xfs: use per-mount cpumask to track nonempty percpu inodegc lists

Directly track which CPUs have contributed to the inodegc percpu lists
instead of trusting the cpu online mask.  This eliminates a theoretical
problem where the inodegc flush functions might fail to flush a CPU's
inodes if that CPU happened to be dying at exactly the same time.  Most
likely nobody's noticed this because the CPU dead hook moves the percpu
inodegc list to another CPU and schedules that worker immediately.  But
it's quite possible that this is a subtle race leading to UAF if the
inodegc flush were part of an unmount.

Further benefits: This reduces the overhead of the inodegc flush code
slightly by allowing us to ignore CPUs that have empty lists.  Better
yet, it reduces our dependence on the cpu online masks, which have been
the cause of confusion and drama lately.

Fixes: ab23a7768739 ("xfs: per-cpu deferred inode inactivation queues")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

1 files changed, 4 insertions, 2 deletions

diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index a25eece3be2b..f4a8879ba0e9 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -60,6 +60,7 @@ struct xfs_error_cfg {
  * Per-cpu deferred inode inactivation GC lists.
  */
 struct xfs_inodegc {
+	struct xfs_mount	*mp;
 	struct llist_head	list;
 	struct delayed_work	work;
 	int			error;
@@ -67,9 +68,7 @@ struct xfs_inodegc {
 	/* approximate count of inodes in the list */
 	unsigned int		items;
 	unsigned int		shrinker_hits;
-#if defined(DEBUG) || defined(XFS_WARN)
 	unsigned int		cpu;
-#endif
 };
 
 /*
@@ -249,6 +248,9 @@ typedef struct xfs_mount {
 	unsigned int		*m_errortag;
 	struct xfs_kobj		m_errortag_kobj;
 #endif
+
+	/* cpus that have inodes queued for inactivation */
+	struct cpumask		m_inodegc_cpumask;
 } xfs_mount_t;
 
 #define M_IGEO(mp)		(&(mp)->m_ino_geo)