btrfs send stream version 2

index c0074d2d7d6d..eccd69387065 100644
@@ -649,7 +649,10 @@ static int send_header(struct send_ctx *sctx)
 	struct btrfs_stream_header hdr;
 
 	strcpy(hdr.magic, BTRFS_SEND_STREAM_MAGIC);
-	hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION);
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2)
+		hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION_2);
+	else
+		hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION_1);
 
 	return write_buf(sctx->send_filp, &hdr, sizeof(hdr),
 					&sctx->send_off);

@@ -6535,6 +6538,8 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	INIT_LIST_HEAD(&sctx->name_cache_list);
 
 	sctx->flags = arg->flags;
+	if (sctx->flags & BTRFS_SEND_FLAG_CALCULATE_DATA_SIZE)
+		sctx->flags |= BTRFS_SEND_FLAG_STREAM_V2;
 
 	sctx->send_filp = fget(arg->send_fd);
 	if (!sctx->send_filp) {

index ead397f7034f..a9b5489d690e 100644
@@ -10,7 +10,8 @@
 #include "ctree.h"
 
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
-#define BTRFS_SEND_STREAM_VERSION 1
+#define BTRFS_SEND_STREAM_VERSION_1 1
+#define BTRFS_SEND_STREAM_VERSION_2 2
 
 #define BTRFS_SEND_BUF_SIZE SZ_64K
 #define BTRFS_SEND_READ_SIZE (48 * SZ_1K)

@@ -77,6 +78,15 @@ enum btrfs_send_cmd {
 
 	BTRFS_SEND_C_END,
 	BTRFS_SEND_C_UPDATE_EXTENT,
+
+	/*
+	 * The following commands were added in stream version 2.
+	 */
+	BTRFS_SEND_C_TOTAL_DATA_SIZE,
+	BTRFS_SEND_C_FALLOCATE,
+	BTRFS_SEND_C_INODE_SET_FLAGS,
+	BTRFS_SEND_C_UTIMES2, /* Same as UTIMES, but it includes OTIME too. */
+
 	__BTRFS_SEND_C_MAX,
 };
 #define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1)

@@ -115,10 +125,19 @@ enum {
 	BTRFS_SEND_A_CLONE_OFFSET,
 	BTRFS_SEND_A_CLONE_LEN,
 
+	/*
+	 * The following attributes were added in stream version 2.
+	 */
+	BTRFS_SEND_A_FALLOCATE_FLAGS,
+	BTRFS_SEND_A_INODE_FLAGS,
+
 	__BTRFS_SEND_A_MAX,
 };
 #define BTRFS_SEND_A_MAX (__BTRFS_SEND_A_MAX - 1)
 
+#define BTRFS_SEND_A_FALLOCATE_FLAG_KEEP_SIZE   (1 << 0)
+#define BTRFS_SEND_A_FALLOCATE_FLAG_PUNCH_HOLE  (1 << 1)
+
 #ifdef __KERNEL__
 long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg);
 #endif

index c8d99b9ca550..ed63176660d2 100644
@@ -711,10 +711,29 @@ struct btrfs_ioctl_received_subvol_args {
  */
 #define BTRFS_SEND_FLAG_OMIT_END_CMD		0x4
 
+/*
+ * Calculate the amount (in bytes) of new file data between the send and
+ * parent snapshots, or in case of a full send, the total amount of file data
+ * we will send.
+ * This corresponds to the sum of the data lengths of each write, clone and
+ * fallocate commands that are sent through the send stream. The receiving end
+ * can use this information to compute progress.
+ *
+ * Added in send stream version 2, and implies producing a version 2 stream.
+ */
+#define BTRFS_SEND_FLAG_CALCULATE_DATA_SIZE	0x8
+
+/*
+ * Used by a client to request a version 2 of the send stream.
+ */
+#define BTRFS_SEND_FLAG_STREAM_V2              0x10
+
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \
-	 BTRFS_SEND_FLAG_OMIT_END_CMD)
+	 BTRFS_SEND_FLAG_OMIT_END_CMD | \
+	 BTRFS_SEND_FLAG_CALCULATE_DATA_SIZE | \
+	 BTRFS_SEND_FLAG_STREAM_V2)
 
