* Copyright (c) 2015, STRATO AG, Inc. All rights reserved.
* Copyright (c) 2016 Actifio, Inc. All rights reserved.
* Copyright 2017 Nexenta Systems, Inc.
+ * Copyright (c) 2017 Open-E, Inc. All Rights Reserved.
*/
/* Portions Copyright 2010 Robert Milkowski */
#include <sys/zfs_onexit.h>
#include <sys/dsl_destroy.h>
#include <sys/vdev.h>
+#include <sys/zfeature.h>
#include <sys/policy.h>
#include <sys/spa_impl.h>
#include <sys/dmu_send.h>
+#include <sys/zfs_project.h>
+#include "zfs_namecheck.h"
/*
* Needed to close a window in dnode_move() that allows the objset to be freed
*/
int dmu_rescan_dnode_threshold = 1 << DN_MAX_INDBLKSHIFT;
+static char *upgrade_tag = "upgrade_tag";
+
static void dmu_objset_find_dp_cb(void *arg);
static void dmu_objset_upgrade(objset_t *os, dmu_objset_upgrade_cb_t cb);
}
}
+static void
+smallblk_changed_cb(void *arg, uint64_t newval)
+{
+ objset_t *os = arg;
+
+ /*
+ * Inheritance and range checking should have been done by now.
+ */
+ ASSERT(newval <= SPA_OLD_MAXBLOCKSIZE);
+ ASSERT(ISP2(newval));
+
+ os->os_zpl_special_smallblock = newval;
+}
+
static void
logbias_changed_cb(void *arg, uint64_t newval)
{
{
objset_phys_t *osp = buf;
- ASSERT(size == OBJSET_OLD_PHYS_SIZE || size == sizeof (objset_phys_t));
+ ASSERT(size == OBJSET_PHYS_SIZE_V1 || size == OBJSET_PHYS_SIZE_V2 ||
+ size == sizeof (objset_phys_t));
dnode_byteswap(&osp->os_meta_dnode);
byteswap_uint64_array(&osp->os_zil_header, sizeof (zil_header_t));
osp->os_type = BSWAP_64(osp->os_type);
osp->os_flags = BSWAP_64(osp->os_flags);
- if (size == sizeof (objset_phys_t)) {
+ if (size >= OBJSET_PHYS_SIZE_V2) {
dnode_byteswap(&osp->os_userused_dnode);
dnode_byteswap(&osp->os_groupused_dnode);
+ if (size >= sizeof (objset_phys_t))
+ dnode_byteswap(&osp->os_projectused_dnode);
}
}
multilist_get_num_sublists(ml));
}
+/*
+ * Instantiates the objset_t in-memory structure corresponding to the
+ * objset_phys_t that's pointed to by the specified blkptr_t.
+ */
int
dmu_objset_open_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp,
objset_t **osp)
ASSERT(ds == NULL || MUTEX_HELD(&ds->ds_opening_lock));
+ /*
+ * The $ORIGIN dataset (if it exists) doesn't have an associated
+ * objset, so there's no reason to open it. The $ORIGIN dataset
+ * will not exist on pools older than SPA_VERSION_ORIGIN.
+ */
+ if (ds != NULL && spa_get_dsl(spa) != NULL &&
+ spa_get_dsl(spa)->dp_origin_snap != NULL) {
+ ASSERT3P(ds->ds_dir, !=,
+ spa_get_dsl(spa)->dp_origin_snap->ds_dir);
+ }
+
os = kmem_zalloc(sizeof (objset_t), KM_SLEEP);
os->os_dsl_dataset = ds;
os->os_spa = spa;
if (!BP_IS_HOLE(os->os_rootbp)) {
arc_flags_t aflags = ARC_FLAG_WAIT;
zbookmark_phys_t zb;
+ int size;
enum zio_flag zio_flags = ZIO_FLAG_CANFAIL;
SET_BOOKMARK(&zb, ds ? ds->ds_object : DMU_META_OBJSET,
ZB_ROOT_OBJECT, ZB_ROOT_LEVEL, ZB_ROOT_BLKID);
return (err);
}
+ if (spa_version(spa) < SPA_VERSION_USERSPACE)
+ size = OBJSET_PHYS_SIZE_V1;
+ else if (!spa_feature_is_enabled(spa,
+ SPA_FEATURE_PROJECT_QUOTA))
+ size = OBJSET_PHYS_SIZE_V2;
+ else
+ size = sizeof (objset_phys_t);
+
/* Increase the blocksize if we are permitted. */
- if (spa_version(spa) >= SPA_VERSION_USERSPACE &&
- arc_buf_size(os->os_phys_buf) < sizeof (objset_phys_t)) {
+ if (arc_buf_size(os->os_phys_buf) < size) {
arc_buf_t *buf = arc_alloc_buf(spa, &os->os_phys_buf,
- ARC_BUFC_METADATA, sizeof (objset_phys_t));
- bzero(buf->b_data, sizeof (objset_phys_t));
+ ARC_BUFC_METADATA, size);
+ bzero(buf->b_data, size);
bcopy(os->os_phys_buf->b_data, buf->b_data,
arc_buf_size(os->os_phys_buf));
arc_buf_destroy(os->os_phys_buf, &os->os_phys_buf);
os->os_flags = os->os_phys->os_flags;
} else {
int size = spa_version(spa) >= SPA_VERSION_USERSPACE ?
- sizeof (objset_phys_t) : OBJSET_OLD_PHYS_SIZE;
+ sizeof (objset_phys_t) : OBJSET_PHYS_SIZE_V1;
os->os_phys_buf = arc_alloc_buf(spa, &os->os_phys_buf,
ARC_BUFC_METADATA, size);
os->os_phys = os->os_phys_buf->b_data;
bzero(os->os_phys, size);
}
+ /*
+ * These properties will be filled in by the logic in zfs_get_zplprop()
+ * when they are queried for the first time.
+ */
+ os->os_version = OBJSET_PROP_UNINITIALIZED;
+ os->os_normalization = OBJSET_PROP_UNINITIALIZED;
+ os->os_utf8only = OBJSET_PROP_UNINITIALIZED;
+ os->os_casesensitivity = OBJSET_PROP_UNINITIALIZED;
/*
* Note: the changed_cb will be called once before the register
zfs_prop_to_name(ZFS_PROP_DNODESIZE),
dnodesize_changed_cb, os);
}
+ if (err == 0) {
+ err = dsl_prop_register(ds,
+ zfs_prop_to_name(
+ ZFS_PROP_SPECIAL_SMALL_BLOCKS),
+ smallblk_changed_cb, os);
+ }
}
if (needlock)
dsl_pool_config_exit(dmu_objset_pool(os), FTAG);
dnode_special_open(os, &os->os_phys->os_meta_dnode,
DMU_META_DNODE_OBJECT, &os->os_meta_dnode);
- if (arc_buf_size(os->os_phys_buf) >= sizeof (objset_phys_t)) {
+ if (OBJSET_BUF_HAS_USERUSED(os->os_phys_buf)) {
dnode_special_open(os, &os->os_phys->os_userused_dnode,
DMU_USERUSED_OBJECT, &os->os_userused_dnode);
dnode_special_open(os, &os->os_phys->os_groupused_dnode,
DMU_GROUPUSED_OBJECT, &os->os_groupused_dnode);
+ if (OBJSET_BUF_HAS_PROJECTUSED(os->os_phys_buf))
+ dnode_special_open(os,
+ &os->os_phys->os_projectused_dnode,
+ DMU_PROJECTUSED_OBJECT, &os->os_projectused_dnode);
}
mutex_init(&os->os_upgrade_lock, NULL, MUTEX_DEFAULT, NULL);
return (SET_ERROR(EINVAL));
} else if (!readonly && dsl_dataset_is_snapshot(ds)) {
return (SET_ERROR(EROFS));
+ } else if (!readonly && decrypt &&
+ dsl_dir_incompatible_encryption_version(ds->ds_dir)) {
+ return (SET_ERROR(EROFS));
}
/* if we are decrypting, we can now check MACs in os->os_phys_buf */
if (decrypt && arc_is_unauthenticated((*osp)->os_phys_buf)) {
+ zbookmark_phys_t zb;
+
+ SET_BOOKMARK(&zb, ds->ds_object, ZB_ROOT_OBJECT,
+ ZB_ROOT_LEVEL, ZB_ROOT_BLKID);
err = arc_untransform((*osp)->os_phys_buf, (*osp)->os_spa,
- ds->ds_object, B_FALSE);
+ &zb, B_FALSE);
if (err != 0)
return (err);
return (err);
}
- dsl_pool_rele(dp, FTAG);
-
- /* user accounting requires the dataset to be decrypted */
- if (dmu_objset_userobjspace_upgradable(*osp) &&
+ /*
+ * User accounting requires the dataset to be decrypted and rw.
+ * We also don't begin user accounting during claiming to help
+ * speed up pool import times and to keep this txg reserved
+ * completely for recovery work.
