[ Upstream commit
703133de331a7a7df47f31fb9de51dc6f68a9de8 ]
If local fragmentation is allowed, then ip_select_ident() and
ip_select_ident_more() need to generate unique IDs to ensure
correct defragmentation on the peer.
For example, if IPsec (tunnel mode) has to encrypt large skbs
that have local_df bit set, then all IP fragments that belonged
to different ESP datagrams would have used the same identificator.
If one of these IP fragments would get lost or reordered, then
peer could possibly stitch together wrong IP fragments that did
not belong to the same datagram. This would lead to a packet loss
or data corruption.
Signed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
nf_reset(skb);
skb->ip_summed = CHECKSUM_NONE;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, &rt->dst, NULL);
ip_send_check(iph);
ip_local_out(skb);
extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
-static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
{
- if (iph->frag_off & htons(IP_DF)) {
+ struct iphdr *iph = ip_hdr(skb);
+
+ if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
/* This is only to work around buggy Windows95/2000
* VJ compression implementations. If the ID field
* does not change, they drop every other packet in
__ip_select_ident(iph, dst, 0);
}
-static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more)
+static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more)
{
- if (iph->frag_off & htons(IP_DF)) {
+ struct iphdr *iph = ip_hdr(skb);
+
+ if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
if (sk && inet_sk(sk)->inet_daddr) {
iph->id = htons(inet_sk(sk)->inet_id);
inet_sk(sk)->inet_id += 1 + more;
int pkt_len = skb->len - skb_transport_offset(skb); \
\
skb->ip_summed = CHECKSUM_NONE; \
- ip_select_ident(iph, &rt->dst, NULL); \
+ ip_select_ident(skb, &rt->dst, NULL); \
\
err = ip_local_out(skb); \
if (likely(net_xmit_eval(err) == 0)) { \
pip->saddr = fl4.saddr;
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
- ip_select_ident(pip, &rt->dst, NULL);
+ ip_select_ident(skb, &rt->dst, NULL);
((u8*)&pip[1])[0] = IPOPT_RA;
((u8*)&pip[1])[1] = 4;
((u8*)&pip[1])[2] = 0;
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->protocol = IPPROTO_IGMP;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, &rt->dst, NULL);
((u8*)&iph[1])[0] = IPOPT_RA;
((u8*)&iph[1])[1] = 4;
((u8*)&iph[1])[2] = 0;
* At the moment of writing this notes identifier of IP packets is generated
* to be unpredictable using this code only for packets subjected
* (actually or potentially) to defragmentation. I.e. DF packets less than
- * PMTU in size uses a constant ID and do not use this code (see
- * ip_select_ident() in include/net/ip.h).
+ * PMTU in size when local fragmentation is disabled use a constant ID and do
+ * not use this code (see ip_select_ident() in include/net/ip.h).
*
* Route cache entries hold references to our nodes.
* New cache entries get references via lookup by destination IP address in
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
- ip_select_ident(iph, &rt->dst, sk);
+ ip_select_ident(skb, &rt->dst, sk);
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
}
- ip_select_ident_more(iph, &rt->dst, sk,
+ ip_select_ident_more(skb, &rt->dst, sk,
(skb_shinfo(skb)->gso_segs ?: 1) - 1);
skb->priority = sk->sk_priority;
iph->ihl = 5;
iph->tos = inet->tos;
iph->frag_off = df;
- ip_select_ident(iph, &rt->dst, sk);
+ ip_select_ident(skb, &rt->dst, sk);
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
iph->tot_len = htons(skb->len);
- ip_select_ident(iph, skb_dst(skb), NULL);
+ ip_select_ident(skb, skb_dst(skb), NULL);
ip_send_check(iph);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, &rt->dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
- ip_select_ident(top_iph, dst->child, NULL);
+ ip_select_ident(skb, dst->child, NULL);
top_iph->ttl = ip4_dst_hoplimit(dst->child);
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;