123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594 |
- // SPDX-License-Identifier: GPL-2.0-only
- #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/ip.h>
- #include <net/ip6_route.h>
- #include <net/netfilter/nf_tables.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_l4proto.h>
- #include <net/netfilter/nf_conntrack_tuple.h>
- static DEFINE_MUTEX(flowtable_lock);
- static LIST_HEAD(flowtables);
- static void
- flow_offload_fill_dir(struct flow_offload *flow,
- enum flow_offload_tuple_dir dir)
- {
- struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
- struct nf_conntrack_tuple *ctt = &flow->ct->tuplehash[dir].tuple;
- ft->dir = dir;
- switch (ctt->src.l3num) {
- case NFPROTO_IPV4:
- ft->src_v4 = ctt->src.u3.in;
- ft->dst_v4 = ctt->dst.u3.in;
- break;
- case NFPROTO_IPV6:
- ft->src_v6 = ctt->src.u3.in6;
- ft->dst_v6 = ctt->dst.u3.in6;
- break;
- }
- ft->l3proto = ctt->src.l3num;
- ft->l4proto = ctt->dst.protonum;
- ft->src_port = ctt->src.u.tcp.port;
- ft->dst_port = ctt->dst.u.tcp.port;
- }
- struct flow_offload *flow_offload_alloc(struct nf_conn *ct)
- {
- struct flow_offload *flow;
- if (unlikely(nf_ct_is_dying(ct) ||
- !atomic_inc_not_zero(&ct->ct_general.use)))
- return NULL;
- flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
- if (!flow)
- goto err_ct_refcnt;
- flow->ct = ct;
- flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
- flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_REPLY);
- if (ct->status & IPS_SRC_NAT)
- __set_bit(NF_FLOW_SNAT, &flow->flags);
- if (ct->status & IPS_DST_NAT)
- __set_bit(NF_FLOW_DNAT, &flow->flags);
- return flow;
- err_ct_refcnt:
- nf_ct_put(ct);
- return NULL;
- }
- EXPORT_SYMBOL_GPL(flow_offload_alloc);
- static int flow_offload_fill_route(struct flow_offload *flow,
- const struct nf_flow_route *route,
- enum flow_offload_tuple_dir dir)
- {
- struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple;
- struct dst_entry *other_dst = route->tuple[!dir].dst;
- struct dst_entry *dst = route->tuple[dir].dst;
- if (!dst_hold_safe(route->tuple[dir].dst))
- return -1;
- switch (flow_tuple->l3proto) {
- case NFPROTO_IPV4:
- flow_tuple->mtu = ip_dst_mtu_maybe_forward(dst, true);
- break;
- case NFPROTO_IPV6:
- flow_tuple->mtu = ip6_dst_mtu_forward(dst);
- break;
- }
- flow_tuple->iifidx = other_dst->dev->ifindex;
- flow_tuple->dst_cache = dst;
- return 0;
- }
- int flow_offload_route_init(struct flow_offload *flow,
- const struct nf_flow_route *route)
- {
- int err;
- err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
- if (err < 0)
- return err;
- err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
- if (err < 0)
- goto err_route_reply;
- flow->type = NF_FLOW_OFFLOAD_ROUTE;
- return 0;
- err_route_reply:
- dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst);
- return err;
- }
- EXPORT_SYMBOL_GPL(flow_offload_route_init);
- static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
- {
- tcp->state = TCP_CONNTRACK_ESTABLISHED;
- tcp->seen[0].td_maxwin = 0;
- tcp->seen[1].td_maxwin = 0;
- }
- #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ)
- #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ)
- static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
- {
- const struct nf_conntrack_l4proto *l4proto;
- int l4num = nf_ct_protonum(ct);
- unsigned int timeout;
- l4proto = nf_ct_l4proto_find(l4num);
- if (!l4proto)
- return;
- if (l4num == IPPROTO_TCP)
- timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT;
- else if (l4num == IPPROTO_UDP)
- timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT;
- else
- return;
- if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout)
- WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout);
- }
- static void flow_offload_fixup_ct_state(struct nf_conn *ct)
- {
- if (nf_ct_protonum(ct) == IPPROTO_TCP)
- flow_offload_fixup_tcp(&ct->proto.tcp);
- }
