OpenZFS 9075 - Improve ZFS pool import/load process and corrupted pool recovery

Some work has been done lately to improve the debugability of the ZFS pool
load (and import) process. This includes:

	7638 Refactor spa_load_impl into several functions
	8961 SPA load/import should tell us why it failed
	7277 zdb should be able to print zfs_dbgmsg's

To iterate on top of that, there's a few changes that were made to make the
import process more resilient and crash free. One of the first tasks during the
pool load process is to parse a config provided from userland that describes
what devices the pool is composed of. A vdev tree is generated from that config,
and then all the vdevs are opened.

The Meta Object Set (MOS) of the pool is accessed, and several metadata objects
that are necessary to load the pool are read. The exact configuration of the
pool is also stored inside the MOS. Since the configuration provided from
userland is external and might not accurately describe the vdev tree
of the pool at the txg that is being loaded, it cannot be relied upon to safely
operate the pool. For that reason, the configuration in the MOS is read early
on. In the past, the two configurations were compared together and if there was
a mismatch then the load process was aborted and an error was returned.

The latter was a good way to ensure a pool does not get corrupted, however it
made the pool load process needlessly fragile in cases where the vdev
configuration changed or the userland configuration was outdated. Since the MOS
is stored in 3 copies, the configuration provided by userland doesn't have to be
perfect in order to read its contents. Hence, a new approach has been adopted:
The pool is first opened with the untrusted userland configuration just so that
the real configuration can be read from the MOS. The trusted MOS configuration
is then used to generate a new vdev tree and the pool is re-opened.

When the pool is opened with an untrusted configuration, writes are disabled
to avoid accidentally damaging it. During reads, some sanity checks are
performed on block pointers to see if each DVA points to a known vdev;
when the configuration is untrusted, instead of panicking the system if those
checks fail we simply avoid issuing reads to the invalid DVAs.

This new two-step pool load process now allows rewinding pools accross
vdev tree changes such as device replacement, addition, etc. Loading a pool
from an external config file in a clustering environment also becomes much
safer now since the pool will import even if the config is outdated and didn't,
for instance, register a recent device addition.

With this code in place, it became relatively easy to implement a
long-sought-after feature: the ability to import a pool with missing top level
(i.e. non-redundant) devices. Note that since this almost guarantees some loss
of data, this feature is for now restricted to a read-only import.

Porting notes (ZTS):
* Fix 'make dist' target in zpool_import

* The maximum path length allowed by tar is 99 characters.  Several
  of the new test cases exceeded this limit resulting in them not
  being included in the tarball.  Shorten the names slightly.

* Set/get tunables using accessor functions.

* Get last synced txg via the "zfs_txg_history" mechanism.

* Clear zinject handlers in cleanup for import_cache_device_replaced
  and import_rewind_device_replaced in order that the zpool can be
  exported if there is an error.

* Increase FILESIZE to 8G in zfs-test.sh to allow for a larger
  ext4 file system to be created on ZFS_DISK2.  Also, there's
  no need to partition ZFS_DISK2 at all.  The partitioning had
  already been disabled for multipath devices.  Among other things,
  the partitioning steals some space from the ext4 file system,
  makes it difficult to accurately calculate the paramters to
  parted and can make some of the tests fail.

* Increase FS_SIZE and FILE_SIZE in the zpool_import test
  configuration now that FILESIZE is larger.

* Write more data in order that device evacuation take lonnger in
  a couple tests.

* Use mkdir -p to avoid errors when the directory already exists.

* Remove use of sudo in import_rewind_config_changed.

