Re: [PATCH v8 7/8] vhost-user: add vhost-user

[Stefano Brivio <sbrivio@redhat.com>]

On Thu, 17 Oct 2024 02:10:31 +0200
Stefano Brivio <sbrivio@redhat.com> wrote:

> On Wed, 16 Oct 2024 11:41:34 +1100
> David Gibson <david@gibson.dropbear.id.au> wrote:
> 
> > On Tue, Oct 15, 2024 at 09:54:38PM +0200, Stefano Brivio wrote:  
> > > [Still partial review]    
> > [snip]  
> > > > +	if (peek_offset_cap)
> > > > +		already_sent = 0;
> > > > +
> > > > +	iov_vu[0].iov_base = tcp_buf_discard;
> > > > +	iov_vu[0].iov_len = already_sent;    
> > > 
> > > I think I had a similar comment to a previous revision. Now, I haven't
> > > tested this (yet) on a kernel with support for SO_PEEK_OFF on TCP, but
> > > I think this should eventually follow the same logic as the (updated)
> > > tcp_buf_data_from_sock(): we should use tcp_buf_discard only if
> > > (!peek_offset_cap).
> > > 
> > > It's fine to always initialise VIRTQUEUE_MAX_SIZE iov_vu items,
> > > starting from 1, for simplicity. But I'm not sure if it's safe to pass a
> > > zero iov_len if (peek_offset_cap).    
> >   
> > > I'll test that (unless you already did) -- if it works, we can fix this
> > > up later as well.    
> > 
> > I believe I tested it at some point, and I think we're already using
> > it somewhere.  
> 
> I tested it again just to be sure on a recent net.git kernel: sometimes
> the first test in passt_vu_in_ns/tcp, "TCP/IPv4: host to guest: big
> transfer" hangs on my setup, sometimes it's the "TCP/IPv4: ns to guest
> (using loopback address): big transfer" test instead.
> 
> I can reproduce at least one of the two issues consistently (tests
> stopped 5 times out of 5).
> 
> The socat client completes the transfer, the server is still waiting
> for something. I haven't taken captures yet or tried to re-send from
> the client.

...Laurent, let me know if I should dig into this any further.

For reference, the kernel commit introducing SO_PEEK_OFF support for TCP
on IPv6 is be9a4fb831b8 ("tcp: add SO_PEEK_OFF socket option tor
TCPv6"). Without that commit, passt won't set peek_offset_cap.

It was added in 6.11-rc5, so it's part of kernel-6.11.3-200.fc40 (latest
stable kernel) for Fedora 40. passt will print "SO_PEEK_OFF supported"
if you run it with -d -f.

-- 
Stefano