1 files changed, 57 insertions, 81 deletions

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 123ac54af071..6a92ecf9eaa2 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -25,6 +25,14 @@
 #include "compression.h"
 
 /*
+ * Maximum number of references an extent can have in order for us to attempt to
+ * issue clone operations instead of write operations. This currently exists to
+ * avoid hitting limitations of the backreference walking code (taking a lot of
+ * time and using too much memory for extents with large number of references).
+ */
+#define SEND_MAX_EXTENT_REFS	64
+
+/*
  * A fs_path is a helper to dynamically build path names with unknown size.
  * It reallocates the internal buffer on demand.
  * It allows fast adding of path elements on the right side (normal path) and
@@ -1248,12 +1256,21 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
 	 */
 	if (found->root == bctx->sctx->send_root) {
 		/*
-		 * TODO for the moment we don't accept clones from the inode
-		 * that is currently send. We may change this when
-		 * BTRFS_IOC_CLONE_RANGE supports cloning from and to the same
-		 * file.
+		 * If the source inode was not yet processed we can't issue a
+		 * clone operation, as the source extent does not exist yet at
+		 * the destination of the stream.
+		 */
+		if (ino > bctx->cur_objectid)
+			return 0;
+		/*
+		 * We clone from the inode currently being sent as long as the
+		 * source extent is already processed, otherwise we could try
+		 * to clone from an extent that does not exist yet at the
+		 * destination of the stream.
 		 */
-		if (ino >= bctx->cur_objectid)
+		if (ino == bctx->cur_objectid &&
+		    offset + bctx->extent_len >
+		    bctx->sctx->cur_inode_next_write_offset)
 			return 0;
 	}
 
@@ -1302,6 +1319,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 	struct clone_root *cur_clone_root;
 	struct btrfs_key found_key;
 	struct btrfs_path *tmp_path;
+	struct btrfs_extent_item *ei;
 	int compressed;
 	u32 i;
 
@@ -1349,7 +1367,6 @@ static int find_extent_clone(struct send_ctx *sctx,
 	ret = extent_from_logical(fs_info, disk_byte, tmp_path,
 				  &found_key, &flags);
 	up_read(&fs_info->commit_root_sem);
-	btrfs_release_path(tmp_path);
 
 	if (ret < 0)
 		goto out;
@@ -1358,6 +1375,21 @@ static int find_extent_clone(struct send_ctx *sctx,
 		goto out;
 	}
 
+	ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0],
+			    struct btrfs_extent_item);
+	/*
+	 * Backreference walking (iterate_extent_inodes() below) is currently
+	 * too expensive when an extent has a large number of references, both
+	 * in time spent and used memory. So for now just fallback to write
+	 * operations instead of clone operations when an extent has more than
+	 * a certain amount of references.
+	 */
+	if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) {
+		ret = -ENOENT;
+		goto out;
+	}
+	btrfs_release_path(tmp_path);
+
 	/*
 	 * Setup the clone roots.
 	 */
@@ -4779,7 +4811,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
@@ -5554,10 +5586,7 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset)
 {
 	struct btrfs_path *path;
 	struct btrfs_root *root = sctx->send_root;
-	struct btrfs_file_extent_item *fi;
 	struct btrfs_key key;
-	u64 extent_end;
-	u8 type;
 	int ret;
 
 	path = alloc_path_for_send();
@@ -5577,18 +5606,7 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset)
 	if (key.objectid != sctx->cur_ino || key.type != BTRFS_EXTENT_DATA_KEY)
 		goto out;
 
-	fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
-			    struct btrfs_file_extent_item);
-	type = btrfs_file_extent_type(path->nodes[0], fi);
-	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
-		extent_end = ALIGN(key.offset + size,
-				   sctx->send_root->fs_info->sectorsize);
-	} else {
-		extent_end = key.offset +
-			btrfs_file_extent_num_bytes(path->nodes[0], fi);
-	}
-	sctx->cur_inode_last_extent = extent_end;
+	sctx->cur_inode_last_extent = btrfs_file_extent_end(path);
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -5642,16 +5660,7 @@ static int range_is_hole_in_parent(struct send_ctx *sctx,
 			break;
 
 		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, fi) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			u64 size = btrfs_file_extent_ram_bytes(leaf, fi);
-
-			extent_end = ALIGN(key.offset + size,
-					   root->fs_info->sectorsize);
-		} else {
-			extent_end = key.offset +
-				btrfs_file_extent_num_bytes(leaf, fi);
-		}
+		extent_end = btrfs_file_extent_end(path);
 		if (extent_end <= start)
 			goto next;
 		if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) {
@@ -5672,9 +5681,6 @@ out:
 static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			   struct btrfs_key *key)
 {
-	struct btrfs_file_extent_item *fi;
-	u64 extent_end;
-	u8 type;
 	int ret = 0;
 
 	if (sctx->cur_ino != key->objectid || !need_send_hole(sctx))
@@ -5686,18 +5692,6 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			return ret;
 	}
 
-	fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
-			    struct btrfs_file_extent_item);
-	type = btrfs_file_extent_type(path->nodes[0], fi);
-	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
-		extent_end = ALIGN(key->offset + size,
-				   sctx->send_root->fs_info->sectorsize);
-	} else {
-		extent_end = key->offset +
-			btrfs_file_extent_num_bytes(path->nodes[0], fi);
-	}
-
 	if (path->slots[0] == 0 &&
 	    sctx->cur_inode_last_extent < key->offset) {
 		/*
@@ -5723,7 +5717,7 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 		else
 			ret = 0;
 	}
-	sctx->cur_inode_last_extent = extent_end;
+	sctx->cur_inode_last_extent = btrfs_file_extent_end(path);
 	return ret;
 }
 
