drivers/infiniband/sw/rxe/rxe_net.c

// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/*
 * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
 * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved.
 */

#include <linux/skbuff.h>
#include <linux/if_arp.h>
#include <linux/netdevice.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <net/udp_tunnel.h>
#include <net/sch_generic.h>
#include <linux/netfilter.h>
#include <rdma/ib_addr.h>

#include "rxe.h"
#include "rxe_net.h"
#include "rxe_loc.h"
#include "rxe_ns.h"

#ifndef SK_REF_FOR_TUNNEL
#define SK_REF_FOR_TUNNEL	2
#endif

#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
 * lockdep can detect false positive circular dependencies
 * when there are user-space socket API users or in kernel
 * users switching between a tcp and rdma transport.
 * Maybe also switching between siw and rxe may cause
 * problems as per default sockets are only classified
 * by family and not by ip protocol. And there might
 * be different locks used between the application
 * and the low level sockets.
 *
 * Problems were seen with ksmbd.ko and cifs.ko,
 * switching transports, use git blame to find
 * more details.
 */
static struct lock_class_key rxe_recv_sk_key[2];
static struct lock_class_key rxe_recv_slock_key[2];
#endif /* CONFIG_DEBUG_LOCK_ALLOC */

static inline void rxe_reclassify_recv_socket(struct socket *sock)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct sock *sk = sock->sk;

	if (WARN_ON_ONCE(!sock_allow_reclassification(sk)))
		return;

	switch (sk->sk_family) {
	case AF_INET:
		sock_lock_init_class_and_name(sk,
					      "slock-AF_INET-RDMA-RXE-RECV",
					      &rxe_recv_slock_key[0],
					      "sk_lock-AF_INET-RDMA-RXE-RECV",
					      &rxe_recv_sk_key[0]);
		break;
	case AF_INET6:
		sock_lock_init_class_and_name(sk,
					      "slock-AF_INET6-RDMA-RXE-RECV",
					      &rxe_recv_slock_key[1],
					      "sk_lock-AF_INET6-RDMA-RXE-RECV",
					      &rxe_recv_sk_key[1]);
		break;
	default:
		WARN_ON_ONCE(1);
		return;
	}
	/*
	 * sock_lock_init_class_and_name() calls
	 * sk_owner_set(sk, THIS_MODULE); in order
	 * to make sure the referenced global
	 * variables rxe_recv_slock_key and
	 * rxe_recv_sk_key are not removed
	 * before the socket is closed.
	 *
	 * However this prevents rxe_net_exit()
	 * from being called and 'rmmod rdma_rxe'
	 * is refused because of the references.
	 *
	 * For the global sockets in recv_sockets,
	 * we are sure that rxe_net_exit() will call
	 * rxe_release_udp_tunnel -> udp_tunnel_sock_release.
	 *
	 * So we don't need the additional reference to
	 * our own (THIS_MODULE).
	 */
	sk_owner_put(sk);
	/*
	 * We also call sk_owner_clear() otherwise
	 * sk_owner_put(sk) in sk_prot_free will
	 * fail, which is called via
	 * sk_free -> __sk_free -> sk_destruct
	 * and sk_destruct calls __sk_destruct
	 * directly or via call_rcu()
	 * so sk_prot_free() might be called
	 * after rxe_net_exit().
	 */
	sk_owner_clear(sk);
#endif /* CONFIG_DEBUG_LOCK_ALLOC */
}

static struct dst_entry *rxe_find_route4(struct rxe_qp *qp,
					 struct net *net,
					 struct net_device *ndev,
					 struct in_addr *saddr,
					 struct in_addr *daddr)
{
	struct rtable *rt;
	struct flowi4 fl = {};

	fl.flowi4_oif = ndev->ifindex;
	memcpy(&fl.saddr, saddr, sizeof(*saddr));
	memcpy(&fl.daddr, daddr, sizeof(*daddr));
	fl.flowi4_proto = IPPROTO_UDP;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt)) {
		rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr);
		return NULL;
	}

