Merge branch 'bpf-flow-labels'

Daniel Borkmann says:

====================
BPF support for flow labels

This set adds support for tunnel key flow labels for vxlan
and geneve devices in collect meta data mode and eBPF support
for managing these. For details please see individual patches.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 47 insertions, 12 deletions

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 6a0cbbe03e5d..33185b9a435e 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -68,6 +68,7 @@ struct geneve_dev {
 	u8                 tos;		/* TOS override */
 	union geneve_addr  remote;	/* IP address for link partner */
 	struct list_head   next;	/* geneve's per namespace list */
+	__be32		   label;	/* IPv6 flowlabel override */
 	__be16		   dst_port;
 	bool		   collect_md;
 	struct gro_cells   gro_cells;
@@ -846,6 +847,7 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 		fl6->daddr = info->key.u.ipv6.dst;
 		fl6->saddr = info->key.u.ipv6.src;
 		fl6->flowi6_tos = RT_TOS(info->key.tos);
+		fl6->flowlabel = info->key.label;
 		dst_cache = &info->dst_cache;
 	} else {
 		prio = geneve->tos;
@@ -857,6 +859,7 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 		}
 
 		fl6->flowi6_tos = RT_TOS(prio);
+		fl6->flowlabel = geneve->label;
 		fl6->daddr = geneve->remote.sin6.sin6_addr;
 		dst_cache = &geneve->dst_cache;
 	}
@@ -998,6 +1001,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct flowi6 fl6;
 	__u8 prio, ttl;
 	__be16 sport;
+	__be32 label;
 	bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
 	u32 flags = geneve->flags;
 
@@ -1041,6 +1045,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 		prio = ip_tunnel_ecn_encap(key->tos, iip, skb);
 		ttl = key->ttl;
+		label = info->key.label;
 	} else {
 		err = geneve6_build_skb(dst, skb, 0, geneve->vni,
 					0, NULL, flags, xnet);
@@ -1052,9 +1057,11 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (!ttl && ipv6_addr_is_multicast(&fl6.daddr))
 			ttl = 1;
 		ttl = ttl ? : ip6_dst_hoplimit(dst);
+		label = geneve->label;
 	}
+
 	udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev,
-			     &fl6.saddr, &fl6.daddr, prio, ttl,
+			     &fl6.saddr, &fl6.daddr, prio, ttl, label,
 			     sport, geneve->dst_port,
 			     !!(flags & GENEVE_F_UDP_ZERO_CSUM6_TX));
 	return NETDEV_TX_OK;
@@ -1238,6 +1245,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_REMOTE6]		= { .len = sizeof(struct in6_addr) },
 	[IFLA_GENEVE_TTL]		= { .type = NLA_U8 },
 	[IFLA_GENEVE_TOS]		= { .type = NLA_U8 },
+	[IFLA_GENEVE_LABEL]		= { .type = NLA_U32 },
 	[IFLA_GENEVE_PORT]		= { .type = NLA_U16 },
 	[IFLA_GENEVE_COLLECT_METADATA]	= { .type = NLA_FLAG },
 	[IFLA_GENEVE_UDP_CSUM]		= { .type = NLA_U8 },
@@ -1295,8 +1303,8 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn,
 
 static int geneve_configure(struct net *net, struct net_device *dev,
 			    union geneve_addr *remote,
-			    __u32 vni, __u8 ttl, __u8 tos, __be16 dst_port,
-			    bool metadata, u32 flags)
+			    __u32 vni, __u8 ttl, __u8 tos, __be32 label,
+			    __be16 dst_port, bool metadata, u32 flags)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *t, *geneve = netdev_priv(dev);
@@ -1306,7 +1314,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 	if (!remote)
 		return -EINVAL;
 	if (metadata &&
-	    (remote->sa.sa_family != AF_UNSPEC || vni || tos || ttl))
+	    (remote->sa.sa_family != AF_UNSPEC || vni || tos || ttl || label))
 		return -EINVAL;
 
 	geneve->net = net;
@@ -1321,10 +1329,14 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 	    (remote->sa.sa_family == AF_INET6 &&
 	     ipv6_addr_is_multicast(&remote->sin6.sin6_addr)))
 		return -EINVAL;
+	if (label && remote->sa.sa_family != AF_INET6)
+		return -EINVAL;
+
 	geneve->remote = *remote;
 
 	geneve->ttl = ttl;
 	geneve->tos = tos;
+	geneve->label = label;
 	geneve->dst_port = dst_port;
 	geneve->collect_md = metadata;
 	geneve->flags = flags;
@@ -1367,6 +1379,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 	__u8 ttl = 0, tos = 0;
 	bool metadata = false;
 	union geneve_addr remote = geneve_remote_unspec;
+	__be32 label = 0;
 	__u32 vni = 0;
 	u32 flags = 0;
 
@@ -1403,6 +1416,10 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 	if (data[IFLA_GENEVE_TOS])
 		tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
 
+	if (data[IFLA_GENEVE_LABEL])
+		label = nla_get_be32(data[IFLA_GENEVE_LABEL]) &
+			IPV6_FLOWLABEL_MASK;
+
 	if (data[IFLA_GENEVE_PORT])
 		dst_port = nla_get_be16(data[IFLA_GENEVE_PORT]);
 
@@ -1421,8 +1438,8 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 	    nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]))
 		flags |= GENEVE_F_UDP_ZERO_CSUM6_RX;
 
-	return geneve_configure(net, dev, &remote, vni, ttl, tos, dst_port,
-				metadata, flags);
+	return geneve_configure(net, dev, &remote, vni, ttl, tos, label,
+				dst_port, metadata, flags);
 }
 
 static void geneve_dellink(struct net_device *dev, struct list_head *head)
@@ -1439,6 +1456,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
+		nla_total_size(sizeof(__be32)) +  /* IFLA_GENEVE_LABEL */
 		nla_total_size(sizeof(__be16)) +  /* IFLA_GENEVE_PORT */
 		nla_total_size(0) +	 /* IFLA_GENEVE_COLLECT_METADATA */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */
@@ -1469,7 +1487,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	}
 
 	if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) ||
-	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
+	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos) ||
+	    nla_put_be32(skb, IFLA_GENEVE_LABEL, geneve->label))
 		goto nla_put_failure;
 
 	if (nla_put_be16(skb, IFLA_GENEVE_PORT, geneve->dst_port))
@@ -1521,7 +1540,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 		return dev;
 
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
-			       0, 0, 0, htons(dst_port), true,
+			       0, 0, 0, 0, htons(dst_port), true,
 			       GENEVE_F_UDP_ZERO_CSUM6_RX);
 	if (err)
 		goto err;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2399099e68cf..8eda76f9e474 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1790,6 +1790,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
 #if IS_ENABLED(CONFIG_IPV6)
 static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 					  struct sk_buff *skb, int oif, u8 tos,
+					  __be32 label,
 					  const struct in6_addr *daddr,
 					  struct in6_addr *saddr,
 					  struct dst_cache *dst_cache,
@@ -1813,6 +1814,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	fl6.flowi6_tos = RT_TOS(tos);
 	fl6.daddr = *daddr;
 	fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr;
+	fl6.flowlabel = label;
 	fl6.flowi6_mark = skb->mark;
 	fl6.flowi6_proto = IPPROTO_UDP;
 
@@ -1888,7 +1890,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	struct vxlan_metadata _md;
 	struct vxlan_metadata *md = &_md;
 	__be16 src_port = 0, dst_port;
-	__be32 vni;
+	__be32 vni, label;
 	__be16 df = 0;
 	__u8 tos, ttl;
 	int err;
@@ -1939,12 +1941,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	if (tos == 1)
 		tos = ip_tunnel_get_dsfield(old_iph, skb);
 
+	label = vxlan->cfg.label;
 	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
 				     vxlan->cfg.port_max, true);
 
 	if (info) {
 		ttl = info->key.ttl;
 		tos = info->key.tos;
+		label = info->key.label;
 		udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
 
 		if (info->options_len)
@@ -2020,7 +2024,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		ndst = vxlan6_get_route(vxlan, skb,
 					rdst ? rdst->remote_ifindex : 0, tos,
-					&dst->sin6.sin6_addr, &saddr,
+					label, &dst->sin6.sin6_addr, &saddr,
 					dst_cache, info);
 		if (IS_ERR(ndst)) {
 			netdev_dbg(dev, "no route to %pI6\n",
@@ -2067,7 +2071,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 		udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
 				     &saddr, &dst->sin6.sin6_addr, tos, ttl,
-				     src_port, dst_port, !udp_sum);
+				     label, src_port, dst_port, !udp_sum);
 #endif
 	}
 
@@ -2390,7 +2394,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		if (!vxlan->vn6_sock)
 			return -EINVAL;
 		ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
-					&info->key.u.ipv6.dst,
+					info->key.label, &info->key.u.ipv6.dst,
 					&info->key.u.ipv6.src, NULL, info);
 		if (IS_ERR(ndst))
 			return PTR_ERR(ndst);
@@ -2505,6 +2509,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_LOCAL6]	= { .len = sizeof(struct in6_addr) },
 	[IFLA_VXLAN_TOS]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_TTL]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_LABEL]	= { .type = NLA_U32 },
 	[IFLA_VXLAN_LEARNING]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_AGEING]	= { .type = NLA_U32 },
 	[IFLA_VXLAN_LIMIT]	= { .type = NLA_U32 },
@@ -2739,6 +2744,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		vxlan->flags |= VXLAN_F_IPV6;
 	}
 
+	if (conf->label && !use_ipv6) {
+		pr_info("label only supported in use with IPv6\n");
+		return -EINVAL;
+	}
+
 	if (conf->remote_ifindex) {
 		lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
 		dst->remote_ifindex = conf->remote_ifindex;
@@ -2887,6 +2897,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_TTL])
 		conf.ttl = nla_get_u8(data[IFLA_VXLAN_TTL]);
 
+	if (data[IFLA_VXLAN_LABEL])
+		conf.label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
+			     IPV6_FLOWLABEL_MASK;
+
 	if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING]))
 		conf.flags |= VXLAN_F_LEARN;
 
@@ -2990,6 +3004,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
+		nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_RSC */
@@ -3053,6 +3068,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) ||
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
+	    nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 			!!(vxlan->flags & VXLAN_F_LEARN)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_PROXY,