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

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

1 files changed, 117 insertions, 19 deletions

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index b615729812e5..eb8181987620 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -48,21 +48,30 @@ static int xfrmi_dev_init(struct net_device *dev);
 static void xfrmi_dev_setup(struct net_device *dev);
 static struct rtnl_link_ops xfrmi_link_ops __read_mostly;
 static unsigned int xfrmi_net_id __read_mostly;
+static const struct net_device_ops xfrmi_netdev_ops;
+
+#define XFRMI_HASH_BITS	8
+#define XFRMI_HASH_SIZE	BIT(XFRMI_HASH_BITS)
 
 struct xfrmi_net {
 	/* lists for storing interfaces in use */
-	struct xfrm_if __rcu *xfrmi[1];
+	struct xfrm_if __rcu *xfrmi[XFRMI_HASH_SIZE];
 };
 
 #define for_each_xfrmi_rcu(start, xi) \
 	for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next))
 
+static u32 xfrmi_hash(u32 if_id)
+{
+	return hash_32(if_id, XFRMI_HASH_BITS);
+}
+
 static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
 {
 	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
 	struct xfrm_if *xi;
 
-	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
+	for_each_xfrmi_rcu(xfrmn->xfrmi[xfrmi_hash(x->if_id)], xi) {
 		if (x->if_id == xi->p.if_id &&
 		    (xi->dev->flags & IFF_UP))
 			return xi;
@@ -74,8 +83,7 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
 static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb,
 					    unsigned short family)
 {
-	struct xfrmi_net *xfrmn;
-	struct xfrm_if *xi;
+	struct net_device *dev;
 	int ifindex = 0;
 
 	if (!secpath_exists(skb) || !skb->dev)
@@ -89,23 +97,26 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb,
 		ifindex = inet_sdif(skb);
 		break;
 	}
-	if (!ifindex)
-		ifindex = skb->dev->ifindex;
 
-	xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
+	if (ifindex) {
+		struct net *net = xs_net(xfrm_input_state(skb));
 
-	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
-		if (ifindex == xi->dev->ifindex &&
-			(xi->dev->flags & IFF_UP))
-				return xi;
+		dev = dev_get_by_index_rcu(net, ifindex);
+	} else {
+		dev = skb->dev;
 	}
 
-	return NULL;
+	if (!dev || !(dev->flags & IFF_UP))
+		return NULL;
+	if (dev->netdev_ops != &xfrmi_netdev_ops)
+		return NULL;
+
+	return netdev_priv(dev);
 }
 
 static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
 {
-	struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0];
+	struct xfrm_if __rcu **xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)];
 
 	rcu_assign_pointer(xi->next , rtnl_dereference(*xip));
 	rcu_assign_pointer(*xip, xi);
@@ -116,7 +127,7 @@ static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
 	struct xfrm_if __rcu **xip;
 	struct xfrm_if *iter;
 
-	for (xip = &xfrmn->xfrmi[0];
+	for (xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)];
 	     (iter = rtnl_dereference(*xip)) != NULL;
 	     xip = &iter->next) {
 		if (xi == iter) {
@@ -160,7 +171,7 @@ static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p)
 	struct xfrm_if *xi;
 	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
 
-	for (xip = &xfrmn->xfrmi[0];
+	for (xip = &xfrmn->xfrmi[xfrmi_hash(p->if_id)];
 	     (xi = rtnl_dereference(*xip)) != NULL;
 	     xip = &xi->next)
 		if (xi->p.if_id == p->if_id)
@@ -760,11 +771,14 @@ static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list)
 		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
 		struct xfrm_if __rcu **xip;
 		struct xfrm_if *xi;
+		int i;
 
-		for (xip = &xfrmn->xfrmi[0];
-		     (xi = rtnl_dereference(*xip)) != NULL;
-		     xip = &xi->next)
-			unregister_netdevice_queue(xi->dev, &list);
+		for (i = 0; i < XFRMI_HASH_SIZE; i++) {
+			for (xip = &xfrmn->xfrmi[i];
+			     (xi = rtnl_dereference(*xip)) != NULL;
+			     xip = &xi->next)
+				unregister_netdevice_queue(xi->dev, &list);
+		}
 	}
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
@@ -800,6 +814,33 @@ static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = {
 	.priority	=	10,
 };
 
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+static int xfrmi6_rcv_tunnel(struct sk_buff *skb)
+{
+	const xfrm_address_t *saddr;
+	__be32 spi;
+
+	saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr;
+	spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr);
+
+	return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL);
+}
+
+static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = {
+	.handler	=	xfrmi6_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	-1,
+};
+
+static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
+	.handler	=	xfrmi6_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	-1,
+};
+#endif
+
 static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
 	.handler	=	xfrm4_rcv,
 	.input_handler	=	xfrm_input,
@@ -824,6 +865,27 @@ static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = {
 	.priority	=	10,
 };
 
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+static int xfrmi4_rcv_tunnel(struct sk_buff *skb)
+{
+	return xfrm4_rcv_spi(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr);
+}
+
+static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = {
+	.handler	=	xfrmi4_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	-1,
+};
+
+static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = {
+	.handler	=	xfrmi4_rcv_tunnel,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	-1,
+};
+#endif
+
 static int __init xfrmi4_init(void)
 {
 	int err;
@@ -837,9 +899,23 @@ static int __init xfrmi4_init(void)
 	err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
 	if (err < 0)
 		goto xfrm_proto_comp_failed;
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+	err = xfrm4_tunnel_register(&xfrmi_ipip_handler, AF_INET);
+	if (err < 0)
+		goto xfrm_tunnel_ipip_failed;
+	err = xfrm4_tunnel_register(&xfrmi_ipip6_handler, AF_INET6);
+	if (err < 0)
+		goto xfrm_tunnel_ipip6_failed;
+#endif
 
 	return 0;
 
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+xfrm_tunnel_ipip6_failed:
+	xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET);
+xfrm_tunnel_ipip_failed:
+	xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+#endif
 xfrm_proto_comp_failed:
 	xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
 xfrm_proto_ah_failed:
@@ -850,6 +926,10 @@ xfrm_proto_esp_failed:
 
 static void xfrmi4_fini(void)
 {
+#if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL)
+	xfrm4_tunnel_deregister(&xfrmi_ipip6_handler, AF_INET6);
+	xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET);
+#endif
 	xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
 	xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
@@ -868,9 +948,23 @@ static int __init xfrmi6_init(void)
 	err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
 	if (err < 0)
 		goto xfrm_proto_comp_failed;
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+	err = xfrm6_tunnel_register(&xfrmi_ipv6_handler, AF_INET6);
+	if (err < 0)
+		goto xfrm_tunnel_ipv6_failed;
+	err = xfrm6_tunnel_register(&xfrmi_ip6ip_handler, AF_INET);
+	if (err < 0)
+		goto xfrm_tunnel_ip6ip_failed;
+#endif
 
 	return 0;
 
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+xfrm_tunnel_ip6ip_failed:
+	xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6);
+xfrm_tunnel_ipv6_failed:
+	xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+#endif
 xfrm_proto_comp_failed:
 	xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
 xfrm_proto_ah_failed:
@@ -881,6 +975,10 @@ xfrm_proto_esp_failed:
 
 static void xfrmi6_fini(void)
 {
+#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
+	xfrm6_tunnel_deregister(&xfrmi_ip6ip_handler, AF_INET);
+	xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6);
+#endif
 	xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
 	xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
 	xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);