Authored by: Pavel Zakharov <[email protected]>
Reviewed by: George Wilson <[email protected]>
Reviewed by: Matthew Ahrens <[email protected]>
Reviewed by: Andrew Stormont <[email protected]>
Approved by: Hans Rosenfeld <[email protected]>
Ported-by: Tim Chase <[email protected]>
Signed-off-by: Tim Chase <[email protected]>

OpenZFS-issue: https://illumos.org/issues/9075
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/619c0123
Closes #7459

1 files changed, 336 insertions, 128 deletions

diff --git a/module/zfs/vdev.c b/module/zfs/vdev.c
index 3654919fc..ad53c0c89 100644
--- a/module/zfs/vdev.c
+++ b/module/zfs/vdev.c
@@ -74,6 +74,8 @@ unsigned int zfs_checksums_per_second = 20;
  */
 int zfs_scan_ignore_errors = 0;
 
+int vdev_validate_skip = B_FALSE;
+
 /*PRINTFLIKE2*/
 void
 vdev_dbgmsg(vdev_t *vd, const char *fmt, ...)
@@ -96,6 +98,57 @@ vdev_dbgmsg(vdev_t *vd, const char *fmt, ...)
 	}
 }
 
+void
+vdev_dbgmsg_print_tree(vdev_t *vd, int indent)
+{
+	char state[20];
+
+	if (vd->vdev_ishole || vd->vdev_ops == &vdev_missing_ops) {
+		zfs_dbgmsg("%*svdev %u: %s", indent, "", vd->vdev_id,
+		    vd->vdev_ops->vdev_op_type);
+		return;
+	}
+
+	switch (vd->vdev_state) {
+	case VDEV_STATE_UNKNOWN:
+		(void) snprintf(state, sizeof (state), "unknown");
+		break;
+	case VDEV_STATE_CLOSED:
+		(void) snprintf(state, sizeof (state), "closed");
+		break;
+	case VDEV_STATE_OFFLINE:
+		(void) snprintf(state, sizeof (state), "offline");
+		break;
+	case VDEV_STATE_REMOVED:
+		(void) snprintf(state, sizeof (state), "removed");
+		break;
+	case VDEV_STATE_CANT_OPEN:
+		(void) snprintf(state, sizeof (state), "can't open");
+		break;
+	case VDEV_STATE_FAULTED:
+		(void) snprintf(state, sizeof (state), "faulted");
+		break;
+	case VDEV_STATE_DEGRADED:
+		(void) snprintf(state, sizeof (state), "degraded");
+		break;
+	case VDEV_STATE_HEALTHY:
+		(void) snprintf(state, sizeof (state), "healthy");
+		break;
+	default:
+		(void) snprintf(state, sizeof (state), "<state %u>",
+		    (uint_t)vd->vdev_state);
+	}
+
+	zfs_dbgmsg("%*svdev %u: %s%s, guid: %llu, path: %s, %s", indent,
+	    "", vd->vdev_id, vd->vdev_ops->vdev_op_type,
+	    vd->vdev_islog ? " (log)" : "",
+	    (u_longlong_t)vd->vdev_guid,
+	    vd->vdev_path ? vd->vdev_path : "N/A", state);
+
+	for (uint64_t i = 0; i < vd->vdev_children; i++)
+		vdev_dbgmsg_print_tree(vd->vdev_child[i], indent + 2);
+}
+
 /*
  * Virtual device management.
  */
@@ -1424,8 +1477,13 @@ vdev_open(vdev_t *vd)
 		    vd->vdev_stat.vs_aux != VDEV_AUX_OPEN_FAILED)
 			vd->vdev_removed = B_FALSE;
 
-		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
-		    vd->vdev_stat.vs_aux);
+		if (vd->vdev_stat.vs_aux == VDEV_AUX_CHILDREN_OFFLINE) {
+			vdev_set_state(vd, B_TRUE, VDEV_STATE_OFFLINE,
+			    vd->vdev_stat.vs_aux);
+		} else {
+			vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
+			    vd->vdev_stat.vs_aux);
+		}
 		return (error);
 	}
 
@@ -1596,29 +1654,29 @@ vdev_open(vdev_t *vd)
 
