[linux.git] / net / netfilter / nf_flow_table.c

#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_tuple.h>

struct flow_offload_entry {
	struct flow_offload	flow;
	struct nf_conn		*ct;
	struct rcu_head		rcu_head;
};

struct flow_offload *
flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
{
	struct flow_offload_entry *entry;
	struct flow_offload *flow;

	if (unlikely(nf_ct_is_dying(ct) ||
	    !atomic_inc_not_zero(&ct->ct_general.use)))
		return NULL;

	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
	if (!entry)
		goto err_ct_refcnt;

	flow = &entry->flow;

	if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst))
		goto err_dst_cache_original;

	if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst))
		goto err_dst_cache_reply;

	entry->ct = ct;

	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) {
	case NFPROTO_IPV4:
		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 =
			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in;
		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 =
			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in;
		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 =
			ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in;
		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 =
			ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in;
		break;
	case NFPROTO_IPV6:
		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 =
			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 =
			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6;
		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 =
			ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6;
		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 =
			ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6;
		break;
	}

	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto =
		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto =
		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto =
		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto =
		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;

	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache =
		  route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache =
		  route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst;

	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port =
		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port;
	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port =
		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port =
		ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port =
		ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;

	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir =
						FLOW_OFFLOAD_DIR_ORIGINAL;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir =
						FLOW_OFFLOAD_DIR_REPLY;

	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
		route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx =
		route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
		route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx =
		route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;

	if (ct->status & IPS_SRC_NAT)
		flow->flags |= FLOW_OFFLOAD_SNAT;
	else if (ct->status & IPS_DST_NAT)
		flow->flags |= FLOW_OFFLOAD_DNAT;

	return flow;

err_dst_cache_reply:
	dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst);
err_dst_cache_original:
	kfree(entry);
err_ct_refcnt:
	nf_ct_put(ct);

	return NULL;
}
EXPORT_SYMBOL_GPL(flow_offload_alloc);

void flow_offload_free(struct flow_offload *flow)
{
	struct flow_offload_entry *e;

	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
	e = container_of(flow, struct flow_offload_entry, flow);
	kfree(e);
}
EXPORT_SYMBOL_GPL(flow_offload_free);

void flow_offload_dead(struct flow_offload *flow)
{
	flow->flags |= FLOW_OFFLOAD_DYING;
}
EXPORT_SYMBOL_GPL(flow_offload_dead);

int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
{
	flow->timeout = (u32)jiffies;

	rhashtable_insert_fast(&flow_table->rhashtable,
			       &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
			       *flow_table->type->params);
	rhashtable_insert_fast(&flow_table->rhashtable,
			       &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
			       *flow_table->type->params);
	return 0;
}
EXPORT_SYMBOL_GPL(flow_offload_add);

void flow_offload_del(struct nf_flowtable *flow_table,
		      struct flow_offload *flow)
{
	struct flow_offload_entry *e;

	rhashtable_remove_fast(&flow_table->rhashtable,
			       &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
			       *flow_table->type->params);
	rhashtable_remove_fast(&flow_table->rhashtable,
			       &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
			       *flow_table->type->params);

	e = container_of(flow, struct flow_offload_entry, flow);
	kfree_rcu(e, rcu_head);
}
EXPORT_SYMBOL_GPL(flow_offload_del);

struct flow_offload_tuple_rhash *
flow_offload_lookup(struct nf_flowtable *flow_table,
		    struct flow_offload_tuple *tuple)
{
	return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
				      *flow_table->type->params);
}
EXPORT_SYMBOL_GPL(flow_offload_lookup);

static void nf_flow_release_ct(const struct flow_offload *flow)
{
	struct flow_offload_entry *e;

	e = container_of(flow, struct flow_offload_entry, flow);
	nf_ct_delete(e->ct, 0, 0);
	nf_ct_put(e->ct);
}

int nf_flow_table_iterate(struct nf_flowtable *flow_table,
			  void (*iter)(struct flow_offload *flow, void *data),
			  void *data)
{
	struct flow_offload_tuple_rhash *tuplehash;
	struct rhashtable_iter hti;
	struct flow_offload *flow;
	int err;

	err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
	if (err)
		return err;

	rhashtable_walk_start(&hti);

	while ((tuplehash = rhashtable_walk_next(&hti))) {
		if (IS_ERR(tuplehash)) {
			err = PTR_ERR(tuplehash);
			if (err != -EAGAIN)
				goto out;

