Message-ID: <8687bc31-92a7-8ff4-168f-f194180d0cbf@salutedevices.com>
Date: Mon, 11 Dec 2023 14:58:49 +0300
From: Arseniy Krasnov <avkrasnov@...utedevices.com>
To: Stefano Garzarella <sgarzare@...hat.com>
CC: "Michael S. Tsirkin" <mst@...hat.com>, 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>, Jason Wang <jasowang@...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: [PATCH net-next v7 3/4] virtio/vsock: fix logic which reduces
 credit update messages



On 11.12.2023 15:01, Stefano Garzarella wrote:
> On Thu, Dec 07, 2023 at 01:50:05AM +0300, Arseniy Krasnov wrote:
>>
>>
>> On 07.12.2023 01:08, Michael S. Tsirkin wrote:
>>> On Thu, Dec 07, 2023 at 12:52:51AM +0300, Arseniy Krasnov wrote:
>>>>
>>>>
>>>> On 07.12.2023 00:53, Michael S. Tsirkin wrote:
>>>>> On Thu, Dec 07, 2023 at 12:18:48AM +0300, Arseniy Krasnov wrote:
>>>>>> Add one more condition for sending credit update during dequeue from
>>>>>> stream socket: when number of bytes in the rx queue is smaller than
>>>>>> SO_RCVLOWAT value of the socket. This is actual for non-default value
>>>>>> of SO_RCVLOWAT (e.g. not 1) - idea is to "kick" peer to continue data
>>>>>> transmission, because we need at least SO_RCVLOWAT bytes in our rx
>>>>>> queue to wake up user for reading data (in corner case it is also
>>>>>> possible to stuck both tx and rx sides, this is why 'Fixes' is used).
>>>>>> Also handle case when 'fwd_cnt' wraps, while 'last_fwd_cnt' is still
>>>>>> not.
>>>>>>
>>>>>> Fixes: b89d882dc9fc ("vsock/virtio: reduce credit update messages")
>>>>>> Signed-off-by: Arseniy Krasnov <avkrasnov@...utedevices.com>
>>>>>> ---
>>>>>>  Changelog:
>>>>>>  v6 -> v7:
>>>>>>   * Handle wrap of 'fwd_cnt'.
>>>>>>   * Do to send credit update when 'fwd_cnt' == 'last_fwd_cnt'.
>>>>>>
>>>>>>  net/vmw_vsock/virtio_transport_common.c | 18 +++++++++++++++---
>>>>>>  1 file changed, 15 insertions(+), 3 deletions(-)
>>>>>>
>>>>>> diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
>>>>>> index e137d740804e..39f8660d825d 100644
>>>>>> --- a/net/vmw_vsock/virtio_transport_common.c
>>>>>> +++ b/net/vmw_vsock/virtio_transport_common.c
>>>>>> @@ -558,6 +558,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
>>>>>>      struct virtio_vsock_sock *vvs = vsk->trans;
>>>>>>      size_t bytes, total = 0;
>>>>>>      struct sk_buff *skb;
>>>>>> +    u32 fwd_cnt_delta;
>>>>>> +    bool low_rx_bytes;
>>>>>>      int err = -EFAULT;
>>>>>>      u32 free_space;
>>>>>>
>>>>>> @@ -601,7 +603,15 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
>>>>>>          }
>>>>>>      }
>>>>>>
>>>>>> -    free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt);
>>>>>> +    /* Handle wrap of 'fwd_cnt'. */
>>>>>> +    if (vvs->fwd_cnt < vvs->last_fwd_cnt)
>>>>>> +        fwd_cnt_delta = vvs->fwd_cnt + (U32_MAX - vvs->last_fwd_cnt);
>>>>>
>>>>> Are you sure there's no off by one here? for example if fwd_cnt is 0
>>>>> and last_fwd_cnt is 0xfffffffff then apparently delta is 0.
>>>>
>>>> Seems yes, I need +1 here
>>>
>>> And then you will get a nop, because assigning U32_MAX + 1 to u32
>>> gives you 0. Adding () does nothing to change the result,
>>> + and - are commutative.
>>
>> Ahh, unsigned here, yes.
> 
> Ooops, sorry I was confused here!
> 
>>
>> @Stefano, what did You mean about wrapping here?
>>
>> I think Michael is right, for example
> 
> Yep, I agree!
> Sorry for this wrong suggestion!

Got it! I'll remove it, no problem 

Thanks, Arseniy

> 
> Stefano
> 
>>
>> vvs->fwd_cnt wraps and now == 5
>> vvs->last_fwd_cnt == 0xffffffff
>>
>> now delta before this patch will be 6 - correct value
>>
>> May be I didn't get your idea, so implement it very naive?
>>
>> Thanks, Arseniy
>>
>>>
>>>
>>>>>
>>>>>
>>>>>> +    else
>>>>>> +        fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt;
>>>>>
>>>>> I actually don't see what is wrong with just
>>>>>     fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt
>>>>> 32 bit unsigned math will I think handle wrap around correctly.
>>>>>
>>>>> And given buf_alloc is also u32 - I don't see where the bug is in
>>>>> the original code.
>>>>
>>>> I think problem is when fwd_cnt wraps, while last_fwd_cnt is not. In this
>>>> case fwd_cnt_delta will be too big, so we won't send credit update which
>>>> leads to stall for sender
>>>>
>>>> Thanks, Arseniy
>>>
>>> Care coming up with an example?
>>>
>>>
>>>>>
>>>>>
>>>>>> +
>>>>>> +    free_space = vvs->buf_alloc - fwd_cnt_delta;
>>>>>> +    low_rx_bytes = (vvs->rx_bytes <
>>>>>> +            sock_rcvlowat(sk_vsock(vsk), 0, INT_MAX));
>>>>>>
>>>>>>      spin_unlock_bh(&vvs->rx_lock);
>>>>>>
>>>>>> @@ -611,9 +621,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
>>>>>>       * too high causes extra messages. Too low causes transmitter
>>>>>>       * stalls. As stalls are in theory more expensive than extra
>>>>>>       * messages, we set the limit to a high value. TODO: experiment
>>>>>> -     * with different values.
>>>>>> +     * with different values. Also send credit update message when
>>>>>> +     * number of bytes in rx queue is not enough to wake up reader.
>>>>>>       */
>>>>>> -    if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
>>>>>> +    if (fwd_cnt_delta &&
>>>>>> +        (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || low_rx_bytes))
>>>>>>          virtio_transport_send_credit_update(vsk);
>>>>>>
>>>>>>      return total;
>>>>>> -- 
>>>>>> 2.25.1
>>>>>
>>>
>>
> 

Powered by blists - more mailing lists