From 544d5c7d9f4d1ec4f170bc5bcc522012cb7704bc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso <pablo@netfilter.org> Date: Sun, 5 Feb 2012 03:44:51 +0100 Subject: netfilter: ctnetlink: allow to set expectfn for expectations This patch allows you to set expectfn which is specifically used by the NAT side of most of the existing conntrack helpers. I have added a symbol map that uses a string as key to look up for the function that is attached to the expectation object. This is the best solution I came out with to solve this issue. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> --- net/ipv4/netfilter/nf_nat_core.c | 8 ++++++++ net/ipv4/netfilter/nf_nat_h323.c | 14 ++++++++++++++ net/ipv4/netfilter/nf_nat_sip.c | 7 +++++++ 3 files changed, 29 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index a708933dc230..abb52adf5acd 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -686,6 +686,11 @@ static struct pernet_operations nf_nat_net_ops = { .exit = nf_nat_net_exit, }; +static struct nf_ct_helper_expectfn follow_master_nat = { + .name = "nat-follow-master", + .expectfn = nf_nat_follow_master, +}; + static int __init nf_nat_init(void) { size_t i; @@ -717,6 +722,8 @@ static int __init nf_nat_init(void) l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); + nf_ct_helper_expectfn_register(&follow_master_nat); + BUG_ON(nf_nat_seq_adjust_hook != NULL); RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); @@ -736,6 +743,7 @@ static void __exit nf_nat_cleanup(void) unregister_pernet_subsys(&nf_nat_net_ops); nf_ct_l3proto_put(l3proto); nf_ct_extend_unregister(&nat_extend); + nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); RCU_INIT_POINTER(nf_ct_nat_offset, NULL); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index dc1dd912baf4..82536701e3a3 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -568,6 +568,16 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, return 0; } +static struct nf_ct_helper_expectfn q931_nat = { + .name = "Q.931", + .expectfn = ip_nat_q931_expect, +}; + +static struct nf_ct_helper_expectfn callforwarding_nat = { + .name = "callforwarding", + .expectfn = ip_nat_callforwarding_expect, +}; + /****************************************************************************/ static int __init init(void) { @@ -590,6 +600,8 @@ static int __init init(void) RCU_INIT_POINTER(nat_h245_hook, nat_h245); RCU_INIT_POINTER(nat_callforwarding_hook, nat_callforwarding); RCU_INIT_POINTER(nat_q931_hook, nat_q931); + nf_ct_helper_expectfn_register(&q931_nat); + nf_ct_helper_expectfn_register(&callforwarding_nat); return 0; } @@ -605,6 +617,8 @@ static void __exit fini(void) RCU_INIT_POINTER(nat_h245_hook, NULL); RCU_INIT_POINTER(nat_callforwarding_hook, NULL); RCU_INIT_POINTER(nat_q931_hook, NULL); + nf_ct_helper_expectfn_unregister(&q931_nat); + nf_ct_helper_expectfn_unregister(&callforwarding_nat); synchronize_rcu(); } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index d0319f96269f..57932c43960e 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -526,6 +526,11 @@ err1: return NF_DROP; } +static struct nf_ct_helper_expectfn sip_nat = { + .name = "sip", + .expectfn = ip_nat_sip_expected, +}; + static void __exit nf_nat_sip_fini(void) { RCU_INIT_POINTER(nf_nat_sip_hook, NULL); @@ -535,6 +540,7 @@ static void __exit nf_nat_sip_fini(void) RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); + nf_ct_helper_expectfn_unregister(&sip_nat); synchronize_rcu(); } @@ -554,6 +560,7 @@ static int __init nf_nat_sip_init(void) RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port); RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session); RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media); + nf_ct_helper_expectfn_register(&sip_nat); return 0; } -- cgit From 6939c33a757bd006c5e0b8b5fd429fc587a4d0f4 Mon Sep 17 00:00:00 2001 From: Richard Weinberger <richard@nod.at> Date: Fri, 10 Feb 2012 23:10:52 +0100 Subject: netfilter: merge ipt_LOG and ip6_LOG into xt_LOG ipt_LOG and ip6_LOG have a lot of common code, merge them to reduce duplicate code. Signed-off-by: Richard Weinberger <richard@nod.at> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_LOG.h | 19 + include/linux/netfilter_ipv4/ipt_LOG.h | 2 + include/linux/netfilter_ipv6/ip6t_LOG.h | 2 + net/ipv4/netfilter/Kconfig | 9 - net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/ipt_LOG.c | 516 ------------------ net/ipv6/netfilter/Kconfig | 9 - net/ipv6/netfilter/Makefile | 1 - net/ipv6/netfilter/ip6t_LOG.c | 527 ------------------ net/netfilter/Kconfig | 9 + net/netfilter/Makefile | 1 + net/netfilter/xt_LOG.c | 921 ++++++++++++++++++++++++++++++++ 13 files changed, 955 insertions(+), 1063 deletions(-) create mode 100644 include/linux/netfilter/xt_LOG.h delete mode 100644 net/ipv4/netfilter/ipt_LOG.c delete mode 100644 net/ipv6/netfilter/ip6t_LOG.c create mode 100644 net/netfilter/xt_LOG.c (limited to 'net/ipv4') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index e144f54185c0..aaa72aaa21de 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -22,6 +22,7 @@ header-y += xt_CT.h header-y += xt_DSCP.h header-y += xt_IDLETIMER.h header-y += xt_LED.h +header-y += xt_LOG.h header-y += xt_MARK.h header-y += xt_nfacct.h header-y += xt_NFLOG.h diff --git a/include/linux/netfilter/xt_LOG.h b/include/linux/netfilter/xt_LOG.h new file mode 100644 index 000000000000..cac079095305 --- /dev/null +++ b/include/linux/netfilter/xt_LOG.h @@ -0,0 +1,19 @@ +#ifndef _XT_LOG_H +#define _XT_LOG_H + +/* make sure not to change this without changing nf_log.h:NF_LOG_* (!) */ +#define XT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ +#define XT_LOG_TCPOPT 0x02 /* Log TCP options */ +#define XT_LOG_IPOPT 0x04 /* Log IP options */ +#define XT_LOG_UID 0x08 /* Log UID owning local socket */ +#define XT_LOG_NFLOG 0x10 /* Unsupported, don't reuse */ +#define XT_LOG_MACDECODE 0x20 /* Decode MAC header */ +#define XT_LOG_MASK 0x2f + +struct xt_log_info { + unsigned char level; + unsigned char logflags; + char prefix[30]; +}; + +#endif /* _XT_LOG_H */ diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index dcdbadf9fd4a..5d8152077d71 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -1,6 +1,8 @@ #ifndef _IPT_LOG_H #define _IPT_LOG_H +#warning "Please update iptables, this file will be removed soon!" + /* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IPT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 9dd5579e02ec..3dd0bc4e0735 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -1,6 +1,8 @@ #ifndef _IP6T_LOG_H #define _IP6T_LOG_H +#warning "Please update iptables, this file will be removed soon!" + /* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IP6T_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 74dfc9e5211f..fcc543cd987a 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -123,15 +123,6 @@ config IP_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_LOG - tristate "LOG target support" - default m if NETFILTER_ADVANCED=n - help - This option adds a `LOG' target, which allows you to create rules in - any iptables table which records the packet header to the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_ULOG tristate "ULOG target support" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 213a462b739b..240b68469a7a 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -54,7 +54,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o # targets obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o -obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c deleted file mode 100644 index d76d6c9ed946..000000000000 --- a/net/ipv4/netfilter/ipt_LOG.c +++ /dev/null @@ -1,516 +0,0 @@ -/* - * This is a module which is used for logging packets. - */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/ip.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/route.h> - -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv4/ipt_LOG.h> -#include <net/netfilter/nf_log.h> -#include <net/netfilter/xt_log.