Date:	Wed, 19 Nov 2014 11:14:55 +0200
From:	"Michael S. Tsirkin" <mst@...hat.com>
To:	Ben Hutchings <ben@...adent.org.uk>
Cc:	netdev@...r.kernel.org,
	Hannes Frederic Sowa <hannes@...essinduktion.org>,
	virtualization@...ts.linux-foundation.org
Subject: Re: [PATCH v2 net 1/2] drivers/net: Disable UFO through virtio

On Thu, Oct 30, 2014 at 06:27:12PM +0000, Ben Hutchings wrote:
> IPv6 does not allow fragmentation by routers, so there is no
> fragmentation ID in the fixed header.  UFO for IPv6 requires the ID to
> be passed separately, but there is no provision for this in the virtio
> net protocol.
> 
> Until recently our software implementation of UFO/IPv6 generated a new
> ID, but this was a bug.  Now we will use ID=0 for any UFO/IPv6 packet
> passed through a tap, which is even worse.
> 
> Unfortunately there is no distinction between UFO/IPv4 and v6
> features, so disable UFO on taps and virtio_net completely until we
> have a proper solution.
> 
> We cannot depend on VM managers respecting the tap feature flags, so
> keep accepting UFO packets but log a warning the first time we do
> this.
> 
> Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
> Fixes: 916e4cf46d02 ("ipv6: reuse ip6_frag_id from ip6_ufo_append_data")


There's something I don't understand here. I see:

        NETIF_F_UFO_BIT,                /* ... UDPv4 fragmentation */

this comment is wrong then?

The patches drastically regress performance for UDPv4 for VMs only, but
isn't it likely many other devices based their code on this comment?

How about we disable UFO for IPv6 globally, and put the
flag back in?
We can then gradually add NETIF_F_UFO6_BIT for devices that
actually support UFO for IPv6.

Thoughts?



