UBUNTU: Ubuntu-4.15.0-39.42

[mirror_ubuntu-bionic-kernel.git] / fs / super.c

diff --git a/fs/super.c b/fs/super.c
index 8857be9d604eeed74b03f37df8c825f9e4a41d30..5c9fa51c133fad7ea040e2e5f4d9f76f6c6d3347 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -120,13 +120,23 @@ static unsigned long super_cache_count(struct shrinker *shrink,
        sb = container_of(shrink, struct super_block, s_shrink);
 
        /*
-        * Don't call trylock_super as it is a potential
-        * scalability bottleneck. The counts could get updated
-        * between super_cache_count and super_cache_scan anyway.
-        * Call to super_cache_count with shrinker_rwsem held
-        * ensures the safety of call to list_lru_shrink_count() and
-        * s_op->nr_cached_objects().
+        * We don't call trylock_super() here as it is a scalability bottleneck,
+        * so we're exposed to partial setup state. The shrinker rwsem does not
+        * protect filesystem operations backing list_lru_shrink_count() or
+        * s_op->nr_cached_objects(). Counts can change between
+        * super_cache_count and super_cache_scan, so we really don't need locks
+        * here.
+        *
+        * However, if we are currently mounting the superblock, the underlying
+        * filesystem might be in a state of partial construction and hence it
+        * is dangerous to access it.  trylock_super() uses a SB_BORN check to
+        * avoid this situation, so do the same here. The memory barrier is
+        * matched with the one in mount_fs() as we don't hold locks here.
         */
+       if (!(sb->s_flags & SB_BORN))
+               return 0;
+       smp_rmb();
+
        if (sb->s_op && sb->s_op->nr_cached_objects)
                total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
@@ -166,6 +176,7 @@ 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);
 }
@@ -251,6 +262,8 @@ 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:
@@ -517,11 +530,7 @@ retry:
        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;
 }
 
@@ -1255,6 +1264,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
        sb = root->d_sb;
        BUG_ON(!sb);
        WARN_ON(!sb->s_bdi);
+
+       /*
+        * Write barrier is for super_cache_count(). We place it before setting
+        * SB_BORN as the data dependency between the two functions is the
+        * superblock structure contents that we just set up, not the SB_BORN
+        * flag.
+        */
+       smp_wmb();
        sb->s_flags |= SB_BORN;
 
        error = security_sb_kern_mount(sb, flags, secdata);