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("Xtables: IPv4 packet logging to syslog"); - -/* One level of recursion won't kill us */ -static void dump_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, - unsigned int iphoff) -{ - struct iphdr _iph; - const struct iphdr *ih; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Important fields: - * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ - /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ - sb_add(m, "SRC=%pI4 DST=%pI4 ", - &ih->saddr, &ih->daddr); - - /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ - sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, - ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); - - /* Max length: 6 "CE DF MF " */ - if (ntohs(ih->frag_off) & IP_CE) - sb_add(m, "CE "); - if (ntohs(ih->frag_off) & IP_DF) - sb_add(m, "DF "); - if (ntohs(ih->frag_off) & IP_MF) - sb_add(m, "MF "); - - /* Max length: 11 "FRAG:65535 " */ - if (ntohs(ih->frag_off) & IP_OFFSET) - sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - - if ((logflags & IPT_LOG_IPOPT) && - ih->ihl * 4 > sizeof(struct iphdr)) { - const unsigned char *op; - unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; - unsigned int i, optsize; - - optsize = ih->ihl * 4 - sizeof(struct iphdr); - op = skb_header_pointer(skb, iphoff+sizeof(_iph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - - switch (ih->protocol) { - case IPPROTO_TCP: { - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - sb_add(m, "PROTO=TCP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_tcph), &_tcph); - if (th == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & IPT_LOG_TCPSEQ) - sb_add(m, "SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - /* Max length: 13 "WINDOW=65535 " */ - sb_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3F " */ - sb_add(m, "RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - sb_add(m, "CWR "); - if (th->ece) - sb_add(m, "ECE "); - if (th->urg) - sb_add(m, "URG "); - if (th->ack) - sb_add(m, "ACK "); - if (th->psh) - sb_add(m, "PSH "); - if (th->rst) - sb_add(m, "RST "); - if (th->syn) - sb_add(m, "SYN "); - if (th->fin) - sb_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & IPT_LOG_TCPOPT) && - th->doff * 4 > sizeof(struct tcphdr)) { - unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; - const unsigned char *op; - unsigned int i, optsize; - - optsize = th->doff * 4 - sizeof(struct tcphdr); - op = skb_header_pointer(skb, - iphoff+ih->ihl*4+sizeof(_tcph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - break; - } - case IPPROTO_UDP: - case IPPROTO_UDPLITE: { - struct udphdr _udph; - const struct udphdr *uh; - - if (ih->protocol == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - sb_add(m, "PROTO=UDP " ); - else /* Max length: 14 "PROTO=UDPLITE " */ - sb_add(m, "PROTO=UDPLITE "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_udph), &_udph); - if (uh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - break; - } - case IPPROTO_ICMP: { - struct icmphdr _icmph; - const struct icmphdr *ich; - static const size_t required_len[NR_ICMP_TYPES+1] - = { [ICMP_ECHOREPLY] = 4, - [ICMP_DEST_UNREACH] - = 8 + sizeof(struct iphdr), - [ICMP_SOURCE_QUENCH] - = 8 + sizeof(struct iphdr), - [ICMP_REDIRECT] - = 8 + sizeof(struct iphdr), - [ICMP_ECHO] = 4, - [ICMP_TIME_EXCEEDED] - = 8 + sizeof(struct iphdr), - [ICMP_PARAMETERPROB] - = 8 + sizeof(struct iphdr), - [ICMP_TIMESTAMP] = 20, - [ICMP_TIMESTAMPREPLY] = 20, - [ICMP_ADDRESS] = 12, - [ICMP_ADDRESSREPLY] = 12 }; - - /* Max length: 11 "PROTO=ICMP " */ - sb_add(m, "PROTO=ICMP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_icmph), &_icmph); - if (ich == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES && - required_len[ich->type] && - skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - switch (ich->type) { - case ICMP_ECHOREPLY: - case ICMP_ECHO: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ich->un.echo.id), - ntohs(ich->un.echo.sequence)); - break; - - case ICMP_PARAMETERPROB: - /* Max length: 14 "PARAMETER=255 " */ - sb_add(m, "PARAMETER=%u ", - ntohl(ich->un.gateway) >> 24); - break; - case ICMP_REDIRECT: - /* Max length: 24 "GATEWAY=255.255.255.255 " */ - sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); - /* Fall through */ - case ICMP_DEST_UNREACH: - case ICMP_SOURCE_QUENCH: - case ICMP_TIME_EXCEEDED: - /* Max length: 3+maxlen */ - if (!iphoff) { /* Only recurse once. */ - sb_add(m, "["); - dump_packet(m, info, skb, - iphoff + ih->ihl*4+sizeof(_icmph)); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH && - ich->code == ICMP_FRAG_NEEDED) - sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); - } - break; - } - /* Max Length */ - case IPPROTO_AH: { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 9 "PROTO=AH " */ - sb_add(m, "PROTO=AH "); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ah = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_ahdr), &_ahdr); - if (ah == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - break; - } - case IPPROTO_ESP: { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 10 "PROTO=ESP " */ - sb_add(m, "PROTO=ESP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - eh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_esph), &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); - break; - } - /* Max length: 10 "PROTO 255 " */ - default: - sb_add(m, "PROTO=%u ", ih->protocol); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) { - read_lock_bh(&skb->sk->sk_callback_lock); - if (skb->sk->sk_socket && skb->sk->sk_socket->file) - sb_add(m, "UID=%u GID=%u ", - skb->sk->sk_socket->file->f_cred->fsuid, - skb->sk->sk_socket->file->f_cred->fsgid); - read_unlock_bh(&skb->sk->sk_callback_lock); - } - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (!iphoff && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); - - /* Proto Max log string length */ - /* IP: 40+46+6+11+127 = 230 */ - /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ - /* UDP: 10+max(25,20) = 35 */ - /* UDPLITE: 14+max(25,20) = 39 */ - /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ - /* ESP: 10+max(25)+15 = 50 */ - /* AH: 9+max(25)+15 = 49 */ - /* unknown: 10 */ - - /* (ICMP allows recursion one level deep) */ - /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ - /* maxlen = 230+ 91 + 230 + 252 = 803 */ -} - -static void dump_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & IPT_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int i; - - sb_add(m, "%02x", *p++); - for (i = 1; i < dev->hard_header_len; i++, p++) - sb_add(m, ":%02x", *p); - } - sb_add(m, " "); -} - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 5, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void -ipt_log_packet(u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); -#ifdef CONFIG_BRIDGE_NETFILTER - if (skb->nf_bridge) { - const struct net_device *physindev; - const struct net_device *physoutdev; - - physindev = skb->nf_bridge->physindev; - if (physindev && in != physindev) - sb_add(m, "PHYSIN=%s ", physindev->name); - physoutdev = skb->nf_bridge->physoutdev; - if (physoutdev && out != physoutdev) - sb_add(m, "PHYSOUT=%s ", physoutdev->name); - } -#endif - - if (in != NULL) - dump_mac_header(m, loginfo, skb); - - dump_packet(m, loginfo, skb, 0); - - sb_close(m); -} - -static unsigned int -log_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct ipt_log_info *loginfo = par->targinfo; - struct nf_loginfo li; - - li.type = NF_LOG_TYPE_LOG; - li.u.log.level = loginfo->level; - li.u.log.logflags = loginfo->logflags; - - ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in, par->out, &li, - loginfo->prefix); - return XT_CONTINUE; -} - -static int log_tg_check(const struct xt_tgchk_param *par) -{ - const struct ipt_log_info *loginfo = par->targinfo; - - if (loginfo->level >= 8) { - pr_debug("level %u >= 8\n", loginfo->level); - return -EINVAL; - } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("prefix is not null-terminated\n"); - return -EINVAL; - } - return 0; -} - -static struct xt_target log_tg_reg __read_mostly = { - .name = "LOG", - .family = NFPROTO_IPV4, - .target = log_tg, - .targetsize = sizeof(struct ipt_log_info), - .checkentry = log_tg_check, - .me = THIS_MODULE, -}; - -static struct nf_logger ipt_log_logger __read_mostly = { - .name = "ipt_LOG", - .logfn = &ipt_log_packet, - .me = THIS_MODULE, -}; - -static int __init log_tg_init(void) -{ - int ret; - - ret = xt_register_target(&log_tg_reg); - if (ret < 0) - return ret; - nf_log_register(NFPROTO_IPV4, &ipt_log_logger); - return 0; -} - -static void __exit log_tg_exit(void) -{ - nf_log_unregister(&ipt_log_logger); - xt_unregister_target(&log_tg_reg); -} - -module_init(log_tg_init); -module_exit(log_tg_exit); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 9a68fb5b9e77..d33cddd16fbb 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -154,15 +154,6 @@ config IP6_NF_TARGET_HL (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. -config IP6_NF_TARGET_LOG - tristate "LOG target support" - default m if NETFILTER_ADVANCED=n - help - This option adds a `LOG' target, which allows you to create rules in - any iptables table which records the packet header to the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 2eaed96db02c..d4dfd0a21097 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -31,5 +31,4 @@ obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets -obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c deleted file mode 100644 index e6af8d72f26b..000000000000 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ /dev/null @@ -1,527 +0,0 @@ -/* - * This is a module which is used for logging packets. - */ - -/* (C) 2001 Jan Rekorajski <baggins@pld.org.pl> - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/ip.h> -#include <linux/spinlock.h> -#include <linux/icmpv6.