net/ipv6/seg6_local.c

/*
 *  SR-IPv6 implementation
 *
 *  Author:
 *  David Lebrun <david.lebrun@uclouvain.be>
 *
 *
 *  This program is free software; you can redistribute it and/or
 *        modify it under the terms of the GNU General Public License
 *        as published by the Free Software Foundation; either version
 *        2 of the License, or (at your option) any later version.
 */

#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/net.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include <net/ip6_fib.h>
#include <net/route.h>
#include <net/seg6.h>
#include <linux/seg6.h>
#include <linux/seg6_local.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/dst_cache.h>
#ifdef CONFIG_IPV6_SEG6_HMAC
#include <net/seg6_hmac.h>
#endif

struct seg6_local_lwt;

struct seg6_action_desc {
	int action;
	unsigned long attrs;
	int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
	int static_headroom;
};

struct seg6_local_lwt {
	int action;
	struct ipv6_sr_hdr *srh;
	int table;
	struct in_addr nh4;
	struct in6_addr nh6;
	int iif;
	int oif;

	int headroom;
	struct seg6_action_desc *desc;
};

static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt)
{
	return (struct seg6_local_lwt *)lwt->data;
}

static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb)
{
	struct ipv6_sr_hdr *srh;
	struct ipv6hdr *hdr;
	int len;

	hdr = ipv6_hdr(skb);
	if (hdr->nexthdr != IPPROTO_ROUTING)
		return NULL;

	srh = (struct ipv6_sr_hdr *)(hdr + 1);
	len = (srh->hdrlen + 1) << 3;

	if (!pskb_may_pull(skb, sizeof(*hdr) + len))
		return NULL;

	if (!seg6_validate_srh(srh, len))
		return NULL;

	return srh;
}

static struct ipv6_sr_hdr *get_and_validate_srh(struct sk_buff *skb)
{
	struct ipv6_sr_hdr *srh;

	srh = get_srh(skb);
	if (!srh)
		return NULL;

	if (srh->segments_left == 0)
		return NULL;

#ifdef CONFIG_IPV6_SEG6_HMAC
	if (!seg6_hmac_validate_skb(skb))
		return NULL;
#endif

	return srh;
}

/* regular endpoint function */
static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	struct ipv6_sr_hdr *srh;
	struct in6_addr *addr;

	srh = get_and_validate_srh(skb);
	if (!srh)
		goto drop;

	srh->segments_left--;
	addr = srh->segments + srh->segments_left;

	ipv6_hdr(skb)->daddr = *addr;

	skb_dst_drop(skb);
	ip6_route_input(skb);

	return dst_input(skb);

drop:
	kfree_skb(skb);
	return -EINVAL;
}

/* regular endpoint, and forward to specified nexthop */
static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	struct net *net = dev_net(skb->dev);
	struct ipv6_sr_hdr *srh;
	struct dst_entry *dst;
	struct in6_addr *addr;
	struct ipv6hdr *hdr;
	struct flowi6 fl6;
	int flags;

	srh = get_and_validate_srh(skb);
	if (!srh)
		goto drop;

	srh->segments_left--;
	addr = srh->segments + srh->segments_left;

	hdr = ipv6_hdr(skb);
	hdr->daddr = *addr;

	skb_dst_drop(skb);

	fl6.flowi6_iif = skb->dev->ifindex;
	fl6.daddr = slwt->nh6;
	fl6.saddr = hdr->saddr;
	fl6.flowlabel = ip6_flowinfo(hdr);
	fl6.flowi6_mark = skb->mark;
	fl6.flowi6_proto = hdr->nexthdr;

	flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE |
		RT6_LOOKUP_F_REACHABLE;

	dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags);
	if (dst->dev->flags & IFF_LOOPBACK)
		goto drop;

	skb_dst_set(skb, dst);

	return dst_input(skb);

drop:
	kfree_skb(skb);
	return -EINVAL;
}

/* decapsulate and forward to specified nexthop */
static int input_action_end_dx6(struct sk_buff *skb,
				struct seg6_local_lwt *slwt)
{
	struct net *net = dev_net(skb->dev);
	struct ipv6hdr *inner_hdr;
	struct ipv6_sr_hdr *srh;
	struct dst_entry *dst;
	unsigned int off = 0;
	struct flowi6 fl6;
	bool use_nh;
	int flags;

