Remove code for zfs remap

The "zfs remap" command was disabled by
6e91a72fe3ff8bb282490773bd687632f3e8c79d, because it has little utility
and introduced some tricky bugs.  This commit removes the code for it,
the associated ZFS_IOC_REMAP ioctl, and tests.

Note that the ioctl and property will remain, but have no functionality.
This allows older software to fail gracefully if it attempts to use
these, and avoids a backwards incompatibility that would be introduced if
we renumbered the later ioctls/props.

Reviewed-by: Tom Caputi <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Matthew Ahrens <[email protected]>
Closes #8944 

6 files changed, 3 insertions, 364 deletions

diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c
index 8afc3df37..abfae29ad 100644
--- a/module/zfs/dbuf.c
+++ b/module/zfs/dbuf.c
@@ -4445,60 +4445,6 @@ dbuf_remap_impl(dnode_t *dn, blkptr_t *bp, dmu_tx_t *tx)
 }
 
 /*
- * Returns true if a dbuf_remap would modify the dbuf. We do this by attempting
- * to remap a copy of every bp in the dbuf.
- */
-boolean_t
-dbuf_can_remap(const dmu_buf_impl_t *db)
-{
-	spa_t *spa = dmu_objset_spa(db->db_objset);
-	blkptr_t *bp = db->db.db_data;
-	boolean_t ret = B_FALSE;
-
-	ASSERT3U(db->db_level, >, 0);
-	ASSERT3S(db->db_state, ==, DB_CACHED);
-
-	ASSERT(spa_feature_is_active(spa, SPA_FEATURE_DEVICE_REMOVAL));
-
-	spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
-	for (int i = 0; i < db->db.db_size >> SPA_BLKPTRSHIFT; i++) {
-		blkptr_t bp_copy = bp[i];
-		if (spa_remap_blkptr(spa, &bp_copy, NULL, NULL)) {
-			ret = B_TRUE;
-			break;
-		}
-	}
-	spa_config_exit(spa, SCL_VDEV, FTAG);
-
-	return (ret);
-}
-
-boolean_t
-dnode_needs_remap(const dnode_t *dn)
-{
-	spa_t *spa = dmu_objset_spa(dn->dn_objset);
-	boolean_t ret = B_FALSE;
-
-	if (dn->dn_phys->dn_nlevels == 0) {
-		return (B_FALSE);
-	}
-
-	ASSERT(spa_feature_is_active(spa, SPA_FEATURE_DEVICE_REMOVAL));
-
-	spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
-	for (int j = 0; j < dn->dn_phys->dn_nblkptr; j++) {
-		blkptr_t bp_copy = dn->dn_phys->dn_blkptr[j];
-		if (spa_remap_blkptr(spa, &bp_copy, NULL, NULL)) {
-			ret = B_TRUE;
-			break;
-		}
-	}
-	spa_config_exit(spa, SCL_VDEV, FTAG);
-
-	return (ret);
-}
-
-/*
  * Remap any existing BP's to concrete vdevs, if possible.
  */
 static void
diff --git a/module/zfs/dmu.c b/module/zfs/dmu.c
index 4af2a13e7..0722f5c5e 100644
--- a/module/zfs/dmu.c
+++ b/module/zfs/dmu.c
@@ -75,13 +75,6 @@ unsigned long zfs_per_txg_dirty_frees_percent = 5;
 int zfs_dmu_offset_next_sync = 0;
 
 /*
- * This can be used for testing, to ensure that certain actions happen
- * while in the middle of a remap (which might otherwise complete too
- * quickly).  Used by ztest(8).
- */
-int zfs_object_remap_one_indirect_delay_ms = 0;
-
-/*
  * Limit the amount we can prefetch with one call to this amount.  This
  * helps to limit the amount of memory that can be used by prefetching.
  * Larger objects should be prefetched a bit at a time.
@@ -1114,137 +1107,6 @@ dmu_write_by_dnode(dnode_t *dn, uint64_t offset, uint64_t size,
 	dmu_buf_rele_array(dbp, numbufs, FTAG);
 }
 