+ */
+ if ((dmu_objset_userobjspace_upgradable(*osp) ||
+ dmu_objset_projectquota_upgradable(*osp)) &&
+ !readonly && !dp->dp_spa->spa_claiming &&
(ds->ds_dir->dd_crypto_obj == 0 || decrypt))
- dmu_objset_userobjspace_upgrade(*osp);
+ dmu_objset_id_quota_upgrade(*osp);
+ dsl_pool_rele(dp, FTAG);
return (0);
}
* same name so that it can be partially torn down and reconstructed.
*/
void
-dmu_objset_refresh_ownership(objset_t *os, boolean_t decrypt, void *tag)
+dmu_objset_refresh_ownership(dsl_dataset_t *ds, dsl_dataset_t **newds,
+ boolean_t decrypt, void *tag)
{
dsl_pool_t *dp;
- dsl_dataset_t *ds, *newds;
char name[ZFS_MAX_DATASET_NAME_LEN];
- ds = os->os_dsl_dataset;
VERIFY3P(ds, !=, NULL);
VERIFY3P(ds->ds_owner, ==, tag);
VERIFY(dsl_dataset_long_held(ds));
dsl_dataset_name(ds, name);
- dp = dmu_objset_pool(os);
+ dp = ds->ds_dir->dd_pool;
dsl_pool_config_enter(dp, FTAG);
- dmu_objset_disown(os, decrypt, tag);
+ dsl_dataset_disown(ds, decrypt, tag);
VERIFY0(dsl_dataset_own(dp, name,
- (decrypt) ? DS_HOLD_FLAG_DECRYPT : 0, tag, &newds));
- VERIFY3P(newds, ==, os->os_dsl_dataset);
+ (decrypt) ? DS_HOLD_FLAG_DECRYPT : 0, tag, newds));
dsl_pool_config_exit(dp, FTAG);
}
kmem_free(dn_marker, sizeof (dnode_t));
if (DMU_USERUSED_DNODE(os) != NULL) {
+ if (DMU_PROJECTUSED_DNODE(os) != NULL)
+ dnode_evict_dbufs(DMU_PROJECTUSED_DNODE(os));
dnode_evict_dbufs(DMU_GROUPUSED_DNODE(os));
dnode_evict_dbufs(DMU_USERUSED_DNODE(os));
}
void
dmu_objset_evict(objset_t *os)
{
- int t;
-
dsl_dataset_t *ds = os->os_dsl_dataset;
- for (t = 0; t < TXG_SIZE; t++)
+ for (int t = 0; t < TXG_SIZE; t++)
ASSERT(!dmu_objset_is_dirty(os, t));
if (ds)
dnode_special_close(&os->os_meta_dnode);
if (DMU_USERUSED_DNODE(os)) {
+ if (DMU_PROJECTUSED_DNODE(os))
+ dnode_special_close(&os->os_projectused_dnode);
dnode_special_close(&os->os_userused_dnode);
dnode_special_close(&os->os_groupused_dnode);
}
kmem_free(os, sizeof (objset_t));
}
-timestruc_t
+inode_timespec_t
dmu_objset_snap_cmtime(objset_t *os)
{
return (dsl_dir_snap_cmtime(os->os_dsl_dataset->ds_dir));
os->os_phys->os_flags |=
OBJSET_FLAG_USEROBJACCOUNTING_COMPLETE;
}
+ if (dmu_objset_projectquota_enabled(os)) {
+ ds->ds_feature_activation_needed[
+ SPA_FEATURE_PROJECT_QUOTA] = B_TRUE;
+ os->os_phys->os_flags |=
+ OBJSET_FLAG_PROJECTQUOTA_COMPLETE;
+ }
os->os_flags = os->os_phys->os_flags;
}
if (strlen(doca->doca_name) >= ZFS_MAX_DATASET_NAME_LEN)
return (SET_ERROR(ENAMETOOLONG));
+ if (dataset_nestcheck(doca->doca_name) != 0)
+ return (SET_ERROR(ENAMETOOLONG));
+
error = dsl_dir_hold(dp, doca->doca_name, FTAG, &pdd, &tail);
if (error != 0)
return (error);
return (SET_ERROR(EEXIST));
}
- error = dmu_objset_create_crypt_check(pdd, doca->doca_dcp);
+ error = dmu_objset_create_crypt_check(pdd, doca->doca_dcp, NULL);
if (error != 0) {
dsl_dir_rele(pdd, FTAG);
return (error);
* allocated. Rather than adding NULL checks throughout this code
* or adding dummy dcp's to all of the callers we simply create a
* dummy one here and use that. This zero dcp will have the same
- * effect as asking for inheritence of all encryption params.
