From fc0663d6b5e6d8e9b57f872a644c0aafd82361b7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:23:40 +0000 Subject: macvlan: allow multiple driver backends This makes it possible to hook into the macvlan driver from another kernel module. In particular, the goal is to extend it with the macvtap backend that provides a tun/tap compatible interface directly on the macvlan device. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux/if_macvlan.h') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 5f200bac374..9a11544bb0b 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -1,6 +1,76 @@ #ifndef _LINUX_IF_MACVLAN_H #define _LINUX_IF_MACVLAN_H +#include +#include +#include +#include +#include + +struct macvlan_port; +struct macvtap_queue; + +/** + * struct macvlan_rx_stats - MACVLAN percpu rx stats + * @rx_packets: number of received packets + * @rx_bytes: number of received bytes + * @multicast: number of received multicast packets + * @rx_errors: number of errors + */ +struct macvlan_rx_stats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long multicast; + unsigned long rx_errors; +}; + +struct macvlan_dev { + struct net_device *dev; + struct list_head list; + struct hlist_node hlist; + struct macvlan_port *port; + struct net_device *lowerdev; + struct macvlan_rx_stats *rx_stats; + enum macvlan_mode mode; + int (*receive)(struct sk_buff *skb); + int (*forward)(struct net_device *dev, struct sk_buff *skb); +}; + +static inline void macvlan_count_rx(const struct macvlan_dev *vlan, + unsigned int len, bool success, + bool multicast) +{ + struct macvlan_rx_stats *rx_stats; + + rx_stats = per_cpu_ptr(vlan->rx_stats, smp_processor_id()); + if (likely(success)) { + rx_stats->rx_packets++;; + rx_stats->rx_bytes += len; + if (multicast) + rx_stats->multicast++; + } else { + rx_stats->rx_errors++; + } +} + +extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + int (*receive)(struct sk_buff *skb), + int (*forward)(struct net_device *dev, + struct sk_buff *skb)); + +extern void macvlan_count_rx(const struct macvlan_dev *vlan, + unsigned int len, bool success, + bool multicast); + +extern void macvlan_dellink(struct net_device *dev, struct list_head *head); + +extern int macvlan_link_register(struct rtnl_link_ops *ops); + +extern netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, + struct net_device *dev); + + extern struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *); #endif /* _LINUX_IF_MACVLAN_H */ -- cgit v1.2.3-70-g09d2 From 20d29d7a916a47bf533b5709437fe735b6b5b79e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 30 Jan 2010 12:24:26 +0000 Subject: net: macvtap driver In order to use macvlan with qemu and other tools that require a tap file descriptor, the macvtap driver adds a small backend with a character device with the same interface as the tun driver, with a minimum set of features. Macvtap interfaces are created in the same way as macvlan interfaces using ip link, but the netif is just used as a handle for configuration and accounting, while the data goes through the chardev. Each macvtap interface has its own character device, simplifying permission management significantly over the generic tun/tap driver. Cc: Patrick McHardy Cc: Stephen Hemminger Cc: David S. Miller" Cc: "Michael S. Tsirkin" Cc: Herbert Xu Cc: Or Gerlitz Cc: netdev@vger.kernel.org Cc: bridge@lists.linux-foundation.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/Kconfig | 12 + drivers/net/Makefile | 1 + drivers/net/macvtap.c | 581 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/if_macvlan.h | 1 + 4 files changed, 595 insertions(+) create mode 100644 drivers/net/macvtap.c (limited to 'include/linux/if_macvlan.h') diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index cb0e534418e..411e2070311 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -90,6 +90,18 @@ config MACVLAN To compile this driver as a module, choose M here: the module will be called macvlan. +config MACVTAP + tristate "MAC-VLAN based tap driver (EXPERIMENTAL)" + depends on MACVLAN + help + This adds a specialized tap character device driver that is based + on the MAC-VLAN network interface, called