextents > 0 && ip->i_d.di_nextents <= 2);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Lock the inode, fix the size, and join it to the transaction.
* Hold it so in the normal path, we still have it locked for
* the second transaction. In the error paths we need it
* held so the cancel won't rele it, see below.
*/
size = (int)ip->i_d.di_size;
ip->i_d.di_size = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Find the block(s) so we can inval and unmap them.
*/
done = 0;
xfs_defer_init(&dfops, &first_block);
nmaps = ARRAY_SIZE(mval);
error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
mval, &nmaps, 0);
if (error)
goto error_trans_cancel;
/*
* Invalidate the block(s). No validation is done.
*/
for (i = 0; i < nmaps; i++) {
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
if (!bp) {
error = -ENOMEM;
goto error_bmap_cancel;
}
xfs_trans_binval(tp, bp);
}
/*
* Unmap the dead block(s) to the dfops.
*/
error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps,
&first_block, &dfops, &done);
if (error)
goto error_bmap_cancel;
ASSERT(done);
/*
* Commit the first transaction. This logs the EFI and the inode.
*/
error = xfs_defer_finish(&tp, &dfops, ip);
if (error)
goto error_bmap_cancel;
/*
* The first xact was committed, so add the inode to the new one.
* Mark it dirty so it will be logged and moved forward in the log as
* part of every commit.
*/
xfs_trans_ijoin(tp, ip, 0);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Commit the transaction containing extent freeing and EFDs.
*/
error = xfs_trans_commit(tp);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error_unlock;
}
/*
* Remove the memory for extent descriptions (just bookkeeping).
*/
if (ip->i_df.if_bytes)
xfs_idata_realloc(ip, -ip->i_df.if_bytes, XFS_DATA_FORK);
ASSERT(ip->i_df.if_bytes == 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
error_bmap_cancel:
xfs_defer_cancel(&dfops);
error_trans_cancel:
xfs_trans_cancel(tp);
error_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
int
xfs_symlink(
struct xfs_inode *dp,
struct xfs_name *link_name,
const char *target_path,
umode_t mode,
struct xfs_inode **ipp)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_trans *tp = NULL;
struct xfs_inode *ip = NULL;
int error = 0;
int pathlen;
struct xfs_defer_ops dfops;
xfs_fsblock_t first_block;
bool unlock_dp_on_error = false;
xfs_fileoff_t first_fsb;
xfs_filblks_t fs_blocks;
int nmaps;
struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
xfs_daddr_t d;
const char *cur_chunk;
int byte_cnt;
int n;
xfs_buf_t *bp;
prid_t prid;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *pdqp = NULL;
uint resblks;
*ipp = NULL;
trace_xfs_symlink(dp, link_name);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Check component lengths of the target path name.
*/
pathlen = strlen(target_path);
if (pathlen >= MAXPATHLEN) /* total string too long */
return -ENAMETOOLONG;
udqp = gdqp = NULL;
prid = xfs_get_initial_prid(dp);
/*
* Make sure that we have allocated dquot(s) on disk.
*/
error = xfs_qm_vop_dqalloc(dp,
xfs_kuid_to_uid(current_fsuid()),
xfs_kgid_to_gid(current_fsgid()), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
return error;
/*
* The symlink will fit into the inode data fork?
* There can't be any attributes so we get the whole variable part.
*/
if (pathlen <= XFS_LITINO(mp, dp->i_d.di_version))
fs_blocks = 0;
else
fs_blocks = xfs_symlink_blocks(mp, pathlen);
resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp);
if (error == -ENOSPC && fs_blocks == 0) {
resblks = 0;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, 0, 0, 0,
&tp);
}
if (error)
goto out_release_inode;
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
unlock_dp_on_error = true;
/*
* Check whether the directory allows new symlinks or not.
*/
if (dp->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) {
error = -EPERM;
goto out_trans_cancel;
}
/*
* Reserve disk quota : blocks and inode.
*/
error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
pdqp, resblks, 1, 0);
if (error)
goto out_trans_cancel;
/*
* Check for ability to enter directory entry, if no space reserved.