 struct btrfs_ioctl_send_args {
 	__s64 send_fd;			/* in */

index eccd69387065..7b184831812b 100644
@@ -66,7 +66,13 @@ struct clone_root {
 #define SEND_CTX_MAX_NAME_CACHE_SIZE 128
 #define SEND_CTX_NAME_CACHE_CLEAN_SIZE (SEND_CTX_MAX_NAME_CACHE_SIZE * 2)
 
+enum btrfs_send_phase {
+	SEND_PHASE_STREAM_CHANGES,
+	SEND_PHASE_COMPUTE_DATA_SIZE,
+};
+
 struct send_ctx {
+	enum btrfs_send_phase phase;
 	struct file *send_filp;
 	loff_t send_off;
 	char *send_buf;

@@ -102,6 +108,7 @@ struct send_ctx {
 	u64 cur_inode_next_write_offset;
 
 	u64 send_progress;
+	u64 total_data_size;
 
 	struct list_head new_refs;
 	struct list_head deleted_refs;

@@ -709,6 +716,8 @@ static int send_rename(struct send_ctx *sctx,
 	struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
 	int ret;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_rename %s -> %s", from->start, to->start);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_RENAME);

@@ -758,6 +767,8 @@ static int send_unlink(struct send_ctx *sctx, struct fs_path *path)
 	struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
 	int ret;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_unlink %s", path->start);
 
 	ret = begin_cmd(sctx, BTRFS_SEND_C_UNLINK);

@@ -780,6 +791,7 @@ static int send_rmdir(struct send_ctx *sctx, struct fs_path *path)
 {
 	struct btrfs_fs_info *fs_info = sctx->send_root->fs_info;
 	int ret;
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
 
 	btrfs_debug(fs_info, "send_rmdir %s", path->start);
 

@@ -2419,6 +2431,8 @@ static int send_truncate(struct send_ctx *sctx, u64 ino, u64 gen, u64 size)
 	int ret = 0;
 	struct fs_path *p;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_truncate %llu size=%llu", ino, size);
 
 	p = fs_path_alloc();

@@ -2449,6 +2463,8 @@ static int send_chmod(struct send_ctx *sctx, u64 ino, u64 gen, u64 mode)
 	int ret = 0;
 	struct fs_path *p;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_chmod %llu mode=%llu", ino, mode);
 
 	p = fs_path_alloc();

@@ -2479,6 +2495,8 @@ static int send_chown(struct send_ctx *sctx, u64 ino, u64 gen, u64 uid, u64 gid)
 	int ret = 0;
 	struct fs_path *p;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_chown %llu uid=%llu, gid=%llu",
 		    ino, uid, gid);
 

@@ -2516,6 +2534,8 @@ static int send_utimes(struct send_ctx *sctx, u64 ino, u64 gen)
 	struct btrfs_key key;
 	int slot;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_utimes %llu", ino);
 
 	p = fs_path_alloc();

@@ -2578,6 +2598,8 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino)
 	u64 mode;
 	u64 rdev;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(fs_info, "send_create_inode %llu", ino);
 
 	p = fs_path_alloc();

@@ -2725,6 +2747,8 @@ static int send_create_inode_if_needed(struct send_ctx *sctx)
 {
 	int ret;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	if (S_ISDIR(sctx->cur_inode_mode)) {
 		ret = did_create_dir(sctx, sctx->cur_ino);
 		if (ret < 0)

@@ -2825,6 +2849,8 @@ static int orphanize_inode(struct send_ctx *sctx, u64 ino, u64 gen,
 	int ret;
 	struct fs_path *orphan;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	orphan = fs_path_alloc();
 	if (!orphan)
 		return -ENOMEM;

