Btrfs: introduce subvol uuids and times

This patch introduces uuids for subvolumes. Each
subvolume has it's own uuid. In case it was snapshotted,
it also contains parent_uuid. In case it was received,
it also contains received_uuid.

It also introduces subvolume ctime/otime/stime/rtime. The
first two are comparable to the times found in inodes. otime
is the origin/creation time and ctime is the change time.
stime/rtime are only valid on received subvolumes.
stime is the time of the subvolume when it was
sent. rtime is the time of the subvolume when it was
received.

Additionally to the times, we have a transid for each
time. They are updated at the same place as the times.

btrfs receive uses stransid and rtransid to find out
if a received subvolume changed in the meantime.

If an older kernel mounts a filesystem with the
extented fields, all fields become invalid. The next
mount with a new kernel will detect this and reset the
fields.

Signed-off-by: Alexander Block <[email protected]>
Reviewed-by: David Sterba <[email protected]>
Reviewed-by: Arne Jansen <[email protected]>
Reviewed-by: Jan Schmidt <[email protected]>
Reviewed-by: Alex Lyakas <[email protected]>

Author: Alexander Block

fs/btrfs/check-integrity.c

@@ -1032,6 +1032,7 @@ static int btrfsic_process_metablock(
 			struct btrfs_disk_key *disk_key;
 			u8 type;
 			u32 item_offset;
+			u32 item_size;
 
 			if (disk_item_offset + sizeof(struct btrfs_item) >
 			    sf->block_ctx->len) {
@@ -1047,6 +1048,7 @@ static int btrfsic_process_metablock(
 						     disk_item_offset,
 						     sizeof(struct btrfs_item));
 			item_offset = le32_to_cpu(disk_item.offset);
+			item_size = le32_to_cpu(disk_item.size);
 			disk_key = &disk_item.key;
 			type = disk_key->type;
 
@@ -1057,14 +1059,13 @@ static int btrfsic_process_metablock(
 
 				root_item_offset = item_offset +
 					offsetof(struct btrfs_leaf, items);
-				if (root_item_offset +
-				    sizeof(struct btrfs_root_item) >
+				if (root_item_offset + item_size >
 				    sf->block_ctx->len)
 					goto leaf_item_out_of_bounce_error;
 				btrfsic_read_from_block_data(
 					sf->block_ctx, &root_item,
 					root_item_offset,
-					sizeof(struct btrfs_root_item));
+					item_size);
 				next_bytenr = le64_to_cpu(root_item.bytenr);
 
 				sf->error =

fs/btrfs/ctree.h

@@ -709,6 +709,36 @@ struct btrfs_root_item {
 	struct btrfs_disk_key drop_progress;
 	u8 drop_level;
 	u8 level;
+
+	/*
+	 * The following fields appear after subvol_uuids+subvol_times
+	 * were introduced.
+	 */
+
+	/*
+	 * This generation number is used to test if the new fields are valid
+	 * and up to date while reading the root item. Everytime the root item
+	 * is written out, the "generation" field is copied into this field. If
+	 * anyone ever mounted the fs with an older kernel, we will have
+	 * mismatching generation values here and thus must invalidate the
+	 * new fields. See btrfs_update_root and btrfs_find_last_root for
+	 * details.
+	 * the offset of generation_v2 is also used as the start for the memset
+	 * when invalidating the fields.
+	 */
+	__le64 generation_v2;
+	u8 uuid[BTRFS_UUID_SIZE];
+	u8 parent_uuid[BTRFS_UUID_SIZE];
+	u8 received_uuid[BTRFS_UUID_SIZE];
+	__le64 ctransid; /* updated when an inode changes */
+	__le64 otransid; /* trans when created */
+	__le64 stransid; /* trans when sent. non-zero for received subvol */
+	__le64 rtransid; /* trans when received. non-zero for received subvol */
+	struct btrfs_timespec ctime;
+	struct btrfs_timespec otime;
+	struct btrfs_timespec stime;
+	struct btrfs_timespec rtime;
+	__le64 reserved[8]; /* for future */
 } __attribute__ ((__packed__));
 
 /*
@@ -1416,6 +1446,8 @@ struct btrfs_root {
 	dev_t anon_dev;
 
 	int force_cow;
+
+	spinlock_t root_times_lock;
 };
 