	return &rt->dst;
}

#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
					 struct net *net,
					 struct net_device *ndev,
					 struct in6_addr *saddr,
					 struct in6_addr *daddr)
{
	struct dst_entry *ndst;
	struct flowi6 fl6 = {};

	fl6.flowi6_oif = ndev->ifindex;
	memcpy(&fl6.saddr, saddr, sizeof(*saddr));
	memcpy(&fl6.daddr, daddr, sizeof(*daddr));
	fl6.flowi6_proto = IPPROTO_UDP;

	ndst = ip6_dst_lookup_flow(net, rxe_ns_pernet_sk6(net), &fl6, NULL);
	if (IS_ERR(ndst)) {
		rxe_dbg_qp(qp, "no route to %pI6\n", daddr);
		return NULL;
	}

	if (unlikely(ndst->error)) {
		rxe_dbg_qp(qp, "no route to %pI6\n", daddr);
		goto put;
	}

	return ndst;
put:
	dst_release(ndst);
	return NULL;
}

#else

static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
					 struct net *net,
					 struct net_device *ndev,
					 struct in6_addr *saddr,
					 struct in6_addr *daddr)
{
	return NULL;
}

#endif

static struct dst_entry *rxe_find_route(struct net_device *ndev,
					struct rxe_qp *qp,
					struct rxe_av *av)
{
	struct dst_entry *dst = NULL;
	struct net *net;

	if (qp_type(qp) == IB_QPT_RC)
		dst = sk_dst_get(qp->sk->sk);

	if (!dst || !dst_check(dst, qp->dst_cookie)) {
		if (dst)
			dst_release(dst);

		net = dev_net(ndev);

		if (av->network_type == RXE_NETWORK_TYPE_IPV4) {
			struct in_addr *saddr;
			struct in_addr *daddr;

			saddr = &av->sgid_addr._sockaddr_in.sin_addr;
			daddr = &av->dgid_addr._sockaddr_in.sin_addr;
			dst = rxe_find_route4(qp, net, ndev, saddr, daddr);
		} else if (av->network_type == RXE_NETWORK_TYPE_IPV6) {
			struct in6_addr *saddr6;
			struct in6_addr *daddr6;

			saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr;
			daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr;
			dst = rxe_find_route6(qp, net, ndev, saddr6, daddr6);
#if IS_ENABLED(CONFIG_IPV6)
			if (dst)
				qp->dst_cookie =
					rt6_get_cookie((struct rt6_info *)dst);
#endif
		}

		if (dst && (qp_type(qp) == IB_QPT_RC)) {
			dst_hold(dst);
			sk_dst_set(qp->sk->sk, dst);
		}
	}
	return dst;
}

static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
	struct udphdr *udph;
	struct rxe_dev *rxe;
	struct net_device *ndev = skb->dev;
	struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);

	/* takes a reference on rxe->ib_dev
	 * drop when skb is freed
	 */
	rxe = rxe_get_dev_from_net(ndev);
	if (!rxe && is_vlan_dev(ndev))
		rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev));
	if (!rxe)
		goto drop;

	if (skb_linearize(skb)) {
		ib_device_put(&rxe->ib_dev);
		goto drop;
	}

	udph = udp_hdr(skb);
	pkt->rxe = rxe;
	pkt->port_num = 1;
	pkt->hdr = (u8 *)(udph + 1);
	pkt->mask = RXE_GRH_MASK;
	pkt->paylen = udp_get_len_short(udph) - sizeof(*udph);

	/* remove udp header */
	skb_pull(skb, sizeof(struct udphdr));

	rxe_rcv(skb);

	return 0;
drop:
	kfree_skb(skb);

	return 0;
}

static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
					   bool ipv6)
{
	int err;
	struct socket *sock;
	struct udp_port_cfg udp_cfg = { };
	struct udp_tunnel_sock_cfg tnl_cfg = { };

	if (ipv6) {
		udp_cfg.family = AF_INET6;
		udp_cfg.ipv6_v6only = 1;
	} else {
		udp_cfg.family = AF_INET;
	}

	udp_cfg.local_udp_port = port;

