[2/3] net: netfilter: Add RFC-7597 Section 5.1 PSID support

Commit Message

Cole Dishington July 16, 2021, 12:27 a.m. UTC

Adds support for masquerading into a smaller subset of ports -
defined by the PSID values from RFC-7597 Section 5.1. This is part of
the support for MAP-E and Lightweight 4over6, which allows multiple
devices to share an IPv4 address by splitting the L4 port / id into
ranges.

Co-developed-by: Anthony Lineham <[e-mail]>
Signed-off-by: Anthony Lineham <[e-mail]>
Co-developed-by: Scott Parlane <[e-mail]>
Signed-off-by: Scott Parlane <[e-mail]>
Signed-off-by: Blair Steven <[e-mail]>
Signed-off-by: Cole Dishington <[e-mail]>
---

Notes:
    Thanks for your time reviewing!
    
    Changes in v4:
    - Add support for a=0 (A=2^16) special case.
    - Now that offset=0 is used for the special case of 2^16 (as it cannot fit
      in a u16) the divide by zero issues are no longer present.

 net/netfilter/nf_nat_core.c       | 39 +++++++++++++++++++++++++++----
 net/netfilter/nf_nat_masquerade.c | 20 ++++++++++++++--
 2 files changed, 53 insertions(+), 6 deletions(-)

Comments

Florian Westphal July 16, 2021, 3:18 p.m. UTC | #1

Cole Dishington <[e-mail]> wrote:
> diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
> index 7de595ead06a..4a9448684504 100644
> --- a/net/netfilter/nf_nat_core.c
> +++ b/net/netfilter/nf_nat_core.c
> @@ -195,13 +195,36 @@ static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t,
>  static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple,
>  			     enum nf_nat_manip_type maniptype,
>  			     const union nf_conntrack_man_proto *min,
> -			     const union nf_conntrack_man_proto *max)
> +			     const union nf_conntrack_man_proto *max,
> +			     const union nf_conntrack_man_proto *base,
> +			     bool is_psid)
>  {
>  	__be16 port;
> +	u16 psid, psid_mask, offset_mask;
> +
> +	/* In this case we are in PSID mode, avoid checking all ranges by computing bitmasks */
> +	if (is_psid) {
> +		u16 power_j = ntohs(max->all) - ntohs(min->all) + 1;
> +		u32 offset = ntohs(base->all);
> +		u16 power_a;
> +
> +		if (offset == 0)
> +			offset = 1 << 16;
> +
> +		power_a = (1 << 16) / offset;

Since the dividie is only needed nat setup and not for each packet I
think its ok.

> +	if (range->flags & NF_NAT_RANGE_PSID) {
> +		u16 base = ntohs(range->base_proto.all);
> +		u16 min =  ntohs(range->min_proto.all);
> +		u16 off = 0;
> +
> +		/* If offset=0, port range is in one contiguous block */
> +		if (base)
> +			off = prandom_u32() % (((1 << 16) / base) - 1);

Bases 32769 > gives 0 for the modulo value, so perhaps compute that
independently.

You could reject > 32769 in the iptables checkentry target.

Also, base of 21846 and above always give 0 result (% 1).

I don't know psid well enough to give a recommendation here.

If such inputs are nonsensical, just reject it when userspace asks for
this and add a 

if (WARN_ON_ONCE(base > bogus))
	return NF_DROP;

with s small coment explaining that xtables is supposed to not provide
such value.

Other than this I think its ok.

I still dislike the 'bool is_psid' in the nat core, but I can't find
a better solution.