@@ -3200,6 +3226,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	bool is_orphan;
 	int ret;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	name = fs_path_alloc();
 	from_path = fs_path_alloc();
 	if (!name || !from_path) {

@@ -3792,6 +3820,9 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	bool orphanized_dir = false;
 	bool orphanized_ancestor = false;
 
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE)
+		return 0;
+
 	btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino);
 
 	/*

@@ -4391,6 +4422,8 @@ static int process_all_refs(struct send_ctx *sctx,
 	iterate_inode_ref_t cb;
 	int pending_move = 0;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	path = alloc_path_for_send();
 	if (!path)
 		return -ENOMEM;

@@ -4708,6 +4741,8 @@ static int process_all_new_xattrs(struct send_ctx *sctx)
 	struct extent_buffer *eb;
 	int slot;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	path = alloc_path_for_send();
 	if (!path)
 		return -ENOMEM;

@@ -4849,6 +4884,8 @@ static int send_write(struct send_ctx *sctx, u64 offset, u32 len)
 	struct fs_path *p;
 	ssize_t num_read = 0;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;

@@ -4884,6 +4921,22 @@ static int send_write(struct send_ctx *sctx, u64 offset, u32 len)
 	return num_read;
 }
 
+static int send_total_data_size(struct send_ctx *sctx, u64 data_size)
+{
+	int ret;
+
+	ret = begin_cmd(sctx, BTRFS_SEND_C_TOTAL_DATA_SIZE);
+	if (ret < 0)
+		goto out;
+
+	TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, data_size);
+	ret = send_cmd(sctx);
+
+tlv_put_failure:
+out:
+	return ret;
+}
+
 /*
  * Send a clone command to user space.
  */

@@ -4895,6 +4948,8 @@ static int send_clone(struct send_ctx *sctx,
 	struct fs_path *p;
 	u64 gen;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	btrfs_debug(sctx->send_root->fs_info,
 		    "send_clone offset=%llu, len=%d, clone_root=%llu, clone_inode=%llu, clone_offset=%llu",
 		    offset, len, clone_root->root->objectid, clone_root->ino,

@@ -4966,6 +5021,8 @@ static int send_update_extent(struct send_ctx *sctx,
 	int ret = 0;
 	struct fs_path *p;
 
+	ASSERT(sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE);
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;

@@ -4997,6 +5054,10 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	u64 len;
 	int ret = 0;
 
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE) {
+		sctx->total_data_size += end - offset;
+		return 0;
+	}
 	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
 		return send_update_extent(sctx, offset, end - offset);
 

@@ -5250,6 +5311,12 @@ static int send_write_or_clone(struct send_ctx *sctx,
 		goto out;
 	}
 
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE) {
+		if (offset < sctx->cur_inode_size)
+			sctx->total_data_size += len;
+		goto out;
+	}
+
 	if (clone_root && IS_ALIGNED(offset + len, bs)) {
 		u64 disk_byte;
 		u64 data_offset;

@@ -5681,10 +5748,12 @@ static int process_extent(struct send_ctx *sctx,
 		}
 	}
 
-	ret = find_extent_clone(sctx, path, key->objectid, key->offset,
-			sctx->cur_inode_size, &found_clone);
-	if (ret != -ENOENT && ret < 0)
-		goto out;
+	if (sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE) {
+		ret = find_extent_clone(sctx, path, key->objectid, key->offset,
+					sctx->cur_inode_size, &found_clone);
+		if (ret != -ENOENT && ret < 0)
+			goto out;
+	}
 
 	ret = send_write_or_clone(sctx, path, key, found_clone);
 	if (ret)

@@ -5815,6 +5884,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	if (!at_end && sctx->cmp_key->objectid == sctx->cur_ino)
 		goto out;
 
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE)
+		goto truncate_inode;
+
 	ret = get_inode_info(sctx->send_root, sctx->cur_ino, NULL, NULL,
 			&left_mode, &left_uid, &left_gid, NULL);
 	if (ret < 0)

