RE: [PATCH net-next 11/14] vsock: add multi-transports support

[Jorgen Hansen via Virtualization <virtualization@lists.linux-foundation.org>]

> From: Stefano Garzarella [mailto:sgarzare@redhat.com]
> Sent: Wednesday, October 23, 2019 11:56 AM

Thanks a lot for working on this!

> With the multi-transports support, we can use vsock with nested VMs (using
> also different hypervisors) loading both guest->host and
> host->guest transports at the same time.
> 
> Major changes:
> - vsock core module can be loaded regardless of the transports
> - vsock_core_init() and vsock_core_exit() are renamed to
>   vsock_core_register() and vsock_core_unregister()
> - vsock_core_register() has a feature parameter (H2G, G2H, DGRAM)
>   to identify which directions the transport can handle and if it's
>   support DGRAM (only vmci)
> - each stream socket is assigned to a transport when the remote CID
>   is set (during the connect() or when we receive a connection request
>   on a listener socket).

How about allowing the transport to be set during bind as well? That
would allow an application to ensure that it is using a specific transport,
i.e., if it binds to the host CID, it will use H2G, and if it binds to something
else it will use G2H? You can still use VMADDR_CID_ANY if you want to
initially listen to both transports.


>   The remote CID is used to decide which transport to use:
>   - remote CID > VMADDR_CID_HOST will use host->guest transport
>   - remote CID <= VMADDR_CID_HOST will use guest->host transport
> - listener sockets are not bound to any transports since no transport
>   operations are done on it. In this way we can create a listener
>   socket, also if the transports are not loaded or with VMADDR_CID_ANY
>   to listen on all transports.
> - DGRAM sockets are handled as before, since only the vmci_transport
>   provides this feature.
> 
> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
> ---
> RFC -> v1:
> - documented VSOCK_TRANSPORT_F_* flags
> - fixed vsock_assign_transport() when the socket is already assigned
>   (e.g connection failed)
> - moved features outside of struct vsock_transport, and used as
>   parameter of vsock_core_register()
> ---
>  drivers/vhost/vsock.c                   |   5 +-
>  include/net/af_vsock.h                  |  17 +-
>  net/vmw_vsock/af_vsock.c                | 237 ++++++++++++++++++------
>  net/vmw_vsock/hyperv_transport.c        |  26 ++-
>  net/vmw_vsock/virtio_transport.c        |   7 +-
>  net/vmw_vsock/virtio_transport_common.c |  28 ++-
>  net/vmw_vsock/vmci_transport.c          |  31 +++-
>  7 files changed, 270 insertions(+), 81 deletions(-)
> 


> diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index
> d89381166028..dddd85d9a147 100644
> --- a/net/vmw_vsock/af_vsock.c
> +++ b/net/vmw_vsock/af_vsock.c
> @@ -130,7 +130,12 @@ static struct proto vsock_proto = {  #define
> VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256)  #define
> VSOCK_DEFAULT_BUFFER_MIN_SIZE 128
> 
> -static const struct vsock_transport *transport_single;
> +/* Transport used for host->guest communication */ static const struct
> +vsock_transport *transport_h2g;
> +/* Transport used for guest->host communication */ static const struct
> +vsock_transport *transport_g2h;
> +/* Transport used for DGRAM communication */ static const struct
> +vsock_transport *transport_dgram;
>  static DEFINE_MUTEX(vsock_register_mutex);
> 
>  /**** UTILS ****/
> @@ -182,7 +187,7 @@ static int vsock_auto_bind(struct vsock_sock *vsk)
>  	return __vsock_bind(sk, &local_addr);
>  }
> 
> -static int __init vsock_init_tables(void)
> +static void vsock_init_tables(void)
>  {
>  	int i;
> 
> @@ -191,7 +196,6 @@ static int __init vsock_init_tables(void)
> 
>  	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
>  		INIT_LIST_HEAD(&vsock_connected_table[i]);
> -	return 0;
>  }
> 
>  static void __vsock_insert_bound(struct list_head *list, @@ -376,6 +380,62
> @@ void vsock_enqueue_accept(struct sock *listener, struct sock
> *connected)  }  EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
> 
> +/* Assign a transport to a socket and call the .init transport callback.
> + *
> + * Note: for stream socket this must be called when vsk->remote_addr is
> +set
> + * (e.g. during the connect() or when a connection request on a
> +listener
> + * socket is received).
> + * The vsk->remote_addr is used to decide which transport to use:
> + *  - remote CID > VMADDR_CID_HOST will use host->guest transport
> + *  - remote CID <= VMADDR_CID_HOST will use guest->host transport  */
> +int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock
> +*psk) {
> +	const struct vsock_transport *new_transport;
> +	struct sock *sk = sk_vsock(vsk);
> +
> +	switch (sk->sk_type) {
> +	case SOCK_DGRAM:
> +		new_transport = transport_dgram;
> +		break;
> +	case SOCK_STREAM:
> +		if (vsk->remote_addr.svm_cid > VMADDR_CID_HOST)
> +			new_transport = transport_h2g;
> +		else
> +			new_transport = transport_g2h;
> +		break;

You already mentioned that you are working on a fix for loopback
here for the guest, but presumably a host could also do loopback.
If we select transport during bind to a specific CID, this comment
Isn't relevant, but otherwise, we should look at the local addr as
well, since a socket with local addr of host CID shouldn't use
the guest to host transport, and a socket with local addr > host CID
shouldn't use host to guest.


> +	default:
> +		return -ESOCKTNOSUPPORT;
> +	}
> +
> +	if (vsk->transport) {
> +		if (vsk->transport == new_transport)
> +			return 0;
> +
> +		vsk->transport->release(vsk);
> +		vsk->transport->destruct(vsk);
> +	}
> +
> +	if (!new_transport)
> +		return -ENODEV;
> +
> +	vsk->transport = new_transport;
> +
> +	return vsk->transport->init(vsk, psk); }
> +EXPORT_SYMBOL_GPL(vsock_assign_transport);
> +
> +static bool vsock_find_cid(unsigned int cid) {
> +	if (transport_g2h && cid == transport_g2h->get_local_cid())
> +		return true;
> +
> +	if (transport_h2g && cid == VMADDR_CID_HOST)
> +		return true;
> +
> +	return false;
> +}
> +
>  static struct sock *vsock_dequeue_accept(struct sock *listener)  {
>  	struct vsock_sock *vlistener;


> diff --git a/net/vmw_vsock/vmci_transport.c
> b/net/vmw_vsock/vmci_transport.c index 5955238ffc13..2eb3f16d53e7
> 100644
> --- a/net/vmw_vsock/vmci_transport.c
> +++ b/net/vmw_vsock/vmci_transport.c

> @@ -1017,6 +1018,15 @@ static int vmci_transport_recv_listen(struct sock
> *sk,
>  	vsock_addr_init(&vpending->remote_addr, pkt->dg.src.context,
>  			pkt->src_port);
> 
> +	err = vsock_assign_transport(vpending, vsock_sk(sk));
> +	/* Transport assigned (looking at remote_addr) must be the same
> +	 * where we received the request.
> +	 */
> +	if (err || !vmci_check_transport(vpending)) {

We need to send a reset on error, i.e.,
  vmci_transport_send_reset(sk, pkt);

> +		sock_put(pending);
> +		return err;
> +	}
> +
>  	/* If the proposed size fits within our min/max, accept it. Otherwise
>  	 * propose our own size.
>  	 */

Thanks,
Jorgen