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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 135 insertions, 36 deletions

diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 6015802ebe6f..9584526c0778 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -28,6 +28,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/compat.h>
 #include <net/net_namespace.h>
+#include <linux/module.h>
 
 #include "datapath.h"
 #include "vport.h"
@@ -36,22 +37,7 @@
 static void ovs_vport_record_error(struct vport *,
 				   enum vport_err_type err_type);
 
-/* List of statically compiled vport implementations.  Don't forget to also
- * add yours to the list at the bottom of vport.h. */
-static const struct vport_ops *vport_ops_list[] = {
-	&ovs_netdev_vport_ops,
-	&ovs_internal_vport_ops,
-
-#ifdef CONFIG_OPENVSWITCH_GRE
-	&ovs_gre_vport_ops,
-#endif
-#ifdef CONFIG_OPENVSWITCH_VXLAN
-	&ovs_vxlan_vport_ops,
-#endif
-#ifdef CONFIG_OPENVSWITCH_GENEVE
-	&ovs_geneve_vport_ops,
-#endif
-};
+static LIST_HEAD(vport_ops_list);
 
 /* Protected by RCU read lock for reading, ovs_mutex for writing. */
 static struct hlist_head *dev_table;
@@ -82,12 +68,38 @@ void ovs_vport_exit(void)
 	kfree(dev_table);
 }
 
-static struct hlist_head *hash_bucket(struct net *net, const char *name)
+static struct hlist_head *hash_bucket(const struct net *net, const char *name)
 {
 	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
 	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
 }
 
+int ovs_vport_ops_register(struct vport_ops *ops)
+{
+	int err = -EEXIST;
+	struct vport_ops *o;
+
+	ovs_lock();
+	list_for_each_entry(o, &vport_ops_list, list)
+		if (ops->type == o->type)
+			goto errout;
+
+	list_add_tail(&ops->list, &vport_ops_list);
+	err = 0;
+errout:
+	ovs_unlock();
+	return err;
+}
+EXPORT_SYMBOL_GPL(ovs_vport_ops_register);
+
+void ovs_vport_ops_unregister(struct vport_ops *ops)
+{
+	ovs_lock();
+	list_del(&ops->list);
+	ovs_unlock();
+}
+EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);
+
 /**
  *	ovs_vport_locate - find a port that has already been created
  *
@@ -95,7 +107,7 @@ static struct hlist_head *hash_bucket(struct net *net, const char *name)
  *
  * Must be called with ovs or RCU read lock.
  */
-struct vport *ovs_vport_locate(struct net *net, const char *name)
+struct vport *ovs_vport_locate(const struct net *net, const char *name)
 {
 	struct hlist_head *bucket = hash_bucket(net, name);
 	struct vport *vport;
@@ -153,6 +165,7 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 
 	return vport;
 }
+EXPORT_SYMBOL_GPL(ovs_vport_alloc);
 
 /**
  *	ovs_vport_free - uninitialize and free vport
@@ -173,6 +186,18 @@ void ovs_vport_free(struct vport *vport)
 	free_percpu(vport->percpu_stats);
 	kfree(vport);
 }
+EXPORT_SYMBOL_GPL(ovs_vport_free);
+
+static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
+{
+	struct vport_ops *ops;
+
+	list_for_each_entry(ops, &vport_ops_list, list)
+		if (ops->type == parms->type)
+			return ops;
+
+	return NULL;
+}
 
 /**
  *	ovs_vport_add - add vport device (for kernel callers)
@@ -184,31 +209,40 @@ void ovs_vport_free(struct vport *vport)
  */
 struct vport *ovs_vport_add(const struct vport_parms *parms)
 {
+	struct vport_ops *ops;
 	struct vport *vport;
-	int err = 0;
-	int i;
 
-	for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
-		if (vport_ops_list[i]->type == parms->type) {
-			struct hlist_head *bucket;
+	ops = ovs_vport_lookup(parms);
+	if (ops) {
+		struct hlist_head *bucket;
 
