80 lines
3.0 KiB
Diff
80 lines
3.0 KiB
Diff
|
From de7d5664d0f7a4a29c32aa98331d965f6c5c6de8 Mon Sep 17 00:00:00 2001
|
||
|
|
From: Brian Foster <bfoster@redhat.com>
|
||
|
|
Date: Tue, 15 Sep 2020 15:59:38 -0400
|
||
|
|
Subject: [PATCH 11/16] xfs: fix off-by-one in inode alloc block reservation
|
||
|
|
calculation
|
||
|
|
|
||
|
|
Source kernel commit: 657f101930bc6c5b41bd7d6c22565c4302a80d33
|
||
|
|
|
||
|
|
The inode chunk allocation transaction reserves inobt_maxlevels-1
|
||
|
|
blocks to accommodate a full split of the inode btree. A full split
|
||
|
|
requires an allocation for every existing level and a new root
|
||
|
|
block, which means inobt_maxlevels is the worst case block
|
||
|
|
requirement for a transaction that inserts to the inobt. This can
|
||
|
|
lead to a transaction block reservation overrun when tmpfile
|
||
|
|
creation allocates an inode chunk and expands the inobt to its
|
||
|
|
maximum depth. This problem has been observed in conjunction with
|
||
|
|
overlayfs, which makes frequent use of tmpfiles internally.
|
||
|
|
|
||
|
|
The existing reservation code goes back as far as the Linux git repo
|
||
|
|
history (v2.6.12). It was likely never observed as a problem because
|
||
|
|
the traditional file/directory creation transactions also include
|
||
|
|
worst case block reservation for directory modifications, which most
|
||
|
|
likely is able to make up for a single block deficiency in the inode
|
||
|
|
allocation portion of the calculation. tmpfile support is relatively
|
||
|
|
more recent (v3.15), less heavily used, and only includes the inode
|
||
|
|
allocation block reservation as tmpfiles aren't linked into the
|
||
|
|
directory tree on creation.
|
||
|
|
|
||
|
|
Fix up the inode alloc block reservation macro and a couple of the
|
||
|
|
block allocator minleft parameters that enforce an allocation to
|
||
|
|
leave enough free blocks in the AG for a full inobt split.
|
||
|
|
|
||
|
|
Signed-off-by: Brian Foster <bfoster@redhat.com>
|
||
|
|
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
|
||
|
|
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
|
||
|
|
Signed-off-by: Eric Sandeen <sandeen@sandeen.net>
|
||
|
|
---
|
||
|
|
libxfs/xfs_ialloc.c | 4 ++--
|
||
|
|
libxfs/xfs_trans_space.h | 2 +-
|
||
|
|
2 files changed, 3 insertions(+), 3 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
|
||
|
|
index 00b3326..750b223 100644
|
||
|
|
--- a/libxfs/xfs_ialloc.c
|
||
|
|
+++ b/libxfs/xfs_ialloc.c
|
||
|
|
@@ -683,7 +683,7 @@ xfs_ialloc_ag_alloc(
|
||
|
|
args.minalignslop = igeo->cluster_align - 1;
|
||
|
|
|
||
|
|
/* Allow space for the inode btree to split. */
|
||
|
|
- args.minleft = igeo->inobt_maxlevels - 1;
|
||
|
|
+ args.minleft = igeo->inobt_maxlevels;
|
||
|
|
if ((error = xfs_alloc_vextent(&args)))
|
||
|
|
return error;
|
||
|
|
|
||
|
|
@@ -731,7 +731,7 @@ xfs_ialloc_ag_alloc(
|
||
|
|
/*
|
||
|
|
* Allow space for the inode btree to split.
|
||
|
|
*/
|
||
|
|
- args.minleft = igeo->inobt_maxlevels - 1;
|
||
|
|
+ args.minleft = igeo->inobt_maxlevels;
|
||
|
|
if ((error = xfs_alloc_vextent(&args)))
|
||
|
|
return error;
|
||
|
|
}
|
||
|
|
diff --git a/libxfs/xfs_trans_space.h b/libxfs/xfs_trans_space.h
|
||
|
|
index c6df01a..7ad3659 100644
|
||
|
|
--- a/libxfs/xfs_trans_space.h
|
||
|
|
+++ b/libxfs/xfs_trans_space.h
|
||
|
|
@@ -58,7 +58,7 @@
|
||
|
|
#define XFS_IALLOC_SPACE_RES(mp) \
|
||
|
|
(M_IGEO(mp)->ialloc_blks + \
|
||
|
|
((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \
|
||
|
|
- (M_IGEO(mp)->inobt_maxlevels - 1)))
|
||
|
|
+ M_IGEO(mp)->inobt_maxlevels))
|
||
|
|
|
||
|
|
/*
|
||
|
|
* Space reservation values for various transactions.
|
||
|
|
--
|
||
|
|
1.8.3.1
|
||
|
|
|