On Thu, Sep 06, 2018 at 12:05:23PM +0800, Jason Wang wrote:
> This patch introduces to a new tun/tap specific msg_control:
>
> #define TUN_MSG_UBUF 1
> #define TUN_MSG_PTR 2
> struct tun_msg_ctl {
> int type;
> void *ptr;
> };
>
> This allows us to pass different kinds of msg_control through
> sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will
> be used by the existed vhost_net zerocopy code. The second is XDP
> buff, which allows vhost_net to pass XDP buff to TUN. This could be
> used to implement accepting an array of XDP buffs from vhost_net in
> the following patches.
>
> Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
At this point, do we want to just add a new sock opt for tap's
benefit? Seems cleaner than (ab)using sendmsg.
> ---
> drivers/net/tap.c | 18 ++++++++++++------
> drivers/net/tun.c | 6 +++++-
> drivers/vhost/net.c | 7 +++++--
> include/linux/if_tun.h | 7 +++++++
> 4 files changed, 29 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/net/tap.c b/drivers/net/tap.c
> index f0f7cd977667..7996ed7cbf18 100644
> --- a/drivers/net/tap.c
> +++ b/drivers/net/tap.c
> @@ -619,7 +619,7 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad,
> #define TAP_RESERVE HH_DATA_OFF(ETH_HLEN)
>
> /* Get packet from user space buffer */
> -static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
> +static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
> struct iov_iter *from, int noblock)
> {
> int good_linear = SKB_MAX_HEAD(TAP_RESERVE);
> @@ -663,7 +663,7 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
> if (unlikely(len < ETH_HLEN))
> goto err;
>
> - if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
> + if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
> struct iov_iter i;
>
> copylen = vnet_hdr.hdr_len ?
> @@ -724,11 +724,11 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
> tap = rcu_dereference(q->tap);
> /* copy skb_ubuf_info for callback when skb has no error */
> if (zerocopy) {
> - skb_shinfo(skb)->destructor_arg = m->msg_control;
> + skb_shinfo(skb)->destructor_arg = msg_control;
> skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
> skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
> - } else if (m && m->msg_control) {
> - struct ubuf_info *uarg = m->msg_control;
> + } else if (msg_control) {
> + struct ubuf_info *uarg = msg_control;
> uarg->callback(uarg, false);
> }
>
> @@ -1150,7 +1150,13 @@ static int tap_sendmsg(struct socket *sock, struct msghdr *m,
> size_t total_len)
> {
> struct tap_queue *q = container_of(sock, struct tap_queue, sock);
> - return tap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT);
> + struct tun_msg_ctl *ctl = m->msg_control;
> +
> + if (ctl && ctl->type != TUN_MSG_UBUF)
> + return -EINVAL;
> +
> + return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter,
> + m->msg_flags & MSG_DONTWAIT);
> }
>
> static int tap_recvmsg(struct socket *sock, struct msghdr *m,
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index ff1cbf3ebd50..c839a4bdcbd9 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -2429,11 +2429,15 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
> int ret;
> struct tun_file *tfile = container_of(sock, struct tun_file, socket);
> struct tun_struct *tun = tun_get(tfile);
> + struct tun_msg_ctl *ctl = m->msg_control;
>
> if (!tun)
> return -EBADFD;
>
> - ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
> + if (ctl && ctl->type != TUN_MSG_UBUF)
> + return -EINVAL;
> +
> + ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter,
> m->msg_flags & MSG_DONTWAIT,
> m->msg_flags & MSG_MORE);
> tun_put(tun);
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 4e656f89cb22..fb01ce6d981c 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -620,6 +620,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
> .msg_controllen = 0,
> .msg_flags = MSG_DONTWAIT,
> };
> + struct tun_msg_ctl ctl;
> size_t len, total_len = 0;
> int err;
> struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
> @@ -664,8 +665,10 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
> ubuf->ctx = nvq->ubufs;
> ubuf->desc = nvq->upend_idx;
> refcount_set(&ubuf->refcnt, 1);
> - msg.msg_control = ubuf;
> - msg.msg_controllen = sizeof(ubuf);
> + msg.msg_control = &ctl;
> + ctl.type = TUN_MSG_UBUF;
> + ctl.ptr = ubuf;
> + msg.msg_controllen = sizeof(ctl);
> ubufs = nvq->ubufs;
> atomic_inc(&ubufs->refcount);
> nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
> diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
> index 3d2996dc7d85..ba46dced1f38 100644
> --- a/include/linux/if_tun.h
> +++ b/include/linux/if_tun.h
> @@ -19,6 +19,13 @@
>
> #define TUN_XDP_FLAG 0x1UL
>
> +#define TUN_MSG_UBUF 1
> +#define TUN_MSG_PTR 2
Looks like TUN_MSG_PTR should be pushed out to a follow-up patch?
> +struct tun_msg_ctl {
> + int type;
> + void *ptr;
> +};
> +
type actually includes a size. Why not two short fields then?
> #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
> struct socket *tun_get_socket(struct file *);
> struct ptr_ring *tun_get_tx_ring(struct file *file);
> --
> 2.17.1