*/
if (!resblks) {
error = xfs_dir_canenter(tp, dp, link_name);
if (error)
goto out_trans_cancel;
}
/*
* Initialize the bmap freelist prior to calling either
* bmapi or the directory create code.
*/
xfs_defer_init(&dfops, &first_block);
/*
* Allocate an inode for the symlink.
*/
error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0,
prid, resblks > 0, &ip, NULL);
if (error)
goto out_trans_cancel;
/*
* Now we join the directory inode to the transaction. We do not do it
* earlier because xfs_dir_ialloc might commit the previous transaction
* (and release all the locks). An error from here on will result in
* the transaction cancel unlocking dp so don't do it explicitly in the
* error path.
*/
xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
unlock_dp_on_error = false;
/*
* Also attach the dquot(s) to it, if applicable.
*/
xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
if (resblks)
resblks -= XFS_IALLOC_SPACE_RES(mp);
/*
* If the symlink will fit into the inode, write it inline.
*/
if (pathlen <= XFS_IFORK_DSIZE(ip)) {
xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
ip->i_d.di_size = pathlen;
ip->i_d.di_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
} else {
int offset;
first_fsb = 0;
nmaps = XFS_SYMLINK_MAPS;
error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
XFS_BMAPI_METADATA, &first_block, resblks,
mval, &nmaps, &dfops);
if (error)
goto out_bmap_cancel;
if (resblks)
resblks -= fs_blocks;
ip->i_d.di_size = pathlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
cur_chunk = target_path;
offset = 0;
for (n = 0; n < nmaps; n++) {
char *buf;
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
BTOBB(byte_cnt), 0);
if (!bp) {
error = -ENOMEM;
goto out_bmap_cancel;
}
bp->b_ops = &xfs_symlink_buf_ops;
byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
byte_cnt = min(byte_cnt, pathlen);
buf = bp->b_addr;
buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
byte_cnt, bp);
memcpy(buf, cur_chunk, byte_cnt);
cur_chunk += byte_cnt;
pathlen -= byte_cnt;
offset += byte_cnt;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
(char *)bp->b_addr);
}
ASSERT(pathlen == 0);
}
/*
* Create the directory entry for the symlink.
*/
error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
&first_block, &dfops, resblks);
if (error)
goto out_bmap_cancel;
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/*
* If this is a synchronous mount, make sure that the
* symlink transaction goes to disk before returning to
* the user.
*/
if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
xfs_trans_set_sync(tp);
}
error = xfs_defer_finish(&tp, &dfops, NULL);
if (error)
goto out_bmap_cancel;
error = xfs_trans_commit(tp);
if (error)
goto out_release_inode;
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
*ipp = ip;
return 0;
out_bmap_cancel:
xfs_defer_cancel(&dfops);
out_trans_cancel:
xfs_trans_cancel(tp);
out_release_inode:
/*
* Wait until after the current transaction is aborted to finish the
* setup of the inode and release the inode. This prevents recursive
* transactions and deadlocks from xfs_inactive.
*/
if (ip) {
xfs_finish_inode_setup(ip);
IRELE(ip);
}
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
if (unlock_dp_on_error)
xfs_iunlock(dp, XFS_ILOCK_EXCL);
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;
}
/*
* Remove the value associated with an attribute by deleting the
* out-of-line buffer that it is stored on.
*/
int
xfs_attr_rmtval_remove(
struct xfs_da_args *args)
{
struct xfs_mount *mp = args->dp->i_mount;
xfs_dablk_t lblkno;
int blkcnt;
int error;
int done;
trace_xfs_attr_rmtval_remove(args);
/*
* Roll through the "value", invalidating the attribute value's blocks.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
while (blkcnt > 0) {
struct xfs_bmbt_irec map;
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
int nmap;
/*
* Try to remember where we decided to put the value.
*/
nmap = 1;
error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
if (error)
return error;
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
/*
* If the "remote" value is in the cache, remove it.
