Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
netfilter/ipvs fixes for net

The following patchset contains fixes for netfilter/ipvs. This round of
fixes is larger than usual at this stage, specifically because of the
nf_tables bridge reject fixes that I would like to see in 3.18. The
patches are:

1) Fix a null-pointer dereference that may occur when logging
   errors. This problem was introduced by 4a4739d56b0 ("ipvs: Pull
   out crosses_local_route_boundary logic") in v3.17-rc5.

2) Update hook mask in nft_reject_bridge so we can also filter out
   packets from there. This fixes 36d2af5 ("netfilter: nf_tables: allow
   to filter from prerouting and postrouting"), which needs this chunk
   to work.

3) Two patches to refactor common code to forge the IPv4 and IPv6
   reject packets from the bridge. These are required by the nf_tables
   reject bridge fix.

4) Fix nft_reject_bridge by avoiding the use of the IP stack to reject
   packets from the bridge. The idea is to forge the reject packets and
   inject them to the original port via br_deliver() which is now
   exported for that purpose.

5) Restrict nft_reject_bridge to bridge prerouting and input hooks.
   the original skbuff may cloned after prerouting when the bridge stack
   needs to flood it to several bridge ports, it is too late to reject
   the traffic.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 109 insertions, 66 deletions

diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 20d9def..015eb8a 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -12,116 +12,102 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_checksum.h>
 #include <linux/netfilter_ipv6.h>
+#include <net/netfilter/ipv6/nf_reject.h>
 
-void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
+const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
+					      struct tcphdr *otcph,
+					      unsigned int *otcplen, int hook)
 {
-	struct sk_buff *nskb;
-	struct tcphdr otcph, *tcph;
-	unsigned int otcplen, hh_len;
-	int tcphoff, needs_ack;
 	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
-	struct ipv6hdr *ip6h;
-#define DEFAULT_TOS_VALUE	0x0U
-	const __u8 tclass = DEFAULT_TOS_VALUE;
-	struct dst_entry *dst = NULL;
 	u8 proto;
 	__be16 frag_off;
-	struct flowi6 fl6;
-
-	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
-	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
-		pr_debug("addr is not unicast.\n");
-		return;
-	}
+	int tcphoff;
 
 	proto = oip6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data),
+				   &proto, &frag_off);
 
 	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
 		pr_debug("Cannot get TCP header.\n");
-		return;
+		return NULL;
 	}
 
-	otcplen = oldskb->len - tcphoff;
+	*otcplen = oldskb->len - tcphoff;
 
 	/* IP header checks: fragment, too short. */
-	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
-		pr_debug("proto(%d) != IPPROTO_TCP, "
-			 "or too short. otcplen = %d\n",
-			 proto, otcplen);
-		return;
+	if (proto != IPPROTO_TCP || *otcplen < sizeof(struct tcphdr)) {
+		pr_debug("proto(%d) != IPPROTO_TCP or too short (len = %d)\n",
+			 proto, *otcplen);
+		return NULL;
 	}
 
-	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
-		BUG();
+	otcph = skb_header_pointer(oldskb, tcphoff, sizeof(struct tcphdr),
+				   otcph);
+	if (otcph == NULL)
+		return NULL;
 
 	/* No RST for RST. */
-	if (otcph.rst) {
+	if (otcph->rst) {
 		pr_debug("RST is set\n");
-		return;
+		return NULL;
 	}
 
 	/* Check checksum. */
 	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
 		pr_debug("TCP checksum is invalid\n");
-		return;
-	}
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.saddr = oip6h->daddr;
-	fl6.daddr = oip6h->saddr;
-	fl6.fl6_sport = otcph.dest;
-	fl6.fl6_dport = otcph.source;
-	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == NULL || dst->error) {
-		dst_release(dst);
-		return;
-	}
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
-	if (IS_ERR(dst))
-		return;
-
-	hh_len = (dst->dev->hard_header_len + 15)&~15;
-	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
-			 + sizeof(struct tcphdr) + dst->trailer_len,
-			 GFP_ATOMIC);
-
-	if (!nskb) {
-		net_dbg_ratelimited("cannot alloc skb\n");
-		dst_release(dst);
-		return;
+		return NULL;
 	}
 