+ * effect as asking for inheritance of all encryption params.
*/
doca.doca_dcp = (dcp != NULL) ? dcp : &tmp_dcp;
6, ZFS_SPACE_CHECK_NORMAL));
}
+static int
+dmu_objset_remap_indirects_impl(objset_t *os, uint64_t last_removed_txg)
+{
+ int error = 0;
+ uint64_t object = 0;
+ while ((error = dmu_object_next(os, &object, B_FALSE, 0)) == 0) {
+ error = dmu_object_remap_indirects(os, object,
+ last_removed_txg);
+ /*
+ * If the ZPL removed the object before we managed to dnode_hold
+ * it, we would get an ENOENT. If the ZPL declares its intent
+ * to remove the object (dnode_free) before we manage to
+ * dnode_hold it, we would get an EEXIST. In either case, we
+ * want to continue remapping the other objects in the objset;
+ * in all other cases, we want to break early.
+ */
+ if (error != 0 && error != ENOENT && error != EEXIST) {
+ break;
+ }
+ }
+ if (error == ESRCH) {
+ error = 0;
+ }
+ return (error);
+}
+
+int
+dmu_objset_remap_indirects(const char *fsname)
+{
+ int error = 0;
+ objset_t *os = NULL;
+ uint64_t last_removed_txg;
+ uint64_t remap_start_txg;
+ dsl_dir_t *dd;
+
+ error = dmu_objset_hold(fsname, FTAG, &os);
+ if (error != 0) {
+ return (error);
+ }
+ dd = dmu_objset_ds(os)->ds_dir;
+
+ if (!spa_feature_is_enabled(dmu_objset_spa(os),
+ SPA_FEATURE_OBSOLETE_COUNTS)) {
+ dmu_objset_rele(os, FTAG);
+ return (SET_ERROR(ENOTSUP));
+ }
+
+ if (dsl_dataset_is_snapshot(dmu_objset_ds(os))) {
+ dmu_objset_rele(os, FTAG);
+ return (SET_ERROR(EINVAL));
+ }
+
+ /*
+ * If there has not been a removal, we're done.
+ */
+ last_removed_txg = spa_get_last_removal_txg(dmu_objset_spa(os));
+ if (last_removed_txg == -1ULL) {
+ dmu_objset_rele(os, FTAG);
+ return (0);
+ }
+
+ /*
+ * If we have remapped since the last removal, we're done.
+ */
+ if (dsl_dir_is_zapified(dd)) {
+ uint64_t last_remap_txg;
+ if (zap_lookup(spa_meta_objset(dmu_objset_spa(os)),
+ dd->dd_object, DD_FIELD_LAST_REMAP_TXG,
+ sizeof (last_remap_txg), 1, &last_remap_txg) == 0 &&
+ last_remap_txg > last_removed_txg) {
+ dmu_objset_rele(os, FTAG);
+ return (0);
+ }
+ }
+
+ dsl_dataset_long_hold(dmu_objset_ds(os), FTAG);
+ dsl_pool_rele(dmu_objset_pool(os), FTAG);
+
+ remap_start_txg = spa_last_synced_txg(dmu_objset_spa(os));
+ error = dmu_objset_remap_indirects_impl(os, last_removed_txg);
+ if (error == 0) {
+ /*
+ * We update the last_remap_txg to be the start txg so that
+ * we can guarantee that every block older than last_remap_txg
+ * that can be remapped has been remapped.
