Merge tag 'for-5.0-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A handful of fixes (some of them in testing for a long time):

   - fix some test failures regarding cleanup after transaction abort

   - revert of a patch that could cause a deadlock

   - delayed iput fixes, that can help in ENOSPC situation when there's
     low space and a lot data to write"

* tag 'for-5.0-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: wakeup cleaner thread when adding delayed iput
  btrfs: run delayed iputs before committing
  btrfs: wait on ordered extents on abort cleanup
  btrfs: handle delayed ref head accounting cleanup in abort
  Revert "btrfs: balance dirty metadata pages in btrfs_finish_ordered_io"

fs/btrfs/ctree.h

@@ -35,6 +35,7 @@
 struct btrfs_trans_handle;
 struct btrfs_transaction;
 struct btrfs_pending_snapshot;
+struct btrfs_delayed_ref_root;
 extern struct kmem_cache *btrfs_trans_handle_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
@@ -786,6 +787,9 @@ enum {
 	 * main phase. The fs_info::balance_ctl is initialized.
 	 */
 	BTRFS_FS_BALANCE_RUNNING,
+
+	/* Indicate that the cleaner thread is awake and doing something. */
+	BTRFS_FS_CLEANER_RUNNING,
 };
 
 struct btrfs_fs_info {
@@ -2661,6 +2665,9 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info,
 				 unsigned long count, u64 transid, int wait);
+void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
+				  struct btrfs_delayed_ref_root *delayed_refs,
+				  struct btrfs_delayed_ref_head *head);
 int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,

fs/btrfs/disk-io.c

@@ -1682,6 +1682,8 @@ static int cleaner_kthread(void *arg)
 	while (1) {
 		again = 0;
 
+		set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
+
 		/* Make the cleaner go to sleep early. */
 		if (btrfs_need_cleaner_sleep(fs_info))
 			goto sleep;
@@ -1728,6 +1730,7 @@ static int cleaner_kthread(void *arg)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 sleep:
+		clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
 		if (kthread_should_park())
 			kthread_parkme();
 		if (kthread_should_stop())
@@ -4201,6 +4204,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
 		spin_lock(&fs_info->ordered_root_lock);
 	}
 	spin_unlock(&fs_info->ordered_root_lock);
+
+	/*
+	 * We need this here because if we've been flipped read-only we won't
+	 * get sync() from the umount, so we need to make sure any ordered
+	 * extents that haven't had their dirty pages IO start writeout yet
+	 * actually get run and error out properly.
+	 */
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 }
 
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
@@ -4265,6 +4276,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 		if (pin_bytes)
 			btrfs_pin_extent(fs_info, head->bytenr,
 					 head->num_bytes, 1);
+		btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head);
 		btrfs_put_delayed_ref_head(head);
 		cond_resched();
 		spin_lock(&delayed_refs->lock);

fs/btrfs/extent-tree.c

@@ -2456,12 +2456,10 @@ static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans,
 	return ret ? ret : 1;
 }
 
-static void cleanup_ref_head_accounting(struct btrfs_trans_handle *trans,
+void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
+				  struct btrfs_delayed_ref_root *delayed_refs,
 				  struct btrfs_delayed_ref_head *head)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_delayed_ref_root *delayed_refs =
-		&trans->transaction->delayed_refs;
 	int nr_items = 1;	/* Dropping this ref head update. */
 
 	if (head->total_ref_mod < 0) {
@@ -2544,7 +2542,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	cleanup_ref_head_accounting(trans, head);
+	btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head);
 
 	trace_run_delayed_ref_head(fs_info, head, 0);
 	btrfs_delayed_ref_unlock(head);
@@ -4954,6 +4952,15 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 			ret = 0;
 		break;
 	case COMMIT_TRANS:
+		/*
+		 * If we have pending delayed iputs then we could free up a
+		 * bunch of pinned space, so make sure we run the iputs before
+		 * we do our pinned bytes check below.
+		 */
+		mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
+		btrfs_run_delayed_iputs(fs_info);
+		mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+
 		ret = may_commit_transaction(fs_info, space_info);
 		break;
 	default:
@@ -7188,7 +7195,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 	if (head->must_insert_reserved)
 		ret = 1;
 
-	cleanup_ref_head_accounting(trans, head);
+	btrfs_cleanup_ref_head_accounting(trans->fs_info, delayed_refs, head);
 	mutex_unlock(&head->mutex);
 	btrfs_put_delayed_ref_head(head);
 	return ret;

fs/btrfs/inode.c

@@ -3129,9 +3129,6 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	/* once for the tree */
 	btrfs_put_ordered_extent(ordered_extent);
 
-	/* Try to release some metadata so we don't get an OOM but don't wait */
-	btrfs_btree_balance_dirty_nodelay(fs_info);
-
 	return ret;
 }
 
@@ -3254,6 +3251,8 @@ void btrfs_add_delayed_iput(struct inode *inode)
 	ASSERT(list_empty(&binode->delayed_iput));
 	list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
 	spin_unlock(&fs_info->delayed_iput_lock);
+	if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags))
+		wake_up_process(fs_info->cleaner_kthread);
 }
 
 void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)