[mirror_ubuntu-jammy-kernel.git] / net / netfilter / nft_flow_offload.c

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/workqueue.h>
#include <linux/spinlock.h>
#include <linux/netfilter/nf_tables.h>
#include <net/ip.h> /* for ipv4 options. */
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <linux/netfilter/nf_conntrack_common.h>
#include <net/netfilter/nf_flow_table.h>

struct nft_flow_offload {
	struct nft_flowtable	*flowtable;
};

static int nft_flow_route(const struct nft_pktinfo *pkt,
			  const struct nf_conn *ct,
			  struct nf_flow_route *route,
			  enum ip_conntrack_dir dir)
{
	struct dst_entry *this_dst = skb_dst(pkt->skb);
	struct dst_entry *other_dst = NULL;
	struct flowi fl;

	memset(&fl, 0, sizeof(fl));
	switch (nft_pf(pkt)) {
	case NFPROTO_IPV4:
		fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip;
		fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
		break;
	case NFPROTO_IPV6:
		fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6;
		fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex;
		break;
	}

	nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt));
	if (!other_dst)
		return -ENOENT;

	route->tuple[dir].dst		= this_dst;
	route->tuple[!dir].dst		= other_dst;

	return 0;
}

static bool nft_flow_offload_skip(struct sk_buff *skb)
{
	struct ip_options *opt  = &(IPCB(skb)->opt);

	if (unlikely(opt->optlen))
		return true;
	if (skb_sec_path(skb))
		return true;

	return false;
}

static void nft_flow_offload_eval(const struct nft_expr *expr,
				  struct nft_regs *regs,
				  const struct nft_pktinfo *pkt)
{
	struct nft_flow_offload *priv = nft_expr_priv(expr);
	struct nf_flowtable *flowtable = &priv->flowtable->data;
	enum ip_conntrack_info ctinfo;
	struct nf_flow_route route;
	struct flow_offload *flow;
	enum ip_conntrack_dir dir;
	struct nf_conn *ct;
	int ret;

	if (nft_flow_offload_skip(pkt->skb))
		goto out;

	ct = nf_ct_get(pkt->skb, &ctinfo);
	if (!ct)
		goto out;

	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
	case IPPROTO_TCP:
	case IPPROTO_UDP:
		break;
	default:
		goto out;
	}

	if (test_bit(IPS_HELPER_BIT, &ct->status))
		goto out;

	if (ctinfo == IP_CT_NEW ||
	    ctinfo == IP_CT_RELATED)
		goto out;

	if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
		goto out;

	dir = CTINFO2DIR(ctinfo);
	if (nft_flow_route(pkt, ct, &route, dir) < 0)
		goto err_flow_route;

	flow = flow_offload_alloc(ct, &route);
	if (!flow)
		goto err_flow_alloc;

	ret = flow_offload_add(flowtable, flow);
	if (ret < 0)
		goto err_flow_add;

	return;

err_flow_add:
	flow_offload_free(flow);
err_flow_alloc:
	dst_release(route.tuple[!dir].dst);
err_flow_route:
	clear_bit(IPS_OFFLOAD_BIT, &ct->status);
out:
	regs->verdict.code = NFT_BREAK;
}

static int nft_flow_offload_validate(const struct nft_ctx *ctx,
				     const struct nft_expr *expr,
				     const struct nft_data **data)
{
	unsigned int hook_mask = (1 << NF_INET_FORWARD);

	return nft_chain_validate_hooks(ctx->chain, hook_mask);
}

static int nft_flow_offload_init(const struct nft_ctx *ctx,
				 const struct nft_expr *expr,
				 const struct nlattr * const tb[])
{
	struct nft_flow_offload *priv = nft_expr_priv(expr);
	u8 genmask = nft_genmask_next(ctx->net);
	struct nft_flowtable *flowtable;

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

	flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME],
					 genmask);
	if (IS_ERR(flowtable))
		return PTR_ERR(flowtable);

	priv->flowtable = flowtable;
	flowtable->use++;

	return nf_ct_netns_get(ctx->net, ctx->family);
}

static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
				     const struct nft_expr *expr)
{
	struct nft_flow_offload *priv = nft_expr_priv(expr);

	priv->flowtable->use--;
	nf_ct_netns_put(ctx->net, ctx->family);
}

static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
	struct nft_flow_offload *priv = nft_expr_priv(expr);

	if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name))
		goto nla_put_failure;

	return 0;

nla_put_failure:
	return -1;
}

static struct nft_expr_type nft_flow_offload_type;
static const struct nft_expr_ops nft_flow_offload_ops = {
	.type		= &nft_flow_offload_type,
	.size		= NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)),
	.eval		= nft_flow_offload_eval,
	.init		= nft_flow_offload_init,
	.destroy	= nft_flow_offload_destroy,
	.validate	= nft_flow_offload_validate,
	.dump		= nft_flow_offload_dump,
};

