Re: [PATCH net-next v2] xen-netfront: Add support for IPv6 offloads

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

On Fri, Nov 15, 2013 at 05:52:59PM +0000, Paul Durrant wrote:
> This patch adds support for IPv6 checksum offload and GSO when those
> features are available in the backend.

Wei, Annie, thoughts?
> 
> Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Cc: David Vrabel <david.vrabel@citrix.com>
> Cc: Ian Campbell <ian.campbell@citrix.com>
> ---
> 
> v2:
>  - Addressed comments raised by Ian Campbell
> 
>  drivers/net/xen-netfront.c |  226 ++++++++++++++++++++++++++++++++++++++++----
>  include/linux/ipv6.h       |    2 +
>  2 files changed, 211 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
> index dd1011e..afadfb5 100644
> --- a/drivers/net/xen-netfront.c
> +++ b/drivers/net/xen-netfront.c
> @@ -616,7 +616,9 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
>  		tx->flags |= XEN_NETTXF_extra_info;
>  
>  		gso->u.gso.size = skb_shinfo(skb)->gso_size;
> -		gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
> +		gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?
> +			          XEN_NETIF_GSO_TYPE_TCPV6 :
> +			          XEN_NETIF_GSO_TYPE_TCPV4;
>  		gso->u.gso.pad = 0;
>  		gso->u.gso.features = 0;
>  
> @@ -808,15 +810,18 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
>  		return -EINVAL;
>  	}
>  
> -	/* Currently only TCPv4 S.O. is supported. */
> -	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
> +	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4 &&
> +	    gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV6) {
>  		if (net_ratelimit())
>  			pr_warn("Bad GSO type %d\n", gso->u.gso.type);
>  		return -EINVAL;
>  	}
>  
>  	skb_shinfo(skb)->gso_size = gso->u.gso.size;
> -	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
> +	skb_shinfo(skb)->gso_type =
> +		(gso->u.gso.type == XEN_NETIF_GSO_TYPE_TCPV4) ?
> +		SKB_GSO_TCPV4 :
> +		SKB_GSO_TCPV6;
>  
>  	/* Header must be checked, and gso_segs computed. */
>  	skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
> @@ -856,11 +861,34 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np,
>  	return cons;
>  }
>  
> -static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
> +static inline bool maybe_pull_tail(struct sk_buff *skb, unsigned int len)
>  {
> -	struct iphdr *iph;
> -	int err = -EPROTO;
> +	int target;
> +
> +	if (!skb_is_nonlinear(skb) || skb_headlen(skb) >= len)
> +		return true;
> +
> +	/* If we need to pullup then pullup to the max, so we
> +	 * won't need to do it again.
> +	 */
> +	target = min_t(int, skb->len, MAX_TCP_HEADER);
> +	__pskb_pull_tail(skb, target - skb_headlen(skb));
> +
> +	if (skb_headlen(skb) < len) {
> +		net_err_ratelimited("Failed to pullup packet header\n");
> +		return false;    
> +	}
> +
> +	return true;
> +}
> +
> +static int checksum_setup_ip(struct net_device *dev, struct sk_buff *skb)
> +{
> +	struct iphdr *iph = (void *)skb->data;
> +	unsigned int header_size;
> +	unsigned int off;
>  	int recalculate_partial_csum = 0;
> +	int err = -EPROTO;
>  
>  	/*
>  	 * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
> @@ -879,40 +907,56 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
>  	if (skb->ip_summed != CHECKSUM_PARTIAL)
>  		return 0;
>  
> -	if (skb->protocol != htons(ETH_P_IP))
> +	off = sizeof(struct iphdr);
