---

yaml
---
r: 103247
b: refs/heads/master
c: 4ce2417
h: refs/heads/master
i:
  103245: cba2e6a
  103243: 072b5e2
  103239: 039187b
  103231: 1bed8fe
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 055e5110ae0c0c1176a75b78d789294f2ff2f7af
+refs/heads/master: 4ce2417bfb3c7b1c5ed449782f4d86bafd7f1b69

trunk/drivers/net/tun.c

@@ -63,6 +63,7 @@
 #include <linux/if_tun.h>
 #include <linux/crc32.h>
 #include <linux/nsproxy.h>
+#include <linux/virtio_net.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -283,6 +284,7 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv,
 	struct tun_pi pi = { 0, __constant_htons(ETH_P_IP) };
 	struct sk_buff *skb;
 	size_t len = count, align = 0;
+	struct virtio_net_hdr gso = { 0 };
 
 	if (!(tun->flags & TUN_NO_PI)) {
 		if ((len -= sizeof(pi)) > count)
@@ -292,6 +294,17 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv,
 			return -EFAULT;
 	}
 
+	if (tun->flags & TUN_VNET_HDR) {
+		if ((len -= sizeof(gso)) > count)
+			return -EINVAL;
+
+		if (memcpy_fromiovec((void *)&gso, iv, sizeof(gso)))
+			return -EFAULT;
+
+		if (gso.hdr_len > len)
+			return -EINVAL;
+	}
+
 	if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
 		align = NET_IP_ALIGN;
 		if (unlikely(len < ETH_HLEN))
@@ -311,6 +324,16 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv,
 		return -EFAULT;
 	}
 
+	if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+		if (!skb_partial_csum_set(skb, gso.csum_start,
+					  gso.csum_offset)) {
+			tun->dev->stats.rx_frame_errors++;
+			kfree_skb(skb);
+			return -EINVAL;
+		}
+	} else if (tun->flags & TUN_NOCHECKSUM)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case TUN_TUN_DEV:
 		if (tun->flags & TUN_NO_PI) {
@@ -337,8 +360,35 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv,
 		break;
 	};
 
-	if (tun->flags & TUN_NOCHECKSUM)
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		pr_debug("GSO!\n");
+		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+		case VIRTIO_NET_HDR_GSO_TCPV4:
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+			break;
+		case VIRTIO_NET_HDR_GSO_TCPV6:
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+			break;
+		default:
+			tun->dev->stats.rx_frame_errors++;
+			kfree_skb(skb);
+			return -EINVAL;
+		}
+
+		if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+		skb_shinfo(skb)->gso_size = gso.gso_size;
+		if (skb_shinfo(skb)->gso_size == 0) {
+			tun->dev->stats.rx_frame_errors++;
+			kfree_skb(skb);
+			return -EINVAL;
+		}
+
+		/* Header must be checked, and gso_segs computed. */
+		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+		skb_shinfo(skb)->gso_segs = 0;
+	}
 
 	netif_rx_ni(skb);
 	tun->dev->last_rx = jiffies;
@@ -384,6 +434,39 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun,
 		total += sizeof(pi);
 	}
 
+	if (tun->flags & TUN_VNET_HDR) {
+		struct virtio_net_hdr gso = { 0 }; /* no info leak */
+		if ((len -= sizeof(gso)) < 0)
+			return -EINVAL;
+
+		if (skb_is_gso(skb)) {
+			struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+			/* This is a hint as to how much should be linear. */
+			gso.hdr_len = skb_headlen(skb);
+			gso.gso_size = sinfo->gso_size;
+			if (sinfo->gso_type & SKB_GSO_TCPV4)
+				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+			else if (sinfo->gso_type & SKB_GSO_TCPV6)
+				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+			else
+				BUG();
+			if (sinfo->gso_type & SKB_GSO_TCP_ECN)
+				gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+		} else
+			gso.gso_type = VIRTIO_NET_HDR_GSO_NONE;
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+			gso.csum_start = skb->csum_start - skb_headroom(skb);
+			gso.csum_offset = skb->csum_offset;
+		} /* else everything is zero */
+
+		if (unlikely(memcpy_toiovec(iv, (void *)&gso, sizeof(gso))))
+			return -EFAULT;
+		total += sizeof(gso);
+	}
+
 	len = min_t(int, skb->len, len);
 
 	skb_copy_datagram_iovec(skb, 0, iv, len);
@@ -598,6 +681,11 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	else
 		tun->flags &= ~TUN_ONE_QUEUE;
 
