fsnotify: Move mark list head from object into dedicated structure

Currently notification marks are attached to object (inode or vfsmnt) by
a hlist_head in the object. The list is also protected by a spinlock in
the object. So while there is any mark attached to the list of marks,
the object must be pinned in memory (and thus e.g. last iput() deleting
inode cannot happen). Also for list iteration in fsnotify() to work, we
must hold fsnotify_mark_srcu lock so that mark itself and
mark->obj_list.next cannot get freed. Thus we are required to wait for
response to fanotify events from userspace process with
fsnotify_mark_srcu lock held. That causes issues when userspace process
is buggy and does not reply to some event - basically the whole
notification subsystem gets eventually stuck.

So to be able to drop fsnotify_mark_srcu lock while waiting for
response, we have to pin the mark in memory and make sure it stays in
the object list (as removing the mark waiting for response could lead to
lost notification events for groups later in the list). However we don't
want inode reclaim to block on such mark as that would lead to system
just locking up elsewhere.

This commit is the first in the series that paves way towards solving
these conflicting lifetime needs. Instead of anchoring the list of marks
directly in the object, we anchor it in a dedicated structure
(fsnotify_mark_connector) and just point to that structure from the
object. The following commits will also add spinlock protecting the list
and object pointer to the structure.

Reviewed-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>

2 files changed, 13 insertions, 1 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7251f7bb45e8..66e52342be2d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -546,6 +546,8 @@ is_uncached_acl(struct posix_acl *acl)
 #define IOP_XATTR	0x0008
 #define IOP_DEFAULT_READLINK	0x0010
 
+struct fsnotify_mark_connector;
+
 /*
  * Keep mostly read-only and often accessed (especially for
  * the RCU path lookup and 'stat' data) fields at the beginning
@@ -645,7 +647,7 @@ struct inode {
 
 #ifdef CONFIG_FSNOTIFY
 	__u32			i_fsnotify_mask; /* all events this inode cares about */
-	struct hlist_head	i_fsnotify_marks;
+	struct fsnotify_mark_connector	*i_fsnotify_marks;
 #endif
 
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index e6e689b5569e..8b63085f8855 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -195,6 +195,15 @@ struct fsnotify_group {
 #define FSNOTIFY_EVENT_INODE	2
 
 /*
+ * Inode / vfsmount point to this structure which tracks all marks attached to
+ * the inode / vfsmount. The structure is freed only when inode / vfsmount gets
+ * freed.
+ */
+struct fsnotify_mark_connector {
+	struct hlist_head list;
+};
+
+/*
  * A mark is simply an object attached to an in core inode which allows an
  * fsnotify listener to indicate they are either no longer interested in events
  * of a type matching mask or only interested in those events.
@@ -346,6 +355,7 @@ extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
 extern void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group);
 /* run all the marks in a group, and clear all of the marks where mark->flags & flags is true*/
 extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags);
+extern void fsnotify_connector_free(struct fsnotify_mark_connector **connp);
 extern void fsnotify_get_mark(struct fsnotify_mark *mark);
 extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_unmount_inodes(struct super_block *sb);