-			vport = vport_ops_list[i]->create(parms);
-			if (IS_ERR(vport)) {
-				err = PTR_ERR(vport);
-				goto out;
-			}
+		if (!try_module_get(ops->owner))
+			return ERR_PTR(-EAFNOSUPPORT);
 
-			bucket = hash_bucket(ovs_dp_get_net(vport->dp),
-					     vport->ops->get_name(vport));
-			hlist_add_head_rcu(&vport->hash_node, bucket);
+		vport = ops->create(parms);
+		if (IS_ERR(vport)) {
+			module_put(ops->owner);
 			return vport;
 		}
+
+		bucket = hash_bucket(ovs_dp_get_net(vport->dp),
+				     vport->ops->get_name(vport));
+		hlist_add_head_rcu(&vport->hash_node, bucket);
+		return vport;
 	}
 
-	err = -EAFNOSUPPORT;
+	/* Unlock to attempt module load and return -EAGAIN if load
+	 * was successful as we need to restart the port addition
+	 * workflow.
+	 */
+	ovs_unlock();
+	request_module("vport-type-%d", parms->type);
+	ovs_lock();
 
-out:
-	return ERR_PTR(err);
+	if (!ovs_vport_lookup(parms))
+		return ERR_PTR(-EAFNOSUPPORT);
+	else
+		return ERR_PTR(-EAGAIN);
 }
 
 /**
@@ -242,6 +276,8 @@ void ovs_vport_del(struct vport *vport)
 	hlist_del_rcu(&vport->hash_node);
 
 	vport->ops->destroy(vport);
+
+	module_put(vport->ops->owner);
 }
 
 /**
@@ -344,7 +380,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
  *
  * Must be called with ovs_mutex.
  */
-int ovs_vport_set_upcall_portids(struct vport *vport,  struct nlattr *ids)
+int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
 {
 	struct vport_portids *old, *vport_portids;
 
@@ -435,7 +471,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
  * skb->data should point to the Ethernet header.
  */
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
-		       struct ovs_tunnel_info *tun_info)
+		       const struct ovs_tunnel_info *tun_info)
 {
 	struct pcpu_sw_netstats *stats;
 	struct sw_flow_key key;
@@ -457,6 +493,7 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	}
 	ovs_dp_process_packet(skb, &key);
 }
+EXPORT_SYMBOL_GPL(ovs_vport_receive);
 
 /**
  *	ovs_vport_send - send a packet on a device
@@ -535,3 +572,65 @@ void ovs_vport_deferred_free(struct vport *vport)
 
 	call_rcu(&vport->rcu, free_vport_rcu);
 }
+EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
+
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+			       struct net *net,
+			       const struct ovs_tunnel_info *tun_info,
+			       u8 ipproto,
+			       u32 skb_mark,
+			       __be16 tp_src,
+			       __be16 tp_dst)
+{
+	const struct ovs_key_ipv4_tunnel *tun_key;
+	struct rtable *rt;
+	struct flowi4 fl;
+
+	if (unlikely(!tun_info))
+		return -EINVAL;
+
+	tun_key = &tun_info->tunnel;
+
+	/* Route lookup to get srouce IP address.
+	 * The process may need to be changed if the corresponding process
+	 * in vports ops changed.
+	 */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb_mark;
+	fl.flowi4_proto = ipproto;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt))
+		return PTR_ERR(rt);
+
+	ip_rt_put(rt);
+
+	/* Generate egress_tun_info based on tun_info,
+	 * saddr, tp_src and tp_dst
+	 */
+	__ovs_flow_tun_info_init(egress_tun_info,
+				 fl.saddr, tun_key->ipv4_dst,
+				 tun_key->ipv4_tos,
+				 tun_key->ipv4_ttl,
+				 tp_src, tp_dst,
+				 tun_key->tun_id,
+				 tun_key->tun_flags,
+				 tun_info->options,
+				 tun_info->options_len);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
+
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				  struct ovs_tunnel_info *info)
+{
+	/* get_egress_tun_info() is only implemented on tunnel ports. */
+	if (unlikely(!vport->ops->get_egress_tun_info))
+		return -EINVAL;
+
+	return vport->ops->get_egress_tun_info(vport, skb, info);
+}