	/* Create UDP socket */
	err = udp_sock_create(net, &udp_cfg, &sock);
	if (err < 0)
		return ERR_PTR(err);
	rxe_reclassify_recv_socket(sock);

	tnl_cfg.encap_type = 1;
	tnl_cfg.encap_rcv = rxe_udp_encap_recv;

	/* Setup UDP tunnel */
	setup_udp_tunnel_sock(net, sock->sk, &tnl_cfg);

	return sock;
}

static void rxe_release_udp_tunnel(struct sock *sk)
{
	if (sk)
		udp_tunnel_sock_release(sk);
}

static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port,
			    __be16 dst_port)
{
	struct udphdr *udph;

	__skb_push(skb, sizeof(*udph));
	skb_reset_transport_header(skb);
	udph = udp_hdr(skb);

	udph->dest = dst_port;
	udph->source = src_port;
	udp_set_len_short(udph, skb->len);
	udph->check = 0;
}

static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb,
			     __be32 saddr, __be32 daddr, __u8 proto,
			     __u8 tos, __u8 ttl, __be16 df, bool xnet)
{
	struct iphdr *iph;

	skb_scrub_packet(skb, xnet);

	skb_clear_hash(skb);
	skb_dst_set(skb, dst_clone(dst));
	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));

	skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);

	iph = ip_hdr(skb);

	iph->version	=	IPVERSION;
	iph->ihl	=	sizeof(struct iphdr) >> 2;
	iph->tot_len	=	htons(skb->len);
	iph->frag_off	=	df;
	iph->protocol	=	proto;
	iph->tos	=	tos;
	iph->daddr	=	daddr;
	iph->saddr	=	saddr;
	iph->ttl	=	ttl;
	__ip_select_ident(dev_net(dst->dev), iph,
			  skb_shinfo(skb)->gso_segs ?: 1);
}

static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb,
			     struct in6_addr *saddr, struct in6_addr *daddr,
			     __u8 proto, __u8 prio, __u8 ttl)
{
	struct ipv6hdr *ip6h;

	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
			    | IPSKB_REROUTED);
	skb_dst_set(skb, dst_clone(dst));

	__skb_push(skb, sizeof(*ip6h));
	skb_reset_network_header(skb);
	ip6h		  = ipv6_hdr(skb);
	ip6_flow_hdr(ip6h, prio, htonl(0));
	ip6h->payload_len = htons(skb->len);
	ip6h->nexthdr     = proto;
	ip6h->hop_limit   = ttl;
	ip6h->daddr	  = *daddr;
	ip6h->saddr	  = *saddr;
	ip6h->payload_len = htons(skb->len - sizeof(*ip6h));
}

static int prepare4(struct rxe_av *av, struct rxe_pkt_info *pkt,
		    struct sk_buff *skb)
{
	struct rxe_qp *qp = pkt->qp;
	struct dst_entry *dst;
	bool xnet = false;
	__be16 df = htons(IP_DF);
	struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr;
	struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr;

	dst = rxe_find_route(skb->dev, qp, av);
	if (!dst) {
		rxe_dbg_qp(qp, "Host not reachable\n");
		return -EHOSTUNREACH;
	}

	prepare_udp_hdr(skb, cpu_to_be16(qp->src_port),
			cpu_to_be16(ROCE_V2_UDP_DPORT));

	prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP,
			 av->grh.traffic_class, av->grh.hop_limit, df, xnet);

	dst_release(dst);
	return 0;
}

static int prepare6(struct rxe_av *av, struct rxe_pkt_info *pkt,
		    struct sk_buff *skb)
{
	struct rxe_qp *qp = pkt->qp;
	struct dst_entry *dst;
	struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr;
	struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr;

