mm,vmscan: Allow preallocating memory for register_shrinker().

syzbot is catching so many bugs triggered by commit 9ee332d
("sget(): handle failures of register_shrinker()"). That commit expected
that calling kill_sb() from deactivate_locked_super() without successful
fill_super() is safe, but the reality was different; some callers assign
attributes which are needed for kill_sb() after sget() succeeds.

For example, [1] is a report where sb->s_mode (which seems to be either
FMODE_READ | FMODE_EXCL | FMODE_WRITE or FMODE_READ | FMODE_EXCL) is not
assigned unless sget() succeeds. But it does not worth complicate sget()
so that register_shrinker() failure path can safely call
kill_block_super() via kill_sb(). Making alloc_super() fail if memory
allocation for register_shrinker() failed is much simpler. Let's avoid
calling deactivate_locked_super() from sget_userns() by preallocating
memory for the shrinker and making register_shrinker() in sget_userns()
never fail.

[1] https://syzkaller.appspot.com/bug?id=588996a25a2587be2e3a54e8646728fb9cae44e7

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: syzbot <syzbot+5a170e19c963a2e0df79@syzkaller.appspotmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/super.c

@@ -167,6 +167,7 @@ static void destroy_unused_super(struct super_block *s)
 	security_sb_free(s);
 	put_user_ns(s->s_user_ns);
 	kfree(s->s_subtype);
+	free_prealloced_shrinker(&s->s_shrink);
 	/* no delays needed */
 	destroy_super_work(&s->destroy_work);
 }
@@ -252,6 +253,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
 	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
+	if (prealloc_shrinker(&s->s_shrink))
+		goto fail;
 	return s;
 
 fail:
@@ -518,11 +521,7 @@ struct super_block *sget_userns(struct file_system_type *type,
 	hlist_add_head(&s->s_instances, &type->fs_supers);
 	spin_unlock(&sb_lock);
 	get_filesystem(type);
-	err = register_shrinker(&s->s_shrink);
-	if (err) {
-		deactivate_locked_super(s);
-		s = ERR_PTR(err);
-	}
+	register_shrinker_prepared(&s->s_shrink);
 	return s;
 }
 

include/linux/shrinker.h

@@ -75,6 +75,9 @@ struct shrinker {
 #define SHRINKER_NUMA_AWARE	(1 << 0)
 #define SHRINKER_MEMCG_AWARE	(1 << 1)
 
-extern int register_shrinker(struct shrinker *);
-extern void unregister_shrinker(struct shrinker *);
+extern int prealloc_shrinker(struct shrinker *shrinker);
+extern void register_shrinker_prepared(struct shrinker *shrinker);
+extern int register_shrinker(struct shrinker *shrinker);
+extern void unregister_shrinker(struct shrinker *shrinker);
+extern void free_prealloced_shrinker(struct shrinker *shrinker);
 #endif

mm/vmscan.c

@@ -303,7 +303,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
 /*
  * Add a shrinker callback to be called from the vm.
  */
-int register_shrinker(struct shrinker *shrinker)
+int prealloc_shrinker(struct shrinker *shrinker)
 {
 	size_t size = sizeof(*shrinker->nr_deferred);
 
@@ -313,10 +313,29 @@ int register_shrinker(struct shrinker *shrinker)
 	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
+	return 0;
+}
+
+void free_prealloced_shrinker(struct shrinker *shrinker)
+{
+	kfree(shrinker->nr_deferred);
+	shrinker->nr_deferred = NULL;
+}
 
+void register_shrinker_prepared(struct shrinker *shrinker)
+{
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
 	up_write(&shrinker_rwsem);
+}
+
+int register_shrinker(struct shrinker *shrinker)
+{
+	int err = prealloc_shrinker(shrinker);
+
+	if (err)
+		return err;
+	register_shrinker_prepared(shrinker);
 	return 0;
 }
 EXPORT_SYMBOL(register_shrinker);