ipv4: fix DO and PROBE pmtu mode regarding local fragmentation with UFO/CORK

[~andy/linux] / net / ipv4 / ip_output.c

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a04d872c54f919c7133e7830773301cdf070f3ed..51be64e18e32e92ffaf898351142f01d9c9c42ec 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -772,15 +772,20 @@ static inline int ip_ufo_append_data(struct sock *sk,
                /* initialize protocol header pointer */
                skb->transport_header = skb->network_header + fragheaderlen;
 
-               skb->ip_summed = CHECKSUM_PARTIAL;
                skb->csum = 0;
 
-               /* specify the length of each IP datagram fragment */
-               skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
-               skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
                __skb_queue_tail(queue, skb);
+       } else if (skb_is_gso(skb)) {
+               goto append;
        }
 
+       skb->ip_summed = CHECKSUM_PARTIAL;
+       /* specify the length of each IP datagram fragment */
+       skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
+       skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
+append:
        return skb_append_datato_frags(sk, skb, getfrag, from,
                                       (length - transhdrlen));
 }
@@ -805,7 +810,7 @@ static int __ip_append_data(struct sock *sk,
        int copy;
        int err;
        int offset = 0;
-       unsigned int maxfraglen, fragheaderlen;
+       unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
        int csummode = CHECKSUM_NONE;
        struct rtable *rt = (struct rtable *)cork->dst;
 
@@ -818,8 +823,10 @@ static int __ip_append_data(struct sock *sk,
 
        fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
        maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+       maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+                        mtu : 0xFFFF;
 
-       if (cork->length + length > 0xFFFF - fragheaderlen) {
+       if (cork->length + length > maxnonfragsize - fragheaderlen) {
                ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
                               mtu-exthdrlen);
                return -EMSGSIZE;
@@ -1060,6 +1067,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
                         rt->dst.dev->mtu : dst_mtu(&rt->dst);
        cork->dst = &rt->dst;
        cork->length = 0;
+       cork->ttl = ipc->ttl;
+       cork->tos = ipc->tos;
+       cork->priority = ipc->priority;
        cork->tx_flags = ipc->tx_flags;
 
        return 0;
@@ -1114,7 +1124,7 @@ ssize_t   ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
        int mtu;
        int len;
        int err;
-       unsigned int maxfraglen, fragheaderlen, fraggap;
+       unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
 
        if (inet->hdrincl)
                return -EPERM;
@@ -1138,8 +1148,10 @@ ssize_t  ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
        fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
        maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+       maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+                        mtu : 0xFFFF;
 
-       if (cork->length + size > 0xFFFF - fragheaderlen) {
+       if (cork->length + size > maxnonfragsize - fragheaderlen) {
                ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
                return -EMSGSIZE;
        }
@@ -1311,7 +1323,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
        if (cork->flags & IPCORK_OPT)
                opt = cork->opt;
 
-       if (rt->rt_type == RTN_MULTICAST)
+       if (cork->ttl != 0)
+               ttl = cork->ttl;
+       else if (rt->rt_type == RTN_MULTICAST)
                ttl = inet->mc_ttl;
        else
                ttl = ip_select_ttl(inet, &rt->dst);
@@ -1319,7 +1333,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
        iph = ip_hdr(skb);
        iph->version = 4;
        iph->ihl = 5;
-       iph->tos = inet->tos;
+       iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
        iph->frag_off = df;
        iph->ttl = ttl;
        iph->protocol = sk->sk_protocol;
@@ -1331,7 +1345,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
                ip_options_build(skb, opt, cork->addr, rt, 0);
        }
 
-       skb->priority = sk->sk_priority;
+       skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
        skb->mark = sk->sk_mark;
        /*
         * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1481,6 +1495,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
        ipc.addr = daddr;
        ipc.opt = NULL;
        ipc.tx_flags = 0;
+       ipc.ttl = 0;
+       ipc.tos = -1;
 
        if (replyopts.opt.opt.optlen) {
                ipc.opt = &replyopts.opt;