*/
bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
if (bp) {
xfs_buf_stale(bp);
xfs_buf_relse(bp);
bp = NULL;
}
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
/*
* Keep de-allocating extents until the remote-value region is gone.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
done = 0;
while (!done) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
XFS_BMAPI_ATTRFORK, 1, args->firstblock,
args->dfops, &done);
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops,
args->dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
/*
* Close out trans and start the next one in the chain.
*/
error = xfs_trans_roll(&args->trans, args->dp);
if (error)
return error;
}
return 0;
}
int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
unsigned char *value,
int valuelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_da_args args;
struct xfs_defer_ops dfops;
struct xfs_trans_res tres;
xfs_fsblock_t firstblock;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, local;
XFS_STATS_INC(mp, xs_attr_set);
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
args.value = value;
args.valuelen = valuelen;
args.firstblock = &firstblock;
args.dfops = &dfops;
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
error = xfs_qm_dqattach(dp, 0);
if (error)
return error;
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
if (XFS_IFORK_Q(dp) == 0) {
int sf_size = sizeof(xfs_attr_sf_hdr_t) +
XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
if (error)
return error;
}
tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
M_RES(mp)->tr_attrsetrt.tr_logres * args.total;
tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
error = xfs_trans_alloc(mp, &tres, args.total, 0,
rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
if (error)
return error;
xfs_ilock(dp, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
if (error) {
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_trans_cancel(args.trans);
return error;
}
xfs_trans_ijoin(args.trans, dp, 0);
/*
* If the attribute list is non-existent or a shortform list,
* upgrade it to a single-leaf-block attribute list.
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
(dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
dp->i_d.di_anextents == 0)) {
/*
* Build initial attribute list (if required).
*/
if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(&args);
/*
* Try to add the attr to the attribute list in
* the inode.
*/
error = xfs_attr_shortform_addname(&args);
if (error != -ENOSPC) {
/*
* Commit the shortform mods, and we're done.
* NOTE: this is also the error path (EEXIST, etc).
*/
ASSERT(args.trans != NULL);
/*
* If this is a synchronous mount, make sure that
* the transaction goes to disk before returning
* to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if (!error && (flags & ATTR_KERNOTIME) == 0) {
xfs_trans_ichgtime(args.trans, dp,
XFS_ICHGTIME_CHG);
}
err2 = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error ? error : err2;
}
/*
* It won't fit in the shortform, transform to a leaf block.
* GROT: another possible req'mt for a double-split btree op.
*/
xfs_defer_init(args.dfops, args.firstblock);
error = xfs_attr_shortform_to_leaf(&args);
if (!error)
error = xfs_defer_finish(&args.trans, args.dfops, dp);
if (error) {
args.trans = NULL;
xfs_defer_cancel(&dfops);
goto out;
}
/*
* Commit the leaf transformation. We'll need another (linked)
* transaction to add the new attribute to the leaf.
*/
error = xfs_trans_roll(&args.trans, dp);
if (error)
goto out;
}
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
error = xfs_attr_leaf_addname(&args);
else
error = xfs_attr_node_addname(&args);
if (error)
goto out;
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(args.trans);
if ((flags & ATTR_KERNOTIME) == 0)
xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
/*
* Commit the last in the sequence of transactions.
*/
xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
error = xfs_trans_commit(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
out:
if (args.trans)
xfs_trans_cancel(args.trans);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Add a name to the leaf attribute list structure
*
* This leaf block cannot have a "remote" value, we only call this routine
* if bmap_one_block() says there is only one block (ie: no remote blks).
*/
STATIC int
xfs_attr_leaf_addname(xfs_da_args_t *args)
{
xfs_inode_t *dp;
struct xfs_buf *bp;
int retval, error, forkoff;
trace_xfs_attr_leaf_addname(args);
/*
* Read the (only) block in the attribute list in.
*/
dp = args->dp;
args->blkno = 0;
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, -1, &bp);
if (error)
return error;
/*
* Look up the given attribute in the leaf block. Figure out if
* the given flags produce an error or call for an atomic rename.