macvtap. A macvtap device + can be added in the same way as a macvlan device, using 'type + macvlan', and then be accessed through the tap user space interface. + + To compile this driver as a module, choose M here: the module + will be called macvtap. + config EQUALIZER tristate "EQL (serial line load balancing) support" ---help--- diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 0b763cbe9b1..95958032cd3 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -169,6 +169,7 @@ obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o obj-$(CONFIG_DUMMY) += dummy.o obj-$(CONFIG_IFB) += ifb.o obj-$(CONFIG_MACVLAN) += macvlan.o +obj-$(CONFIG_MACVTAP) += macvtap.o obj-$(CONFIG_DE600) += de600.o obj-$(CONFIG_DE620) += de620.o obj-$(CONFIG_LANCE) += lance.o diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c new file mode 100644 index 00000000000..ad1f6ef8930 --- /dev/null +++ b/drivers/net/macvtap.c @@ -0,0 +1,581 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * A macvtap queue is the central object of this driver, it connects + * an open character device to a macvlan interface. There can be + * multiple queues on one interface, which map back to queues + * implemented in hardware on the underlying device. + * + * macvtap_proto is used to allocate queues through the sock allocation + * mechanism. + * + * TODO: multiqueue support is currently not implemented, even though + * macvtap is basically prepared for that. We will need to add this + * here as well as in virtio-net and qemu to get line rate on 10gbit + * adapters from a guest. + */ +struct macvtap_queue { + struct sock sk; + struct socket sock; + struct macvlan_dev *vlan; + struct file *file; +}; + +static struct proto macvtap_proto = { + .name = "macvtap", + .owner = THIS_MODULE, + .obj_size = sizeof (struct macvtap_queue), +}; + +/* + * Minor number matches netdev->ifindex, so need a potentially + * large value. This also makes it possible to split the + * tap functionality out again in the future by offering it + * from other drivers besides macvtap. As long as every device + * only has one tap, the interface numbers assure that the + * device nodes are unique. + */ +static unsigned int macvtap_major; +#define MACVTAP_NUM_DEVS 65536 +static struct class *macvtap_class; +static struct cdev macvtap_cdev; + +/* + * RCU usage: + * The macvtap_queue is referenced both from the chardev struct file + * and from the struct macvlan_dev using rcu_read_lock. + * + * We never actually update the contents of a macvtap_queue atomically + * with RCU but it is used for race-free destruction of a queue when + * either the file or the macvlan_dev goes away. Pointers back to + * the dev and the file are implicitly valid as long as the queue + * exists. + * + * The callbacks from macvlan are always done with rcu_read_lock held + * already, while in the file_operations, we get it ourselves. + * + * When destroying a queue, we remove the pointers from the file and + * from the dev and then synchronize_rcu to make sure no thread is + * still using the queue. There may still be references to the struct + * sock inside of the queue from outbound SKBs, but these never + * reference back to the file or the dev. The data structure is freed + * through __sk_free when both our references and any pending SKBs + * are gone. + * + * macvtap_lock is only used to prevent multiple concurrent open() + * calls to assign a new vlan->tap pointer. It could be moved into + * the macvlan_dev itself but is extremely rarely used. + */ +static DEFINE_SPINLOCK(macvtap_lock); + +/* + * Choose the next free queue, for now there is only one + */ +static int macvtap_set_queue(struct net_device *dev, struct file *file, + struct macvtap_queue *q) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + int err = -EBUSY; + + spin_lock(&macvtap_lock); + if (rcu_dereference(vlan->tap)) + goto out; + + err = 0; + q->vlan = vlan; + rcu_assign_pointer(vlan->tap, q); + + q->file = file; + rcu_assign_pointer(file->private_data, q); + +out: + spin_unlock(&macvtap_lock); + return err; +} + +/* + * We must destroy each queue exactly once, when either + * the netdev or