> +
> +	header_size = skb->network_header + off;
> +	if (!maybe_pull_tail(skb, header_size))
>  		goto out;
>  
> -	iph = (void *)skb->data;
> +	off = iph->ihl * 4;
>  
>  	switch (iph->protocol) {
>  	case IPPROTO_TCP:
> -		if (!skb_partial_csum_set(skb, 4 * iph->ihl,
> +		if (!skb_partial_csum_set(skb, off,
>  					  offsetof(struct tcphdr, check)))
>  			goto out;
>  
>  		if (recalculate_partial_csum) {
>  			struct tcphdr *tcph = tcp_hdr(skb);
> +
> +			header_size = skb->network_header +
> +				off +
> +				sizeof(struct tcphdr);
> +			if (!maybe_pull_tail(skb, header_size))
> +				goto out;
> +
>  			tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
> -							 skb->len - iph->ihl*4,
> +							 skb->len - off,
>  							 IPPROTO_TCP, 0);
>  		}
>  		break;
>  	case IPPROTO_UDP:
> -		if (!skb_partial_csum_set(skb, 4 * iph->ihl,
> +		if (!skb_partial_csum_set(skb, off,
>  					  offsetof(struct udphdr, check)))
>  			goto out;
>  
>  		if (recalculate_partial_csum) {
>  			struct udphdr *udph = udp_hdr(skb);
> +
> +			header_size = skb->network_header +
> +				off +
> +				sizeof(struct udphdr);
> +			if (!maybe_pull_tail(skb, header_size))
> +				goto out;
> +
>  			udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
> -							 skb->len - iph->ihl*4,
> +							 skb->len - off,
>  							 IPPROTO_UDP, 0);
>  		}
>  		break;
>  	default:
> -		if (net_ratelimit())
> -			pr_err("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
> -			       iph->protocol);
> +		net_err_ratelimited("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
> +				    iph->protocol);
>  		goto out;
>  	}
>  
> @@ -922,6 +966,122 @@ out:
>  	return err;
>  }
>  
> +static int checksum_setup_ipv6(struct net_device *dev, struct sk_buff *skb)
> +{
> +	struct ipv6hdr *ipv6h = (void *)skb->data;
> +	u8 nexthdr;
> +	unsigned int header_size;
> +	unsigned int off;
> +	bool fragment;
> +	bool done;
> +	int err = -EPROTO;
> +
> +	done = false;
> +
> +	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
> +	if (skb->ip_summed != CHECKSUM_PARTIAL)
> +		return 0;
> +
> +	off = sizeof(struct ipv6hdr);
> +
> +	header_size = skb->network_header + off;
> +	if (!maybe_pull_tail(skb, header_size))
> +		goto out;
> +
> +	nexthdr = ipv6h->nexthdr;
> +
> +	while ((off <= sizeof(struct ipv6hdr) + ntohs(ipv6h->payload_len)) &&
> +	       !done) {
> +		switch (nexthdr) {
> +		case IPPROTO_DSTOPTS:
> +		case IPPROTO_HOPOPTS:
> +		case IPPROTO_ROUTING: {
> +			struct ipv6_opt_hdr *hp = (void *)(skb->data + off);
> +
> +			header_size = skb->network_header +
> +				off +
> +				sizeof(struct ipv6_opt_hdr);
> +			if (!maybe_pull_tail(skb, header_size))
> +				goto out;
> +
> +			nexthdr = hp->nexthdr;
> +			off += ipv6_optlen(hp);
> +			break;
> +		}
> +		case IPPROTO_AH: {
> +			struct ip_auth_hdr *hp = (void *)(skb->data + off);
> +
> +			header_size = skb->network_header +
> +				off +
> +				sizeof(struct ip_auth_hdr);
> +			if (!maybe_pull_tail(skb, header_size))
> +				goto out;
> +
> +			nexthdr = hp->nexthdr;
> +			off += ipv6_ahlen(hp);
> +			break;
> +		}
> +		case IPPROTO_FRAGMENT:
> +			fragment = true;
> +			/* fall through */
> +		default:
> +			done = true;
> +			break;
> +		}
> +	}
> +
> +	if (!done) {
> +		net_err_ratelimited("Failed to parse packet header\n");
> +		goto out;
> +	}
> +
> +	if (fragment) {
