diff options
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/af_inet.c | 2 | ||||
| -rw-r--r-- | net/ipv4/ah4.c | 1 | ||||
| -rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 22 | ||||
| -rw-r--r-- | net/ipv4/datagram.c | 2 | ||||
| -rw-r--r-- | net/ipv4/esp4.c | 1 | ||||
| -rw-r--r-- | net/ipv4/fib_trie.c | 2 | ||||
| -rw-r--r-- | net/ipv4/inet_connection_sock.c | 2 | ||||
| -rw-r--r-- | net/ipv4/inet_diag.c | 101 | ||||
| -rw-r--r-- | net/ipv4/inetpeer.c | 5 | ||||
| -rw-r--r-- | net/ipv4/ip_gre.c | 25 | ||||
| -rw-r--r-- | net/ipv4/ip_output.c | 15 | ||||
| -rw-r--r-- | net/ipv4/ip_tunnel.c | 39 | ||||
| -rw-r--r-- | net/ipv4/ip_vti.c | 9 | ||||
| -rw-r--r-- | net/ipv4/ipip.c | 9 | ||||
| -rw-r--r-- | net/ipv4/netfilter/Kconfig | 43 | ||||
| -rw-r--r-- | net/ipv4/netfilter/Makefile | 2 | ||||
| -rw-r--r-- | net/ipv4/nexthop.c | 38 | ||||
| -rw-r--r-- | net/ipv4/raw_diag.c | 1 | ||||
| -rw-r--r-- | net/ipv4/syncookies.c | 40 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 3 | ||||
| -rw-r--r-- | net/ipv4/tcp_diag.c | 1 | ||||
| -rw-r--r-- | net/ipv4/tcp_input.c | 23 | ||||
| -rw-r--r-- | net/ipv4/tunnel4.c | 1 | ||||
| -rw-r--r-- | net/ipv4/udp_diag.c | 2 | ||||
| -rw-r--r-- | net/ipv4/udp_tunnel_core.c | 1 | ||||
| -rw-r--r-- | net/ipv4/xfrm4_tunnel.c | 1 |
26 files changed, 237 insertions, 154 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a5a820ee2026..ad278009e469 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1326,7 +1326,7 @@ int inet_sk_rebuild_header(struct sock *sk) fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, - sk->sk_protocol, RT_CONN_FLAGS(sk), + sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a2e6e1fdf82b..64aec3dff8ec 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -597,5 +597,6 @@ static void __exit ah4_fini(void) module_init(ah4_init); module_exit(ah4_fini); +MODULE_DESCRIPTION("IPv4 AH transformation library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index ae8b15e6896f..834edc18463a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include <net/bpf_sk_storage.h> /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; @@ -191,7 +197,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -339,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { .release = __bpf_tcp_ca_release, }; -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -350,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 2cc50cbfc2a3..cc6d0bd7b0a9 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -119,7 +119,7 @@ void ip4_datagram_release_cb(struct sock *sk) rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + ip_sock_rt_tos(sk), sk->sk_bound_dev_if); dst = !IS_ERR(rt) ? &rt->dst : NULL; sk_dst_set(sk, dst); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4ccfc104f13a..4dd9e5040672 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void) module_init(esp4_init); module_exit(esp4_fini); +MODULE_DESCRIPTION("IPv4 ESP transformation library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3ff35f811765..0fc7ab5832d1 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -501,7 +501,7 @@ static void tnode_free(struct key_vector *tn) if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; - synchronize_rcu(); + synchronize_net(); } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 459af1f89739..747ed7344cbe 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1467,7 +1467,7 @@ static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *f rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) rt = NULL; if (rt) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8e6b6aa0579e..7adace541fe2 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -32,7 +32,7 @@ #include <linux/inet_diag.h> #include <linux/sock_diag.h> -static const struct inet_diag_handler **inet_diag_table; +static const struct inet_diag_handler __rcu **inet_diag_table; struct inet_diag_entry { const __be32 *saddr; @@ -48,28 +48,28 @@ struct inet_diag_entry { #endif }; -static DEFINE_MUTEX(inet_diag_table_mutex); - static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { - if (proto < 0 || proto >= IPPROTO_MAX) { - mutex_lock(&inet_diag_table_mutex); - return ERR_PTR(-ENOENT); - } + const struct inet_diag_handler *handler; - if (!inet_diag_table[proto]) + if (proto < 0 || proto >= IPPROTO_MAX) + return NULL; + + if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); - mutex_lock(&inet_diag_table_mutex); - if (!inet_diag_table[proto]) - return ERR_PTR(-ENOENT); + rcu_read_lock(); + handler = rcu_dereference(inet_diag_table[proto]); + if (handler && !try_module_get(handler->owner)) + handler = NULL; + rcu_read_unlock(); - return inet_diag_table[proto]; + return handler; } static void inet_diag_unlock_handler(const struct inet_diag_handler *handler) { - mutex_unlock(&inet_diag_table_mutex); + module_put(handler->owner); } void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) @@ -104,9 +104,12 @@ static size_t inet_sk_attr_size(struct sock *sk, const struct inet_diag_handler *handler; size_t aux = 0; - handler = inet_diag_table[req->sdiag_protocol]; + rcu_read_lock(); + handler = rcu_dereference(inet_diag_table[req->sdiag_protocol]); + DEBUG_NET_WARN_ON_ONCE(!handler); if (handler && handler->idiag_get_aux_size) aux = handler->idiag_get_aux_size(sk, net_admin); + rcu_read_unlock(); return nla_total_size(sizeof(struct tcp_info)) + nla_total_size(sizeof(struct inet_diag_msg)) @@ -244,10 +247,16 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; + int protocol; cb_data = cb->data; - handler = inet_diag_table[inet_diag_get_protocol(req, cb_data)]; - BUG_ON(!handler); + protocol = inet_diag_get_protocol(req, cb_data); + + /* inet_diag_lock_handler() made sure inet_diag_table[] is stable. */ + handler = rcu_dereference_protected(inet_diag_table[protocol], 1); + DEBUG_NET_WARN_ON_ONCE(!handler); + if (!handler) + return -ENXIO; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); @@ -605,9 +614,10 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, protocol = inet_diag_get_protocol(req, &dump_data); handler = inet_diag_lock_handler(protocol); - if (IS_ERR(handler)) { - err = PTR_ERR(handler); - } else if (cmd == SOCK_DIAG_BY_FAMILY) { + if (!handler) + return -ENOENT; + + if (cmd == SOCK_DIAG_BY_FAMILY) { struct netlink_callback cb = { .nlh = nlh, .skb = in_skb, @@ -1035,6 +1045,10 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, num = 0; ilb = &hashinfo->lhash2[i]; + if (hlist_nulls_empty(&ilb->nulls_head)) { + s_num = 0; + continue; + } spin_lock(&ilb->lock); sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); @@ -1099,6 +1113,10 @@ resume_bind_walk: accum = 0; ibb = &hashinfo->bhash2[i]; + if (hlist_empty(&ibb->chain)) { + s_num = 0; + continue; + } spin_lock_bh(&ibb->lock); inet_bind_bucket_for_each(tb2, &ibb->chain) { if (!net_eq(ib2_net(tb2), net)) @@ -1259,12 +1277,12 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, again: prev_min_dump_alloc = cb->min_dump_alloc; handler = inet_diag_lock_handler(protocol); - if (!IS_ERR(handler)) + if (handler) { handler->dump(skb, cb, r); - else - err = PTR_ERR(handler); - inet_diag_unlock_handler(handler); - + inet_diag_unlock_handler(handler); + } else { + err = -ENOENT; + } /* The skb is not large enough to fit one sk info and * inet_sk_diag_fill() has requested for a larger skb. */ @@ -1457,10 +1475,9 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } handler = inet_diag_lock_handler(sk->sk_protocol); - if (IS_ERR(handler)) { - inet_diag_unlock_handler(handler); + if (!handler) { nlmsg_cancel(skb, nlh); - return PTR_ERR(handler); + return -ENOENT; } attr = handler->idiag_info_size @@ -1479,6 +1496,7 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } static const struct sock_diag_handler inet_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1486,6 +1504,7 @@ static const struct sock_diag_handler inet_diag_handler = { }; static const struct sock_diag_handler inet6_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET6, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1495,20 +1514,12 @@ static const struct sock_diag_handler inet6_diag_handler = { int inet_diag_register(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; - int err = -EINVAL; if (type >= IPPROTO_MAX) - goto out; + return -EINVAL; - mutex_lock(&inet_diag_table_mutex); - err = -EEXIST; - if (!inet_diag_table[type]) { - inet_diag_table[type] = h; - err = 0; - } - mutex_unlock(&inet_diag_table_mutex); -out: - return err; + return !cmpxchg((const struct inet_diag_handler **)&inet_diag_table[type], + NULL, h) ? 