+	if (ifr->ifr_flags & IFF_VNET_HDR)
+		tun->flags |= TUN_VNET_HDR;
+	else
+		tun->flags &= ~TUN_VNET_HDR;
+
 	file->private_data = tun;
 	tun->attached = 1;
 	get_net(dev_net(tun->dev));
@@ -611,6 +699,46 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 	return err;
 }
 
+/* This is like a cut-down ethtool ops, except done via tun fd so no
+ * privs required. */
+static int set_offload(struct net_device *dev, unsigned long arg)
+{
+	unsigned int old_features, features;
+
+	old_features = dev->features;
+	/* Unset features, set them as we chew on the arg. */
+	features = (old_features & ~(NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST
+				    |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6));
+
+	if (arg & TUN_F_CSUM) {
+		features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+		arg &= ~TUN_F_CSUM;
+
+		if (arg & (TUN_F_TSO4|TUN_F_TSO6)) {
+			if (arg & TUN_F_TSO_ECN) {
+				features |= NETIF_F_TSO_ECN;
+				arg &= ~TUN_F_TSO_ECN;
+			}
+			if (arg & TUN_F_TSO4)
+				features |= NETIF_F_TSO;
+			if (arg & TUN_F_TSO6)
+				features |= NETIF_F_TSO6;
+			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
+		}
+	}
+
+	/* This gives the user a way to test for new features in future by
+	 * trying to set them. */
+	if (arg)
+		return -EINVAL;
+
+	dev->features = features;
+	if (old_features != dev->features)
+		netdev_features_change(dev);
+
+	return 0;
+}
+
 static int tun_chr_ioctl(struct inode *inode, struct file *file,
 			 unsigned int cmd, unsigned long arg)
 {
@@ -640,6 +768,15 @@ static int tun_chr_ioctl(struct inode *inode, struct file *file,
 		return 0;
 	}
 
+	if (cmd == TUNGETFEATURES) {
+		/* Currently this just means: "what IFF flags are valid?".
+		 * This is needed because we never checked for invalid flags on
+		 * TUNSETIFF. */
+		return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
+				IFF_VNET_HDR,
+				(unsigned int __user*)argp);
+	}
+
 	if (!tun)
 		return -EBADFD;
 
@@ -707,6 +844,15 @@ static int tun_chr_ioctl(struct inode *inode, struct file *file,
 		break;
 #endif
 
+	case TUNSETOFFLOAD:
+	{
+		int ret;
+		rtnl_lock();
+		ret = set_offload(tun->dev, arg);
+		rtnl_unlock();
+		return ret;
+	}
+
 	case SIOCGIFFLAGS:
 		ifr.ifr_flags = tun->if_flags;
 		if (copy_to_user( argp, &ifr, sizeof ifr))

trunk/include/linux/if_tun.h

@@ -31,6 +31,7 @@
 #define TUN_NO_PI	0x0040
 #define TUN_ONE_QUEUE	0x0080
 #define TUN_PERSIST 	0x0100	
+#define TUN_VNET_HDR 	0x0200
 
 /* Ioctl defines */
 #define TUNSETNOCSUM  _IOW('T', 200, int) 
@@ -40,12 +41,21 @@
 #define TUNSETOWNER   _IOW('T', 204, int)
 #define TUNSETLINK    _IOW('T', 205, int)
 #define TUNSETGROUP   _IOW('T', 206, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD _IOW('T', 208, unsigned int)
 
