for-5.0-rc4-tag

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAlxWtJgACgkQxWXV+ddt
 WDsDow//ZpnyDwQWvSIfF2UUQOPlcBjbHKuBA7rU0wdybW635QYGR0mqnI+1VnMj
 7ssUkeN6N0a2gQzrUG4Y+zpdzOWv2xQ4jKZ9GMOp9gwyzEFyPkcFXOnmM8UfYtVu
 e3fK65e8BZHmTeu0kGKah4Dt1g0t4fUmhsKR4Pfp5YNJC+zuuGTwUW1K/ZQHXJ+3
 kTHc7WP1lsF7wgaZ+Gl+Kvp8fVrHVdygMVTdRBW8QaBgPLa/KExvK62jW+NmCYhj
 7OIkWdew7e8IXc3Ie5IbOomHAv7IgqqgiO9VO9+n0EpyV4UobUgxrgBKJ+0yc1Ya
 eidbKhMslwUE50y00JVm+vw0gwQHkR+hZDn/mRB6xiIeI8tu/yQIJZ6AhYJXoByR
 cu8+SNO5Z5dOZ1f146ZH8lnkr24tuSnkDUhbRDR5pdb4tAHHej2ALzhbfbwbPEpF
 IverYLw5fOMGeRU/mBsjkVadpSZ4S0HVNU85ERdhLtVLK1PSaY2UkUaA+Ii5y7au
 EYDjaGMflmJ8cAVqgtgedEff2n8OKDnzRZlz4IPLI73MVSITGZkM7PmYmYsLm2Bs
 mDPnmyqR8kzcd1RRtSeZTvqOpAIZG+QUOmD2jiKrchmp54Sz0V/HJWRs3aQybD6Q
 ph0yAcbkvgp/ewe5IFgaI0kcyH7zYdL6GtiI2WUE3/8DObgrgsA=
 =E2PP
 -----END PGP SIGNATURE-----

Merge tag 'for-5.0-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - regression fix: transaction commit can run away due to delayed ref
   waiting heuristic, this is not necessary now because of the proper
   reservation mechanism introduced in 5.0

 - regression fix: potential crash due to use-before-check of an ERR_PTR
   return value

 - fix for transaction abort during transaction commit that needs to
   properly clean up pending block groups

 - fix deadlock during b-tree node/leaf splitting, when this happens on
   some of the fundamental trees, we must prevent new tree block
   allocation to re-enter indirectly via the block group flushing path

 - potential memory leak after errors during mount

* tag 'for-5.0-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: On error always free subvol_name in btrfs_mount
  btrfs: clean up pending block groups when transaction commit aborts
  btrfs: fix potential oops in device_list_add
  btrfs: don't end the transaction for delayed refs in throttle
  Btrfs: fix deadlock when allocating tree block during leaf/node split
This commit is contained in:
Linus Torvalds 2019-02-03 08:48:33 -08:00
commit 312b3a93dd
4 changed files with 71 additions and 38 deletions