			continue;
		}
		if (tuplehash->tuple.dir)
			continue;

		flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);

		iter(flow, data);
	}
out:
	rhashtable_walk_stop(&hti);
	rhashtable_walk_exit(&hti);

	return err;
}
EXPORT_SYMBOL_GPL(nf_flow_table_iterate);

static inline bool nf_flow_has_expired(const struct flow_offload *flow)
{
	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
}

static inline bool nf_flow_is_dying(const struct flow_offload *flow)
{
	return flow->flags & FLOW_OFFLOAD_DYING;
}

void nf_flow_offload_work_gc(struct work_struct *work)
{
	struct flow_offload_tuple_rhash *tuplehash;
	struct nf_flowtable *flow_table;
	struct rhashtable_iter hti;
	struct flow_offload *flow;
	int err;

	flow_table = container_of(work, struct nf_flowtable, gc_work.work);

	err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
	if (err)
		goto schedule;

	rhashtable_walk_start(&hti);

	while ((tuplehash = rhashtable_walk_next(&hti))) {
		if (IS_ERR(tuplehash)) {
			err = PTR_ERR(tuplehash);
			if (err != -EAGAIN)
				goto out;

			continue;
		}
		if (tuplehash->tuple.dir)
			continue;

		flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);

		if (nf_flow_has_expired(flow) ||
		    nf_flow_is_dying(flow)) {
			flow_offload_del(flow_table, flow);
			nf_flow_release_ct(flow);
		}
	}
out:
	rhashtable_walk_stop(&hti);
	rhashtable_walk_exit(&hti);
schedule:
	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);

static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
{
	const struct flow_offload_tuple *tuple = data;

	return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
}

static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
{
	const struct flow_offload_tuple_rhash *tuplehash = data;

	return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
}

static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
					const void *ptr)
{
	const struct flow_offload_tuple *tuple = arg->key;
	const struct flow_offload_tuple_rhash *x = ptr;

	if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
		return 1;

	return 0;
}

const struct rhashtable_params nf_flow_offload_rhash_params = {
	.head_offset		= offsetof(struct flow_offload_tuple_rhash, node),
	.hashfn			= flow_offload_hash,
	.obj_hashfn		= flow_offload_hash_obj,
	.obj_cmpfn		= flow_offload_hash_cmp,
	.automatic_shrinking	= true,
};
EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params);

static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
				__be16 port, __be16 new_port)
{
	struct tcphdr *tcph;

	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
		return -1;

	tcph = (void *)(skb_network_header(skb) + thoff);
	inet_proto_csum_replace2(&tcph->check, skb, port, new_port, true);

	return 0;
}

static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
				__be16 port, __be16 new_port)
{
	struct udphdr *udph;

	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
		return -1;

	udph = (void *)(skb_network_header(skb) + thoff);
	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
		inet_proto_csum_replace2(&udph->check, skb, port,
					 new_port, true);
		if (!udph->check)
			udph->check = CSUM_MANGLED_0;
	}

	return 0;
}

static int nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff,
			    u8 protocol, __be16 port, __be16 new_port)
{
	switch (protocol) {
	case IPPROTO_TCP:
		if (nf_flow_nat_port_tcp(skb, thoff, port, new_port) < 0)
			return NF_DROP;
		break;
	case IPPROTO_UDP:
		if (nf_flow_nat_port_udp(skb, thoff, port, new_port) < 0)
			return NF_DROP;
		break;
	}

	return 0;
}

int nf_flow_snat_port(const struct flow_offload *flow,
		      struct sk_buff *skb, unsigned int thoff,
		      u8 protocol, enum flow_offload_tuple_dir dir)
{
	struct flow_ports *hdr;
	__be16 port, new_port;

	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
	    skb_try_make_writable(skb, thoff + sizeof(*hdr)))
		return -1;

	hdr = (void *)(skb_network_header(skb) + thoff);

	switch (dir) {
	case FLOW_OFFLOAD_DIR_ORIGINAL:
		port = hdr->source;
		new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port;
		hdr->source = new_port;
		break;
	case FLOW_OFFLOAD_DIR_REPLY:
		port = hdr->dest;
		new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port;
		hdr->dest = new_port;
		break;
	default:
		return -1;
	}

	return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
}
EXPORT_SYMBOL_GPL(nf_flow_snat_port);

int nf_flow_dnat_port(const struct flow_offload *flow,
		      struct sk_buff *skb, unsigned int thoff,
		      u8 protocol, enum flow_offload_tuple_dir dir)
{
	struct flow_ports *hdr;
	__be16 port, new_port;