-static int
-dmu_object_remap_one_indirect(objset_t *os, dnode_t *dn,
-    uint64_t last_removal_txg, uint64_t offset)
-{
-	uint64_t l1blkid = dbuf_whichblock(dn, 1, offset);
-	dnode_t *dn_tx;
-	int err = 0;
-
-	rw_enter(&dn->dn_struct_rwlock, RW_READER);
-	dmu_buf_impl_t *dbuf = dbuf_hold_level(dn, 1, l1blkid, FTAG);
-	ASSERT3P(dbuf, !=, NULL);
-
-	/*
-	 * If the block hasn't been written yet, this default will ensure
-	 * we don't try to remap it.
-	 */
-	uint64_t birth = UINT64_MAX;
-	ASSERT3U(last_removal_txg, !=, UINT64_MAX);
-	if (dbuf->db_blkptr != NULL)
-		birth = dbuf->db_blkptr->blk_birth;
-	rw_exit(&dn->dn_struct_rwlock);
-
-	/*
-	 * If this L1 was already written after the last removal, then we've
-	 * already tried to remap it.  An additional hold is taken after the
-	 * dmu_tx_assign() to handle the case where the dnode is freed while
-	 * waiting for the next open txg.
-	 */
-	if (birth <= last_removal_txg &&
-	    dbuf_read(dbuf, NULL, DB_RF_MUST_SUCCEED) == 0 &&
-	    dbuf_can_remap(dbuf)) {
-		dmu_tx_t *tx = dmu_tx_create(os);
-		dmu_tx_hold_remap_l1indirect(tx, dn->dn_object);
-		err = dmu_tx_assign(tx, TXG_WAIT);
-		if (err == 0) {
-			err = dnode_hold(os, dn->dn_object, FTAG, &dn_tx);
-			if (err == 0) {
-				(void) dbuf_dirty(dbuf, tx);
-				dnode_rele(dn_tx, FTAG);
-			}
-			dmu_tx_commit(tx);
-		} else {
-			dmu_tx_abort(tx);
-		}
-	}
-
-	dbuf_rele(dbuf, FTAG);
-
-	delay(MSEC_TO_TICK(zfs_object_remap_one_indirect_delay_ms));
-
-	return (err);
-}
-
-/*
- * Remap all blockpointers in the object, if possible, so that they reference
- * only concrete vdevs.
- *
- * To do this, iterate over the L0 blockpointers and remap any that reference
- * an indirect vdev. Note that we only examine L0 blockpointers; since we
- * cannot guarantee that we can remap all blockpointer anyways (due to split
- * blocks), we do not want to make the code unnecessarily complicated to
- * catch the unlikely case that there is an L1 block on an indirect vdev that
- * contains no indirect blockpointers.
- */
-int
-dmu_object_remap_indirects(objset_t *os, uint64_t object,
-    uint64_t last_removal_txg)
-{
-	uint64_t offset, l1span;
-	int err;
-	dnode_t *dn, *dn_tx;
-
-	err = dnode_hold(os, object, FTAG, &dn);
-	if (err != 0) {
-		return (err);
-	}
-
-	if (dn->dn_nlevels <= 1) {
-		if (issig(JUSTLOOKING) && issig(FORREAL)) {
-			err = SET_ERROR(EINTR);
-		}
-
-		/*
-		 * If the dnode has no indirect blocks, we cannot dirty them.
-		 * We still want to remap the blkptr(s) in the dnode if
-		 * appropriate, so mark it as dirty.  An additional hold is
-		 * taken after the dmu_tx_assign() to handle the case where
-		 * the dnode is freed while waiting for the next open txg.
-		 */
-		if (err == 0 && dnode_needs_remap(dn)) {
-			dmu_tx_t *tx = dmu_tx_create(os);
-			dmu_tx_hold_bonus(tx, object);
-			err = dmu_tx_assign(tx, TXG_WAIT);
-			if (err == 0) {
-				err = dnode_hold(os, object, FTAG, &dn_tx);
-				if (err == 0) {
-					dnode_setdirty(dn_tx, tx);
-					dnode_rele(dn_tx, FTAG);
-				}
-				dmu_tx_commit(tx);
-			} else {
-				dmu_tx_abort(tx);
-			}
-		}
-
-		dnode_rele(dn, FTAG);
-		return (err);
-	}
-
-	offset = 0;
-	l1span = 1ULL << (dn->dn_indblkshift - SPA_BLKPTRSHIFT +
-	    dn->dn_datablkshift);
-	/*
-	 * Find the next L1 indirect that is not a hole.
-	 */
-	while (dnode_next_offset(dn, 0, &offset, 2, 1, 0) == 0) {
-		if (issig(JUSTLOOKING) && issig(FORREAL)) {
-			err = SET_ERROR(EINTR);
-			break;
-		}
-		if ((err = dmu_object_remap_one_indirect(os, dn,
-		    last_removal_txg, offset)) != 0) {
-			break;
-		}
-		offset += l1span;
-	}
-
-	dnode_rele(dn, FTAG);
-	return (err);
-}
-
 void
 dmu_prealloc(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
     dmu_tx_t *tx)
diff --git a/module/zfs/dmu_objset.c b/module/zfs/dmu_objset.c
index 6b8c380e5..4091ac355 100644
--- a/module/zfs/dmu_objset.c
+++ b/module/zfs/dmu_objset.c
@@ -1396,101 +1396,6 @@ dmu_objset_clone(const char *clone, const char *origin)
 	    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)
 {
diff --git a/module/zfs/dmu_tx.c b/module/zfs/dmu_tx.c
index 7d65e842f..4f489de5f 100644
--- a/module/zfs/dmu_tx.c
+++ b/module/zfs/dmu_tx.c
@@ -317,23 +317,6 @@ dmu_tx_hold_write(dmu_tx_t *tx, uint64_t object, uint64_t off, int len)
 }
 