@@ -7034,7 +7028,6 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	int clone_sources_to_rollback = 0;
 	unsigned alloc_size;
 	int sort_clone_roots = 0;
-	int index;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -7053,12 +7046,6 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	spin_unlock(&send_root->root_item_lock);
 
 	/*
-	 * This is done when we lookup the root, it should already be complete
-	 * by the time we get here.
-	 */
-	WARN_ON(send_root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE);
-
-	/*
 	 * Userspace tools do the checks and warn the user if it's
 	 * not RO.
 	 */
@@ -7078,13 +7065,6 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 		goto out;
 	}
 
-	if (!access_ok(arg->clone_sources,
-			sizeof(*arg->clone_sources) *
-			arg->clone_sources_count)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
 	if (arg->flags & ~BTRFS_SEND_FLAG_MASK) {
 		ret = -EINVAL;
 		goto out;
@@ -7167,11 +7147,8 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 			key.type = BTRFS_ROOT_ITEM_KEY;
 			key.offset = (u64)-1;
 
-			index = srcu_read_lock(&fs_info->subvol_srcu);
-
-			clone_root = btrfs_read_fs_root_no_name(fs_info, &key);
+			clone_root = btrfs_get_fs_root(fs_info, &key, true);
 			if (IS_ERR(clone_root)) {
-				srcu_read_unlock(&fs_info->subvol_srcu, index);
 				ret = PTR_ERR(clone_root);
 				goto out;
 			}
@@ -7179,20 +7156,19 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 			if (!btrfs_root_readonly(clone_root) ||
 			    btrfs_root_dead(clone_root)) {
 				spin_unlock(&clone_root->root_item_lock);
-				srcu_read_unlock(&fs_info->subvol_srcu, index);
+				btrfs_put_root(clone_root);
 				ret = -EPERM;
 				goto out;
 			}
 			if (clone_root->dedupe_in_progress) {
 				dedupe_in_progress_warn(clone_root);
 				spin_unlock(&clone_root->root_item_lock);
-				srcu_read_unlock(&fs_info->subvol_srcu, index);
+				btrfs_put_root(clone_root);
 				ret = -EAGAIN;
 				goto out;
 			}
 			clone_root->send_in_progress++;
 			spin_unlock(&clone_root->root_item_lock);
-			srcu_read_unlock(&fs_info->subvol_srcu, index);
 
 			sctx->clone_roots[i].root = clone_root;
 			clone_sources_to_rollback = i + 1;
@@ -7206,11 +7182,8 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 		key.type = BTRFS_ROOT_ITEM_KEY;
 		key.offset = (u64)-1;
 
-		index = srcu_read_lock(&fs_info->subvol_srcu);
-
-		sctx->parent_root = btrfs_read_fs_root_no_name(fs_info, &key);
+		sctx->parent_root = btrfs_get_fs_root(fs_info, &key, true);
 		if (IS_ERR(sctx->parent_root)) {
-			srcu_read_unlock(&fs_info->subvol_srcu, index);
 			ret = PTR_ERR(sctx->parent_root);
 			goto out;
 		}
@@ -7220,20 +7193,16 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 		if (!btrfs_root_readonly(sctx->parent_root) ||
 				btrfs_root_dead(sctx->parent_root)) {
 			spin_unlock(&sctx->parent_root->root_item_lock);
-			srcu_read_unlock(&fs_info->subvol_srcu, index);
 			ret = -EPERM;
 			goto out;
 		}
 		if (sctx->parent_root->dedupe_in_progress) {
 			dedupe_in_progress_warn(sctx->parent_root);
 			spin_unlock(&sctx->parent_root->root_item_lock);
-			srcu_read_unlock(&fs_info->subvol_srcu, index);
 			ret = -EAGAIN;
 			goto out;
 		}
 		spin_unlock(&sctx->parent_root->root_item_lock);
-
-		srcu_read_unlock(&fs_info->subvol_srcu, index);
 	}
 
 	/*
@@ -7241,7 +7210,8 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	 * is behind the current send position. This is checked while searching
 	 * for possible clone sources.
 	 */
-	sctx->clone_roots[sctx->clone_roots_cnt++].root = sctx->send_root;
+	sctx->clone_roots[sctx->clone_roots_cnt++].root =
+		btrfs_grab_root(sctx->send_root);
 
 	/* We do a bsearch later */
 	sort(sctx->clone_roots, sctx->clone_roots_cnt,
@@ -7326,18 +7296,24 @@ out:
 	}
 
 	if (sort_clone_roots) {
-		for (i = 0; i < sctx->clone_roots_cnt; i++)
+		for (i = 0; i < sctx->clone_roots_cnt; i++) {
 			btrfs_root_dec_send_in_progress(
 					sctx->clone_roots[i].root);
+			btrfs_put_root(sctx->clone_roots[i].root);
+		}
 	} else {
-		for (i = 0; sctx && i < clone_sources_to_rollback; i++)
+		for (i = 0; sctx && i < clone_sources_to_rollback; i++) {
 			btrfs_root_dec_send_in_progress(
 					sctx->clone_roots[i].root);
+			btrfs_put_root(sctx->clone_roots[i].root);
+		}
 
 		btrfs_root_dec_send_in_progress(send_root);
 	}
-	if (sctx && !IS_ERR_OR_NULL(sctx->parent_root))
+	if (sctx && !IS_ERR_OR_NULL(sctx->parent_root)) {
 		btrfs_root_dec_send_in_progress(sctx->parent_root);
+		btrfs_put_root(sctx->parent_root);
+	}
 
 	kvfree(clone_sources_tmp);