/*
* Roll a transaction, keeping the AG headers locked and reinitializing
* the btree cursors.
*/
int
xrep_roll_ag_trans(
struct xfs_scrub *sc)
{
int error;
/* Keep the AG header buffers locked so we can keep going. */
if (sc->sa.agi_bp)
xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
if (sc->sa.agf_bp)
xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
if (sc->sa.agfl_bp)
xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
/*
* Roll the transaction. We still own the buffer and the buffer lock
* regardless of whether or not the roll succeeds. If the roll fails,
* the buffers will be released during teardown on our way out of the
* kernel. If it succeeds, we join them to the new transaction and
* move on.
*/
error = xfs_trans_roll(&sc->tp);
if (error)
return error;
/* Join AG headers to the new transaction. */
if (sc->sa.agi_bp)
xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
if (sc->sa.agf_bp)
xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
if (sc->sa.agfl_bp)
xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
return 0;
}
/*
* Indiscriminately delete the entire attribute fork
*
* Recurse (gasp!) through the attribute nodes until we find leaves.
* We're doing a depth-first traversal in order to invalidate everything.
*/
int
xfs_attr3_root_inactive(
struct xfs_trans **trans,
struct xfs_inode *dp)
{
struct xfs_da_blkinfo *info;
struct xfs_buf *bp;
xfs_daddr_t blkno;
int error;
/*
* Read block 0 to see what we have to work with.
* We only get here if we have extents, since we remove
* the extents in reverse order the extent containing
* block 0 must still be there.
*/
error = xfs_da3_node_read(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
if (error)
return error;
blkno = bp->b_bn;
/*
* Invalidate the tree, even if the "tree" is only a single leaf block.
* This is a depth-first traversal!
*/
info = bp->b_addr;
switch (info->magic) {
case cpu_to_be16(XFS_DA_NODE_MAGIC):
case cpu_to_be16(XFS_DA3_NODE_MAGIC):
error = xfs_attr3_node_inactive(trans, dp, bp, 1);
break;
case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
error = xfs_attr3_leaf_inactive(trans, dp, bp);
break;
default:
error = -EIO;
xfs_trans_brelse(*trans, bp);
break;
}
if (error)
return error;
/*
* Invalidate the incore copy of the root block.
*/
error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
if (error)
return error;
xfs_trans_binval(*trans, bp); /* remove from cache */
/*
* Commit the invalidate and start the next transaction.
*/
error = xfs_trans_roll(trans, dp);
return error;
}
int
xfs_trans_roll_inode(
struct xfs_trans **tpp,
struct xfs_inode *ip)
{
int error;
xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
error = xfs_trans_roll(tpp);
if (!error)
xfs_trans_ijoin(*tpp, ip, 0);
return error;
}
/*
* Wrapper around call to libxfs_ialloc. Takes care of committing and
* allocating a new transaction as needed.
*
* Originally there were two copies of this code - one in mkfs, the
* other in repair - now there is just the one.