@@ -5845,6 +5917,7 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 			need_truncate = 0;
 	}
 
+truncate_inode:
 	if (S_ISREG(sctx->cur_inode_mode)) {
 		if (need_send_hole(sctx)) {
 			if (sctx->cur_inode_last_extent == (u64)-1 ||

@@ -5887,7 +5960,8 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	 * If other directory inodes depended on our current directory
 	 * inode's move/rename, now do their move/rename operations.
 	 */
-	if (!is_waiting_for_move(sctx, sctx->cur_ino)) {
+	if (sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE &&
+	    !is_waiting_for_move(sctx, sctx->cur_ino)) {
 		ret = apply_children_dir_moves(sctx);
 		if (ret)
 			goto out;

@@ -5972,7 +6046,8 @@ static int changed_inode(struct send_ctx *sctx,
 				sctx->left_path->nodes[0], left_ii);
 		sctx->cur_inode_rdev = btrfs_inode_rdev(
 				sctx->left_path->nodes[0], left_ii);
-		if (sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID)
+		if (sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID &&
+		    sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE)
 			ret = send_create_inode_if_needed(sctx);
 	} else if (result == BTRFS_COMPARE_TREE_DELETED) {
 		sctx->cur_inode_gen = right_gen;

@@ -5994,17 +6069,19 @@ 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 = 0;
-			sctx->cur_inode_deleted = 1;
-			sctx->cur_inode_size = btrfs_inode_size(
+			if (sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE) {
+				sctx->cur_inode_gen = right_gen;
+				sctx->cur_inode_new = 0;
+				sctx->cur_inode_deleted = 1;
+				sctx->cur_inode_size = btrfs_inode_size(
 					sctx->right_path->nodes[0], right_ii);
-			sctx->cur_inode_mode = btrfs_inode_mode(
+				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;
+				ret = process_all_refs(sctx,
+						   BTRFS_COMPARE_TREE_DELETED);
+				if (ret < 0)
+					goto out;
+			}
 
 			/*
 			 * Now process the inode as if it was new.

@@ -6018,29 +6095,38 @@ static int changed_inode(struct send_ctx *sctx,
 					sctx->left_path->nodes[0], left_ii);
 			sctx->cur_inode_rdev = btrfs_inode_rdev(
 					sctx->left_path->nodes[0], left_ii);
-			ret = send_create_inode_if_needed(sctx);
-			if (ret < 0)
-				goto out;
-
-			ret = process_all_refs(sctx, BTRFS_COMPARE_TREE_NEW);
-			if (ret < 0)
-				goto out;
+			if (sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE) {
+				ret = send_create_inode_if_needed(sctx);
+				if (ret < 0)
+					goto out;
+				ret = process_all_refs(sctx,
+						       BTRFS_COMPARE_TREE_NEW);
+				if (ret < 0)
+					goto out;
+			}
 			/*
 			 * Advance send_progress now as we did not get into
 			 * process_recorded_refs_if_needed in the new_gen case.
 			 */
 			sctx->send_progress = sctx->cur_ino + 1;
 
-			/*
-			 * Now process all extents and xattrs of the inode as if
-			 * they were all new.
-			 */
-			ret = process_all_extents(sctx);
-			if (ret < 0)
-				goto out;
-			ret = process_all_new_xattrs(sctx);
-			if (ret < 0)
-				goto out;
+			if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE) {
+				if (S_ISREG(sctx->cur_inode_mode))
+					sctx->total_data_size +=
+						sctx->cur_inode_size;
+				/* TODO: maybe account for xattrs one day too */
+			} else {
+				/*
+				 * Now process all extents and xattrs of the
+				 * inode as if they were all new.
+				 */
+				ret = process_all_extents(sctx);
+				if (ret < 0)
+					goto out;
+				ret = process_all_new_xattrs(sctx);
+				if (ret < 0)
+					goto out;
+			}
 		} else {
 			sctx->cur_inode_gen = left_gen;
 			sctx->cur_inode_new = 0;