	dst = rxe_find_route(skb->dev, qp, av);
	if (!dst) {
		rxe_dbg_qp(qp, "Host not reachable\n");
		return -EHOSTUNREACH;
	}

	prepare_udp_hdr(skb, cpu_to_be16(qp->src_port),
			cpu_to_be16(ROCE_V2_UDP_DPORT));

	prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP,
			 av->grh.traffic_class,
			 av->grh.hop_limit);

	dst_release(dst);
	return 0;
}

int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt,
		struct sk_buff *skb)
{
	int err = 0;

	if (skb->protocol == htons(ETH_P_IP))
		err = prepare4(av, pkt, skb);
	else if (skb->protocol == htons(ETH_P_IPV6))
		err = prepare6(av, pkt, skb);

	if (ether_addr_equal(skb->dev->dev_addr, av->dmac))
		pkt->mask |= RXE_LOOPBACK_MASK;

	return err;
}

static void rxe_skb_tx_dtor(struct sk_buff *skb)
{
	struct rxe_qp *qp = skb->sk->sk_user_data;
	int skb_out;

	skb_out = atomic_dec_return(&qp->skb_out);
	if (unlikely(qp->need_req_skb &&
		skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW))
		rxe_sched_task(&qp->send_task);

	rxe_put(qp);
	sock_put(skb->sk);
}

static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
{
	int err;
	struct sock *sk = pkt->qp->sk->sk;

	sock_hold(sk);
	skb->sk = sk;
	skb->destructor = rxe_skb_tx_dtor;
	rxe_get(pkt->qp);
	atomic_inc(&pkt->qp->skb_out);

	if (skb->protocol == htons(ETH_P_IP))
		err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
	else
		err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);

	return err;
}

/* fix up a send packet to match the packets
 * received from UDP before looping them back
 */
static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt)
{
	struct sock *sk = pkt->qp->sk->sk;

	memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt));

	sock_hold(sk);
	skb->sk = sk;
	skb->destructor = rxe_skb_tx_dtor;
	rxe_get(pkt->qp);
	atomic_inc(&pkt->qp->skb_out);

	if (skb->protocol == htons(ETH_P_IP))
		skb_pull(skb, sizeof(struct iphdr));
	else
		skb_pull(skb, sizeof(struct ipv6hdr));

	if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) {
		kfree_skb(skb);
		return -EIO;
	}

	/* remove udp header */
	skb_pull(skb, sizeof(struct udphdr));

	rxe_rcv(skb);

	return 0;
}

int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
		    struct sk_buff *skb)
{
	int err;
	int is_request = pkt->mask & RXE_REQ_MASK;
	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
	unsigned int skblen = skb->len;
	unsigned long flags;

	spin_lock_irqsave(&qp->state_lock, flags);
	if ((is_request && (qp_state(qp) < IB_QPS_RTS)) ||
	    (!is_request && (qp_state(qp) < IB_QPS_RTR))) {
		spin_unlock_irqrestore(&qp->state_lock, flags);
		rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n");
		goto drop;
	}
	spin_unlock_irqrestore(&qp->state_lock, flags);

	rxe_icrc_generate(skb, pkt);

	if (pkt->mask & RXE_LOOPBACK_MASK)
		err = rxe_loopback(skb, pkt);
	else
		err = rxe_send(skb, pkt);
	if (err) {
		rxe_counter_inc(rxe, RXE_CNT_SEND_ERR);
		return err;
	}

	rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS);
	rxe_counter_add(rxe, RXE_CNT_SENT_BYTES, skblen);
	goto done;

drop:
	kfree_skb(skb);
	err = 0;
done:
	return err;
}

struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
				int paylen, struct rxe_pkt_info *pkt)
{
	unsigned int hdr_len;
	struct sk_buff *skb = NULL;
	struct net_device *ndev;
	const struct ib_gid_attr *attr;
	const int port_num = 1;

	attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index);
	if (IS_ERR(attr))
		return NULL;