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/ipv6.h> -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <net/netfilter/nf_log.h> -#include <net/netfilter/xt_log.h> - -MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); -MODULE_DESCRIPTION("Xtables: IPv6 packet logging to syslog"); -MODULE_LICENSE("GPL"); - -struct in_device; -#include <net/route.h> -#include <linux/netfilter_ipv6/ip6t_LOG.h> - -/* One level of recursion won't kill us */ -static void dump_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, unsigned int ip6hoff, - int recurse) -{ - u_int8_t currenthdr; - int fragment; - struct ipv6hdr _ip6h; - const struct ipv6hdr *ih; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ - sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); - - /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ - sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", - ntohs(ih->payload_len) + sizeof(struct ipv6hdr), - (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, - ih->hop_limit, - (ntohl(*(__be32 *)ih) & 0x000fffff)); - - fragment = 0; - ptr = ip6hoff + sizeof(struct ipv6hdr); - currenthdr = ih->nexthdr; - while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { - struct ipv6_opt_hdr _hdr; - const struct ipv6_opt_hdr *hp; - - hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); - if (hp == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 48 "OPT (...) " */ - if (logflags & IP6T_LOG_IPOPT) - sb_add(m, "OPT ( "); - - switch (currenthdr) { - case IPPROTO_FRAGMENT: { - struct frag_hdr _fhdr; - const struct frag_hdr *fh; - - sb_add(m, "FRAG:"); - fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), - &_fhdr); - if (fh == NULL) { - sb_add(m, "TRUNCATED "); - return; - } - - /* Max length: 6 "65535 " */ - sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); - - /* Max length: 11 "INCOMPLETE " */ - if (fh->frag_off & htons(0x0001)) - sb_add(m, "INCOMPLETE "); - - sb_add(m, "ID:%08x ", ntohl(fh->identification)); - - if (ntohs(fh->frag_off) & 0xFFF8) - fragment = 1; - - hdrlen = 8; - - break; - } - case IPPROTO_DSTOPTS: - case IPPROTO_ROUTING: - case IPPROTO_HOPOPTS: - if (fragment) { - if (logflags & IP6T_LOG_IPOPT) - sb_add(m, ")"); - return; - } - hdrlen = ipv6_optlen(hp); - break; - /* Max Length */ - case IPPROTO_AH: - if (logflags & IP6T_LOG_IPOPT) { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - /* Max length: 3 "AH " */ - sb_add(m, "AH "); - - if (fragment) { - sb_add(m, ")"); - return; - } - - ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), - &_ahdr); - if (ah == NULL) { - /* - * Max length: 26 "INCOMPLETE [65535 - * bytes] )" - */ - sb_add(m, "INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 15 "SPI=0xF1234567 */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - - } - - hdrlen = (hp->hdrlen+2)<<2; - break; - case IPPROTO_ESP: - if (logflags & IP6T_LOG_IPOPT) { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 4 "ESP " */ - sb_add(m, "ESP "); - - if (fragment) { - sb_add(m, ")"); - return; - } - - /* - * Max length: 26 "INCOMPLETE [65535 bytes] )" - */ - eh = skb_header_pointer(skb, ptr, sizeof(_esph), - &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 16 "SPI=0xF1234567 )" */ - sb_add(m, "SPI=0x%x )", ntohl(eh->spi) ); - - } - return; - default: - /* Max length: 20 "Unknown Ext Hdr 255" */ - sb_add(m, "Unknown Ext Hdr %u", currenthdr); - return; - } - if (logflags & IP6T_LOG_IPOPT) - sb_add(m, ") "); - - currenthdr = hp->nexthdr; - ptr += hdrlen; - } - - switch (currenthdr) { - case IPPROTO_TCP: { - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - sb_add(m, "PROTO=TCP "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, ptr, sizeof(_tcph), &_tcph); - if (th == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & IP6T_LOG_TCPSEQ) - sb_add(m, "SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - /* Max length: 13 "WINDOW=65535 " */ - sb_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3C " */ - sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - sb_add(m, "CWR "); - if (th->ece) - sb_add(m, "ECE "); - if (th->urg) - sb_add(m, "URG "); - if (th->ack) - sb_add(m, "ACK "); - if (th->psh) - sb_add(m, "PSH "); - if (th->rst) - sb_add(m, "RST "); - if (th->syn) - sb_add(m, "SYN "); - if (th->fin) - sb_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & IP6T_LOG_TCPOPT) && - th->doff * 4 > sizeof(struct tcphdr)) { - u_int8_t _opt[60 - sizeof(struct tcphdr)]; - const u_int8_t *op; - unsigned int i; - unsigned int optsize = th->doff * 4 - - sizeof(struct tcphdr); - - op = skb_header_pointer(skb, - ptr + sizeof(struct tcphdr), - optsize, _opt); - if (op == NULL) { - sb_add(m, "OPT (TRUNCATED)"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i =0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - break; - } - case IPPROTO_UDP: - case IPPROTO_UDPLITE: { - struct udphdr _udph; - const struct udphdr *uh; - - if (currenthdr == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - sb_add(m, "PROTO=UDP " ); - else /* Max length: 14 "PROTO=UDPLITE " */ - sb_add(m, "PROTO=UDPLITE "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, ptr, sizeof(_udph), &_udph); - if (uh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - break; - } - case IPPROTO_ICMPV6: { - struct icmp6hdr _icmp6h; - const struct icmp6hdr *ic; - - /* Max length: 13 "PROTO=ICMPv6 " */ - sb_add(m, "PROTO=ICMPv6 "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); - if (ic == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); - - switch (ic->icmp6_type) { - case ICMPV6_ECHO_REQUEST: - case ICMPV6_ECHO_REPLY: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ic->icmp6_identifier), - ntohs(ic->icmp6_sequence)); - break; - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - break; - - case ICMPV6_PARAMPROB: - /* Max length: 17 "POINTER=ffffffff " */ - sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); - /* Fall through */ - case ICMPV6_DEST_UNREACH: - case ICMPV6_PKT_TOOBIG: - case ICMPV6_TIME_EXCEED: - /* Max length: 3+maxlen */ - if (recurse) { - sb_add(m, "["); - dump_packet(m, info, skb, - ptr + sizeof(_icmp6h), 0); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) - sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); - } - break; - } - /* Max length: 10 "PROTO=255 " */ - default: - sb_add(m, "PROTO=%u ", currenthdr); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) { - read_lock_bh(&skb->sk->sk_callback_lock); - if (skb->sk->sk_socket && skb->sk->sk_socket->file) - sb_add(m, "UID=%u GID=%u ", - skb->sk->sk_socket->file->f_cred->fsuid, - skb->sk->sk_socket->file->f_cred->fsgid); - read_unlock_bh(&skb->sk->sk_callback_lock); - } - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (!recurse && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); -} - -static void dump_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & IP6T_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int len = dev->hard_header_len; - unsigned int i; - - if (dev->type == ARPHRD_SIT && - (p -= ETH_HLEN) < skb->head) - p = NULL; - - if (p != NULL) { - sb_add(m, "%02x", *p++); - for (i = 1; i < len; i++) - sb_add(m, ":%02x", *p++); - } - sb_add(m, " "); - - if (dev->type == ARPHRD_SIT) { - const struct iphdr *iph = - (struct iphdr *)skb_mac_header(skb); - sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, &iph->daddr); - } - } else - sb_add(m, " "); -} - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 5, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void -ip6t_log_packet(u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); - - if (in != NULL) - dump_mac_header(m, loginfo, skb); - - dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); - - sb_close(m); -} - -static unsigned int -log_tg6(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct ip6t_log_info *loginfo = par->targinfo; - struct nf_loginfo li; - - li.type = NF_LOG_TYPE_LOG; - li.u.log.level = loginfo->level; - li.u.log.logflags = loginfo->logflags; - - ip6t_log_packet(NFPROTO_IPV6, par->hooknum, skb, par->in, par->out, - &li, loginfo->prefix); - return XT_CONTINUE; -} - - -static int log_tg6_check(const struct xt_tgchk_param *par) -{ - const struct ip6t_log_info *loginfo = par->targinfo; - - if (loginfo->level >= 8) { - pr_debug("level %u >= 8\n", loginfo->level); - return -EINVAL; - } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("prefix not null-terminated\n"); - return -EINVAL; - } - return 0; -} - -static struct xt_target log_tg6_reg __read_mostly = { - .name = "LOG", - .family = NFPROTO_IPV6, - .target = log_tg6, - .targetsize = sizeof(struct ip6t_log_info), - .checkentry = log_tg6_check, - .me = THIS_MODULE, -}; - -static struct nf_logger ip6t_logger __read_mostly = { - .name = "ip6t_LOG", - .logfn = &ip6t_log_packet, - .me = THIS_MODULE, -}; - -static int __init log_tg6_init(void) -{ - int ret; - - ret = xt_register_target(&log_tg6_reg); - if (ret < 0) - return ret; - nf_log_register(NFPROTO_IPV6, &ip6t_logger); - return 0; -} - -static void __exit log_tg6_exit(void) -{ - nf_log_unregister(&ip6t_logger); - xt_unregister_target(&log_tg6_reg); -} - -module_init(log_tg6_init); -module_exit(log_tg6_exit); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f8ac4ef0b794..b895d8b13215 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -524,6 +524,15 @@ config NETFILTER_XT_TARGET_LED For more information on the LEDs available on your system, see Documentation/leds/leds-class.txt +config NETFILTER_XT_TARGET_LOG + tristate "LOG target support" + default m if NETFILTER_ADVANCED=n + help + This option adds a `LOG' target, which allows you to create rules in + any iptables table which records the packet header to the syslog. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_MARK tristate '"MARK" target support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 40f4c3d636c5..a28c2a6563f8 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -58,6 +58,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o +obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c new file mode 100644 index 000000000000..1595608a892d --- /dev/null +++ b/net/netfilter/xt_LOG.c @@ -0,0 +1,921 @@ +/* + * This is a module which is used for logging packets. + */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_LOG.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/netfilter/nf_log.h> +#include <net/netfilter/xt_log.h> + +static struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 5, + .logflags = NF_LOG_MASK, + }, + }, +}; + +static int dump_udp_header(struct sbuff *m, const struct sk_buff *skb, + u8 proto, int fragment, unsigned int offset) +{ + struct udphdr _udph; + const struct udphdr *uh; + + if (proto == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + sb_add(m, "PROTO=UDP "); + else /* Max length: 14 "PROTO=UDPLITE " */ + sb_add(m, "PROTO=UDPLITE "); + + if (fragment) + goto out; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (uh == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), + ntohs(uh->len)); + +out: + return 0; +} + +static int dump_tcp_header(struct sbuff *m, const struct sk_buff *skb, + u8 proto, int fragment, unsigned int offset, + unsigned int logflags) +{ + struct tcphdr _tcph; + const struct tcphdr *th; + + /* Max length: 10 "PROTO=TCP " */ + sb_add(m, "PROTO=TCP "); + + if (fragment) + return 0; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); + if (th == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); + /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ + if (logflags & XT_LOG_TCPSEQ) + sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); + + /* Max length: 13 "WINDOW=65535 " */ + sb_add(m, "WINDOW=%u ", ntohs(th->window)); + /* Max length: 9 "RES=0x3C " */ + sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & + TCP_RESERVED_BITS) >> 22)); + /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ + if (th->cwr) + sb_add(m, "CWR "); + if (th->ece) + sb_add(m, "ECE "); + if (th->urg) + sb_add(m, "URG "); + if (th->ack) + sb_add(m, "ACK "); + if (th->psh) + sb_add(m, "PSH "); + if (th->rst) + sb_add(m, "RST "); + if (th->syn) + sb_add(m, "SYN "); + if (th->fin) + sb_add(m, "FIN "); + /* Max length: 11 "URGP=65535 " */ + sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); + + if ((logflags & XT_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { + u_int8_t _opt[60 - sizeof(struct tcphdr)]; + const u_int8_t *op; + unsigned int i; + unsigned int optsize = th->doff*4 - sizeof(struct tcphdr); + + op = skb_header_pointer(skb, offset + sizeof(struct tcphdr), + optsize, _opt); + if (op == NULL) { + sb_add(m, "OPT (TRUNCATED)"); + return 1; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + sb_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + sb_add(m, "%02X", op[i]); + + sb_add(m, ") "); + } + + return 0; +} + +/* One level of recursion won't kill us */ +static void dump_ipv4_packet(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, + unsigned int iphoff) +{ + struct iphdr _iph; + const struct iphdr *ih; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); + if (ih == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Important fields: + * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ + /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ + sb_add(m, "SRC=%pI4 DST=%pI4 ", + &ih->saddr, &ih->daddr); + + /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ + sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", + ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); + + /* Max length: 6 "CE DF MF " */ + if (ntohs(ih->frag_off) & IP_CE) + sb_add(m, "CE "); + if (ntohs(ih->frag_off) & IP_DF) + sb_add(m, "DF "); + if (ntohs(ih->frag_off) & IP_MF) + sb_add(m, "MF "); + + /* Max length: 11 "FRAG:65535 " */ + if (ntohs(ih->frag_off) & IP_OFFSET) + sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); + + if ((logflags & XT_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { + const unsigned char *op; + unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; + unsigned int i, optsize; + + optsize = ih->ihl * 4 - sizeof(struct iphdr); + op = skb_header_pointer(skb, iphoff+sizeof(_iph), + optsize, _opt); + if (op == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + sb_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); + } + + switch (ih->protocol) { + case IPPROTO_TCP: + if (dump_tcp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff+ih->ihl*4, logflags)) + return; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (dump_udp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff+ih->ihl*4)) + return; + case IPPROTO_ICMP: { + struct icmphdr _icmph; + const struct icmphdr *ich; + static const size_t required_len[NR_ICMP_TYPES+1] + = { [ICMP_ECHOREPLY] = 4, + [ICMP_DEST_UNREACH] + = 8 + sizeof(struct iphdr), + [ICMP_SOURCE_QUENCH] + = 8 + sizeof(struct iphdr), + [ICMP_REDIRECT] + = 8 + sizeof(struct iphdr), + [ICMP_ECHO] = 4, + [ICMP_TIME_EXCEEDED] + = 8 + sizeof(struct iphdr), + [ICMP_PARAMETERPROB] + = 8 + sizeof(struct iphdr), + [ICMP_TIMESTAMP] = 20, + [ICMP_TIMESTAMPREPLY] = 20, + [ICMP_ADDRESS] = 12, + [ICMP_ADDRESSREPLY] = 12 }; + + /* Max length: 11 "PROTO=ICMP " */ + sb_add(m, "PROTO=ICMP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, + sizeof(_icmph), &_icmph); + if (ich == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + switch (ich->type) { + case ICMP_ECHOREPLY: + case ICMP_ECHO: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + sb_add(m, "ID=%u SEQ=%u ", + ntohs(ich->un.echo.id), + ntohs(ich->un.echo.sequence)); + break; + + case ICMP_PARAMETERPROB: + /* Max length: 14 "PARAMETER=255 " */ + sb_add(m, "PARAMETER=%u ", + ntohl(ich->un.gateway) >> 24); + break; + case ICMP_REDIRECT: + /* Max length: 24 "GATEWAY=255.255.255.255 " */ + sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); + /* Fall through */ + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_TIME_EXCEEDED: + /* Max length: 3+maxlen */ + if (!iphoff) { /* Only