> +		net_err_ratelimited("Packet is a fragment!\n");
> +		goto out;
> +	}
> +
> +	switch (nexthdr) {
> +	case IPPROTO_TCP:
> +		if (!skb_partial_csum_set(skb, off,
> +					  offsetof(struct tcphdr, check)))
> +			goto out;
> +		break;
> +	case IPPROTO_UDP:
> +		if (!skb_partial_csum_set(skb, off,
> +					  offsetof(struct udphdr, check)))
> +			goto out;
> +		break;
> +	default:
> +		net_err_ratelimited("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
> +				    nexthdr);
> +		goto out;
> +	}
> +
> +	err = 0;
> +
> +out:
> +	return err;
> +}
> +
> +static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
> +{
> +	int err;
> +
> +	switch (skb->protocol) {
> +	case htons(ETH_P_IP):
> +		err = checksum_setup_ip(dev, skb);
> +		break;
> +	case htons(ETH_P_IPV6):
> +		err = checksum_setup_ipv6(dev, skb);
> +		break;
> +	default:
> +		err = -EPROTO;
> +		break;
> +	}
> +
> +	return err;
> +}
> +
>  static int handle_incoming_queue(struct net_device *dev,
>  				 struct sk_buff_head *rxq)
>  {
> @@ -1232,6 +1392,15 @@ static netdev_features_t xennet_fix_features(struct net_device *dev,
>  			features &= ~NETIF_F_SG;
>  	}
>  
> +	if (features & NETIF_F_IPV6_CSUM) {
> +		if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
> +				 "feature-ipv6-csum-offload", "%d", &val) < 0)
> +			val = 0;
> +
> +		if (!val)
> +			features &= ~NETIF_F_IPV6_CSUM;
> +	}
> +
>  	if (features & NETIF_F_TSO) {
>  		if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
>  				 "feature-gso-tcpv4", "%d", &val) < 0)
> @@ -1241,6 +1410,15 @@ static netdev_features_t xennet_fix_features(struct net_device *dev,
>  			features &= ~NETIF_F_TSO;
>  	}
>  
> +	if (features & NETIF_F_TSO6) {
> +		if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
> +				 "feature-gso-tcpv6", "%d", &val) < 0)
> +			val = 0;
> +
> +		if (!val)
> +			features &= ~NETIF_F_TSO6;
> +	}
> +
>  	return features;
>  }
>  
> @@ -1373,7 +1551,9 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
>  	netif_napi_add(netdev, &np->napi, xennet_poll, 64);
>  	netdev->features        = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
>  				  NETIF_F_GSO_ROBUST;
> -	netdev->hw_features	= NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO;
> +	netdev->hw_features	= NETIF_F_SG | 
> +		                  NETIF_F_IPV6_CSUM |
> +		                  NETIF_F_TSO | NETIF_F_TSO6;
>  
>  	/*
>           * Assume that all hw features are available for now. This set
> @@ -1751,6 +1931,18 @@ again:
>  		goto abort_transaction;
>  	}
>  
> +	err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6", "%d", 1);
> +	if (err) {
> +		message = "writing feature-gso-tcpv6";
> +		goto abort_transaction;
> +	}
> +
> +	err = xenbus_printf(xbt, dev->nodename, "feature-ipv6-csum-offload", "%d", 1);
> +	if (err) {
> +		message = "writing feature-gso-tcpv6";
> +		goto abort_transaction;
> +	}
> +
>  	err = xenbus_transaction_end(xbt, 0);
>  	if (err) {
>  		if (err == -EAGAIN)
> diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
> index 5d89d1b..10f1b03 100644
> --- a/include/linux/ipv6.h
> +++ b/include/linux/ipv6.h
> @@ -4,6 +4,8 @@
>  #include <uapi/linux/ipv6.h>
>  
>  #define ipv6_optlen(p)  (((p)->hdrlen+1) << 3)
> +#define ipv6_ahlen(p)   (((p)->hdrlen+2) << 2);
> +
>  /*
>   * This structure contains configuration options per IPv6 link.
>   */
> -- 
> 1.7.10.4
>