static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
unsigned short ulen, __be32 saddr, __be32 daddr)
{
__wsum psum;
if (uh->check == 0 || skb_csum_unnecessary(skb))
return 0;
psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
if (skb->ip_summed == CHECKSUM_COMPLETE &&
!csum_fold(csum_add(psum, skb->csum)))
return 0;
skb->csum = psum;
return __skb_checksum_complete(skb);
}
void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
{
struct iphdr *iph = ip_hdr(skb_in);
u8 proto;
if (iph->frag_off & htons(IP_OFFSET))
return;
if (skb_csum_unnecessary(skb_in)) {
icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
return;
}
if (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP)
proto = iph->protocol;
else
proto = 0;
if (nf_ip_checksum(skb_in, hook, ip_hdrlen(skb_in), proto) == 0)
icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
}
static bool reject6_csum_ok(struct sk_buff *skb, int hook)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
int thoff;
__be16 fo;
u8 proto;
if (skb->csum_bad)
return false;
if (skb_csum_unnecessary(skb))
return true;
proto = ip6h->nexthdr;
thoff = ipv6_skip_exthdr(skb, ((u8 *)(ip6h + 1) - skb->data), &proto, &fo);
if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
return false;
return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
}
static void nft_reject_br_send_v4_unreach(struct net *net,
struct sk_buff *oldskb,
const struct net_device *dev,
int hook, u8 code)
{
struct sk_buff *nskb;
struct iphdr *niph;
struct icmphdr *icmph;
unsigned int len;
void *payload;
__wsum csum;
u8 proto;
if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb))
return;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return;
/* RFC says return as much as we can without exceeding 576 bytes. */
len = min_t(unsigned int, 536, oldskb->len);
if (!pskb_may_pull(oldskb, len))
return;
if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
return;
if (ip_hdr(oldskb)->protocol == IPPROTO_TCP ||
ip_hdr(oldskb)->protocol == IPPROTO_UDP)
proto = ip_hdr(oldskb)->protocol;
else
proto = 0;
if (!skb_csum_unnecessary(oldskb) &&
nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
return;
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
LL_MAX_HEADER + len, GFP_ATOMIC);
if (!nskb)
return;
skb_reserve(nskb, LL_MAX_HEADER);
niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
net->ipv4.sysctl_ip_default_ttl);
skb_reset_transport_header(nskb);
icmph = (struct icmphdr *)skb_put(nskb, sizeof(struct icmphdr));
memset(icmph, 0, sizeof(*icmph));
icmph->type = ICMP_DEST_UNREACH;
icmph->code = code;
payload = skb_put(nskb, len);
memcpy(payload, skb_network_header(oldskb), len);
csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
icmph->checksum = csum_fold(csum);
niph->tot_len = htons(nskb->len);
ip_send_check(niph);
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
}
/*
* Handle ICMP messages in the outside-to-inside direction (incoming).
* Find any that might be relevant, check against existing connections,
* forward to the right destination host if relevant.
* Currently handles error types - unreachable, quench, ttl exceeded.
*/
static int
ip_vs_in_icmp(struct sk_buff **pskb, int *related, unsigned int hooknum)
{
struct sk_buff *skb = *pskb;
struct iphdr *iph;
struct icmphdr _icmph, *ic;
struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */
struct ip_vs_conn *cp;
struct ip_vs_protocol *pp;
unsigned int offset, ihl, verdict;
*related = 1;
/* reassemble IP fragments */
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
skb = ip_vs_gather_frags(skb,
hooknum == NF_IP_LOCAL_IN ?
IP_DEFRAG_VS_IN : IP_DEFRAG_VS_FWD);
if (!skb)
return NF_STOLEN;
*pskb = skb;
}
iph = ip_hdr(skb);
offset = ihl = iph->ihl * 4;
ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
if (ic == NULL)
return NF_DROP;
IP_VS_DBG(12, "Incoming ICMP (%d,%d) %u.%u.%u.%u->%u.%u.%u.%u\n",
ic->type, ntohs(icmp_id(ic)),
NIPQUAD(iph->saddr), NIPQUAD(iph->daddr));
/*
* Work through seeing if this is for us.
* These checks are supposed to be in an order that means easy
* things are checked first to speed up processing.... however
* this means that some packets will manage to get a long way
* down this stack and then be rejected, but that's life.
*/
if ((ic->type != ICMP_DEST_UNREACH) &&
(ic->type != ICMP_SOURCE_QUENCH) &&
(ic->type != ICMP_TIME_EXCEEDED)) {
*related = 0;
return NF_ACCEPT;
}
/* Now find the contained IP header */
offset += sizeof(_icmph);
cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
if (cih == NULL)
return NF_ACCEPT; /* The packet looks wrong, ignore */
pp = ip_vs_proto_get(cih->protocol);
if (!pp)
return NF_ACCEPT;
/* Is the embedded protocol header present? */
if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
pp->dont_defrag))
return NF_ACCEPT;
IP_VS_DBG_PKT(11, pp, skb, offset, "Checking incoming ICMP for");
offset += cih->ihl * 4;
/* The embedded headers contain source and dest in reverse order */
cp = pp->conn_in_get(skb, pp, cih, offset, 1);
if (!cp)
return NF_ACCEPT;
verdict = NF_DROP;
/* Ensure the checksum is correct */
if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
/* Failed checksum! */
IP_VS_DBG(1, "Incoming ICMP: failed checksum from %d.%d.%d.%d!\n",
NIPQUAD(iph->saddr));
goto out;
}
/* do the statistics and put it back */
ip_vs_in_stats(cp, skb);
if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
offset += 2 * sizeof(__u16);
verdict = ip_vs_icmp_xmit(skb, cp, pp, offset);
/* do not touch skb anymore */
out:
__ip_vs_conn_put(cp);
return verdict;
}
