kernfs: fix memleak in kernel_ops_readdir()

If getdents64 is killed or hits on segfault, it'll leave cgroups
directories in sysfs pinned leaking memory because the kernfs node
won't be freed on rmdir and the parent neither.

Repro:

  # for i in `seq 1000`; do mkdir $i; done
  # rmdir *
  # for i in `seq 1000`; do mkdir $i; done
  # rmdir *

  # for i in `seq 1000`; do while :; do ls $i/ >/dev/null; done & done
  # while :; do killall ls; done

  kernfs_node_cache in /proc/slabinfo keeps going up as expected.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org # goes way back to original sysfs days
Link: https://lore.kernel.org/r/20190805173404.GF136335@devbig004.ftw2.facebook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index a387534..1e98efc 100644 (file)
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1684,11 +1684,14 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
                kernfs_get(pos);
 
                mutex_unlock(&kernfs_mutex);
-               if (!dir_emit(ctx, name, len, ino, type))
-                       return 0;
+               if (unlikely(!dir_emit(ctx, name, len, ino, type))) {
+                       kernfs_put(pos);
+                       goto out;
+               }
                mutex_lock(&kernfs_mutex);
        }
        mutex_unlock(&kernfs_mutex);
+out:
        file->private_data = NULL;
        ctx->pos = INT_MAX;
        return 0;