+ */
+ error = dsl_dir_update_last_remap_txg(dd, remap_start_txg);
+ }
+
+ dsl_dataset_long_rele(dmu_objset_ds(os), FTAG);
+ dsl_dataset_rele(dmu_objset_ds(os), FTAG);
+
+ return (error);
+}
+
int
dmu_objset_snapshot_one(const char *fsname, const char *snapname)
{
os->os_upgrade_exit = B_TRUE;
os->os_upgrade_id = 0;
mutex_exit(&os->os_upgrade_lock);
+ dsl_dataset_long_rele(dmu_objset_ds(os), upgrade_tag);
}
static void
if (os->os_upgrade_id != 0)
return;
+ ASSERT(dsl_pool_config_held(dmu_objset_pool(os)));
+ dsl_dataset_long_hold(dmu_objset_ds(os), upgrade_tag);
+
mutex_enter(&os->os_upgrade_lock);
if (os->os_upgrade_id == 0 && os->os_upgrade_status == 0) {
os->os_upgrade_exit = B_FALSE;
os->os_upgrade_id = taskq_dispatch(
os->os_spa->spa_upgrade_taskq,
dmu_objset_upgrade_task_cb, os, TQ_SLEEP);
- if (os->os_upgrade_id == TASKQID_INVALID)
+ if (os->os_upgrade_id == TASKQID_INVALID) {
+ dsl_dataset_long_rele(dmu_objset_ds(os), upgrade_tag);
os->os_upgrade_status = ENOMEM;
+ }
}
mutex_exit(&os->os_upgrade_lock);
}
os->os_upgrade_id = 0;
mutex_exit(&os->os_upgrade_lock);
- taskq_cancel_id(os->os_spa->spa_upgrade_taskq, id);
+ if ((taskq_cancel_id(os->os_spa->spa_upgrade_taskq, id)) == 0) {
+ dsl_dataset_long_rele(dmu_objset_ds(os), upgrade_tag);
+ }
txg_wait_synced(os->os_spa->spa_dsl_pool, 0);
} else {
mutex_exit(&os->os_upgrade_lock);
ASSERT3U(dn->dn_nlevels, <=, DN_MAX_LEVELS);
multilist_sublist_remove(list, dn);
+ /*
+ * If we are not doing useraccounting (os_synced_dnodes == NULL)
+ * we are done with this dnode for this txg. Unset dn_dirty_txg
+ * if later txgs aren't dirtying it so that future holders do
+ * not get a stale value. Otherwise, we will do this in
+ * userquota_updates_task() when processing has completely
+ * finished for this txg.
+ */
multilist_t *newlist = dn->dn_objset->os_synced_dnodes;
if (newlist != NULL) {
(void) dnode_add_ref(dn, newlist);
multilist_insert(newlist, dn);
+ } else {
+ mutex_enter(&dn->dn_mtx);
+ if (dn->dn_dirty_txg == tx->tx_txg)
+ dn->dn_dirty_txg = 0;
+ mutex_exit(&dn->dn_mtx);
}
dnode_sync(dn, tx);
static void
dmu_objset_write_ready(zio_t *zio, arc_buf_t *abuf, void *arg)
{
- int i;
-
blkptr_t *bp = zio->io_bp;
objset_t *os = arg;
dnode_phys_t *dnp = &os->os_phys->os_meta_dnode;
* Update rootbp fill count: it should be the number of objects
* allocated in the object set (not counting the "special"
* objects that are stored in the objset_phys_t -- the meta
- * dnode and user/group accounting objects).
+ * dnode and user/group/project accounting objects).
*/
- for (i = 0; i < dnp->dn_nblkptr; i++)
+ for (int i = 0; i < dnp->dn_nblkptr; i++)
fill += BP_GET_FILL(&dnp->dn_blkptr[i]);
BP_SET_FILL(bp, fill);
dmu_write_policy(os, NULL, 0, 0, &zp);
/*
- * If we are either claiming the ZIL or doing a raw receive write out
- * the os_phys_buf raw. Neither of these actions will effect the MAC
- * at this point.
+ * If we are either claiming the ZIL or doing a raw receive, write
+ * out the os_phys_buf raw. Neither of these actions will effect the
+ * MAC at this point.
*/
- if (arc_is_unauthenticated(os->os_phys_buf) || os->os_next_write_raw) {
+ if (os->os_raw_receive ||
+ os->os_next_write_raw[tx->tx_txg & TXG_MASK]) {
ASSERT(os->os_encrypted);
- os->os_next_write_raw = B_FALSE;
+ os->os_next_write_raw[tx->tx_txg & TXG_MASK] = B_FALSE;