*/
retval = xfs_attr3_leaf_lookup_int(bp, args);
if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
xfs_trans_brelse(args->trans, bp);
return retval;
} else if (retval == -EEXIST) {
if (args->flags & ATTR_CREATE) { /* pure create op */
xfs_trans_brelse(args->trans, bp);
return retval;
}
trace_xfs_attr_leaf_replace(args);
/* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
args->rmtvaluelen2 = args->rmtvaluelen;
/*
* clear the remote attr state now that it is saved so that the
* values reflect the state of the attribute we are about to
* add, not the attribute we just found and will remove later.
*/
args->rmtblkno = 0;
args->rmtblkcnt = 0;
args->rmtvaluelen = 0;
}
/*
* Add the attribute to the leaf block, transitioning to a Btree
* if required.
*/
retval = xfs_attr3_leaf_add(bp, args);
if (retval == -ENOSPC) {
/*
* Promote the attribute list to the Btree format, then
* Commit that transaction so that the node_addname() call
* can manage its own transactions.
*/
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_attr3_leaf_to_node(args);
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
/*
* Commit the current trans (including the inode) and start
* a new one.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
return error;
/*
* Fob the whole rest of the problem off on the Btree code.
*/
error = xfs_attr_node_addname(args);
return error;
}
/*
* Commit the transaction that added the attr name so that
* later routines can manage their own transactions.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
return error;
/*
* If there was an out-of-line value, allocate the blocks we
* identified for its storage and copy the value. This is done
* after we create the attribute so that we don't overflow the
* maximum size of a transaction and/or hit a deadlock.
*/
if (args->rmtblkno > 0) {
error = xfs_attr_rmtval_set(args);
if (error)
return error;
}
/*
* If this is an atomic rename operation, we must "flip" the
* incomplete flags on the "new" and "old" attribute/value pairs
* so that one disappears and one appears atomically. Then we
* must remove the "old" attribute/value pair.
*/
if (args->op_flags & XFS_DA_OP_RENAME) {
/*
* In a separate transaction, set the incomplete flag on the
* "old" attr and clear the incomplete flag on the "new" attr.
*/
error = xfs_attr3_leaf_flipflags(args);
if (error)
return error;
/*
* Dismantle the "old" attribute/value pair by removing
* a "remote" value (if it exists).
*/
args->index = args->index2;
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
return error;
}
/*
* Read in the block containing the "old" attr, then
* remove the "old" attr from that block (neat, huh!)
*/
error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
-1, &bp);
if (error)
return error;
xfs_attr3_leaf_remove(bp, args);
/*
* If the result is small enough, shrink it all into the inode.
*/
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error)
error = xfs_defer_finish(&args->trans,
args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
}
/*
* Commit the remove and start the next trans in series.
*/
error = xfs_trans_roll(&args->trans, dp);
} else if (args->rmtblkno > 0) {
/*
* Added a "remote" value, just clear the incomplete flag.
*/
error = xfs_attr3_leaf_clearflag(args);
}
return error;
}
/*
* Remove a name from a B-tree attribute list.
*
* This will involve walking down the Btree, and may involve joining
* leaf nodes and even joining intermediate nodes up to and including
* the root node (a special case of an intermediate node).
*/
STATIC int
xfs_attr_node_removename(xfs_da_args_t *args)
{
xfs_da_state_t *state;
xfs_da_state_blk_t *blk;
xfs_inode_t *dp;
struct xfs_buf *bp;
int retval, error, forkoff;
trace_xfs_attr_node_removename(args);
/*
* Tie a string around our finger to remind us where we are.
*/
dp = args->dp;
state = xfs_da_state_alloc();
state->args = args;
state->mp = dp->i_mount;
/*
* Search to see if name exists, and get back a pointer to it.
*/
error = xfs_da3_node_lookup_int(state, &retval);
if (error || (retval != -EEXIST)) {
if (error == 0)
error = retval;
goto out;
}
/*
* If there is an out-of-line value, de-allocate the blocks.
* This is done before we remove the attribute so that we don't
* overflow the maximum size of a transaction and/or hit a deadlock.
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->bp != NULL);
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
if (args->rmtblkno > 0) {
/*
* Fill in disk block numbers in the state structure
* so that we can get the buffers back after we commit
* several transactions in the following calls.
