1 files changed, 40 insertions, 13 deletions

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4ef4167072b8..1c4b693ee4a3 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -348,6 +348,7 @@ static bool proto_cmd_ok(const struct send_ctx *sctx, int cmd)
 	switch (sctx->proto) {
 	case 1:	 return cmd <= BTRFS_SEND_C_MAX_V1;
 	case 2:	 return cmd <= BTRFS_SEND_C_MAX_V2;
+	case 3:	 return cmd <= BTRFS_SEND_C_MAX_V3;
 	default: return false;
 	}
 }
@@ -5701,6 +5702,7 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path,
 		u64 ext_len;
 		u64 clone_len;
 		u64 clone_data_offset;
+		bool crossed_src_i_size = false;
 
 		if (slot >= btrfs_header_nritems(leaf)) {
 			ret = btrfs_next_leaf(clone_root->root, path);
@@ -5758,8 +5760,10 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path,
 		if (key.offset >= clone_src_i_size)
 			break;
 
-		if (key.offset + ext_len > clone_src_i_size)
+		if (key.offset + ext_len > clone_src_i_size) {
 			ext_len = clone_src_i_size - key.offset;
+			crossed_src_i_size = true;
+		}
 
 		clone_data_offset = btrfs_file_extent_offset(leaf, ei);
 		if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte) {
@@ -5820,6 +5824,25 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path,
 				ret = send_clone(sctx, offset, clone_len,
 						 clone_root);
 			}
+		} else if (crossed_src_i_size && clone_len < len) {
+			/*
+			 * If we are at i_size of the clone source inode and we
+			 * can not clone from it, terminate the loop. This is
+			 * to avoid sending two write operations, one with a
+			 * length matching clone_len and the final one after
+			 * this loop with a length of len - clone_len.
+			 *
+			 * When using encoded writes (BTRFS_SEND_FLAG_COMPRESSED
+			 * was passed to the send ioctl), this helps avoid
+			 * sending an encoded write for an offset that is not
+			 * sector size aligned, in case the i_size of the source
+			 * inode is not sector size aligned. That will make the
+			 * receiver fallback to decompression of the data and
+			 * writing it using regular buffered IO, therefore while
+			 * not incorrect, it's not optimal due decompression and
+			 * possible re-compression at the receiver.
+			 */
+			break;
 		} else {
 			ret = send_extent_data(sctx, dst_path, offset,
 					       clone_len);
@@ -6469,7 +6492,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 		if (ret < 0)
 			goto out;
 	}
-	if (sctx->cur_inode_needs_verity) {
+
+	if (proto_cmd_ok(sctx, BTRFS_SEND_C_ENABLE_VERITY)
+	    && sctx->cur_inode_needs_verity) {
 		ret = process_verity(sctx);
 		if (ret < 0)
 			goto out;
@@ -6665,17 +6690,19 @@ static int changed_inode(struct send_ctx *sctx,
 			/*
 			 * First, process the inode as if it was deleted.
 			 */
-			sctx->cur_inode_gen = right_gen;
-			sctx->cur_inode_new = false;
-			sctx->cur_inode_deleted = true;
-			sctx->cur_inode_size = btrfs_inode_size(
-					sctx->right_path->nodes[0], right_ii);
-			sctx->cur_inode_mode = btrfs_inode_mode(
-					sctx->right_path->nodes[0], right_ii);
-			ret = process_all_refs(sctx,
-					BTRFS_COMPARE_TREE_DELETED);
-			if (ret < 0)
-				goto out;
+			if (old_nlinks > 0) {
+				sctx->cur_inode_gen = right_gen;
+				sctx->cur_inode_new = false;
+				sctx->cur_inode_deleted = true;
+				sctx->cur_inode_size = btrfs_inode_size(
+						sctx->right_path->nodes[0], right_ii);
+				sctx->cur_inode_mode = btrfs_inode_mode(
+						sctx->right_path->nodes[0], right_ii);
+				ret = process_all_refs(sctx,
+						BTRFS_COMPARE_TREE_DELETED);
+				if (ret < 0)
+					goto out;
+			}
 
 			/*
 			 * Now process the inode as if it was new.