Patch

diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 7de595ead06a..4a9448684504 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -195,13 +195,36 @@  static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t,
 static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple,
 			     enum nf_nat_manip_type maniptype,
 			     const union nf_conntrack_man_proto *min,
-			     const union nf_conntrack_man_proto *max)
+			     const union nf_conntrack_man_proto *max,
+			     const union nf_conntrack_man_proto *base,
+			     bool is_psid)
 {
 	__be16 port;
+	u16 psid, psid_mask, offset_mask;
+
+	/* In this case we are in PSID mode, avoid checking all ranges by computing bitmasks */
+	if (is_psid) {
+		u16 power_j = ntohs(max->all) - ntohs(min->all) + 1;
+		u32 offset = ntohs(base->all);
+		u16 power_a;
+
+		if (offset == 0)
+			offset = 1 << 16;
+
+		power_a = (1 << 16) / offset;
+		offset_mask = (power_a - 1) * offset;
+		psid_mask = ((offset / power_j) << 1) - 1;
+		psid = ntohs(min->all) & psid_mask;
+	}
 
 	switch (tuple->dst.protonum) {
 	case IPPROTO_ICMP:
 	case IPPROTO_ICMPV6:
+		if (is_psid) {
+			return (offset_mask == 0 ||
+				(ntohs(tuple->src.u.icmp.id) & offset_mask) != 0) &&
+				((ntohs(tuple->src.u.icmp.id) & psid_mask) == psid);
+		}
 		return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
 		       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
 	case IPPROTO_GRE: /* all fall though */
@@ -215,6 +238,10 @@  static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple,
 		else
 			port = tuple->dst.u.all;
 
+		if (is_psid) {
+			return (offset_mask == 0 || (ntohs(port) & offset_mask) != 0) &&
+				((ntohs(port) & psid_mask) == psid);
+		}
 		return ntohs(port) >= ntohs(min->all) &&
 		       ntohs(port) <= ntohs(max->all);
 	default:
@@ -239,7 +266,8 @@  static int in_range(const struct nf_conntrack_tuple *tuple,
 		return 1;
 
 	return l4proto_in_range(tuple, NF_NAT_MANIP_SRC,
-				&range->min_proto, &range->max_proto);
+				&range->min_proto, &range->max_proto, &range->base_proto,
+				range->flags & NF_NAT_RANGE_PSID);
 }
 
 static inline int
@@ -532,8 +560,11 @@  get_unique_tuple(struct nf_conntrack_tuple *tuple,
 		if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
 			if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) &&
 			    l4proto_in_range(tuple, maniptype,
-			          &range->min_proto,
-			          &range->max_proto) &&
+				  &range->min_proto,
+				  &range->max_proto,
+				  &range->base_proto,
+				  range->flags &
+				  NF_NAT_RANGE_PSID) &&
 			    (range->min_proto.all == range->max_proto.all ||
 			     !nf_nat_used_tuple(tuple, ct)))
 				return;
diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c
index 8e8a65d46345..7e2fb0da344a 100644
--- a/net/netfilter/nf_nat_masquerade.c
+++ b/net/netfilter/nf_nat_masquerade.c
@@ -55,8 +55,24 @@  nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 	newrange.flags       = range->flags | NF_NAT_RANGE_MAP_IPS;
 	newrange.min_addr.ip = newsrc;
 	newrange.max_addr.ip = newsrc;
-	newrange.min_proto   = range->min_proto;
-	newrange.max_proto   = range->max_proto;
+
+	if (range->flags & NF_NAT_RANGE_PSID) {
+		u16 base = ntohs(range->base_proto.all);
+		u16 min =  ntohs(range->min_proto.all);
+		u16 off = 0;
+
+		/* If offset=0, port range is in one contiguous block */
+		if (base)
+			off = prandom_u32() % (((1 << 16) / base) - 1);
+
+		newrange.min_proto.all   = htons(min + base * off);
+		newrange.max_proto.all   = htons(ntohs(newrange.min_proto.all) + ntohs(range->max_proto.all) - min);
+		newrange.base_proto      = range->base_proto;
+		newrange.flags           = newrange.flags | NF_NAT_RANGE_PROTO_SPECIFIED;
+	} else {
+		newrange.min_proto       = range->min_proto;
+		newrange.max_proto       = range->max_proto;
+	}
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);