arc_convert_to_raw(os->os_phys_buf,
os->os_dsl_dataset->ds_object, ZFS_HOST_BYTEORDER,
DMU_OT_OBJSET, NULL, NULL, NULL);
dnode_sync(DMU_GROUPUSED_DNODE(os), tx);
}
+ if (DMU_PROJECTUSED_DNODE(os) &&
+ DMU_PROJECTUSED_DNODE(os)->dn_type != DMU_OT_NONE) {
+ DMU_PROJECTUSED_DNODE(os)->dn_zio = zio;
+ dnode_sync(DMU_PROJECTUSED_DNODE(os), tx);
+ }
+
txgoff = tx->tx_txg & TXG_MASK;
if (dmu_objset_userused_enabled(os) &&
spa_feature_is_enabled(os->os_spa, SPA_FEATURE_USEROBJ_ACCOUNTING));
}
+boolean_t
+dmu_objset_projectquota_enabled(objset_t *os)
+{
+ return (used_cbs[os->os_phys->os_type] != NULL &&
+ DMU_PROJECTUSED_DNODE(os) != NULL &&
+ spa_feature_is_enabled(os->os_spa, SPA_FEATURE_PROJECT_QUOTA));
+}
+
typedef struct userquota_node {
/* must be in the first filed, see userquota_update_cache() */
char uqn_id[20 + DMU_OBJACCT_PREFIX_LEN];
typedef struct userquota_cache {
avl_tree_t uqc_user_deltas;
avl_tree_t uqc_group_deltas;
+ avl_tree_t uqc_project_deltas;
} userquota_cache_t;
static int
kmem_free(uqn, sizeof (*uqn));
}
avl_destroy(&cache->uqc_group_deltas);
+
+ if (dmu_objset_projectquota_enabled(os)) {
+ cookie = NULL;
+ while ((uqn = avl_destroy_nodes(&cache->uqc_project_deltas,
+ &cookie)) != NULL) {
+ mutex_enter(&os->os_userused_lock);
+ VERIFY0(zap_increment(os, DMU_PROJECTUSED_OBJECT,
+ uqn->uqn_id, uqn->uqn_delta, tx));
+ mutex_exit(&os->os_userused_lock);
+ kmem_free(uqn, sizeof (*uqn));
+ }
+ avl_destroy(&cache->uqc_project_deltas);
+ }
}
static void
}
static void
-do_userquota_update(userquota_cache_t *cache, uint64_t used, uint64_t flags,
- uint64_t user, uint64_t group, boolean_t subtract)
+do_userquota_update(objset_t *os, userquota_cache_t *cache, uint64_t used,
+ uint64_t flags, uint64_t user, uint64_t group, uint64_t project,
+ boolean_t subtract)
{
- if ((flags & DNODE_FLAG_USERUSED_ACCOUNTED)) {
+ if (flags & DNODE_FLAG_USERUSED_ACCOUNTED) {
int64_t delta = DNODE_MIN_SIZE + used;
char name[20];
(void) sprintf(name, "%llx", (longlong_t)group);
userquota_update_cache(&cache->uqc_group_deltas, name, delta);
+
+ if (dmu_objset_projectquota_enabled(os)) {
+ (void) sprintf(name, "%llx", (longlong_t)project);
+ userquota_update_cache(&cache->uqc_project_deltas,
+ name, delta);
+ }
}
}
static void
-do_userobjquota_update(userquota_cache_t *cache, uint64_t flags,
- uint64_t user, uint64_t group, boolean_t subtract)
+do_userobjquota_update(objset_t *os, userquota_cache_t *cache, uint64_t flags,
+ uint64_t user, uint64_t group, uint64_t project, boolean_t subtract)
{
if (flags & DNODE_FLAG_USEROBJUSED_ACCOUNTED) {
char name[20 + DMU_OBJACCT_PREFIX_LEN];
(void) snprintf(name, sizeof (name), DMU_OBJACCT_PREFIX "%llx",
(longlong_t)group);
userquota_update_cache(&cache->uqc_group_deltas, name, delta);
+
+ if (dmu_objset_projectquota_enabled(os)) {
+ (void) snprintf(name, sizeof (name),
+ DMU_OBJACCT_PREFIX "%llx", (longlong_t)project);
+ userquota_update_cache(&cache->uqc_project_deltas,
+ name, delta);
+ }
}
}
sizeof (userquota_node_t), offsetof(userquota_node_t, uqn_node));
avl_create(&cache.uqc_group_deltas, userquota_compare,
sizeof (userquota_node_t), offsetof(userquota_node_t, uqn_node));
+ if (dmu_objset_projectquota_enabled(os))
+ avl_create(&cache.uqc_project_deltas, userquota_compare,
+ sizeof (userquota_node_t), offsetof(userquota_node_t,
+ uqn_node));
