2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
* CDDL HEADER START
|
|
|
|
*
|
|
|
|
* The contents of this file are subject to the terms of the
|
|
|
|
* Common Development and Distribution License (the "License").
|
|
|
|
* You may not use this file except in compliance with the License.
|
|
|
|
*
|
|
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
|
|
* See the License for the specific language governing permissions
|
|
|
|
* and limitations under the License.
|
|
|
|
*
|
|
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
|
|
*
|
|
|
|
* CDDL HEADER END
|
|
|
|
*/
|
|
|
|
/*
|
2010-05-28 20:45:14 +00:00
|
|
|
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
2013-03-08 18:41:28 +00:00
|
|
|
* Copyright (c) 2013 by Delphix. All rights reserved.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <sys/dmu.h>
|
|
|
|
#include <sys/dmu_objset.h>
|
|
|
|
#include <sys/dmu_tx.h>
|
|
|
|
#include <sys/dnode.h>
|
2013-10-08 17:13:05 +00:00
|
|
|
#include <sys/zap.h>
|
|
|
|
#include <sys/zfeature.h>
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
uint64_t
|
|
|
|
dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize,
|
|
|
|
dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx)
|
|
|
|
{
|
|
|
|
uint64_t object;
|
|
|
|
uint64_t L2_dnode_count = DNODES_PER_BLOCK <<
|
2010-08-26 21:24:34 +00:00
|
|
|
(DMU_META_DNODE(os)->dn_indblkshift - SPA_BLKPTRSHIFT);
|
2008-11-20 20:01:55 +00:00
|
|
|
dnode_t *dn = NULL;
|
|
|
|
int restarted = B_FALSE;
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
mutex_enter(&os->os_obj_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
for (;;) {
|
2010-05-28 20:45:14 +00:00
|
|
|
object = os->os_obj_next;
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
* Each time we polish off an L2 bp worth of dnodes
|
|
|
|
* (2^13 objects), move to another L2 bp that's still
|
|
|
|
* reasonably sparse (at most 1/4 full). Look from the
|
|
|
|
* beginning once, but after that keep looking from here.
|
|
|
|
* If we can't find one, just keep going from here.
|
|
|
|
*/
|
|
|
|
if (P2PHASE(object, L2_dnode_count) == 0) {
|
|
|
|
uint64_t offset = restarted ? object << DNODE_SHIFT : 0;
|
2010-08-26 21:24:34 +00:00
|
|
|
int error = dnode_next_offset(DMU_META_DNODE(os),
|
2008-12-03 20:09:06 +00:00
|
|
|
DNODE_FIND_HOLE,
|
|
|
|
&offset, 2, DNODES_PER_BLOCK >> 2, 0);
|
2008-11-20 20:01:55 +00:00
|
|
|
restarted = B_TRUE;
|
|
|
|
if (error == 0)
|
|
|
|
object = offset >> DNODE_SHIFT;
|
|
|
|
}
|
2010-05-28 20:45:14 +00:00
|
|
|
os->os_obj_next = ++object;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX We should check for an i/o error here and return
|
|
|
|
* up to our caller. Actually we should pre-read it in
|
|
|
|
* dmu_tx_assign(), but there is currently no mechanism
|
|
|
|
* to do so.