static struct nft_expr_type nft_flow_offload_type __read_mostly = {
	.name		= "flow_offload",
	.ops		= &nft_flow_offload_ops,
	.maxattr	= NFTA_FLOW_MAX,
	.owner		= THIS_MODULE,
};

static int flow_offload_netdev_event(struct notifier_block *this,
				     unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);

	if (event != NETDEV_DOWN)
		return NOTIFY_DONE;

	nf_flow_table_cleanup(dev);

	return NOTIFY_DONE;
}

static struct notifier_block flow_offload_netdev_notifier = {
	.notifier_call	= flow_offload_netdev_event,
};

static int __init nft_flow_offload_module_init(void)
{
	int err;

	err = register_netdevice_notifier(&flow_offload_netdev_notifier);
	if (err)
		goto err;

	err = nft_register_expr(&nft_flow_offload_type);
	if (err < 0)
		goto register_expr;

	return 0;

register_expr:
	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
err:
	return err;
}

static void __exit nft_flow_offload_module_exit(void)
{
	nft_unregister_expr(&nft_flow_offload_type);
	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
}

module_init(nft_flow_offload_module_init);
module_exit(nft_flow_offload_module_exit);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_ALIAS_NFT_EXPR("flow_offload");
Commit	Line	Data
a3c90f7a PNA	1	#include <linux/kernel.h>
	2	#include <linux/module.h>
	3	#include <linux/init.h>
	4	#include <linux/netlink.h>
	5	#include <linux/netfilter.h>
	6	#include <linux/workqueue.h>
	7	#include <linux/spinlock.h>
	8	#include <linux/netfilter/nf_tables.h>
	9	#include <net/ip.h> /* for ipv4 options. */
	10	#include <net/netfilter/nf_tables.h>
	11	#include <net/netfilter/nf_tables_core.h>
	12	#include <net/netfilter/nf_conntrack_core.h>
	13	#include <linux/netfilter/nf_conntrack_common.h>
	14	#include <net/netfilter/nf_flow_table.h>
	15
	16	struct nft_flow_offload {
	17	struct nft_flowtable *flowtable;
	18	};
	19
	20	static int nft_flow_route(const struct nft_pktinfo *pkt,
	21	const struct nf_conn *ct,
	22	struct nf_flow_route *route,
	23	enum ip_conntrack_dir dir)
	24	{
	25	struct dst_entry *this_dst = skb_dst(pkt->skb);
	26	struct dst_entry *other_dst = NULL;
	27	struct flowi fl;
	28
	29	memset(&fl, 0, sizeof(fl));
	30	switch (nft_pf(pkt)) {
	31	case NFPROTO_IPV4:
a799aea0	32	fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip;
10f4e765	33	fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
a3c90f7a PNA	34	break;
a3c90f7a PNA	35	case NFPROTO_IPV6:
a799aea0	36	fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6;
10f4e765	37	fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex;
a3c90f7a PNA	38	break;
	39	}
	40
	41	nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt));
	42	if (!other_dst)
	43	return -ENOENT;
	44
	45	route->tuple[dir].dst = this_dst;
a3c90f7a	46	route->tuple[!dir].dst = other_dst;
a3c90f7a PNA	47
	48	return 0;
	49	}
	50
	51	static bool nft_flow_offload_skip(struct sk_buff *skb)
	52	{
	53	struct ip_options *opt = &(IPCB(skb)->opt);
	54
	55	if (unlikely(opt->optlen))
	56	return true;
	57	if (skb_sec_path(skb))
	58	return true;
	59
	60	return false;
	61	}
	62
	63	static void nft_flow_offload_eval(const struct nft_expr *expr,
	64	struct nft_regs *regs,
	65	const struct nft_pktinfo *pkt)
	66	{
	67	struct nft_flow_offload *priv = nft_expr_priv(expr);
	68	struct nf_flowtable *flowtable = &priv->flowtable->data;
	69	enum ip_conntrack_info ctinfo;
	70	struct nf_flow_route route;
	71	struct flow_offload *flow;
	72	enum ip_conntrack_dir dir;
	73	struct nf_conn *ct;
	74	int ret;
	75
	76	if (nft_flow_offload_skip(pkt->skb))
	77	goto out;
	78
	79	ct = nf_ct_get(pkt->skb, &ctinfo);
	80	if (!ct)
	81	goto out;
	82
	83	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
	84	case IPPROTO_TCP:
	85	case IPPROTO_UDP:
	86	break;
	87	default:
	88	goto out;
	89	}
	90
	91	if (test_bit(IPS_HELPER_BIT, &ct->status))
	92	goto out;
	93
	94	if (ctinfo == IP_CT_NEW \|\|
	95	ctinfo == IP_CT_RELATED)
	96	goto out;
	97
	98	if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
	99	goto out;
	100
	101	dir = CTINFO2DIR(ctinfo);
	102	if (nft_flow_route(pkt, ct, &route, dir) < 0)
