Re: [PATCHv3 6/8] RDMA/rxe: add the support of net namespace

[Zhu Yanjun <yanjun.zhu@xxxxxxxxx>]

在 2023/2/14 14:06, Zhu Yanjun 写道:
> From: Zhu Yanjun <yanjun.zhu@xxxxxxxxx>
>
> Originally init_net is used to indicate the current net namespace.
> Currently more net namespaces are supported.
>
> Signed-off-by: Zhu Yanjun <yanjun.zhu@xxxxxxxxx>

Add netdev@xxxxxxxxxxxxxxx.

Zhu Yanjun

> ---
>   drivers/infiniband/sw/rxe/rxe.c     |  2 +-
>   drivers/infiniband/sw/rxe/rxe_net.c | 33 +++++++++++++++++------------
>   drivers/infiniband/sw/rxe/rxe_net.h |  2 +-
>   3 files changed, 22 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
> index e81c2164d77f..4a17e4a003f5 100644
> --- a/drivers/infiniband/sw/rxe/rxe.c
> +++ b/drivers/infiniband/sw/rxe/rxe.c
> @@ -196,7 +196,7 @@ static int rxe_newlink(const char *ibdev_name, struct net_device *ndev)
>   		goto err;
>   	}
>   
> -	err = rxe_net_init();
> +	err = rxe_net_init(ndev);
>   	if (err)
>   		return err;
>   
> diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
> index b56e2c32fbf7..9af90587642a 100644
> --- a/drivers/infiniband/sw/rxe/rxe_net.c
> +++ b/drivers/infiniband/sw/rxe/rxe_net.c
> @@ -32,7 +32,7 @@ static struct dst_entry *rxe_find_route4(struct rxe_qp *qp,
>   	memcpy(&fl.daddr, daddr, sizeof(*daddr));
>   	fl.flowi4_proto = IPPROTO_UDP;
>   
> -	rt = ip_route_output_key(&init_net, &fl);
> +	rt = ip_route_output_key(dev_net(ndev), &fl);
>   	if (IS_ERR(rt)) {
>   		rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr);
>   		return NULL;
> @@ -56,7 +56,8 @@ static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
>   		struct sock *sk;
>   
>   		rcu_read_lock();
> -		sk = udp6_lib_lookup(&init_net, NULL, 0, &in6addr_any, htons(ROCE_V2_UDP_DPORT), 0);
> +		sk = udp6_lib_lookup(dev_net(ndev), NULL, 0, &in6addr_any,
> +				     htons(ROCE_V2_UDP_DPORT), 0);
>   		rcu_read_unlock();
>   		if (!sk) {
>   			pr_info("file: %s +%d, error\n", __FILE__, __LINE__);
> @@ -549,9 +550,13 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
>   void rxe_net_del(struct ib_device *dev)
>   {
>   	struct sock *sk;
> +	struct rxe_dev *rdev;
> +
> +	rdev = container_of(dev, struct rxe_dev, ib_dev);
>   
>   	rcu_read_lock();
> -	sk = udp4_lib_lookup(&init_net, 0, 0, htonl(INADDR_ANY), htons(ROCE_V2_UDP_DPORT), 0);
> +	sk = udp4_lib_lookup(dev_net(rdev->ndev), 0, 0, htonl(INADDR_ANY),
> +			     htons(ROCE_V2_UDP_DPORT), 0);
>   	rcu_read_unlock();
>   	if (!sk)
>   		return;
> @@ -564,7 +569,8 @@ void rxe_net_del(struct ib_device *dev)
>   		rxe_release_udp_tunnel(sk->sk_socket);
>   
>   	rcu_read_lock();
> -	sk = udp6_lib_lookup(&init_net, NULL, 0, &in6addr_any, htons(ROCE_V2_UDP_DPORT), 0);
> +	sk = udp6_lib_lookup(dev_net(rdev->ndev), NULL, 0, &in6addr_any,
> +			     htons(ROCE_V2_UDP_DPORT), 0);
>   	rcu_read_unlock();
>   	if (!sk)
>   		return;
> @@ -636,6 +642,7 @@ static int rxe_notify(struct notifier_block *not_blk,
>   	switch (event) {
>   	case NETDEV_UNREGISTER:
>   		ib_unregister_device_queued(&rxe->ib_dev);
> +		rxe_net_del(&rxe->ib_dev);
>   		break;
>   	case NETDEV_UP:
>   		rxe_port_up(rxe);
> @@ -669,19 +676,19 @@ static struct notifier_block rxe_net_notifier = {
>   	.notifier_call = rxe_notify,
>   };
>   
> -static int rxe_net_ipv4_init(void)
> +static int rxe_net_ipv4_init(struct net_device *ndev)
>   {
>   	struct sock *sk;
>   	struct socket *sock;
>   
>   	rcu_read_lock();
> -	sk = udp4_lib_lookup(&init_net, 0, 0, htonl(INADDR_ANY),
> +	sk = udp4_lib_lookup(dev_net(ndev), 0, 0, htonl(INADDR_ANY),
>   			     htons(ROCE_V2_UDP_DPORT), 0);
>   	rcu_read_unlock();
>   	if (sk)
>   		return 0;
>   
> -	sock = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false);
> +	sock = rxe_setup_udp_tunnel(dev_net(ndev), htons(ROCE_V2_UDP_DPORT), false);
>   	if (IS_ERR(sock)) {
>   		pr_err("Failed to create IPv4 UDP tunnel\n");
>   		return -1;
> @@ -690,20 +697,20 @@ static int rxe_net_ipv4_init(void)
>   	return 0;
>   }
>   
> -static int rxe_net_ipv6_init(void)
> +static int rxe_net_ipv6_init(struct net_device *ndev)
>   {
>   #if IS_ENABLED(CONFIG_IPV6)
>   	struct sock *sk;
>   	struct socket *sock;
>   
>   	rcu_read_lock();
> -	sk = udp6_lib_lookup(&init_net, NULL, 0, &in6addr_any,
> +	sk = udp6_lib_lookup(dev_net(ndev), NULL, 0, &in6addr_any,
>   			     htons(ROCE_V2_UDP_DPORT), 0);
>   	rcu_read_unlock();
>   	if (sk)
>   		return 0;
>   
> -	sock = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true);
> +	sock = rxe_setup_udp_tunnel(dev_net(ndev), 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;
> @@ -735,14 +742,14 @@ void rxe_net_exit(void)
>   	unregister_netdevice_notifier(&rxe_net_notifier);
>   }
>   
> -int rxe_net_init(void)
> +int rxe_net_init(struct net_device *ndev)
>   {
>   	int err;
>   
> -	err = rxe_net_ipv4_init();
> +	err = rxe_net_ipv4_init(ndev);
>   	if (err)
>   		return err;
> -	err = rxe_net_ipv6_init();
> +	err = rxe_net_ipv6_init(ndev);
>   	if (err)
>   		goto err_out;
>   	return 0;
> diff --git a/drivers/infiniband/sw/rxe/rxe_net.h b/drivers/infiniband/sw/rxe/rxe_net.h
> index 027b20e1bab6..56249677d692 100644
> --- a/drivers/infiniband/sw/rxe/rxe_net.h
> +++ b/drivers/infiniband/sw/rxe/rxe_net.h
> @@ -15,7 +15,7 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev);
>   void rxe_net_del(struct ib_device *dev);
>   
>   int rxe_register_notifier(void);
> -int rxe_net_init(void);
> +int rxe_net_init(struct net_device *ndev);
>   void rxe_net_exit(void);
>   
>   #endif /* RXE_NET_H */