0 : -EEXIST; } EXPORT_SYMBOL_GPL(inet_diag_register); @@ -1519,12 +1530,16 @@ void inet_diag_unregister(const struct inet_diag_handler *h) if (type >= IPPROTO_MAX) return; - mutex_lock(&inet_diag_table_mutex); - inet_diag_table[type] = NULL; - mutex_unlock(&inet_diag_table_mutex); + xchg((const struct inet_diag_handler **)&inet_diag_table[type], + NULL); } EXPORT_SYMBOL_GPL(inet_diag_unregister); +static const struct sock_diag_inet_compat inet_diag_compat = { + .owner = THIS_MODULE, + .fn = inet_diag_rcv_msg_compat, +}; + static int __init inet_diag_init(void) { const int inet_diag_table_size = (IPPROTO_MAX * @@ -1543,7 +1558,7 @@ static int __init inet_diag_init(void) if (err) goto out_free_inet; - sock_diag_register_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_register_inet_compat(&inet_diag_compat); out: return err; @@ -1558,7 +1573,7 @@ static void __exit inet_diag_exit(void) { sock_diag_unregister(&inet6_diag_handler); sock_diag_unregister(&inet_diag_handler); - sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_unregister_inet_compat(&inet_diag_compat); kfree(inet_diag_table); } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e9fed83e9b3c..5bd759963451 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -81,10 +81,7 @@ void __init inet_initpeers(void) inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128); - peer_cachep = kmem_cache_create("inet_peer_cache", - sizeof(struct inet_peer), - 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, - NULL); + peer_cachep = KMEM_CACHE(inet_peer, SLAB_HWCACHE_ALIGN | SLAB_PANIC); } /* Called with rcu_read_lock() or base->lock held */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5169c3c72cff..7b16c211b904 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1025,14 +1025,16 @@ static int __net_init ipgre_init_net(struct net *net) return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } -static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) +static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); + ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, + dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, - .exit_batch = ipgre_exit_batch_net, + .exit_batch_rtnl = ipgre_exit_batch_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1697,14 +1699,16 @@ static int __net_init ipgre_tap_init_net(struct net *net) return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } -static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) +static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); + ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, + dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, - .exit_batch = ipgre_tap_exit_batch_net, + .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1715,14 +1719,16 @@ static int __net_init erspan_init_net(struct net *net) &erspan_link_ops, "erspan0"); } -static void __net_exit erspan_exit_batch_net(struct list_head *net_list) +static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); + ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, + dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, - .exit_batch = erspan_exit_batch_net, + .exit_batch_rtnl = erspan_exit_batch_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1793,6 +1799,7 @@ static void __exit ipgre_fini(void) module_init(ipgre_init); module_exit(ipgre_fini); +MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 41537d18eecf..1fe794967211 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -493,7 +493,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS_TOS(sk, tos), + RT_TOS(tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; @@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); @@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); @@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk, cork->length += length; + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, @@ -1274,6 +1275,8 @@ error: cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index beeae624c412..756f8b923883 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -102,10 +102,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else - cand = t; + cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { @@ -117,9 +116,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -137,9 +136,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -150,9 +149,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, !