	/* this function accepts IPv6 encapsulated packets, with either
	 * an SRH with SL=0, or no SRH.
	 */

	srh = get_srh(skb);
	if (srh && srh->segments_left > 0)
		goto drop;

#ifdef CONFIG_IPV6_SEG6_HMAC
	if (srh && !seg6_hmac_validate_skb(skb))
		goto drop;
#endif

	if (ipv6_find_hdr(skb, &off, IPPROTO_IPV6, NULL, NULL) < 0)
		goto drop;

	if (!pskb_pull(skb, off))
		goto drop;

	skb_postpull_rcsum(skb, skb_network_header(skb), off);

	skb_reset_network_header(skb);
	skb_reset_transport_header(skb);
	skb->encapsulation = 0;

	inner_hdr = ipv6_hdr(skb);

	/* The inner packet is not associated to any local interface,
	 * so we do not call netif_rx().
	 *
	 * If slwt->nh6 is set to ::, then lookup the nexthop for the
	 * inner packet's DA. Otherwise, use the specified nexthop.
	 */

	use_nh = !ipv6_addr_any(&slwt->nh6);

	skb_dst_drop(skb);

	fl6.flowi6_iif = skb->dev->ifindex;
	fl6.daddr = use_nh ? slwt->nh6 : inner_hdr->daddr;
	fl6.saddr = inner_hdr->saddr;
	fl6.flowlabel = ip6_flowinfo(inner_hdr);
	fl6.flowi6_mark = skb->mark;
	fl6.flowi6_proto = inner_hdr->nexthdr;

	flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_REACHABLE;
	if (use_nh)
		flags |= RT6_LOOKUP_F_IFACE;

	dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags);
	if (dst->dev->flags & IFF_LOOPBACK)
		goto drop;

	skb_dst_set(skb, dst);

	return dst_input(skb);
drop:
	kfree_skb(skb);
	return -EINVAL;
}

/* push an SRH on top of the current one */
static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	struct ipv6_sr_hdr *srh;
	int err = -EINVAL;

	srh = get_and_validate_srh(skb);
	if (!srh)
		goto drop;

	err = seg6_do_srh_inline(skb, slwt->srh);
	if (err)
		goto drop;

	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
	skb_set_transport_header(skb, sizeof(struct ipv6hdr));

	skb_dst_drop(skb);
	ip6_route_input(skb);

	return dst_input(skb);

drop:
	kfree_skb(skb);
	return err;
}

/* encapsulate within an outer IPv6 header and a specified SRH */
static int input_action_end_b6_encap(struct sk_buff *skb,
				     struct seg6_local_lwt *slwt)
{
	struct ipv6_sr_hdr *srh;
	struct in6_addr *addr;
	int err = -EINVAL;

	srh = get_and_validate_srh(skb);
	if (!srh)
		goto drop;

	srh->segments_left--;
	addr = srh->segments + srh->segments_left;
	ipv6_hdr(skb)->daddr = *addr;

	skb_reset_inner_headers(skb);
	skb->encapsulation = 1;

	err = seg6_do_srh_encap(skb, slwt->srh, IPPROTO_IPV6);
	if (err)
		goto drop;