@@ -6077,6 +6163,9 @@ static int changed_ref(struct send_ctx *sctx,
 		return -EIO;
 	}
 
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE)
+		return 0;
+
 	if (!sctx->cur_inode_new_gen &&
 	    sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID) {
 		if (result == BTRFS_COMPARE_TREE_NEW)

@@ -6105,6 +6194,9 @@ static int changed_xattr(struct send_ctx *sctx,
 		return -EIO;
 	}
 
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE)
+		return 0;
+
 	if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
 		if (result == BTRFS_COMPARE_TREE_NEW)
 			ret = process_new_xattr(sctx);

@@ -6273,6 +6365,8 @@ static int changed_cb(struct btrfs_path *left_path,
 	if (result == BTRFS_COMPARE_TREE_SAME) {
 		if (key->type == BTRFS_INODE_REF_KEY ||
 		    key->type == BTRFS_INODE_EXTREF_KEY) {
+			if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE)
+				return 0;
 			ret = compare_refs(sctx, left_path, key);
 			if (!ret)
 				return 0;

@@ -6369,6 +6463,24 @@ static int full_send_tree(struct send_ctx *sctx)
 	return ret;
 }
 
+static int compute_total_data_size(struct send_ctx *sctx)
+{
+	int ret;
+
+	sctx->total_data_size = 0;
+
+	if (sctx->parent_root) {
+		ret = btrfs_compare_trees(sctx->send_root, sctx->parent_root,
+					  changed_cb, sctx);
+		if (!ret)
+			ret = finish_inode_if_needed(sctx, 1);
+	} else {
+		ret = full_send_tree(sctx);
+	}
+
+	return ret;
+}
+
 static int send_subvol(struct send_ctx *sctx)
 {
 	int ret;

@@ -6383,6 +6495,19 @@ static int send_subvol(struct send_ctx *sctx)
 	if (ret < 0)
 		goto out;
 
+	if (sctx->flags & BTRFS_SEND_FLAG_CALCULATE_DATA_SIZE) {
+		sctx->phase = SEND_PHASE_COMPUTE_DATA_SIZE;
+		ret = compute_total_data_size(sctx);
+		if (ret < 0)
+			goto out;
+		ret = send_total_data_size(sctx, sctx->total_data_size);
+		if (ret < 0)
+			goto out;
+		sctx->phase = SEND_PHASE_STREAM_CHANGES;
+		sctx->cur_ino = 0;
+		sctx->send_progress = 0;
+	}
+
 	if (sctx->parent_root) {
 		ret = btrfs_compare_trees(sctx->send_root, sctx->parent_root,
 				changed_cb, sctx);

index 7b184831812b..328c7a2857ae 100644
@@ -581,6 +581,7 @@ static int tlv_put(struct send_ctx *sctx, u16 attr, const void *data, int len)
 		return tlv_put(sctx, attr, &__tmp, sizeof(__tmp));	\
 	}
 
+TLV_PUT_DEFINE_INT(32)
 TLV_PUT_DEFINE_INT(64)
 
 static int tlv_put_string(struct send_ctx *sctx, u16 attr,

@@ -5047,17 +5048,57 @@ static int send_update_extent(struct send_ctx *sctx,
 	return ret;
 }
 