recurse once. */ + sb_add(m, "["); + dump_ipv4_packet(m, info, skb, + iphoff + ih->ihl*4+sizeof(_icmph)); + sb_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) + sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); + } + break; + } + /* Max Length */ + case IPPROTO_AH: { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 9 "PROTO=AH " */ + sb_add(m, "PROTO=AH "); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ah = skb_header_pointer(skb, iphoff+ih->ihl*4, + sizeof(_ahdr), &_ahdr); + if (ah == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); + break; + } + case IPPROTO_ESP: { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 10 "PROTO=ESP " */ + sb_add(m, "PROTO=ESP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + eh = skb_header_pointer(skb, iphoff+ih->ihl*4, + sizeof(_esph), &_esph); + if (eh == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); + break; + } + /* Max length: 10 "PROTO 255 " */ + default: + sb_add(m, "PROTO=%u ", ih->protocol); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && !iphoff && skb->sk) { + read_lock_bh(&skb->sk->sk_callback_lock); + if (skb->sk->sk_socket && skb->sk->sk_socket->file) + sb_add(m, "UID=%u GID=%u ", + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); + read_unlock_bh(&skb->sk->sk_callback_lock); + } + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (!iphoff && skb->mark) + sb_add(m, "MARK=0x%x ", skb->mark); + + /* Proto Max log string length */ + /* IP: 40+46+6+11+127 = 230 */ + /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ + /* UDP: 10+max(25,20) = 35 */ + /* UDPLITE: 14+max(25,20) = 39 */ + /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ + /* ESP: 10+max(25)+15 = 50 */ + /* AH: 9+max(25)+15 = 49 */ + /* unknown: 10 */ + + /* (ICMP allows recursion one level deep) */ + /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ + /* maxlen = 230+ 91 + 230 + 252 = 803 */ +} + +static void dump_ipv4_mac_header(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + sb_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int i; + + sb_add(m, "%02x", *p++); + for (i = 1; i < dev->hard_header_len; i++, p++) + sb_add(m, ":%02x", *p); + } + sb_add(m, " "); +} + +static void +log_packet_common(struct sbuff *m, + u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + prefix, + in ? in->name : "", + out ? out->name : ""); +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge) { + const struct net_device *physindev; + const struct net_device *physoutdev; + + physindev = skb->nf_bridge->physindev; + if (physindev && in != physindev) + sb_add(m, "PHYSIN=%s ", physindev->name); + physoutdev = skb->nf_bridge->physoutdev; + if (physoutdev && out != physoutdev) + sb_add(m, "PHYSOUT=%s ", physoutdev->name); + } +#endif +} + + +static void +ipt_log_packet(u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct sbuff *m = sb_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + log_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); + + if (in != NULL) + dump_ipv4_mac_header(m, loginfo, skb); + + dump_ipv4_packet(m, loginfo, skb, 0); + + sb_close(m); +} + +#if IS_ENABLED(CONFIG_IPV6) +/* One level of recursion won't kill us */ +static void dump_ipv6_packet(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int ip6hoff, + int recurse) +{ + u_int8_t currenthdr; + int fragment; + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + unsigned int ptr; + unsigned int hdrlen = 0; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); + if (ih == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ + sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + + /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ + sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + ntohs(ih->payload_len) + sizeof(struct ipv6hdr), + (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, + ih->hop_limit, + (ntohl(*(__be32 *)ih) & 0x000fffff)); + + fragment = 0; + ptr = ip6hoff + sizeof(struct ipv6hdr); + currenthdr = ih->nexthdr; + while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { + struct ipv6_opt_hdr _hdr; + const struct ipv6_opt_hdr *hp; + + hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); + if (hp == NULL) { + sb_add(m, "TRUNCATED"); + return; + } + + /* Max length: 48 "OPT (...) " */ + if (logflags & XT_LOG_IPOPT) + sb_add(m, "OPT ( "); + + switch (currenthdr) { + case IPPROTO_FRAGMENT: { + struct frag_hdr _fhdr; + const struct frag_hdr *fh; + + sb_add(m, "FRAG:"); + fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), + &_fhdr); + if (fh == NULL) { + sb_add(m, "TRUNCATED "); + return; + } + + /* Max length: 6 "65535 " */ + sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); + + /* Max length: 11 "INCOMPLETE " */ + if (fh->frag_off & htons(0x0001)) + sb_add(m, "INCOMPLETE "); + + sb_add(m, "ID:%08x ", ntohl(fh->identification)); + + if (ntohs(fh->frag_off) & 0xFFF8) + fragment = 1; + + hdrlen = 8; + + break; + } + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + case IPPROTO_HOPOPTS: + if (fragment) { + if (logflags & XT_LOG_IPOPT) + sb_add(m, ")"); + return; + } + hdrlen = ipv6_optlen(hp); + break; + /* Max Length */ + case IPPROTO_AH: + if (logflags & XT_LOG_IPOPT) { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + /* Max length: 3 "AH " */ + sb_add(m, "AH "); + + if (fragment) { + sb_add(m, ")"); + return; + } + + ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), + &_ahdr); + if (ah == NULL) { + /* + * Max length: 26 "INCOMPLETE [65535 + * bytes] )" + */ + sb_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 15 "SPI=0xF1234567 */ + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); + + } + + hdrlen = (hp->hdrlen+2)<<2; + break; + case IPPROTO_ESP: + if (logflags & XT_LOG_IPOPT) { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 4 "ESP " */ + sb_add(m, "ESP "); + + if (fragment) { + sb_add(m, ")"); + return; + } + + /* + * Max length: 26 "INCOMPLETE [65535 bytes] )" + */ + eh = skb_header_pointer(skb, ptr, sizeof(_esph), + &_esph); + if (eh == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 16 "SPI=0xF1234567 )" */ + sb_add(m, "SPI=0x%x )", ntohl(eh->spi)); + + } + return; + default: + /* Max length: 20 "Unknown Ext Hdr 255" */ + sb_add(m, "Unknown Ext Hdr %u", currenthdr); + return; + } + if (logflags & XT_LOG_IPOPT) + sb_add(m, ") "); + + currenthdr = hp->nexthdr; + ptr += hdrlen; + } + + switch (currenthdr) { + case IPPROTO_TCP: + if (dump_tcp_header(m, skb, currenthdr, fragment, ptr, + logflags)) + return; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (dump_udp_header(m, skb, currenthdr, fragment, ptr)) + return; + case IPPROTO_ICMPV6: { + struct icmp6hdr _icmp6h; + const struct icmp6hdr *ic; + + /* Max length: 13 "PROTO=ICMPv6 " */ + sb_add(m, "PROTO=ICMPv6 "); + + if (fragment) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); + if (ic == NULL) { + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); + return; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); + + switch (ic->icmp6_type) { + case ICMPV6_ECHO_REQUEST: + case ICMPV6_ECHO_REPLY: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + sb_add(m, "ID=%u SEQ=%u ", + ntohs(ic->icmp6_identifier), + ntohs(ic->icmp6_sequence)); + break; + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + break; + + case ICMPV6_PARAMPROB: + /* Max length: 17 "POINTER=ffffffff " */ + sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); + /* Fall through */ + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + /* Max length: 3+maxlen */ + if (recurse) { + sb_add(m, "["); + dump_ipv6_packet(m, info, skb, + ptr + sizeof(_icmp6h), 0); + sb_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) + sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); + } + break; + } + /* Max length: 10 "PROTO=255 " */ + default: + sb_add(m, "PROTO=%u ", currenthdr); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && recurse && skb->sk) { + read_lock_bh(&skb->sk->sk_callback_lock); + if (skb->sk->sk_socket && skb->sk->sk_socket->file) + sb_add(m, "UID=%u GID=%u ", + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); + read_unlock_bh(&skb->sk->sk_callback_lock); + } + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (!recurse && skb->mark) + sb_add(m, "MARK=0x%x ", skb->mark); +} + +static void dump_ipv6_mac_header(struct sbuff *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + sb_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int len = dev->hard_header_len; + unsigned