diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c90edf04a9dbba150d6b3c85e8b30ef4086bcea3..9b307034d32c05973b62ceb6237200a28f7772df 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1391,7 +1391,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
goto out;
}
-static int btrfs_init_fs_root(struct btrfs_root *root)
+/*
+ * Initialize subvolume root in-memory structure
+ *
+ * @anon_dev: anonymous device to attach to the root, if zero, allocate new
+ */
+static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
{
int ret;
unsigned int nofs_flag;
@@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
*/
if (is_fstree(root->root_key.objectid) &&
btrfs_root_refs(&root->root_item) > 0) {
- ret = get_anon_bdev(&root->anon_dev);
- if (ret)
- goto fail;
+ if (!anon_dev) {
+ ret = get_anon_bdev(&root->anon_dev);
+ if (ret)
+ goto fail;
+ } else {
+ root->anon_dev = anon_dev;
+ }
}
mutex_lock(&root->objectid_mutex);
@@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
}
-struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
- u64 objectid, bool check_ref)
+/*
+ * Get an in-memory reference of a root structure.
+ *
+ * For essential trees like root/extent tree, we grab it from fs_info directly.
+ * For subvolume trees, we check the cached filesystem roots first. If not
+ * found, then read it from disk and add it to cached fs roots.
+ *
+ * Caller should release the root by calling btrfs_put_root() after the usage.
+ *
+ * NOTE: Reloc and log trees can't be read by this function as they share the
+ * same root objectid.
+ *
+ * @objectid: root id
+ * @anon_dev: preallocated anonymous block device number for new roots,
+ * pass 0 for new allocation.
+ * @check_ref: whether to check root item references, If true, return -ENOENT
+ * for orphan roots
+ */
+static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
+ u64 objectid, dev_t anon_dev,
+ bool check_ref)
{
struct btrfs_root *root;
struct btrfs_path *path;
@@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
+ /* Shouldn't get preallocated anon_dev for cached roots */
+ ASSERT(!anon_dev);
if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
btrfs_put_root(root);
return ERR_PTR(-ENOENT);
@@ -1586,7 +1616,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
goto fail;
}
- ret = btrfs_init_fs_root(root);
+ ret = btrfs_init_fs_root(root, anon_dev);
if (ret)
goto fail;
@@ -1619,6 +1649,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
return ERR_PTR(ret);
}
+/*
+ * Get in-memory reference of a root structure
+ *
+ * @objectid: tree objectid
+ * @check_ref: if set, verify that the tree exists and the item has at least
+ * one reference
+ */
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+ u64 objectid, bool check_ref)
+{
+ return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+}
+
+/*
+ * Get in-memory reference of a root structure, created as new, optionally pass
+ * the anonymous block device id
+ *
+ * @objectid: tree objectid
+ * @anon_dev: if zero, allocate a new anonymous block device or use the
+ * parameter value
+ */
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+ u64 objectid, dev_t anon_dev)
+{
+ return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
+}
+
static int btrfs_congested_fn(void *congested_data, int bdi_bits)
{
struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index bf43245406c4d98b813e4015a6040bc1bbfa7307..00dc39d47ed346449c66e37c8f453f86428bd405 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, bool check_ref);
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+ u64 objectid, dev_t anon_dev);
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4adfdfa28e53f527aa77def08e1b1e4e3b36ea93..ab34179d7cbc8b2d9b1d3fde8591fe01f79d4d3c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir,
struct inode *inode;
int ret;
int err;
+ dev_t anon_dev = 0;
u64 objectid;
u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
u64 index = 0;
@@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir,
if (ret)
goto fail_free;
+ ret = get_anon_bdev(&anon_dev);
+ if (ret < 0)
+ goto fail_free;
+
/*
* Don't create subvolume whose level is not zero. Or qgroup will be
* screwed up since it assumes subvolume qgroup's level to be 0.
@@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir,
goto fail;
key.offset = (u64)-1;
- new_root = btrfs_get_fs_root(fs_info, objectid, true);
+ new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
if (IS_ERR(new_root)) {
+ free_anon_bdev(anon_dev);
ret = PTR_ERR(new_root);
btrfs_abort_transaction(trans, ret);
goto fail;
}
+ /* Freeing will be done in btrfs_put_root() of new_root */
+ anon_dev = 0;
btrfs_record_root_in_trans(trans, new_root);
@@ -735,6 +743,8 @@ static noinline int create_subvol(struct inode *dir,
return ret;
fail_free:
+ if (anon_dev)
+ free_anon_bdev(anon_dev);
kfree(root_item);
return ret;
}
@@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (!pending_snapshot)
return -ENOMEM;
+ ret = get_anon_bdev(&pending_snapshot->anon_dev);
+ if (ret < 0)
+ goto free_pending;
pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
GFP_KERNEL);
pending_snapshot->path = btrfs_alloc_path();
@@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
d_instantiate(dentry, inode);
ret = 0;
+ pending_snapshot->anon_dev = 0;
fail:
+ /* Prevent double freeing of anon_dev */
+ if (ret && pending_snapshot->snap)
+ pending_snapshot->snap->anon_dev = 0;
btrfs_put_root(pending_snapshot->snap);
btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
free_pending:
+ if (pending_snapshot->anon_dev)
+ free_anon_bdev(pending_snapshot->anon_dev);
kfree(pending_snapshot->root_item);
btrfs_free_path(pending_snapshot->path);
kfree(pending_snapshot);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b359d4b17658b12734433eefcd283b9237220e24..3a7c392fbcc90b2c53e321603b8554516c3c67e1 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1630,7 +1630,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
}
key.offset = (u64)-1;
- pending->snap = btrfs_get_fs_root(fs_info, objectid, true);
+ pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
if (IS_ERR(pending->snap)) {
ret = PTR_ERR(pending->snap);
btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 6f65fff6cf50386f1739591c70dee41aaa2d23a1..98f7860af5e99ebc524ea0e704ca90c19e3185b9 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -151,6 +151,8 @@ struct btrfs_pending_snapshot {
struct btrfs_block_rsv block_rsv;
/* extra metadata reservation for relocation */
int error;
+ /* Preallocated anonymous block device number */
+ dev_t anon_dev;
bool readonly;
struct list_head list;
};