	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
	    skb_try_make_writable(skb, thoff + sizeof(*hdr)))
		return -1;

	hdr = (void *)(skb_network_header(skb) + thoff);

	switch (dir) {
	case FLOW_OFFLOAD_DIR_ORIGINAL:
		port = hdr->dest;
		new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port;
		hdr->dest = new_port;
		break;
	case FLOW_OFFLOAD_DIR_REPLY:
		port = hdr->source;
		new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port;
		hdr->source = new_port;
		break;
	default:
		return -1;
	}

	return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
}
EXPORT_SYMBOL_GPL(nf_flow_dnat_port);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <[email protected]>");
Commit	Line	Data
ac2a6666 PNA	1	#include <linux/kernel.h>
	2	#include <linux/init.h>
	3	#include <linux/module.h>
	4	#include <linux/netfilter.h>
	5	#include <linux/rhashtable.h>
	6	#include <linux/netdevice.h>
	7	#include <net/netfilter/nf_flow_table.h>
	8	#include <net/netfilter/nf_conntrack.h>
	9	#include <net/netfilter/nf_conntrack_core.h>
	10	#include <net/netfilter/nf_conntrack_tuple.h>
	11
	12	struct flow_offload_entry {
	13	struct flow_offload flow;
	14	struct nf_conn *ct;
	15	struct rcu_head rcu_head;
	16	};
	17
	18	struct flow_offload *
	19	flow_offload_alloc(struct nf_conn ct, struct nf_flow_route route)
	20	{
	21	struct flow_offload_entry *entry;
	22	struct flow_offload *flow;
	23
	24	if (unlikely(nf_ct_is_dying(ct) \|\|
	25	!atomic_inc_not_zero(&ct->ct_general.use)))
	26	return NULL;
	27
	28	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
	29	if (!entry)
	30	goto err_ct_refcnt;
	31
	32	flow = &entry->flow;
	33
	34	if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst))
	35	goto err_dst_cache_original;
	36
	37	if (!dst_hold_safe(route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst))
	38	goto err_dst_cache_reply;
	39
	40	entry->ct = ct;
	41
	42	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) {
	43	case NFPROTO_IPV4:
	44	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 =
	45	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in;
	46	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 =
	47	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in;
	48	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 =
	49	ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in;
	50	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 =
	51	ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in;
	52	break;
	53	case NFPROTO_IPV6:
	54	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 =
	55	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
	56	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 =
	57	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6;
	58	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 =
	59	ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6;
	60	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 =
	61	ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6;
	62	break;
	63	}
	64
65	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto =
66	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
67	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto =
68	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
69	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto =
70	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
71	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto =
72	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
73
74	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache =
75	route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst;
76	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache =
77	route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst;
78
79	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port =
80	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port;
81	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port =
82	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
83	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port =
84	ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port;
85	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port =
86	ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;
87
88	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir =
89	FLOW_OFFLOAD_DIR_ORIGINAL;
90	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir =
91	FLOW_OFFLOAD_DIR_REPLY;
92
93	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
94	route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
95	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx =
96	route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
97	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
