Re: [RFC v2] ipvs: allow transmit of GRO aggregated skbs

[Simon Horman <horms@xxxxxxxxxxxx>]

This is a first attempt at allowing LVS to transmit
skbs of greater than MTU length that have been aggregated by GRO.

I have lightly tested the ip_vs_dr_xmit() portion of this patch and
although it seems to work I am unsure that netif_needs_gso() is the correct
test to use.

Signed-off-by: Simon Horman <horms@xxxxxxxxxxxx>

--- 

* 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)

Index: lvs-test-2.6/net/netfilter/ipvs/ip_vs_xmit.c
===================================================================
--- lvs-test-2.6.orig/net/netfilter/ipvs/ip_vs_xmit.c   2010-10-30 
11:43:37.000000000 +0900
+++ lvs-test-2.6/net/netfilter/ipvs/ip_vs_xmit.c        2010-11-06 
08:09:17.000000000 +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)) &&
+           !netif_needs_gso(rt->dst.dev, 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 && !netif_needs_gso(rt->dst.dev, 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)) &&
+           !netif_needs_gso(rt->dst.dev, 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 && !netif_needs_gso(rt->dst.dev, skb)) {
                if (!skb->dev) {
                        struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -790,8 +792,9 @@ 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) &&
+           !netif_needs_gso(rt->dst.dev, 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 +906,8 @@ 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) &&
+           !netif_needs_gso(rt->dst.dev, skb)) {
                if (!skb->dev) {
                        struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -1008,7 +1012,8 @@ 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 &&
+           !netif_needs_gso(rt->dst.dev, 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 +1179,8 @@ 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)) &&
+           !netif_needs_gso(rt->dst.dev, 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 +1294,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb,
 
        /* MTU checking */
        mtu = dst_mtu(&rt->dst);
-       if (skb->len > mtu) {
+       if (skb->len > mtu && !netif_needs_gso(rt->dst.dev, 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@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html