[PATCH v2 4/5] btrfs: Add a lockdep model for the pending_ordered wait event

[Ioannis Angelakopoulos <iangelak@fb.com>]

In contrast to the num_writers and num_extwriters wait events, the
condition for the pending_ordered wait event is signaled in a different
context from the wait event itself. The condition signaling occurs in
btrfs_remove_ordered_extent() in fs/btrfs/ordered-data.c while the wait
event is implemented in btrfs_commit_transaction() in
fs/btrfs/transaction.c

Thus the thread signaling the condition has to acquire the lockdep map as a
reader at the start of btrfs_remove_ordered_extent() and release it after
it has signaled the condition. In this case some dependencies might be left
out due to the placement of the annotation, but it is better than no
annotation at all.

Signed-off-by: Ioannis Angelakopoulos <iangelak@fb.com>
---
 fs/btrfs/ctree.h        | 1 +
 fs/btrfs/disk-io.c      | 4 ++++
 fs/btrfs/ordered-data.c | 3 +++
 fs/btrfs/transaction.c  | 1 +
 4 files changed, 9 insertions(+)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e6c7cafcd296..661d19ac41d1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1098,6 +1098,7 @@ struct btrfs_fs_info {
 	struct lockdep_map btrfs_trans_num_writers_map;
 	struct lockdep_map btrfs_trans_num_extwriters_map;
 	struct lockdep_map btrfs_state_change_map[4];
+	struct lockdep_map btrfs_trans_pending_ordered_map;
 
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index be5cf86fa992..e9956cbf653f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3052,6 +3052,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	static struct lock_class_key btrfs_trans_unblocked_key;
 	static struct lock_class_key btrfs_trans_sup_committed_key;
 	static struct lock_class_key btrfs_trans_completed_key;
+	static struct lock_class_key btrfs_trans_pending_ordered_key;
 
 	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
 	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
@@ -3087,6 +3088,9 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	lockdep_init_map(&fs_info->btrfs_trans_num_extwriters_map,
 					 "btrfs_trans_num_extwriters",
 					 &btrfs_trans_num_extwriters_key, 0);
+	lockdep_init_map(&fs_info->btrfs_trans_pending_ordered_map,
+					 "btrfs_trans_pending_ordered",
+					 &btrfs_trans_pending_ordered_key, 0);
 
 	lockdep_init_map(&fs_info->btrfs_state_change_map[0],
 					 "btrfs_trans_commit_start",
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 1952ac85222c..2a4cb6db42d1 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -525,6 +525,7 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 	struct rb_node *node;
 	bool pending;
 
+	btrfs_lockdep_acquire(fs_info, btrfs_trans_pending_ordered);
 	/* This is paired with btrfs_add_ordered_extent. */
 	spin_lock(&btrfs_inode->lock);
 	btrfs_mod_outstanding_extents(btrfs_inode, -1);
@@ -580,6 +581,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 		}
 	}
 
+	btrfs_lockdep_release(fs_info, btrfs_trans_pending_ordered);
+
 	spin_lock(&root->ordered_extent_lock);
 	list_del_init(&entry->root_extent_list);
 	root->nr_ordered_extents--;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index e4efaa27ec17..3522e8f3381c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2320,6 +2320,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	 * transaction. Otherwise if this transaction commits before the ordered
 	 * extents complete we lose logged data after a power failure.
 	 */
+	btrfs_might_wait_for_event(fs_info, btrfs_trans_pending_ordered);
 	wait_event(cur_trans->pending_wait,
 		   atomic_read(&cur_trans->pending_ordered) == 0);
 
-- 
2.30.2