diff options
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/netfilter/Kconfig | 102 | ||||
| -rw-r--r-- | net/ipv4/netfilter/Makefile | 2 | ||||
| -rw-r--r-- | net/ipv4/route.c | 2 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 14 | ||||
| -rw-r--r-- | net/ipv4/tcp_input.c | 27 | ||||
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 5 | ||||
| -rw-r--r-- | net/ipv4/tcp_metrics.c | 6 | ||||
| -rw-r--r-- | net/ipv4/tcp_output.c | 24 |
8 files changed, 106 insertions, 76 deletions
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index fb173126f03d..7cbcaf4f0194 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -82,6 +82,52 @@ config NF_TABLES_ARP help This option enables the ARP support for nf_tables. +config NF_NAT_IPV4 + tristate "IPv4 NAT" + depends on NF_CONNTRACK_IPV4 + default m if NETFILTER_ADVANCED=n + select NF_NAT + help + The IPv4 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. This can be + controlled by iptables or nft. + +if NF_NAT_IPV4 + +config NF_NAT_SNMP_BASIC + tristate "Basic SNMP-ALG support" + depends on NF_CONNTRACK_SNMP + depends on NETFILTER_ADVANCED + default NF_NAT && NF_CONNTRACK_SNMP + ---help--- + + This module implements an Application Layer Gateway (ALG) for + SNMP payloads. In conjunction with NAT, it allows a network + management system to access multiple private networks with + conflicting addresses. It works by modifying IP addresses + inside SNMP payloads to match IP-layer NAT mapping. + + This is the "basic" form of SNMP-ALG, as described in RFC 2962 + + To compile it as a module, choose M here. If unsure, say N. + +config NF_NAT_PROTO_GRE + tristate + depends on NF_CT_PROTO_GRE + +config NF_NAT_PPTP + tristate + depends on NF_CONNTRACK + default NF_CONNTRACK_PPTP + select NF_NAT_PROTO_GRE + +config NF_NAT_H323 + tristate + depends on NF_CONNTRACK + default NF_CONNTRACK_H323 + +endif # NF_NAT_IPV4 + config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" default m if NETFILTER_ADVANCED=n @@ -170,19 +216,21 @@ config IP_NF_TARGET_SYNPROXY To compile it as a module, choose M here. If unsure, say N. # NAT + specific targets: nf_conntrack -config NF_NAT_IPV4 - tristate "IPv4 NAT" +config IP_NF_NAT + tristate "iptables NAT support" depends on NF_CONNTRACK_IPV4 default m if NETFILTER_ADVANCED=n select NF_NAT + select NF_NAT_IPV4 + select NETFILTER_XT_NAT help - The IPv4 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. It is controlled by - the `nat' table in iptables: see the man page for iptables(8). + This enables the `nat' table in iptables. This allows masquerading, + port forwarding and other forms of full Network Address Port + Translation. To compile it as a module, choose M here. If unsure, say N. -if NF_NAT_IPV4 +if IP_NF_NAT config IP_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" @@ -214,47 +262,7 @@ config IP_NF_TARGET_REDIRECT (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_REDIRECT. -endif - -config NF_NAT_SNMP_BASIC - tristate "Basic SNMP-ALG support" - depends on NF_CONNTRACK_SNMP && NF_NAT_IPV4 - depends on NETFILTER_ADVANCED - default NF_NAT && NF_CONNTRACK_SNMP - ---help--- - - This module implements an Application Layer Gateway (ALG) for - SNMP payloads. In conjunction with NAT, it allows a network - management system to access multiple private networks with - conflicting addresses. It works by modifying IP addresses - inside SNMP payloads to match IP-layer NAT mapping. - - This is the "basic" form of SNMP-ALG, as described in RFC 2962 - - To compile it as a module, choose M here. If unsure, say N. - -# If they want FTP, set to $CONFIG_IP_NF_NAT (m or y), -# or $CONFIG_IP_NF_FTP (m or y), whichever is weaker. -# From kconfig-language.txt: -# -# <expr> '&&' <expr> (6) -# -# (6) Returns the result of min(/expr/, /expr/). - -config NF_NAT_PROTO_GRE - tristate - depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE - -config NF_NAT_PPTP - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_PPTP - select NF_NAT_PROTO_GRE - -config NF_NAT_H323 - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_H323 +endif # IP_NF_NAT # mangle + specific targets config IP_NF_MANGLE diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 33001621465b..edf4af32e9f2 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o # the three instances of ip_tables obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o -obj-$(CONFIG_NF_NAT_IPV4) += iptable_nat.o +obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 190199851c9a..eaa4b000c7b4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1798,8 +1798,6 @@ local_input: no_route: RT_CACHE_STAT_INC(in_no_route); res.type = RTN_UNREACHABLE; - if (err == -ESRCH) - err = -ENETUNREACH; goto local_input; /* diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 181b70ebd964..541f26a67ba2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1188,13 +1188,6 @@ new_segment: goto wait_for_memory; /* - * All packets are restored as if they have - * already been sent. - */ - if (tp->repair) - TCP_SKB_CB(skb)->when = tcp_time_stamp; - - /* * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) @@ -1203,6 +1196,13 @@ new_segment: skb_entail(sk, skb); copy = size_goal; max = size_goal; + + /* All packets are restored as if they have + * already been sent. skb_mstamp isn't set to + * avoid wrong rtt estimation. + */ + if (tp->repair) + TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a3d47af01906..a906e0200ff2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2687,7 +2687,6 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) */ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) { - struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); @@ -2713,12 +2712,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) if (recovered) { /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ - icsk->icsk_retransmits = 0; tcp_try_undo_recovery(sk); return; } - if (flag & FLAG_DATA_ACKED) - icsk->icsk_retransmits = 0; if (tcp_is_reno(tp)) { /* A Reno DUPACK means new data in F-RTO step 2.b above are * delivered. Lower inflight to clock out (re)tranmissions. @@ -3050,10 +3046,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, first_ackt.v64 = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); u8 sacked = scb->sacked; u32 acked_pcount; + if (unlikely(shinfo->tx_flags & SKBTX_ACK_TSTAMP) && + between(shinfo->tskey, prior_snd_una, tp->snd_una - 1)) + __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { if (tcp_skb_pcount(skb) == 1 || @@ -3107,11 +3108,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->retrans_stamp = 0; } - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_ACK_TSTAMP) && - between(skb_shinfo(skb)->tskey, prior_snd_una, - tp->snd_una + 1)) - __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); - if (!fully_acked) break; @@ -3405,8 +3401,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) + if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; + icsk->icsk_retransmits = 0; + } prior_fackets = tp->fackets_out; @@ -5979,12 +5977,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, * timewait bucket, so that all the necessary checks * are made in the function processing timewait state. */ - if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle) { + if (tcp_death_row.sysctl_tw_recycle) { bool strict; dst = af_ops->route_req(sk, &fl, req, &strict); + if (dst && strict && - !tcp_peer_is_proven(req, dst, true)) { + !tcp_peer_is_proven(req, dst, true, + tmp_opt.saw_tstamp)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); goto drop_and_release; } @@ -5993,7 +5993,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, else if (!sysctl_tcp_syncookies && (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < (sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false)) { + !tcp_peer_is_proven(req, dst, false, + tmp_opt.saw_tstamp)) { /* Without syncookies last quarter of * backlog is filled with destinations, * proven to be alive. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index dceff5fe8e66..cd17f009aede 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -271,7 +271,7 @@ EXPORT_SYMBOL(tcp_v4_connect); * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ -static void tcp_v4_mtu_reduced(struct sock *sk) +void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -302,6 +302,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } +EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -1787,6 +1788,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); @@ -2406,7 +2408,6 @@ struct proto tcp_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 0d54e59b9ea8..ed9c9a91851c 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -576,7 +576,8 @@ reset: tp->snd_cwnd_stamp = tcp_time_stamp; } -bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check) +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, + bool paws_check, bool timestamps) { struct tcp_metrics_block *tm; bool ret; @@ -589,7 +590,8 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool pa if (paws_check) { if (tm && (u32)get_seconds() - tm->tcpm_ts_stamp < TCP_PAWS_MSL && - (s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW) + ((s32)(tm->tcpm_ts - req->ts_recent) > TCP_PAWS_WINDOW || + !timestamps)) ret = false; else ret = true; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8fcfc91964ec..5a7c41fbc6d3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -800,7 +800,7 @@ void tcp_release_cb(struct sock *sk) __sock_put(sk); } if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { - sk->sk_prot->mtu_reduced(sk); + inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } @@ -1069,6 +1069,21 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de tcp_verify_left_out(tp); } +static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (unlikely(shinfo->tx_flags & SKBTX_ANY_TSTAMP) && + !before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) { + struct skb_shared_info *shinfo2 = skb_shinfo(skb2); + u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP; + + shinfo->tx_flags &= ~tsflags; + shinfo2->tx_flags |= tsflags; + swap(shinfo->tskey, shinfo2->tskey); + } +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. @@ -1136,6 +1151,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, */ TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when; buff->tstamp = skb->tstamp; + tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); @@ -1652,6 +1668,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); + tcp_fragment_tstamp(skb, buff); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(sk, skb, mss_now); @@ -1917,8 +1934,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); - if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { + /* "when" is used as a start point for the retransmit timer */ + TCP_SKB_CB(skb)->when = tcp_time_stamp; goto repair; /* Skip network transmission */ + } cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { |