[v3] ipvs: allow transmit of GRO aggregated skbs

Attempt at allowing LVS to transmit skbs of greater than MTU length that
have been aggregated by GRO and can thus be deaggregated by GSO.

Cc: Julian Anastasov <ja@ssi.bg>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Simon Horman <horms@verge.net.au>

--- 

* LRO is still an outstanding issue, but as its deprecated in favour
  of GRO perhaps it doesn't need to be solved.

* v1
  - Based on 2.6.35

* v2
  - Rebase on current nf-next-2.6 tree (~2.6.37-rc1)

* v3
  - Use skb_is_gso() instead of netif_needs_gso() as suggested by
    Julian Anastasov and confirmed by Herbert Xu.

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

On Tue, Nov 09, 2010 at 10:08:49AM +0900, Simon Horman wrote:
> Attempt at allowing LVS to transmit skbs of greater than MTU length that
> have been aggregated by GRO and can thus be deaggregated by GSO.
> 
> Cc: Julian Anastasov <ja@ssi.bg>
> Cc: Herbert Xu <herbert@gondor.apana.org.au>
> Signed-off-by: Simon Horman <horms@verge.net.au>
> 
> --- 
> 
> * LRO is still an outstanding issue, but as its deprecated in favour
>   of GRO perhaps it doesn't need to be solved.
> 
> * v1
>   - Based on 2.6.35
> 
> * v2
>   - Rebase on current nf-next-2.6 tree (~2.6.37-rc1)
> 
> * v3
>   - Use skb_is_gso() instead of netif_needs_gso() as suggested by
>     Julian Anastasov and confirmed by Herbert Xu.

On thinking about this a bit more, I believe that this is material
for stable as its affecting deployed systems. I'll back-port it
and add the appropriate CC once its seen a bit more testing.

> 
> Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_xmit.c
> ===================================================================
> --- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_xmit.c	2010-11-08 16:27:31.000000000 +0900
> +++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_xmit.c	2010-11-08 16:29:19.000000000 +0900
> @@ -408,7 +408,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, s
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
> +	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
> +	    !skb_is_gso(skb)) {
>  		ip_rt_put(rt);
>  		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
>  		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
> @@ -461,7 +462,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if (skb->len > mtu) {
> +	if (skb->len > mtu && !skb_is_gso(skb)) {
>  		if (!skb->dev) {
>  			struct net *net = dev_net(skb_dst(skb)->dev);
>  
> @@ -560,7 +561,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, stru
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
> +	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
> +	    !skb_is_gso(skb)) {
>  		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
>  		IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
>  				 "ip_vs_nat_xmit(): frag needed for");
> @@ -675,7 +677,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, s
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if (skb->len > mtu) {
> +	if (skb->len > mtu && !skb_is_gso(skb)) {
>  		if (!skb->dev) {
>  			struct net *net = dev_net(skb_dst(skb)->dev);
>  
> @@ -790,8 +792,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, s
>  
>  	df |= (old_iph->frag_off & htons(IP_DF));
>  
> -	if ((old_iph->frag_off & htons(IP_DF))
> -	    && mtu < ntohs(old_iph->tot_len)) {
> +	if ((old_iph->frag_off & htons(IP_DF) &&
> +	    mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
>  		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
>  		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
>  		goto tx_error_put;
> @@ -903,7 +905,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb
>  	if (skb_dst(skb))
>  		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
>  
> -	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) {
> +	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
> +	    !skb_is_gso(skb)) {
>  		if (!skb->dev) {
>  			struct net *net = dev_net(skb_dst(skb)->dev);
>  
> @@ -1008,7 +1011,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struc
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
> +	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu &&
> +	    !skb_is_gso(skb)) {
>  		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
>  		ip_rt_put(rt);
>  		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
> @@ -1174,7 +1178,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, str
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) {
> +	if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
> +	    !skb_is_gso(skb)) {
>  		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
>  		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
>  		goto tx_error_put;
> @@ -1288,7 +1293,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb,
>  
>  	/* MTU checking */
>  	mtu = dst_mtu(&rt->dst);
> -	if (skb->len > mtu) {
> +	if (skb->len > mtu && !skb_is_gso(skb)) {
>  		if (!skb->dev) {
>  			struct net *net = dev_net(skb_dst(skb)->dev);
>  
> --
> To unsubscribe from this list: send the line "unsubscribe lvs-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html