	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
	skb_set_transport_header(skb, sizeof(struct ipv6hdr));

	skb_dst_drop(skb);
	ip6_route_input(skb);

	return dst_input(skb);

drop:
	kfree_skb(skb);
	return err;
}

static struct seg6_action_desc seg6_action_table[] = {
	{
		.action		= SEG6_LOCAL_ACTION_END,
		.attrs		= 0,
		.input		= input_action_end,
	},
	{
		.action		= SEG6_LOCAL_ACTION_END_X,
		.attrs		= (1 << SEG6_LOCAL_NH6),
		.input		= input_action_end_x,
	},
	{
		.action		= SEG6_LOCAL_ACTION_END_DX6,
		.attrs		= (1 << SEG6_LOCAL_NH6),
		.input		= input_action_end_dx6,
	},
	{
		.action		= SEG6_LOCAL_ACTION_END_B6,
		.attrs		= (1 << SEG6_LOCAL_SRH),
		.input		= input_action_end_b6,
	},
	{
		.action		= SEG6_LOCAL_ACTION_END_B6_ENCAP,
		.attrs		= (1 << SEG6_LOCAL_SRH),
		.input		= input_action_end_b6_encap,
		.static_headroom	= sizeof(struct ipv6hdr),
	}
};

static struct seg6_action_desc *__get_action_desc(int action)
{
	struct seg6_action_desc *desc;
	int i, count;

	count = sizeof(seg6_action_table) / sizeof(struct seg6_action_desc);
	for (i = 0; i < count; i++) {
		desc = &seg6_action_table[i];
		if (desc->action == action)
			return desc;
	}

	return NULL;
}

static int seg6_local_input(struct sk_buff *skb)
{
	struct dst_entry *orig_dst = skb_dst(skb);
	struct seg6_action_desc *desc;
	struct seg6_local_lwt *slwt;

	slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
	desc = slwt->desc;

	return desc->input(skb, slwt);
}

static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
	[SEG6_LOCAL_ACTION]	= { .type = NLA_U32 },
	[SEG6_LOCAL_SRH]	= { .type = NLA_BINARY },
	[SEG6_LOCAL_TABLE]	= { .type = NLA_U32 },
	[SEG6_LOCAL_NH4]	= { .type = NLA_BINARY,
				    .len = sizeof(struct in_addr) },
	[SEG6_LOCAL_NH6]	= { .type = NLA_BINARY,
				    .len = sizeof(struct in6_addr) },
	[SEG6_LOCAL_IIF]	= { .type = NLA_U32 },
	[SEG6_LOCAL_OIF]	= { .type = NLA_U32 },
};

static int parse_nla_srh(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	struct ipv6_sr_hdr *srh;
	int len;

	srh = nla_data(attrs[SEG6_LOCAL_SRH]);
	len = nla_len(attrs[SEG6_LOCAL_SRH]);

	/* SRH must contain at least one segment */
	if (len < sizeof(*srh) + sizeof(struct in6_addr))
		return -EINVAL;

	if (!seg6_validate_srh(srh, len))
		return -EINVAL;

	slwt->srh = kmalloc(len, GFP_KERNEL);
	if (!slwt->srh)
		return -ENOMEM;

	memcpy(slwt->srh, srh, len);

	slwt->headroom += len;

	return 0;
}

static int put_nla_srh(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	struct ipv6_sr_hdr *srh;
	struct nlattr *nla;
	int len;

	srh = slwt->srh;
	len = (srh->hdrlen + 1) << 3;

	nla = nla_reserve(skb, SEG6_LOCAL_SRH, len);
	if (!nla)
		return -EMSGSIZE;

	memcpy(nla_data(nla), srh, len);

	return 0;
}

static int cmp_nla_srh(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
	int len = (a->srh->hdrlen + 1) << 3;

	if (len != ((b->srh->hdrlen + 1) << 3))
		return 1;

	return memcmp(a->srh, b->srh, len);
}

static int parse_nla_table(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	slwt->table = nla_get_u32(attrs[SEG6_LOCAL_TABLE]);

	return 0;
}

static int put_nla_table(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	if (nla_put_u32(skb, SEG6_LOCAL_TABLE, slwt->table))
		return -EMSGSIZE;

	return 0;
}

static int cmp_nla_table(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
	if (a->table != b->table)
		return 1;

	return 0;
}

static int parse_nla_nh4(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	memcpy(&slwt->nh4, nla_data(attrs[SEG6_LOCAL_NH4]),
	       sizeof(struct in_addr));