View File

@ -968,6 +968,48 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
return 0;
}
static struct extent_buffer *alloc_tree_block_no_bg_flush(
struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 parent_start,
const struct btrfs_disk_key *disk_key,
int level,
u64 hint,
u64 empty_size)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_buffer *ret;
/*
* If we are COWing a node/leaf from the extent, chunk, device or free
* space trees, make sure that we do not finish block group creation of
* pending block groups. We do this to avoid a deadlock.
* COWing can result in allocation of a new chunk, and flushing pending
* block groups (btrfs_create_pending_block_groups()) can be triggered
* when finishing allocation of a new chunk. Creation of a pending block
* group modifies the extent, chunk, device and free space trees,
* therefore we could deadlock with ourselves since we are holding a
* lock on an extent buffer that btrfs_create_pending_block_groups() may
* try to COW later.
* For similar reasons, we also need to delay flushing pending block
* groups when splitting a leaf or node, from one of those trees, since
* we are holding a write lock on it and its parent or when inserting a
* new root node for one of those trees.
*/
if (root == fs_info->extent_root ||
root == fs_info->chunk_root ||
root == fs_info->dev_root ||
root == fs_info->free_space_root)
trans->can_flush_pending_bgs = false;
ret = btrfs_alloc_tree_block(trans, root, parent_start,
root->root_key.objectid, disk_key, level,
hint, empty_size);
trans->can_flush_pending_bgs = true;
return ret;
}
/*
* does the dirty work in cow of a single block. The parent block (if
* supplied) is updated to point to the new cow copy. The new buffer is marked
@ -1015,28 +1057,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
parent_start = parent->start;
/*
* If we are COWing a node/leaf from the extent, chunk, device or free
* space trees, make sure that we do not finish block group creation of
* pending block groups. We do this to avoid a deadlock.
* COWing can result in allocation of a new chunk, and flushing pending
* block groups (btrfs_create_pending_block_groups()) can be triggered
* when finishing allocation of a new chunk. Creation of a pending block
* group modifies the extent, chunk, device and free space trees,
* therefore we could deadlock with ourselves since we are holding a
* lock on an extent buffer that btrfs_create_pending_block_groups() may
* try to COW later.
*/
if (root == fs_info->extent_root ||
root == fs_info->chunk_root ||
root == fs_info->dev_root ||
root == fs_info->free_space_root)
trans->can_flush_pending_bgs = false;
cow = btrfs_alloc_tree_block(trans, root, parent_start,
root->root_key.objectid, &disk_key, level,
search_start, empty_size);
trans->can_flush_pending_bgs = true;
cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
level, search_start, empty_size);
if (IS_ERR(cow))
return PTR_ERR(cow);
@ -3345,8 +3367,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
else
btrfs_node_key(lower, &lower_key, 0);
c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
&lower_key, level, root->node->start, 0);
c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
root->node->start, 0);
if (IS_ERR(c))
return PTR_ERR(c);
@ -3475,8 +3497,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
mid = (c_nritems + 1) / 2;
btrfs_node_key(c, &disk_key, mid);
split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
&disk_key, level, c->start, 0);
split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
c->start, 0);
if (IS_ERR(split))
return PTR_ERR(split);
@ -4260,8 +4282,8 @@ again:
else
btrfs_item_key(l, &disk_key, mid);
right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
&disk_key, 0, l->start, 0);
right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
l->start, 0);
if (IS_ERR(right))
return PTR_ERR(right);

View File

@ -1621,6 +1621,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
flags | SB_RDONLY, device_name, data);
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
kfree(subvol_name);
goto out;
}
@ -1630,12 +1631,14 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
if (error < 0) {
root = ERR_PTR(error);
mntput(mnt_root);
kfree(subvol_name);
goto out;
}
}
}
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
kfree(subvol_name);
goto out;
}

View File

@ -850,14 +850,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
btrfs_trans_release_chunk_metadata(trans);
if (lock && should_end_transaction(trans) &&
READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
spin_lock(&info->trans_lock);
if (cur_trans->state == TRANS_STATE_RUNNING)
cur_trans->state = TRANS_STATE_BLOCKED;
spin_unlock(&info->trans_lock);
}
if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
if (throttle)
return btrfs_commit_transaction(trans);
@ -1879,6 +1871,21 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
kmem_cache_free(btrfs_trans_handle_cachep, trans);
}
/*
* Release reserved delayed ref space of all pending block groups of the
* transaction and remove them from the list
*/
static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_block_group_cache *block_group, *tmp;
list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
btrfs_delayed_refs_rsv_release(fs_info, 1);
list_del_init(&block_group->bg_list);
}
}
static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
{
/*
@ -2270,6 +2277,7 @@ scrub_continue:
btrfs_scrub_continue(fs_info);
cleanup_transaction:
btrfs_trans_release_metadata(trans);
btrfs_cleanup_pending_block_groups(trans);
btrfs_trans_release_chunk_metadata(trans);
trans->block_rsv = NULL;
btrfs_warn(fs_info, "Skipping commit of aborted transaction.");

View File

@ -957,11 +957,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
else
fs_devices = alloc_fs_devices(disk_super->fsid, NULL);
fs_devices->fsid_change = fsid_change_in_progress;
if (IS_ERR(fs_devices))
return ERR_CAST(fs_devices);
fs_devices->fsid_change = fsid_change_in_progress;
mutex_lock(&fs_devices->device_list_mutex);
list_add(&fs_devices->fs_list, &fs_uuids);