 /*
  * Called once the vdevs are all opened, this routine validates the label
- * contents.  This needs to be done before vdev_load() so that we don't
+ * contents. This needs to be done before vdev_load() so that we don't
  * inadvertently do repair I/Os to the wrong device.
  *
- * If 'strict' is false ignore the spa guid check. This is necessary because
- * if the machine crashed during a re-guid the new guid might have been written
- * to all of the vdev labels, but not the cached config. The strict check
- * will be performed when the pool is opened again using the mos config.
- *
  * This function will only return failure if one of the vdevs indicates that it
  * has since been destroyed or exported.  This is only possible if
  * /etc/zfs/zpool.cache was readonly at the time.  Otherwise, the vdev state
  * will be updated but the function will return 0.
  */
 int
-vdev_validate(vdev_t *vd, boolean_t strict)
+vdev_validate(vdev_t *vd)
 {
 	spa_t *spa = vd->vdev_spa;
 	nvlist_t *label;
-	uint64_t guid = 0, top_guid;
+	uint64_t guid = 0, aux_guid = 0, top_guid;
 	uint64_t state;
+	nvlist_t *nvl;
+	uint64_t txg;
 
-	for (int c = 0; c < vd->vdev_children; c++)
-		if (vdev_validate(vd->vdev_child[c], strict) != 0)
+	if (vdev_validate_skip)
+		return (0);
+
+	for (uint64_t c = 0; c < vd->vdev_children; c++)
+		if (vdev_validate(vd->vdev_child[c]) != 0)
 			return (SET_ERROR(EBADF));
 
 	/*
@@ -1626,115 +1684,276 @@ vdev_validate(vdev_t *vd, boolean_t strict)
 	 * any further validation.  Otherwise, label I/O will fail and we will
 	 * overwrite the previous state.
 	 */
-	if (vd->vdev_ops->vdev_op_leaf && vdev_readable(vd)) {
-		uint64_t aux_guid = 0;
-		nvlist_t *nvl;
-		uint64_t txg = spa_last_synced_txg(spa) != 0 ?
-		    spa_last_synced_txg(spa) : -1ULL;
+	if (!vd->vdev_ops->vdev_op_leaf || !vdev_readable(vd))
+		return (0);
 
-		if ((label = vdev_label_read_config(vd, txg)) == NULL) {
-			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
-			    VDEV_AUX_BAD_LABEL);
-			vdev_dbgmsg(vd, "vdev_validate: failed reading config");
-			return (0);
-		}
+	/*
+	 * If we are performing an extreme rewind, we allow for a label that
+	 * was modified at a point after the current txg.
+	 */
+	if (spa->spa_extreme_rewind || spa_last_synced_txg(spa) == 0)
+		txg = UINT64_MAX;
+	else
+		txg = spa_last_synced_txg(spa);
 
-		/*
-		 * Determine if this vdev has been split off into another
-		 * pool.  If so, then refuse to open it.
-		 */
-		if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_SPLIT_GUID,
-		    &aux_guid) == 0 && aux_guid == spa_guid(spa)) {
-			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
-			    VDEV_AUX_SPLIT_POOL);
-			nvlist_free(label);
-			vdev_dbgmsg(vd, "vdev_validate: vdev split into other "
-			    "pool");
-			return (0);
-		}
+	if ((label = vdev_label_read_config(vd, txg)) == NULL) {
+		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_BAD_LABEL);
+		vdev_dbgmsg(vd, "vdev_validate: failed reading config");
+		return (0);
+	}
 
-		if (strict && (nvlist_lookup_uint64(label,
-		    ZPOOL_CONFIG_POOL_GUID, &guid) != 0 ||
-		    guid != spa_guid(spa))) {
-			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
-			    VDEV_AUX_CORRUPT_DATA);
-			nvlist_free(label);
-			vdev_dbgmsg(vd, "vdev_validate: vdev label pool_guid "
-			    "doesn't match config (%llu != %llu)",
-			    (u_longlong_t)guid,
-			    (u_longlong_t)spa_guid(spa));
-			return (0);
-		}
+	/*
+	 * Determine if this vdev has been split off into another
+	 * pool.  If so, then refuse to open it.
+	 */
+	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_SPLIT_GUID,
+	    &aux_guid) == 0 && aux_guid == spa_guid(spa)) {
+		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_SPLIT_POOL);
+		nvlist_free(label);
+		vdev_dbgmsg(vd, "vdev_validate: vdev split into other pool");
+		return (0);
+	}
 
