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 <arnd@arndb.de>
Acked-by: Sridhar Samudrala <sri@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 97 insertions, 24 deletions

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7050997..e354501 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 9e93553..e4e2fd1 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 4c89283..91a324c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -22,6 +22,7 @@
 #include <linux/if_packet.h>
 #include <linux/if_arp.h>
 #include <linux/if_tun.h>
+#include <linux/if_macvlan.h>
 
 #include <net/sock.h>
 
@@ -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 f9cb9ba..b78a712 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -7,6 +7,19 @@
 #include <linux/netlink.h>
 #include <net/netlink.h>
 
+#if defined(CONFIG_MACVTAP) || defined(CONFIG_MACVTAP_MODULE)
+struct socket *macvtap_get_socket(struct file *);
+#else
+#include <linux/err.h>
+#include <linux/errno.h>
+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;