 struct btrfs_ioctl_defrag_range_args {
@@ -2189,6 +2221,16 @@ BTRFS_SETGET_STACK_FUNCS(root_used, struct btrfs_root_item, bytes_used, 64);
 BTRFS_SETGET_STACK_FUNCS(root_limit, struct btrfs_root_item, byte_limit, 64);
 BTRFS_SETGET_STACK_FUNCS(root_last_snapshot, struct btrfs_root_item,
 			 last_snapshot, 64);
+BTRFS_SETGET_STACK_FUNCS(root_generation_v2, struct btrfs_root_item,
+			 generation_v2, 64);
+BTRFS_SETGET_STACK_FUNCS(root_ctransid, struct btrfs_root_item,
+			 ctransid, 64);
+BTRFS_SETGET_STACK_FUNCS(root_otransid, struct btrfs_root_item,
+			 otransid, 64);
+BTRFS_SETGET_STACK_FUNCS(root_stransid, struct btrfs_root_item,
+			 stransid, 64);
+BTRFS_SETGET_STACK_FUNCS(root_rtransid, struct btrfs_root_item,
+			 rtransid, 64);
 
 static inline bool btrfs_root_readonly(struct btrfs_root *root)
 {
@@ -2822,13 +2864,18 @@ int __must_check btrfs_update_root(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct btrfs_key *key,
 				   struct btrfs_root_item *item);
+void btrfs_read_root_item(struct btrfs_root *root,
+			 struct extent_buffer *eb, int slot,
+			 struct btrfs_root_item *item);
 int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct
 			 btrfs_root_item *item, struct btrfs_key *key);
 int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
 int btrfs_find_orphan_roots(struct btrfs_root *tree_root);
 void btrfs_set_root_node(struct btrfs_root_item *item,
 			 struct extent_buffer *node);
 void btrfs_check_and_init_root_item(struct btrfs_root_item *item);
+void btrfs_update_root_times(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root);
 
 /* dir-item.c */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,

fs/btrfs/disk-io.c

@@ -1182,6 +1182,8 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->defrag_running = 0;
 	root->root_key.objectid = objectid;
 	root->anon_dev = 0;
+
+	spin_lock_init(&root->root_times_lock);
 }
 
 static int __must_check find_and_setup_root(struct btrfs_root *tree_root,
@@ -1326,6 +1328,7 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 	u64 generation;
 	u32 blocksize;
 	int ret = 0;
+	int slot;
 
 	root = btrfs_alloc_root(fs_info);
 	if (!root)
@@ -1352,9 +1355,8 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 	ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
 	if (ret == 0) {
 		l = path->nodes[0];
-		read_extent_buffer(l, &root->root_item,
-				btrfs_item_ptr_offset(l, path->slots[0]),
-				sizeof(root->root_item));
+		slot = path->slots[0];
+		btrfs_read_root_item(tree_root, l, slot, &root->root_item);
 		memcpy(&root->root_key, location, sizeof(*location));
 	}
 	btrfs_free_path(path);

fs/btrfs/inode.c

@@ -2734,6 +2734,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 */
 	if (!btrfs_is_free_space_inode(root, inode)
 	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+		btrfs_update_root_times(trans, root);
+
 		ret = btrfs_delayed_update_inode(trans, root, inode);
 		if (!ret)
 			btrfs_set_inode_last_trans(trans, inode);
@@ -4723,6 +4725,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	trace_btrfs_inode_new(inode);
 	btrfs_set_inode_last_trans(trans, inode);
 
+	btrfs_update_root_times(trans, root);
+
 	return inode;
 fail:
 	if (dir)

fs/btrfs/ioctl.c

@@ -41,6 +41,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
+#include <linux/uuid.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -346,11 +347,13 @@ static noinline int create_subvol(struct btrfs_root *root,
 	struct btrfs_root *new_root;
 	struct dentry *parent = dentry->d_parent;
 	struct inode *dir;
+	struct timespec cur_time = CURRENT_TIME;
 	int ret;
 	int err;
 	u64 objectid;
 	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
+	uuid_le new_uuid;
 
 	ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
 	if (ret)
@@ -389,8 +392,9 @@ static noinline int create_subvol(struct btrfs_root *root,
 			    BTRFS_UUID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
+	memset(&root_item, 0, sizeof(root_item));
+
 	inode_item = &root_item.inode;
-	memset(inode_item, 0, sizeof(*inode_item));
 	inode_item->generation = cpu_to_le64(1);
 	inode_item->size = cpu_to_le64(3);
 	inode_item->nlink = cpu_to_le32(1);
@@ -408,8 +412,15 @@ static noinline int create_subvol(struct btrfs_root *root,
 	btrfs_set_root_used(&root_item, leaf->len);
 	btrfs_set_root_last_snapshot(&root_item, 0);
 
-	memset(&root_item.drop_progress, 0, sizeof(root_item.drop_progress));
-	root_item.drop_level = 0;
+	btrfs_set_root_generation_v2(&root_item,
+			btrfs_root_generation(&root_item));
+	uuid_le_gen(&new_uuid);
+	memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
+	root_item.otime.sec = cpu_to_le64(cur_time.tv_sec);
+	root_item.otime.nsec = cpu_to_le64(cur_time.tv_nsec);
+	root_item.ctime = root_item.otime;
+	btrfs_set_root_ctransid(&root_item, trans->transid);
+	btrfs_set_root_otransid(&root_item, trans->transid);
 
 	btrfs_tree_unlock(leaf);
 	free_extent_buffer(leaf);
@@ -3395,6 +3406,87 @@ static long btrfs_ioctl_balance_progress(struct btrfs_root *root,
 	return ret;
 }
 