(t->dev->flags & IFF_UP)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -221,7 +220,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - link == t->parms.link && + link == READ_ONCE(t->parms.link) && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; @@ -747,7 +746,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), - dev_net(dev), tunnel->parms.link, + dev_net(dev), READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) @@ -867,7 +866,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; - t->parms.link = p->link; + WRITE_ONCE(t->parms.link, p->link); t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) @@ -1057,9 +1056,9 @@ EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { - struct ip_tunnel *tunnel = netdev_priv(dev); + const struct ip_tunnel *tunnel = netdev_priv(dev); - return tunnel->parms.link; + return READ_ONCE(tunnel->parms.link); } EXPORT_SYMBOL(ip_tunnel_get_iflink); @@ -1130,19 +1129,17 @@ static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, } void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, - struct rtnl_link_ops *ops) + struct rtnl_link_ops *ops, + struct list_head *dev_to_kill) { struct ip_tunnel_net *itn; struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { itn = net_generic(net, id); - ip_tunnel_destroy(net, itn, &list, ops); + ip_tunnel_destroy(net, itn, dev_to_kill, ops); } - unregister_netdevice_many(&list); - rtnl_unlock(); } EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); @@ -1271,6 +1268,7 @@ int ip_tunnel_init(struct net_device *dev) if (tunnel->collect_md) netif_keep_dst(dev); + netdev_lockdep_set_classes(dev); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); @@ -1298,4 +1296,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) } EXPORT_SYMBOL_GPL(ip_tunnel_setup); +MODULE_DESCRIPTION("IPv4 tunnel implementation library"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9ab9b3ebe0cd..ee587adb169f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -510,14 +510,16 @@ static int __net_init vti_init_net(struct net *net) return 0; } -static void __net_exit vti_exit_batch_net(struct list_head *list_net) +static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops); + ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops, + dev_to_kill); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, - .exit_batch = vti_exit_batch_net, + .exit_batch_rtnl = vti_exit_batch_rtnl, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -721,6 +723,7 @@ static void __exit vti_fini(void) module_init(vti_init); module_exit(vti_fini); +MODULE_DESCRIPTION("Virtual (secure) IP tunneling library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti"); MODULE_ALIAS_NETDEV("ip_vti0"); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 27b8f83c6ea2..f2696eaadbe6 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -592,14 +592,16 @@ static int __net_init ipip_init_net(struct net *net) return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } -static void __net_exit ipip_exit_batch_net(struct list_head *list_net) +static void __net_exit ipip_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); + ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops, + dev_to_kill); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, - .exit_batch = ipip_exit_batch_net, + .exit_batch_rtnl = ipip_exit_batch_rtnl, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -658,6 +660,7 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); +MODULE_DESCRIPTION("IP/IP protocol decoder library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index f71a7e9a7de6..783523087281 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -10,6 +10,10 @@ config NF_DEFRAG_IPV4 tristate default n +# old sockopt interface and eval loop +config IP_NF_IPTABLES_LEGACY + tristate + config NF_SOCKET_IPV4 tristate "IPv4 socket lookup support" help @@ -152,7 +156,7 @@ config IP_NF_MATCH_ECN config IP_NF_MATCH_RPFILTER tristate '"rpfilter" reverse path filter match support' depends on NETFILTER_ADVANCED - depends on IP_NF_MANGLE || IP_NF_RAW + depends on IP_NF_MANGLE || IP_NF_RAW || NFT_COMPAT help This option allows you to match packets whose replies would go out via the interface the packet came in. @@ -173,6 +177,7 @@ config IP_NF_MATCH_TTL config IP_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n + select IP_NF_IPTABLES_LEGACY help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -182,7 +187,7 @@ config IP_NF_FILTER config IP_NF_TARGET_REJECT tristate "REJECT target support" - depends on IP_NF_FILTER + depends on IP_NF_FILTER || NFT_COMPAT select NF_REJECT_IPV4 default m if NETFILTER_ADVANCED=n help @@ -212,6 +217,7 @@ config IP_NF_NAT default m if NETFILTER_ADVANCED=n select NF_NAT select NETFILTER_XT_NAT + select IP6_NF_IPTABLES_LEGACY help This enables the `nat' table in iptables. This allows masquerading, port forwarding and other forms of full Network Address Port @@ -252,6 +258,7 @@ endif # IP_NF_NAT config IP_NF_MANGLE tristate "Packet mangling" default