From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 21 Nov 2018 14:03:11 -0500
Subject: btrfs: loop in inode_rsv_refill
Git-commit: 5df1136363cabc4d3f92fc91e3f92bd6a5eebd27
Patch-mainline: v5.1-rc1
References: bsc#1165949

With severe fragmentation we can end up with our inode rsv size being
huge during writeout, which would cause us to need to make very large
metadata reservations.

However we may not actually need that much once writeout is complete,
because of the over-reservation for the worst case.

So instead try to make our reservation, and if we couldn't make it
re-calculate our new reservation size and try again.  If our reservation
size doesn't change between tries then we know we are actually out of
space and can error. Flushing that could have been running in parallel
did not make any space.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
[ rename to calc_refill_bytes, update comment and changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
Acked-by: Nikolay Borisov <nborisov@suse.com>
---
 fs/btrfs/extent-tree.c |   63 ++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 47 insertions(+), 16 deletions(-)

--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5922,6 +5922,21 @@ int btrfs_block_rsv_refill(struct btrfs_
 	return ret;
 }
 
+static void calc_refill_bytes(struct btrfs_block_rsv *block_rsv,
+				u64 *metadata_bytes, u64 *qgroup_bytes)
+{
+	*metadata_bytes = 0;
+	*qgroup_bytes = 0;
+
+	spin_lock(&block_rsv->lock);
+	if (block_rsv->reserved < block_rsv->size)
+		*metadata_bytes = block_rsv->size - block_rsv->reserved;
+	if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
+		*qgroup_bytes = block_rsv->qgroup_rsv_size -
+			block_rsv->qgroup_rsv_reserved;
+	spin_unlock(&block_rsv->lock);
+}
+
 /**
  * btrfs_inode_rsv_refill - refill the inode block rsv.
  * @inode - the inode we are refilling.
@@ -5937,25 +5952,42 @@ int btrfs_inode_rsv_refill(struct btrfs_
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
-	u64 num_bytes = 0;
-	u64 qgroup_num_bytes = 0;
+	u64 num_bytes, last = 0;
+	u64 qgroup_num_bytes;
 	int ret = -ENOSPC;
 
-	spin_lock(&block_rsv->lock);
-	if (block_rsv->reserved < block_rsv->size)
-		num_bytes = block_rsv->size - block_rsv->reserved;
-	if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
-		qgroup_num_bytes = block_rsv->qgroup_rsv_size -
-				   block_rsv->qgroup_rsv_reserved;
-	spin_unlock(&block_rsv->lock);
-
+	calc_refill_bytes(block_rsv, &num_bytes, &qgroup_num_bytes);
 	if (num_bytes == 0)
 		return 0;
 
-	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
-	if (ret)
-		return ret;
-	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+	do {
+		ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes,
+							 true);
+		if (ret)
+			return ret;
+		ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+		if (ret) {
+			btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+			last = num_bytes;
+			/*
+			 * If we are fragmented we can end up with a lot of
+			 * outstanding extents which will make our size be much
+			 * larger than our reserved amount.
+			 *
+			 * If the reservation happens here, it might be very
+			 * big though not needed in the end, if the delalloc
+			 * flushing happens.
+			 *
+			 * If this is the case try and do the reserve again.
+			 */
+			if (flush == BTRFS_RESERVE_FLUSH_ALL)
+				calc_refill_bytes(block_rsv, &num_bytes,
+						   &qgroup_num_bytes);
+			if (num_bytes == 0)
+				return 0;
+		}
+	} while (ret && last != num_bytes);
+
 	if (!ret) {
 		block_rsv_add_bytes(block_rsv, num_bytes, 0);
 		trace_btrfs_space_reservation(root->fs_info, "delalloc",
@@ -5965,8 +5997,7 @@ int btrfs_inode_rsv_refill(struct btrfs_
 		spin_lock(&block_rsv->lock);
 		block_rsv->qgroup_rsv_reserved += qgroup_num_bytes;
 		spin_unlock(&block_rsv->lock);
-	} else
-		btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+	}
 	return ret;
 }