+static int send_fallocate(struct send_ctx *sctx, u32 flags,
+			  u64 offset, u64 len)
+{
+	struct fs_path *p = NULL;
+	int ret = 0;
+
+	ASSERT(sctx->flags & BTRFS_SEND_FLAG_STREAM_V2);
+
+	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE) {
+		sctx->total_data_size += len;
+		return 0;
+	}
+
+	p = fs_path_alloc();
+	if (!p)
+		return -ENOMEM;
+	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
+	if (ret < 0)
+		goto out;
+
+	ret = begin_cmd(sctx, BTRFS_SEND_C_FALLOCATE);
+	if (ret < 0)
+		goto out;
+	TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
+	TLV_PUT_U32(sctx, BTRFS_SEND_A_FALLOCATE_FLAGS, flags);
+	TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
+	TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, len);
+	ret = send_cmd(sctx);
+
+tlv_put_failure:
+out:
+	fs_path_free(p);
+	return ret;
+}
+
+
 static int send_hole(struct send_ctx *sctx, u64 end)
 {
 	struct fs_path *p = NULL;
 	u64 offset = sctx->cur_inode_last_extent;
-	u64 len;
+	u64 len = end - offset;
 	int ret = 0;
 
 	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE) {
-		sctx->total_data_size += end - offset;
+		sctx->total_data_size += len;
 		return 0;
 	}
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2)
+		return send_fallocate(sctx, BTRFS_SEND_PUNCH_HOLE_FALLOC_FLAGS,
+				      offset, len);
+
 	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
 		return send_update_extent(sctx, offset, end - offset);
 

@@ -5304,7 +5345,8 @@ static int send_write_or_clone(struct send_ctx *sctx,
 		ret = 0;
 		goto out;
 	}
-	if (offset + len > sctx->cur_inode_size)
+	if (offset < sctx->cur_inode_size &&
+	    offset + len > sctx->cur_inode_size)
 		len = sctx->cur_inode_size - offset;
 	if (len == 0) {
 		ret = 0;

@@ -5325,6 +5367,12 @@ static int send_write_or_clone(struct send_ctx *sctx,
 		data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
 		ret = clone_range(sctx, clone_root, disk_byte, data_offset,
 				  offset, len);
+	} else if (btrfs_file_extent_disk_bytenr(path->nodes[0], ei) == 0 &&
+		 type != BTRFS_FILE_EXTENT_INLINE &&
+		 (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) &&
+		 offset < sctx->cur_inode_size) {
+		ret = send_fallocate(sctx, BTRFS_SEND_PUNCH_HOLE_FALLOC_FLAGS,
+				     offset, len);
 	} else {
 		ret = send_extent_data(sctx, offset, len);
 	}

index a9b5489d690e..a5830d216ac1 100644
@@ -138,6 +138,10 @@ enum {
 #define BTRFS_SEND_A_FALLOCATE_FLAG_KEEP_SIZE   (1 << 0)
 #define BTRFS_SEND_A_FALLOCATE_FLAG_PUNCH_HOLE  (1 << 1)
 
+#define BTRFS_SEND_PUNCH_HOLE_FALLOC_FLAGS        \
+	(BTRFS_SEND_A_FALLOCATE_FLAG_KEEP_SIZE |  \
+	 BTRFS_SEND_A_FALLOCATE_FLAG_PUNCH_HOLE)
+
 #ifdef __KERNEL__
 long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg);
 #endif

index 328c7a2857ae..c8ea1ccaa3d8 100644
@@ -98,9 +98,10 @@ struct send_ctx {
 	 */
 	u64 cur_ino;
 	u64 cur_inode_gen;
-	int cur_inode_new;
-	int cur_inode_new_gen;
-	int cur_inode_deleted;
+	u8 cur_inode_new:1;
+	u8 cur_inode_new_gen:1;
+	u8 cur_inode_skip_truncate:1;
+	u8 cur_inode_deleted:1;
 	u64 cur_inode_size;
 	u64 cur_inode_mode;
 	u64 cur_inode_rdev;

@@ -5313,6 +5314,19 @@ static int clone_range(struct send_ctx *sctx,
 	return ret;
 }
 
+static int truncate_before_falloc(struct send_ctx *sctx)
+{
+	int ret = 0;
+
+	if (!sctx->cur_inode_skip_truncate) {
+		ret = send_truncate(sctx, sctx->cur_ino,
+				    sctx->cur_inode_gen,
+				    sctx->cur_inode_size);
+		sctx->cur_inode_skip_truncate = 1;
+	}
+	return ret;
+}
+
 static int send_write_or_clone(struct send_ctx *sctx,
 			       struct btrfs_path *path,
 			       struct btrfs_key *key,

@@ -5354,8 +5368,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 	}
 
 	if (sctx->phase == SEND_PHASE_COMPUTE_DATA_SIZE) {
-		if (offset < sctx->cur_inode_size)
-			sctx->total_data_size += len;
+		sctx->total_data_size += len;
 		goto out;
 	}
 

@@ -5373,6 +5386,21 @@ static int send_write_or_clone(struct send_ctx *sctx,
 		 offset < sctx->cur_inode_size) {
 		ret = send_fallocate(sctx, BTRFS_SEND_PUNCH_HOLE_FALLOC_FLAGS,
 				     offset, len);
+	} else if (type == BTRFS_FILE_EXTENT_PREALLOC &&
+		   (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2)) {
+		u32 flags = 0;
+		if (offset < sctx->cur_inode_size) {
+			ret = send_fallocate(sctx,
+					     BTRFS_SEND_PUNCH_HOLE_FALLOC_FLAGS,
+					     offset, len);
+		} else {
+			flags |= BTRFS_SEND_A_FALLOCATE_FLAG_KEEP_SIZE;
+			ret = truncate_before_falloc(sctx);
+		}
+		if (ret)
+			goto out;
+		ret = send_fallocate(sctx, flags, offset, len);
+
 	} else {
 		ret = send_extent_data(sctx, offset, len);
 	}

@@ -5775,19 +5803,24 @@ static int process_extent(struct send_ctx *sctx,
 		ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				    struct btrfs_file_extent_item);
 		type = btrfs_file_extent_type(path->nodes[0], ei);
-		if (type == BTRFS_FILE_EXTENT_PREALLOC ||
-		    type == BTRFS_FILE_EXTENT_REG) {
-			/*
-			 * The send spec does not have a prealloc command yet,
-			 * so just leave a hole for prealloc'ed extents until
-			 * we have enough commands queued up to justify rev'ing
-			 * the send spec.
-			 */
-			if (type == BTRFS_FILE_EXTENT_PREALLOC) {
-				ret = 0;
-				goto out;
+		if (type == BTRFS_FILE_EXTENT_PREALLOC &&
+		    (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2)) {
+			u64 len;
+			u32 flags = 0;
+
+			len = btrfs_file_extent_num_bytes(path->nodes[0], ei);
+			if (key->offset >= sctx->cur_inode_size) {
+				flags |= BTRFS_SEND_A_FALLOCATE_FLAG_KEEP_SIZE;
+				ret = truncate_before_falloc(sctx);
+				if (ret)
+					goto out;
 			}
-
+			ret = send_fallocate(sctx, flags, key->offset, len);
+			goto out;
+		} else if (type == BTRFS_FILE_EXTENT_PREALLOC) {
+			ret = 0;
+			goto out;
+		} else if (type == BTRFS_FILE_EXTENT_REG) {
 			/* Have a hole, just skip it. */
 			if (btrfs_file_extent_disk_bytenr(path->nodes[0], ei) == 0) {
 				ret = 0;

@@ -5982,7 +6015,8 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 					goto out;
 			}
 		}
-		if (need_truncate) {
+		if (need_truncate && !sctx->cur_inode_skip_truncate
+		    && sctx->phase != SEND_PHASE_COMPUTE_DATA_SIZE) {
 			ret = send_truncate(sctx, sctx->cur_ino,
 					    sctx->cur_inode_gen,
 					    sctx->cur_inode_size);

@@ -6044,6 +6078,7 @@ static int changed_inode(struct send_ctx *sctx,
 	sctx->cur_inode_new_gen = 0;
 	sctx->cur_inode_last_extent = (u64)-1;
 	sctx->cur_inode_next_write_offset = 0;
+	sctx->cur_inode_skip_truncate = 0;
 
