On Thu, 16 May 2013 13:15:57 +0800, Liu Bo wrote:
> On Thu, May 16, 2013 at 12:31:11PM +0800, Miao Xie wrote:
>> On thu, 16 May 2013 11:36:46 +0800, Liu Bo wrote:
>>> On Wed, May 15, 2013 at 03:48:20PM +0800, Miao Xie wrote:
>>>> The grab/put funtions will be used in the next patch, which need grab
>>>> the root object and ensure it is not freed. We use reference counter
>>>> instead of the srcu lock is to aovid blocking the memory reclaim task,
>>>> which invokes synchronize_srcu().
>>>>
>>>
>>> I don't think this is necessary, we put 'kfree(root)' because we really
>>> need to free them at the very end time, when there should be no inodes
>>> linking on the root(we should have cleaned all inodes out from it).
>>>
>>> So when we flush delalloc inodes and wait for ordered extents to finish,
>>> the root should be valid, otherwise someone is doing wrong things.
>>>
>>> And even with this grab_fs_root to avoid freeing root, it's just the
>>> root that remains in memory, all its attributes, like root->node,
>>> commit_root, root->inode_tree, are already NULL or empty.
>>
>> Please consider the case:
>> Task1 Task2 Cleaner
>> get the root
>> flush all delalloc inodes
>> drop subvolume
>> iput the last inode
>> move the root into the dead list
>> drop subvolume
>> kfree(root)
>> If Task1 accesses the root now, oops will happen.
>
> Then it's task1's fault, why it is not protected by subvol_srcu section when
> it's possible that someone like task2 sets root's refs to 0?
>
> synchronize_srcu(subvol_srcu) before adding root into dead root list is
> just for this race case, why do we need another?
Please read my changelog.
Miao
>
> thanks,
> liubo
>
>>
>> I introduced there two functions just to protect the access of the root object, not its
>> attributes, so don't worry about the attributes. (Please see the first sentence of the
>> changelog.)
>>
>> Thanks
>> Miao
>>
>>>
>>> thanks,
>>> liubo
>>>
>>>> Signed-off-by: Miao Xie <miaox@xxxxxxxxxxxxxx>
>>>> ---
>>>> fs/btrfs/ctree.h | 1 +
>>>> fs/btrfs/disk-io.c | 5 +++--
>>>> fs/btrfs/disk-io.h | 21 +++++++++++++++++++++
>>>> fs/btrfs/extent-tree.c | 2 +-
>>>> 4 files changed, 26 insertions(+), 3 deletions(-)
>>>>
>>>> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
>>>> index 845b77f..958ce6c 100644
>>>> --- a/fs/btrfs/ctree.h
>>>> +++ b/fs/btrfs/ctree.h
>>>> @@ -1739,6 +1739,7 @@ struct btrfs_root {
>>>> int force_cow;
>>>>
>>>> spinlock_t root_item_lock;
>>>> + atomic_t refs;
>>>> };
>>>>
>>>> struct btrfs_ioctl_defrag_range_args {
>>>> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
>>>> index 42d6ba2..642c861 100644
>>>> --- a/fs/btrfs/disk-io.c
>>>> +++ b/fs/btrfs/disk-io.c
>>>> @@ -1216,6 +1216,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
>>>> atomic_set(&root->log_writers, 0);
>>>> atomic_set(&root->log_batch, 0);
>>>> atomic_set(&root->orphan_inodes, 0);
>>>> + atomic_set(&root->refs, 1);
>>>> root->log_transid = 0;
>>>> root->last_log_commit = 0;
>>>> extent_io_tree_init(&root->dirty_log_pages,
>>>> @@ -2049,7 +2050,7 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
>>>> } else {
>>>> free_extent_buffer(gang[0]->node);
>>>> free_extent_buffer(gang[0]->commit_root);
>>>> - kfree(gang[0]);
>>>> + btrfs_put_fs_root(gang[0]);
>>>> }
>>>> }
>>>>
>>>> @@ -3415,7 +3416,7 @@ static void free_fs_root(struct btrfs_root *root)
>>>> kfree(root->free_ino_ctl);
>>>> kfree(root->free_ino_pinned);
>>>> kfree(root->name);
>>>> - kfree(root);
>>>> + btrfs_put_fs_root(root);
>>>> }
>>>>
>>>> void btrfs_free_fs_root(struct btrfs_root *root)
>>>> diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
>>>> index 534d583..b71acd6e 100644
>>>> --- a/fs/btrfs/disk-io.h
>>>> +++ b/fs/btrfs/disk-io.h
>>>> @@ -76,6 +76,27 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root);
>>>> void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
>>>> struct btrfs_root *root);
>>>> void btrfs_free_fs_root(struct btrfs_root *root);
>>>> +
>>>> +/*
>>>> + * This function is used to grab the root, and avoid it is freed when we
>>>> + * access it. But it doesn't ensure that the tree is not dropped.
>>>> + *
>>>> + * If you want to ensure the whole tree is safe, you should use
>>>> + * fs_info->subvol_srcu
>>>> + */
>>>> +static inline struct btrfs_root *btrfs_grab_fs_root(struct btrfs_root *root)
>>>> +{
>>>> + if (atomic_inc_not_zero(&root->refs))
>>>> + return root;
>>>> + return NULL;
>>>> +}
>>>> +
>>>> +static inline void btrfs_put_fs_root(struct btrfs_root *root)
>>>> +{
>>>> + if (atomic_dec_and_test(&root->refs))
>>>> + kfree(root);
>>>> +}
>>>> +
>>>> void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
>>>> int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
>>>> int atomic);
>>>> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
>>>> index 08e42c8..08f9862 100644
>>>> --- a/fs/btrfs/extent-tree.c
>>>> +++ b/fs/btrfs/extent-tree.c
>>>> @@ -7463,7 +7463,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
>>>> } else {
>>>> free_extent_buffer(root->node);
>>>> free_extent_buffer(root->commit_root);
>>>> - kfree(root);
>>>> + btrfs_put_fs_root(root);
>>>> }
>>>> out_end_trans:
>>>> btrfs_end_transaction_throttle(trans, tree_root);
>>>> --
>>>> 1.8.1.4
>>>>
>>>> --
>>>> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
>>>> the body of a message to majordomo@xxxxxxxxxxxxxxx
>>>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>> --
>>> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
>>> the body of a message to majordomo@xxxxxxxxxxxxxxx
>>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>>
>>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
