Re: [PATCH net v3 1/8] net: account for ingress-resolved virtio net hdr state

[Willem de Bruijn]

Michael S. Tsirkin wrote:
> On Tue, Oct 20, 2026 at 03:27:46PM -0400, Willem de Bruijn wrote:
> > Michael S. Tsirkin wrote:
> > > The following patch will add ingress resolution of uncommon virtio net
> > > hdr checksum metadata (software checksum completion at ingress) which
> > > adds performance overhead to the packet processing.
> > > 
> > > We should make it visible, so a hypothetical workload relying on
> > > uncommon metadata can be distinguished from none at all. This way issues
> > > in the parsing will be reported and not quietly pay the host-CPU
> > > checksum overhead instead of offload.
> > > 
> > > Flip every call to virtio_net_hdr_to_skb to test for negative errno
> > > only, and have tun count these events per device as rx_csum_sw, exposed
> > > via ethtool -S.
> > > 
> > > Assisted-by: LLM
> > > Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
> > > ---
> > >  drivers/net/tap.c        |  4 ++--
> > >  drivers/net/tun.c        | 41 ++++++++++++++++++++++++++++++++++++++--
> > >  drivers/net/virtio_net.c |  2 +-
> > >  net/packet/af_packet.c   |  4 ++--
> > >  4 files changed, 44 insertions(+), 7 deletions(-)
> > > 
> > > diff --git a/drivers/net/tap.c b/drivers/net/tap.c
> > > index ff67d99deb39..73e883394446 100644
> > > --- a/drivers/net/tap.c
> > > +++ b/drivers/net/tap.c
> > > @@ -649,7 +649,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
> > >  
> > >  	if (vnet_hdr_len) {
> > >  		err = tun_vnet_hdr_to_skb(q->flags, skb, &vnet_hdr);
> > > -		if (err) {
> > > +		if (err < 0) {
> > >  			rcu_read_unlock();
> > >  			drop_reason = SKB_DROP_REASON_DEV_HDR;
> > >  			goto err_kfree;
> > > @@ -1084,7 +1084,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
> > >  
> > >  	if (vnet_hdr_len) {
> > >  		err = tun_vnet_hdr_to_skb(q->flags, skb, gso);
> > > -		if (err) {
> > > +		if (err < 0) {
> > >  			rcu_read_unlock();
> > >  			goto err_kfree;
> > >  		}
> > 
> > similar to tun, should tap count this event?
> > 
> > > diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> > > index 242899f7fd07..19cb443c89b0 100644
> > > --- a/drivers/net/tun.c
> > > +++ b/drivers/net/tun.c
> > > @@ -210,6 +210,7 @@ struct tun_struct {
> > >  	u32 flow_count;
> > >  	u32 rx_batched;
> > >  	atomic_long_t rx_frame_errors;
> > > +	atomic64_t rx_csum_sw;
> > 
> > is a normal (and cheaper on 32b platforms) atomic_t or atomic_long_t sufficient?
> 
> well it can overflow easily. i don't know that we care that a slow
> path will be even a bit slower on these ancient platforms. correct
> reporting seems more important.

Ok. I would hope that monitoring catches this before it hits 4B, but
agreed that as slow path it doesn't matter.

> 
> > >  	struct bpf_prog __rcu *xdp_prog;
> > >  	struct tun_prog __rcu *steering_prog;
> > >  	struct tun_prog __rcu *filter_prog;
> > > @@ -1935,11 +1936,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
> > >  		break;
> > >  	}
> > >  
> > > -	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) {
> > > +	err = tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr);
> > > +	if (err < 0) {
> > >  		atomic_long_inc(&tun->rx_frame_errors);
> > >  		err = -EINVAL;
> > >  		goto free_skb;
> > >  	}
> > > +	if (err > 0) {
> > 
> > } else if (err > 0) {
> > 
> > > +		atomic64_inc(&tun->rx_csum_sw);
> > > +		err = 0;
> > > +	}
> > >  
> > >  	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP)
> > >  		skb->protocol = eth_type_trans(skb, tun->dev);
> > > @@ -2605,12 +2611,15 @@ static int tun_xdp_one(struct tun_struct *tun,
> > >  	tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso;
> > >  	skb->dev = tun->dev;
> > >  	skb_set_network_header(skb, ETH_HLEN);
> > > -	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) {
> > > +	ret = tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr);
> > > +	if (ret < 0) {
> > >  		atomic_long_inc(&tun->rx_frame_errors);
> > >  		kfree_skb(skb);
> > >  		ret = -EINVAL;
> > >  		goto out;
> > >  	}
> > > +	if (ret > 0)
> > 
> > same
> > 
> > > +		atomic64_inc(&tun->rx_csum_sw);
> > 
> > maybe reset ret = 0 in all these branches
> > 
> > >  
> > >  	skb->protocol = eth_type_trans(skb, tun->dev);
> > >  	skb_reset_network_header(skb);
> > > @@ -3739,7 +3748,35 @@ static void tun_get_channels(struct net_device *dev,
> > >  	channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1;
> > >  }
> > >  
> > > +#define TUN_STATS_LEN	1
> > > +static const char tun_ethtool_strings[TUN_STATS_LEN][ETH_GSTRING_LEN] = {
> > > +	"rx_csum_sw",
> > > +};
> > > +
> > > +static int tun_get_sset_count(struct net_device *dev, int sset)
> > > +{
> > > +	return sset == ETH_SS_STATS ? TUN_STATS_LEN : -EOPNOTSUPP;
> > > +}
> > > +
> > > +static void tun_get_strings(struct net_device *dev, u32 stringset, u8 *data)
> > > +{
> > > +	if (stringset == ETH_SS_STATS)
> > > +		memcpy(data, tun_ethtool_strings,
> > > +		       sizeof(tun_ethtool_strings));
> > > +}
> > > +
> > > +static void tun_get_ethtool_stats(struct net_device *dev,
> > > +				  struct ethtool_stats *stats, u64 *data)
> > > +{
> > > +	struct tun_struct *tun = netdev_priv(dev);
> > > +
> > > +	data[0] = atomic64_read(&tun->rx_csum_sw);
> > > +}
> > > +
> > >  static const struct ethtool_ops tun_ethtool_ops = {
> > > +	.get_sset_count		= tun_get_sset_count,
> > > +	.get_strings		= tun_get_strings,
> > > +	.get_ethtool_stats	= tun_get_ethtool_stats,
> > >  	.supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES,
> > >  	.get_drvinfo	= tun_get_drvinfo,
> > >  	.get_msglevel	= tun_get_msglevel,
> > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > index daab43ac92ce..2e6fd81df9c4 100644
> > > --- a/drivers/net/virtio_net.c
> > > +++ b/drivers/net/virtio_net.c
> > > @@ -2519,7 +2519,7 @@ static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *
> > >  	skb_set_network_header(skb, ETH_HLEN);
> > >  	if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl,
> > >  				      vi->rx_tnl_csum,
> > > -				      virtio_is_little_endian(vi->vdev))) {
> > > +				      virtio_is_little_endian(vi->vdev)) < 0) {
> > >  		net_warn_ratelimited("%s: bad gso: type: %x, size: %u, flags %x tunnel %d tnl csum %d\n",
> > >  				     dev->name, hdr->hdr.gso_type,
> > >  				     hdr->hdr.gso_size, hdr->hdr.flags,
> > 
> > should virtio_net count these too? Or do we assume that devices are
> > more trustworthy, so unlikely to cause this issue?
> 
> With memory encryption, from an untrusted host?
> i can add that.

I honestly don't know if it's worth the effort. Just curious whether
you had purposely skipped this and tap.
> 
> > > diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> > > index 52ae3d875e97..e6aec9ecfa99 100644
> > > --- a/net/packet/af_packet.c
> > > +++ b/net/packet/af_packet.c
> > > @@ -2913,7 +2913,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
> > >  		}
> > >  
> > >  		if (has_vnet_hdr) {
> > > -			if (virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le())) {
> > > +			if (virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()) < 0) {
> > >  				tp_len = -EINVAL;
> > >  				goto tpacket_error;
> > >  			}
> > > @@ -3136,7 +3136,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
> > >  
> > >  	if (vnet_hdr_sz) {
> > >  		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
> > > -		if (err)
> > > +		if (err < 0)
> > >  			goto out_free;
> > >  		len += vnet_hdr_sz;
> > >  	}
> > > -- 
> > > MST
> > > 
> > 
>