From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752101AbbJFIUz (ORCPT ); Tue, 6 Oct 2015 04:20:55 -0400 Received: from mail-wi0-f174.google.com ([209.85.212.174]:33743 "EHLO mail-wi0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750897AbbJFIUx (ORCPT ); Tue, 6 Oct 2015 04:20:53 -0400 Date: Tue, 6 Oct 2015 10:20:48 +0200 From: Ingo Molnar To: Daniel Borkmann Cc: Alexei Starovoitov , "David S. Miller" , Andy Lutomirski , Hannes Frederic Sowa , Eric Dumazet , Kees Cook , linux-api@vger.kernel.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH net-next 1/2] bpf: enable non-root eBPF programs Message-ID: <20151006082048.GA18287@gmail.com> References: <1444078101-29060-1-git-send-email-ast@plumgrid.com> <1444078101-29060-2-git-send-email-ast@plumgrid.com> <5612F639.2050305@iogearbox.net> <56131B1F.80002@plumgrid.com> <20151006071347.GB14093@gmail.com> <561380BB.4040506@iogearbox.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <561380BB.4040506@iogearbox.net> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Daniel Borkmann wrote: > On 10/06/2015 09:13 AM, Ingo Molnar wrote: > > > >* Alexei Starovoitov wrote: > > > >>On 10/5/15 3:14 PM, Daniel Borkmann wrote: > >>>One scenario that comes to mind ... what happens when there are kernel > >>>pointers stored in skb->cb[] (either from the current layer or an old > >>>one from a different layer that the skb went through previously, but > >>>which did not get overwritten)? > >>> > >>>Socket filters could read a portion of skb->cb[] also when unprived and > >>>leak that out through maps. I think the verifier doesn't catch that, > >>>right? > >> > >>grrr. indeed. previous layer before sk_filter() can leave junk in there. > > > >Could this be solved by activating zeroing/sanitizing of this data if there's an > >active BPF function around that can access that socket? > > I think this check could only be done in sk_filter() for testing these > conditions (unprivileged user + access to cb area), so it would need to > happen from outside a native eBPF program. :/ Yes, the kernel (with code running outside of any eBPF program) would guarantee that those data fields are zeroed/sanitized, if there's an eBPF program that is attached to that socket. > [...] Also classic BPF would then need to test for it, since a socket filter > doesn't really know whether native eBPF is loaded there or a classic-to-eBPF > transformed one, and classic never makes use of this. Anyway, it could be done > by adding a bit flag cb_access:1 to the bpf_prog, set it during eBPF > verification phase, and test it inside sk_filter() if I see it correctly. That could also be done in an unlikely() branch, to keep the cost to the non-eBPF case near zero. > The reason is that this sanitizing must only be done in the 'top-level' program > that is run from sk_filter() _directly_, because a user at any time could decide > to put an already loaded eBPF fd into a tail call map. And cb[] is then used to > pass args/state around between two programs, thus it cannot be unconditionally > cleared from within the program. The association to a socket filter > (SO_ATTACH_BPF) happens at a later time after a native eBPF program has already > been loaded via bpf(2). So zeroing tends to be very cheap and it could also be beneficial to performance in terms of bringing the cacheline into the CPU cache. But I really don't know the filter code so I'm just handwaving. Thanks, Ingo