m if NETFILTER_ADVANCED=n + select IP_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -261,7 +268,7 @@ config IP_NF_MANGLE config IP_NF_TARGET_ECN tristate "ECN target support" - depends on IP_NF_MANGLE + depends on IP_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds a `ECN' target, which can be used in the iptables mangle @@ -286,6 +293,7 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' + select IP_NF_IPTABLES_LEGACY help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -299,6 +307,7 @@ config IP_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED + select IP_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -309,36 +318,34 @@ endif # IP_NF_IPTABLES # ARP tables config IP_NF_ARPTABLES - tristate "ARP tables support" - select NETFILTER_XTABLES - select NETFILTER_FAMILY_ARP - depends on NETFILTER_ADVANCED - help - arptables is a general, extensible packet identification framework. - The ARP packet filtering and mangling (manipulation)subsystems - use this: say Y or M here if you want to use either of those. - - To compile it as a module, choose M here. If unsure, say N. + tristate -if IP_NF_ARPTABLES +config NFT_COMPAT_ARP + tristate + depends on NF_TABLES_ARP && NFT_COMPAT + default m if NFT_COMPAT=m + default y if NFT_COMPAT=y config IP_NF_ARPFILTER - tristate "ARP packet filtering" + tristate "arptables-legacy packet filtering support" + select IP_NF_ARPTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and - local output. On a bridge, you can also specify filtering rules - for forwarded ARP packets. See the man page for arptables(8). + local output. This is only needed for arptables-legacy(8). + Neither arptables-nft nor nftables need this to work. To compile it as a module, choose M here. If unsure, say N. config IP_NF_ARP_MANGLE tristate "ARP payload mangling" + depends on IP_NF_ARPTABLES || NFT_COMPAT_ARP help Allows altering the ARP packet payload: source and destination hardware and network addresses. -endif # IP_NF_ARPTABLES + This option is needed by both arptables-legacy and arptables-nft. + It is not used by nftables. endmenu diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 5a26f9de1ab9..85502d4dfbb4 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # generic IP tables -obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o +obj-$(CONFIG_IP_NF_IPTABLES_LEGACY) += ip_tables.o # the three instances of ip_tables obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index bbff68b5b5d4..70509da4f080 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3631,17 +3631,24 @@ unlock: } EXPORT_SYMBOL(register_nexthop_notifier); -int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; - rtnl_lock(); err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); - if (err) - goto unlock; - nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); -unlock: + if (!err) + nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); + return err; +} +EXPORT_SYMBOL(__unregister_nexthop_notifier); + +int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = __unregister_nexthop_notifier(net, nb); rtnl_unlock(); return err; } @@ -3737,16 +3744,20 @@ out: } EXPORT_SYMBOL(nexthop_res_grp_activity_update); -static void __net_exit nexthop_net_exit_batch(struct list_head *net_list) +static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { + ASSERT_RTNL(); + list_for_each_entry(net, net_list, exit_list) flush_all_nexthops(net); - kfree(net->nexthop.devhash); - } - rtnl_unlock(); +} + +static void __net_exit nexthop_net_exit(struct net *net) +{ + kfree(net->nexthop.devhash); + net->nexthop.devhash = NULL; } static int __net_init nexthop_net_init(struct net *net) @@ -3764,7 +3775,8 @@ static int __net_init nexthop_net_init(struct net *net) static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, - .exit_batch = nexthop_net_exit_batch, + .exit = nexthop_net_exit, + .exit_batch_rtnl = nexthop_net_exit_batch_rtnl, }; static int __init nexthop_init(void) diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index fe2140c8375c..cc793bd8de25 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -213,6 +213,7 @@ static int raw_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler raw_diag_handler = { + .owner = THIS_MODULE, .dump = raw_diag_dump, .dump_one = raw_diag_dump_one, .idiag_get_info = raw_diag_get_info, diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 61f1c96cfe63..be88bf586ff9 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -51,15 +51,6 