Free objects when receiving full stream as clone

All objects after the last written or freed object are not supposed to
exist after receiving the stream.  Free them accordingly, as if a
freeobjects record for them had been included in the stream.

Reviewed by: Paul Dagnelie <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Fabian Grünbichler <[email protected]>
Closes #5699
Closes #6507
Closes #6616

2 files changed, 52 insertions, 1 deletions

diff --git a/include/sys/dmu_send.h b/include/sys/dmu_send.h
index e9bef8bdd..5cf67a6ab 100644
--- a/include/sys/dmu_send.h
+++ b/include/sys/dmu_send.h
@@ -61,6 +61,7 @@ typedef struct dmu_recv_cookie {
 	boolean_t drc_byteswap;
 	boolean_t drc_force;
 	boolean_t drc_resumable;
+	boolean_t drc_clone;
 	struct avl_tree *drc_guid_to_ds_map;
 	zio_cksum_t drc_cksum;
 	uint64_t drc_newsnapobj;
diff --git a/module/zfs/dmu_send.c b/module/zfs/dmu_send.c
index 0c53ced0f..0fd2d6a5e 100644
--- a/module/zfs/dmu_send.c
+++ b/module/zfs/dmu_send.c
@@ -1807,6 +1807,7 @@ dmu_recv_begin(char *tofs, char *tosnap, dmu_replay_record_t *drr_begin,
 	drc->drc_force = force;
 	drc->drc_resumable = resumable;
 	drc->drc_cred = CRED();
+	drc->drc_clone = (origin != NULL);
 
 	if (drc->drc_drrb->drr_magic == BSWAP_64(DMU_BACKUP_MAGIC)) {
 		drc->drc_byteswap = B_TRUE;
@@ -1867,7 +1868,9 @@ struct receive_writer_arg {
 	/* A map from guid to dataset to help handle dedup'd streams. */
 	avl_tree_t *guid_to_ds_map;
 	boolean_t resumable;
-	uint64_t last_object, last_offset;
+	uint64_t last_object;
+	uint64_t last_offset;
+	uint64_t max_object; /* highest object ID referenced in stream */
 	uint64_t bytes_read; /* bytes read when current record created */
 };
 
@@ -2141,6 +2144,9 @@ receive_object(struct receive_writer_arg *rwa, struct drr_object *drro,
 		return (SET_ERROR(EINVAL));
 	object = err == 0 ? drro->drr_object : DMU_NEW_OBJECT;
 
+	if (drro->drr_object > rwa->max_object)
+		rwa->max_object = drro->drr_object;
+
 	/*
 	 * If we are losing blkptrs or changing the block size this must
 	 * be a new file instance.  We must clear out the previous file
@@ -2241,6 +2247,9 @@ receive_freeobjects(struct receive_writer_arg *rwa,
 		err = dmu_free_long_object(rwa->os, obj);
 		if (err != 0)
 			return (err);
+
+		if (obj > rwa->max_object)
+			rwa->max_object = obj;
 	}
 	if (next_err != ESRCH)
 		return (next_err);
@@ -2271,6 +2280,9 @@ receive_write(struct receive_writer_arg *rwa, struct drr_write *drrw,
 	rwa->last_object = drrw->drr_object;
 	rwa->last_offset = drrw->drr_offset;
 
+	if (rwa->last_object > rwa->max_object)
+		rwa->max_object = rwa->last_object;
+
 	if (dmu_object_info(rwa->os, drrw->drr_object, NULL) != 0)
 		return (SET_ERROR(EINVAL));
 
@@ -2346,6 +2358,9 @@ receive_write_byref(struct receive_writer_arg *rwa,
 		ref_os = rwa->os;
 	}
 
+	if (drrwbr->drr_object > rwa->max_object)
+		rwa->max_object = drrwbr->drr_object;
+
 	err = dmu_buf_hold(ref_os, drrwbr->drr_refobject,
 	    drrwbr->drr_refoffset, FTAG, &dbp, DMU_READ_PREFETCH);
 	if (err != 0)
@@ -2388,6 +2403,9 @@ receive_write_embedded(struct receive_writer_arg *rwa,
 	if (drrwe->drr_compression >= ZIO_COMPRESS_FUNCTIONS)
 		return (EINVAL);
 
+	if (drrwe->drr_object > rwa->max_object)
+		rwa->max_object = drrwe->drr_object;
+
 	tx = dmu_tx_create(rwa->os);
 
 	dmu_tx_hold_write(tx, drrwe->drr_object,
@@ -2424,6 +2442,9 @@ receive_spill(struct receive_writer_arg *rwa, struct drr_spill *drrs,
 	if (dmu_object_info(rwa->os, drrs->drr_object, NULL) != 0)
 		return (SET_ERROR(EINVAL));
 
+	if (drrs->drr_object > rwa->max_object)
+		rwa->max_object = drrs->drr_object;
+
 	VERIFY0(dmu_bonus_hold(rwa->os, drrs->drr_object, FTAG, &db));
 	if ((err = dmu_spill_hold_by_bonus(db, FTAG, &db_spill)) != 0) {
 		dmu_buf_rele(db, FTAG);
@@ -2468,6 +2489,9 @@ receive_free(struct receive_writer_arg *rwa, struct drr_free *drrf)
 	if (dmu_object_info(rwa->os, drrf->drr_object, NULL) != 0)
 		return (SET_ERROR(EINVAL));
 
+	if (drrf->drr_object > rwa->max_object)
+		rwa->max_object = drrf->drr_object;
+
 	err = dmu_free_long_range(rwa->os, drrf->drr_object,
 	    drrf->drr_offset, drrf->drr_length);
 
@@ -3191,6 +3215,32 @@ dmu_recv_stream(dmu_recv_cookie_t *drc, vnode_t *vp, offset_t *voffp,
 	}
 	mutex_exit(&rwa->mutex);
 
+	/*
+	 * If we are receiving a full stream as a clone, all object IDs which
+	 * are greater than the maximum ID referenced in the stream are
+	 * by definition unused and must be freed.
+	 */
+	if (drc->drc_clone && drc->drc_drrb->drr_fromguid == 0) {
+		uint64_t obj = rwa->max_object + 1;
+		int free_err = 0;
+		int next_err = 0;
+
+		while (next_err == 0) {
+			free_err = dmu_free_long_object(rwa->os, obj);
+			if (free_err != 0 && free_err != ENOENT)
+				break;
+
+			next_err = dmu_object_next(rwa->os, &obj, FALSE, 0);
+		}
+
+		if (err == 0) {
+			if (free_err != 0 && free_err != ENOENT)
+				err = free_err;
+			else if (next_err != ESRCH)
+				err = next_err;
+		}
+	}
+
 	cv_destroy(&rwa->cv);
 	mutex_destroy(&rwa->mutex);
 	bqueue_destroy(&rwa->q);