diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 15 | ||||
-rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 17 | ||||
-rw-r--r-- | net/ipv4/esp4_offload.c | 3 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 8 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 6 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 7 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 84 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 5 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_CLUSTERIP.c | 4 | ||||
-rw-r--r-- | net/ipv4/ping.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 8 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 117 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 61 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 4 | ||||
-rw-r--r-- | net/ipv4/udp.c | 2 | ||||
-rw-r--r-- | net/ipv4/udp_tunnel_nic.c | 2 |
17 files changed, 234 insertions, 113 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 378bcd777514..ab4a06be489b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -522,9 +522,9 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { - if (sk->sk_prot->get_port(sk, snum)) { + err = sk->sk_prot->get_port(sk, snum); + if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; - err = -EADDRINUSE; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { @@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { - struct inet_bind_hashbucket *prev_addr_hashbucket; struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; @@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; } - prev_addr_hashbucket = - inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, - sock_net(sk), inet->inet_num); - - inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; - - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { - inet->inet_saddr = old_saddr; - inet->inet_rcv_saddr = old_saddr; ip_rt_put(rt); return err; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 6da16ae6a962..4517d2bd186a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -61,7 +61,9 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; - if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + if (base_type(info->reg_type) == PTR_TO_BTF_ID && + !bpf_type_has_unsafe_modifiers(info->reg_type) && + info->btf_id == sock_id) /* promote it to tcp_sock */ info->btf_id = tcp_sock_id; @@ -69,18 +71,17 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { + const struct btf_type *t; size_t end; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + t = btf_type_by_id(reg->btf, reg->btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); return -EACCES; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 170152772d33..3969fa805679 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f721c308248b..19a662003eef 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -888,9 +888,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, return 1; } - /* cannot match on nexthop object attributes */ - if (fi->nh) - return 1; + if (fi->nh) { + if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp) + return 1; + return 0; + } if (cfg->fc_oif || cfg->fc_gw_family) { struct fib_nh *nh; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 452ff177e4da..74d403dbd2b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -126,7 +126,7 @@ struct key_vector { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ - struct key_vector __rcu *tnode[0]; + DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4e84ed21d16f..4a34bc7cb15e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -471,11 +471,11 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; + int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; - int ret = 1, port = snum, l3mdev; struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); @@ -1186,7 +1186,7 @@ int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - int err = -EADDRINUSE; + int err; reqsk_queue_alloc(&icsk->icsk_accept_queue); @@ -1202,7 +1202,8 @@ int inet_csk_listen_start(struct sock *sk) * after validation is complete. */ inet_sk_state_store(sk, TCP_LISTEN); - if (!sk->sk_prot->get_port(sk, inet->inet_num)) { + err = sk->sk_prot->get_port(sk, inet->inet_num); + if (!err) { inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 033bf3c2538f..3cec471a2cd2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) +static void inet_update_saddr(struct sock *sk, void *saddr, int family) +{ + if (family == AF_INET) { + inet_sk(sk)->inet_saddr = *(__be32 *)saddr; + sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); + } +#if IS_ENABLED(CONFIG_IPV6) + else { + sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; + } +#endif +} + +static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); - struct inet_bind_hashbucket *head2; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); + int bhash; + + if (!inet_csk(sk)->icsk_bind2_hash) { + /* Not bind()ed before. */ + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + return 0; + } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); - if (!new_tb2) + if (!new_tb2) { + if (reset) { + /* The (INADDR_ANY, port) bucket might have already + * been freed, then we cannot fixup icsk_bind2_hash, + * so we give up and unlink sk from bhash/bhash2 not + * to leave inconsistency in bhash2. + */ + inet_put_port(sk); + inet_reset_saddr(sk); + } + return -ENOMEM; + } + bhash = inet_bhashfn(net, port, hinfo->bhash_size); + head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - if (prev_saddr) { - spin_lock_bh(&prev_saddr->lock); - __sk_del_bind2_node(sk); - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); - } + /* If we change saddr locklessly, another thread + * iterating over bhash might see corrupted address. + */ + spin_lock_bh(&head->lock); - spin_lock_bh(&head2->lock); + spin_lock(&head2->lock); + __sk_del_bind2_node(sk); + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); + spin_unlock(&head2->lock); + + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); + + spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; @@ -893,15 +939,29 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc } sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; - spin_unlock_bh(&head2->lock); + spin_unlock(&head2->lock); + + spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); return 0; } + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +{ + return __inet_bhash2_update_saddr(sk, saddr, family, false); +} EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +void inet_bhash2_reset_saddr(struct sock *sk) +{ + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + __inet_bhash2_update_saddr(sk, NULL, 0, true); +} +EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); + /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1b512390b3cf..e880ce77322a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, iph->tos, dev); if (unlikely(err)) goto drop_error; + } else { + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY)) + IPCB(skb)->flags |= IPSKB_NOPOLICY; } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index f8e176c77d1c..b3cc416ed292 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index bde333b24837..bb9854c2b7a1 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -138,7 +138,7 @@ next_port: fail: spin_unlock(&ping_table.lock); - return 1; + return -EADDRINUSE; } EXPORT_SYMBOL_GPL(ping_get_port); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4a69c5fcfedc..001947136b0a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); @@ -4465,11 +4464,8 @@ bool tcp_alloc_md5sig_pool(void) if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { mutex_lock(&tcp_md5sig_mutex); - if (!tcp_md5sig_pool_populated) { + if (!tcp_md5sig_pool_populated) __tcp_alloc_md5sig_pool(); - if (tcp_md5sig_pool_populated) - static_branch_inc(&tcp_md5_needed); - } mutex_unlock(&tcp_md5sig_mutex); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0ae291e53eab..1efacbe948da 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6845,7 +6845,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) xchg(&queue->synflood_warned, 1) == 0) { if (IS_ENABLED(CONFIG_IPV6) && sk->sk_family == AF_INET6) { net_info_ratelimited("%s: Possible SYN flooding on port [%pI6c]:%u. %s.