diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/Kconfig | 10 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 2 | ||||
-rw-r--r-- | net/ipv4/datagram.c | 2 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 4 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 2 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 10 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/nft_fib_ipv4.c | 1 | ||||
-rw-r--r-- | net/ipv4/nexthop.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_bpf.c | 12 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp_ulp.c | 3 | ||||
-rw-r--r-- | net/ipv4/udp.c | 3 | ||||
-rw-r--r-- | net/ipv4/udp_bpf.c | 4 |
16 files changed, 45 insertions, 21 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index e983bb0c5012..2dfb12230f08 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -402,6 +402,16 @@ config INET_IPCOMP If unsure, say Y. +config INET_TABLE_PERTURB_ORDER + int "INET: Source port perturbation table size (as power of 2)" if EXPERT + default 16 + help + Source port perturbation table size (as power of 2) for + RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm. + + The default is almost always what you want. + Only change this if you know what you are doing. + config INET_XFRM_TUNNEL tristate select INET_TUNNEL diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3dd02396517d..4728087c42a5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -754,6 +754,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags, (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_CLOSE_WAIT | TCPF_CLOSE))); + if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) + set_bit(SOCK_SUPPORT_ZC, &newsock->flags); sock_graft(sk2, newsock); newsock->state = SS_CONNECTED; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 0ee7fd259730..4d1af0cd7d99 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = get_random_u16(); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 943edf4ad4db..f361d3d56be2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { - ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) @@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) - ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e9a7f70a54df..f721c308248b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1231,7 +1231,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, nh->fib_nh_dev = in_dev->dev; netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); - nh->fib_nh_scope = RT_SCOPE_LINK; + nh->fib_nh_scope = RT_SCOPE_HOST; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index d3dc28156622..033bf3c2538f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -906,13 +906,13 @@ EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. + * * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though - * attacks were since demonstrated, thus we use 65536 instead to really - * give more isolation and privacy, at the expense of 256kB of kernel - * memory. + * attacks were since demonstrated, thus we use 65536 by default instead + * to really give more isolation and privacy, at the expense of 256kB + * of kernel memory. */ -#define INET_TABLE_PERTURB_SHIFT 16 -#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) +#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER) static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ff85db52b2e5..ded5bef02f77 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); + flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index e886147eed11..fc65d69f23e1 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), }; const struct net_device *oif; const struct net_device *found; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 853a75a8fbaf..d8ef05347fd9 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2534,7 +2534,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, - fib_nh->fib_nh_scope); + !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f8232811a5be..54836a6b81d6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk) WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); } EXPORT_SYMBOL(tcp_init_sock); @@ -3646,7 +3647,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; - else if (sk->sk_state == TCP_ESTABLISHED) + else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index a1626afe87a1..cf9c3e8f7ccb 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, { bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; - u32 tosend, delta = 0; + u32 tosend, origsize, sent, delta = 0; u32 eval = __SK_NONE; int ret; @@ -333,10 +333,12 @@ more_data: cork = true; psock->cork = NULL; } - sk_msg_return(sk, msg, msg->sg.size); + sk_msg_return(sk, msg, tosend); release_sock(sk); + origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) sock_put(sk_redir); @@ -375,7 +377,7 @@ more_data: msg->sg.data[msg->sg.start].page_link && msg->sg.data[msg->sg.start].length) { if (eval == __SK_REDIRECT) - sk_mem_charge(sk, msg->sg.size); + sk_mem_charge(sk, tosend - sent); goto more_data; } } @@ -607,7 +609,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) } else { sk->sk_write_space = psock->saved_write_space; /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); } return 0; } @@ -620,7 +622,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) } /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); + sock_replace_proto(sk, &tcp_bpf_prots[family][config]); return 0; } EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bc2ea12221f9..0640453fce54 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2192,7 +2192,8 @@ void tcp_enter_loss(struct sock *sk) */ static bool tcp_check_sack_reneging(struct sock *sk, int flag) { - if (flag & FLAG_SACK_RENEGING) { + if (flag & FLAG_SACK_RENEGING && + flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7a250ef9d1b7..87d440f47a70 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1874,11 +1874,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, __skb_push(skb, hdrlen); no_coalesce: + limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ - limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024; + limit += 64 * 1024; if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 7c27aa629af1..9ae50b1bd844 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -136,6 +136,9 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (icsk->icsk_ulp_ops) goto out_err; + if (sk->sk_socket) + clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + err = ulp_ops->init(sk); if (err) goto out_err; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 662d717d5123..6a320a614e54 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; @@ -1624,6 +1624,7 @@ int udp_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index ff15918b7bdc..e5dc91d0e079 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -141,14 +141,14 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } if (sk->sk_family == AF_INET6) udp_bpf_check_v6_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]); + sock_replace_proto(sk, &udp_bpf_prots[family]); return 0; } EXPORT_SYMBOL_GPL(udp_bpf_update_proto); |