*/
int
libxfs_inode_alloc(
xfs_trans_t **tp,
xfs_inode_t *pip,
mode_t mode,
nlink_t nlink,
xfs_dev_t rdev,
struct cred *cr,
struct fsxattr *fsx,
xfs_inode_t **ipp)
{
xfs_buf_t *ialloc_context;
xfs_inode_t *ip;
int error;
ialloc_context = (xfs_buf_t *)0;
error = libxfs_ialloc(*tp, pip, mode, nlink, rdev, cr, fsx,
1, &ialloc_context, &ip);
if (error) {
*ipp = NULL;
return error;
}
if (!ialloc_context && !ip) {
*ipp = NULL;
return -ENOSPC;
}
if (ialloc_context) {
xfs_trans_bhold(*tp, ialloc_context);
error = xfs_trans_roll(tp, NULL);
if (error) {
fprintf(stderr, _("%s: cannot duplicate transaction: %s\n"),
progname, strerror(error));
exit(1);
}
xfs_trans_bjoin(*tp, ialloc_context);
error = libxfs_ialloc(*tp, pip, mode, nlink, rdev, cr,
fsx, 1, &ialloc_context, &ip);
if (!ip)
error = -ENOSPC;
if (error)
return error;
}
*ipp = 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 committed, 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_bmap_init(args->flist, args->firstblock);
error = xfs_attr3_leaf_to_node(args);
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans
* and started a new one. We need the inode to be
* in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
/*
* 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_bmap_init(args->flist, args->firstblock);
error = xfs_da3_split(state);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
} 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_bmap_init(args->flist, args->firstblock);
error = xfs_da3_join(state);
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans
* and started a new one. We need the inode to be
* in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
}
/*
* 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;
}
/*
* 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, committed, 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_bmap_init(args->flist, args->firstblock);
error = xfs_attr3_leaf_to_node(args);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
/*
* 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_bmap_init(args->flist, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans
* and started a new one. We need the inode to be
* in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
}
/*
* 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;
}
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_bmap_free flist;
struct xfs_trans_res tres;
xfs_fsblock_t firstblock;
int rsvd = (flags & ATTR_ROOT) != 0;
int error, err2, committed, local;
XFS_STATS_INC(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.flist = &flist;
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;
}
/*
* Start our first transaction of the day.
*
* All future transactions during this code must be "chained" off
* this one via the trans_dup() call. All transactions will contain
* the inode, and the inode will always be marked with trans_ihold().
* Since the inode will be locked in all transactions, we must log
* the inode in every transaction to let it float upward through
* the log.
*/
args.trans = xfs_trans_alloc(mp, XFS_TRANS_ATTR_SET);
/*
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
if (rsvd)
args.trans->t_flags |= XFS_TRANS_RESERVE;
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;
error = xfs_trans_reserve(args.trans, &tres, args.total, 0);
if (error) {
xfs_trans_cancel(args.trans);
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_bmap_init(args.flist, args.firstblock);
error = xfs_attr_shortform_to_leaf(&args);
if (!error) {
error = xfs_bmap_finish(&args.trans, args.flist,
&committed);
}
if (error) {
ASSERT(committed);
args.trans = NULL;
xfs_bmap_cancel(&flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args.trans, dp, 0);
/*
* 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;
}
/*
* 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, committed, 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_bmap_init(args->flist, args->firstblock);
error = xfs_da3_join(state);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
/*
* 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_bmap_init(args->flist, args->firstblock);
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (!error) {
error = xfs_bmap_finish(&args->trans,
args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
goto out;
}
/*
* bmap_finish() may have committed the last trans
* and started a new one. We need the inode to be
* in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
} else
xfs_trans_brelse(args->trans, bp);
}
error = 0;
out:
xfs_da_state_free(state);
return error;
}
/*
* Look at all the extents for this logical region,
* invalidate any buffers that are incore/in transactions.
*/
STATIC int
xfs_attr3_leaf_freextent(
struct xfs_trans **trans,
struct xfs_inode *dp,
xfs_dablk_t blkno,
int blkcnt)
{
struct xfs_bmbt_irec map;
struct xfs_buf *bp;
xfs_dablk_t tblkno;
xfs_daddr_t dblkno;
int tblkcnt;
int dblkcnt;
int nmap;
int error;
/*
* Roll through the "value", invalidating the attribute value's
* blocks.
*/
tblkno = blkno;
tblkcnt = blkcnt;
while (tblkcnt > 0) {
/*
* Try to remember where we decided to put the value.
*/
nmap = 1;
error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
&map, &nmap, XFS_BMAPI_ATTRFORK);
if (error) {
return error;
}
ASSERT(nmap == 1);
ASSERT(map.br_startblock != DELAYSTARTBLOCK);
/*
* If it's a hole, these are already unmapped
* so there's nothing to invalidate.
*/
if (map.br_startblock != HOLESTARTBLOCK) {
dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
map.br_startblock);
dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
map.br_blockcount);
bp = xfs_trans_get_buf(*trans,
dp->i_mount->m_ddev_targp,
dblkno, dblkcnt, 0);
if (!bp)
return -ENOMEM;
xfs_trans_binval(*trans, bp);
/*
* Roll to next transaction.
*/
error = xfs_trans_roll(trans, dp);
if (error)
return error;
}
tblkno += map.br_blockcount;
tblkcnt -= map.br_blockcount;
}
return 0;
}
/*
* Recurse (gasp!) through the attribute nodes until we find leaves.
* We're doing a depth-first traversal in order to invalidate everything.
*/
STATIC int
xfs_attr3_node_inactive(
struct xfs_trans **trans,
struct xfs_inode *dp,
struct xfs_buf *bp,
int level)
{
xfs_da_blkinfo_t *info;
xfs_da_intnode_t *node;
xfs_dablk_t child_fsb;
xfs_daddr_t parent_blkno, child_blkno;
int error, i;
struct xfs_buf *child_bp;
struct xfs_da_node_entry *btree;
struct xfs_da3_icnode_hdr ichdr;
/*
* Since this code is recursive (gasp!) we must protect ourselves.
*/
if (level > XFS_DA_NODE_MAXDEPTH) {
xfs_trans_brelse(*trans, bp); /* no locks for later trans */
return -EIO;
}
node = bp->b_addr;
dp->d_ops->node_hdr_from_disk(&ichdr, node);
parent_blkno = bp->b_bn;
if (!ichdr.count) {
xfs_trans_brelse(*trans, bp);
return 0;
}
btree = dp->d_ops->node_tree_p(node);
child_fsb = be32_to_cpu(btree[0].before);
xfs_trans_brelse(*trans, bp); /* no locks for later trans */
/*
* If this is the node level just above the leaves, simply loop
* over the leaves removing all of them. If this is higher up
* in the tree, recurse downward.
*/
for (i = 0; i < ichdr.count; i++) {
/*
* Read the subsidiary block to see what we have to work with.
* Don't do this in a transaction. This is a depth-first
* traversal of the tree so we may deal with many blocks
* before we come back to this one.
*/
error = xfs_da3_node_read(*trans, dp, child_fsb, -2, &child_bp,
XFS_ATTR_FORK);
if (error)
return error;
if (child_bp) {
/* save for re-read later */
child_blkno = XFS_BUF_ADDR(child_bp);
/*
* Invalidate the subtree, however we have to.
*/
info = child_bp->b_addr;
switch (info->magic) {
case cpu_to_be16(XFS_DA_NODE_MAGIC):
case cpu_to_be16(XFS_DA3_NODE_MAGIC):
error = xfs_attr3_node_inactive(trans, dp,
child_bp, level + 1);
break;
case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
error = xfs_attr3_leaf_inactive(trans, dp,
child_bp);
break;
default:
error = -EIO;
xfs_trans_brelse(*trans, child_bp);
break;
}
if (error)
return error;
/*
* Remove the subsidiary block from the cache
* and from the log.
*/
error = xfs_da_get_buf(*trans, dp, 0, child_blkno,
&child_bp, XFS_ATTR_FORK);
if (error)
return error;
xfs_trans_binval(*trans, child_bp);
}
/*
* If we're not done, re-read the parent to get the next
* child block number.
*/
if (i + 1 < ichdr.count) {
error = xfs_da3_node_read(*trans, dp, 0, parent_blkno,
&bp, XFS_ATTR_FORK);
if (error)
return error;
child_fsb = be32_to_cpu(btree[i + 1].before);
xfs_trans_brelse(*trans, bp);
}
/*
* Atomically commit the whole invalidate stuff.
*/
error = xfs_trans_roll(trans, dp);
if (error)
return error;
}
return 0;
}
/*
* 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) {
int committed;
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
1, args->firstblock, args->flist,
&done);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, args->dp, 0);
/*
* 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;
}
/*
* 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) {
int committed;
/*
* Allocate a single extent, up to the size of the value.
*/
xfs_bmap_init(args->flist, args->firstblock);
nmap = 1;
error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
blkcnt,
XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
args->firstblock, args->total, &map, &nmap,
args->flist);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
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_bmap_init(args->flist, 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;
}
/*
* 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;
}