|
|
|
|
*/
|
2010-05-28 20:45:14 +00:00
|
|
|
(void) dnode_hold_impl(os, object, DNODE_MUST_BE_FREE,
|
2008-11-20 20:01:55 +00:00
|
|
|
FTAG, &dn);
|
|
|
|
if (dn)
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (dmu_object_next(os, &object, B_TRUE, 0) == 0)
|
2010-05-28 20:45:14 +00:00
|
|
|
os->os_obj_next = object - 1;
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, tx);
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
mutex_exit(&os->os_obj_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
dmu_tx_add_new_object(tx, os, object);
|
|
|
|
return (object);
|
|
|
|
}
|
|
|
|
|
|
|
|
int
|
|
|
|
dmu_object_claim(objset_t *os, uint64_t object, dmu_object_type_t ot,
|
|
|
|
int blocksize, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx)
|
|
|
|
{
|
|
|
|
dnode_t *dn;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (object == DMU_META_DNODE_OBJECT && !dmu_tx_private_ok(tx))
|
2013-03-08 18:41:28 +00:00
|
|
|
return (SET_ERROR(EBADF));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
err = dnode_hold_impl(os, object, DNODE_MUST_BE_FREE, FTAG, &dn);
|
2008-11-20 20:01:55 +00:00
|
|
|
if (err)
|
|
|
|
return (err);
|
|
|
|
dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, tx);
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
|
|
|
|
dmu_tx_add_new_object(tx, os, object);
|
|
|
|
return (0);
|
|
|
|
}
|
|
|
|
|
|
|
|
int
|
|
|
|
dmu_object_reclaim(objset_t *os, uint64_t object, dmu_object_type_t ot,
|
2009-07-02 22:44:48 +00:00
|
|
|
int blocksize, dmu_object_type_t bonustype, int bonuslen)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
dnode_t *dn;
|
2009-07-02 22:44:48 +00:00
|
|
|
dmu_tx_t *tx;
|
|
|
|
int nblkptr;
|
2008-11-20 20:01:55 +00:00
|
|
|
int err;
|
|
|
|
|
2009-07-02 22:44:48 +00:00
|
|
|
if (object == DMU_META_DNODE_OBJECT)
|
2013-03-08 18:41:28 +00:00
|
|
|
return (SET_ERROR(EBADF));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED,
|
2008-11-20 20:01:55 +00:00
|
|
|
FTAG, &dn);
|
|
|
|
if (err)
|
|
|
|
return (err);
|
2009-07-02 22:44:48 +00:00
|
|
|
|
|
|
|
if (dn->dn_type == ot && dn->dn_datablksz == blocksize &&
|
|
|
|
dn->dn_bonustype == bonustype && dn->dn_bonuslen == bonuslen) {
|
|
|
|
/* nothing is changing, this is a noop */
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
return (0);
|
|
|
|
}
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
if (bonustype == DMU_OT_SA) {
|
|
|
|
nblkptr = 1;
|
|
|
|
} else {
|
|
|
|
nblkptr = 1 + ((DN_MAX_BONUSLEN - bonuslen) >> SPA_BLKPTRSHIFT);
|
|
|
|
}
|
2009-07-02 22:44:48 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are losing blkptrs or changing the block size this must
|
|
|
|
* be a new file instance. We must clear out the previous file
|
|
|
|
* contents before we can change this type of metadata in the dnode.
|
|
|
|
*/
|
|
|
|
if (dn->dn_nblkptr > nblkptr || dn->dn_datablksz != blocksize) {
|
|
|
|
err = dmu_free_long_range(os, object, 0, DMU_OBJECT_END);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
tx = dmu_tx_create(os);
|
|
|
|
dmu_tx_hold_bonus(tx, object);
|
|
|
|
err = dmu_tx_assign(tx, TXG_WAIT);
|
|
|
|
if (err) {
|
|
|
|
dmu_tx_abort(tx);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
dnode_reallocate(dn, ot, blocksize, bonustype, bonuslen, tx);
|
2009-07-02 22:44:48 +00:00
|
|
|
|
|
|
|
dmu_tx_commit(tx);
|
|
|
|
out:
|
2008-11-20 20:01:55 +00:00
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
|
2009-07-02 22:44:48 +00:00
|
|
|
return (err);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
int
|
|
|
|
dmu_object_free(objset_t *os, uint64_t object, dmu_tx_t *tx)
|
|
|
|
{
|
|
|
|
dnode_t *dn;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
ASSERT(object != DMU_META_DNODE_OBJECT || dmu_tx_private_ok(tx));
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED,
|
2008-11-20 20:01:55 +00:00
|
|
|
FTAG, &dn);
|
|
|
|
if (err)
|
|
|
|
return (err);
|
|
|
|
|
|
|
|
ASSERT(dn->dn_type != DMU_OT_NONE);
|
2008-12-03 20:09:06 +00:00
|
|
|
dnode_free_range(dn, 0, DMU_OBJECT_END, tx);
|
2008-11-20 20:01:55 +00:00
|
|
|
dnode_free(dn, tx);
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
|
|
|
|
return (0);
|
|
|
|
}
|
|
|
|
|
|
|
|
int
|
|
|
|
dmu_object_next(objset_t *os, uint64_t *objectp, boolean_t hole, uint64_t txg)
|
|
|
|
{
|
|
|
|
uint64_t offset = (*objectp + 1) << DNODE_SHIFT;
|
|
|
|
int error;
|
|
|
|
|
2010-08-26 21:24:34 +00:00
|
|
|
error = dnode_next_offset(DMU_META_DNODE(os),
|
2008-12-03 20:09:06 +00:00
|
|
|
(hole ? DNODE_FIND_HOLE : 0), &offset, 0, DNODES_PER_BLOCK, txg);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
*objectp = offset >> DNODE_SHIFT;
|
|
|
|
|
|
|
|
return (error);
|
|
|
|
}
|
2010-08-26 18:49:16 +00:00
|
|
|
|
2013-10-08 17:13:05 +00:00
|
|
|
/*
|
|
|
|
* Turn this object from old_type into DMU_OTN_ZAP_METADATA, and bump the
|
|
|
|
* refcount on SPA_FEATURE_EXTENSIBLE_DATASET.