> ---
>  drivers/net/macvtap.c    | 13 +++++--------
>  drivers/net/tun.c        | 19 +++++++++++--------
>  drivers/net/virtio_net.c | 24 ++++++++++++++----------
>  3 files changed, 30 insertions(+), 26 deletions(-)
> 
> diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
> index 65e2892..2aeaa61 100644
> --- a/drivers/net/macvtap.c
> +++ b/drivers/net/macvtap.c
> @@ -65,7 +65,7 @@ static struct cdev macvtap_cdev;
>  static const struct proto_ops macvtap_socket_ops;
>  
>  #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
> -		      NETIF_F_TSO6 | NETIF_F_UFO)
> +		      NETIF_F_TSO6)
>  #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
>  #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
>  
> @@ -569,6 +569,8 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
>  			gso_type = SKB_GSO_TCPV6;
>  			break;
>  		case VIRTIO_NET_HDR_GSO_UDP:
> +			pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n",
> +				     current->comm);
>  			gso_type = SKB_GSO_UDP;
>  			break;
>  		default:
> @@ -614,8 +616,6 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
>  			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
>  		else if (sinfo->gso_type & SKB_GSO_TCPV6)
>  			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
> -		else if (sinfo->gso_type & SKB_GSO_UDP)
> -			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
>  		else
>  			BUG();
>  		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
> @@ -950,9 +950,6 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg)
>  			if (arg & TUN_F_TSO6)
>  				feature_mask |= NETIF_F_TSO6;
>  		}
> -
> -		if (arg & TUN_F_UFO)
> -			feature_mask |= NETIF_F_UFO;
>  	}
>  
>  	/* tun/tap driver inverts the usage for TSO offloads, where
> @@ -963,7 +960,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg)
>  	 * When user space turns off TSO, we turn off GSO/LRO so that
>  	 * user-space will not receive TSO frames.
>  	 */
> -	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO))
> +	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6))
>  		features |= RX_OFFLOADS;
>  	else
>  		features &= ~RX_OFFLOADS;
> @@ -1064,7 +1061,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
>  	case TUNSETOFFLOAD:
>  		/* let the user check for future flags */
>  		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
> -			    TUN_F_TSO_ECN | TUN_F_UFO))
> +			    TUN_F_TSO_ECN))
>  			return -EINVAL;
>  
>  		rtnl_lock();
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index 186ce54..280d3d2 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -174,7 +174,7 @@ struct tun_struct {
>  	struct net_device	*dev;
>  	netdev_features_t	set_features;
>  #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
> -			  NETIF_F_TSO6|NETIF_F_UFO)
> +			  NETIF_F_TSO6)
>  
>  	int			vnet_hdr_sz;
>  	int			sndbuf;
> @@ -1149,8 +1149,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
>  			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
>  			break;
>  		case VIRTIO_NET_HDR_GSO_UDP:
> +		{
> +			static bool warned;
> +
> +			if (!warned) {
> +				warned = true;
> +				netdev_warn(tun->dev,
> +					    "%s: using disabled UFO feature; please fix this program\n",
> +					    current->comm);
> +			}
>  			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
>  			break;
> +		}
>  		default:
>  			tun->dev->stats.rx_frame_errors++;
>  			kfree_skb(skb);
> @@ -1251,8 +1261,6 @@ static ssize_t tun_put_user(struct tun_struct *tun,
>  				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
>  			else if (sinfo->gso_type & SKB_GSO_TCPV6)
>  				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
> -			else if (sinfo->gso_type & SKB_GSO_UDP)
> -				gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
>  			else {
>  				pr_err("unexpected GSO type: "
>  				       "0x%x, gso_size %d, hdr_len %d\n",
> @@ -1762,11 +1770,6 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
>  				features |= NETIF_F_TSO6;
>  			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
>  		}
> -
> -		if (arg & TUN_F_UFO) {
> -			features |= NETIF_F_UFO;
> -			arg &= ~TUN_F_UFO;
> -		}
>  	}
>  
>  	/* This gives the user a way to test for new features in future by
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index d75256bd..ec2a8b4 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -491,8 +491,17 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
>  			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
>  			break;
>  		case VIRTIO_NET_HDR_GSO_UDP:
> +		{
> +			static bool warned;
> +
> +			if (!warned) {
> +				warned = true;
> +				netdev_warn(dev,
> +					    "host using disabled UFO feature; please fix it\n");
> +			}
>  			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
>  			break;
> +		}
>  		case VIRTIO_NET_HDR_GSO_TCPV6:
>  			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
>  			break;
> @@ -881,8 +890,6 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
>  			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
>  		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
>  			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
> -		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
> -			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
>  		else
>  			BUG();
>  		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
> @@ -1705,7 +1712,7 @@ static int virtnet_probe(struct virtio_device *vdev)
>  			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
>  
>  		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
> -			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
> +			dev->hw_features |= NETIF_F_TSO
>  				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
>  		}
>  		/* Individual feature bits: what can host handle? */
> @@ -1715,11 +1722,9 @@ static int virtnet_probe(struct virtio_device *vdev)
>  			dev->hw_features |= NETIF_F_TSO6;
>  		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
>  			dev->hw_features |= NETIF_F_TSO_ECN;
> -		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
> -			dev->hw_features |= NETIF_F_UFO;
>  
>  		if (gso)
> -			dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO);
> +			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
>  		/* (!csum && gso) case will be fixed by register_netdev() */
>  	}
>  	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
> @@ -1757,8 +1762,7 @@ static int virtnet_probe(struct virtio_device *vdev)
>  	/* If we can receive ANY GSO packets, we must allocate large ones. */
>  	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
>  	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
> -	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
> -	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
> +	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
>  		vi->big_packets = true;
>  
>  	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
> @@ -1952,9 +1956,9 @@ static struct virtio_device_id id_table[] = {
>  static unsigned int features[] = {
>  	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
>  	VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
> -	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
> +	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6,
>  	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
> -	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
> +	VIRTIO_NET_F_GUEST_ECN,
>  	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
>  	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
>  	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
> 
> 
> -- 
> Ben Hutchings
> The program is absolutely right; therefore, the computer must be wrong.



> _______________________________________________
> Virtualization mailing list
> Virtualization@...ts.linux-foundation.org
> https://lists.linuxfoundation.org/mailman/listinfo/virtualization

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists