[PATCHv2 0/8] vxlan: bug fixes

@@ -680,9 +680,13 @@ static netdev_tx_t vxlan_xmit(struct sk_
 
 	hash = skb_get_rxhash(skb);
 
-	rt = ip_route_output_gre(dev_net(dev), &fl4, dst,
-				 vxlan->saddr, vxlan->vni,
-				 RT_TOS(tos), vxlan->link);
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.flowi4_oif = vxlan->link;
+	fl4.flowi4_tos = RT_TOS(tos);
+	fl4.daddr = dst;
+	fl4.saddr = vxlan->saddr;
+
+	rt = ip_route_output_key(dev_net(dev), &fl4);
 	if (IS_ERR(rt)) {
 		netdev_dbg(dev, "no route to %pI4\n", &dst);
 		dev->stats.tx_carrier_errors++;

@@ -724,7 +728,7 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	iph->frag_off	= df;
 	iph->protocol	= IPPROTO_UDP;
 	iph->tos	= vxlan_ecn_encap(tos, old_iph, skb);
-	iph->daddr	= fl4.daddr;
+	iph->daddr	= dst;
 	iph->saddr	= fl4.saddr;
 	iph->ttl	= ttl ? : ip4_dst_hoplimit(&rt->dst);
 

@@ -621,6 +621,22 @@ static inline u8 vxlan_ecn_encap(u8 tos,
 	return INET_ECN_encapsulate(tos, inner);
 }
 
+static __be32 vxlan_find_dst(struct vxlan_dev *vxlan, struct sk_buff *skb)
+{
+	const struct ethhdr *eth = (struct ethhdr *) skb->data;
+	const struct vxlan_fdb *f;
+
+	if (is_multicast_ether_addr(eth->h_dest))
+		return vxlan->gaddr;
+
+	f = vxlan_find_mac(vxlan, eth->h_dest);
+	if (f)
+		return f->remote_ip;
+	else
+		return vxlan->gaddr;
+
+}
+
 /* Transmit local packets over Vxlan
  *
  * Outer IP header inherits ECN and DF from inner header.

@@ -632,13 +648,11 @@ static netdev_tx_t vxlan_xmit(struct sk_
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct rtable *rt;
-	const struct ethhdr *eth;
 	const struct iphdr *old_iph;
 	struct iphdr *iph;
 	struct vxlanhdr *vxh;
 	struct udphdr *uh;
 	struct flowi4 fl4;
-	struct vxlan_fdb *f;
 	unsigned int pkt_len = skb->len;
 	u32 hash;
 	__be32 dst;

@@ -646,21 +660,16 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	__u8 tos, ttl;
 	int err;
 
+	dst = vxlan_find_dst(vxlan, skb);
+	if (!dst)
+		goto drop;
+
 	/* Need space for new headers (invalidates iph ptr) */
 	if (skb_cow_head(skb, VXLAN_HEADROOM))
 		goto drop;
 
-	eth = (void *)skb->data;
 	old_iph = ip_hdr(skb);
 
-	if (!is_multicast_ether_addr(eth->h_dest) &&
-	    (f = vxlan_find_mac(vxlan, eth->h_dest)))
-		dst = f->remote_ip;
-	else if (vxlan->gaddr) {
-		dst = vxlan->gaddr;
-	} else
-		goto drop;
-
 	ttl = vxlan->ttl;
 	if (!ttl && IN_MULTICAST(ntohl(dst)))
 		ttl = 1;

@@ -637,6 +637,23 @@ static __be32 vxlan_find_dst(struct vxla
 
 }
 
+static void vxlan_sock_free(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+
+/* On transmit, associate with the tunnel socket */
+static void vxlan_set_owner(struct net_device *dev, struct sk_buff *skb)
+{
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+	struct sock *sk = vn->sock->sk;
+
+	skb_orphan(skb);
+	sock_hold(sk);
+	skb->sk = sk;
+	skb->destructor = vxlan_sock_free;
+}
+
 /* Transmit local packets over Vxlan
  *
  * Outer IP header inherits ECN and DF from inner header.

@@ -732,6 +749,8 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	iph->saddr	= fl4.saddr;
 	iph->ttl	= ttl ? : ip4_dst_hoplimit(&rt->dst);
 
+	vxlan_set_owner(dev, skb);
+
 	/* See __IPTUNNEL_XMIT */
 	skb->ip_summed = CHECKSUM_NONE;
 	ip_select_ident(iph, &rt->dst, NULL);

@@ -228,9 +228,9 @@ static u32 eth_hash(const unsigned char
 
 	/* only want 6 bytes */
 #ifdef __BIG_ENDIAN
-	value <<= 16;
-#else
 	value >>= 16;
+#else
+	value <<= 16;
 #endif
 	return hash_64(value, FDB_HASH_BITS);
 }

@@ -106,6 +106,8 @@ struct vxlan_dev {
 	__be32	          gaddr;	/* multicast group */
 	__be32		  saddr;	/* source address */
 	unsigned int      link;		/* link to multicast over */
+	__u16		  port_min;	/* source port range */
+	__u16		  port_max;
 	__u8		  tos;		/* TOS override */
 	__u8		  ttl;
 	bool		  learn;

@@ -654,12 +656,29 @@ static void vxlan_set_owner(struct net_d
 	skb->destructor = vxlan_sock_free;
 }
 
+/* Compute source port for outgoing packet
+ *   first choice to use L4 flow hash since it will spread
+ *     better and maybe available from hardware
+ *   secondary choice is to use jhash on the Ethernet header
+ */
+static u16 vxlan_src_port(const struct vxlan_dev *vxlan, struct sk_buff *skb)
+{
+	unsigned int range = (vxlan->port_max - vxlan->port_min) + 1;
+	u32 hash;
+
+	hash = skb_get_rxhash(skb);
+	if (!hash)
+		hash = jhash(skb->data, 2 * ETH_ALEN,
+			     (__force u32) skb->protocol);
+
+	return (((u64) hash * range) >> 32) + vxlan->port_min;
+}
+
 /* Transmit local packets over Vxlan
  *
  * Outer IP header inherits ECN and DF from inner header.
  * Outer UDP destination is the VXLAN assigned port.
- *           source port is based on hash of flow if available
- *                       otherwise use a random value
+ *           source port is based on hash of flow
  */
 static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 {

@@ -671,8 +690,8 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	struct udphdr *uh;
 	struct flowi4 fl4;
 	unsigned int pkt_len = skb->len;
-	u32 hash;
 	__be32 dst;
+	__u16 src_port;
 	__be16 df = 0;
 	__u8 tos, ttl;
 	int err;

@@ -695,7 +714,7 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	if (tos == 1)
 		tos = vxlan_get_dsfield(old_iph, skb);
 
-	hash = skb_get_rxhash(skb);
+	src_port = vxlan_src_port(vxlan, skb);
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.flowi4_oif = vxlan->link;

@@ -732,7 +751,7 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	uh = udp_hdr(skb);
 
 	uh->dest = htons(vxlan_port);
-	uh->source = hash ? :random32();
+	uh->source = htons(src_port);
 
 	uh->len = htons(skb->len);
 	uh->check = 0;

@@ -960,6 +979,7 @@ static void vxlan_setup(struct net_devic
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	unsigned h;
+	int low, high;
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);

@@ -979,6 +999,10 @@ static void vxlan_setup(struct net_devic
 	vxlan->age_timer.function = vxlan_cleanup;
 	vxlan->age_timer.data = (unsigned long) vxlan;
 
+	inet_get_local_port_range(&low, &high);
+	vxlan->port_min = low;
+	vxlan->port_max = high;
+
 	vxlan->dev = dev;
 
 	for (h = 0; h < FDB_HASH_SIZE; ++h)

@@ -995,6 +1019,7 @@ static const struct nla_policy vxlan_pol
 	[IFLA_VXLAN_LEARNING]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_AGEING]	= { .type = NLA_U32 },
 	[IFLA_VXLAN_LIMIT]	= { .type = NLA_U32 },
+	[IFLA_VXLAN_PORT_RANGE] = { .len  = sizeof(struct ifla_vxlan_port_range) },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])

@@ -1027,6 +1052,18 @@ static int vxlan_validate(struct nlattr
 			return -EADDRNOTAVAIL;
 		}
 	}
+
+	if (data[IFLA_VXLAN_PORT_RANGE]) {
+		const struct ifla_vxlan_port_range *p
+			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
+
+		if (ntohs(p->high) < ntohs(p->low)) {
+			pr_debug("port range %u .. %u not valid\n",
+				 ntohs(p->low), ntohs(p->high));
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 

@@ -1077,6 +1114,13 @@ static int vxlan_newlink(struct net *net
 	if (data[IFLA_VXLAN_LIMIT])
 		vxlan->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]);
 
+	if (data[IFLA_VXLAN_PORT_RANGE]) {
+		const struct ifla_vxlan_port_range *p
+			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
+		vxlan->port_min = ntohs(p->low);
+		vxlan->port_max = ntohs(p->high);
+	}
+
 	err = register_netdevice(dev);
 	if (!err)
 		hlist_add_head_rcu(&vxlan->hlist, vni_head(net, vxlan->vni));

@@ -1105,12 +1149,17 @@ static size_t vxlan_get_size(const struc
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_AGEING */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_LIMIT */
+		nla_total_size(sizeof(struct ifla_vxlan_port_range)) +
 		0;
 }
 
 static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	const struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct ifla_vxlan_port_range ports = {
+		.low =  htons(vxlan->port_min),
+		.high = htons(vxlan->port_max),
+	};
 
 	if (nla_put_u32(skb, IFLA_VXLAN_ID, vxlan->vni))
 		goto nla_put_failure;

@@ -1131,6 +1180,9 @@ static int vxlan_fill_info(struct sk_buf
 	    nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax))
 		goto nla_put_failure;
 
+	if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
--- a/include/linux/if_link.h	2012-10-09 18:08:22.126560329 -0700
+++ b/include/linux/if_link.h	2012-10-09 18:08:35.086431755 -0700

@@ -284,10 +284,16 @@ enum {
 	IFLA_VXLAN_LEARNING,
 	IFLA_VXLAN_AGEING,
 	IFLA_VXLAN_LIMIT,
+	IFLA_VXLAN_PORT_RANGE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
 
+struct ifla_vxlan_port_range {
+	__be16	low;
+	__be16	high;
+};
+
 /* SR-IOV virtual function management section */
 
 enum {

@@ -983,6 +983,7 @@ static void vxlan_setup(struct net_devic
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
+	dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = vxlan_free;

@@ -537,7 +537,6 @@ static int vxlan_udp_encap_recv(struct s
 	}
 
 	__skb_pull(skb, sizeof(struct vxlanhdr));
-	skb_postpull_rcsum(skb, eth_hdr(skb), sizeof(struct vxlanhdr));
 
 	/* Is this VNI defined? */
 	vni = ntohl(vxh->vx_vni) >> 8;

@@ -556,7 +555,6 @@ static int vxlan_udp_encap_recv(struct s
 	/* Re-examine inner Ethernet packet */
 	oip = ip_hdr(skb);
 	skb->protocol = eth_type_trans(skb, vxlan->dev);
-	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	/* Ignore packet loops (and multicast echo) */
 	if (compare_ether_addr(eth_hdr(skb)->h_source,

@@ -568,6 +566,7 @@ static int vxlan_udp_encap_recv(struct s
 
 	__skb_tunnel_rx(skb, vxlan->dev);
 	skb_reset_network_header(skb);
+	skb->ip_summed = CHECKSUM_NONE;
 
 	err = IP_ECN_decapsulate(oip, skb);
 	if (unlikely(err)) {

@@ -1090,14 +1090,18 @@ static int vxlan_newlink(struct net *net
 	if (data[IFLA_VXLAN_LOCAL])
 		vxlan->saddr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
 
-	if (data[IFLA_VXLAN_LINK]) {
-		vxlan->link = nla_get_u32(data[IFLA_VXLAN_LINK]);
+	if (data[IFLA_VXLAN_LINK] &&
+	    (vxlan->link = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
+		struct net_device *lowerdev
+			 = __dev_get_by_index(net, vxlan->link);
 
-		if (!tb[IFLA_MTU]) {
-			struct net_device *lowerdev;
-			lowerdev = __dev_get_by_index(net, vxlan->link);
-			dev->mtu = lowerdev->mtu - VXLAN_HEADROOM;
+		if (!lowerdev) {
+			pr_info("ifindex %d does not exist\n", vxlan->link);
+			return -ENODEV;
 		}
+
+		if (!tb[IFLA_MTU])
+			dev->mtu = lowerdev->mtu - VXLAN_HEADROOM;
 	}
 
 	if (data[IFLA_VXLAN_TOS])

@@ -282,10 +282,16 @@ enum {
 	IFLA_VXLAN_LEARNING,
 	IFLA_VXLAN_AGEING,
 	IFLA_VXLAN_LIMIT,
+	IFLA_VXLAN_PORT_RANGE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
 
+struct ifla_vxlan_port_range {
+	__be16	low;
+	__be16	high;
+};
+
 /* SR-IOV virtual function management section */
 
 enum {

@@ -24,7 +24,8 @@
 static void explain(void)
 {
 	fprintf(stderr, "Usage: ... vxlan id VNI [ group ADDR ] [ local ADDR ]\n");
-	fprintf(stderr, "                 [ ttl TTL ] [ tos TOS ] [ [no]learning ] [ dev PHYS_DEV ]\n");
+	fprintf(stderr, "                 [ ttl TTL ] [ tos TOS ] [ dev PHYS_DEV ]\n");
+	fprintf(stderr, "                 [ port MIN MAX ] [ [no]learning ]\n");
 	fprintf(stderr, "\n");
 	fprintf(stderr, "Where: VNI := 0-16777215\n");
 	fprintf(stderr, "       ADDR := { IP_ADDRESS | any }\n");

@@ -46,6 +47,7 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 	__u8 noage = 0;
 	__u32 age = 0;
 	__u32 maxaddr = 0;
+	struct ifla_vxlan_port_range range = { 0, 0 };
 
 	while (argc > 0) {
 		if (!matches(*argv, "id") ||

@@ -79,9 +81,9 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 			NEXT_ARG();
 			if (strcmp(*argv, "inherit") != 0) {
 				if (get_unsigned(&uval, *argv, 0))
-					invarg("invalid TTL\n", *argv);
+					invarg("invalid TTL", *argv);
 				if (uval > 255)
-					invarg("TTL must be <= 255\n", *argv);
+					invarg("TTL must be <= 255", *argv);
 				ttl = uval;
 			}
 		} else if (!matches(*argv, "tos") ||

@@ -100,13 +102,23 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 			if (strcmp(*argv, "none") == 0)
 				noage = 1;
 			else if (get_u32(&age, *argv, 0))
-				invarg("ageing timer\n", *argv);
+				invarg("ageing timer", *argv);
 		} else if (!matches(*argv, "maxaddress")) {
 			NEXT_ARG();
 			if (strcmp(*argv, "unlimited") == 0)
 				maxaddr = 0;
 			else if (get_u32(&maxaddr, *argv, 0))
-				invarg("max addresses\n", *argv);
+				invarg("max addresses", *argv);
+		} else if (!matches(*argv, "port")) {
+			__u16 minport, maxport;
+			NEXT_ARG();
+			if (get_u16(&minport, *argv, 0))
+				invarg("min port", *argv);
+			NEXT_ARG();
+			if (get_u16(&maxport, *argv, 0))
+				invarg("max port", *argv);
+			range.low = htons(minport);
+			range.high = htons(maxport);
 		} else if (!matches(*argv, "nolearning")) {
 			learning = 0;
 		} else if (!matches(*argv, "learning")) {

@@ -140,6 +152,9 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 		addattr32(n, 1024, IFLA_VXLAN_AGEING, age);
 	if (maxaddr)
 		addattr32(n, 1024, IFLA_VXLAN_LIMIT, maxaddr);
+	if (range.low || range.high)
+		addattr_l(n, 1024, IFLA_VXLAN_PORT_RANGE,
+			  &range, sizeof(range));
 
 	return 0;
 }

@@ -148,6 +163,8 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 {
 	__u32 vni;
 	unsigned link;
+	__u8 tos;
+	__u32 maxaddr;
 	char s1[1024];
 	char s2[64];
 

@@ -187,13 +204,18 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 			fprintf(f, "dev %u ", link);
 	}
 
+	if (tb[IFLA_VXLAN_PORT_RANGE]) {
+		const struct ifla_vxlan_port_range *r
+			= RTA_DATA(tb[IFLA_VXLAN_PORT_RANGE]);
+		fprintf(f, "port %u %u ", ntohs(r->low), ntohs(r->high));
+	}	
+
 	if (tb[IFLA_VXLAN_LEARNING] &&
 	    !rta_getattr_u8(tb[IFLA_VXLAN_LEARNING]))
 		fputs("nolearning ", f);
-
-	if (tb[IFLA_VXLAN_TOS]) {
-		__u8 tos = rta_getattr_u8(tb[IFLA_VXLAN_TOS]);
-
+	
+	if (tb[IFLA_VXLAN_TOS] &&
+	    (tos = rta_getattr_u8(tb[IFLA_VXLAN_TOS]))) {
 		if (tos == 1)
 			fprintf(f, "tos inherit ");
 		else

@@ -213,13 +235,10 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 		else
 			fprintf(f, "ageing %u ", age);
 	}
-	if (tb[IFLA_VXLAN_LIMIT]) {
-		__u32 maxaddr = rta_getattr_u32(tb[IFLA_VXLAN_LIMIT]);
-		if (maxaddr == 0)
-			fprintf(f, "maxaddr unlimited ");
-		else
-			fprintf(f, "maxaddr %u ", maxaddr);
-	}
+
+	if (tb[IFLA_VXLAN_LIMIT] &&
+	    (maxaddr = rta_getattr_u32(tb[IFLA_VXLAN_LIMIT]) != 0))
+		    fprintf(f, "maxaddr %u ", maxaddr);
 }
 
 struct link_util vxlan_link_util = {