Implement Redacted Send/Receive

Redacted send/receive allows users to send subsets of their data to 
a target system. One possible use case for this feature is to not 
transmit sensitive information to a data warehousing, test/dev, or 
analytics environment. Another is to save space by not replicating 
unimportant data within a given dataset, for example in backup tools 
like zrepl.

Redacted send/receive is a three-stage process. First, a clone (or 
clones) is made of the snapshot to be sent to the target. In this 
clone (or clones), all unnecessary or unwanted data is removed or
modified. This clone is then snapshotted to create the "redaction 
snapshot" (or snapshots). Second, the new zfs redact command is used 
to create a redaction bookmark. The redaction bookmark stores the 
list of blocks in a snapshot that were modified by the redaction 
snapshot(s). Finally, the redaction bookmark is passed as a parameter 
to zfs send. When sending to the snapshot that was redacted, the
redaction bookmark is used to filter out blocks that contain sensitive 
or unwanted information, and those blocks are not included in the send 
stream.  When sending from the redaction bookmark, the blocks it 
contains are considered as candidate blocks in addition to those 
blocks in the destination snapshot that were modified since the 
creation_txg of the redaction bookmark.  This step is necessary to 
allow the target to rehydrate data in the case where some blocks are 
accidentally or unnecessarily modified in the redaction snapshot.

The changes to bookmarks to enable fast space estimation involve 
adding deadlists to bookmarks. There is also logic to manage the 
life cycles of these deadlists.

The new size estimation process operates in cases where previously 
an accurate estimate could not be provided. In those cases, a send 
is performed where no data blocks are read, reducing the runtime 
significantly and providing a byte-accurate size estimate.

Reviewed-by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed-by: Matt Ahrens <mahrens@delphix.com>
Reviewed-by: Prashanth Sreenivasa <pks@delphix.com>
Reviewed-by: John Kennedy <john.kennedy@delphix.com>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Chris Williamson <chris.williamson@delphix.com>
Reviewed-by: Pavel Zhakarov <pavel.zakharov@delphix.com>
Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com>
Reviewed-by: Prakash Surya <prakash.surya@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #7958

lib/libzfs/libzfs_dataset.c

@@ -22,7 +22,7 @@
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
  * Copyright (c) 2018, Joyent, Inc. All rights reserved.
- * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2018 by Delphix. All rights reserved.
  * Copyright (c) 2012 DEY Storage Systems, Inc.  All rights reserved.
  * Copyright (c) 2012 Pawel Jakub Dawidek <pawel@dawidek.net>.
  * Copyright (c) 2013 Martin Matuska. All rights reserved.
@@ -597,7 +597,6 @@ zfs_bookmark_exists(const char *path)
 	int err;
 	boolean_t rv;
 
-
 	(void) strlcpy(fsname, path, sizeof (fsname));
 	pound = strchr(fsname, '#');
 	if (pound == NULL)
@@ -2408,6 +2407,10 @@ get_numeric_property(zfs_handle_t *zhp, zfs_prop_t prop, zprop_source_t *src,
 		*val = zhp->zfs_dmustats.dds_inconsistent;
 		break;
 
+	case ZFS_PROP_REDACTED:
+		*val = zhp->zfs_dmustats.dds_redacted;
+		break;
+
 	default:
 		switch (zfs_prop_get_type(prop)) {
 		case PROP_TYPE_NUMBER:
@@ -2620,6 +2623,37 @@ zfs_get_clones_nvl(zfs_handle_t *zhp)
 	return (value);
 }
 
+static int
+get_rsnaps_string(zfs_handle_t *zhp, char *propbuf, size_t proplen)
+{
+	nvlist_t *value;
+	uint64_t *snaps;
+	uint_t nsnaps;
+
+	if (nvlist_lookup_nvlist(zhp->zfs_props,
+	    zfs_prop_to_name(ZFS_PROP_REDACT_SNAPS), &value) != 0)
+		return (-1);
+	if (nvlist_lookup_uint64_array(value, ZPROP_VALUE, &snaps,
+	    &nsnaps) != 0)
+		return (-1);
+	if (nsnaps == 0) {
+		/* There's no redaction snapshots; pass a special value back */
+		(void) snprintf(propbuf, proplen, "none");
+		return (0);
+	}
+	propbuf[0] = '\0';
+	for (int i = 0; i < nsnaps; i++) {
+		char buf[128];
+		if (propbuf[0] != '\0')
+			(void) strlcat(propbuf, ",", proplen);
+		(void) snprintf(buf, sizeof (buf), "%llu",
+		    (u_longlong_t)snaps[i]);
+		(void) strlcat(propbuf, buf, proplen);
+	}
+
+	return (0);
+}
+
 /*
  * Accepts a property and value and checks that the value
  * matches the one found by the channel program. If they are
@@ -2814,6 +2848,11 @@ zfs_prop_get(zfs_handle_t *zhp, zfs_prop_t prop, char *propbuf, size_t proplen,
 		zcp_check(zhp, prop, 0, str);
 		break;
 
+	case ZFS_PROP_REDACT_SNAPS:
+		if (get_rsnaps_string(zhp, propbuf, proplen) != 0)
+			return (-1);
+		break;
+
 	case ZFS_PROP_CLONES:
 		if (get_clones_string(zhp, propbuf, proplen) != 0)
 			return (-1);
@@ -3333,6 +3372,9 @@ zfs_prop_get_userquota(zfs_handle_t *zhp, const char *propname,
 	return (0);
 }
 
+/*
+ * propname must start with "written@" or "written#".
+ */
 int
 zfs_prop_get_written_int(zfs_handle_t *zhp, const char *propname,
     uint64_t *propvalue)
@@ -3343,8 +3385,10 @@ zfs_prop_get_written_int(zfs_handle_t *zhp, const char *propname,
 
 	(void) strlcpy(zc.zc_name, zhp->zfs_name, sizeof (zc.zc_name));
 
-	snapname = strchr(propname, '@') + 1;
-	if (strchr(snapname, '@')) {
+	assert(zfs_prop_written(propname));
+	snapname = propname + strlen("written@");
+	if (strchr(snapname, '@') != NULL || strchr(snapname, '#') != NULL) {
+		/* full snapshot or bookmark name specified */
 		(void) strlcpy(zc.zc_value, snapname, sizeof (zc.zc_value));
 	} else {
 		/* snapname is the short name, append it to zhp's fsname */
@@ -3355,8 +3399,7 @@ zfs_prop_get_written_int(zfs_handle_t *zhp, const char *propname,
 		cp = strchr(zc.zc_value, '@');
 		if (cp != NULL)
 			*cp = '\0';
-		(void) strlcat(zc.zc_value, "@", sizeof (zc.zc_value));
-		(void) strlcat(zc.zc_value, snapname, sizeof (zc.zc_value));
+		(void) strlcat(zc.zc_value, snapname - 1, sizeof (zc.zc_value));
 	}
 
 	err = ioctl(zhp->zfs_hdl->libzfs_fd, ZFS_IOC_SPACE_WRITTEN, &zc);

lib/libzfs/libzfs_iter.c

@@ -21,7 +21,7 @@
 
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2013, 2015 by Delphix. All rights reserved.
+ * Copyright (c) 2013, 2019 by Delphix. All rights reserved.
  * Copyright 2014 Nexenta Systems, Inc.  All rights reserved.
  * Copyright (c) 2019 Datto Inc.
  */
@@ -212,10 +212,12 @@ zfs_iter_bookmarks(zfs_handle_t *zhp, zfs_iter_f func, void *data)
 
 	/* Setup the requested properties nvlist. */
 	props = fnvlist_alloc();
-	fnvlist_add_boolean(props, zfs_prop_to_name(ZFS_PROP_GUID));
-	fnvlist_add_boolean(props, zfs_prop_to_name(ZFS_PROP_CREATETXG));
-	fnvlist_add_boolean(props, zfs_prop_to_name(ZFS_PROP_CREATION));
-	fnvlist_add_boolean(props, zfs_prop_to_name(ZFS_PROP_IVSET_GUID));
+	for (zfs_prop_t p = 0; p < ZFS_NUM_PROPS; p++) {
+		if (zfs_prop_valid_for_type(p, ZFS_TYPE_BOOKMARK, B_FALSE)) {
+			fnvlist_add_boolean(props, zfs_prop_to_name(p));
+		}
+	}
+	fnvlist_add_boolean(props, "redact_complete");
 
