From mboxrd@z Thu Jan  1 00:00:00 1970
From: Jason Wang <jasowang@redhat.com>
Subject: Re: [PATCH 3/5] VSOCK: support receive mergeable rx buffer in guest
Date: Wed, 7 Nov 2018 21:29:45 +0800
Message-ID: <52234dd6-6101-9fe7-e4ca-dc138bbd85ab@redhat.com>
References: <5BDFF57C.5020106@huawei.com>
 <791d67e7-ad95-38e4-0d38-2b7c54d68040@redhat.com>
 <5BE137B2.5040305@huawei.com>
 <1b67b8ef-5dcc-0383-1b32-d80f294533d3@redhat.com>
 <5BE28F37.1030208@huawei.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Cc: netdev@vger.kernel.org, kvm@vger.kernel.org,
        virtualization@lists.linux-foundation.org
To: jiangyiwen <jiangyiwen@huawei.com>, stefanha@redhat.com
Return-path: <netdev-owner@vger.kernel.org>
In-Reply-To: <5BE28F37.1030208@huawei.com>
Content-Language: en-US
Sender: netdev-owner@vger.kernel.org
List-Id: kvm.vger.kernel.org


On 2018/11/7 下午3:07, jiangyiwen wrote:
> On 2018/11/7 14:20, Jason Wang wrote:
>> On 2018/11/6 下午2:41, jiangyiwen wrote:
>>> On 2018/11/6 12:00, Jason Wang wrote:
>>>> On 2018/11/5 下午3:47, jiangyiwen wrote:
>>>>> Guest receive mergeable rx buffer, it can merge
>>>>> scatter rx buffer into a big buffer and then copy
>>>>> to user space.
>>>>>
>>>>> Signed-off-by: Yiwen Jiang<jiangyiwen@huawei.com>
>>>>> ---
>>>>>     include/linux/virtio_vsock.h            |  9 ++++
>>>>>     net/vmw_vsock/virtio_transport.c        | 75 +++++++++++++++++++++++++++++----
>>>>>     net/vmw_vsock/virtio_transport_common.c | 59 ++++++++++++++++++++++----
>>>>>     3 files changed, 127 insertions(+), 16 deletions(-)
>>>>>
>>>>> diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
>>>>> index da9e1fe..6be3cd7 100644
>>>>> --- a/include/linux/virtio_vsock.h
>>>>> +++ b/include/linux/virtio_vsock.h
>>>>> @@ -13,6 +13,8 @@
>>>>>     #define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE    (1024 * 4)
>>>>>     #define VIRTIO_VSOCK_MAX_BUF_SIZE        0xFFFFFFFFUL
>>>>>     #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE        (1024 * 64)
>>>>> +/* virtio_vsock_pkt + max_pkt_len(default MAX_PKT_BUF_SIZE) */
>>>>> +#define VIRTIO_VSOCK_MAX_MRG_BUF_NUM ((VIRTIO_VSOCK_MAX_PKT_BUF_SIZE / PAGE_SIZE) + 1)
>>>>>
>>>>>     /* Virtio-vsock feature */
>>>>>     #define VIRTIO_VSOCK_F_MRG_RXBUF 0 /* Host can merge receive buffers. */
>>>>> @@ -48,6 +50,11 @@ struct virtio_vsock_sock {
>>>>>         struct list_head rx_queue;
>>>>>     };
>>>>>
>>>>> +struct virtio_vsock_mrg_rxbuf {
>>>>> +    void *buf;
>>>>> +    u32 len;
>>>>> +};
>>>>> +
>>>>>     struct virtio_vsock_pkt {
>>>>>         struct virtio_vsock_hdr    hdr;
>>>>>         struct virtio_vsock_mrg_rxbuf_hdr mrg_rxbuf_hdr;
>>>>> @@ -59,6 +66,8 @@ struct virtio_vsock_pkt {
>>>>>         u32 len;
>>>>>         u32 off;
>>>>>         bool reply;
>>>>> +    bool mergeable;
>>>>> +    struct virtio_vsock_mrg_rxbuf mrg_rxbuf[VIRTIO_VSOCK_MAX_MRG_BUF_NUM];
>>>>>     };
>>>> It's better to use iov here I think, and drop buf completely.
>>>>
>>>> And this is better to be done in an independent patch.
>>>>
>>> You're right, I can use kvec instead of customized structure,
>>> in addition, I don't understand about drop buf completely and
>>> an independent patch.
>> I mean there a void *buf in struct virtio_vsock_pkt. You can drop it and switch to use iov(iter) or other data structure that supports sg.
>>
>> Thanks
>>
> Yes, I understand your idea, I don't want to modify tx process method, so I
> keep the buf.
>

I'm afraid this will end of codes that is hard to be maintained. Let's 
try to unify them.

Thanks