From 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 11 Dec 2013 13:27:10 -0500 Subject: [PATCH 1/2] macvtap: Add support of packet capture on macvtap device. Macvtap device currently doesn not allow a user to capture traffic on due to the fact that it steals the packets from the network stack before the skb->dev is set correctly on the receive side, and that use uses macvlan transmit path directly on the send side. As a result, we never get a change to give traffic to the taps while the correct device is set in the skb. This patch makes macvtap device behave almost exaclty like macvlan. On the send side, we switch to using dev_queue_xmit(). On the receive side, to deliver packets to macvtap, we now use netif_rx and dev_forward_skb just like macvlan. The only differnce now is that macvtap has its own rx_handler which is attached to the macvtap netdev. It is here that we now steal the packet and provide it to the socket. As a result, we can now capture traffic on the macvtap device: tcpdump -i macvtap0 It also gives us the abilit to add tc actions to the macvtap device and actually utilize different bandwidth management queues on output. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 59 +++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 27 deletions(-) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 4a34bcb6549f..85ecfccf9c60 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -70,6 +70,11 @@ static const struct proto_ops macvtap_socket_ops; #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) +static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler_data); +} + /* * RCU usage: * The macvtap_queue and the macvlan_dev are loosely coupled, the @@ -271,24 +276,27 @@ static void macvtap_del_queues(struct net_device *dev) sock_put(&qlist[j]->sk); } -/* - * 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) +static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb) { - struct macvlan_dev *vlan = netdev_priv(dev); - struct macvtap_queue *q = macvtap_get_queue(dev, skb); + struct sk_buff *skb = *pskb; + struct net_device *dev = skb->dev; + struct macvlan_dev *vlan; + struct macvtap_queue *q; netdev_features_t features = TAP_FEATURES; + vlan = macvtap_get_vlan_rcu(dev); + if (!vlan) + return RX_HANDLER_PASS; + + q = macvtap_get_queue(dev, skb); if (!q) - goto drop; + return RX_HANDLER_PASS; if (skb_queue_len(&q->sk.sk_receive_queue) >= dev->tx_queue_len) goto drop; - skb->dev = dev; + skb_push(skb, ETH_HLEN); + /* Apply the forward feature mask so that we perform segmentation * according to users wishes. This only works if VNET_HDR is * enabled. @@ -320,22 +328,13 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb) wake_up: wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND); - return NET_RX_SUCCESS; + return RX_HANDLER_CONSUMED; drop: + /* Count errors/drops only here, thus don't care about args. */ + macvlan_count_rx(vlan, 0, 0, 0); kfree_skb(skb); - return NET_RX_DROP; -} - -/* - * 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); + return RX_HANDLER_CONSUMED; } static int macvtap_get_minor(struct macvlan_dev *vlan) @@ -385,6 +384,8 @@ static int macvtap_newlink(struct net *src_net, struct nlattr *data[]) { struct macvlan_dev *vlan = netdev_priv(dev); + int err; + INIT_LIST_HEAD(&vlan->queue_list); /* Since macvlan supports all offloads by default, make @@ -392,16 +393,21 @@ static int macvtap_newlink(struct net *src_net, */ vlan->tap_features = TUN_OFFLOADS; + err = netdev_rx_handler_register(dev, macvtap_handle_frame, vlan); + if (err) + return err; + /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ return macvlan_common_newlink(src_net, dev, tb, data, - macvtap_receive, macvtap_forward); + netif_rx, dev_forward_skb); } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { + netdev_rx_handler_unregister(dev); macvtap_del_queues(dev); macvlan_dellink(dev, head); } @@ -725,9 +731,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } if (vlan) { - local_bh_disable(); - macvlan_start_xmit(skb, vlan->dev); - local_bh_enable(); + skb->dev = vlan->dev; + dev_queue_xmit(skb); } else { kfree_skb(skb); } From 2f6a1b6607fd6b0eb9501843a40e0c7555f37b4a Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 11 Dec 2013 13:27:11 -0500 Subject: [PATCH 2/2] macvlan: Remove custom recieve and forward handlers Since now macvlan and macvtap use the same receive and forward handlers, we can remove them completely and use netif_rx and dev_forward_skb() directly. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 17 +++++------------ drivers/net/macvtap.c | 3 +-- include/linux/if_macvlan.h | 7 +------ 3 files changed, 7 insertions(+), 20 deletions(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cfb91570cddd..24ea994b6274 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -120,7 +120,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb, struct net_device *dev = vlan->dev; if (local) - return vlan->forward(dev, skb); + return dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) @@ -128,7 +128,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb, else skb->pkt_type = PACKET_MULTICAST; - return vlan->receive(skb); + return netif_rx(skb); } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) @@ -251,7 +251,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) skb->dev = dev; skb->pkt_type = PACKET_HOST; - ret = vlan->receive(skb); + ret = netif_rx(skb); out: macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0); @@ -803,10 +803,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) } 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)) + struct nlattr *tb[], struct nlattr *data[]) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; @@ -848,8 +845,6 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; - vlan->receive = receive; - vlan->forward = forward; vlan->set_features = MACVLAN_FEATURES; vlan->mode = MACVLAN_MODE_VEPA; @@ -894,9 +889,7 @@ EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - return macvlan_common_newlink(src_net, dev, tb, data, - netif_rx, - dev_forward_skb); + return macvlan_common_newlink(src_net, dev, tb, data); } void macvlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 85ecfccf9c60..64409af0da31 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -400,8 +400,7 @@ static int macvtap_newlink(struct net *src_net, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - return macvlan_common_newlink(src_net, dev, tb, data, - netif_rx, dev_forward_skb); + return macvlan_common_newlink(src_net, dev, tb, data); } static void macvtap_dellink(struct net_device *dev, diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 84ba5ac39e03..ea22721ba269 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -69,8 +69,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - int (*receive)(struct sk_buff *skb); - int (*forward)(struct net_device *dev, struct sk_buff *skb); /* This array tracks active taps. */ struct macvtap_queue __rcu *taps[MAX_MACVTAP_QUEUES]; /* This list tracks all taps (both enabled and disabled) */ @@ -103,10 +101,7 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); 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)); + struct nlattr *tb[], struct nlattr *data[]); extern void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success,