	return 0;
}

static int put_nla_nh4(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	struct nlattr *nla;

	nla = nla_reserve(skb, SEG6_LOCAL_NH4, sizeof(struct in_addr));
	if (!nla)
		return -EMSGSIZE;

	memcpy(nla_data(nla), &slwt->nh4, sizeof(struct in_addr));

	return 0;
}

static int cmp_nla_nh4(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
	return memcmp(&a->nh4, &b->nh4, sizeof(struct in_addr));
}

static int parse_nla_nh6(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	memcpy(&slwt->nh6, nla_data(attrs[SEG6_LOCAL_NH6]),
	       sizeof(struct in6_addr));

	return 0;
}

static int put_nla_nh6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	struct nlattr *nla;

	nla = nla_reserve(skb, SEG6_LOCAL_NH6, sizeof(struct in6_addr));
	if (!nla)
		return -EMSGSIZE;

	memcpy(nla_data(nla), &slwt->nh6, sizeof(struct in6_addr));

	return 0;
}

static int cmp_nla_nh6(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
	return memcmp(&a->nh6, &b->nh6, sizeof(struct in6_addr));
}

static int parse_nla_iif(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	slwt->iif = nla_get_u32(attrs[SEG6_LOCAL_IIF]);

	return 0;
}

static int put_nla_iif(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	if (nla_put_u32(skb, SEG6_LOCAL_IIF, slwt->iif))
		return -EMSGSIZE;

	return 0;
}

static int cmp_nla_iif(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
	if (a->iif != b->iif)
		return 1;

	return 0;
}

static int parse_nla_oif(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	slwt->oif = nla_get_u32(attrs[SEG6_LOCAL_OIF]);

	return 0;
}

static int put_nla_oif(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
	if (nla_put_u32(skb, SEG6_LOCAL_OIF, slwt->oif))
		return -EMSGSIZE;

	return 0;
}

static int cmp_nla_oif(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
{
	if (a->oif != b->oif)
		return 1;

	return 0;
}

struct seg6_action_param {
	int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt);
	int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
	int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b);
};

static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
	[SEG6_LOCAL_SRH]	= { .parse = parse_nla_srh,
				    .put = put_nla_srh,
				    .cmp = cmp_nla_srh },

	[SEG6_LOCAL_TABLE]	= { .parse = parse_nla_table,
				    .put = put_nla_table,
				    .cmp = cmp_nla_table },

	[SEG6_LOCAL_NH4]	= { .parse = parse_nla_nh4,
				    .put = put_nla_nh4,
				    .cmp = cmp_nla_nh4 },

	[SEG6_LOCAL_NH6]	= { .parse = parse_nla_nh6,
				    .put = put_nla_nh6,
				    .cmp = cmp_nla_nh6 },

	[SEG6_LOCAL_IIF]	= { .parse = parse_nla_iif,
				    .put = put_nla_iif,
				    .cmp = cmp_nla_iif },

	[SEG6_LOCAL_OIF]	= { .parse = parse_nla_oif,
				    .put = put_nla_oif,
				    .cmp = cmp_nla_oif },
};

static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
	struct seg6_action_param *param;
	struct seg6_action_desc *desc;
	int i, err;

	desc = __get_action_desc(slwt->action);
	if (!desc)
		return -EINVAL;

	if (!desc->input)
		return -EOPNOTSUPP;

	slwt->desc = desc;
	slwt->headroom += desc->static_headroom;

	for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
		if (desc->attrs & (1 << i)) {
			if (!attrs[i])
				return -EINVAL;

			param = &seg6_action_params[i];

			err = param->parse(attrs, slwt);
			if (err < 0)
				return err;
		}
	}

	return 0;
}

static int seg6_local_build_state(struct nlattr *nla, unsigned int family,
				  const void *cfg, struct lwtunnel_state **ts,
				  struct netlink_ext_ack *extack)
{
	struct nlattr *tb[SEG6_LOCAL_MAX + 1];
	struct lwtunnel_state *newts;
	struct seg6_local_lwt *slwt;
	int err;

