[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20161017185552.GA24653@lst.de>
Date: Mon, 17 Oct 2016 20:55:52 +0200
From: Christoph Hellwig <hch@....de>
To: Jeff Moyer <jmoyer@...hat.com>
Cc: Christoph Hellwig <hch@....de>, viro@...iv.linux.org.uk,
jack@...e.cz, dmonakhov@...nvz.org, linux-fsdevel@...r.kernel.org,
linux-aio@...ck.org, linux-kernel@...r.kernel.org,
Peter Zijlstra <peterz@...radead.org>,
Oleg Nesterov <oleg@...hat.com>,
Mikulas Patocka <mpatocka@...hat.com>
Subject: Re: [PATCH] aio: fix a use after free (and fix freeze protection
of aio writes)
On Mon, Oct 17, 2016 at 02:19:47PM -0400, Jeff Moyer wrote:
> This ends up being a call to __sb_end_write:
>
> void __sb_end_write(struct super_block *sb, int level)
> {
> percpu_up_read(sb->s_writers.rw_sem + level-1);
> }
>
> Nothing guarantees that submission and completion happen on the same
> CPU. Is this safe?
Good point. From my reading of the percpu_rwsem implementation it
is not safe to release it from a different CPU. Which makes me
wonder how we can protect aio writes properly here..
Powered by blists - more mailing lists