From fb7589a162162223e6bb6422dde3fb1ce07d9a78 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 21 Aug 2013 14:31:38 +0400 Subject: tun: Add ability to create tun device with given index Tun devices cannot be created with ifidex user wants, but it's required by checkpoint-restore project. Long time ago such ability was implemented for rtnl_ops-based interface for creating links (9c7dafbf net: Allow to create links with given ifindex), but the only API for creating and managing tuntap devices is ioctl-based and is evolving with adding new ones (cde8b15f tuntap: add ioctl to attach or detach a file form tuntap device). Following that trend, here's how a new ioctl that sets the ifindex for device, that _will_ be created by TUNSETIFF ioctl looks like. So those who want a tuntap device with the ifindex N, should open the tun device, call ioctl(fd, TUNSETIFINDEX, &N), then call TUNSETIFF. If the index N is busy, then the register_netdev will find this out and the ioctl would be failed with -EBUSY. If setifindex is not called, then it will be generated as before. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- drivers/net/tun.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7ed13cc0dcb2..4b65fbcc490f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -138,7 +138,10 @@ struct tun_file { struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; - u16 queue_index; + union { + u16 queue_index; + unsigned int ifindex; + }; struct list_head next; struct tun_struct *detached; }; @@ -1601,6 +1604,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; + dev->ifindex = tfile->ifindex; tun = netdev_priv(dev); tun->dev = dev; @@ -1817,6 +1821,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, kgid_t group; int sndbuf; int vnet_hdr_sz; + unsigned int ifindex; int ret; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) { @@ -1851,6 +1856,19 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ret = -EFAULT; goto unlock; } + if (cmd == TUNSETIFINDEX) { + ret = -EPERM; + if (tun) + goto unlock; + + ret = -EFAULT; + if (copy_from_user(&ifindex, argp, sizeof(ifindex))) + goto unlock; + + ret = 0; + tfile->ifindex = ifindex; + goto unlock; + } ret = -EBADFD; if (!tun) @@ -2099,6 +2117,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) rcu_assign_pointer(tfile->tun, NULL); tfile->net = get_net(current->nsproxy->net_ns); tfile->flags = 0; + tfile->ifindex = 0; rcu_assign_pointer(tfile->socket.wq, &tfile->wq); init_waitqueue_head(&tfile->wq.wait); -- cgit From 3d407a80b62fc5891b41fe9045f23aba4437fc33 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 21 Aug 2013 14:32:00 +0400 Subject: tun: Report whether the queue is attached or not Multiqueue tun devices allow to attach and detach from its queues while keeping the interface itself set on file. Knowing this is critical for the checkpoint part of criu project. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- drivers/net/tun.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 4b65fbcc490f..db43a2409733 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1881,6 +1881,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, case TUNGETIFF: tun_get_iff(current->nsproxy->net_ns, tun, &ifr); + if (tfile->detached) + ifr.ifr_flags |= IFF_DETACH_QUEUE; + if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; -- cgit From 849c9b6f93cc4cb5eb59301b6380a7a81b43f414 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 21 Aug 2013 14:32:21 +0400 Subject: tun: Allow to skip filter on attach There's a small problem with sk-filters on tun devices. Consider an application doing this sequence of steps: fd = open("/dev/net/tun"); ioctl(fd, TUNSETIFF, { .ifr_name = "tun0" }); ioctl(fd, TUNATTACHFILTER, &my_filter); ioctl(fd, TUNSETPERSIST, 1); close(fd); At that point the tun0 will remain in the system and will keep in mind that there should be a socket filter at address '&my_filter'. If after that we do fd = open("/dev/net/tun"); ioctl(fd, TUNSETIFF, { .ifr_name = "tun0" }); we most likely receive the -EFAULT error, since tun_attach() would try to connect the filter back. But (!) if we provide a filter at address &my_filter, then tun0 will be created and the "new" filter would be attached, but application may not know about that. This may create certain problems to anyone using tun-s, but it's critical problem for c/r -- if we meet a persistent tun device with a filter in mind, we will not be able to attach to it to dump its state (flags, owner, address, vnethdr size, etc.). The proposal is to allow to attach to tun device (with TUNSETIFF) w/o attaching the filter to the tun-file's socket. After this attach app may e.g clean the device by dropping the filter, it doesn't want to have one, or (in case of c/r) get information about the device with tun ioctls. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- drivers/net/tun.c | 12 +++++++----- include/uapi/linux/if_tun.h | 1 + 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index db43a2409733..6acbdbccebcd 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -501,7 +501,7 @@ static void tun_detach_all(struct net_device *dev) module_put(THIS_MODULE); } -static int tun_attach(struct tun_struct *tun, struct file *file) +static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) { struct tun_file *tfile = file->private_data; int err; @@ -526,7 +526,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file) err = 0; /* Re-attach the filter to presist device */ - if (tun->filter_attached == true) { + if (!skip_filter && (tun->filter_attached == true)) { err = sk_attach_filter(&tun->fprog, tfile->socket.sk); if (!err) goto out; @@ -1557,7 +1557,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (err < 0) return err; - err = tun_attach(tun, file); + err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER); if (err < 0) return err; @@ -1631,7 +1631,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) dev->vlan_features = dev->features; INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file); + err = tun_attach(tun, file, false); if (err < 0) goto err_free_dev; @@ -1795,7 +1795,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; - ret = tun_attach(tun, file); + ret = tun_attach(tun, file, false); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached) @@ -1883,6 +1883,8 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, if (tfile->detached) ifr.ifr_flags |= IFF_DETACH_QUEUE; + if (!tfile->socket.sk->sk_filter) + ifr.ifr_flags |= IFF_NOFILTER; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index c58d023c4822..cc127b2b4c3d 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -71,6 +71,7 @@ #define IFF_DETACH_QUEUE 0x0400 /* read-only flag */ #define IFF_PERSIST 0x0800 +#define IFF_NOFILTER 0x1000 /* Socket options */ #define TUN_TX_TIMESTAMP 1 -- cgit From 76975e9cb4a7c6fe39478a3dc4dd292a5c6c8c74 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 21 Aug 2013 14:32:39 +0400 Subject: tun: Get skfilter layout The only thing we may have from tun device is the fprog, whic contains the number of filter elements and a pointer to (user-space) memory where the elements are. The program itself may not be available if the device is persistent and detached. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- drivers/net/tun.c | 10 ++++++++++ include/uapi/linux/if_tun.h | 1 + 2 files changed, 11 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 6acbdbccebcd..60a1e93e9d35 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2042,6 +2042,16 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, tun_detach_filter(tun, tun->numqueues); break; + case TUNGETFILTER: + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = -EFAULT; + if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) + break; + ret = 0; + break; + default: ret = -EINVAL; break; diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index cc127b2b4c3d..e9502dd1ee2c 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -57,6 +57,7 @@ #define TUNSETVNETHDRSZ _IOW('T', 216, int) #define TUNSETQUEUE _IOW('T', 217, int) #define TUNSETIFINDEX _IOW('T', 218, unsigned int) +#define TUNGETFILTER _IOR('T', 219, struct sock_fprog) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 -- cgit