 	if ((err = lzc_get_bookmarks(zhp->zfs_name, props, &bmarks)) != 0)
 		goto out;

lib/libzfs/libzfs_mount.c

@@ -22,7 +22,7 @@
 /*
  * Copyright 2015 Nexenta Systems, Inc.  All rights reserved.
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2014, 2017 by Delphix. All rights reserved.
+ * Copyright (c) 2014, 2019 by Delphix. All rights reserved.
  * Copyright 2016 Igor Kozhukhov <ikozhukhov@gmail.com>
  * Copyright 2017 RackTop Systems.
  * Copyright (c) 2018 Datto Inc.
@@ -306,7 +306,7 @@ zfs_is_mounted(zfs_handle_t *zhp, char **where)
  */
 static boolean_t
 zfs_is_mountable(zfs_handle_t *zhp, char *buf, size_t buflen,
-    zprop_source_t *source)
+    zprop_source_t *source, int flags)
 {
 	char sourceloc[MAXNAMELEN];
 	zprop_source_t sourcetype;
@@ -329,6 +329,13 @@ zfs_is_mountable(zfs_handle_t *zhp, char *buf, size_t buflen,
 	    getzoneid() == GLOBAL_ZONEID)
 		return (B_FALSE);
 
+	if (zfs_prop_get_int(zhp, ZFS_PROP_ZONED) &&
+	    getzoneid() == GLOBAL_ZONEID)
+		return (B_FALSE);
+
+	if (zfs_prop_get_int(zhp, ZFS_PROP_REDACTED) && !(flags & MS_FORCE))
+		return (B_FALSE);
+
 	if (source)
 		*source = sourcetype;
 
@@ -495,8 +502,10 @@ zfs_mount(zfs_handle_t *zhp, const char *options, int flags)
 	if (zpool_get_prop_int(zhp->zpool_hdl, ZPOOL_PROP_READONLY, NULL))
 		(void) strlcat(mntopts, "," MNTOPT_RO, sizeof (mntopts));
 
-	if (!zfs_is_mountable(zhp, mountpoint, sizeof (mountpoint), NULL))
+	if (!zfs_is_mountable(zhp, mountpoint, sizeof (mountpoint), NULL,
+	    flags)) {
 		return (0);
+	}
 
 	/*
 	 * Append default mount options which apply to the mount point.
@@ -868,7 +877,7 @@ zfs_share_proto(zfs_handle_t *zhp, zfs_share_proto_t *proto)
 	zprop_source_t sourcetype;
 	int ret;
 
-	if (!zfs_is_mountable(zhp, mountpoint, sizeof (mountpoint), NULL))
+	if (!zfs_is_mountable(zhp, mountpoint, sizeof (mountpoint), NULL, 0))
 		return (0);
 
 	for (curr_proto = proto; *curr_proto != PROTO_END; curr_proto++) {
@@ -1135,8 +1144,7 @@ remove_mountpoint(zfs_handle_t *zhp)
 	char mountpoint[ZFS_MAXPROPLEN];
 	zprop_source_t source;
 
-	if (!zfs_is_mountable(zhp, mountpoint, sizeof (mountpoint),
-	    &source))
+	if (!zfs_is_mountable(zhp, mountpoint, sizeof (mountpoint), &source, 0))
 		return;
 
 	if (source == ZPROP_SRC_DEFAULT ||

lib/libzfs/libzfs_util.c

@@ -468,6 +468,7 @@ zfs_standard_error_fmt(libzfs_handle_t *hdl, int error, const char *fmt, ...)
 	case EREMOTEIO:
 		zfs_verror(hdl, EZFS_ACTIVE_POOL, fmt, ap);
 		break;
+	case ZFS_ERR_UNKNOWN_SEND_STREAM_FEATURE:
 	case ZFS_ERR_IOC_CMD_UNAVAIL:
 		zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "the loaded zfs "
 		    "module does not support this operation. A reboot may "