xfrm: allow to avoid copying DSCP during encapsulation

By default, DSCP is copying during encapsulation.
Copying the DSCP in IPsec tunneling may be a bit dangerous because packets with
different DSCP may get reordered relative to each other in the network and then
dropped by the remote IPsec GW if the reordering becomes too big compared to the
replay window.

It is possible to avoid this copy with netfilter rules, but it's very convenient
to be able to configure it for each SA directly.

This patch adds a toogle for this purpose. By default, it's not set to maintain
backward compatibility.

Field flags in struct xfrm_usersa_info is full, hence I add a new attribute.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

include/net/xfrm.h

@@ -162,6 +162,7 @@ struct xfrm_state {
 		xfrm_address_t	saddr;
 		int		header_len;
 		int		trailer_len;
+		u32		extra_flags;
 	} props;
 
 	struct xfrm_lifetime_cfg lft;

include/uapi/linux/xfrm.h

@@ -297,6 +297,7 @@ enum xfrm_attr_type_t {
 	XFRMA_MARK,		/* struct xfrm_mark */
 	XFRMA_TFCPAD,		/* __u32 */
 	XFRMA_REPLAY_ESN_VAL,	/* struct xfrm_replay_esn */
+	XFRMA_SA_EXTRA_FLAGS,	/* __u32 */
 	__XFRMA_MAX
 
 #define XFRMA_MAX (__XFRMA_MAX - 1)
@@ -367,6 +368,8 @@ struct xfrm_usersa_info {
 #define XFRM_STATE_ESN		128
 };
 
+#define XFRM_SA_XFLAG_DONT_ENCAP_DSCP	1
+
 struct xfrm_usersa_id {
 	xfrm_address_t			daddr;
 	__be32				spi;

net/ipv4/ipcomp.c

@@ -75,6 +75,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
 	t->props.mode = x->props.mode;
 	t->props.saddr.a4 = x->props.saddr.a4;
 	t->props.flags = x->props.flags;
+	t->props.extra_flags = x->props.extra_flags;
 	memcpy(&t->mark, &x->mark, sizeof(t->mark));
 
 	if (xfrm_init_state(t))

net/ipv4/xfrm4_mode_tunnel.c

@@ -103,8 +103,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
 
-	/* DS disclosed */
-	top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos,
+	/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
+	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+		top_iph->tos = 0;
+	else
+		top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+	top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
 					    XFRM_MODE_SKB_CB(skb)->tos);
 
 	flags = x->props.flags;

net/ipv6/xfrm6_mode_tunnel.c

@@ -49,8 +49,11 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	       sizeof(top_iph->flow_lbl));
 	top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
 
-	dsfield = XFRM_MODE_SKB_CB(skb)->tos;
-	dsfield = INET_ECN_encapsulate(dsfield, dsfield);
+	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+		dsfield = 0;
+	else
+		dsfield = XFRM_MODE_SKB_CB(skb)->tos;
+	dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
 	if (x->props.flags & XFRM_STATE_NOECN)
 		dsfield &= ~INET_ECN_MASK;
 	ipv6_change_dsfield(top_iph, 0, dsfield);

net/xfrm/xfrm_state.c

@@ -1187,6 +1187,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
 		goto error;
 
 	x->props.flags = orig->props.flags;
+	x->props.extra_flags = orig->props.extra_flags;
 
 	x->curlft.add_time = orig->curlft.add_time;
 	x->km.state = orig->km.state;

net/xfrm/xfrm_user.c

@@ -515,6 +515,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 
 	copy_from_user_state(x, p);
 
+	if (attrs[XFRMA_SA_EXTRA_FLAGS])
+		x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]);
+
 	if ((err = attach_aead(&x->aead, &x->props.ealgo,
 			       attrs[XFRMA_ALG_AEAD])))
 		goto error;
@@ -779,6 +782,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 
 	copy_to_user_state(x, p);
 
+	if (x->props.extra_flags) {
+		ret = nla_put_u32(skb, XFRMA_SA_EXTRA_FLAGS,
+				  x->props.extra_flags);
+		if (ret)
+			goto out;
+	}
+
 	if (x->coaddr) {
 		ret = nla_put(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr);
 		if (ret)
@@ -2302,6 +2312,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_MARK]		= { .len = sizeof(struct xfrm_mark) },
 	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
 	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
+	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
 };
 
 static struct xfrm_link {
@@ -2495,6 +2506,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x)
 				    x->security->ctx_len);
 	if (x->coaddr)
 		l += nla_total_size(sizeof(*x->coaddr));
+	if (x->props.extra_flags)
+		l += nla_total_size(sizeof(x->props.extra_flags));
 
 	/* Must count x->lastused as it may become non-zero behind our back. */
 	l += nla_total_size(sizeof(u64));