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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for your net-next
tree. Basically, improvements for the packet rejection infrastructure,
deprecation of CLUSTERIP, cleanups for nf_tables and some untangling for
br_netfilter. More specifically they are:

1) Send packet to reset flow if checksum is valid, from Florian Westphal.

2) Fix nf_tables reject bridge from the input chain, also from Florian.

3) Deprecate the CLUSTERIP target, the cluster match supersedes it in
   functionality and it's known to have problems.

4) A couple of cleanups for nf_tables rule tracing infrastructure, from
   Patrick McHardy.

5) Another cleanup to place transaction declarations at the bottom of
   nf_tables.h, also from Patrick.

6) Consolidate Kconfig dependencies wrt. NF_TABLES.

7) Limit table names to 32 bytes in nf_tables.

8) mac header copying in bridge netfilter is already required when
   calling ip_fragment(), from Florian Westphal.

9) move nf_bridge_update_protocol() to br_netfilter.c, also from
   Florian.

10) Small refactor in br_netfilter in the transmission path, again from
    Florian.

11) Move br_nf_pre_routing_finish_bridge_slow() to br_netfilter.
====================

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

5 files changed, 147 insertions, 29 deletions

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ffd379db5938..294cbcc49263 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -36,13 +36,10 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	u16 vid = 0;
 
 	rcu_read_lock();
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
-		br_nf_pre_routing_finish_bridge_slow(skb);
+	if (br_nf_prerouting_finish_bridge(skb)) {
 		rcu_read_unlock();
 		return NETDEV_TX_OK;
 	}
-#endif
 
 	u64_stats_update_begin(&brstats->syncp);
 	brstats->tx_packets++;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 1238fabff874..3304a5442331 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -37,9 +37,7 @@ static inline int should_deliver(const struct net_bridge_port *p,
 
 int br_dev_queue_push_xmit(struct sk_buff *skb)
 {
-	/* ip_fragment doesn't copy the MAC header */
-	if (nf_bridge_maybe_copy_header(skb) ||
-	    !is_skb_forwardable(skb->dev, skb)) {
+	if (!is_skb_forwardable(skb->dev, skb)) {
 		kfree_skb(skb);
 	} else {
 		skb_push(skb, ETH_HLEN);
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 0ee453fad3de..a8361c7cdf81 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -239,6 +239,14 @@ drop:
 	return -1;
 }
 
+static void nf_bridge_update_protocol(struct sk_buff *skb)
+{
+	if (skb->nf_bridge->mask & BRNF_8021Q)
+		skb->protocol = htons(ETH_P_8021Q);
+	else if (skb->nf_bridge->mask & BRNF_PPPoE)
+		skb->protocol = htons(ETH_P_PPP_SES);
+}
+
 /* PF_BRIDGE/PRE_ROUTING *********************************************/
 /* Undo the changes made for ip6tables PREROUTING and continue the
  * bridge PRE_ROUTING hook. */
@@ -764,23 +772,53 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 }
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+static bool nf_bridge_copy_header(struct sk_buff *skb)
+{
+	int err;
+	unsigned int header_size;
+
+	nf_bridge_update_protocol(skb);
+	header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
+	err = skb_cow_head(skb, header_size);
+	if (err)
+		return false;
+
+	skb_copy_to_linear_data_offset(skb, -header_size,
+				       skb->nf_bridge->data, header_size);
+	__skb_push(skb, nf_bridge_encap_header_len(skb));
+	return true;
+}
+
+static int br_nf_push_frag_xmit(struct sk_buff *skb)
+{
+	if (!nf_bridge_copy_header(skb)) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	return br_dev_queue_push_xmit(skb);
+}
+
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	int ret;
 	int frag_max_size;
+	unsigned int mtu_reserved;
 
+	if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP))
+		return br_dev_queue_push_xmit(skb);
+
+	mtu_reserved = nf_bridge_mtu_reduction(skb);
 	/* This is wrong! We should preserve the original fragment
 	 * boundaries by preserving frag_list rather than refragmenting.
 	 */
-	if (skb->protocol == htons(ETH_P_IP) &&
-	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
-	    !skb_is_gso(skb)) {
+	if (skb->len + mtu_reserved > skb->dev->mtu) {
 		frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
 		if (br_parse_ip_options(skb))
 			/* Drop invalid packet */
 			return NF_DROP;
 		IPCB(skb)->frag_max_size = frag_max_size;
-		ret = ip_fragment(skb, br_dev_queue_push_xmit);
+		ret = ip_fragment(skb, br_nf_push_frag_xmit);
 	} else
 		ret = br_dev_queue_push_xmit(skb);
 
@@ -854,6 +892,38 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
 	return NF_ACCEPT;
 }
 
+/* This is called when br_netfilter has called into iptables/netfilter,
+ * and DNAT has taken place on a bridge-forwarded packet.
+ *
+ * neigh->output has created a new MAC header, with local br0 MAC
+ * as saddr.
+ *
+ * This restores the original MAC saddr of the bridged packet
+ * before invoking bridge forward logic to transmit the packet.
+ */
+static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
+{
+	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+
+	skb_pull(skb, ETH_HLEN);
+	nf_bridge->mask &= ~BRNF_BRIDGED_DNAT;
+
+	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN),
+				       skb->nf_bridge->data, ETH_HLEN-ETH_ALEN);
+	skb->dev = nf_bridge->physindev;
+	br_handle_frame_finish(skb);
+}
+
+int br_nf_prerouting_finish_bridge(struct sk_buff *skb)
+{
+	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
+		br_nf_pre_routing_finish_bridge_slow(skb);
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(br_nf_prerouting_finish_bridge);
+
 void br_netfilter_enable(void)
 {
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index c32e279c62f8..f0a0438dbd6d 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -765,10 +765,15 @@ static inline int br_vlan_enabled(struct net_bridge *br)
 
