path: root/net/sched/act_ct.c

// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* -
 * net/sched/act_ct.c  Connection Tracking action
 *
 * Authors:   Paul Blakey <paulb@mellanox.com>
 *            Yossi Kuperman <yossiku@mellanox.com>
 *            Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/act_api.h>
#include <net/ip.h>
#include <net/ipv6_frag.h>
#include <uapi/linux/tc_act/tc_ct.h>
#include <net/tc_act/tc_ct.h>

#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <uapi/linux/netfilter/nf_nat.h>

static struct tc_action_ops act_ct_ops;
static unsigned int ct_net_id;

struct tc_ct_action_net {
	struct tc_action_net tn; /* Must be first */
	bool labels;
};

/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
				   u16 zone_id, bool force)
{
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;

	ct = nf_ct_get(skb, &ctinfo);
	if (!ct)
		return false;
	if (!net_eq(net, read_pnet(&ct->ct_net)))
		return false;
	if (nf_ct_zone(ct)->id != zone_id)
		return false;

	/* Force conntrack entry direction. */
	if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
		if (nf_ct_is_confirmed(ct))
			nf_ct_kill(ct);

		nf_conntrack_put(&ct->ct_general);
		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);

		return false;
	}

	return true;
}

/* Trim the skb to the length specified by the IP/IPv6 header,
 * removing any trailing lower-layer padding. This prepares the skb
 * for higher-layer processing that assumes skb->len excludes padding
 * (such as nf_ip_checksum). The caller needs to pull the skb to the
 * network header, and ensure ip_hdr/ipv6_hdr points to valid data.
 */
static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)
{
	unsigned int len;
	int err;

	switch (family) {
	case NFPROTO_IPV4:
		len = ntohs(ip_hdr(skb)->tot_len);
		break;
	case NFPROTO_IPV6:
		len = sizeof(struct ipv6hdr)
			+ ntohs(ipv6_hdr(skb)->payload_len);
		break;
	default:
		len = skb->len;
	}

	err = pskb_trim_rcsum(skb, len);

	return err;
}

static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
{
	u8 family = NFPROTO_UNSPEC;

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		family = NFPROTO_IPV4;
		break;
	case htons(ETH_P_IPV6):
		family = NFPROTO_IPV6;
		break;
	default:
		break;
	}

	return family;
}

static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag)
{
	unsigned int len;

	len =  skb_network_offset(skb) + sizeof(struct iphdr);
	if (unlikely(skb->len < len))
		return -EINVAL;
	if (unlikely(!pskb_may_pull(skb, len)))
		return -ENOMEM;

	*frag = ip_is_fragment(ip_hdr(skb));
	return 0;
}

static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
{
	unsigned int flags = 0, len, payload_ofs = 0;
	unsigned short frag_off;
	int nexthdr;

	len =  skb_network_offset(skb) + sizeof(struct ipv6hdr);
	if (unlikely(skb->len < len))
		return -EINVAL;
	if (unlikely(!pskb_may_pull(skb, len)))
		return -ENOMEM;

	nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags);
	if (unlikely(nexthdr < 0))
		return -EPROTO;

	*frag = flags & IP6_FH_F_FRAG;
	return 0;
}

static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
				   u8 family, u16 zone)
{
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;
	int err = 0;
	bool frag;

	/* Previously seen (loopback)? Ignore. */
	ct = nf_ct_get(skb, &ctinfo);
	if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
		return 0;

	if (family == NFPROTO_IPV4)
		err = tcf_ct_ipv4_is_fragment(skb, &frag);
	else
		err = tcf_ct_ipv6_is_fragment(skb, &frag);
	if (err || !frag)
		return err;

	skb_get(skb);

	if (family == NFPROTO_IPV4) {
		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;

		memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
		local_bh_disable();
		err = ip_defrag(net, skb, user);
		local_bh_enable();
		if (err && err != -EINPROGRESS)
			goto out_free;
	} else { /* NFPROTO_IPV6 */
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;

		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
		err = nf_ct_frag6_gather(net, skb, user);
		if (err && err != -EINPROGRESS)
			goto out_free;
#else
		err = -EOPNOTSUPP;
		goto out_free;
#endif
	}

	skb_clear_hash(skb);
	skb->ignore_df = 1;
	return err;