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 <ablock84@googlemail.com>
Reviewed-by: David Sterba <dave@jikos.cz>
Reviewed-by: Arne Jansen <sensille@gmx.net>
Reviewed-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
Reviewed-by: Alex Lyakas <alex.bolshoy.btrfs@gmail.com>

1 files changed, 101 insertions, 6 deletions

diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 24fb8ce4e071..6bb465cca20f 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -16,12 +16,55 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/uuid.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "disk-io.h"
 #include "print-tree.h"
 
 /*
+ * Read a root item from the tree. In case we detect a root item smaller then
+ * sizeof(root_item), we know it's an old version of the root structure and
+ * initialize all new fields to zero. The same happens if we detect mismatching
+ * generation numbers as then we know the root was once mounted with an older
+ * kernel that was not aware of the root item structure change.
+ */
+void btrfs_read_root_item(struct btrfs_root *root,
+			 struct extent_buffer *eb, int slot,
+			 struct btrfs_root_item *item)
+{
+	uuid_le uuid;
+	int len;
+	int need_reset = 0;
+
+	len = btrfs_item_size_nr(eb, slot);
+	read_extent_buffer(eb, item, btrfs_item_ptr_offset(eb, slot),
+			min_t(int, len, (int)sizeof(*item)));
+	if (len < sizeof(*item))
+		need_reset = 1;
+	if (!need_reset && btrfs_root_generation(item)
+		!= btrfs_root_generation_v2(item)) {
+		if (btrfs_root_generation_v2(item) != 0) {
+			printk(KERN_WARNING "btrfs: mismatching "
+					"generation and generation_v2 "
+					"found in root item. This root "
+					"was probably mounted with an "
+					"older kernel. Resetting all "
+					"new fields.\n");
+		}
+		need_reset = 1;
+	}
+	if (need_reset) {
+		memset(&item->generation_v2, 0,
+			sizeof(*item) - offsetof(struct btrfs_root_item,
+					generation_v2));
+
+		uuid_le_gen(&uuid);
+		memcpy(item->uuid, uuid.b, BTRFS_UUID_SIZE);
+	}
+}
+
+/*
  * lookup the root with the highest offset for a given objectid.  The key we do
  * find is copied into 'key'.  If we find something return 0, otherwise 1, < 0
  * on error.
@@ -61,10 +104,10 @@ int btrfs_find_last_root(struct btrfs_root *root, u64 objectid,
 		goto out;
 	}
 	if (item)
-		read_extent_buffer(l, item, btrfs_item_ptr_offset(l, slot),
-				   sizeof(*item));
+		btrfs_read_root_item(root, l, slot, item);
 	if (key)
 		memcpy(key, &found_key, sizeof(found_key));
+
 	ret = 0;
 out:
 	btrfs_free_path(path);
@@ -91,16 +134,15 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
 	int ret;
 	int slot;
 	unsigned long ptr;
+	int old_len;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
 	ret = btrfs_search_slot(trans, root, key, path, 0, 1);
-	if (ret < 0) {
-		btrfs_abort_transaction(trans, root, ret);
-		goto out;
-	}
+	if (ret < 0)
+		goto out_abort;
 
 	if (ret != 0) {
 		btrfs_print_leaf(root, path->nodes[0]);
@@ -113,16 +155,56 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
 	l = path->nodes[0];
 	slot = path->slots[0];
 	ptr = btrfs_item_ptr_offset(l, slot);
+	old_len = btrfs_item_size_nr(l, slot);
+
+	/*
+	 * If this is the first time we update the root item which originated
+	 * from an older kernel, we need to enlarge the item size to make room
+	 * for the added fields.
+	 */
+	if (old_len < sizeof(*item)) {
+		btrfs_release_path(path);
+		ret = btrfs_search_slot(trans, root, key, path,
+				-1, 1);
+		if (ret < 0)
+			goto out_abort;
+		ret = btrfs_del_item(trans, root, path);
+		if (ret < 0)
+			goto out_abort;
+		btrfs_release_path(path);
+		ret = btrfs_insert_empty_item(trans, root, path,
+				key, sizeof(*item));
+		if (ret < 0)
+			goto out_abort;
+		l = path->nodes[0];
+		slot = path->slots[0];
+		ptr = btrfs_item_ptr_offset(l, slot);
+	}
+
+	/*
+	 * Update generation_v2 so at the next mount we know the new root
+	 * fields are valid.
+	 */
+	btrfs_set_root_generation_v2(item, btrfs_root_generation(item));
+
 	write_extent_buffer(l, item, ptr, sizeof(*item));
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 out:
 	btrfs_free_path(path);
 	return ret;
+
+out_abort:
+	btrfs_abort_transaction(trans, root, ret);
+	goto out;
 }
 
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      struct btrfs_key *key, struct btrfs_root_item *item)
 {
+	/*
+	 * Make sure generation v1 and v2 match. See update_root for details.
+	 */
+	btrfs_set_root_generation_v2(item, btrfs_root_generation(item));
 	return btrfs_insert_item(trans, root, key, item, sizeof(*item));
 }
 
@@ -454,3 +536,16 @@ void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item)
 		root_item->byte_limit = 0;
 	}
 }
+
+void btrfs_update_root_times(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root)
+{
+	struct btrfs_root_item *item = &root->root_item;
+	struct timespec ct = CURRENT_TIME;
+
+	spin_lock(&root->root_times_lock);
+	item->ctransid = trans->transid;
+	item->ctime.sec = cpu_to_le64(ct.tv_sec);
+	item->ctime.nsec = cpu_to_le64(ct.tv_nsec);
+	spin_unlock(&root->root_times_lock);
+}