98	route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
99	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx =
100	route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
101
102	if (ct->status & IPS_SRC_NAT)
103	flow->flags \|= FLOW_OFFLOAD_SNAT;
104	else if (ct->status & IPS_DST_NAT)
105	flow->flags \|= FLOW_OFFLOAD_DNAT;
106
107	return flow;
108
109	err_dst_cache_reply:
110	dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst);
111	err_dst_cache_original:
112	kfree(entry);
113	err_ct_refcnt:
114	nf_ct_put(ct);
115
116	return NULL;
117	}
118	EXPORT_SYMBOL_GPL(flow_offload_alloc);
119
120	void flow_offload_free(struct flow_offload *flow)
121	{
122	struct flow_offload_entry *e;
123
124	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
125	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
126	e = container_of(flow, struct flow_offload_entry, flow);
127	kfree(e);
128	}
129	EXPORT_SYMBOL_GPL(flow_offload_free);
130
131	void flow_offload_dead(struct flow_offload *flow)
132	{
133	flow->flags \|= FLOW_OFFLOAD_DYING;
134	}
135	EXPORT_SYMBOL_GPL(flow_offload_dead);
136
137	int flow_offload_add(struct nf_flowtable flow_table, struct flow_offload flow)
138	{
139	flow->timeout = (u32)jiffies;
140
141	rhashtable_insert_fast(&flow_table->rhashtable,
142	&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
143	*flow_table->type->params);
144	rhashtable_insert_fast(&flow_table->rhashtable,
145	&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
146	*flow_table->type->params);
147	return 0;
148	}
149	EXPORT_SYMBOL_GPL(flow_offload_add);
150
151	void flow_offload_del(struct nf_flowtable *flow_table,
152	struct flow_offload *flow)
153	{
154	struct flow_offload_entry *e;
155
156	rhashtable_remove_fast(&flow_table->rhashtable,
157	&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
158	*flow_table->type->params);
159	rhashtable_remove_fast(&flow_table->rhashtable,
160	&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
161	*flow_table->type->params);
162
163	e = container_of(flow, struct flow_offload_entry, flow);
164	kfree_rcu(e, rcu_head);
165	}
166	EXPORT_SYMBOL_GPL(flow_offload_del);
167
168	struct flow_offload_tuple_rhash *
169	flow_offload_lookup(struct nf_flowtable *flow_table,
170	struct flow_offload_tuple *tuple)
171	{
172	return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
173	*flow_table->type->params);
174	}
175	EXPORT_SYMBOL_GPL(flow_offload_lookup);
176
177	static void nf_flow_release_ct(const struct flow_offload *flow)
178	{
179	struct flow_offload_entry *e;
180
181	e = container_of(flow, struct flow_offload_entry, flow);
182	nf_ct_delete(e->ct, 0, 0);
183	nf_ct_put(e->ct);
184	}
185
186	int nf_flow_table_iterate(struct nf_flowtable *flow_table,
187	void (iter)(struct flow_offload flow, void *data),
188	void *data)
189	{
190	struct flow_offload_tuple_rhash *tuplehash;
191	struct rhashtable_iter hti;
192	struct flow_offload *flow;
193	int err;
194
195	err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
196	if (err)
197	return err;
198
199	rhashtable_walk_start(&hti);
200
201	while ((tuplehash = rhashtable_walk_next(&hti))) {
202	if (IS_ERR(tuplehash)) {
203	err = PTR_ERR(tuplehash);
204	if (err != -EAGAIN)
205	goto out;
206
207	continue;
208	}
209	if (tuplehash->tuple.dir)
210	continue;
211
212	flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
213
214	iter(flow, data);
215	}
216	out:
217	rhashtable_walk_stop(&hti);
218	rhashtable_walk_exit(&hti);
219
220	return err;
221	}
222	EXPORT_SYMBOL_GPL(nf_flow_table_iterate);
223
224	static inline bool nf_flow_has_expired(const struct flow_offload *flow)
225	{
226	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
227	}
228
229	static inline bool nf_flow_is_dying(const struct flow_offload *flow)
230	{
231	return flow->flags & FLOW_OFFLOAD_DYING;
232	}
233
234	void nf_flow_offload_work_gc(struct work_struct *work)
235	{
236	struct flow_offload_tuple_rhash *tuplehash;
237	struct nf_flowtable *flow_table;
238	struct rhashtable_iter hti;
239	struct flow_offload *flow;
240	int err;
241
242	flow_table = container_of(work, struct nf_flowtable, gc_work.work);
243
244	err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
245	if (err)
246	goto schedule;
247
248	rhashtable_walk_start(&hti);
249
250	while ((tuplehash = rhashtable_walk_next(&hti))) {
251	if (IS_ERR(tuplehash)) {
252	err = PTR_ERR(tuplehash);
253	if (err != -EAGAIN)
254	goto out;
255
256	continue;
257	}
258	if (tuplehash->tuple.dir)
259	continue;
260
261	flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
262
263	if (nf_flow_has_expired(flow) \|\|
264	nf_flow_is_dying(flow)) {
265	flow_offload_del(flow_table, flow);
