From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [PATCH RFC] tun: export underlying socket Date: Fri, 11 Sep 2009 07:59:43 +0300 Message-ID: <20090911045943.GA1613@redhat.com> References: <20090910125929.GA32593@redhat.com> <200909110017.27668.paul.moore@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: David Miller , netdev@vger.kernel.org, herbert@gondor.apana.org.au To: Paul Moore Return-path: Received: from mx1.redhat.com ([209.132.183.28]:3336 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751222AbZIKFBY (ORCPT ); Fri, 11 Sep 2009 01:01:24 -0400 Content-Disposition: inline In-Reply-To: <200909110017.27668.paul.moore@hp.com> Sender: netdev-owner@vger.kernel.org List-ID: On Fri, Sep 11, 2009 at 12:17:27AM -0400, Paul Moore wrote: > On Thursday 10 September 2009 08:59:29 am Michael S. Tsirkin wrote: > > Tun device looks similar to a packet socket > > in that both pass complete frames from/to userspace. > > > > This patch fills in enough fields in the socket underlying tun driver > > to support sendmsg/recvmsg operations, and exports access to this socket > > to modules. > > > > This way, code using raw sockets to inject packets > > into a physical device, can support injecting > > packets into host network stack almost without modification. > > > > First user of this interface will be vhost virtualization > > accelerator. > > No comments on the code at this point - I'm just trying to understand the > intended user right now which I'm assuming is the vhost-net bits you sent > previously? Yes - these now use raw socket, I'll add something like sock = tun_get_socket(file) if (!IS_ERR(sock)) { return sock; } > > Signed-off-by: Michael S. Tsirkin > > --- > > > > This patch is on top of net-next master. > > An alternative approach would be to add an ioctl to tun, to export the > > underlying socket to userspace: a uniform way to work with a network > > device and the host stack might be useful there, as well. > > Kernel users could then do sockfd_lookup to get the socket. > > I decided against it for now as it requires more code. > > Please comment. > > > > drivers/net/tun.c | 78 > > +++++++++++++++++++++++++++++++++++++++++++---- include/linux/if_tun.h | > > 14 ++++++++ > > 2 files changed, 85 insertions(+), 7 deletions(-) > > > > diff --git a/drivers/net/tun.c b/drivers/net/tun.c > > index 589a44a..76f5faa 100644 > > --- a/drivers/net/tun.c > > +++ b/drivers/net/tun.c > > @@ -151,6 +151,7 @@ static int tun_attach(struct tun_struct *tun, struct > > file *file) err = 0; > > tfile->tun = tun; > > tun->tfile = tfile; > > + tun->socket.file = file; > > dev_hold(tun->dev); > > sock_hold(tun->socket.sk); > > atomic_inc(&tfile->count); > > @@ -165,6 +166,7 @@ static void __tun_detach(struct tun_struct *tun) > > /* Detach from net device */ > > netif_tx_lock_bh(tun->dev); > > tun->tfile = NULL; > > + tun->socket.file = NULL; > > netif_tx_unlock_bh(tun->dev); > > > > /* Drop read queue */ > > @@ -750,7 +752,7 @@ static __inline__ ssize_t tun_put_user(struct > > tun_struct *tun, len = min_t(int, skb->len, len); > > > > skb_copy_datagram_const_iovec(skb, 0, iv, total, len); > > - total += len; > > + total += skb->len; > > > > tun->dev->stats.tx_packets++; > > tun->dev->stats.tx_bytes += len; > > @@ -758,12 +760,10 @@ static __inline__ ssize_t tun_put_user(struct > > tun_struct *tun, return total; > > } > > > > -static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec > > *iv, - unsigned long count, loff_t pos) > > +static ssize_t tun_do_read(struct tun_struct *tun, > > + struct kiocb *iocb, const struct iovec *iv, > > + unsigned long count, int noblock) > > { > > - struct file *file = iocb->ki_filp; > > - struct tun_file *tfile = file->private_data; > > - struct tun_struct *tun = __tun_get(tfile); > > DECLARE_WAITQUEUE(wait, current); > > struct sk_buff *skb; > > ssize_t len, ret = 0; > > @@ -785,7 +785,7 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, > > const struct iovec *iv, > > > > /* Read