*/
error = xfs_attr_fillstate(state);
if (error)
goto out;
/*
* Mark the attribute as INCOMPLETE, then bunmapi() the
* remote value.
*/
error = xfs_attr3_leaf_setflag(args);
if (error)
goto out;
error = xfs_attr_rmtval_remove(args);
if (error)
goto out;
/*
* Refill the state structure with buffers, the prior calls
* released our buffers.
*/
error = xfs_attr_refillstate(state);
if (error)
goto out;
}
/*
* Remove the name and update the hashvals in the tree.
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
retval = xfs_attr3_leaf_remove(blk->bp, args);
xfs_da3_fixhashpath(state, &state->path);
/*
* Check to see if the tree needs to be collapsed.
*/
if (retval && (state->path.active > 1)) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_da3_join(state);
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
goto out;
}
/*
* Commit the Btree join operation and start a new trans.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
}
/*
* If the result is small enough, push it all into the inode.
*/
if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
/*
* Have to get rid of the copy of this dabuf in the state.
*/
ASSERT(state->path.active == 1);
ASSERT(state->path.blk[0].bp);
state->path.blk[0].bp = NULL;
error = xfs_attr3_leaf_read(args->trans, args->dp, 0, -1, &bp);
if (error)
goto out;
if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error)
error = xfs_defer_finish(&args->trans,
args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
goto out;
}
} else
xfs_trans_brelse(args->trans, bp);
}
error = 0;
out:
xfs_da_state_free(state);
return error;
}
/*
* 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)
{
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_defer_ops dfops;
struct xfs_bmbt_irec irec;
xfs_fsblock_t firstfsb;
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);
xfs_defer_init(&dfops, &firstfsb);
/* 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_dfops;
}
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_dfops;
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_dfops;
}
/* Finish transaction, free inodes. */
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto err_dfops;
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
return error;
err_dfops:
xfs_defer_cancel(&dfops);
err_inode:
xfs_trans_cancel(tp);
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
}
return error;
}
/*
* Allocate a block and fill it with dquots.
* This is called when the bmapi finds a hole.
*/
STATIC int
xfs_qm_dqalloc(
xfs_trans_t **tpp,
xfs_mount_t *mp,
xfs_dquot_t *dqp,
xfs_inode_t *quotip,
xfs_fileoff_t offset_fsb,
xfs_buf_t **O_bpp)
{
xfs_fsblock_t firstblock;
struct xfs_defer_ops dfops;
xfs_bmbt_irec_t map;
int nmaps, error;
xfs_buf_t *bp;
xfs_trans_t *tp = *tpp;
ASSERT(tp != NULL);
trace_xfs_dqalloc(dqp);
/*
* Initialize the bmap freelist prior to calling bmapi code.
*/
xfs_defer_init(&dfops, &firstblock);
xfs_ilock(quotip, XFS_ILOCK_EXCL);
/*
* Return if this type of quotas is turned off while we didn't
* have an inode lock
*/
if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return -ESRCH;
}
xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
nmaps = 1;
error = xfs_bmapi_write(tp, quotip, offset_fsb,
XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
&map, &nmaps, &dfops);
if (error)
goto error0;
ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
ASSERT(nmaps == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
/*
* Keep track of the blkno to save a lookup later
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
/* now we can just get the buffer (there's nothing to read yet) */
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen,
0);
if (!bp) {
error = -ENOMEM;
goto error1;
}
bp->b_ops = &xfs_dquot_buf_ops;
/*
* Make a chunk of dquots out of this buffer and log
* the entire thing.
*/
xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
/*
* xfs_defer_finish() may commit the current transaction and
* start a second transaction if the freelist is not empty.
*
* Since we still want to modify this buffer, we need to
* ensure that the buffer is not released on commit of
* the first transaction and ensure the buffer is added to the
* second transaction.
*
* If there is only one transaction then don't stop the buffer
* from being released when it commits later on.
*/
xfs_trans_bhold(tp, bp);
error = xfs_defer_finish(tpp, &dfops);
if (error)
goto error1;
/* Transaction was committed? */
if (*tpp != tp) {
tp = *tpp;
xfs_trans_bjoin(tp, bp);
} else {
xfs_trans_bhold_release(tp, bp);
}
*O_bpp = bp;
return 0;
error1:
xfs_defer_cancel(&dfops);
error0:
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
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;
}
/*
* Add a name to a Btree-format attribute list.
*
* This will involve walking down the Btree, and may involve splitting
* leaf nodes and even splitting intermediate nodes up to and including
* the root node (a special case of an intermediate node).
*
* "Remote" attribute values confuse the issue and atomic rename operations
* add a whole extra layer of confusion on top of that.
*/
STATIC int
xfs_attr_node_addname(xfs_da_args_t *args)
{
xfs_da_state_t *state;
xfs_da_state_blk_t *blk;
xfs_inode_t *dp;
xfs_mount_t *mp;
int retval, error;
trace_xfs_attr_node_addname(args);
/*
* Fill in bucket of arguments/results/context to carry around.
*/
dp = args->dp;
mp = dp->i_mount;
restart:
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
/*
* Search to see if name already exists, and get back a pointer
* to where it should go.
*/
error = xfs_da3_node_lookup_int(state, &retval);
if (error)
goto out;
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
if ((args->flags & ATTR_REPLACE) && (retval == -ENOATTR)) {
goto out;
} else if (retval == -EEXIST) {
if (args->flags & ATTR_CREATE)
goto out;
trace_xfs_attr_node_replace(args);
/* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
args->rmtvaluelen2 = args->rmtvaluelen;
/*
* clear the remote attr state now that it is saved so that the
* values reflect the state of the attribute we are about to
* add, not the attribute we just found and will remove later.
*/
args->rmtblkno = 0;
args->rmtblkcnt = 0;
args->rmtvaluelen = 0;
}
retval = xfs_attr3_leaf_add(blk->bp, state->args);
if (retval == -ENOSPC) {
if (state->path.active == 1) {
/*
* Its really a single leaf node, but it had
* out-of-line values so it looked like it *might*
* have been a b-tree.
*/
xfs_da_state_free(state);
state = NULL;
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_attr3_leaf_to_node(args);
if (!error)
error = xfs_defer_finish(&args->trans,
args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
goto out;
}
/*
* Commit the node conversion and start the next
* trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
goto restart;
}
/*
* Split as many Btree elements as required.
* This code tracks the new and old attr's location
* in the index/blkno/rmtblkno/rmtblkcnt fields and
* in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
*/
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_da3_split(state);
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
goto out;
}
} else {
/*
* Addition succeeded, update Btree hashvals.
*/
xfs_da3_fixhashpath(state, &state->path);
}
/*
* Kill the state structure, we're done with it and need to
* allow the buffers to come back later.
*/
xfs_da_state_free(state);
state = NULL;
/*
* Commit the leaf addition or btree split and start the next
* trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
/*
* If there was an out-of-line value, allocate the blocks we
* identified for its storage and copy the value. This is done
* after we create the attribute so that we don't overflow the
* maximum size of a transaction and/or hit a deadlock.
*/
if (args->rmtblkno > 0) {
error = xfs_attr_rmtval_set(args);
if (error)
return error;
}
/*
* If this is an atomic rename operation, we must "flip" the
* incomplete flags on the "new" and "old" attribute/value pairs
* so that one disappears and one appears atomically. Then we
* must remove the "old" attribute/value pair.
*/
if (args->op_flags & XFS_DA_OP_RENAME) {
/*
* In a separate transaction, set the incomplete flag on the
* "old" attr and clear the incomplete flag on the "new" attr.
*/
error = xfs_attr3_leaf_flipflags(args);
if (error)
goto out;
/*
* Dismantle the "old" attribute/value pair by removing
* a "remote" value (if it exists).
*/
args->index = args->index2;
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
return error;
}
/*
* Re-find the "old" attribute entry after any split ops.
* The INCOMPLETE flag means that we will find the "old"
* attr, not the "new" one.
*/
args->flags |= XFS_ATTR_INCOMPLETE;
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
state->inleaf = 0;
error = xfs_da3_node_lookup_int(state, &retval);
if (error)
goto out;
/*
* Remove the name and update the hashvals in the tree.
*/
blk = &state->path.blk[ state->path.active-1 ];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
error = xfs_attr3_leaf_remove(blk->bp, args);
xfs_da3_fixhashpath(state, &state->path);
/*
* Check to see if the tree needs to be collapsed.
*/
if (retval && (state->path.active > 1)) {
xfs_defer_init(args->dfops, args->firstblock);
error = xfs_da3_join(state);
if (!error)
error = xfs_defer_finish(&args->trans,
args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
goto out;
}
}
/*
* Commit and start the next trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
goto out;
} else if (args->rmtblkno > 0) {
/*
* Added a "remote" value, just clear the incomplete flag.
*/
error = xfs_attr3_leaf_clearflag(args);
if (error)
goto out;
}
retval = error = 0;
out:
if (state)
xfs_da_state_free(state);
if (error)
return error;
return retval;
}
/*
* Process a refcount update intent item that was recovered from the log.
* We need to update the refcountbt.
*/
int
xfs_cui_recover(
struct xfs_mount *mp,
struct xfs_cui_log_item *cuip)
{
int i;
int error = 0;
unsigned int refc_type;
struct xfs_phys_extent *refc;
xfs_fsblock_t startblock_fsb;
bool op_ok;
struct xfs_cud_log_item *cudp;
struct xfs_trans *tp;
struct xfs_btree_cur *rcur = NULL;
enum xfs_refcount_intent_type type;
xfs_fsblock_t firstfsb;
xfs_fsblock_t new_fsb;
xfs_extlen_t new_len;
struct xfs_bmbt_irec irec;
struct xfs_defer_ops dfops;
bool requeue_only = false;
ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags));
/*
* First check the validity of the extents described by the
* CUI. If any are bad, then assume that all are bad and
* just toss the CUI.
*/
for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
refc = &cuip->cui_format.cui_extents[i];
startblock_fsb = XFS_BB_TO_FSB(mp,
XFS_FSB_TO_DADDR(mp, refc->pe_startblock));
switch (refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK) {
case XFS_REFCOUNT_INCREASE:
case XFS_REFCOUNT_DECREASE:
case XFS_REFCOUNT_ALLOC_COW:
case XFS_REFCOUNT_FREE_COW:
op_ok = true;
break;
default:
op_ok = false;
break;
}
if (!op_ok || startblock_fsb == 0 ||
refc->pe_len == 0 ||
startblock_fsb >= mp->m_sb.sb_dblocks ||
refc->pe_len >= mp->m_sb.sb_agblocks ||
(refc->pe_flags & ~XFS_REFCOUNT_EXTENT_FLAGS)) {
/*
* This will pull the CUI from the AIL and
* free the memory associated with it.
*/
set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
xfs_cui_release(cuip);
return -EIO;
}
}
/*
* Under normal operation, refcount updates are deferred, so we
* wouldn't be adding them directly to a transaction. All
* refcount updates manage reservation usage internally and
* dynamically by deferring work that won't fit in the
* transaction. Normally, any work that needs to be deferred
* gets attached to the same defer_ops that scheduled the
* refcount update. However, we're in log recovery here, so we
* we create our own defer_ops and use that to finish up any
* work that doesn't fit.