266	nf_flow_release_ct(flow);
267	}
268	}
269	out:
270	rhashtable_walk_stop(&hti);
271	rhashtable_walk_exit(&hti);
272	schedule:
273	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
274	}
275	EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);
276
277	static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
278	{
279	const struct flow_offload_tuple *tuple = data;
280
281	return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
282	}
283
284	static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
285	{
286	const struct flow_offload_tuple_rhash *tuplehash = data;
287
288	return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
289	}
290
291	static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
292	const void *ptr)
293	{
294	const struct flow_offload_tuple *tuple = arg->key;
295	const struct flow_offload_tuple_rhash *x = ptr;
296
297	if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
298	return 1;
299
300	return 0;
301	}
302
303	const struct rhashtable_params nf_flow_offload_rhash_params = {
304	.head_offset = offsetof(struct flow_offload_tuple_rhash, node),
305	.hashfn = flow_offload_hash,
306	.obj_hashfn = flow_offload_hash_obj,
307	.obj_cmpfn = flow_offload_hash_cmp,
308	.automatic_shrinking = true,
309	};
310	EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params);
311
312	static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
313	__be16 port, __be16 new_port)
314	{
315	struct tcphdr *tcph;
316
317	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) \|\|
318	skb_try_make_writable(skb, thoff + sizeof(*tcph)))
319	return -1;
320
321	tcph = (void *)(skb_network_header(skb) + thoff);
322	inet_proto_csum_replace2(&tcph->check, skb, port, new_port, true);
323
324	return 0;
325	}
326
327	static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
328	__be16 port, __be16 new_port)
329	{
330	struct udphdr *udph;
331
332	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) \|\|
333	skb_try_make_writable(skb, thoff + sizeof(*udph)))
334	return -1;
335
336	udph = (void *)(skb_network_header(skb) + thoff);
337	if (udph->check \|\| skb->ip_summed == CHECKSUM_PARTIAL) {
338	inet_proto_csum_replace2(&udph->check, skb, port,
339	new_port, true);
340	if (!udph->check)
341	udph->check = CSUM_MANGLED_0;
342	}
343
344	return 0;
345	}
346
347	static int nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff,
348	u8 protocol, __be16 port, __be16 new_port)
349	{
350	switch (protocol) {
351	case IPPROTO_TCP:
352	if (nf_flow_nat_port_tcp(skb, thoff, port, new_port) < 0)
353	return NF_DROP;
354	break;
355	case IPPROTO_UDP:
356	if (nf_flow_nat_port_udp(skb, thoff, port, new_port) < 0)
357	return NF_DROP;
358	break;
359	}
360
361	return 0;
362	}
363
364	int nf_flow_snat_port(const struct flow_offload *flow,
365	struct sk_buff *skb, unsigned int thoff,
366	u8 protocol, enum flow_offload_tuple_dir dir)
367	{
368	struct flow_ports *hdr;
369	__be16 port, new_port;
370
371	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) \|\|
372	skb_try_make_writable(skb, thoff + sizeof(*hdr)))
373	return -1;
374
375	hdr = (void *)(skb_network_header(skb) + thoff);
376
377	switch (dir) {
378	case FLOW_OFFLOAD_DIR_ORIGINAL:
379	port = hdr->source;
380	new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port;
381	hdr->source = new_port;
382	break;
383	case FLOW_OFFLOAD_DIR_REPLY:
384	port = hdr->dest;
385	new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port;
386	hdr->dest = new_port;
387	break;
388	default:
389	return -1;
390	}
391
392	return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
393	}
394	EXPORT_SYMBOL_GPL(nf_flow_snat_port);
395
396	int nf_flow_dnat_port(const struct flow_offload *flow,
397	struct sk_buff *skb, unsigned int thoff,
398	u8 protocol, enum flow_offload_tuple_dir dir)
399	{
400	struct flow_ports *hdr;
401	__be16 port, new_port;
402
403	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) \|\|
404	skb_try_make_writable(skb, thoff + sizeof(*hdr)))
405	return -1;
406
407	hdr = (void *)(skb_network_header(skb) + thoff);
408
409	switch (dir) {
410	case FLOW_OFFLOAD_DIR_ORIGINAL:
411	port = hdr->dest;
412	new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port;
413	hdr->dest = new_port;
414	break;
415	case FLOW_OFFLOAD_DIR_REPLY:
416	port = hdr->source;
417	new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port;
418	hdr->source = new_port;
419	break;
420	default:
421	return -1;
422	}
423
424	return nf_flow_nat_port(skb, thoff, protocol, port, new_port);
425	}
426	EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
427
428	MODULE_LICENSE("GPL");
429	MODULE_AUTHOR("Pablo Neira Ayuso <[email protected]>");