Re: [REGRESSION] Massive virtio-net throughput drop in guest VM with Linux 6.8+

[Markus Fohrer]

Am Freitag, dem 04.04.2025 um 10:52 +0200 schrieb Markus Fohrer:
> Am Freitag, dem 04.04.2025 um 04:29 -0400 schrieb Michael S. Tsirkin:
> > On Fri, Apr 04, 2025 at 10:16:55AM +0200, Markus Fohrer wrote:
> > > Am Donnerstag, dem 03.04.2025 um 09:04 -0400 schrieb Michael S.
> > > Tsirkin:
> > > > On Wed, Apr 02, 2025 at 11:12:07PM +0200, Markus Fohrer wrote:
> > > > > Hi,
> > > > > 
> > > > > I'm observing a significant performance regression in KVM
> > > > > guest
> > > > > VMs
> > > > > using virtio-net with recent Linux kernels (6.8.1+ and 6.14).
> > > > > 
> > > > > When running on a host system equipped with a Broadcom
> > > > > NetXtreme-E
> > > > > (bnxt_en) NIC and AMD EPYC CPUs, the network throughput in
> > > > > the
> > > > > guest drops to 100–200 KB/s. The same guest configuration
> > > > > performs
> > > > > normally (~100 MB/s) when using kernel 6.8.0 or when the VM
> > > > > is
> > > > > moved to a host with Intel NICs.
> > > > > 
> > > > > Test environment:
> > > > > - Host: QEMU/KVM, Linux 6.8.1 and 6.14.0
> > > > > - Guest: Linux with virtio-net interface
> > > > > - NIC: Broadcom BCM57416 (bnxt_en driver, no issues at host
> > > > > level)
> > > > > - CPU: AMD EPYC
> > > > > - Storage: virtio-scsi
> > > > > - VM network: virtio-net, virtio-scsi (no CPU or IO
> > > > > bottlenecks)
> > > > > - Traffic test: iperf3, scp, wget consistently slow in guest
> > > > > 
> > > > > This issue is not present:
> > > > > - On 6.8.0 
> > > > > - On hosts with Intel NICs (same VM config)
> > > > > 
> > > > > I have bisected the issue to the following upstream commit:
> > > > > 
> > > > >   49d14b54a527 ("virtio-net: Suppress tx timeout warning for
> > > > > small
> > > > > tx")
> > > > >   https://git.kernel.org/linus/49d14b54a527
> > > > 
> > > > Thanks a lot for the info!
> > > > 
> > > > 
> > > > both the link and commit point at:
> > > > 
> > > > commit 49d14b54a527289d09a9480f214b8c586322310a
> > > > Author: Eric Dumazet <edumazet@xxxxxxxxxx>
> > > > Date:   Thu Sep 26 16:58:36 2024 +0000
> > > > 
> > > >     net: test for not too small csum_start in
> > > > virtio_net_hdr_to_skb()
> > > >     
> > > > 
> > > > is this what you mean?
> > > > 
> > > > I don't know which commit is "virtio-net: Suppress tx timeout
> > > > warning
> > > > for small tx"
> > > > 
> > > > 
> > > > 
> > > > > Reverting this commit restores normal network performance in
> > > > > affected guest VMs.
> > > > > 
> > > > > I’m happy to provide more data or assist with testing a
> > > > > potential
> > > > > fix.
> > > > > 
> > > > > Thanks,
> > > > > Markus Fohrer
> > > > 
> > > > 
> > > > Thanks! First I think it's worth checking what is the setup,
> > > > e.g.
> > > > which offloads are enabled.
> > > > Besides that, I'd start by seeing what's doing on. Assuming I'm
> > > > right
> > > > about
> > > > Eric's patch:
> > > > 
> > > > diff --git a/include/linux/virtio_net.h
> > > > b/include/linux/virtio_net.h
> > > > index 276ca543ef44d8..02a9f4dc594d02 100644
> > > > --- a/include/linux/virtio_net.h
> > > > +++ b/include/linux/virtio_net.h
> > > > @@ -103,8 +103,10 @@ static inline int
> > > > virtio_net_hdr_to_skb(struct
> > > > sk_buff *skb,
> > > >  
> > > >  		if (!skb_partial_csum_set(skb, start, off))
> > > >  			return -EINVAL;
> > > > +		if (skb_transport_offset(skb) < nh_min_len)
> > > > +			return -EINVAL;
> > > >  
> > > > -		nh_min_len = max_t(u32, nh_min_len,
> > > > skb_transport_offset(skb));
> > > > +		nh_min_len = skb_transport_offset(skb);
> > > >  		p_off = nh_min_len + thlen;
> > > >  		if (!pskb_may_pull(skb, p_off))
> > > >  			return -EINVAL;
> > > > 
> > > > 
> > > > sticking a printk before return -EINVAL to show the offset and
> > > > nh_min_len
> > > > would be a good 1st step. Thanks!
> > > > 
> > > 
> > > I added the following printk inside virtio_net_hdr_to_skb():
> > > 
> > >     if (skb_transport_offset(skb) < nh_min_len){
> > >         printk(KERN_INFO "virtio_net: 3 drop,
> > > transport_offset=%u,
> > > nh_min_len=%u\n",
> > >                skb_transport_offset(skb), nh_min_len);
> > >         return -EINVAL;
> > >     }
> > > 
> > > Built and installed the kernel, then triggered a large download
> > > via:
> > > 
> > >     wget http://speedtest.belwue.net/10G
> > > 
> > > Relevant output from `dmesg -w`:
> > > 
> > > [   57.327943] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.428942] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.428962] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.553068] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.553088] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.576678] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.618438] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.618453] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.703077] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.823072] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.891982] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   57.946190] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > > [   58.218686] virtio_net: 3 drop, transport_offset=34,
> > > nh_min_len=40  
> > 
> > Hmm indeed. And what about these values?
> >                 u32 start = __virtio16_to_cpu(little_endian, hdr-
> > > csum_start);
> >                 u32 off = __virtio16_to_cpu(little_endian, hdr-
> > > csum_offset);
> >                 u32 needed = start + max_t(u32, thlen, off +
> > sizeof(__sum16));
> > print them too?
> > 
> > 
> > 
> > > I would now do the test with commit
> > > 49d14b54a527289d09a9480f214b8c586322310a and commit
> > > 49d14b54a527289d09a9480f214b8c586322310a~1
> > > 
> > 
> > Worth checking though it seems likely now the hypervisor is doing
> > weird
> > things. what kind of backend is it? qemu? tun? vhost-user? vhost-
> > net?
> > 
> 
> Backend: QEMU/KVM hypervisor (Proxmox)
> 
> 
> printk output:
> 
> [   58.641906] virtio_net: drop, transport_offset=34  start=34,
> off=16,
> needed=54, nh_min_len=40
> [   58.678048] virtio_net: drop, transport_offset=34  start=34,
> off=16,
> needed=54, nh_min_len=40
> [   58.952871] virtio_net: drop, transport_offset=34  start=34,
> off=16,
> needed=54, nh_min_len=40
> [   58.962157] virtio_net: drop, transport_offset=34  start=34,
> off=16,
> needed=54, nh_min_len=40
> [   59.071645] virtio_net: drop, transport_offset=34  start=34,
> off=16,
> needed=54, nh_min_len=40
> 
> 
> 
> 
> 

I just noticed that commit 17bd3bd82f9f79f3feba15476c2b2c95a9b11ff8
(tcp_offload.c: gso fix) also touches checksum handling and may
affect how skb state is passed to virtio_net_hdr_to_skb().

Is it possible that the regression only appears due to the combination
of 17bd3bd8 and 49d14b54a5?