while ((dn = multilist_sublist_head(list)) != NULL) {
int flags;
flags = dn->dn_id_flags;
ASSERT(flags);
if (flags & DN_ID_OLD_EXIST) {
- do_userquota_update(&cache,
- dn->dn_oldused, dn->dn_oldflags,
- dn->dn_olduid, dn->dn_oldgid, B_TRUE);
- do_userobjquota_update(&cache, dn->dn_oldflags,
- dn->dn_olduid, dn->dn_oldgid, B_TRUE);
+ do_userquota_update(os, &cache, dn->dn_oldused,
+ dn->dn_oldflags, dn->dn_olduid, dn->dn_oldgid,
+ dn->dn_oldprojid, B_TRUE);
+ do_userobjquota_update(os, &cache, dn->dn_oldflags,
+ dn->dn_olduid, dn->dn_oldgid,
+ dn->dn_oldprojid, B_TRUE);
}
if (flags & DN_ID_NEW_EXIST) {
- do_userquota_update(&cache,
+ do_userquota_update(os, &cache,
DN_USED_BYTES(dn->dn_phys), dn->dn_phys->dn_flags,
- dn->dn_newuid, dn->dn_newgid, B_FALSE);
- do_userobjquota_update(&cache, dn->dn_phys->dn_flags,
- dn->dn_newuid, dn->dn_newgid, B_FALSE);
+ dn->dn_newuid, dn->dn_newgid,
+ dn->dn_newprojid, B_FALSE);
+ do_userobjquota_update(os, &cache,
+ dn->dn_phys->dn_flags, dn->dn_newuid, dn->dn_newgid,
+ dn->dn_newprojid, B_FALSE);
}
mutex_enter(&dn->dn_mtx);
if (dn->dn_id_flags & DN_ID_NEW_EXIST) {
dn->dn_olduid = dn->dn_newuid;
dn->dn_oldgid = dn->dn_newgid;
+ dn->dn_oldprojid = dn->dn_newprojid;
dn->dn_id_flags |= DN_ID_OLD_EXIST;
if (dn->dn_bonuslen == 0)
dn->dn_id_flags |= DN_ID_CHKED_SPILL;
dn->dn_id_flags |= DN_ID_CHKED_BONUS;
}
dn->dn_id_flags &= ~(DN_ID_NEW_EXIST);
+ if (dn->dn_dirty_txg == spa_syncing_txg(os->os_spa))
+ dn->dn_dirty_txg = 0;
mutex_exit(&dn->dn_mtx);
multilist_sublist_remove(list, dn);
if (!dmu_objset_userused_enabled(os))
return;
- /* if this is a raw receive just return and handle accounting later */
+ /*
+ * If this is a raw receive just return and handle accounting
+ * later when we have the keys loaded. We also don't do user
+ * accounting during claiming since the datasets are not owned
+ * for the duration of claiming and this txg should only be
+ * used for recovery.
+ */
if (os->os_encrypted && dmu_objset_is_receiving(os))
return;
- /* Allocate the user/groupused objects if necessary. */
+ if (tx->tx_txg <= os->os_spa->spa_claim_max_txg)
+ return;
+
+ /* Allocate the user/group/project used objects if necessary. */
if (DMU_USERUSED_DNODE(os)->dn_type == DMU_OT_NONE) {
VERIFY0(zap_create_claim(os,
DMU_USERUSED_OBJECT,
DMU_OT_USERGROUP_USED, DMU_OT_NONE, 0, tx));
}
+ if (dmu_objset_projectquota_enabled(os) &&
+ DMU_PROJECTUSED_DNODE(os)->dn_type == DMU_OT_NONE) {
+ VERIFY0(zap_create_claim(os, DMU_PROJECTUSED_OBJECT,
+ DMU_OT_USERGROUP_USED, DMU_OT_NONE, 0, tx));
+ }
+
for (int i = 0;
i < multilist_get_num_sublists(os->os_synced_dnodes); i++) {
userquota_updates_arg_t *uua =
dmu_buf_impl_t *db = NULL;
uint64_t *user = NULL;
uint64_t *group = NULL;
+ uint64_t *project = NULL;
int flags = dn->dn_id_flags;
int error;
boolean_t have_spill = B_FALSE;
ASSERT(data);
user = &dn->dn_olduid;
group = &dn->dn_oldgid;
+ project = &dn->dn_oldprojid;
} else if (data) {
user = &dn->dn_newuid;
group = &dn->dn_newgid;
+ project = &dn->dn_newprojid;
}
/*
* type has changed and that type isn't an object type to track
*/
error = used_cbs[os->os_phys->os_type](dn->dn_bonustype, data,
- user, group);
+ user, group, project);
/*
* Preserve existing uid/gid when the callback can't determine
if (flags & DN_ID_OLD_EXIST) {
dn->dn_newuid = dn->dn_olduid;
dn->dn_newgid = dn->dn_oldgid;