|
|
|
|
*
|
|
|
|
* Only for use from syncing context, on MOS objects.
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
dmu_object_zapify(objset_t *mos, uint64_t object, dmu_object_type_t old_type,
|
|
|
|
dmu_tx_t *tx)
|
|
|
|
{
|
|
|
|
dnode_t *dn;
|
|
|
|
|
|
|
|
ASSERT(dmu_tx_is_syncing(tx));
|
|
|
|
|
|
|
|
VERIFY0(dnode_hold(mos, object, FTAG, &dn));
|
|
|
|
if (dn->dn_type == DMU_OTN_ZAP_METADATA) {
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
ASSERT3U(dn->dn_type, ==, old_type);
|
|
|
|
ASSERT0(dn->dn_maxblkid);
|
|
|
|
dn->dn_next_type[tx->tx_txg & TXG_MASK] = dn->dn_type =
|
|
|
|
DMU_OTN_ZAP_METADATA;
|
|
|
|
dnode_setdirty(dn, tx);
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
|
|
|
|
mzap_create_impl(mos, object, 0, 0, tx);
|
|
|
|
|
|
|
|
spa_feature_incr(dmu_objset_spa(mos),
|
|
|
|
SPA_FEATURE_EXTENSIBLE_DATASET, tx);
|
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
dmu_object_free_zapified(objset_t *mos, uint64_t object, dmu_tx_t *tx)
|
|
|
|
{
|
|
|
|
dnode_t *dn;
|
|
|
|
dmu_object_type_t t;
|
|
|
|
|
|
|
|
ASSERT(dmu_tx_is_syncing(tx));
|
|
|
|
|
|
|
|
VERIFY0(dnode_hold(mos, object, FTAG, &dn));
|
|
|
|
t = dn->dn_type;
|
|
|
|
dnode_rele(dn, FTAG);
|
|
|
|
|
|
|
|
if (t == DMU_OTN_ZAP_METADATA) {
|
|
|
|
spa_feature_decr(dmu_objset_spa(mos),
|
|
|
|
SPA_FEATURE_EXTENSIBLE_DATASET, tx);
|
|
|
|
}
|
|
|
|
VERIFY0(dmu_object_free(mos, object, tx));
|
|
|
|
}
|
|
|
|
|
2010-08-26 18:49:16 +00:00
|
|
|
#if defined(_KERNEL) && defined(HAVE_SPL)
|
|
|
|
EXPORT_SYMBOL(dmu_object_alloc);
|
|
|
|
EXPORT_SYMBOL(dmu_object_claim);
|
|
|
|
EXPORT_SYMBOL(dmu_object_reclaim);
|
|
|
|
EXPORT_SYMBOL(dmu_object_free);
|
|
|
|
EXPORT_SYMBOL(dmu_object_next);
|
2013-10-08 17:13:05 +00:00
|
|
|
EXPORT_SYMBOL(dmu_object_zapify);
|
|
|
|
EXPORT_SYMBOL(dmu_object_free_zapified);
|
2010-08-26 18:49:16 +00:00
|
|
|
#endif
|