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
 #define IFF_TAP		0x0002
 #define IFF_NO_PI	0x1000
 #define IFF_ONE_QUEUE	0x2000
+#define IFF_VNET_HDR	0x4000
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM	0x01	/* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4	0x02	/* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6	0x04	/* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN	0x08	/* I can handle TSO with ECN bits. */
 
 struct tun_pi {
 	unsigned short flags;

trunk/include/net/fib_rules.h

@@ -62,7 +62,7 @@ struct fib_rules_ops
 
 	/* Called after modifications to the rules set, must flush
 	 * the route cache if one exists. */
-	void			(*flush_cache)(void);
+	void			(*flush_cache)(struct fib_rules_ops *ops);
 
 	int			nlgroup;
 	const struct nla_policy	*policy;

trunk/include/net/netns/ipv4.h

@@ -18,6 +18,7 @@ struct netns_ipv4 {
 	struct ctl_table_header	*forw_hdr;
 	struct ctl_table_header	*frags_hdr;
 	struct ctl_table_header	*ipv4_hdr;
+	struct ctl_table_header *route_hdr;
 #endif
 	struct ipv4_devconf	*devconf_all;
 	struct ipv4_devconf	*devconf_dflt;
@@ -45,5 +46,8 @@ struct netns_ipv4 {
 	int sysctl_icmp_ratelimit;
 	int sysctl_icmp_ratemask;
 	int sysctl_icmp_errors_use_inbound_ifaddr;
+
+	struct timer_list rt_secret_timer;
+	atomic_t rt_genid;
 };
 #endif

trunk/include/net/route.h

@@ -111,7 +111,7 @@ struct in_device;
 extern int		ip_rt_init(void);
 extern void		ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
 				       __be32 src, struct net_device *dev);
-extern void		rt_cache_flush(int how);
+extern void		rt_cache_flush(struct net *net, int how);
 extern int		__ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
 extern int		ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
 extern int		ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);

trunk/net/core/fib_rules.c

@@ -69,7 +69,7 @@ static void rules_ops_put(struct fib_rules_ops *ops)
 static void flush_route_cache(struct fib_rules_ops *ops)
 {
 	if (ops->flush_cache)
-		ops->flush_cache();
+		ops->flush_cache(ops);
 }
 
 int fib_rules_register(struct fib_rules_ops *ops)

trunk/net/decnet/dn_rules.c

@@ -229,7 +229,7 @@ static u32 dn_fib_rule_default_pref(struct fib_rules_ops *ops)
 	return 0;
 }
 
-static void dn_fib_rule_flush_cache(void)
+static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops)
 {
 	dn_rt_cache_flush(-1);
 }

trunk/net/ipv4/arp.c

@@ -1197,7 +1197,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, vo
 	switch (event) {
 	case NETDEV_CHANGEADDR:
 		neigh_changeaddr(&arp_tbl, dev);
-		rt_cache_flush(0);
+		rt_cache_flush(dev_net(dev), 0);
 		break;
 	default:
 		break;

trunk/net/ipv4/devinet.c

@@ -1348,7 +1348,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
 				dev_disable_lro(idev->dev);
 			}
 			rtnl_unlock();
-			rt_cache_flush(0);
+			rt_cache_flush(net, 0);
 		}
 	}
 
@@ -1362,9 +1362,10 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write,
 	int *valp = ctl->data;
 	int val = *valp;
 	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
+	struct net *net = ctl->extra2;
 
 	if (write && *valp != val)
-		rt_cache_flush(0);
+		rt_cache_flush(net, 0);
 
 	return ret;
 }
@@ -1375,9 +1376,10 @@ int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen,
 {
 	int ret = devinet_conf_sysctl(table, name, nlen, oldval, oldlenp,
 				      newval, newlen);
+	struct net *net = table->extra2;
 
 	if (ret == 1)
-		rt_cache_flush(0);
+		rt_cache_flush(net, 0);
 
 	return ret;
 }