-	skb_dst_set(nskb, dst);
+	return otcph;
+}
+EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_get);
 
-	skb_reserve(nskb, hh_len + dst->header_len);
+struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb,
+				     const struct sk_buff *oldskb,
+				     __be16 protocol, int hoplimit)
+{
+	struct ipv6hdr *ip6h;
+	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
+#define DEFAULT_TOS_VALUE	0x0U
+	const __u8 tclass = DEFAULT_TOS_VALUE;
 
 	skb_put(nskb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(nskb);
 	ip6h = ipv6_hdr(nskb);
 	ip6_flow_hdr(ip6h, tclass, 0);
-	ip6h->hop_limit = ip6_dst_hoplimit(dst);
-	ip6h->nexthdr = IPPROTO_TCP;
+	ip6h->hop_limit = hoplimit;
+	ip6h->nexthdr = protocol;
 	ip6h->saddr = oip6h->daddr;
 	ip6h->daddr = oip6h->saddr;
 
+	nskb->protocol = htons(ETH_P_IPV6);
+
+	return ip6h;
+}
+EXPORT_SYMBOL_GPL(nf_reject_ip6hdr_put);
+
+void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
+			      const struct sk_buff *oldskb,
+			      const struct tcphdr *oth, unsigned int otcplen)
+{
+	struct tcphdr *tcph;
+	int needs_ack;
+
 	skb_reset_transport_header(nskb);
 	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
 	/* Truncate to length (no data) */
 	tcph->doff = sizeof(struct tcphdr)/4;
-	tcph->source = otcph.dest;
-	tcph->dest = otcph.source;
+	tcph->source = oth->dest;
+	tcph->dest = oth->source;
 
-	if (otcph.ack) {
+	if (oth->ack) {
 		needs_ack = 0;
-		tcph->seq = otcph.ack_seq;
+		tcph->seq = oth->ack_seq;
 		tcph->ack_seq = 0;
 	} else {
 		needs_ack = 1;
-		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
-				      + otcplen - (otcph.doff<<2));
+		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
+				      otcplen - (oth->doff<<2));
 		tcph->seq = 0;
 	}
 
@@ -139,6 +125,63 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 				      sizeof(struct tcphdr), IPPROTO_TCP,
 				      csum_partial(tcph,
 						   sizeof(struct tcphdr), 0));
+}
+EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put);
+
+void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	struct tcphdr _otcph;
+	const struct tcphdr *otcph;
+	unsigned int otcplen, hh_len;
+	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
+	struct ipv6hdr *ip6h;
+	struct dst_entry *dst = NULL;
+	struct flowi6 fl6;
+
+	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
+	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
+		pr_debug("addr is not unicast.\n");
+		return;
+	}
+
+	otcph = nf_reject_ip6_tcphdr_get(oldskb, &_otcph, &otcplen, hook);
+	if (!otcph)
+		return;
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	fl6.saddr = oip6h->daddr;
+	fl6.daddr = oip6h->saddr;
+	fl6.fl6_sport = otcph->dest;
+	fl6.fl6_dport = otcph->source;
+	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (dst == NULL || dst->error) {
+		dst_release(dst);
+		return;
+	}
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	if (IS_ERR(dst))
+		return;
+
+	hh_len = (dst->dev->hard_header_len + 15)&~15;
+	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+			 + sizeof(struct tcphdr) + dst->trailer_len,
+			 GFP_ATOMIC);
+
+	if (!nskb) {
+		net_dbg_ratelimited("cannot alloc skb\n");
+		dst_release(dst);
+		return;
+	}
+
+	skb_dst_set(nskb, dst);
+
+	skb_reserve(nskb, hh_len + dst->header_len);
+	ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
+				    ip6_dst_hoplimit(dst));
+	nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);
 
 	nf_ct_attach(nskb, oldskb);