On 4/28/23 04:39, Zhu Yanjun wrote:
> From: Zhu Yanjun <yanjun.zhu@xxxxxxxxx>
>
> When running "rdma link del" command, dellink function will be called.
> If the sock refcnt is greater than the refcnt needed for udp tunnel,
> the sock refcnt will be decreased by 1.
>
> If equal, the last rdma link is removed. The udp tunnel will be
> destroyed.
>
> Tested-by: Rain River <rain.1986.08.12@xxxxxxxxx>
> Signed-off-by: Zhu Yanjun <yanjun.zhu@xxxxxxxxx>
> ---
> drivers/infiniband/sw/rxe/rxe.c | 12 +++++++++++-
> drivers/infiniband/sw/rxe/rxe_net.c | 17 +++++++++++++++--
> drivers/infiniband/sw/rxe/rxe_net.h | 1 +
> 3 files changed, 27 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
> index 0ce6adb43cfc..ebfabc6d6b76 100644
> --- a/drivers/infiniband/sw/rxe/rxe.c
> +++ b/drivers/infiniband/sw/rxe/rxe.c
> @@ -166,10 +166,12 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
> /* called by ifc layer to create new rxe device.
> * The caller should allocate memory for rxe by calling ib_alloc_device.
> */
> +static struct rdma_link_ops rxe_link_ops;
> int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name)
> {
> rxe_init(rxe);
> rxe_set_mtu(rxe, mtu);
> + rxe->ib_dev.link_ops = &rxe_link_ops;
>
> return rxe_register_device(rxe, ibdev_name);
> }
> @@ -206,9 +208,17 @@ static int rxe_newlink(const char *ibdev_name, struct net_device *ndev)
> return err;
> }
>
> -struct rdma_link_ops rxe_link_ops = {
> +static int rxe_dellink(struct ib_device *dev)
> +{
> + rxe_net_del(dev);
> +
> + return 0;
> +}
> +
> +static struct rdma_link_ops rxe_link_ops = {
> .type = "rxe",
> .newlink = rxe_newlink,
> + .dellink = rxe_dellink,
> };
>
> static int __init rxe_module_init(void)
> diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
> index 3ca92e062800..4cc7de7b115b 100644
> --- a/drivers/infiniband/sw/rxe/rxe_net.c
> +++ b/drivers/infiniband/sw/rxe/rxe_net.c
> @@ -530,6 +530,21 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
> return 0;
> }
>
> +#define SK_REF_FOR_TUNNEL 2
> +void rxe_net_del(struct ib_device *dev)
> +{
> + if (refcount_read(&recv_sockets.sk6->sk->sk_refcnt) > SK_REF_FOR_TUNNEL)
> + __sock_put(recv_sockets.sk6->sk);
> + else
> + rxe_release_udp_tunnel(recv_sockets.sk6);
> +
> + if (refcount_read(&recv_sockets.sk4->sk->sk_refcnt) > SK_REF_FOR_TUNNEL)
> + __sock_put(recv_sockets.sk4->sk);
> + else
> + rxe_release_udp_tunnel(recv_sockets.sk4);
> +}
> +#undef SK_REF_FOR_TUNNEL
> +
> static void rxe_port_event(struct rxe_dev *rxe,
> enum ib_event_type event)
> {
> @@ -689,8 +704,6 @@ int rxe_register_notifier(void)
>
> void rxe_net_exit(void)
> {
> - rxe_release_udp_tunnel(recv_sockets.sk6);
> - rxe_release_udp_tunnel(recv_sockets.sk4);
> unregister_netdevice_notifier(&rxe_net_notifier);
> }
These calls are moved to rxe_net_del which is called by an explicit unlink command.
But if rxe_net_init fails and returns an error code this will never happen.
This will result in leaking resources.
Bob
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_net.h b/drivers/infiniband/sw/rxe/rxe_net.h
> index a222c3eeae12..f48f22f3353b 100644
> --- a/drivers/infiniband/sw/rxe/rxe_net.h
> +++ b/drivers/infiniband/sw/rxe/rxe_net.h
> @@ -17,6 +17,7 @@ struct rxe_recv_sockets {
> };
>
> 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);
