1 files changed, 39 insertions, 12 deletions

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 157cc54fc634..89656d799ff6 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -198,9 +198,6 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	entry->file_offset = file_offset;
 	entry->start = start;
 	entry->len = len;
-	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) &&
-	    !(type == BTRFS_ORDERED_NOCOW))
-		entry->csum_bytes_left = disk_len;
 	entry->disk_len = disk_len;
 	entry->bytes_left = len;
 	entry->inode = igrab(inode);
@@ -286,10 +283,6 @@ void btrfs_add_ordered_sum(struct inode *inode,
 	tree = &BTRFS_I(inode)->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	list_add_tail(&sum->list, &entry->list);
-	WARN_ON(entry->csum_bytes_left < sum->len);
-	entry->csum_bytes_left -= sum->len;
-	if (entry->csum_bytes_left == 0)
-		wake_up(&entry->wait);
 	spin_unlock_irq(&tree->lock);
 }
 
@@ -509,7 +502,21 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
 
-		list_add_tail(&ordered->trans_list, &trans->ordered);
+		/*
+		 * If our ordered extent completed it means it updated the
+		 * fs/subvol and csum trees already, so no need to make the
+		 * current transaction's commit wait for it, as we end up
+		 * holding memory unnecessarily and delaying the inode's iput
+		 * until the transaction commit (we schedule an iput for the
+		 * inode when the ordered extent's refcount drops to 0), which
+		 * prevents it from being evictable until the transaction
+		 * commits.
+		 */
+		if (test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags))
+			btrfs_put_ordered_extent(ordered);
+		else
+			list_add_tail(&ordered->trans_list, &trans->ordered);
+
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
 	spin_unlock_irq(&log->log_extents_lock[index]);
@@ -722,6 +729,7 @@ void btrfs_start_ordered_extent(struct inode *inode,
 int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 {
 	int ret = 0;
+	int ret_wb = 0;
 	u64 end;
 	u64 orig_end;
 	struct btrfs_ordered_extent *ordered;
@@ -741,9 +749,14 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 	if (ret)
 		return ret;
 
-	ret = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
-	if (ret)
-		return ret;
+	/*
+	 * If we have a writeback error don't return immediately. Wait first
+	 * for any ordered extents that haven't completed yet. This is to make
+	 * sure no one can dirty the same page ranges and call writepages()
+	 * before the ordered extents complete - to avoid failures (-EEXIST)
+	 * when adding the new ordered extents to the ordered tree.
+	 */
+	ret_wb = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
 
 	end = orig_end;
 	while (1) {
@@ -767,7 +780,7 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 			break;
 		end--;
 	}
-	return ret;
+	return ret_wb ? ret_wb : ret;
 }
 
 /*
@@ -838,6 +851,20 @@ out:
 	return entry;
 }
 
+bool btrfs_have_ordered_extents_in_range(struct inode *inode,
+					 u64 file_offset,
+					 u64 len)
+{
+	struct btrfs_ordered_extent *oe;
+
+	oe = btrfs_lookup_ordered_range(inode, file_offset, len);
+	if (oe) {
+		btrfs_put_ordered_extent(oe);
+		return true;
+	}
+	return false;
+}
+
 /*
  * lookup and return any extent before 'file_offset'.  NULL is returned
  * if none is found