	if (av->network_type == RXE_NETWORK_TYPE_IPV4)
		hdr_len = ETH_HLEN + sizeof(struct udphdr) +
			sizeof(struct iphdr);
	else
		hdr_len = ETH_HLEN + sizeof(struct udphdr) +
			sizeof(struct ipv6hdr);

	rcu_read_lock();
	ndev = rdma_read_gid_attr_ndev_rcu(attr);
	if (IS_ERR(ndev)) {
		rcu_read_unlock();
		goto out;
	}
	skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev),
			GFP_ATOMIC);

	if (unlikely(!skb)) {
		rcu_read_unlock();
		goto out;
	}

	/* Add time stamp to skb. */
	skb->tstamp = ktime_get();

	skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev));

	/* FIXME: hold reference to this netdev until life of this skb. */
	skb->dev	= ndev;
	rcu_read_unlock();

	if (av->network_type == RXE_NETWORK_TYPE_IPV4)
		skb->protocol = htons(ETH_P_IP);
	else
		skb->protocol = htons(ETH_P_IPV6);

	pkt->rxe	= rxe;
	pkt->port_num	= port_num;
	pkt->hdr	= skb_put(skb, paylen);
	pkt->mask	|= RXE_GRH_MASK;

out:
	rdma_put_gid_attr(attr);
	return skb;
}

/*
 * this is required by rxe_cfg to match rxe devices in
 * /sys/class/infiniband up with their underlying ethernet devices
 */
const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num)
{
	struct net_device *ndev;
	char *ndev_name;

	ndev = ib_device_get_netdev(&rxe->ib_dev, 1);
	if (!ndev)
		return NULL;
	ndev_name = ndev->name;
	dev_put(ndev);

	return ndev_name;
}

int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
{
	int err;
	struct rxe_dev *rxe = NULL;

	rxe = ib_alloc_device(rxe_dev, ib_dev);
	if (!rxe)
		return -ENOMEM;

	ib_mark_name_assigned_by_user(&rxe->ib_dev);

	err = rxe_add(rxe, ndev->mtu, ibdev_name, ndev);
	if (err) {
		ib_dealloc_device(&rxe->ib_dev);
		return err;
	}

	return 0;
}

static void rxe_sock_put(struct sock *sk,
					void (*set_sk)(struct net *, struct sock *),
					struct net *net)
{
	if (refcount_read(&sk->sk_refcnt) > SK_REF_FOR_TUNNEL) {
		__sock_put(sk);
	} else {
		rxe_release_udp_tunnel(sk);
		sk = NULL;
		set_sk(net, sk);
	}
}

void rxe_net_del(struct ib_device *dev)
{
	struct net_device *ndev;
	struct sock *sk;
	struct net *net;

	ndev = ib_device_get_netdev(dev, 1);
	if (!ndev)
		return;

	net = dev_net(ndev);

	sk = rxe_ns_pernet_sk4(net);
	if (sk)
		rxe_sock_put(sk, rxe_ns_pernet_set_sk4, net);

	sk = rxe_ns_pernet_sk6(net);
	if (sk)
		rxe_sock_put(sk, rxe_ns_pernet_set_sk6, net);

	dev_put(ndev);
}

static void rxe_port_event(struct rxe_dev *rxe,
			   enum ib_event_type event)
{
	struct ib_event ev;

	ev.device = &rxe->ib_dev;
	ev.element.port_num = 1;
	ev.event = event;

	ib_dispatch_event(&ev);
}

/* Caller must hold net_info_lock */
void rxe_port_up(struct rxe_dev *rxe)
{
	rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE);
	dev_info(&rxe->ib_dev.dev, "set active\n");
}