-		if (nvlist_lookup_nvlist(label, ZPOOL_CONFIG_VDEV_TREE, &nvl)
-		    != 0 || nvlist_lookup_uint64(nvl, ZPOOL_CONFIG_ORIG_GUID,
-		    &aux_guid) != 0)
-			aux_guid = 0;
+	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_GUID, &guid) != 0) {
+		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_CORRUPT_DATA);
+		nvlist_free(label);
+		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+		    ZPOOL_CONFIG_POOL_GUID);
+		return (0);
+	}
 
-		/*
-		 * If this vdev just became a top-level vdev because its
-		 * sibling was detached, it will have adopted the parent's
-		 * vdev guid -- but the label may or may not be on disk yet.
-		 * Fortunately, either version of the label will have the
-		 * same top guid, so if we're a top-level vdev, we can
-		 * safely compare to that instead.
-		 *
-		 * If we split this vdev off instead, then we also check the
-		 * original pool's guid.  We don't want to consider the vdev
-		 * corrupt if it is partway through a split operation.
-		 */
-		if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID,
-		    &guid) != 0 ||
-		    nvlist_lookup_uint64(label, ZPOOL_CONFIG_TOP_GUID,
-		    &top_guid) != 0 ||
-		    ((vd->vdev_guid != guid && vd->vdev_guid != aux_guid) &&
-		    (vd->vdev_guid != top_guid || vd != vd->vdev_top))) {
-			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
-			    VDEV_AUX_CORRUPT_DATA);
-			nvlist_free(label);
-			vdev_dbgmsg(vd, "vdev_validate: config guid doesn't "
-			    "match label guid (%llu != %llu)",
-			    (u_longlong_t)vd->vdev_guid, (u_longlong_t)guid);
-			return (0);
+	/*
+	 * If config is not trusted then ignore the spa guid check. This is
+	 * necessary because if the machine crashed during a re-guid the new
+	 * guid might have been written to all of the vdev labels, but not the
+	 * cached config. The check will be performed again once we have the
+	 * trusted config from the MOS.
+	 */
+	if (spa->spa_trust_config && guid != spa_guid(spa)) {
+		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_CORRUPT_DATA);
+		nvlist_free(label);
+		vdev_dbgmsg(vd, "vdev_validate: vdev label pool_guid doesn't "
+		    "match config (%llu != %llu)", (u_longlong_t)guid,
+		    (u_longlong_t)spa_guid(spa));
+		return (0);
+	}
+
+	if (nvlist_lookup_nvlist(label, ZPOOL_CONFIG_VDEV_TREE, &nvl)
+	    != 0 || nvlist_lookup_uint64(nvl, ZPOOL_CONFIG_ORIG_GUID,
+	    &aux_guid) != 0)
+		aux_guid = 0;
+
+	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID, &guid) != 0) {
+		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_CORRUPT_DATA);
+		nvlist_free(label);
+		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+		    ZPOOL_CONFIG_GUID);
+		return (0);
+	}
+
+	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_TOP_GUID, &top_guid)
+	    != 0) {
+		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_CORRUPT_DATA);
+		nvlist_free(label);
+		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+		    ZPOOL_CONFIG_TOP_GUID);
+		return (0);
+	}
+
+	/*
+	 * If this vdev just became a top-level vdev because its sibling was
+	 * detached, it will have adopted the parent's vdev guid -- but the
+	 * label may or may not be on disk yet. Fortunately, either version
+	 * of the label will have the same top guid, so if we're a top-level
+	 * vdev, we can safely compare to that instead.
+	 * However, if the config comes from a cachefile that failed to update
+	 * after the detach, a top-level vdev will appear as a non top-level
+	 * vdev in the config. Also relax the constraints if we perform an
+	 * extreme rewind.
+	 *
+	 * If we split this vdev off instead, then we also check the
+	 * original pool's guid. We don't want to consider the vdev
+	 * corrupt if it is partway through a split operation.
+	 */
+	if (vd->vdev_guid != guid && vd->vdev_guid != aux_guid) {
+		boolean_t mismatch = B_FALSE;
+		if (spa->spa_trust_config && !spa->spa_extreme_rewind) {
+			if (vd != vd->vdev_top || vd->vdev_guid != top_guid)
+				mismatch = B_TRUE;
+		} else {
+			if (vd->vdev_guid != top_guid &&
+			    vd->vdev_top->vdev_guid != guid)
+				mismatch = B_TRUE;
 		}
 
-		if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE,
-		    &state) != 0) {
+		if (mismatch) {
 			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
 			    VDEV_AUX_CORRUPT_DATA);
 			nvlist_free(label);
-			vdev_dbgmsg(vd, "vdev_validate: '%s' missing",
-			    ZPOOL_CONFIG_POOL_STATE);
+			vdev_dbgmsg(vd, "vdev_validate: config guid "
+			    "doesn't match label guid");
+			vdev_dbgmsg(vd, "CONFIG: guid %llu, top_guid %llu",
+			    (u_longlong_t)vd->vdev_guid,
+			    (u_longlong_t)vd->vdev_top->vdev_guid);
+			vdev_dbgmsg(vd, "LABEL: guid %llu, top_guid %llu, "
+			    "aux_guid %llu", (u_longlong_t)guid,
+			    (u_longlong_t)top_guid, (u_longlong_t)aux_guid);
 			return (0);
 		}
+	}
 
+	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE,
+	    &state) != 0) {
+		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
+		    VDEV_AUX_CORRUPT_DATA);
 		nvlist_free(label);
+		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
+		    ZPOOL_CONFIG_POOL_STATE);
+		return (0);
+	}
 
-		/*
-		 * If this is a verbatim import, no need to check the
-		 * state of the pool.
-		 */
-		if (!(spa->spa_import_flags & ZFS_IMPORT_VERBATIM) &&
-		    spa_load_state(spa) == SPA_LOAD_OPEN &&
-		    state != POOL_STATE_ACTIVE) {
-			vdev_dbgmsg(vd, "vdev_validate: invalid pool state "
-			    "(%llu) for spa %s", (u_longlong_t)state,
-			    spa->spa_name);
-			return (SET_ERROR(EBADF));
+	nvlist_free(label);
+
+	/*
+	 * If this is a verbatim import, no need to check the
+	 * state of the pool.
+	 */
+	if (!(spa->spa_import_flags & ZFS_IMPORT_VERBATIM) &&
+	    spa_load_state(spa) == SPA_LOAD_OPEN &&
+	    state != POOL_STATE_ACTIVE) {
+		vdev_dbgmsg(vd, "vdev_validate: invalid pool state (%llu) "
+		    "for spa %s", (u_longlong_t)state, spa->spa_name);
+		return (SET_ERROR(EBADF));
+	}
+
+	/*
+	 * If we were able to open and validate a vdev that was
+	 * previously marked permanently unavailable, clear that state
+	 * now.
+	 */
+	if (vd->vdev_not_present)
+		vd->vdev_not_present = 0;
+
+	return (0);
+}
+
+static void
+vdev_copy_path_impl(vdev_t *svd, vdev_t *dvd)
+{
+	if (svd->vdev_path != NULL && dvd->vdev_path != NULL) {
+		if (strcmp(svd->vdev_path, dvd->vdev_path) != 0) {
+			zfs_dbgmsg("vdev_copy_path: vdev %llu: path changed "
+			    "from '%s' to '%s'", (u_longlong_t)dvd->vdev_guid,
+			    dvd->vdev_path, svd->vdev_path);
+			spa_strfree(dvd->vdev_path);
+			dvd->vdev_path = spa_strdup(svd->vdev_path);
 		}
+	} else if (svd->vdev_path != NULL) {
+		dvd->vdev_path = spa_strdup(svd->vdev_path);
+		zfs_dbgmsg("vdev_copy_path: vdev %llu: path set to '%s'",
+		    (u_longlong_t)dvd->vdev_guid, dvd->vdev_path);
+	}
+}
 