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, count, &syncookie_secret[c]); } -/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ -static u64 tcp_ns_to_ts(bool usec_ts, u64 val) -{ - if (usec_ts) - return div_u64(val, NSEC_PER_USEC); - - return div_u64(val, NSEC_PER_MSEC); -} - /* * when syncookies are in effect and tcp timestamps are enabled we encode * tcp options in the lower bits of the timestamp value that will be @@ -304,6 +295,24 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, return 0; } +#if IS_ENABLED(CONFIG_BPF) +struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb) +{ + struct request_sock *req = inet_reqsk(skb->sk); + + skb->sk = NULL; + skb->destructor = NULL; + + if (cookie_tcp_reqsk_init(sk, skb, req)) { + reqsk_free(req); + req = NULL; + } + + return req; +} +EXPORT_SYMBOL_GPL(cookie_bpf_check); +#endif + struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, @@ -404,9 +413,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) !th->ack || th->rst) goto out; - req = cookie_tcp_check(net, sk, skb); - if (IS_ERR(req)) - goto out; + if (cookie_bpf_ok(skb)) { + req = cookie_bpf_check(sk, skb); + } else { + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + } if (!req) goto out_drop; @@ -454,7 +467,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); - ireq->rcv_wscale = rcv_wscale; + if (!req->syncookie) + ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7e2481b9eae1..c82dc42f57c6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4615,7 +4615,8 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4cbe4b44425a..f428ecf9120f 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -222,6 +222,7 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler tcp_diag_handler = { + .owner = THIS_MODULE, .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index df7b13f0e5e0..b1c4462a0798 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6623,7 +6623,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) const struct tcphdr *th = tcp_hdr(skb); struct request_sock *req; int queued = 0; - bool acceptable; SKB_DR(reason); switch (sk->sk_state) { @@ -6649,12 +6648,10 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) */ rcu_read_lock(); local_bh_disable(); - acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; + icsk->icsk_af_ops->conn_request(sk, skb); local_bh_enable(); rcu_read_unlock(); - if (!acceptable) - return 1; consume_skb(skb); return 0; } @@ -6699,17 +6696,21 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; /* step 5: check the ACK field */ - acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | - FLAG_UPDATE_TS_RECENT | - FLAG_NO_CHALLENGE_ACK) > 0; + reason = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT | + FLAG_NO_CHALLENGE_ACK); - if (!acceptable) { + if ((int)reason <= 0) { if (sk->sk_state == TCP_SYN_RECV) return 1; /* send one RST */ - tcp_send_challenge_ack(sk); - SKB_DR_SET(reason, TCP_OLD_ACK); - goto discard; + /* accept old ack during closing */ + if ((int)reason < 0) { + tcp_send_challenge_ack(sk); + reason = -reason; + goto discard; + } } + SKB_DR_SET(reason, NOT_SPECIFIED); switch (sk->sk_state) { case TCP_SYN_RECV: tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */ diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 5048c47c79b2..4c1f836aae38 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void) module_init(tunnel4_init); module_exit(tunnel4_fini); +MODULE_DESCRIPTION("IPv4 XFRM tunnel library"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index dc41a22ee80e..38cb3a28e4ed 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -237,6 +237,7 @@ static int udplite_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler udp_diag_handler = { + .owner = THIS_MODULE, .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, @@ -260,6 +261,7 @@ static int udplite_diag_dump_one(struct netlink_callback *cb, } static const struct inet_diag_handler udplite_diag_handler = { + .owner = THIS_MODULE, .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, .idiag_get_info = udp_diag_get_info, diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index a87defb2b167..860aff5f8599 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup); +MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 8489fa106583..8cb266af1393 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -114,5 +114,6 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); +MODULE_DESCRIPTION("IPv4 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP); |
