linux-kernel - Re: [PATCH 8/7] net/netfilter/nf_conntrack

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]

Message-ID: <20160902192213.GM10153@twins.programming.kicks-ass.net>
Date:   Fri, 2 Sep 2016 21:22:13 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Manfred Spraul <manfred@...orfullife.com>
Cc:     Will Deacon <will.deacon@....com>, benh@...nel.crashing.org,
        paulmck@...ux.vnet.ibm.com, Ingo Molnar <mingo@...e.hu>,
        Boqun Feng <boqun.feng@...il.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        LKML <linux-kernel@...r.kernel.org>, 1vier1@....de,
        Davidlohr Bueso <dave@...olabs.net>,
        Pablo Neira Ayuso <pablo@...filter.org>,
        netfilter-devel@...r.kernel.org
Subject: Re: [PATCH 8/7] net/netfilter/nf_conntrack_core: Remove another
 memory barrier

On Fri, Sep 02, 2016 at 08:35:55AM +0200, Manfred Spraul wrote:
> On 09/01/2016 06:41 PM, Peter Zijlstra wrote:
> >On Thu, Sep 01, 2016 at 04:30:39PM +0100, Will Deacon wrote:
> >>On Thu, Sep 01, 2016 at 05:27:52PM +0200, Manfred Spraul wrote:
> >>>Since spin_unlock_wait() is defined as equivalent to spin_lock();
> >>>spin_unlock(), the memory barrier before spin_unlock_wait() is
> >>>also not required.
> >Note that ACQUIRE+RELEASE isn't a barrier.
> >
> >Both are semi-permeable and things can cross in the middle, like:
> >
> >
> >	x = 1;
> >	LOCK
> >	UNLOCK
> >	r = y;
> >
> >can (validly) get re-ordered like:
> >
> >	LOCK
> >	r = y;
> >	x = 1;
> >	UNLOCK
> >
> >So if you want things ordered, as I think you do, I think the smp_mb()
> >is still needed.
> CPU1:
> x=1; /* without WRITE_ONCE */
> LOCK(l);
> UNLOCK(l);
> <do_semop>
> smp_store_release(x,0)
> 
> 
> CPU2;
> LOCK(l)
> if (smp_load_acquire(x)==1) goto slow_path
> <do_semop>
> UNLOCK(l)
> 
> Ordering is enforced because both CPUs access the same lock.
> 
> x=1 can't be reordered past the UNLOCK(l), I don't see that further
> guarantees are necessary.
> 
> Correct?

Correct, sadly implementations do not comply :/ In fact, even x86 is
broken here.

I spoke to Will earlier today and he suggests either making
spin_unlock_wait() stronger to avoids any and all such surprises or just
getting rid of the thing.

I'm not sure which way we should go, but please hold off on these two
patches until I've had a chance to audit all of those implementations
again.

I'll try and have a look at your other patches before that.