the file go away. + * + * Using the spinlock makes sure that we don't get + * to the queue again after destroying it. + * + * synchronize_rcu serializes with the packet flow + * that uses rcu_read_lock. + */ +static void macvtap_del_queue(struct macvtap_queue **qp) +{ + struct macvtap_queue *q; + + spin_lock(&macvtap_lock); + q = rcu_dereference(*qp); + if (!q) { + spin_unlock(&macvtap_lock); + return; + } + + rcu_assign_pointer(q->vlan->tap, NULL); + rcu_assign_pointer(q->file->private_data, NULL); + spin_unlock(&macvtap_lock); + + synchronize_rcu(); + sock_put(&q->sk); +} + +/* + * Since we only support one queue, just dereference the pointer. + */ +static struct macvtap_queue *macvtap_get_queue(struct net_device *dev, + struct sk_buff *skb) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + + return rcu_dereference(vlan->tap); +} + +static void macvtap_del_queues(struct net_device *dev) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + macvtap_del_queue(&vlan->tap); +} + +static inline struct macvtap_queue *macvtap_file_get_queue(struct file *file) +{ + rcu_read_lock_bh(); + return rcu_dereference(file->private_data); +} + +static inline void macvtap_file_put_queue(void) +{ + rcu_read_unlock_bh(); +} + +/* + * Forward happens for data that gets sent from one macvlan + * endpoint to another one in bridge mode. We just take + * the skb and put it into the receive queue. + */ +static int macvtap_forward(struct net_device *dev, struct sk_buff *skb) +{ + struct macvtap_queue *q = macvtap_get_queue(dev, skb); + if (!q) + return -ENOLINK; + + skb_queue_tail(&q->sk.sk_receive_queue, skb); + wake_up(q->sk.sk_sleep); + return 0; +} + +/* + * Receive is for data from the external interface (lowerdev), + * in case of macvtap, we can treat that the same way as + * forward, which macvlan cannot. + */ +static int macvtap_receive(struct sk_buff *skb) +{ + skb_push(skb, ETH_HLEN); + return macvtap_forward(skb->dev, skb); +} + +static int macvtap_newlink(struct net *src_net, + struct net_device *dev, + struct nlattr *tb[], + struct nlattr *data[]) +{ + struct device *classdev; + dev_t devt; + int err; + + err = macvlan_common_newlink(src_net, dev, tb, data, + macvtap_receive, macvtap_forward); + if (err) + goto out; + + devt = MKDEV(MAJOR(macvtap_major), dev->ifindex); + + classdev = device_create(macvtap_class, &dev->dev, devt, + dev, "tap%d", dev->ifindex); + if (IS_ERR(classdev)) { + err = PTR_ERR(classdev); + macvtap_del_queues(dev); + } + +out: + return err; +} + +static void macvtap_dellink(struct net_device *dev, + struct list_head *head) +{ + device_destroy(macvtap_class, + MKDEV(MAJOR(macvtap_major), dev->ifindex)); + + macvtap_del_queues(dev); + macvlan_dellink(dev, head); +} + +static struct rtnl_link_ops macvtap_link_ops __read_mostly = { + .kind = "macvtap", + .newlink = macvtap_newlink, + .dellink = macvtap_dellink, +}; + + +static void macvtap_sock_write_space(struct sock *sk) +{ + if (!sock_writeable(sk) || + !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) + return; + + if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + wake_up_interruptible_sync(sk->sk_sleep); +} + +static int macvtap_open(struct inode *inode, struct file *file) +{ + struct net *net = current->nsproxy->net_ns; + struct net_device *dev = dev_get_by_index(net, iminor(inode)); + struct macvtap_queue *q; + int err; + + err = -ENODEV; + if (!dev) + goto out; + + /* check if this is a macvtap device */ + err = -EINVAL; + if (dev->rtnl_link_ops != &macvtap_link_ops) + goto out; + + err = -ENOMEM; + q = (struct macvtap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, + &macvtap_proto); + if (!q) + goto out; + + init_waitqueue_head(&q->sock.wait); + q->sock.type = SOCK_RAW; + q->sock.state = SS_CONNECTED; + sock_init_data(&q->sock, &q->sk); + q->sk.sk_allocation = GFP_ATOMIC; /* for now */ + q->sk.sk_write_space = macvtap_sock_write_space; + + err = macvtap_set_queue(dev, file, q); + if (err) + sock_put(&q->sk); + +out: + if (dev) + dev_put(dev); + + return err; +} + +static int macvtap_release(struct inode *inode, struct file *file) +{ + macvtap_del_queue((struct macvtap_queue **)&file->private_data); + return 0; +} + +static unsigned int macvtap_poll(struct file *file, poll_table * wait) +{ + struct macvtap_queue *q = macvtap_file_get_queue(file); + unsigned int mask = POLLERR; + + if (!q) + goto out; + + mask = 0; + poll_wait(file, &q->sock.wait, wait); + + if (!skb_queue_empty(&q->sk.sk_receive_queue)) + mask |= POLLIN | POLLRDNORM; + + if (sock_writeable(&q->sk) || + (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) && + sock_writeable(&q->sk))) + mask |= POLLOUT | POLLWRNORM; + +out: + macvtap_file_put_queue(); + return mask; +} + +/* Get packet from user space buffer */ +static ssize_t macvtap_get_user(struct macvtap_queue *q, + const struct iovec *iv, size_t count, + int noblock) +{ + struct sk_buff *skb; + size_t len = count; + int err; + + if (unlikely(len < ETH_HLEN)) + return -EINVAL; + + skb = sock_alloc_send_skb(&q->sk, NET_IP_ALIGN + len, noblock, &err); + + if (!skb) { + macvlan_count_rx(q->vlan, 0, false, false); + return err; + } + + skb_reserve(skb, NET_IP_ALIGN); + skb_put(skb, count); + + if (skb_copy_datagram_from_iovec(skb, 0, iv, 0, len)) { + macvlan_count_rx(q->vlan, 0, false, false); + kfree_skb(skb); + return -EFAULT; + } + + skb_set_network_header(skb, ETH_HLEN); + + macvlan_start_xmit(skb, q->vlan->dev); + + return count; +} + +static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + ssize_t result = -ENOLINK; + struct macvtap_queue *q = macvtap_file_get_queue(file); + + if (!q) + goto out; + + result = macvtap_get_user(q, iv, iov_length(iv, count), + file->f_flags & O_NONBLOCK); +out: + macvtap_file_put_queue(); + return result; +} + +/* Put packet to the user space buffer */ +static ssize_t macvtap_put_user(struct macvtap_queue *q, + const struct sk_buff *skb, + const struct iovec *iv, int len) +{ + struct macvlan_dev *vlan = q->vlan; + int ret; + + len = min_t(int, skb->len, len); + + ret = skb_copy_datagram_const_iovec(skb, 0, iv, 0, len); + + macvlan_count_rx(vlan, len, ret == 0, 0); + + return ret ? ret : len; +} + +static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct macvtap_queue *q = macvtap_file_get_queue(file); + + DECLARE_WAITQUEUE(wait, current); + struct sk_buff *skb; + ssize_t len, ret = 0; + + if (!q) { + ret = -ENOLINK; + goto out; + } + + len = iov_length(iv, count); + if (len < 0) { + ret = -EINVAL; + goto out; + } + + add_wait_queue(q->sk.sk_sleep, &wait); + while (len) { + current->state = TASK_INTERRUPTIBLE; + + /* Read frames from the queue */ + skb = skb_dequeue(&q->sk.sk_receive_queue); + if (!skb) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; + } + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + /* Nothing to read, let's sleep */ + schedule(); + continue; + } + ret = macvtap_put_user(q, skb, iv, len); + kfree_skb(skb); + break; + } + + current->state = TASK_RUNNING; + remove_wait_queue(q->sk.sk_sleep, &wait); + +out: + macvtap_file_put_queue(); + return ret; +} + +/* + * provide compatibility with generic tun/tap interface + */ +static long macvtap_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct macvtap_queue *q; + void __user *argp = (void __user *)arg; + struct ifreq __user *ifr = argp; + unsigned int __user *up = argp; + unsigned int u; + char devname[IFNAMSIZ]; + + switch (cmd) { + case TUNSETIFF: + /* ignore the name, just look at flags */ + if (get_user(u, &ifr->ifr_flags)) + return -EFAULT; + if (u != (IFF_TAP | IFF_NO_PI)) + return -EINVAL; + return 0; + + case TUNGETIFF: + q = macvtap_file_get_queue(file); + if (!q) + return -ENOLINK; + memcpy(devname, q->vlan->dev->name, sizeof(devname)); + macvtap_file_put_queue(); + + if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || + put_user((TUN_TAP_DEV | TUN_NO_PI), &ifr->ifr_flags)) + return -EFAULT; + return 0; + + case TUNGETFEATURES: + if (put_user((IFF_TAP | IFF_NO_PI), up)) + return -EFAULT; + return 0; + + case TUNSETSNDBUF: + if (get_user(u, up)) + return -EFAULT; + + q = macvtap_file_get_queue(file); + q->sk.sk_sndbuf = u; + macvtap_file_put_queue(); + return 0; + + case TUNSETOFFLOAD: + /* let the user check for future flags */ + if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | + TUN_F_TSO_ECN | TUN_F_UFO)) + return -EINVAL; + + /* TODO: add support for these, so far we don't + support any offload */ + if (arg & (TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | + TUN_F_TSO_ECN | TUN_F_UFO)) + return -EINVAL; + + return 0; + + default: + return -EINVAL; + } +} + +#ifdef CONFIG_COMPAT +static long macvtap_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return macvtap_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + +static const struct file_operations macvtap_fops = { + .owner = THIS_MODULE, + .open = macvtap_open, + .release = macvtap_release, + .aio_read = macvtap_aio_read, + .aio_write = macvtap_aio_write, + .poll = macvtap_poll, + .llseek = no_llseek, + .unlocked_ioctl = macvtap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = macvtap_compat_ioctl, +#endif +}; + +static int macvtap_init(void) +{ + int err; + + err = alloc_chrdev_region(&macvtap_major, 0, + MACVTAP_NUM_DEVS, "macvtap"); + if (err) + goto out1; + + cdev_init(&macvtap_cdev, &macvtap_fops); + err = cdev_add(&macvtap_cdev, macvtap_major, MACVTAP_NUM_DEVS); + if (err) + goto out2; + + macvtap_class = class_create(THIS_MODULE, "macvtap"); + if (IS_ERR(macvtap_class)) { + err = PTR_ERR(macvtap_class); + goto out3; + } + + err = macvlan_link_register(&macvtap_link_ops); + if (err) + goto out4; + + return 0; + +out4: + class_unregister(macvtap_class); +out3: + cdev_del(&macvtap_cdev); +out2: + unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS); +out1: + return err; +} +module_init(macvtap_init); + +static void macvtap_exit(void) +{ + rtnl_link_unregister(&macvtap_link_ops); + class_unregister(macvtap_class); + cdev_del(&macvtap_cdev); + unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS); +} +module_exit(macvtap_exit); + +MODULE_ALIAS_RTNL_LINK("macvtap"); +MODULE_AUTHOR("Arnd Bergmann "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 9a11544bb0b..51f1512045e 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -34,6 +34,7 @@ struct macvlan_dev { enum macvlan_mode mode; int (*receive)(struct sk_buff *skb); int (*forward)(struct net_device *dev, struct sk_buff *skb); + struct macvtap_queue *tap; }; static inline void macvlan_count_rx(const struct macvlan_dev *vlan, -- cgit v1.2.3-70-g09d2 From 47d742752df4c1088589d4424840bc761613ab2a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Feb 2010 15:21:08 +0000 Subject: percpu: add __percpu sparse annotations to net drivers Add __percpu sparse annotations to net drivers. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. Signed-off-by: Tejun Heo Acked-by: David S. Miller Cc: Eric Dumazet Cc: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/chelsio/sge.c | 2 +- drivers/net/loopback.c | 16 +++++++++------- drivers/net/veth.c | 4 ++-- include/linux/if_macvlan.h | 2 +- 4 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux/if_macvlan.h') diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c index 109d2783e4d..8e12505ac3a 100644 --- a/drivers/net/chelsio/sge.c +++ b/drivers/net/chelsio/sge.c @@ -267,7 +267,7 @@ struct sge { struct sk_buff *espibug_skb[MAX_NPORTS]; u32 sge_control; /* shadow value of sge control reg */ struct sge_intr_counts stats; - struct sge_port_stats *port_stats[MAX_NPORTS]; + struct sge_port_stats __percpu *port_stats[MAX_NPORTS]; struct sched *tx_sched; struct cmdQ cmdQ[SGE_CMDQ_N] ____cacheline_aligned_in_smp; }; diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index b9fcc981983..72b7949c91b 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -72,7 +72,8 @@ struct pcpu_lstats { static netdev_tx_t loopback_xmit(struct sk_buff *skb, struct net_device *dev) { - struct pcpu_lstats *pcpu_lstats, *lb_stats; + struct pcpu_lstats __percpu *pcpu_lstats; + struct pcpu_lstats *lb_stats; int len; skb_orphan(skb); @@ -80,7 +81,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb->protocol = eth_type_trans(skb, dev); /* it's OK to use per_cpu_ptr() because BHs are off */ - pcpu_lstats = dev->ml_priv; + pcpu_lstats = (void __percpu __force *)dev->ml_priv; lb_stats = this_cpu_ptr(pcpu_lstats); len = skb->len; @@ -95,14 +96,14 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, static struct