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: NMiklos Szeredi <mszeredi@redhat.com>
Reviewed-by: NAmir Goldstein <amir73il@gmail.com>
Signed-off-by: NJan Kara <jack@suse.cz>

fs/inode.c

@@ -234,6 +234,9 @@ void __destroy_inode(struct inode *inode)
 	inode_detach_wb(inode);
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
+#ifdef CONFIG_FSNOTIFY
+	fsnotify_connector_free(&inode->i_fsnotify_marks);
+#endif
 	locks_free_lock_context(inode);
 	if (!inode->i_nlink) {
 		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
@@ -371,9 +374,6 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->i_lru);
 	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
-#ifdef CONFIG_FSNOTIFY
-	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
-#endif
 }
 EXPORT_SYMBOL(inode_init_once);
 

fs/mount.h

@@ -59,7 +59,7 @@ struct mount {
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
 #ifdef CONFIG_FSNOTIFY
-	struct hlist_head mnt_fsnotify_marks;
+	struct fsnotify_mark_connector *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 #endif
 	int mnt_id;			/* mount identifier */

fs/namespace.c

@@ -236,9 +236,6 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-#ifdef CONFIG_FSNOTIFY
-		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
-#endif
 		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
 	}
 	return mnt;
@@ -1111,6 +1108,9 @@ static void cleanup_mnt(struct mount *mnt)
 	if (unlikely(mnt->mnt_pins.first))
 		mnt_pin_kill(mnt);
 	fsnotify_vfsmount_delete(&mnt->mnt);
+#ifdef CONFIG_FSNOTIFY
+	fsnotify_connector_free(&mnt->mnt_fsnotify_marks);
+#endif
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
 	mnt_free_id(mnt);

fs/notify/fsnotify.c

@@ -193,6 +193,7 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	struct hlist_node *inode_node = NULL, *vfsmount_node = NULL;
 	struct fsnotify_mark *inode_mark = NULL, *vfsmount_mark = NULL;
 	struct fsnotify_group *inode_group, *vfsmount_group;
+	struct fsnotify_mark_connector *inode_conn, *vfsmount_conn;
 	struct mount *mnt;
 	int idx, ret = 0;
 	/* global tests shouldn't care about events on child only the specific event */
@@ -210,8 +211,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	 * SRCU because we have no references to any objects and do not
 	 * need SRCU to keep them "alive".
 	 */
-	if (hlist_empty(&to_tell->i_fsnotify_marks) &&
-	    (!mnt || hlist_empty(&mnt->mnt_fsnotify_marks)))
+	if (!to_tell->i_fsnotify_marks &&
+	    (!mnt || !mnt->mnt_fsnotify_marks))
 		return 0;
 	/*
 	 * if this is a modify event we may need to clear the ignored masks
@@ -226,15 +227,23 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	idx = srcu_read_lock(&fsnotify_mark_srcu);
 
 	if ((mask & FS_MODIFY) ||
-	    (test_mask & to_tell->i_fsnotify_mask))
-		inode_node = srcu_dereference(to_tell->i_fsnotify_marks.first,
+	    (test_mask & to_tell->i_fsnotify_mask)) {
+		inode_conn = lockless_dereference(to_tell->i_fsnotify_marks);
+		if (inode_conn)
+			inode_node = srcu_dereference(inode_conn->list.first,
 						      &fsnotify_mark_srcu);
+	}
 
 	if (mnt && ((mask & FS_MODIFY) ||
 		    (test_mask & mnt->mnt_fsnotify_mask))) {
-		vfsmount_node = srcu_dereference(mnt->mnt_fsnotify_marks.first,
+		inode_conn = lockless_dereference(to_tell->i_fsnotify_marks);
+		if (inode_conn)
+			inode_node = srcu_dereference(inode_conn->list.first,
 						      &fsnotify_mark_srcu);
-		inode_node = srcu_dereference(to_tell->i_fsnotify_marks.first,
+		vfsmount_conn = lockless_dereference(mnt->mnt_fsnotify_marks);
+		if (vfsmount_conn)
+			vfsmount_node = srcu_dereference(
+						vfsmount_conn->list.first,
 						&fsnotify_mark_srcu);
 	}
 
@@ -293,6 +302,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 }
 EXPORT_SYMBOL_GPL(fsnotify);
 
+extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
 static __init int fsnotify_init(void)
 {
 	int ret;
@@ -303,6 +314,9 @@ static __init int fsnotify_init(void)
 	if (ret)
 		panic("initializing fsnotify_mark_srcu");
 
+	fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
+						    SLAB_PANIC);
+
 	return 0;
 }
 core_initcall(fsnotify_init);

fs/notify/fsnotify.h

@@ -15,7 +15,7 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
 extern struct srcu_struct fsnotify_mark_srcu;
 
 /* Calculate mask of events for a list of marks */
-extern u32 fsnotify_recalc_mask(struct hlist_head *head);
+extern u32 fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
 
