[RFC,v1,0/2] send credit update during setting SO_RCVLOWAT

Message

Arseniy Krasnov Nov. 8, 2023, 7:20 a.m. UTC

Hello,

                               DESCRIPTION

This patchset fixes old problem with hungup of both rx/tx sides and adds
test for it. This happens due to non-default SO_RCVLOWAT value and
deferred credit update in virtio/vsock. Link to previous old patchset:
https://lore.kernel.org/netdev/[e-mail]/

Here is what happens step by step:

                                  TEST

                            INITIAL CONDITIONS

1) Vsock buffer size is 128KB.
2) Maximum packet size is also 64KB as defined in header (yes it is
   hardcoded, just to remind about that value).
3) SO_RCVLOWAT is default, e.g. 1 byte.


                                 STEPS

            SENDER                              RECEIVER
1) sends 128KB + 1 byte in a
   single buffer. 128KB will
   be sent, but for 1 byte
   sender will wait for free
   space at peer. Sender goes
   to sleep.


2)                                     reads 64KB, credit update not sent
3)                                     sets SO_RCVLOWAT to 64KB + 1
4)                                     poll() -> wait forever, there is
                                       only 64KB available to read.

So in step 4) receiver also goes to sleep, waiting for enough data or
connection shutdown message from the sender. Idea to fix it is that rx
kicks tx side to continue transmission (and may be close connection)
when rx changes number of bytes to be woken up (e.g. SO_RCVLOWAT) and
this value is bigger than number of available bytes to read.

I've added small test for this, but not sure as it uses hardcoded value
for maximum packet length, this value is defined in kernel header and
used to control deferred credit update. And as this is not available to
userspace, I can't control test parameters correctly (if one day this
define will be changed - test may become useless). 

Head for this patchset is:
https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=ff269e2cd5adce4ae14f883fc9c8803bc43ee1e9

Arseniy Krasnov (2):
  virtio/vsock: send credit update during setting SO_RCVLOWAT
  vsock/test: SO_RCVLOWAT + deferred credit update test

 drivers/vhost/vsock.c                   |   2 +
 include/linux/virtio_vsock.h            |   1 +
 net/vmw_vsock/virtio_transport.c        |   2 +
 net/vmw_vsock/virtio_transport_common.c |  31 ++++++
 net/vmw_vsock/vsock_loopback.c          |   2 +
 tools/testing/vsock/vsock_test.c        | 131 ++++++++++++++++++++++++
 6 files changed, 169 insertions(+)

Comments

Stefano Garzarella Nov. 15, 2023, 11:08 a.m. UTC | #1

On Wed, Nov 08, 2023 at 10:20:02AM +0300, Arseniy Krasnov wrote:
>Hello,
>
>                               DESCRIPTION
>
>This patchset fixes old problem with hungup of both rx/tx sides and adds
>test for it. This happens due to non-default SO_RCVLOWAT value and
>deferred credit update in virtio/vsock. Link to previous old patchset:
>https://lore.kernel.org/netdev/[e-mail]/
>
>Here is what happens step by step:
>
>                                  TEST
>
>                            INITIAL CONDITIONS
>
>1) Vsock buffer size is 128KB.
>2) Maximum packet size is also 64KB as defined in header (yes it is
>   hardcoded, just to remind about that value).
>3) SO_RCVLOWAT is default, e.g. 1 byte.
>
>
>                                 STEPS
>
>            SENDER                              RECEIVER
>1) sends 128KB + 1 byte in a
>   single buffer. 128KB will
>   be sent, but for 1 byte
>   sender will wait for free
>   space at peer. Sender goes
>   to sleep.
>
>
>2)                                     reads 64KB, credit update not sent
>3)                                     sets SO_RCVLOWAT to 64KB + 1
>4)                                     poll() -> wait forever, there is
>                                       only 64KB available to read.
>
>So in step 4) receiver also goes to sleep, waiting for enough data or
>connection shutdown message from the sender. Idea to fix it is that rx
>kicks tx side to continue transmission (and may be close connection)
>when rx changes number of bytes to be woken up (e.g. SO_RCVLOWAT) and
>this value is bigger than number of available bytes to read.
>
>I've added small test for this, but not sure as it uses hardcoded value

Thanks for adding the test!

>for maximum packet length, this value is defined in kernel header and
>used to control deferred credit update. And as this is not available to
>userspace, I can't control test parameters correctly (if one day this
>define will be changed - test may become useless).

I see, I'll leave a comment in the patch!

Thanks,
Stefano

>
>Head for this patchset is:
>https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=ff269e2cd5adce4ae14f883fc9c8803bc43ee1e9
>
>Arseniy Krasnov (2):
>  virtio/vsock: send credit update during setting SO_RCVLOWAT
>  vsock/test: SO_RCVLOWAT + deferred credit update test
>
> drivers/vhost/vsock.c                   |   2 +
> include/linux/virtio_vsock.h            |   1 +
> net/vmw_vsock/virtio_transport.c        |   2 +
> net/vmw_vsock/virtio_transport_common.c |  31 ++++++
> net/vmw_vsock/vsock_loopback.c          |   2 +
> tools/testing/vsock/vsock_test.c        | 131 ++++++++++++++++++++++++
> 6 files changed, 169 insertions(+)
>
>-- 
>2.25.1
>