netdev - Re: [bpf PATCH] bpf, sockmap: RCU splat with TLS redirect and strparser

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 24 Jun 2020 23:22:02 -0700
From:   Martin KaFai Lau <kafai@...com>
To:     John Fastabend <john.fastabend@...il.com>
CC:     <jakub@...udflare.com>, <daniel@...earbox.net>, <ast@...nel.org>,
        <netdev@...r.kernel.org>, <bpf@...r.kernel.org>
Subject: Re: [bpf PATCH] bpf, sockmap: RCU splat with TLS redirect and
 strparser

On Wed, Jun 24, 2020 at 02:09:23PM -0700, John Fastabend wrote:
> Redirect on non-TLS sockmap side has RCU lock held from sockmap code
> path but when called from TLS this is no longer true. The RCU section
> is needed because we use rcu dereference to fetch the psock of the
> socket we are redirecting to.
sk_psock_verdict_apply() is also called by sk_psock_strp_read() after
rcu_read_unlock().  This issue should not be limited to tls?