\n", - proto, &sk->sk_v6_rcv_saddr, + proto, inet6_rcv_saddr(sk), sk->sk_num, msg); } else { net_info_ratelimited("%s: Possible SYN flooding on port %pI4:%u. %s.\n", diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f0343538d1f8..7fae586405cf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -343,6 +331,7 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; @@ -1064,7 +1053,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) * We need to maintain these in the sk structure. */ -DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); +DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); EXPORT_SYMBOL(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) @@ -1172,10 +1161,25 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, } EXPORT_SYMBOL(tcp_v4_md5_lookup); +static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_info *md5sig; + + md5sig = kmalloc(sizeof(*md5sig), gfp); + if (!md5sig) + return -ENOMEM; + + sk_gso_disable(sk); + INIT_HLIST_HEAD(&md5sig->head); + rcu_assign_pointer(tp->md5sig_info, md5sig); + return 0; +} + /* This can be called on a newly created socket, from other files */ -int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index, u8 flags, - const u8 *newkey, u8 newkeylen, gfp_t gfp) +static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; @@ -1204,15 +1208,6 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); - if (!md5sig) { - md5sig = kmalloc(sizeof(*md5sig), gfp); - if (!md5sig) - return -ENOMEM; - - sk_gso_disable(sk); - INIT_HLIST_HEAD(&md5sig->head); - rcu_assign_pointer(tp->md5sig_info, md5sig); - } key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) @@ -1234,8 +1229,59 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } + +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { + if (tcp_md5sig_info_add(sk, GFP_KERNEL)) + return -ENOMEM; + + if (!static_branch_inc(&tcp_md5_needed.key)) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); + rcu_assign_pointer(tp->md5sig_info, NULL); + kfree_rcu(md5sig); + return -EUSERS; + } + } + + return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, + newkey, newkeylen, GFP_KERNEL); +} EXPORT_SYMBOL(tcp_md5_do_add); +int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, + struct tcp_md5sig_key *key) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { + if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) + return -ENOMEM; + + if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); + net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); + rcu_assign_pointer(tp->md5sig_info, NULL); + kfree_rcu(md5sig); + return -EUSERS; + } + } + + return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, + key->flags, key->key, key->keylen, + sk_gfp_mask(sk, GFP_ATOMIC)); +} +EXPORT_SYMBOL(tcp_md5_key_copy); + int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { @@ -1322,7 +1368,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1573,14 +1619,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, addr = (union tcp_md5_addr *)&newinet->inet_daddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key) { - /* - * We're using one, so create a matching key - * on the newsk structure. If we fail to get - * memory, then we end up not copying the key - * across. Shucks. - */ - tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags, - key->key, key->keylen, GFP_ATOMIC); + if (tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key)) + goto put_and_exit; sk_gso_disable(newsk); } #endif @@ -2272,6 +2312,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_clear_md5_list(sk); kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); tp->md5sig_info = NULL; + static_branch_slow_dec_deferred(&tcp_md5_needed); } #endif diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index c375f603a16c..e002f2e1d4f2 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -240,6 +240,40 @@ kill: } EXPORT_SYMBOL(tcp_timewait_state_process); +static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) +{ +#ifdef CONFIG_TCP_MD5SIG + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + + /* + * The timewait bucket does not have the key DB from the + * sock structure. We just make a quick copy of the + * md5 key being used (if indeed we are using one) + * so the timewait ack generating code has the key. + */ + tcptw->tw_md5_key = NULL; + if (!static_branch_unlikely(&tcp_md5_needed.key)) + return; + + key = tp->af_specific->md5_lookup(sk, sk); + if (key) { + tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); + if (!tcptw->tw_md5_key) + return; + if (!tcp_alloc_md5sig_pool()) + goto out_free; + if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) + goto out_free; + } + return; +out_free: + WARN_ON_ONCE(1); + kfree(tcptw->tw_md5_key); + tcptw->tw_md5_key = NULL; +#endif +} + /* * Move a socket to time-wait or dead fin-wait-2 state. */ @@ -282,26 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } #endif -#ifdef CONFIG_TCP_MD5SIG - /* - * The timewait bucket does not have the key DB from the - * sock structure. We just make a quick copy of the - * md5 key being used (if indeed we are using one) - * so the timewait ack generating code has the key. - */ - do { - tcptw->tw_md5_key = NULL; - if (static_branch_unlikely(&tcp_md5_needed)) { - struct tcp_md5sig_key *key; - - key = tp->af_specific->md5_lookup(sk, sk); - if (key) { - tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); - BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); - } - } - } while (0); -#endif + tcp_time_wait_init(sk, tcptw); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -337,11 +352,13 @@ EXPORT_SYMBOL(tcp_time_wait); void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed)) { + if (static_branch_unlikely(&tcp_md5_needed.key)) { struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) + if (twsk->tw_md5_key) { kfree_rcu(twsk->tw_md5_key, rcu); + static_branch_slow_dec_deferred(&tcp_md5_needed); + } } #endif } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 894410dc9293..71d01cf3c13e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -766,7 +766,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { @@ -922,7 +922,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1fb7d1ed1cb1..9592fe3e444a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -240,7 +240,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; struct net *net = sock_net(sk); - int error = 1; + int error = -EADDRINUSE; if (!snum) { DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index bc3a043a5d5c..029219749785 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -624,6 +624,8 @@ __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); + if (!nest) + return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || |