Message-ID: <2be688af-89a6-d903-017b-dafee3e48c33@sberdevices.ru>
Date:   Mon, 20 Mar 2023 21:02:19 +0300
From:   Arseniy Krasnov <avkrasnov@...rdevices.ru>
To:     Stefano Garzarella <sgarzare@...hat.com>
CC:     Stefan Hajnoczi <stefanha@...hat.com>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>,
        Bobby Eshleman <bobby.eshleman@...edance.com>,
        <kvm@...r.kernel.org>, <virtualization@...ts.linux-foundation.org>,
        <netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <kernel@...rdevices.ru>, <oxffffaa@...il.com>
Subject: Re: [RFC PATCH v2] virtio/vsock: allocate multiple skbuffs on tx



On 20.03.2023 17:29, Stefano Garzarella wrote:
> On Sun, Mar 19, 2023 at 09:46:10PM +0300, Arseniy Krasnov wrote:
>> This adds small optimization for tx path: instead of allocating single
>> skbuff on every call to transport, allocate multiple skbuff's until
>> credit space allows, thus trying to send as much as possible data without
>> return to af_vsock.c.
>>
>> Signed-off-by: Arseniy Krasnov <AVKrasnov@...rdevices.ru>
>> ---
>> Link to v1:
>> https://lore.kernel.org/netdev/2c52aa26-8181-d37a-bccd-a86bd3cbc6e1@sberdevices.ru/
>>
>> Changelog:
>> v1 -> v2:
>> - If sent something, return number of bytes sent (even in
>>   case of error). Return error only if failed to sent first
>>   skbuff.
>>
>> net/vmw_vsock/virtio_transport_common.c | 53 ++++++++++++++++++-------
>> 1 file changed, 39 insertions(+), 14 deletions(-)
>>
>> diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
>> index 6564192e7f20..3fdf1433ec28 100644
>> --- a/net/vmw_vsock/virtio_transport_common.c
>> +++ b/net/vmw_vsock/virtio_transport_common.c
>> @@ -196,7 +196,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
>>     const struct virtio_transport *t_ops;
>>     struct virtio_vsock_sock *vvs;
>>     u32 pkt_len = info->pkt_len;
>> -    struct sk_buff *skb;
>> +    u32 rest_len;
>> +    int ret;
>>
>>     info->type = virtio_transport_get_type(sk_vsock(vsk));
>>
>> @@ -216,10 +217,6 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
>>
>>     vvs = vsk->trans;
>>
>> -    /* we can send less than pkt_len bytes */
>> -    if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
>> -        pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
>> -
>>     /* virtio_transport_get_credit might return less than pkt_len credit */
>>     pkt_len = virtio_transport_get_credit(vvs, pkt_len);
>>
>> @@ -227,17 +224,45 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
>>     if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW)
>>         return pkt_len;
>>
>> -    skb = virtio_transport_alloc_skb(info, pkt_len,
>> -                     src_cid, src_port,
>> -                     dst_cid, dst_port);
>> -    if (!skb) {
>> -        virtio_transport_put_credit(vvs, pkt_len);
>> -        return -ENOMEM;
>> -    }
>> +    ret = 0;
>> +    rest_len = pkt_len;
>> +
>> +    do {
>> +        struct sk_buff *skb;
>> +        size_t skb_len;
>> +
>> +        skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, rest_len);
>> +
>> +        skb = virtio_transport_alloc_skb(info, skb_len,
>> +                         src_cid, src_port,
>> +                         dst_cid, dst_port);
>> +        if (!skb) {
>> +            ret = -ENOMEM;
>> +            break;
>> +        }
>> +
>> +        virtio_transport_inc_tx_pkt(vvs, skb);
>> +
>> +        ret = t_ops->send_pkt(skb);
>> +
>> +        if (ret < 0)
>> +            break;
>>
>> -    virtio_transport_inc_tx_pkt(vvs, skb);
>> +        rest_len -= skb_len;
> 
> t_ops->send_pkt() is returning the number of bytes sent. Current
> implementations always return `skb_len`, so there should be no problem,
> but it would be better to put a comment here, or we should handle the
> case where ret != skb_len to avoid future issues.

Hello, thanks for review!

I see. I think i'll handle such partial sends (ret != skb_len) as error, as
it is the only thing to do - we remove 'skb_len' from user's buffer, but
'send_pkt()' returns another value, so it will be strange for me to continue
this tx loop as everything is ok. Something like this:
+ 
+ if (ret < 0)
+    break;
+ 
+ if (ret != skb_len) {
+    ret = -EFAULT;//or may be -EIO
+    break;
+ }

> 
>> +    } while (rest_len);
>>
>> -    return t_ops->send_pkt(skb);
>> +    /* Don't call this function with zero as argument:
>> +     * it tries to acquire spinlock and such argument
>> +     * makes this call useless.
> 
> Good point, can we do the same also for virtio_transport_get_credit()?
> (Maybe in a separate patch)
> 
> I'm thinking if may be better to do it directly inside the functions,
> but I don't have a strong opinion on that since we only call them here.
> 

I think in this patch i can call 'virtio_transport_put_credit()' without if, but
i'll prepare separate patch which adds zero argument check to this function.
As i see, the only function suitable for such 'if' condition is 'virtio_transport_put_credit()'.
Anyway - for future use this check won't be bad.

Thanks, Arseniy

> Thanks,
> Stefano
> 
>> +     */
>> +    if (rest_len)
>> +        virtio_transport_put_credit(vvs, rest_len);
>> +
>> +    /* Return number of bytes, if any data has been sent. */
>> +    if (rest_len != pkt_len)
>> +        ret = pkt_len - rest_len;
>> +
>> +    return ret;
>> }
>>
>> static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
>> -- 
>> 2.25.1
>>
> 

Powered by blists - more mailing lists