net_device_stats *loopback_get_stats(struct net_device *dev) { - const struct pcpu_lstats *pcpu_lstats; + const struct pcpu_lstats __percpu *pcpu_lstats; struct net_device_stats *stats = &dev->stats; unsigned long bytes = 0; unsigned long packets = 0; unsigned long drops = 0; int i; - pcpu_lstats = dev->ml_priv; + pcpu_lstats = (void __percpu __force *)dev->ml_priv; for_each_possible_cpu(i) { const struct pcpu_lstats *lb_stats; @@ -135,19 +136,20 @@ static const struct ethtool_ops loopback_ethtool_ops = { static int loopback_dev_init(struct net_device *dev) { - struct pcpu_lstats *lstats; + struct pcpu_lstats __percpu *lstats; lstats = alloc_percpu(struct pcpu_lstats); if (!lstats) return -ENOMEM; - dev->ml_priv = lstats; + dev->ml_priv = (void __force *)lstats; return 0; } static void loopback_dev_free(struct net_device *dev) { - struct pcpu_lstats *lstats = dev->ml_priv; + struct pcpu_lstats __percpu *lstats = + (void __percpu __force *)dev->ml_priv; free_percpu(lstats); free_netdev(dev); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 3a15de56df9..35609e64f6f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -34,7 +34,7 @@ struct veth_net_stats { struct veth_priv { struct net_device *peer; - struct veth_net_stats *stats; + struct veth_net_stats __percpu *stats; unsigned ip_summed; }; @@ -263,7 +263,7 @@ static int veth_change_mtu(struct net_device *dev, int new_mtu) static int veth_dev_init(struct net_device *dev) { - struct veth_net_stats *stats; + struct veth_net_stats __percpu *stats; struct veth_priv *priv; stats = alloc_percpu(struct veth_net_stats); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 51f1512045e..f9cb9ba1475 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -30,7 +30,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - struct macvlan_rx_stats *rx_stats; + struct macvlan_rx_stats __percpu *rx_stats; enum macvlan_mode mode; int (*receive)(struct sk_buff *skb); int (*forward)(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3-70-g09d2 From 501c774cb13c3ef8fb7fc5f08fa19473f7d9a0db Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Feb 2010 05:46:50 +0000 Subject: net/macvtap: add vhost support This adds support for passing a macvtap file descriptor into vhost-net, much like we already do for tun/tap. Most of the new code is taken from the respective patch in the tun driver and may get consolidated in the future. Signed-off-by: Arnd Bergmann Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 98 ++++++++++++++++++++++++++++++++++++---------- drivers/vhost/Kconfig | 2 +- drivers/vhost/net.c | 8 +++- include/linux/if_macvlan.h | 13 ++++++ 4 files changed, 97 insertions(+), 24 deletions(-) (limited to 'include/linux/if_macvlan.h') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 70509974976..e354501ab29 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -58,6 +58,8 @@ static unsigned int macvtap_major; static struct class *macvtap_class; static struct cdev macvtap_cdev; +static const struct proto_ops macvtap_socket_ops; + /* * RCU usage: * The macvtap_queue and the macvlan_dev are loosely coupled, the @@ -176,7 +178,7 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb) return -ENOLINK; skb_queue_tail(&q->sk.sk_receive_queue, skb); - wake_up(q->sk.sk_sleep); + wake_up_interruptible_poll(q->sk.sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND); return 0; } @@ -242,7 +244,7 @@ static void macvtap_sock_write_space(struct sock *sk) return; if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND); } static int macvtap_open(struct inode *inode, struct file *file) @@ -270,6 +272,8 @@ static int macvtap_open(struct inode *inode, struct file *file) init_waitqueue_head(&q->sock.wait); q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; + q->sock.file = file; + q->sock.ops = &macvtap_socket_ops; sock_init_data(&q->sock, &q->sk); q->sk.sk_write_space = macvtap_sock_write_space; @@ -387,32 +391,20 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, rcu_read_lock_bh(); vlan = rcu_dereference(q->vlan); - macvlan_count_rx(vlan, len, ret == 0, 0); + if (vlan) + macvlan_count_rx(vlan, len, ret == 0, 0); rcu_read_unlock_bh(); return