ipv6: fix incorrect ipsec fragment

[~andy/linux] / net / ipv6 / ip6_output.c

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d8e05af2c4bb0745823db6cfa37933a3f0269b8b..17b8c67998bb80dc5e7052af210c7b64aa1471ee 100644 (file)
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -252,8 +252,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
                               dst->dev, dst_output);
        }
 
-       if (net_ratelimit())
-               printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
+       net_dbg_ratelimited("IPv6: sending pkt_too_big to self\n");
        skb->dev = dst->dev;
        icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
        IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
@@ -644,7 +643,10 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
        /* We must not fragment if the socket is set to force MTU discovery
         * or if the skb it not generated by a local socket.
         */
-       if (!skb->local_df && skb->len > mtu) {
+       if (unlikely(!skb->local_df && skb->len > mtu)) {
+               if (skb->sk && dst_allfrag(skb_dst(skb)))
+                       sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+
                skb->dev = skb_dst(skb)->dev;
                icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
                IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
@@ -789,6 +791,10 @@ slow_path_clean:
        }
 
 slow_path:
+       if ((skb->ip_summed == CHECKSUM_PARTIAL) &&
+           skb_checksum_help(skb))
+               goto fail;
+
        left = skb->len - hlen;         /* Space per frame */
        ptr = hlen;                     /* Where to start from */
 
@@ -1181,6 +1187,29 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
        return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
 }
 
+static void ip6_append_data_mtu(int *mtu,
+                               int *maxfraglen,
+                               unsigned int fragheaderlen,
+                               struct sk_buff *skb,
+                               struct rt6_info *rt)
+{
+       if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
+               if (skb == NULL) {
+                       /* first fragment, reserve header_len */
+                       *mtu = *mtu - rt->dst.header_len;
+
+               } else {
+                       /*
+                        * this fragment is not first, the headers
+                        * space is regarded as data space.
+                        */
+                       *mtu = dst_mtu(rt->dst.path);
+               }
+               *maxfraglen = ((*mtu - fragheaderlen) & ~7)
+                             + fragheaderlen - sizeof(struct frag_hdr);
+       }
+}
+
 int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
        int offset, int len, int odd, struct sk_buff *skb),
        void *from, int length, int transhdrlen,
@@ -1190,7 +1219,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
        struct inet_sock *inet = inet_sk(sk);
        struct ipv6_pinfo *np = inet6_sk(sk);
        struct inet_cork *cork;
-       struct sk_buff *skb;
+       struct sk_buff *skb, *skb_prev = NULL;
        unsigned int maxfraglen, fragheaderlen;
        int exthdrlen;
        int dst_exthdrlen;
@@ -1199,7 +1228,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
        int copy;
        int err;
        int offset = 0;
-       int csummode = CHECKSUM_NONE;
        __u8 tx_flags = 0;
 
        if (flags&MSG_PROBE)
@@ -1248,8 +1276,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                inet->cork.fl.u.ip6 = *fl6;
                np->cork.hop_limit = hlimit;
                np->cork.tclass = tclass;
-               mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
-                     rt->dst.dev->mtu : dst_mtu(&rt->dst);
+               if (rt->dst.flags & DST_XFRM_TUNNEL)
+                       mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+                             rt->dst.dev->mtu : dst_mtu(&rt->dst);
+               else
+                       mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+                             rt->dst.dev->mtu : dst_mtu(rt->dst.path);
                if (np->frag_size < mtu) {
                        if (np->frag_size)
                                mtu = np->frag_size;
@@ -1345,25 +1377,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                        unsigned int fraglen;
                        unsigned int fraggap;
                        unsigned int alloclen;
-                       struct sk_buff *skb_prev;
 alloc_new_skb:
-                       skb_prev = skb;
-
                        /* There's no room in the current skb */
-                       if (skb_prev)
-                               fraggap = skb_prev->len - maxfraglen;
+                       if (skb)
+                               fraggap = skb->len - maxfraglen;
                        else
                                fraggap = 0;
+                       /* update mtu and maxfraglen if necessary */
+                       if (skb == NULL || skb_prev == NULL)
+                               ip6_append_data_mtu(&mtu, &maxfraglen,
+                                                   fragheaderlen, skb, rt);
+
+                       skb_prev = skb;
 
                        /*
                         * If remaining data exceeds the mtu,
                         * we know we need more fragment(s).
                         */
                        datalen = length + fraggap;
-                       if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
-                               datalen = maxfraglen - fragheaderlen;
 
-                       fraglen = datalen + fragheaderlen;
+                       if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+                               datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
                        if ((flags & MSG_MORE) &&
                            !(rt->dst.dev->features&NETIF_F_SG))
                                alloclen = mtu;
@@ -1372,13 +1406,16 @@ alloc_new_skb:
 
                        alloclen += dst_exthdrlen;
 
-                       /*
-                        * The last fragment gets additional space at tail.
-                        * Note: we overallocate on fragments with MSG_MODE
-                        * because we have no idea if we're the last one.
-                        */
-                       if (datalen == length + fraggap)
-                               alloclen += rt->dst.trailer_len;
+                       if (datalen != length + fraggap) {
+                               /*
+                                * this is not the last fragment, the trailer
+                                * space is regarded as data space.
+                                */
+                               datalen += rt->dst.trailer_len;
+                       }
+
+                       alloclen += rt->dst.trailer_len;
+                       fraglen = datalen + fragheaderlen;
 
                        /*
                         * We just reserve space for fragment header.
@@ -1412,7 +1449,7 @@ alloc_new_skb:
                        /*
                         *      Fill in the control structures
                         */
-                       skb->ip_summed = csummode;
+                       skb->ip_summed = CHECKSUM_NONE;
                        skb->csum = 0;
                        /* reserve for fragmentation and ipsec header */
                        skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
@@ -1455,7 +1492,6 @@ alloc_new_skb:
                        transhdrlen = 0;
                        exthdrlen = 0;
                        dst_exthdrlen = 0;
-                       csummode = CHECKSUM_NONE;
 
                        /*
                         * Put the packet on the pending queue