 	/*
 	 * Set send_progress to current inode. This will tell all get_cur_xxx

index a5830d216ac1..2f5e25e03def 100644
@@ -12,6 +12,7 @@
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 #define BTRFS_SEND_STREAM_VERSION_1 1
 #define BTRFS_SEND_STREAM_VERSION_2 2
+#define BTRFS_SEND_STREAM_VERSION_LATEST BTRFS_SEND_STREAM_VERSION_2
 
 #define BTRFS_SEND_BUF_SIZE SZ_64K
 #define BTRFS_SEND_READ_SIZE (48 * SZ_1K)

index 4848a4318fb5..3c82cba91ff6 100644
@@ -18,6 +18,7 @@
 #include "transaction.h"
 #include "sysfs.h"
 #include "volumes.h"
+#include "send.h"
 
 static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj);
 static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj);

@@ -884,6 +885,28 @@ static int btrfs_init_debugfs(void)
 	return 0;
 }
 
+static ssize_t send_stream_version_show(struct kobject *kobj,
+					struct kobj_attribute *a,
+					char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			BTRFS_SEND_STREAM_VERSION_LATEST);
+}
+
+BTRFS_ATTR(, stream_version, send_stream_version_show);
+
+static struct attribute *btrfs_send_attrs[] = {
+	BTRFS_ATTR_PTR(, stream_version),
+	NULL
+};
+
+static const struct attribute_group btrfs_send_attr_group = {
+	.name = "send",
+	.attrs = btrfs_send_attrs,
+};
+
+
+
 int __init btrfs_init_sysfs(void)
 {
 	int ret;

@@ -900,8 +923,13 @@ int __init btrfs_init_sysfs(void)
 	ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
 	if (ret)
 		goto out2;
+	ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_send_attr_group);
+	if (ret)
+		goto out3;
 
 	return 0;
+out3:
+	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
 out2:
 	debugfs_remove_recursive(btrfs_debugfs_root_dentry);
 out1:

@@ -913,6 +941,7 @@ int __init btrfs_init_sysfs(void)
 void __cold btrfs_exit_sysfs(void)
 {
 	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
+	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_send_attr_group);
 	kset_unregister(btrfs_kset);
 	debugfs_remove_recursive(btrfs_debugfs_root_dentry);
 }

index 2771cc56a622..0a2359144b18 100644
@@ -1461,6 +1461,8 @@ struct btrfs_map_token {
 	unsigned long offset;
 };
 
+unsigned int btrfs_flags_to_ioctl(unsigned int flags);
+
 #define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
 				((bytes) >> (fs_info)->sb->s_blocksize_bits)
 

index 632e26d6f7ce..36ce1e589f9e 100644
@@ -106,7 +106,7 @@ static unsigned int btrfs_mask_flags(umode_t mode, unsigned int flags)
 /*
  * Export inode flags to the format expected by the FS_IOC_GETFLAGS ioctl.
  */
-static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
+unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 {
 	unsigned int iflags = 0;
 

382 lines not on this page · raw message

index 2f5e25e03def..664272ced1af 100644
@@ -85,8 +85,8 @@ enum btrfs_send_cmd {
 	 */
 	BTRFS_SEND_C_TOTAL_DATA_SIZE,
 	BTRFS_SEND_C_FALLOCATE,
-	BTRFS_SEND_C_INODE_SET_FLAGS,
 	BTRFS_SEND_C_UTIMES2, /* Same as UTIMES, but it includes OTIME too. */
+	BTRFS_SEND_C_CHATTR,
 
 	__BTRFS_SEND_C_MAX,
 };

@@ -130,7 +130,7 @@ enum {
 	 * The following attributes were added in stream version 2.
 	 */
 	BTRFS_SEND_A_FALLOCATE_FLAGS,
-	BTRFS_SEND_A_INODE_FLAGS,
+	BTRFS_SEND_A_CHATTR,
 
 	__BTRFS_SEND_A_MAX,
 };