- static void flow_offload_fixup_ct(struct nf_conn *ct)
- {
- flow_offload_fixup_ct_state(ct);
- flow_offload_fixup_ct_timeout(ct);
- }
- static void flow_offload_route_release(struct flow_offload *flow)
- {
- dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
- dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
- }
- void flow_offload_free(struct flow_offload *flow)
- {
- switch (flow->type) {
- case NF_FLOW_OFFLOAD_ROUTE:
- flow_offload_route_release(flow);
- break;
- default:
- break;
- }
- nf_ct_put(flow->ct);
- kfree_rcu(flow, rcu_head);
- }
- EXPORT_SYMBOL_GPL(flow_offload_free);
- 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;
- }
- static 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,
- };
- int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
- {
- int err;
- flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
- err = rhashtable_insert_fast(&flow_table->rhashtable,
- &flow->tuplehash[0].node,
- nf_flow_offload_rhash_params);
- if (err < 0)
- return err;
- err = rhashtable_insert_fast(&flow_table->rhashtable,
- &flow->tuplehash[1].node,
- nf_flow_offload_rhash_params);
- if (err < 0) {
- rhashtable_remove_fast(&flow_table->rhashtable,
- &flow->tuplehash[0].node,
- nf_flow_offload_rhash_params);
- return err;
- }
- nf_ct_offload_timeout(flow->ct);
- if (nf_flowtable_hw_offload(flow_table)) {
- __set_bit(NF_FLOW_HW, &flow->flags);
- nf_flow_offload_add(flow_table, flow);
- }
- return 0;
- }
- EXPORT_SYMBOL_GPL(flow_offload_add);
- void flow_offload_refresh(struct nf_flowtable *flow_table,
- struct flow_offload *flow)
- {
- flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT;
- if (likely(!nf_flowtable_hw_offload(flow_table)))
- return;
- nf_flow_offload_add(flow_table, flow);
- }
- EXPORT_SYMBOL_GPL(flow_offload_refresh);
- static inline bool nf_flow_has_expired(const struct flow_offload *flow)
- {
- return nf_flow_timeout_delta(flow->timeout) <= 0;
- }
- static void flow_offload_del(struct nf_flowtable *flow_table,
- struct flow_offload *flow)
- {
- rhashtable_remove_fast(&flow_table->rhashtable,
- &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
- nf_flow_offload_rhash_params);
- rhashtable_remove_fast(&flow_table->rhashtable,
- &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
- nf_flow_offload_rhash_params);
- clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status);
- if (nf_flow_has_expired(flow))
- flow_offload_fixup_ct(flow->ct);
- else
- flow_offload_fixup_ct_timeout(flow->ct);
- flow_offload_free(flow);
- }
- void flow_offload_teardown(struct flow_offload *flow)
- {
- set_bit(NF_FLOW_TEARDOWN, &flow->flags);
- flow_offload_fixup_ct_state(flow->ct);
- }
- EXPORT_SYMBOL_GPL(flow_offload_teardown);
- struct flow_offload_tuple_rhash *
- flow_offload_lookup(struct nf_flowtable *flow_table,
- struct flow_offload_tuple *tuple)
- {
- struct flow_offload_tuple_rhash *tuplehash;
- struct flow_offload *flow;
- int dir;
- tuplehash = rhashtable_lookup(&flow_table->rhashtable, tuple,
- nf_flow_offload_rhash_params);
- if (!tuplehash)
- return NULL;
- dir = tuplehash->tuple.dir;
- flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
- if (test_bit(NF_FLOW_TEARDOWN, &flow->flags))
- return NULL;
- if (unlikely(nf_ct_is_dying(flow->ct)))
- return NULL;
- return tuplehash;
- }
- EXPORT_SYMBOL_GPL(flow_offload_lookup);
- static 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 = 0;
- rhashtable_walk_enter(&flow_table->rhashtable, &hti);
- rhashtable_walk_start(&hti);
- while ((tuplehash = rhashtable_walk_next(&hti))) {
- if (IS_ERR(tuplehash)) {
- if (PTR_ERR(tuplehash) != -EAGAIN) {
- err = PTR_ERR(tuplehash);
- break;
- }
- continue;
- }
- if (tuplehash->tuple.dir)
- continue;
- flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
- iter(flow, data);
- }
- rhashtable_walk_stop(&hti);
- rhashtable_walk_exit(&hti);
- return err;
- }