 /* compare two groups for sorting of marks lists */
 extern int fsnotify_compare_groups(struct fsnotify_group *a,
@@ -24,7 +24,7 @@ extern int fsnotify_compare_groups(struct fsnotify_group *a,
 extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
 						__u32 mask);
 /* Add mark to a proper place in mark list */
-extern int fsnotify_add_mark_list(struct hlist_head *head,
+extern int fsnotify_add_mark_list(struct fsnotify_mark_connector **connp,
 				  struct fsnotify_mark *mark,
 				  int allow_dups);
 /* add a mark to an inode */
@@ -41,19 +41,21 @@ extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
 /* inode specific destruction of a mark */
 extern void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark);
 /* Find mark belonging to given group in the list of marks */
-extern struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+extern struct fsnotify_mark *fsnotify_find_mark(
+					struct fsnotify_mark_connector *conn,
 					struct fsnotify_group *group);
 /* Destroy all marks in the given list protected by 'lock' */
-extern void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock);
+extern void fsnotify_destroy_marks(struct fsnotify_mark_connector *conn,
+				   spinlock_t *lock);
 /* run the list of all marks associated with inode and destroy them */
 static inline void fsnotify_clear_marks_by_inode(struct inode *inode)
 {
-	fsnotify_destroy_marks(&inode->i_fsnotify_marks, &inode->i_lock);
+	fsnotify_destroy_marks(inode->i_fsnotify_marks, &inode->i_lock);
 }
 /* run the list of all marks associated with vfsmount and destroy them */
 static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
 {
-	fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks,
+	fsnotify_destroy_marks(real_mount(mnt)->mnt_fsnotify_marks,
 			       &mnt->mnt_root->d_lock);
 }
 /* prepare for freeing all marks associated with given group */

fs/notify/inode_mark.c

@@ -37,7 +37,7 @@
 void fsnotify_recalc_inode_mask(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 
 	__fsnotify_update_child_dentry_flags(inode);
@@ -60,7 +60,7 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
 	 * hold the inode->i_lock, so this is the perfect time to update the
 	 * inode->i_fsnotify_mask
 	 */
-	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -82,7 +82,7 @@ struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
 	struct fsnotify_mark *mark;
 
 	spin_lock(&inode->i_lock);
-	mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
+	mark = fsnotify_find_mark(inode->i_fsnotify_marks, group);
 	spin_unlock(&inode->i_lock);
 
 	return mark;
@@ -135,7 +135,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 	mark->inode = inode;
 	ret = fsnotify_add_mark_list(&inode->i_fsnotify_marks, mark,
 				     allow_dups);
-	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
+	inode->i_fsnotify_mask = fsnotify_recalc_mask(inode->i_fsnotify_marks);
 	spin_unlock(&inode->i_lock);
 
 	return ret;

fs/notify/mark.c

@@ -83,6 +83,8 @@
 #define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */
 
 struct srcu_struct fsnotify_mark_srcu;
+struct kmem_cache *fsnotify_mark_connector_cachep;
+
 static DEFINE_SPINLOCK(destroy_lock);
 static LIST_HEAD(destroy_list);
 
@@ -104,12 +106,15 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 }
 
 /* Calculate mask of events for a list of marks */
-u32 fsnotify_recalc_mask(struct hlist_head *head)
+u32 fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 {
 	u32 new_mask = 0;
 	struct fsnotify_mark *mark;
 
-	hlist_for_each_entry(mark, head, obj_list)
+	if (!conn)
+		return 0;
+
+	hlist_for_each_entry(mark, &conn->list, obj_list)
 		new_mask |= mark->mask;
 	return new_mask;
 }
@@ -220,10 +225,14 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	fsnotify_free_mark(mark);
 }
 
-void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
+void fsnotify_destroy_marks(struct fsnotify_mark_connector *conn,
+			    spinlock_t *lock)
 {
 	struct fsnotify_mark *mark;
 
+	if (!conn)
+		return;
+
 	while (1) {
 		/*
 		 * We have to be careful since we can race with e.g.
@@ -233,11 +242,12 @@ void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
 		 * calling fsnotify_destroy_mark() more than once is fine.
 		 */
 		spin_lock(lock);
-		if (hlist_empty(head)) {
+		if (hlist_empty(&conn->list)) {
 			spin_unlock(lock);
 			break;
 		}
-		mark = hlist_entry(head->first, struct fsnotify_mark, obj_list);
+		mark = hlist_entry(conn->list.first, struct fsnotify_mark,
+				   obj_list);
 		/*
 		 * We don't update i_fsnotify_mask / mnt_fsnotify_mask here
 		 * since inode / mount is going away anyway. So just remove
@@ -251,6 +261,14 @@ void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
 	}
 }
 
+void fsnotify_connector_free(struct fsnotify_mark_connector **connp)
+{
+	if (*connp) {
+		kmem_cache_free(fsnotify_mark_connector_cachep, *connp);
+		*connp = NULL;
+	}
+}
+
 void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
 {
 	assert_spin_locked(&mark->lock);
@@ -304,21 +322,54 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
 	return -1;
 }
 
