Patchwork [ipsec-next] xfrm: allow to avoid copying DSCP during encapsulation

login
register
mail settings
Submitter Nicolas Dichtel
Date Feb. 18, 2013, 3:32 p.m.
Message ID <1361201559-31972-1-git-send-email-nicolas.dichtel@6wind.com>
Download mbox | patch
Permalink /patch/221404/
State Awaiting Upstream
Delegated to: David Miller
Headers show

Comments

Nicolas Dichtel - Feb. 18, 2013, 3:32 p.m.
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>
---
 include/net/xfrm.h           |  1 +
 include/uapi/linux/xfrm.h    |  3 +++
 net/ipv4/xfrm4_mode_tunnel.c |  8 ++++++--
 net/ipv6/xfrm6_mode_tunnel.c |  7 +++++--
 net/xfrm/xfrm_user.c         | 13 +++++++++++++
 5 files changed, 28 insertions(+), 4 deletions(-)
Steffen Klassert - Feb. 22, 2013, 6:06 a.m.
On Mon, Feb 18, 2013 at 04:32:39PM +0100, Nicolas Dichtel wrote:
> 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>
> ---
>  include/net/xfrm.h           |  1 +
>  include/uapi/linux/xfrm.h    |  3 +++
>  net/ipv4/xfrm4_mode_tunnel.c |  8 ++++++--
>  net/ipv6/xfrm6_mode_tunnel.c |  7 +++++--
>  net/xfrm/xfrm_user.c         | 13 +++++++++++++
>  5 files changed, 28 insertions(+), 4 deletions(-)
> 
> diff --git a/include/net/xfrm.h b/include/net/xfrm.h
> index 30f3e5b..c5f12da 100644
> --- a/include/net/xfrm.h
> +++ b/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;

Please ensure that your new extra_flags are copied whenever needed.
Right now we would loose them when we clone a state with
xfrm_state_clone().

>  
>  	struct xfrm_lifetime_cfg lft;
> diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
> index 28e493b..f07f422 100644
> --- a/include/uapi/linux/xfrm.h
> +++ b/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_STATE_EXTRA_FLAGS_DONT_ENCAP_DSCP		1

Can we have a shorter name for this flag, please?

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 30f3e5b..c5f12da 100644
--- a/include/net/xfrm.h
+++ b/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;
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 28e493b..f07f422 100644
--- a/include/uapi/linux/xfrm.h
+++ b/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_STATE_EXTRA_FLAGS_DONT_ENCAP_DSCP		1
+
 struct xfrm_usersa_id {
 	xfrm_address_t			daddr;
 	__be32				spi;
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index ddee0a0..0273555 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/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_STATE_EXTRA_FLAGS_DONT_ENCAP_DSCP */
+	if (x->props.extra_flags & XFRM_STATE_EXTRA_FLAGS_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;
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 9f2095b..7c1cc59 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/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_STATE_EXTRA_FLAGS_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);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index eb872b2..8cf7f5f 100644
--- a/net/xfrm/xfrm_user.c
+++ b/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));