linux-kernel - Re: [PATCH v3] mm: Fix kthread_use

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] [day] [month] [year] [list]

Message-Id: <1598597607.h04xhbtpuo.astroid@bobo.none>
Date:   Fri, 28 Aug 2020 16:55:21 +1000
From:   Nicholas Piggin <npiggin@...il.com>
To:     "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
        linux-arch@...r.kernel.org, peterz@...radead.org
Cc:     Andrew Morton <akpm@...ux-foundation.org>, axboe@...nel.dk,
        hch@....de, jannh@...gle.com, keescook@...omium.org,
        linux-kernel@...r.kernel.org, luto@...capital.net,
        mathieu.desnoyers@...icios.com, torvalds@...ux-foundation.org,
        will@...nel.org
Subject: Re: [PATCH v3] mm: Fix kthread_use_mm() vs TLB invalidate

Excerpts from Nicholas Piggin's message of August 28, 2020 1:26 pm:
> Excerpts from peterz@...radead.org's message of August 21, 2020 11:04 pm:
>> On Fri, Aug 21, 2020 at 11:09:51AM +0530, Aneesh Kumar K.V wrote:
>>> Peter Zijlstra <peterz@...radead.org> writes:
>>> 
>>> > For SMP systems using IPI based TLB invalidation, looking at
>>> > current->active_mm is entirely reasonable. This then presents the
>>> > following race condition:
>>> >
>>> >
>>> >   CPU0			CPU1
>>> >
>>> >   flush_tlb_mm(mm)	use_mm(mm)
>>> >     <send-IPI>
>>> > 			  tsk->active_mm = mm;
>>> > 			  <IPI>
>>> > 			    if (tsk->active_mm == mm)
>>> > 			      // flush TLBs
>>> > 			  </IPI>
>>> > 			  switch_mm(old_mm,mm,tsk);
>>> >
>>> >
>>> > Where it is possible the IPI flushed the TLBs for @old_mm, not @mm,
>>> > because the IPI lands before we actually switched.
>>> >
>>> > Avoid this by disabling IRQs across changing ->active_mm and
>>> > switch_mm().
>>> >
>>> > [ There are all sorts of reasons this might be harmless for various
>>> > architecture specific reasons, but best not leave the door open at
>>> > all. ]
>>> 
>>> 
>>> Do we have similar race with exec_mmap()? I am looking at exec_mmap()
>>> runnning parallel to do_exit_flush_lazy_tlb(). We can get
>>> 
>>> 	if (current->active_mm == mm) {
>>> 
>>> true and if we don't disable irq around updating tsk->mm/active_mm we
>>> can end up doing mmdrop on wrong mm?
>> 
>> exec_mmap() is called after de_thread(), there should not be any mm
>> specific invalidations around I think.
>> 
>> Then again, CLONE_VM without CLONE_THREAD might still be possible, so
>> yeah, we probably want IRQs disabled there too, just for consistency and
>> general paranoia if nothing else.
> 
> The problem is probably not this TLB flushing race, but I think there
> is a lazy tlb race.

Hmm, is it possible for something to be holding the mm_users when we
exec? That could actually make it a problem for TLB flushing too.

Thanks,
Nick