-		/*
-		 * If we were able to open and validate a vdev that was
-		 * previously marked permanently unavailable, clear that state
-		 * now.
-		 */
-		if (vd->vdev_not_present)
-			vd->vdev_not_present = 0;
+/*
+ * Recursively copy vdev paths from one vdev to another. Source and destination
+ * vdev trees must have same geometry otherwise return error. Intended to copy
+ * paths from userland config into MOS config.
+ */
+int
+vdev_copy_path_strict(vdev_t *svd, vdev_t *dvd)
+{
+	if ((svd->vdev_ops == &vdev_missing_ops) ||
+	    (svd->vdev_ishole && dvd->vdev_ishole) ||
+	    (dvd->vdev_ops == &vdev_indirect_ops))
+		return (0);
+
+	if (svd->vdev_ops != dvd->vdev_ops) {
+		vdev_dbgmsg(svd, "vdev_copy_path: vdev type mismatch: %s != %s",
+		    svd->vdev_ops->vdev_op_type, dvd->vdev_ops->vdev_op_type);
+		return (SET_ERROR(EINVAL));
+	}
+
+	if (svd->vdev_guid != dvd->vdev_guid) {
+		vdev_dbgmsg(svd, "vdev_copy_path: guids mismatch (%llu != "
+		    "%llu)", (u_longlong_t)svd->vdev_guid,
+		    (u_longlong_t)dvd->vdev_guid);
+		return (SET_ERROR(EINVAL));
 	}
 
+	if (svd->vdev_children != dvd->vdev_children) {
+		vdev_dbgmsg(svd, "vdev_copy_path: children count mismatch: "
+		    "%llu != %llu", (u_longlong_t)svd->vdev_children,
+		    (u_longlong_t)dvd->vdev_children);
+		return (SET_ERROR(EINVAL));
+	}
+
+	for (uint64_t i = 0; i < svd->vdev_children; i++) {
+		int error = vdev_copy_path_strict(svd->vdev_child[i],
+		    dvd->vdev_child[i]);
+		if (error != 0)
+			return (error);
+	}
+
+	if (svd->vdev_ops->vdev_op_leaf)
+		vdev_copy_path_impl(svd, dvd);
+
 	return (0);
 }
 
