Date:   Wed, 31 Jan 2018 15:25:44 -0800
From:   Tim Chen <tim.c.chen@...ux.intel.com>
To:     Josh Poimboeuf <jpoimboe@...hat.com>
Cc:     David Woodhouse <dwmw@...zon.co.uk>, arjan@...ux.intel.com,
        tglx@...utronix.de, karahmed@...zon.de, x86@...nel.org,
        linux-kernel@...r.kernel.org, bp@...en8.de, peterz@...radead.org,
        pbonzini@...hat.com, ak@...ux.intel.com,
        torvalds@...ux-foundation.org, gregkh@...ux-foundation.org,
        mingo@...nel.org, luto@...nel.org, linux@...inikbrodowski.net
Subject: Re: [PATCH] x86/speculation: Use Indirect Branch Prediction Barrier
 in context switch

On 01/30/2018 07:59 PM, Josh Poimboeuf wrote:
> On Tue, Jan 30, 2018 at 01:23:17PM -0800, Tim Chen wrote:
>> On 01/30/2018 09:48 AM, Josh Poimboeuf wrote:
>>> On Mon, Jan 29, 2018 at 10:04:47PM +0000, David Woodhouse wrote:
>>>> From: Tim Chen <tim.c.chen@...ux.intel.com>
>>>>
>>>> Flush indirect branches when switching into a process that marked itself
>>>> non dumpable. This protects high value processes like gpg better,
>>>> without having too high performance overhead.
>>>
>>> I wonder what the point of this patch is.  An audit of my laptop shows
>>> only a single user of PR_SET_DUMPABLE: systemd-coredump.
>>
>> This is an opt in approach.  For processes who need extra
>> security, it set itself as non-dumpable.  Then it can
>> ensure that it doesn't see any poisoned BTB.  
> 
> I don't want other users reading my applications' memory.
> 
> I don't want other containers reading my containers' memory.
> 
> I don't want *any* user tasks reading root daemons' memory.
> 
> Those are not unreasonable expectations.
> 
> So now I have to go and modify all my containers and applications to set
> PR_SET_DUMPABLE?  That seems highly impractical and unlikely.
> 
> Plus, I happen to *like* core dumps.
> 
> The other option is to rebuild the entire userland with retpolines, but
> again, that would make this patch completely pointless.
> 
>>> [ And yes, I have gpg-agent running.  Also, a grep of the gnupg source
>>> doesn't show any evidence of it being used there.  So the gpg thing
>>> seems to be a myth. ]
>>
>> I'm less familiar with gpg-agent.  Dave was the one who
>> put in comments about gpg-agent in this patch so perhaps
>> he can comment.
>>
>>>
>>> But also, I much preferred the original version of the patch which only
>>> skipped IBPB when 'prev' could ptrace 'next'.
>>
>> For the A->kernel thread->B scenario, you will need context of A
>> to decide if you need IBPB when switching to B.  You need to
>> worry about whether the context of A has been released ... etc if
>> you want to use ptrace.
> 
> Is that why the ptrace approach was abandoned?  Surely that's a solvable
> problem?  We have some smart people on lkml.  And anyway I didn't see it
> discussed anywhere.  In the worst case we could just always do IBPB when
> switching between kernel and user tasks.
> 

I think dumpable is not the end all policy.  It is a reasonable starting point
to provide us a means to secure the most sensitive processes without
IBPBing the world.  It is on the performance end of the security/performance trade off.

For people who opt for more security, it is reasonable to consider
alternate policies to distinguish friend and foe so we know if we are coming
from a potentially hostile environment.  Ptrace is one means to do so, and probably
there are other ways depending on usages.  I hope we can have a discussion on what we should
use to determine if two processes are friend or foe.  Say do all the processes
from the same containers are considered friends with each other?
I think once we have this decided, actually putting in IBPB will simple.

Tim

Powered by blists - more mailing lists