/* Caller must hold net_info_lock */
void rxe_port_down(struct rxe_dev *rxe)
{
	rxe_port_event(rxe, IB_EVENT_PORT_ERR);
	rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED);
	dev_info(&rxe->ib_dev.dev, "set down\n");
}

void rxe_set_port_state(struct rxe_dev *rxe)
{
	struct net_device *ndev;

	ndev = ib_device_get_netdev(&rxe->ib_dev, 1);
	if (!ndev)
		return;

	if (ib_get_curr_port_state(ndev) == IB_PORT_ACTIVE)
		rxe_port_up(rxe);
	else
		rxe_port_down(rxe);

	dev_put(ndev);
}

static int rxe_notify(struct notifier_block *not_blk,
		      unsigned long event,
		      void *arg)
{
	struct net_device *ndev = netdev_notifier_info_to_dev(arg);
	struct rxe_dev *rxe = rxe_get_dev_from_net(ndev);

	if (!rxe)
		return NOTIFY_OK;

	switch (event) {
	case NETDEV_UNREGISTER:
		ib_unregister_device_queued(&rxe->ib_dev);
		rxe_net_del(&rxe->ib_dev);
		break;
	case NETDEV_CHANGEMTU:
		rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu);
		rxe_set_mtu(rxe, ndev->mtu);
		break;
	case NETDEV_DOWN:
	case NETDEV_CHANGE:
		if (ib_get_curr_port_state(ndev) == IB_PORT_DOWN)
			rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED);
		break;
	case NETDEV_REBOOT:
	case NETDEV_GOING_DOWN:
	case NETDEV_CHANGEADDR:
	case NETDEV_CHANGENAME:
	case NETDEV_FEAT_CHANGE:
	default:
		rxe_dbg_dev(rxe, "ignoring netdev event = %ld for %s\n",
			event, ndev->name);
		break;
	}

	ib_device_put(&rxe->ib_dev);
	return NOTIFY_OK;
}

static struct notifier_block rxe_net_notifier = {
	.notifier_call = rxe_notify,
};

static int rxe_net_ipv4_init(struct net *net)
{
	struct sock *sk;
	struct socket *sock;

	sk = rxe_ns_pernet_sk4(net);
	if (sk) {
		sock_hold(sk);
		return 0;
	}

	sock = rxe_setup_udp_tunnel(net, htons(ROCE_V2_UDP_DPORT), false);
	if (IS_ERR(sock)) {
		pr_err("Failed to create IPv4 UDP tunnel\n");
		return -1;
	}
	rxe_ns_pernet_set_sk4(net, sock->sk);

	return 0;
}

static int rxe_net_ipv6_init(struct net *net)
{
#if IS_ENABLED(CONFIG_IPV6)
	struct sock *sk;
	struct socket *sock;

	sk = rxe_ns_pernet_sk6(net);
	if (sk) {
		sock_hold(sk);
		return 0;
	}

	sock = rxe_setup_udp_tunnel(net, htons(ROCE_V2_UDP_DPORT), true);
	if (PTR_ERR(sock) == -EAFNOSUPPORT) {
		pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n");
		return 0;
	}

	if (IS_ERR(sock)) {
		pr_err("Failed to create IPv6 UDP tunnel\n");
		return -1;
	}

	rxe_ns_pernet_set_sk6(net, sock->sk);

#endif
	return 0;
}

int rxe_register_notifier(void)
{
	int err;

	err = register_netdevice_notifier(&rxe_net_notifier);
	if (err) {
		pr_err("Failed to register netdev notifier\n");
		return -1;
	}

	return 0;
}

void rxe_net_exit(void)
{
	unregister_netdevice_notifier(&rxe_net_notifier);
}

int rxe_net_init(struct net_device *ndev)
{
	struct net *net;
	struct sock *sk;
	int err;

	net = dev_net(ndev);

	err = rxe_net_ipv4_init(net);
	if (err)
		return err;

	err = rxe_net_ipv6_init(net);
	if (err)
		goto err_out;

	return 0;

err_out:
	/* If ipv6 error, release ipv4 resource */
	sk = rxe_ns_pernet_sk4(net);
	if (sk)
		rxe_sock_put(sk, rxe_ns_pernet_set_sk4, net);

	return err;
}