+static long btrfs_ioctl_set_received_subvol(struct file *file,
+					    void __user *arg)
+{
+	struct btrfs_ioctl_received_subvol_args *sa = NULL;
+	struct inode *inode = fdentry(file)->d_inode;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root_item *root_item = &root->root_item;
+	struct btrfs_trans_handle *trans;
+	struct timespec ct = CURRENT_TIME;
+	int ret = 0;
+
+	ret = mnt_want_write_file(file);
+	if (ret < 0)
+		return ret;
+
+	down_write(&root->fs_info->subvol_sem);
+
+	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (btrfs_root_readonly(root)) {
+		ret = -EROFS;
+		goto out;
+	}
+
+	if (!inode_owner_or_capable(inode)) {
+		ret = -EACCES;
+		goto out;
+	}
+
+	sa = memdup_user(arg, sizeof(*sa));
+	if (IS_ERR(sa)) {
+		ret = PTR_ERR(sa);
+		sa = NULL;
+		goto out;
+	}
+
+	trans = btrfs_start_transaction(root, 1);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		trans = NULL;
+		goto out;
+	}
+
+	sa->rtransid = trans->transid;
+	sa->rtime.sec = ct.tv_sec;
+	sa->rtime.nsec = ct.tv_nsec;
+
+	memcpy(root_item->received_uuid, sa->uuid, BTRFS_UUID_SIZE);
+	btrfs_set_root_stransid(root_item, sa->stransid);
+	btrfs_set_root_rtransid(root_item, sa->rtransid);
+	root_item->stime.sec = cpu_to_le64(sa->stime.sec);
+	root_item->stime.nsec = cpu_to_le32(sa->stime.nsec);
+	root_item->rtime.sec = cpu_to_le64(sa->rtime.sec);
+	root_item->rtime.nsec = cpu_to_le32(sa->rtime.nsec);
+
+	ret = btrfs_update_root(trans, root->fs_info->tree_root,
+				&root->root_key, &root->root_item);
+	if (ret < 0) {
+		btrfs_end_transaction(trans, root);
+		trans = NULL;
+		goto out;
+	} else {
+		ret = btrfs_commit_transaction(trans, root);
+		if (ret < 0)
+			goto out;
+	}
+
+	ret = copy_to_user(arg, sa, sizeof(*sa));
+	if (ret)
+		ret = -EFAULT;
+
+out:
+	kfree(sa);
+	up_write(&root->fs_info->subvol_sem);
+	mnt_drop_write_file(file);
+	return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {
@@ -3477,6 +3569,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_balance_ctl(root, arg);
 	case BTRFS_IOC_BALANCE_PROGRESS:
 		return btrfs_ioctl_balance_progress(root, argp);
+	case BTRFS_IOC_SET_RECEIVED_SUBVOL:
+		return btrfs_ioctl_set_received_subvol(file, argp);
 	case BTRFS_IOC_GET_DEV_STATS:
 		return btrfs_ioctl_get_dev_stats(root, argp, 0);
 	case BTRFS_IOC_GET_AND_RESET_DEV_STATS:

fs/btrfs/ioctl.h

@@ -295,6 +295,21 @@ struct btrfs_ioctl_get_dev_stats {
 	__u64 unused[128 - 2 - BTRFS_DEV_STAT_VALUES_MAX]; /* pad to 1k */
 };
 
+struct btrfs_ioctl_timespec {
+	__u64 sec;
+	__u32 nsec;
+};
+
+struct btrfs_ioctl_received_subvol_args {
+	char	uuid[BTRFS_UUID_SIZE];	/* in */
+	__u64	stransid;		/* in */
+	__u64	rtransid;		/* out */
+	struct btrfs_ioctl_timespec stime; /* in */
+	struct btrfs_ioctl_timespec rtime; /* out */
+	__u64	flags;			/* in */
+	__u64	reserved[16];		/* in */
+};
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \
@@ -359,6 +374,8 @@ struct btrfs_ioctl_get_dev_stats {
 					struct btrfs_ioctl_ino_path_args)
 #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
 					struct btrfs_ioctl_ino_path_args)
+#define BTRFS_IOC_SET_RECEIVED_SUBVOL _IOWR(BTRFS_IOCTL_MAGIC, 37, \
+				struct btrfs_ioctl_received_subvol_args)
 #define BTRFS_IOC_GET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 52, \
 				      struct btrfs_ioctl_get_dev_stats)
 #define BTRFS_IOC_GET_AND_RESET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 53, \