-/* Add mark into proper place in given list of marks */
-int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
-			   int allow_dups)
+static int fsnotify_attach_connector_to_object(
+					struct fsnotify_mark_connector **connp)
+{
+	struct fsnotify_mark_connector *conn;
+
+	conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_ATOMIC);
+	if (!conn)
+		return -ENOMEM;
+	INIT_HLIST_HEAD(&conn->list);
+	/*
+	 * Make sure 'conn' initialization is visible. Matches
+	 * lockless_dereference() in fsnotify().
+	 */
+	smp_wmb();
+	*connp = conn;
+
+	return 0;
+}
+
+/*
+ * Add mark into proper place in given list of marks. These marks may be used
+ * for the fsnotify backend to determine which event types should be delivered
+ * to which group and for which inodes. These marks are ordered according to
+ * priority, highest number first, and then by the group's location in memory.
+ */
+int fsnotify_add_mark_list(struct fsnotify_mark_connector **connp,
+			   struct fsnotify_mark *mark, int allow_dups)
 {
 	struct fsnotify_mark *lmark, *last = NULL;
+	struct fsnotify_mark_connector *conn;
 	int cmp;
+	int err;
+
+	if (!*connp) {
+		err = fsnotify_attach_connector_to_object(connp);
+		if (err)
+			return err;
+	}
+	conn = *connp;
 
 	/* is mark the first mark? */
-	if (hlist_empty(head)) {
-		hlist_add_head_rcu(&mark->obj_list, head);
+	if (hlist_empty(&conn->list)) {
+		hlist_add_head_rcu(&mark->obj_list, &conn->list);
 		return 0;
 	}
 
 	/* should mark be in the middle of the current list? */
-	hlist_for_each_entry(lmark, head, obj_list) {
+	hlist_for_each_entry(lmark, &conn->list, obj_list) {
 		last = lmark;
 
 		if ((lmark->group == mark->group) && !allow_dups)
@@ -419,12 +470,15 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
  * Given a list of marks, find the mark associated with given group. If found
  * take a reference to that mark and return it, else return NULL.
  */
-struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
+struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_mark_connector *conn,
 					 struct fsnotify_group *group)
 {
 	struct fsnotify_mark *mark;
 
-	hlist_for_each_entry(mark, head, obj_list) {
+	if (!conn)
+		return NULL;
+
+	hlist_for_each_entry(mark, &conn->list, obj_list) {
 		if (mark->group == group) {
 			fsnotify_get_mark(mark);
 			return mark;

fs/notify/vfsmount_mark.c

@@ -43,7 +43,7 @@ void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt)
 	struct mount *m = real_mount(mnt);
 
 	spin_lock(&mnt->mnt_root->d_lock);
-	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 }
 
@@ -60,7 +60,7 @@ void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark)
 	hlist_del_init_rcu(&mark->obj_list);
 	mark->mnt = NULL;
 
-	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 }
 
@@ -75,7 +75,7 @@ struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group,
 	struct fsnotify_mark *mark;
 
 	spin_lock(&mnt->mnt_root->d_lock);
-	mark = fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
+	mark = fsnotify_find_mark(m->mnt_fsnotify_marks, group);
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	return mark;
@@ -101,7 +101,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 	spin_lock(&mnt->mnt_root->d_lock);
 	mark->mnt = mnt;
 	ret = fsnotify_add_mark_list(&m->mnt_fsnotify_marks, mark, allow_dups);
-	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
+	m->mnt_fsnotify_mask = fsnotify_recalc_mask(m->mnt_fsnotify_marks);
 	spin_unlock(&mnt->mnt_root->d_lock);
 
 	return ret;

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)

include/linux/fsnotify_backend.h

@@ -194,6 +194,15 @@ struct fsnotify_group {
 #define FSNOTIFY_EVENT_PATH	1
 #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
@@ -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);

kernel/auditsc.c

@@ -73,6 +73,7 @@
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
+#include <linux/fsnotify_backend.h>
 #include <uapi/linux/limits.h>
 
 #include "audit.h"
@@ -1596,7 +1597,8 @@ static inline void handle_one(const struct inode *inode)
 	struct audit_tree_refs *p;
 	struct audit_chunk *chunk;
 	int count;
-	if (likely(hlist_empty(&inode->i_fsnotify_marks)))
+	if (likely(!inode->i_fsnotify_marks ||
+		   hlist_empty(&inode->i_fsnotify_marks->list)))
 		return;
 	context = current->audit_context;
 	p = context->trees;
@@ -1639,7 +1641,8 @@ static void handle_path(const struct dentry *dentry)
 	seq = read_seqbegin(&rename_lock);
 	for(;;) {
 		struct inode *inode = d_backing_inode(d);
-		if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) {
+		if (inode && unlikely(inode->i_fsnotify_marks &&
+		    !hlist_empty(&inode->i_fsnotify_marks->list))) {
 			struct audit_chunk *chunk;
 			chunk = audit_tree_lookup(inode);
 			if (chunk) {