+static void
+vdev_copy_path_search(vdev_t *stvd, vdev_t *dvd)
+{
+	ASSERT(stvd->vdev_top == stvd);
+	ASSERT3U(stvd->vdev_id, ==, dvd->vdev_top->vdev_id);
+
+	for (uint64_t i = 0; i < dvd->vdev_children; i++) {
+		vdev_copy_path_search(stvd, dvd->vdev_child[i]);
+	}
+
+	if (!dvd->vdev_ops->vdev_op_leaf || !vdev_is_concrete(dvd))
+		return;
+
+	/*
+	 * The idea here is that while a vdev can shift positions within
+	 * a top vdev (when replacing, attaching mirror, etc.) it cannot
+	 * step outside of it.
+	 */
+	vdev_t *vd = vdev_lookup_by_guid(stvd, dvd->vdev_guid);
+
+	if (vd == NULL || vd->vdev_ops != dvd->vdev_ops)
+		return;
+
+	ASSERT(vd->vdev_ops->vdev_op_leaf);
+
+	vdev_copy_path_impl(vd, dvd);
+}
+
+/*
+ * Recursively copy vdev paths from one root vdev to another. Source and
+ * destination vdev trees may differ in geometry. For each destination leaf
+ * vdev, search a vdev with the same guid and top vdev id in the source.
+ * Intended to copy paths from userland config into MOS config.
+ */
+void
+vdev_copy_path_relaxed(vdev_t *srvd, vdev_t *drvd)
+{
+	uint64_t children = MIN(srvd->vdev_children, drvd->vdev_children);
+	ASSERT(srvd->vdev_ops == &vdev_root_ops);
+	ASSERT(drvd->vdev_ops == &vdev_root_ops);
+
+	for (uint64_t i = 0; i < children; i++) {
+		vdev_copy_path_search(srvd->vdev_child[i],
+		    drvd->vdev_child[i]);
+	}
+}
+
 /*
  * Close a virtual device.
  */
@@ -1828,7 +2047,7 @@ vdev_reopen(vdev_t *vd)
 		    !l2arc_vdev_present(vd))
 			l2arc_add_vdev(spa, vd);
 	} else {
-		(void) vdev_validate(vd, B_TRUE);
+		(void) vdev_validate(vd);
 	}
 
 	/*
@@ -3873,6 +4092,19 @@ vdev_set_state(vdev_t *vd, boolean_t isopen, vdev_state_t state, vdev_aux_t aux)
 		vdev_propagate_state(vd->vdev_parent);
 }
 
+boolean_t
+vdev_children_are_offline(vdev_t *vd)
+{
+	ASSERT(!vd->vdev_ops->vdev_op_leaf);
+
+	for (uint64_t i = 0; i < vd->vdev_children; i++) {
+		if (vd->vdev_child[i]->vdev_state != VDEV_STATE_OFFLINE)
+			return (B_FALSE);
+	}
+
+	return (B_TRUE);
+}
+
 /*
  * Check the vdev configuration to ensure that it's capable of supporting
  * a root pool. We do not support partial configuration.
@@ -3909,34 +4141,6 @@ vdev_is_concrete(vdev_t *vd)
 }
 
 /*
- * Load the state from the original vdev tree (ovd) which
- * we've retrieved from the MOS config object. If the original
- * vdev was offline or faulted then we transfer that state to the
- * device in the current vdev tree (nvd).
- */
-void
-vdev_load_log_state(vdev_t *nvd, vdev_t *ovd)
-{
-	ASSERT(nvd->vdev_top->vdev_islog);
-	ASSERT(spa_config_held(nvd->vdev_spa,
-	    SCL_STATE_ALL, RW_WRITER) == SCL_STATE_ALL);
-	ASSERT3U(nvd->vdev_guid, ==, ovd->vdev_guid);
-
-	for (int c = 0; c < nvd->vdev_children; c++)
-		vdev_load_log_state(nvd->vdev_child[c], ovd->vdev_child[c]);
-
-	if (nvd->vdev_ops->vdev_op_leaf) {
-		/*
-		 * Restore the persistent vdev state
-		 */
-		nvd->vdev_offline = ovd->vdev_offline;
-		nvd->vdev_faulted = ovd->vdev_faulted;
-		nvd->vdev_degraded = ovd->vdev_degraded;
-		nvd->vdev_removed = ovd->vdev_removed;
-	}
-}
-
-/*
  * Determine if a log device has valid content.  If the vdev was
  * removed or faulted in the MOS config then we know that
  * the content on the log device has already been written to the pool.
@@ -4051,5 +4255,9 @@ module_param(zfs_checksums_per_second, uint, 0644);
 module_param(zfs_scan_ignore_errors, int, 0644);
 MODULE_PARM_DESC(zfs_scan_ignore_errors,
 	"Ignore errors during resilver/scrub");
+
+module_param(vdev_validate_skip, int, 0644);
+MODULE_PARM_DESC(vdev_validate_skip,
+	"Bypass vdev_validate()");
 /* END CSTYLED */
 #endif