*/
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
cudp = xfs_trans_get_cud(tp, cuip);
xfs_defer_init(&dfops, &firstfsb);
for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
refc = &cuip->cui_format.cui_extents[i];
refc_type = refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK;
switch (refc_type) {
case XFS_REFCOUNT_INCREASE:
case XFS_REFCOUNT_DECREASE:
case XFS_REFCOUNT_ALLOC_COW:
case XFS_REFCOUNT_FREE_COW:
type = refc_type;
break;
default:
error = -EFSCORRUPTED;
goto abort_error;
}
if (requeue_only) {
new_fsb = refc->pe_startblock;
new_len = refc->pe_len;
} else
error = xfs_trans_log_finish_refcount_update(tp, cudp,
&dfops, type, refc->pe_startblock, refc->pe_len,
&new_fsb, &new_len, &rcur);
if (error)
goto abort_error;
/* Requeue what we didn't finish. */
if (new_len > 0) {
irec.br_startblock = new_fsb;
irec.br_blockcount = new_len;
switch (type) {
case XFS_REFCOUNT_INCREASE:
error = xfs_refcount_increase_extent(
tp->t_mountp, &dfops, &irec);
break;
case XFS_REFCOUNT_DECREASE:
error = xfs_refcount_decrease_extent(
tp->t_mountp, &dfops, &irec);
break;
case XFS_REFCOUNT_ALLOC_COW:
error = xfs_refcount_alloc_cow_extent(
tp->t_mountp, &dfops,
irec.br_startblock,
irec.br_blockcount);
break;
case XFS_REFCOUNT_FREE_COW:
error = xfs_refcount_free_cow_extent(
tp->t_mountp, &dfops,
irec.br_startblock,
irec.br_blockcount);
break;
default:
ASSERT(0);
}
if (error)
goto abort_error;
requeue_only = true;
}
}
xfs_refcount_finish_one_cleanup(tp, rcur, error);
error = xfs_defer_finish(&tp, &dfops, NULL);
if (error)
goto abort_defer;
set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
error = xfs_trans_commit(tp);
return error;
abort_error:
xfs_refcount_finish_one_cleanup(tp, rcur, error);
abort_defer:
xfs_defer_cancel(&dfops);
xfs_trans_cancel(tp);
return error;
}
/*
* Write the value associated with an attribute into the out-of-line buffer
* that we have defined for it.
*/
int
xfs_attr_rmtval_set(
struct xfs_da_args *args)
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_bmbt_irec map;
xfs_dablk_t lblkno;
xfs_fileoff_t lfileoff = 0;
uint8_t *src = args->value;
int blkcnt;
int valuelen;
int nmap;
int error;
int offset = 0;
trace_xfs_attr_rmtval_set(args);
/*
* Find a "hole" in the attribute address space large enough for
* us to drop the new attribute's value into. Because CRC enable
* attributes have headers, we can't just do a straight byte to FSB
* conversion and have to take the header space into account.
*/
blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
XFS_ATTR_FORK);
if (error)
return error;
args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
args->rmtblkcnt = blkcnt;
/*
* Roll through the "value", allocating blocks on disk as required.
*/
while (blkcnt > 0) {
/*
* Allocate a single extent, up to the size of the value.
*
* Note that we have to consider this a data allocation as we
* write the remote attribute without logging the contents.
* Hence we must ensure that we aren't using blocks that are on
* the busy list so that we don't overwrite blocks which have
* recently been freed but their transactions are not yet
* committed to disk. If we overwrite the contents of a busy
* extent and then crash then the block may not contain the
* correct metadata after log recovery occurs.
*/
xfs_defer_init(args->dfops, args->firstblock);
nmap = 1;
error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
args->total, &map, &nmap, args->dfops);
if (!error)
error = xfs_defer_finish(&args->trans, args->dfops, dp);
if (error) {
args->trans = NULL;
xfs_defer_cancel(args->dfops);
return error;
}
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
/*
* Start the next trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
return error;
}
/*
* Roll through the "value", copying the attribute value to the
* already-allocated blocks. Blocks are written synchronously
* so that we can know they are all on disk before we turn off
* the INCOMPLETE flag.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
valuelen = args->rmtvaluelen;
while (valuelen > 0) {
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
ASSERT(blkcnt > 0);
xfs_defer_init(args->dfops, args->firstblock);
nmap = 1;
error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
blkcnt, &map, &nmap,
XFS_BMAPI_ATTRFORK);
if (error)
return error;
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0);
if (!bp)
return -ENOMEM;
bp->b_ops = &xfs_attr3_rmt_buf_ops;
xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
&valuelen, &src);
error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
xfs_buf_relse(bp);
if (error)
return error;
/* roll attribute extent map forwards */
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
ASSERT(valuelen == 0);
return 0;
}