+ dn->dn_newprojid = dn->dn_oldprojid;
} else {
dn->dn_newuid = 0;
dn->dn_newgid = 0;
+ dn->dn_newprojid = ZFS_DEFAULT_PROJID;
}
error = 0;
}
OBJSET_FLAG_USEROBJACCOUNTING_COMPLETE);
}
+boolean_t
+dmu_objset_projectquota_present(objset_t *os)
+{
+ return (os->os_phys->os_flags &
+ OBJSET_FLAG_PROJECTQUOTA_COMPLETE);
+}
+
static int
dmu_objset_space_upgrade(objset_t *os)
{
}
static int
-dmu_objset_userobjspace_upgrade_cb(objset_t *os)
+dmu_objset_id_quota_upgrade_cb(objset_t *os)
{
int err = 0;
- if (dmu_objset_userobjspace_present(os))
+ if (dmu_objset_userobjspace_present(os) &&
+ dmu_objset_projectquota_present(os))
return (0);
if (dmu_objset_is_snapshot(os))
return (SET_ERROR(EINVAL));
if (!dmu_objset_userobjused_enabled(os))
return (SET_ERROR(ENOTSUP));
+ if (!dmu_objset_projectquota_enabled(os) &&
+ dmu_objset_userobjspace_present(os))
+ return (SET_ERROR(ENOTSUP));
dmu_objset_ds(os)->ds_feature_activation_needed[
SPA_FEATURE_USEROBJ_ACCOUNTING] = B_TRUE;
+ if (dmu_objset_projectquota_enabled(os))
+ dmu_objset_ds(os)->ds_feature_activation_needed[
+ SPA_FEATURE_PROJECT_QUOTA] = B_TRUE;
err = dmu_objset_space_upgrade(os);
if (err)
return (err);
os->os_flags |= OBJSET_FLAG_USEROBJACCOUNTING_COMPLETE;
+ if (dmu_objset_projectquota_enabled(os))
+ os->os_flags |= OBJSET_FLAG_PROJECTQUOTA_COMPLETE;
+
txg_wait_synced(dmu_objset_pool(os), 0);
return (0);
}
void
-dmu_objset_userobjspace_upgrade(objset_t *os)
+dmu_objset_id_quota_upgrade(objset_t *os)
{
- dmu_objset_upgrade(os, dmu_objset_userobjspace_upgrade_cb);
+ dmu_objset_upgrade(os, dmu_objset_id_quota_upgrade_cb);
}
boolean_t
!dmu_objset_userobjspace_present(os));
}
+boolean_t
+dmu_objset_projectquota_upgradable(objset_t *os)
+{
+ return (dmu_objset_type(os) == DMU_OST_ZFS &&
+ !dmu_objset_is_snapshot(os) &&
+ dmu_objset_projectquota_enabled(os) &&
+ !dmu_objset_projectquota_present(os));
+}
+
void
dmu_objset_space(objset_t *os, uint64_t *refdbytesp, uint64_t *availbytesp,
uint64_t *usedobjsp, uint64_t *availobjsp)
dmu_objset_find_dp_impl(dmu_objset_find_ctx_t *dcp)
{
dsl_pool_t *dp = dcp->dc_dp;
- dmu_objset_find_ctx_t *child_dcp;
dsl_dir_t *dd;
dsl_dataset_t *ds;
zap_cursor_t zc;
sizeof (uint64_t));
ASSERT3U(attr->za_num_integers, ==, 1);
- child_dcp =
+ dmu_objset_find_ctx_t *child_dcp =
kmem_alloc(sizeof (*child_dcp), KM_SLEEP);
*child_dcp = *dcp;
child_dcp->dc_ddobj = attr->za_first_integer;
return (error);
}
+boolean_t
+dmu_objset_incompatible_encryption_version(objset_t *os)
+{
+ return (dsl_dir_incompatible_encryption_version(
+ os->os_dsl_dataset->ds_dir));
+}
+
void
dmu_objset_set_user(objset_t *os, void *user_ptr)
{
}
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+#if defined(_KERNEL)
EXPORT_SYMBOL(dmu_objset_zil);
EXPORT_SYMBOL(dmu_objset_pool);
EXPORT_SYMBOL(dmu_objset_ds);
EXPORT_SYMBOL(dmu_objset_userspace_upgrade);
EXPORT_SYMBOL(dmu_objset_userspace_present);
EXPORT_SYMBOL(dmu_objset_userobjused_enabled);
-EXPORT_SYMBOL(dmu_objset_userobjspace_upgrade);
EXPORT_SYMBOL(dmu_objset_userobjspace_upgradable);
EXPORT_SYMBOL(dmu_objset_userobjspace_present);
+EXPORT_SYMBOL(dmu_objset_projectquota_enabled);
+EXPORT_SYMBOL(dmu_objset_projectquota_present);
+EXPORT_SYMBOL(dmu_objset_projectquota_upgradable);
+EXPORT_SYMBOL(dmu_objset_id_quota_upgrade);
#endif
projects / mirror_zfs.git / blobdiff