Received-SPF: pass (google.com: best guess record for domain of linux-nfs-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 12.4 \(3445.104.11\))
Subject: Re: [PATCH v2] svcrdma: Ignore source port when computing DRC hash
From:   Chuck Lever <chuck.lever@oracle.com>
In-Reply-To: <20190619204301.GA3044@fieldses.org>
Date:   Wed, 19 Jun 2019 16:44:52 -0400
Cc:     linux-rdma@vger.kernel.org,
        Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Content-Transfer-Encoding: quoted-printable
Message-Id: <B60A02D7-08D0-40F8-93ED-D290BAC83658@oracle.com>
References: <20190611150116.4209.63309.stgit@klimt.1015granger.net>
 <FAF5EE39-8B5D-4F5C-9E9E-8FCA6EED8378@oracle.com>
 <20190619204301.GA3044@fieldses.org>
To:     Bruce Fields <bfields@fieldses.org>
Sender: linux-nfs-owner@vger.kernel.org
Precedence: bulk


> On Jun 19, 2019, at 4:43 PM, Bruce Fields <bfields@fieldses.org> =
wrote:
>=20
> On Wed, Jun 19, 2019 at 04:25:57PM -0400, Chuck Lever wrote:
>>=20
>>> On Jun 11, 2019, at 11:01 AM, Chuck Lever <chuck.lever@oracle.com> =
wrote:
>>>=20
>>> The DRC appears to be effectively empty after an RPC/RDMA transport
>>> reconnect. The problem is that each connection uses a different
>>> source port, which defeats the DRC hash.
>>>=20
>>> Clients always have to disconnect before they send retransmissions
>>> to reset the connection's credit accounting, thus every retransmit
>>> on NFS/RDMA will miss the DRC.
>>>=20
>>> An NFS/RDMA client's IP source port is meaningless for RDMA
>>> transports. The transport layer typically sets the source port value
>>> on the connection to a random ephemeral port. The server already
>>> ignores it for the "secure port" check. See commit 16e4d93f6de7
>>> ("NFSD: Ignore client's source port on RDMA transports").
>>>=20
>>> The Linux NFS server's DRC resolves XID collisions from the same
>>> source IP address by using the checksum of the first 200 bytes of
>>> the RPC call header.
>>>=20
>>> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
>>> Cc: stable@vger.kernel.org # v4.14+
>>> ---
>>> net/sunrpc/xprtrdma/svc_rdma_transport.c |    7 ++++++-
>>> 1 file changed, 6 insertions(+), 1 deletion(-)
>>>=20
>>> diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c =
b/net/sunrpc/xprtrdma/svc_rdma_transport.c
>>> index 027a3b0..0004535 100644
>>> --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
>>> +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
>>> @@ -211,9 +211,14 @@ static void handle_connect_req(struct =
rdma_cm_id *new_cma_id,
>>> 	/* Save client advertised inbound read limit for use later in =
accept. */
>>> 	newxprt->sc_ord =3D param->initiator_depth;
>>>=20
>>> -	/* Set the local and remote addresses in the transport */
>>> 	sa =3D (struct sockaddr =
*)&newxprt->sc_cm_id->route.addr.dst_addr;
>>> 	svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa));
>>> +	/* The remote port is arbitrary and not under the control of the
>>> +	 * client ULP. Set it to a fixed value so that the DRC continues
>>> +	 * to be effective after a reconnect.
>>> +	 */
>>> +	rpc_set_port((struct sockaddr *)&newxprt->sc_xprt.xpt_remote, =
0);
>>> +
>>> 	sa =3D (struct sockaddr =
*)&newxprt->sc_cm_id->route.addr.src_addr;
>>> 	svc_xprt_set_local(&newxprt->sc_xprt, sa, svc_addr_len(sa));
>>=20
>> Hi Bruce, what's the disposition of this patch?
>=20
> I've queued it up locally for 5.2 and stable.

Great, thank you!


> Apologies, it got a
> little buried in my inbox, thanks for the reminder.
>=20
> --b.

--
Chuck Lever