 void
-dmu_tx_hold_remap_l1indirect(dmu_tx_t *tx, uint64_t object)
-{
-	dmu_tx_hold_t *txh;
-
-	ASSERT(tx->tx_txg == 0);
-	txh = dmu_tx_hold_object_impl(tx, tx->tx_objset,
-	    object, THT_WRITE, 0, 0);
-	if (txh == NULL)
-		return;
-
-	dnode_t *dn = txh->txh_dnode;
-	(void) zfs_refcount_add_many(&txh->txh_space_towrite,
-	    1ULL << dn->dn_indblkshift, FTAG);
-	dmu_tx_count_dnode(txh);
-}
-
-void
 dmu_tx_hold_write_by_dnode(dmu_tx_t *tx, dnode_t *dn, uint64_t off, int len)
 {
 	dmu_tx_hold_t *txh;
diff --git a/module/zfs/dsl_dir.c b/module/zfs/dsl_dir.c
index 6fb711f59..741ca232e 100644
--- a/module/zfs/dsl_dir.c
+++ b/module/zfs/dsl_dir.c
@@ -757,35 +757,6 @@ dsl_enforce_ds_ss_limits(dsl_dir_t *dd, zfs_prop_t prop, cred_t *cr)
 	return (enforce);
 }
 
-static void
-dsl_dir_update_last_remap_txg_sync(void *varg, dmu_tx_t *tx)
-{
-	ddulrt_arg_t *arg = varg;
-	uint64_t last_remap_txg;
-	dsl_dir_t *dd = arg->ddulrta_dd;
-	objset_t *mos = dd->dd_pool->dp_meta_objset;
-
-	dsl_dir_zapify(dd, tx);
-	if (zap_lookup(mos, dd->dd_object, DD_FIELD_LAST_REMAP_TXG,
-	    sizeof (last_remap_txg), 1, &last_remap_txg) != 0 ||
-	    last_remap_txg < arg->ddlrta_txg) {
-		VERIFY0(zap_update(mos, dd->dd_object, DD_FIELD_LAST_REMAP_TXG,
-		    sizeof (arg->ddlrta_txg), 1, &arg->ddlrta_txg, tx));
-	}
-}
-
-int
-dsl_dir_update_last_remap_txg(dsl_dir_t *dd, uint64_t txg)
-{
-	ddulrt_arg_t arg;
-	arg.ddulrta_dd = dd;
-	arg.ddlrta_txg = txg;
-
-	return (dsl_sync_task(spa_name(dd->dd_pool->dp_spa),
-	    NULL, dsl_dir_update_last_remap_txg_sync, &arg,
-	    1, ZFS_SPACE_CHECK_RESERVED));
-}
-
 /*
  * Check if adding additional child filesystem(s) would exceed any filesystem
  * limits or adding additional snapshot(s) would exceed any snapshot limits.
@@ -1083,19 +1054,6 @@ dsl_dir_get_snapshot_count(dsl_dir_t *dd, uint64_t *count)
 	}
 }
 
