Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 284 insertions, 0 deletions

diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
new file mode 100644
index 0000000..b2d01eb
--- /dev/null
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -0,0 +1,284 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/neighbour.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_tables.h>
+/* For layer 4 checksum field offset. */
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
+			      __be32 addr, __be32 new_addr)
+{
+	struct tcphdr *tcph;
+
+	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+		return -1;
+
+	tcph = (void *)(skb_network_header(skb) + thoff);
+	inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
+
+	return 0;
+}
+
+static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
+			      __be32 addr, __be32 new_addr)
+{
+	struct udphdr *udph;
+
+	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
+		return -1;
+
+	udph = (void *)(skb_network_header(skb) + thoff);
+	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+		inet_proto_csum_replace4(&udph->check, skb, addr,
+					 new_addr, true);
+		if (!udph->check)
+			udph->check = CSUM_MANGLED_0;
+	}
+
+	return 0;
+}
+
+static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
+				  unsigned int thoff, __be32 addr,
+				  __be32 new_addr)
+{
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+		if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
+			return NF_DROP;
+		break;
+	case IPPROTO_UDP:
+		if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
+			return NF_DROP;
+		break;
+	}
+
+	return 0;
+}
+
+static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			   struct iphdr *iph, unsigned int thoff,
+			   enum flow_offload_tuple_dir dir)
+{
+	__be32 addr, new_addr;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = iph->saddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
+		iph->saddr = new_addr;
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = iph->daddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
+		iph->daddr = new_addr;
+		break;
+	default:
+		return -1;
+	}
+	csum_replace4(&iph->check, addr, new_addr);
+
+	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			   struct iphdr *iph, unsigned int thoff,
+			   enum flow_offload_tuple_dir dir)
+{
+	__be32 addr, new_addr;
+
+	switch (dir) {
+	case FLOW_OFFLOAD_DIR_ORIGINAL:
+		addr = iph->daddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
+		iph->daddr = new_addr;
+		break;
+	case FLOW_OFFLOAD_DIR_REPLY:
+		addr = iph->saddr;
+		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
+		iph->saddr = new_addr;
+		break;
+	default:
+		return -1;
+	}
+
+	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+			  enum flow_offload_tuple_dir dir)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	unsigned int thoff = iph->ihl * 4;
+
+	if (flow->flags & FLOW_OFFLOAD_SNAT &&
+	    (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+	     nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
+		return -1;
+	if (flow->flags & FLOW_OFFLOAD_DNAT &&
+	    (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+	     nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
+		return -1;
+
+	return 0;
+}
+
+static bool ip_has_options(unsigned int thoff)
+{
+	return thoff != sizeof(struct iphdr);
+}
+
+static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
+			    struct flow_offload_tuple *tuple)
+{
+	struct flow_ports *ports;
+	unsigned int thoff;
+	struct iphdr *iph;
+
+	if (!pskb_may_pull(skb, sizeof(*iph)))
+		return -1;
+
+	iph = ip_hdr(skb);
+	thoff = iph->ihl * 4;
+
+	if (ip_is_fragment(iph) ||
+	    unlikely(ip_has_options(thoff)))
+		return -1;
+
+	if (iph->protocol != IPPROTO_TCP &&
+	    iph->protocol != IPPROTO_UDP)
+		return -1;
+
+	thoff = iph->ihl * 4;
+	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+		return -1;
+
+	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+	tuple->src_v4.s_addr	= iph->saddr;
+	tuple->dst_v4.s_addr	= iph->daddr;
+	tuple->src_port		= ports->source;
+	tuple->dst_port		= ports->dest;
+	tuple->l3proto		= AF_INET;
+	tuple->l4proto		= iph->protocol;
+	tuple->iifidx		= dev->ifindex;
+
+	return 0;
+}
+
+/* Based on ip_exceeds_mtu(). */
+static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+		return false;
+
+	return true;
+}
+
+static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt)
+{
+	u32 mtu;
+
+	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
+	if (__nf_flow_exceeds_mtu(skb, mtu))
+		return true;
+
+	return false;
+}
+
+unsigned int
+nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
+			const struct nf_hook_state *state)
+{
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct nf_flowtable *flow_table = priv;
+	struct flow_offload_tuple tuple = {};
+	enum flow_offload_tuple_dir dir;
+	struct flow_offload *flow;
+	struct net_device *outdev;
+	const struct rtable *rt;
+	struct iphdr *iph;
+	__be32 nexthop;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
+		return NF_ACCEPT;
+
+	tuplehash = flow_offload_lookup(flow_table, &tuple);
+	if (tuplehash == NULL)
+		return NF_ACCEPT;
+
+	outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+	if (!outdev)
+		return NF_ACCEPT;
+
+	dir = tuplehash->tuple.dir;
+	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+
+	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+	if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+		return NF_ACCEPT;
+
+	if (skb_try_make_writable(skb, sizeof(*iph)))
+		return NF_DROP;
+
+	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+	    nf_flow_nat_ip(flow, skb, dir) < 0)
+		return NF_DROP;
+
+	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+	iph = ip_hdr(skb);
+	ip_decrease_ttl(iph);
+
+	skb->dev = outdev;
+	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
+	neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
+
+	return NF_STOLEN;
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
+
+static struct nf_flowtable_type flowtable_ipv4 = {
+	.family		= NFPROTO_IPV4,
+	.params		= &nf_flow_offload_rhash_params,
+	.gc		= nf_flow_offload_work_gc,
+	.hook		= nf_flow_offload_ip_hook,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nf_flow_ipv4_module_init(void)
+{
+	nft_register_flowtable_type(&flowtable_ipv4);
+
+	return 0;
+}
+
+static void __exit nf_flow_ipv4_module_exit(void)
+{
+	nft_unregister_flowtable_type(&flowtable_ipv4);
+}
+
+module_init(nf_flow_ipv4_module_init);
+module_exit(nf_flow_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NF_FLOWTABLE(AF_INET);