	103	goto err_flow_route;
	104
	105	flow = flow_offload_alloc(ct, &route);
	106	if (!flow)
	107	goto err_flow_alloc;
	108
	109	ret = flow_offload_add(flowtable, flow);
	110	if (ret < 0)
111	goto err_flow_add;
112
113	return;
114
115	err_flow_add:
116	flow_offload_free(flow);
117	err_flow_alloc:
118	dst_release(route.tuple[!dir].dst);
119	err_flow_route:
120	clear_bit(IPS_OFFLOAD_BIT, &ct->status);
121	out:
122	regs->verdict.code = NFT_BREAK;
123	}
124
125	static int nft_flow_offload_validate(const struct nft_ctx *ctx,
126	const struct nft_expr *expr,
127	const struct nft_data **data)
128	{
129	unsigned int hook_mask = (1 << NF_INET_FORWARD);
130
131	return nft_chain_validate_hooks(ctx->chain, hook_mask);
132	}
133
134	static int nft_flow_offload_init(const struct nft_ctx *ctx,
135	const struct nft_expr *expr,
136	const struct nlattr * const tb[])
137	{
138	struct nft_flow_offload *priv = nft_expr_priv(expr);
139	u8 genmask = nft_genmask_next(ctx->net);
140	struct nft_flowtable *flowtable;
141
142	if (!tb[NFTA_FLOW_TABLE_NAME])
143	return -EINVAL;
144
cac20fcd PNA	145	flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME],
cac20fcd PNA	146	genmask);
a3c90f7a PNA	147	if (IS_ERR(flowtable))
	148	return PTR_ERR(flowtable);
	149
	150	priv->flowtable = flowtable;
	151	flowtable->use++;
	152
36596dad	153	return nf_ct_netns_get(ctx->net, ctx->family);
a3c90f7a PNA	154	}
	155
	156	static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
	157	const struct nft_expr *expr)
	158	{
	159	struct nft_flow_offload *priv = nft_expr_priv(expr);
	160
	161	priv->flowtable->use--;
36596dad	162	nf_ct_netns_put(ctx->net, ctx->family);
a3c90f7a PNA	163	}
	164
	165	static int nft_flow_offload_dump(struct sk_buff skb, const struct nft_expr expr)
	166	{
	167	struct nft_flow_offload *priv = nft_expr_priv(expr);
	168
	169	if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name))
	170	goto nla_put_failure;
	171
	172	return 0;
	173
	174	nla_put_failure:
	175	return -1;
	176	}
	177
	178	static struct nft_expr_type nft_flow_offload_type;
	179	static const struct nft_expr_ops nft_flow_offload_ops = {
	180	.type = &nft_flow_offload_type,
	181	.size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)),
	182	.eval = nft_flow_offload_eval,
	183	.init = nft_flow_offload_init,
	184	.destroy = nft_flow_offload_destroy,
	185	.validate = nft_flow_offload_validate,
	186	.dump = nft_flow_offload_dump,
	187	};
	188
	189	static struct nft_expr_type nft_flow_offload_type __read_mostly = {
	190	.name = "flow_offload",
	191	.ops = &nft_flow_offload_ops,
	192	.maxattr = NFTA_FLOW_MAX,
	193	.owner = THIS_MODULE,
	194	};
	195
a3c90f7a PNA	196	static int flow_offload_netdev_event(struct notifier_block *this,
	197	unsigned long event, void *ptr)
	198	{
	199	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	200
	201	if (event != NETDEV_DOWN)
	202	return NOTIFY_DONE;
	203
5f1be84a	204	nf_flow_table_cleanup(dev);
a3c90f7a PNA	205
	206	return NOTIFY_DONE;
	207	}
	208
	209	static struct notifier_block flow_offload_netdev_notifier = {
	210	.notifier_call = flow_offload_netdev_event,
	211	};
	212
	213	static int __init nft_flow_offload_module_init(void)
	214	{
	215	int err;
	216
584eab29 TY	217	err = register_netdevice_notifier(&flow_offload_netdev_notifier);
	218	if (err)
	219	goto err;
a3c90f7a PNA	220
	221	err = nft_register_expr(&nft_flow_offload_type);
	222	if (err < 0)
	223	goto register_expr;
	224
	225	return 0;
	226
	227	register_expr:
	228	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
584eab29	229	err:
a3c90f7a PNA	230	return err;
	231	}
	232
	233	static void __exit nft_flow_offload_module_exit(void)
	234	{
a3c90f7a PNA	235	nft_unregister_expr(&nft_flow_offload_type);
a3c90f7a PNA	236	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
a3c90f7a PNA	237	}
	238
	239	module_init(nft_flow_offload_module_init);
	240	module_exit(nft_flow_offload_module_exit);
	241
	242	MODULE_LICENSE("GPL");
	243	MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
	244	MODULE_ALIAS_NFT_EXPR("flow_offload");