Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 8 Jul 2019 20:05:25 -0300
From:   Jason Gunthorpe <jgg@ziepe.ca>
To:     Dag Moxnes <dag.moxnes@oracle.com>
Cc:     Mark Bloch <markb@mellanox.com>,
        "dledford@redhat.com" <dledford@redhat.com>,
        "leon@kernel.org" <leon@kernel.org>,
        Parav Pandit <parav@mellanox.com>,
        "linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v3] RDMA/core: Fix race when resolving IP address
Message-ID: <20190708230525.GI23996@ziepe.ca>
References: <1562584584-13132-1-git-send-email-dag.moxnes@oracle.com>
 <20190708175025.GA6976@ziepe.ca>
 <4b9ae7b8-310c-e0b6-7a8e-33e6d5bef83d@oracle.com>
 <63b9d2cb-f69c-d77c-7803-f08e2a6f755d@mellanox.com>
 <20190708193814.GF23996@ziepe.ca>
 <424b75d7-90ea-8d07-42b9-de9d507b0f85@oracle.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <424b75d7-90ea-8d07-42b9-de9d507b0f85@oracle.com>
User-Agent: Mutt/1.9.4 (2018-02-28)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Jul 08, 2019 at 10:11:29PM +0200, Dag Moxnes wrote:
> 
> 
> Den 08.07.2019 21:38, skrev Jason Gunthorpe:
> > On Mon, Jul 08, 2019 at 07:22:45PM +0000, Mark Bloch wrote:
> > > 
> > > On 7/8/19 11:47 AM, Dag Moxnes wrote:
> > > > Thanks Jason,
> > > > 
> > > > Regards,
> > > > Dag
> > > > 
> > > > Den 08.07.2019 19:50, skrev Jason Gunthorpe:
> > > > > On Mon, Jul 08, 2019 at 01:16:24PM +0200, Dag Moxnes wrote:
> > > > > > Use neighbour lock when copying MAC address from neighbour data struct
> > > > > > in dst_fetch_ha.
> > > > > > 
> > > > > > When not using the lock, it is possible for the function to race with
> > > > > > neigh_update, causing it to copy an invalid MAC address.
> > > > > > 
> > > > > > It is possible to provoke this error by calling rdma_resolve_addr in a
> > > > > > tight loop, while deleting the corresponding ARP entry in another tight
> > > > > > loop.
> > > > > > 
> > > > > > This will cause the race shown it the following sample trace:
> > > > > > 
> > > > > > rdma_resolve_addr()
> > > > > >     rdma_resolve_ip()
> > > > > >       addr_resolve()
> > > > > >         addr_resolve_neigh()
> > > > > >           fetch_ha()
> > > > > >             dst_fetch_ha()
> > > > > >               n->nud_state == NUD_VALID
> > > > > It isn't nud_state that is the problem here, it is the parallel
> > > > > memcpy's onto ha. I fixed the commit message
> > > > > 
> > > > > This could also have been solved by using the ha_lock, but I don't
> > > > > think we have a reason to particularly over-optimize this.
> > > Sorry I'm late to the party, but why not just use: neigh_ha_snapshot()?
> > Yes, that is much better, please respin this
> OK, will do!
> Can I still post it as a v4? Or should I do it differently as you already
> applied it?

post a v4

Jason