-int
-dsl_dir_get_remaptxg(dsl_dir_t *dd, uint64_t *count)
-{
-	if (dsl_dir_is_zapified(dd)) {
-		objset_t *os = dd->dd_pool->dp_meta_objset;
-		return (zap_lookup(os, dd->dd_object, DD_FIELD_LAST_REMAP_TXG,
-		    sizeof (*count), 1, count));
-	} else {
-		return (ENOENT);
-	}
-
-}
-
 void
 dsl_dir_stats(dsl_dir_t *dd, nvlist_t *nv)
 {
@@ -1127,10 +1085,6 @@ dsl_dir_stats(dsl_dir_t *dd, nvlist_t *nv)
 		dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_SNAPSHOT_COUNT,
 		    count);
 	}
-	if (dsl_dir_get_remaptxg(dd, &count) == 0) {
-		dsl_prop_nvlist_add_uint64(nv, ZFS_PROP_REMAPTXG,
-		    count);
-	}
 
 	if (dsl_dir_is_clone(dd)) {
 		char buf[ZFS_MAX_DATASET_NAME_LEN];
diff --git a/module/zfs/zfs_ioctl.c b/module/zfs/zfs_ioctl.c
index 2b67761fd..c2b75cc98 100644
--- a/module/zfs/zfs_ioctl.c
+++ b/module/zfs/zfs_ioctl.c
@@ -1047,14 +1047,6 @@ zfs_secpolicy_bookmark(zfs_cmd_t *zc, nvlist_t *innvl, cred_t *cr)
 
 /* ARGSUSED */
 static int
-zfs_secpolicy_remap(zfs_cmd_t *zc, nvlist_t *innvl, cred_t *cr)
-{
-	return (zfs_secpolicy_write_perms(zc->zc_name,
-	    ZFS_DELEG_PERM_REMAP, cr));
-}
-
-/* ARGSUSED */
-static int
 zfs_secpolicy_destroy_bookmarks(zfs_cmd_t *zc, nvlist_t *innvl, cred_t *cr)
 {
 	nvpair_t *pair, *nextpair;
@@ -3447,11 +3439,8 @@ static const zfs_ioc_key_t zfs_keys_remap[] = {
 static int
 zfs_ioc_remap(const char *fsname, nvlist_t *innvl, nvlist_t *outnvl)
 {
-	if (strchr(fsname, '@') ||
-	    strchr(fsname, '%'))
-		return (SET_ERROR(EINVAL));
-
-	return (dmu_objset_remap_indirects(fsname));
+	/* This IOCTL is no longer supported. */
+	return (0);
 }
 
 /*
@@ -6790,7 +6779,7 @@ zfs_ioctl_init(void)
 	    zfs_keys_clone, ARRAY_SIZE(zfs_keys_clone));
 
 	zfs_ioctl_register("remap", ZFS_IOC_REMAP,
-	    zfs_ioc_remap, zfs_secpolicy_remap, DATASET_NAME,
+	    zfs_ioc_remap, zfs_secpolicy_none, DATASET_NAME,
 	    POOL_CHECK_SUSPENDED | POOL_CHECK_READONLY, B_FALSE, B_TRUE,
 	    zfs_keys_remap, ARRAY_SIZE(zfs_keys_remap));