 /* br_netfilter.c */
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+int br_nf_prerouting_finish_bridge(struct sk_buff *skb);
 int br_nf_core_init(void);
 void br_nf_core_fini(void);
 void br_netfilter_rtable_init(struct net_bridge *);
 #else
+static inline int br_nf_prerouting_finish_bridge(struct sk_buff *skb)
+{
+        return 0;
+}
 static inline int br_nf_core_init(void) { return 0; }
 static inline void br_nf_core_fini(void) {}
 #define br_netfilter_rtable_init(x)
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 3244aead0926..5c6c96585acd 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -21,6 +21,7 @@
 #include <net/ip.h>
 #include <net/ip6_checksum.h>
 #include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv6.h>
 #include "../br_private.h"
 
 static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
@@ -36,7 +37,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	skb_pull(nskb, ETH_HLEN);
 }
 
-static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook)
+/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT)
+ * or the bridge port (NF_BRIDGE PREROUTING).
+ */
+static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb,
+					    const struct net_device *dev,
+					    int hook)
 {
 	struct sk_buff *nskb;
 	struct iphdr *niph;
@@ -65,11 +71,12 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook)
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
 }
 
-static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
-					  u8 code)
+static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb,
+					  const struct net_device *dev,
+					  int hook, u8 code)
 {
 	struct sk_buff *nskb;
 	struct iphdr *niph;
@@ -77,8 +84,9 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 	unsigned int len;
 	void *payload;
 	__wsum csum;
+	u8 proto;
 
-	if (!nft_bridge_iphdr_validate(oldskb))
+	if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb))
 		return;
 
 	/* IP header checks: fragment. */
@@ -91,7 +99,17 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 	if (!pskb_may_pull(oldskb, len))
 		return;
 
-	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), 0))
+	if (pskb_trim_rcsum(oldskb, htons(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) +
@@ -120,11 +138,13 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook,
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
 }
 
 static void nft_reject_br_send_v6_tcp_reset(struct net *net,
-					    struct sk_buff *oldskb, int hook)
+					    struct sk_buff *oldskb,
+					    const struct net_device *dev,
+					    int hook)
 {
 	struct sk_buff *nskb;
 	const struct tcphdr *oth;
@@ -152,12 +172,37 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
+}
+
+static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	int thoff;
+	__be16 fo;
+	u8 proto = ip6h->nexthdr;
+
+	if (skb->csum_bad)
+		return false;
+
+	if (skb_csum_unnecessary(skb))
+		return true;
+
+	if (ip6h->payload_len &&
+	    pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
+		return false;
+
+	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_v6_unreach(struct net *net,
-					  struct sk_buff *oldskb, int hook,
-					  u8 code)
+					  struct sk_buff *oldskb,
+					  const struct net_device *dev,
+					  int hook, u8 code)
 {
 	struct sk_buff *nskb;
 	struct ipv6hdr *nip6h;
@@ -176,6 +221,9 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 	if (!pskb_may_pull(oldskb, len))
 		return;
 
+	if (!reject6_br_csum_ok(oldskb, hook))
+		return;
+
 	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmp6hdr) +
 			 LL_MAX_HEADER + len, GFP_ATOMIC);
 	if (!nskb)
@@ -205,7 +253,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
-	br_deliver(br_port_get_rcu(oldskb->dev), nskb);
+	br_deliver(br_port_get_rcu(dev), nskb);
 }
 
 static void nft_reject_bridge_eval(const struct nft_expr *expr,
@@ -224,16 +272,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
 	case htons(ETH_P_IP):
 		switch (priv->type) {
 		case NFT_REJECT_ICMP_UNREACH:
-			nft_reject_br_send_v4_unreach(pkt->skb,
+			nft_reject_br_send_v4_unreach(pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      priv->icmp_code);
 			break;
 		case NFT_REJECT_TCP_RST:
-			nft_reject_br_send_v4_tcp_reset(pkt->skb,
+			nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in,
 							pkt->ops->hooknum);
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
-			nft_reject_br_send_v4_unreach(pkt->skb,
+			nft_reject_br_send_v4_unreach(pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      nft_reject_icmp_code(priv->icmp_code));
 			break;
@@ -242,16 +290,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
 	case htons(ETH_P_IPV6):
 		switch (priv->type) {
 		case NFT_REJECT_ICMP_UNREACH:
-			nft_reject_br_send_v6_unreach(net, pkt->skb,
+			nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      priv->icmp_code);
 			break;
 		case NFT_REJECT_TCP_RST:
-			nft_reject_br_send_v6_tcp_reset(net, pkt->skb,
+			nft_reject_br_send_v6_tcp_reset(net, pkt->skb, pkt->in,
 							pkt->ops->hooknum);
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
-			nft_reject_br_send_v6_unreach(net, pkt->skb,
+			nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in,
 						      pkt->ops->hooknum,
 						      nft_reject_icmpv6_code(priv->icmp_code));
 			break;