Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 13.4 \(3608.120.23.2.4\))
Subject: Re: [PATCH] svcrdma: fix bounce buffers for non-zero page offsets
From:   Chuck Lever <chuck.lever@oracle.com>
In-Reply-To: <20201002144827.984306-1-dan@kernelim.com>
Date:   Fri, 2 Oct 2020 10:54:28 -0400
Cc:     linux-rdma <linux-rdma@vger.kernel.org>,
        Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Content-Transfer-Encoding: quoted-printable
Message-Id: <7DE1BF37-DF5E-47F2-A24C-A80ED20956CE@oracle.com>
References: <20201002144827.984306-1-dan@kernelim.com>
To:     Dan Aloni <dan@kernelim.com>
Precedence: bulk

Hi Dan-

> On Oct 2, 2020, at 10:48 AM, Dan Aloni <dan@kernelim.com> wrote:
>=20
> This was discovered using O_DIRECT and small unaligned file offsets
> at the client side.
>=20
> Fixes: e248aa7be86 ("svcrdma: Remove max_sge check at connect time")
> Signed-off-by: Dan Aloni <dan@kernelim.com>
> ---
> net/sunrpc/xprtrdma/svc_rdma_sendto.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>=20
> diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c =
b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> index 7b94d971feb3..c991eb1fd4e3 100644
> --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
> @@ -638,7 +638,7 @@ static int svc_rdma_pull_up_reply_msg(struct =
svcxprt_rdma *rdma,
> 		while (remaining) {
> 			len =3D min_t(u32, PAGE_SIZE - pageoff, =
remaining);
>=20
> -			memcpy(dst, page_address(*ppages), len);
> +			memcpy(dst, page_address(*ppages) + pageoff, =
len);

I'm assuming the only relevant place that sets xdr->page_base
is nfsd_splice_actor() ?


> 			remaining -=3D len;
> 			dst +=3D len;
> 			pageoff =3D 0;
> --=20
> 2.26.2
>=20

--
Chuck Lever