vxlan: Allow configuration of DF behaviour

Allow users to set the IPv4 DF bit in outgoing packets, or to inherit its
value from the IPv4 inner header. If the encapsulated protocol is IPv6 and
DF is configured to be inherited, always set it.

For IPv4, inheriting DF from the inner header was probably intended from
the very beginning judging by the comment to vxlan_xmit(), but it wasn't
actually implemented -- also because it would have done more harm than
good, without handling for ICMP Fragmentation Needed messages.

According to RFC 7348, "Path MTU discovery MAY be used". An expired RFC
draft, draft-saum-nvo3-pmtud-over-vxlan-05, whose purpose was to describe
PMTUD implementation, says that "is a MUST that Vxlan gateways [...]
SHOULD set the DF-bit [...]", whatever that means.

Given this background, the only sane option is probably to let the user
decide, and keep the current behaviour as default.

This only applies to non-lwt tunnels: if an external control plane is
used, tunnel key will still control the DF flag.

v2:
- DF behaviour configuration only applies for non-lwt tunnels, move DF
  setting to if (!info) block in vxlan_xmit_one() (Stephen Hemminger)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 1 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0851af6733f3..c3e65e78f015 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2278,13 +2278,24 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 
-		/* Bypass encapsulation if the destination is local */
 		if (!info) {
+			/* Bypass encapsulation if the destination is local */
 			err = encap_bypass_if_local(skb, dev, vxlan, dst,
 						    dst_port, ifindex, vni,
 						    &rt->dst, rt->rt_flags);
 			if (err)
 				goto out_unlock;
+
+			if (vxlan->cfg.df == VXLAN_DF_SET) {
+				df = htons(IP_DF);
+			} else if (vxlan->cfg.df == VXLAN_DF_INHERIT) {
+				struct ethhdr *eth = eth_hdr(skb);
+
+				if (ntohs(eth->h_proto) == ETH_P_IPV6 ||
+				    (ntohs(eth->h_proto) == ETH_P_IP &&
+				     old_iph->frag_off & htons(IP_DF)))
+					df = htons(IP_DF);
+			}
 		} else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
 			df = htons(IP_DF);
 		}
@@ -2837,6 +2848,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_GPE]	= { .type = NLA_FLAG, },
 	[IFLA_VXLAN_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG },
 	[IFLA_VXLAN_TTL_INHERIT]	= { .type = NLA_FLAG },
+	[IFLA_VXLAN_DF]		= { .type = NLA_U8 },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -2893,6 +2905,16 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
+	if (data[IFLA_VXLAN_DF]) {
+		enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]);
+
+		if (df < 0 || df > VXLAN_DF_MAX) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF],
+					    "Invalid DF attribute");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
@@ -3538,6 +3560,9 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 		conf->mtu = nla_get_u32(tb[IFLA_MTU]);
 	}
 
+	if (data[IFLA_VXLAN_DF])
+		conf->df = nla_get_u8(data[IFLA_VXLAN_DF]);
+
 	return 0;
 }
 
@@ -3630,6 +3655,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TTL_INHERIT */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_DF */
 		nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
@@ -3696,6 +3722,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT,
 		       !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
+	    nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) ||
 	    nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 			!!(vxlan->cfg.flags & VXLAN_F_LEARN)) ||