- static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
- {
- struct nf_flowtable *flow_table = data;
- if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct))
- set_bit(NF_FLOW_TEARDOWN, &flow->flags);
- if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
- if (test_bit(NF_FLOW_HW, &flow->flags)) {
- if (!test_bit(NF_FLOW_HW_DYING, &flow->flags))
- nf_flow_offload_del(flow_table, flow);
- else if (test_bit(NF_FLOW_HW_DEAD, &flow->flags))
- flow_offload_del(flow_table, flow);
- } else {
- flow_offload_del(flow_table, flow);
- }
- } else if (test_bit(NF_FLOW_HW, &flow->flags)) {
- nf_flow_offload_stats(flow_table, flow);
- }
- }
- static void nf_flow_offload_work_gc(struct work_struct *work)
- {
- struct nf_flowtable *flow_table;
- flow_table = container_of(work, struct nf_flowtable, gc_work.work);
- nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
- queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
- }
- static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
- __be16 port, __be16 new_port)
- {
- struct tcphdr *tcph;
- if (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, false);
- 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 (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, false);
- 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 (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 (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);
- int nf_flow_table_init(struct nf_flowtable *flowtable)
- {
- int err;
- INIT_DELAYED_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
- flow_block_init(&flowtable->flow_block);
- init_rwsem(&flowtable->flow_block_lock);
- err = rhashtable_init(&flowtable->rhashtable,
- &nf_flow_offload_rhash_params);
- if (err < 0)
- return err;
- queue_delayed_work(system_power_efficient_wq,
- &flowtable->gc_work, HZ);
- mutex_lock(&flowtable_lock);
- list_add(&flowtable->list, &flowtables);
- mutex_unlock(&flowtable_lock);
- return 0;
- }
- EXPORT_SYMBOL_GPL(nf_flow_table_init);
- static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
- {
- struct net_device *dev = data;
- if (!dev) {
- flow_offload_teardown(flow);
- return;
- }
- if (net_eq(nf_ct_net(flow->ct), dev_net(dev)) &&
- (flow->tuplehash[0].tuple.iifidx == dev->ifindex ||
- flow->tuplehash[1].tuple.iifidx == dev->ifindex))
- flow_offload_teardown(flow);
- }
- void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
- struct net_device *dev)
- {
- nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
- flush_delayed_work(&flowtable->gc_work);
- nf_flow_table_offload_flush(flowtable);
- }
- void nf_flow_table_cleanup(struct net_device *dev)
- {
- struct nf_flowtable *flowtable;
- mutex_lock(&flowtable_lock);
- list_for_each_entry(flowtable, &flowtables, list)
- nf_flow_table_gc_cleanup(flowtable, dev);
- mutex_unlock(&flowtable_lock);
- }
- EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
- void nf_flow_table_free(struct nf_flowtable *flow_table)
- {
- mutex_lock(&flowtable_lock);
- list_del(&flow_table->list);
- mutex_unlock(&flowtable_lock);
- cancel_delayed_work_sync(&flow_table->gc_work);
- nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
- nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
- nf_flow_table_offload_flush(flow_table);
- if (nf_flowtable_hw_offload(flow_table))
- nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step,
- flow_table);
- rhashtable_destroy(&flow_table->rhashtable);
- }
- EXPORT_SYMBOL_GPL(nf_flow_table_free);
- static int __init nf_flow_table_module_init(void)
- {
- return nf_flow_table_offload_init();
- }
- static void __exit nf_flow_table_module_exit(void)
- {
- nf_flow_table_offload_exit();
- }
- module_init(nf_flow_table_module_init);
- module_exit(nf_flow_table_module_exit);
- MODULE_LICENSE("GPL");
- MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
- MODULE_DESCRIPTION("Netfilter flow table module");
|