frames from the queue */ > > if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) { > > - if (file->f_flags & O_NONBLOCK) { > > + if (noblock) { > > ret = -EAGAIN; > > break; > > } > > @@ -813,6 +813,21 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, > > const struct iovec *iv, remove_wait_queue(&tun->socket.wait, &wait); > > > > out: > > + return ret; > > +} > > + > > +static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec > > *iv, + unsigned long count, loff_t pos) > > +{ > > + struct file *file = iocb->ki_filp; > > + struct tun_file *tfile = file->private_data; > > + struct tun_struct *tun = __tun_get(tfile); > > + ssize_t ret; > > + > > + if (!tun) > > + return -EBADFD; > > + ret = tun_do_read(tun, iocb, iv, count, file->f_flags & O_NONBLOCK); > > + ret = min_t(ssize_t, ret, count); > > tun_put(tun); > > return ret; > > } > > @@ -865,6 +880,37 @@ static void tun_sock_destruct(struct sock *sk) > > free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev); > > } > > > > +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, > > + struct msghdr *m, size_t total_len) > > +{ > > + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); > > + return tun_get_user(tun, m->msg_iov, total_len, > > + m->msg_flags & MSG_DONTWAIT); > > +} > > + > > +static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, > > + struct msghdr *m, size_t total_len, > > + int flags) > > +{ > > + struct tun_struct *tun = container_of(sock, struct tun_struct, socket); > > + int ret; > > + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) > > + return -EINVAL; > > + ret = tun_do_read(tun, iocb, m->msg_iov, total_len, > > + flags & MSG_DONTWAIT); > > + if (ret > total_len) { > > + m->msg_flags |= MSG_TRUNC; > > + ret = flags & MSG_TRUNC ? ret : total_len; > > + } > > + return ret; > > +} > > + > > +/* Ops structure to mimic raw sockets with tun */ > > +static const struct proto_ops tun_socket_ops = { > > + .sendmsg = tun_sendmsg, > > + .recvmsg = tun_recvmsg, > > +}; > > + > > static struct proto tun_proto = { > > .name = "tun", > > .owner = THIS_MODULE, > > @@ -982,6 +1028,7 @@ static int tun_set_iff(struct net *net, struct file > > *file, struct ifreq *ifr) goto err_free_dev; > > > > init_waitqueue_head(&tun->socket.wait); > > + tun->socket.ops = &tun_socket_ops; > > sock_init_data(&tun->socket, sk); > > sk->sk_write_space = tun_sock_write_space; > > sk->sk_sndbuf = INT_MAX; > > @@ -1483,6 +1530,23 @@ static void tun_cleanup(void) > > rtnl_link_unregister(&tun_link_ops); > > } > > > > +/* Get an underlying socket object from tun file. Returns error unless > > file is + * attached to a device. The returned object works like a packet > > socket, it + * can be used for sock_sendmsg/sock_recvmsg. The caller is > > responsible for + * holding a reference to the file for as long as the > > socket is in use. */ +struct socket *tun_get_socket(struct file *file) > > +{ > > + struct tun_struct *tun; > > + if (file->f_op != &tun_fops) > > + return ERR_PTR(-EINVAL); > > + tun = tun_get(file); > > + if (!tun) > > + return ERR_PTR(-EBADFD); > > + tun_put(tun); > > + return &tun->socket; > > +} > > +EXPORT_SYMBOL_GPL(tun_get_socket); > > + > > module_init(tun_init); > > module_exit(tun_cleanup); > > MODULE_DESCRIPTION(DRV_DESCRIPTION); > > diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h > > index 3f5fd52..404abe0 100644 > > --- a/include/linux/if_tun.h > > +++ b/include/linux/if_tun.h > > @@ -86,4 +86,18 @@ struct tun_filter { > > __u8 addr[0][ETH_ALEN]; > > }; > > > > +#ifdef __KERNEL__ > > +#if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) > > +struct socket *tun_get_socket(struct file *); > > +#else > > +#include > > +#include > > +struct file; > > +struct socket; > > +static inline struct socket *tun_get_socket(struct file *f) > > +{ > > + return ERR_PTR(-EINVAL); > > +} > > +#endif /* CONFIG_TUN */ > > +#endif /* __KERNEL__ */ > > #endif /* __IF_TUN_H */ > > > > -- > paul moore > linux @ hp