ret ? ret : len; } -static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, - unsigned long count, loff_t pos) +static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb, + const struct iovec *iv, unsigned long len, + int noblock) { - struct file *file = iocb->ki_filp; - struct macvtap_queue *q = file->private_data; - DECLARE_WAITQUEUE(wait, current); struct sk_buff *skb; - ssize_t len, ret = 0; - - if (!q) { - ret = -ENOLINK; - goto out; - } - - len = iov_length(iv, count); - if (len < 0) { - ret = -EINVAL; - goto out; - } + ssize_t ret = 0; add_wait_queue(q->sk.sk_sleep, &wait); while (len) { @@ -421,7 +413,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, /* Read frames from the queue */ skb = skb_dequeue(&q->sk.sk_receive_queue); if (!skb) { - if (file->f_flags & O_NONBLOCK) { + if (noblock) { ret = -EAGAIN; break; } @@ -440,7 +432,24 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, current->state = TASK_RUNNING; remove_wait_queue(q->sk.sk_sleep, &wait); + return ret; +} + +static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct macvtap_queue *q = file->private_data; + ssize_t len, ret = 0; + len = iov_length(iv, count); + if (len < 0) { + ret = -EINVAL; + goto out; + } + + ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK); + ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */ out: return ret; } @@ -538,6 +547,53 @@ static const struct file_operations macvtap_fops = { #endif }; +static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock); + return macvtap_get_user(q, m->msg_iov, total_len, + m->msg_flags & MSG_DONTWAIT); +} + +static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len, + int flags) +{ + struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock); + int ret; + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) + return -EINVAL; + ret = macvtap_do_read(q, 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 macvtap_socket_ops = { + .sendmsg = macvtap_sendmsg, + .recvmsg = macvtap_recvmsg, +}; + +/* 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 *macvtap_get_socket(struct file *file) +{ + struct macvtap_queue *q; + if (file->f_op != &macvtap_fops) + return ERR_PTR(-EINVAL); + q = file->private_data; + if (!q) + return ERR_PTR(-EBADFD); + return &q->sock; +} +EXPORT_SYMBOL_GPL(macvtap_get_socket); + static int macvtap_init(void) { int err; diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index 9e9355367bb..e4e2fd1b510 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -1,6 +1,6 @@ config VHOST_NET tristate "Host kernel accelerator for virtio net (EXPERIMENTAL)" - depends on NET && EVENTFD && (TUN || !TUN) && EXPERIMENTAL + depends on NET && EVENTFD && (TUN || !TUN) && (MACVTAP || !MACVTAP) && EXPERIMENTAL ---help--- This kernel module can be loaded in host kernel to accelerate guest networking with virtio_net. Not to be confused with virtio_net diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 4c8928319e1..91a324cc229 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -452,13 +453,16 @@ err: return ERR_PTR(r); } -static struct socket *get_tun_socket(int fd) +static struct socket *get_tap_socket(int fd) { struct file *file = fget(fd); struct socket *sock; if (!file) return ERR_PTR(-EBADF); sock = tun_get_socket(file); + if (!IS_ERR(sock)) + return sock; + sock = macvtap_get_socket(file); if (IS_ERR(sock)) fput(file); return sock; @@ -473,7 +477,7 @@ static struct socket *get_socket(int fd) sock = get_raw_socket(fd); if (!IS_ERR(sock)) return sock; - sock = get_tun_socket(fd); + sock = get_tap_socket(fd); if (!IS_ERR(sock)) return sock; return ERR_PTR(-ENOTSOCK); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index f9cb9ba1475..b78a712247d 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -7,6 +7,19 @@ #include #include +#if defined(CONFIG_MACVTAP) || defined(CONFIG_MACVTAP_MODULE) +struct socket *macvtap_get_socket(struct file *); +#else +#include +#include +struct file; +struct socket; +static inline struct socket *macvtap_get_socket(struct file *f) +{ + return ERR_PTR(-EINVAL); +} +#endif /* CONFIG_MACVTAP */ + struct macvlan_port; struct macvtap_queue; -- cgit v1.2.3-70-g09d2