	err = nla_parse_nested(tb, SEG6_LOCAL_MAX, nla, seg6_local_policy,
			       extack);

	if (err < 0)
		return err;

	if (!tb[SEG6_LOCAL_ACTION])
		return -EINVAL;

	newts = lwtunnel_state_alloc(sizeof(*slwt));
	if (!newts)
		return -ENOMEM;

	slwt = seg6_local_lwtunnel(newts);
	slwt->action = nla_get_u32(tb[SEG6_LOCAL_ACTION]);

	err = parse_nla_action(tb, slwt);
	if (err < 0)
		goto out_free;

	newts->type = LWTUNNEL_ENCAP_SEG6_LOCAL;
	newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT;
	newts->headroom = slwt->headroom;

	*ts = newts;

	return 0;

out_free:
	kfree(slwt->srh);
	kfree(newts);
	return err;
}

static void seg6_local_destroy_state(struct lwtunnel_state *lwt)
{
	struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);

	kfree(slwt->srh);
}

static int seg6_local_fill_encap(struct sk_buff *skb,
				 struct lwtunnel_state *lwt)
{
	struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
	struct seg6_action_param *param;
	int i, err;

	if (nla_put_u32(skb, SEG6_LOCAL_ACTION, slwt->action))
		return -EMSGSIZE;

	for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
		if (slwt->desc->attrs & (1 << i)) {
			param = &seg6_action_params[i];
			err = param->put(skb, slwt);
			if (err < 0)
				return err;
		}
	}

	return 0;
}

static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
{
	struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
	unsigned long attrs;
	int nlsize;

	nlsize = nla_total_size(4); /* action */

	attrs = slwt->desc->attrs;

	if (attrs & (1 << SEG6_LOCAL_SRH))
		nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3);

	if (attrs & (1 << SEG6_LOCAL_TABLE))
		nlsize += nla_total_size(4);

	if (attrs & (1 << SEG6_LOCAL_NH4))
		nlsize += nla_total_size(4);

	if (attrs & (1 << SEG6_LOCAL_NH6))
		nlsize += nla_total_size(16);

	if (attrs & (1 << SEG6_LOCAL_IIF))
		nlsize += nla_total_size(4);

	if (attrs & (1 << SEG6_LOCAL_OIF))
		nlsize += nla_total_size(4);

	return nlsize;
}

static int seg6_local_cmp_encap(struct lwtunnel_state *a,
				struct lwtunnel_state *b)
{
	struct seg6_local_lwt *slwt_a, *slwt_b;
	struct seg6_action_param *param;
	int i;

	slwt_a = seg6_local_lwtunnel(a);
	slwt_b = seg6_local_lwtunnel(b);

	if (slwt_a->action != slwt_b->action)
		return 1;

	if (slwt_a->desc->attrs != slwt_b->desc->attrs)
		return 1;

	for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
		if (slwt_a->desc->attrs & (1 << i)) {
			param = &seg6_action_params[i];
			if (param->cmp(slwt_a, slwt_b))
				return 1;
		}
	}

	return 0;
}

static const struct lwtunnel_encap_ops seg6_local_ops = {
	.build_state	= seg6_local_build_state,
	.destroy_state	= seg6_local_destroy_state,
	.input		= seg6_local_input,
	.fill_encap	= seg6_local_fill_encap,
	.get_encap_size	= seg6_local_get_encap_size,
	.cmp_encap	= seg6_local_cmp_encap,
	.owner		= THIS_MODULE,
};

int __init seg6_local_init(void)
{
	return lwtunnel_encap_add_ops(&seg6_local_ops,
				      LWTUNNEL_ENCAP_SEG6_LOCAL);
}

void seg6_local_exit(void)
{
	lwtunnel_encap_del_ops(&seg6_local_ops, LWTUNNEL_ENCAP_SEG6_LOCAL);
}