int i; + + if (dev->type == ARPHRD_SIT) { + p -= ETH_HLEN; + + if (p < skb->head) + p = NULL; + } + + if (p != NULL) { + sb_add(m, "%02x", *p++); + for (i = 1; i < len; i++) + sb_add(m, ":%02x", *p++); + } + sb_add(m, " "); + + if (dev->type == ARPHRD_SIT) { + const struct iphdr *iph = + (struct iphdr *)skb_mac_header(skb); + sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, + &iph->daddr); + } + } else + sb_add(m, " "); +} + +static void +ip6t_log_packet(u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct sbuff *m = sb_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + log_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); + + if (in != NULL) + dump_ipv6_mac_header(m, loginfo, skb); + + dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + + sb_close(m); +} +#endif + +static unsigned int +log_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_log_info *loginfo = par->targinfo; + struct nf_loginfo li; + + li.type = NF_LOG_TYPE_LOG; + li.u.log.level = loginfo->level; + li.u.log.logflags = loginfo->logflags; + + if (par->family == NFPROTO_IPV4) + ipt_log_packet(NFPROTO_IPV4, par->hooknum, skb, par->in, + par->out, &li, loginfo->prefix); +#if IS_ENABLED(CONFIG_IPV6) + else if (par->family == NFPROTO_IPV6) + ip6t_log_packet(NFPROTO_IPV6, par->hooknum, skb, par->in, + par->out, &li, loginfo->prefix); +#endif + else + WARN_ON_ONCE(1); + + return XT_CONTINUE; +} + +static int log_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_log_info *loginfo = par->targinfo; + + if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) + return -EINVAL; + + if (loginfo->level >= 8) { + pr_debug("level %u >= 8\n", loginfo->level); + return -EINVAL; + } + + if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { + pr_debug("prefix is not null-terminated\n"); + return -EINVAL; + } + + return 0; +} + +static struct xt_target log_tg_regs[] __read_mostly = { + { + .name = "LOG", + .family = NFPROTO_IPV4, + .target = log_tg, + .targetsize = sizeof(struct xt_log_info), + .checkentry = log_tg_check, + .me = THIS_MODULE, + }, +#if IS_ENABLED(CONFIG_IPV6) + { + .name = "LOG", + .family = NFPROTO_IPV6, + .target = log_tg, + .targetsize = sizeof(struct xt_log_info), + .checkentry = log_tg_check, + .me = THIS_MODULE, + }, +#endif +}; + +static struct nf_logger ipt_log_logger __read_mostly = { + .name = "ipt_LOG", + .logfn = &ipt_log_packet, + .me = THIS_MODULE, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static struct nf_logger ip6t_log_logger __read_mostly = { + .name = "ip6t_LOG", + .logfn = &ip6t_log_packet, + .me = THIS_MODULE, +}; +#endif + +static int __init log_tg_init(void) +{ + int ret; + + ret = xt_register_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_IPV4, &ipt_log_logger); +#if IS_ENABLED(CONFIG_IPV6) + nf_log_register(NFPROTO_IPV6, &ip6t_log_logger); +#endif + return 0; +} + +static void __exit log_tg_exit(void) +{ + nf_log_unregister(&ipt_log_logger); +#if IS_ENABLED(CONFIG_IPV6) + nf_log_unregister(&ip6t_log_logger); +#endif + xt_unregister_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); +} + +module_init(log_tg_init); +module_exit(log_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); +MODULE_DESCRIPTION("Xtables: IPv4/IPv6 packet logging"); +MODULE_ALIAS("ipt_LOG"); +MODULE_ALIAS("ip6t_LOG"); -- cgit From 2c8503f55fbdfbeff4164f133df804cf4d316290 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso <pablo@netfilter.org> Date: Tue, 28 Feb 2012 18:23:31 +0100 Subject: netfilter: nf_conntrack: pass timeout array to l4->new and l4->packet This patch defines a new interface for l4 protocol trackers: unsigned int *(*get_timeouts)(struct net *net); that is used to return the array of unsigned int that contains the timeouts that will be applied for this flow. This is passed to the l4proto->new(...) and l4proto->packet(...) functions to specify the timeout policy. This interface allows per-net global timeout configuration (although only DCCP supports this by now) and it will allow custom custom timeout configuration by means of follow-up patches. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> --- include/net/netfilter/nf_conntrack_l4proto.h | 8 +++++-- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 13 +++++++++--- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 13 +++++++++--- net/netfilter/nf_conntrack_core.c | 18 ++++++++++------ net/netfilter/nf_conntrack_proto_dccp.c | 16 +++++++++----- net/netfilter/nf_conntrack_proto_generic.c | 29 ++++++++++++++++---------- net/netfilter/nf_conntrack_proto_gre.c | 15 +++++++++---- net/netfilter/nf_conntrack_proto_sctp.c | 14 ++++++++++--- net/netfilter/nf_conntrack_proto_tcp.c | 22 ++++++++++++------- net/netfilter/nf_conntrack_proto_udp.c | 16 ++++++++++---- net/netfilter/nf_conntrack_proto_udplite.c | 16 ++++++++++---- 11 files changed, 128 insertions(+), 52 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index e3d3ee3c06a2..c48b67405aa0 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -39,12 +39,13 @@ struct nf_conntrack_l4proto { unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum); + unsigned int hooknum, + unsigned int *timeouts); /* Called when a new connection for this protocol found; * returns TRUE if it's OK. If so, packet() called next. */ bool (*new)(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff); + unsigned int dataoff, unsigned int *timeouts); /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); @@ -60,6 +61,9 @@ struct nf_conntrack_l4proto { /* Print out the private part of the conntrack. */ int (*print_conntrack)(struct seq_file *s, struct nf_conn *); + /* Return the array of timeouts for this protocol. */ + unsigned int *(*get_timeouts)(struct net *net); + /* convert protoinfo to nfnetink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index ab5b27a2916f..6b801124b31f 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -75,25 +75,31 @@ static int icmp_print_tuple(struct seq_file *s, ntohs(tuple->src.u.icmp.id)); } +static unsigned int *icmp_get_timeouts(struct net *net) +{ + return &nf_ct_icmp_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ static int icmp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeout) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, @@ -298,6 +304,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .invert_tuple = icmp_invert_tuple, .print_tuple = icmp_print_tuple, .packet = icmp_packet, + .get_timeouts = icmp_get_timeouts, .new = icmp_new, .error = icmp_error, .destroy = NULL, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 7c05e7eacbc6..2eb9751eb7a8 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -88,25 +88,31 @@ static int icmpv6_print_tuple(struct seq_file *s, ntohs(tuple->src.u.icmp.id)); } +static unsigned int *icmpv6_get_timeouts(struct net *net) +{ + return &nf_ct_icmpv6_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ static int icmpv6_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeout) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { static const u_int8_t valid_new[] = { [ICMPV6_ECHO_REQUEST - 128] = 1, @@ -293,6 +299,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .invert_tuple = icmpv6_invert_tuple, .print_tuple = icmpv6_print_tuple, .packet = icmpv6_packet, + .get_timeouts = icmpv6_get_timeouts, .new = icmpv6_new, .error = icmpv6_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ed86a3be678e..d18995eea1c6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -763,7 +763,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, - unsigned int dataoff, u32 hash) + unsigned int dataoff, u32 hash, + unsigned int *timeouts) { struct nf_conn *ct; struct nf_conn_help *help; @@ -782,7 +783,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; - if (!l4proto->new(ct, skb, dataoff)) { + if (!l4proto->new(ct, skb, dataoff, timeouts)) { nf_conntrack_free(ct); pr_debug("init conntrack: can't track with proto module\n"); return NULL; @@ -848,7 +849,8 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, int *set_reply, - enum ip_conntrack_info *ctinfo) + enum ip_conntrack_info *ctinfo, + unsigned int *timeouts) { struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; @@ -868,7 +870,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, h = __nf_conntrack_find_get(net, zone, &tuple, hash); if (!h) { h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, - skb, dataoff, hash); + skb, dataoff, hash, timeouts); if (!h) return NULL; if (IS_ERR(h)) @@ -909,6 +911,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, enum ip_conntrack_info ctinfo; struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts; unsigned int dataoff; u_int8_t protonum; int set_reply = 0; @@ -955,8 +958,11 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, goto out; } + timeouts = l4proto->get_timeouts(net); + ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, - l3proto, l4proto, &set_reply, &ctinfo); + l3proto, l4proto, &set_reply, &ctinfo, + timeouts); if (!ct) { /* Not valid part of a connection */ NF_CT_STAT_INC_ATOMIC(net, invalid); @@ -973,7 +979,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, NF_CT_ASSERT(skb->nfct); - ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum); + ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index d6dde6dc09e6..8ea33598a0a7 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -423,7 +423,7 @@ static bool dccp_invert_tuple(struct nf_conntrack_tuple *inv, } static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { struct net *net = nf_ct_net(ct); struct dccp_net *dn; @@ -472,12 +472,17 @@ static u64 dccp_ack_seq(const struct dccp_hdr *dh) ntohl(dhack->dccph_ack_nr_low); } +static unsigned int *dccp_get_timeouts(struct net *net) +{ + return dccp_pernet(net)->dccp_timeout; +} + static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int hooknum) + u_int8_t pf, unsigned int hooknum, + unsigned int *timeouts) { struct net *net = nf_ct_net(ct); - struct dccp_net *dn; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct dccp_hdr _dh, *dh; u_int8_t type, old_state, new_state; @@ -559,8 +564,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); - dn = dccp_pernet(net); - nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; } @@ -767,6 +771,7 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .invert_tuple = dccp_invert_tuple, .new = dccp_new, .packet = dccp_packet, + .get_timeouts = dccp_get_timeouts, .error = dccp_error, .print_tuple = dccp_print_tuple, .print_conntrack = dccp_print_conntrack, @@ -789,6 +794,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .invert_tuple = dccp_invert_tuple, .new = dccp_new, .packet = dccp_packet, + .get_timeouts = dccp_get_timeouts, .error = dccp_error, .print_tuple = dccp_print_tuple, .print_conntrack = dccp_print_conntrack, diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e2091d0c7a2f..0e6c5451db80 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -40,21 +40,27 @@ static int generic_print_tuple(struct seq_file *s, return 0; } +static unsigned int *generic_get_timeouts(struct net *net) +{ + return &nf_ct_generic_timeout; +} + /* Returns verdict for packet, or -1 for invalid. */ -static int packet(struct nf_conn *ct, - const struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - u_int8_t pf, - unsigned int hooknum) +static int generic_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + u_int8_t pf, + unsigned int hooknum, + unsigned int *timeout) { - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_generic_timeout); + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ -static bool new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) +static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff, unsigned int *timeouts) { return true; } @@ -93,8 +99,9 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly = .pkt_to_tuple = generic_pkt_to_tuple, .invert_tuple = generic_invert_tuple, .print_tuple = generic_print_tuple, - .packet = packet, - .new = new, + .packet = generic_packet, + .get_timeouts = generic_get_timeouts, + .new = generic_new, #ifdef CONFIG_SYSCTL .ctl_table_header = &generic_sysctl_header, .ctl_table = generic_sysctl_table, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 8144f22d159a..1bf01c95658b 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -235,13 +235,19 @@ static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) (ct->proto.gre.stream_timeout / HZ)); } +static unsigned int *gre_get_timeouts(struct net *net) +{ + return gre_timeouts; +} + /* Returns verdict for packet, and may modify conntrack */ static int gre_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { /* If we've seen traffic both ways, this is a GRE connection. * Extend timeout. */ @@ -260,15 +266,15 @@ static int gre_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool gre_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { pr_debug(": "); nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); /* initialize to sane value. Ideally a conntrack helper * (e.g. in case of pptp) is increasing them */ - ct->proto.gre.stream_timeout = gre_timeouts[GRE_CT_REPLIED]; - ct->proto.gre.timeout = gre_timeouts[GRE_CT_UNREPLIED]; + ct->proto.gre.stream_timeout = timeouts[GRE_CT_REPLIED]; + ct->proto.gre.timeout = timeouts[GRE_CT_UNREPLIED]; return true; } @@ -295,6 +301,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .invert_tuple = gre_invert_tuple, .print_tuple = gre_print_tuple, .print_conntrack = gre_print_conntrack, + .get_timeouts = gre_get_timeouts, .packet = gre_packet, .new = gre_new, .destroy = gre_destroy, diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index afa69136061a..2a0703371e24 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -279,13 +279,19 @@ static int sctp_new_state(enum ip_conntrack_dir dir, return sctp_conntracks[dir][i][cur_state]; } +static unsigned int *sctp_get_timeouts(struct net *net) +{ + return sctp_timeouts; +} + /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ static int sctp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { enum sctp_conntrack new_state, old_state; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -370,7 +376,7 @@ static int sctp_packet(struct nf_conn *ct, } spin_unlock_bh(&ct->lock); - nf_ct_refresh_acct(ct, ctinfo, skb, sctp_timeouts[new_state]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && dir == IP_CT_DIR_REPLY && @@ -390,7 +396,7 @@ out: /* Called when a new connection for this protocol found. */ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { enum sctp_conntrack new_state; const struct sctphdr *sh; @@ -664,6 +670,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .print_tuple = sctp_print_tuple, .print_conntrack = sctp_print_conntrack, .packet = sctp_packet, + .get_timeouts = sctp_get_timeouts, .new = sctp_new, .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -694,6 +701,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .print_tuple = sctp_print_tuple, .print_conntrack = sctp_print_conntrack, .packet = sctp_packet, + .get_timeouts = sctp_get_timeouts, .new = sctp_new, .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 57c778546094..8372bb43feb0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -813,13 +813,19 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +static unsigned int *tcp_get_timeouts(struct net *net) +{ + return tcp_timeouts; +} + /* Returns verdict for packet, or -1 for invalid. */ static int tcp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple *tuple; @@ -1014,14 +1020,14 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans && - tcp_timeouts[new_state] > tcp_timeouts[TCP_CONNTRACK_RETRANS]) - timeout = tcp_timeouts[TCP_CONNTRACK_RETRANS]; + timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) + timeout = timeouts[TCP_CONNTRACK_RETRANS]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && - tcp_timeouts[new_state] > tcp_timeouts[TCP_CONNTRACK_UNACK]) - timeout = tcp_timeouts[TCP_CONNTRACK_UNACK]; + timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) + timeout = timeouts[TCP_CONNTRACK_UNACK]; else - timeout = tcp_timeouts[new_state]; + timeout = timeouts[new_state]; spin_unlock_bh(&ct->lock); if (new_state != old_state) @@ -1053,7 +1059,7 @@ static int tcp_packet(struct nf_conn *ct, /* Called when a new connection for this protocol found. */ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { enum tcp_conntrack new_state; const struct tcphdr *th; @@ -1444,6 +1450,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = .print_tuple = tcp_print_tuple, .print_conntrack = tcp_print_conntrack, .packet = tcp_packet, + .get_timeouts = tcp_get_timeouts, .new = tcp_new, .error = tcp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -1476,6 +1483,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = .print_tuple = tcp_print_tuple, .print_conntrack = tcp_print_conntrack, .packet = tcp_packet, + .get_timeouts = tcp_get_timeouts, .new = tcp_new, .error = tcp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 5b24ff882f95..70e005992d5b 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -71,32 +71,38 @@ static int udp_print_tuple(struct seq_file *s, ntohs(tuple->dst.u.udp.port)); } +static unsigned int *udp_get_timeouts(struct net *net) +{ + return udp_timeouts; +} + /* Returns verdict for packet, and may modify conntracktype */ static int udp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { /* If we've seen traffic both ways, this is some kind of UDP stream. Extend timeout. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, - udp_timeouts[UDP_CT_REPLIED]); + timeouts[UDP_CT_REPLIED]); /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { nf_ct_refresh_acct(ct, ctinfo, skb, - udp_timeouts[UDP_CT_UNREPLIED]); + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { return true; } @@ -196,6 +202,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = .invert_tuple = udp_invert_tuple, .print_tuple = udp_print_tuple, .packet = udp_packet, + .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -224,6 +231,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = .invert_tuple = udp_invert_tuple, .print_tuple = udp_print_tuple, .packet = udp_packet, + .get_timeouts = udp_get_timeouts, .new = udp_new, .error = udp_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index e73071743e01..0b32ccb1d515 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -68,32 +68,38 @@ static int udplite_print_tuple(struct seq_file *s, ntohs(tuple->dst.u.udp.port)); } +static unsigned int *udplite_get_timeouts(struct net *net) +{ + return udplite_timeouts; +} + /* Returns verdict for packet, and may modify conntracktype */ static int udplite_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum) + unsigned int hooknum, + unsigned int *timeouts) { /* If we've seen traffic both ways, this is some kind of UDP stream. Extend timeout. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, - udplite_timeouts[UDPLITE_CT_REPLIED]); + timeouts[UDPLITE_CT_REPLIED]); /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { nf_ct_refresh_acct(ct, ctinfo, skb, - udplite_timeouts[UDPLITE_CT_UNREPLIED]); + timeouts[UDPLITE_CT_UNREPLIED]); } return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static bool udplite_new(struct nf_conn *ct, const struct sk_buff *skb, - unsigned int dataoff) + unsigned int dataoff, unsigned int *timeouts) { return true; } @@ -181,6 +187,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = .invert_tuple = udplite_invert_tuple, .print_tuple = udplite_print_tuple, .packet = udplite_packet, + .get_timeouts = udplite_get_timeouts, .new = udplite_new, .error = udplite_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) @@ -205,6 +212,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .invert_tuple = udplite_invert_tuple, .print_tuple = udplite_print_tuple, .packet = udplite_packet, + .get_timeouts = udplite_get_timeouts, .new = udplite_new, .error = udplite_error, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) -- cgit From 50978462300f74dc48aea4a38471cb69bdf741a5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso <pablo@netfilter.org> Date: Tue, 28 Feb 2012 19:13:48 +0100 Subject: netfilter: add cttimeout infrastructure for fine timeout tuning This patch adds the infrastructure to add fine timeout tuning over nfnetlink. Now you can use the NFNL_SUBSYS_CTNETLINK_TIMEOUT subsystem to create/delete/dump timeout objects that contain some specific timeout policy for one flow. The follow up patches will allow you attach timeout policy object to conntrack via the CT target and the conntrack extension infrastructure. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/nfnetlink.h | 3 +- include/linux/netfilter/nfnetlink_cttimeout.h | 114 +++++++ include/net/netfilter/nf_conntrack_l4proto.h | 11 + net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 47 +++ net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 47 +++ net/netfilter/Kconfig | 11 + net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_proto_dccp.c | 70 +++++ net/netfilter/nf_conntrack_proto_generic.c | 48 +++ net/netfilter/nf_conntrack_proto_gre.c | 55 ++++ net/netfilter/nf_conntrack_proto_sctp.c | 69 +++++ net/netfilter/nf_conntrack_proto_tcp.c | 127 ++++++++ net/netfilter/nf_conntrack_proto_udp.c | 64 ++++ net/netfilter/nf_conntrack_proto_udplite.c | 66 ++++ net/netfilter/nfnetlink_cttimeout.c | 398 +++++++++++++++++++++++++ 16 files changed, 1131 insertions(+), 1 deletion(-) create mode 100644 include/linux/netfilter/nfnetlink_cttimeout.h create mode 100644 net/netfilter/nfnetlink_cttimeout.c (limited to 'net/ipv4') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index aaa72aaa21de..1697036336b6 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -10,6 +10,7 @@ header-y += nfnetlink.h header-y += nfnetlink_acct.h header-y += nfnetlink_compat.h header-y += nfnetlink_conntrack.h +header-y += nfnetlink_cttimeout.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h header-y += x_tables.h diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index b64454c2f79f..6fd1f0d07e64 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -49,7 +49,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_OSF 5 #define NFNL_SUBSYS_IPSET 6 #define NFNL_SUBSYS_ACCT 7 -#define NFNL_SUBSYS_COUNT 8 +#define NFNL_SUBSYS_CTNETLINK_TIMEOUT 8 +#define NFNL_SUBSYS_COUNT 9 #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink_cttimeout.h b/include/linux/netfilter/nfnetlink_cttimeout.h new file mode 100644 index 000000000000..a2810a7c5e30 --- /dev/null +++ b/include/linux/netfilter/nfnetlink_cttimeout.h @@ -0,0 +1,114 @@ +#ifndef _CTTIMEOUT_NETLINK_H +#define _CTTIMEOUT_NETLINK_H +#include <linux/netfilter/nfnetlink.h> + +enum ctnl_timeout_msg_types { + IPCTNL_MSG_TIMEOUT_NEW, + IPCTNL_MSG_TIMEOUT_GET, + IPCTNL_MSG_TIMEOUT_DELETE, + + IPCTNL_MSG_TIMEOUT_MAX +}; + +enum ctattr_timeout { + CTA_TIMEOUT_UNSPEC, + CTA_TIMEOUT_NAME, + CTA_TIMEOUT_L3PROTO, + CTA_TIMEOUT_L4PROTO, + CTA_TIMEOUT_DATA, + CTA_TIMEOUT_USE, + __CTA_TIMEOUT_MAX +}; +#define CTA_TIMEOUT_MAX (__CTA_TIMEOUT_MAX - 1) + +enum ctattr_timeout_generic { + CTA_TIMEOUT_GENERIC_UNSPEC, + CTA_TIMEOUT_GENERIC_TIMEOUT, + __CTA_TIMEOUT_GENERIC_MAX +}; +#define CTA_TIMEOUT_GENERIC_MAX (__CTA_TIMEOUT_GENERIC_MAX - 1) + +enum ctattr_timeout_tcp { + CTA_TIMEOUT_TCP_UNSPEC, + CTA_TIMEOUT_TCP_SYN_SENT, + CTA_TIMEOUT_TCP_SYN_RECV, + CTA_TIMEOUT_TCP_ESTABLISHED, + CTA_TIMEOUT_TCP_FIN_WAIT, + CTA_TIMEOUT_TCP_CLOSE_WAIT, + CTA_TIMEOUT_TCP_LAST_ACK, + CTA_TIMEOUT_TCP_TIME_WAIT, + CTA_TIMEOUT_TCP_CLOSE, + CTA_TIMEOUT_TCP_SYN_SENT2, + CTA_TIMEOUT_TCP_RETRANS, + CTA_TIMEOUT_TCP_UNACK, + __CTA_TIMEOUT_TCP_MAX +}; +#define CTA_TIMEOUT_TCP_MAX (__CTA_TIMEOUT_TCP_MAX - 1) + +enum ctattr_timeout_udp { + CTA_TIMEOUT_UDP_UNSPEC, + CTA_TIMEOUT_UDP_UNREPLIED, + CTA_TIMEOUT_UDP_REPLIED, + __CTA_TIMEOUT_UDP_MAX +}; +#define CTA_TIMEOUT_UDP_MAX (__CTA_TIMEOUT_UDP_MAX - 1) + +enum ctattr_timeout_udplite { + CTA_TIMEOUT_UDPLITE_UNSPEC, + CTA_TIMEOUT_UDPLITE_UNREPLIED, + CTA_TIMEOUT_UDPLITE_REPLIED, + __CTA_TIMEOUT_UDPLITE_MAX +}; +#define CTA_TIMEOUT_UDPLITE_MAX (__CTA_TIMEOUT_UDPLITE_MAX - 1) + +enum ctattr_timeout_icmp { + CTA_TIMEOUT_ICMP_UNSPEC, + CTA_TIMEOUT_ICMP_TIMEOUT, + __CTA_TIMEOUT_ICMP_MAX +}; +#define CTA_TIMEOUT_ICMP_MAX (__CTA_TIMEOUT_ICMP_MAX - 1) + +enum ctattr_timeout_dccp { + CTA_TIMEOUT_DCCP_UNSPEC, + CTA_TIMEOUT_DCCP_REQUEST, + CTA_TIMEOUT_DCCP_RESPOND, + CTA_TIMEOUT_DCCP_PARTOPEN, + CTA_TIMEOUT_DCCP_OPEN, + CTA_TIMEOUT_DCCP_CLOSEREQ, + CTA_TIMEOUT_DCCP_CLOSING, + CTA_TIMEOUT_DCCP_TIMEWAIT, + __CTA_TIMEOUT_DCCP_MAX +}; +#define CTA_TIMEOUT_DCCP_MAX (__CTA_TIMEOUT_DCCP_MAX - 1) + +enum ctattr_timeout_sctp { + CTA_TIMEOUT_SCTP_UNSPEC, + CTA_TIMEOUT_SCTP_CLOSED, + CTA_TIMEOUT_SCTP_COOKIE_WAIT, + CTA_TIMEOUT_SCTP_COOKIE_ECHOED, + CTA_TIMEOUT_SCTP_ESTABLISHED, + CTA_TIMEOUT_SCTP_SHUTDOWN_SENT, + CTA_TIMEOUT_SCTP_SHUTDOWN_RECD, + CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, + __CTA_TIMEOUT_SCTP_MAX +}; +#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) + +enum ctattr_timeout_icmpv6 { + CTA_TIMEOUT_ICMPV6_UNSPEC, + CTA_TIMEOUT_ICMPV6_TIMEOUT, + __CTA_TIMEOUT_ICMPV6_MAX +}; +#define CTA_TIMEOUT_ICMPV6_MAX (__CTA_TIMEOUT_ICMPV6_MAX - 1) + +enum ctattr_timeout_gre { + CTA_TIMEOUT_GRE_UNSPEC, + CTA_TIMEOUT_GRE_UNREPLIED, + CTA_TIMEOUT_GRE_REPLIED, + __CTA_TIMEOUT_GRE_MAX +}; +#define CTA_TIMEOUT_GRE_MAX (__CTA_TIMEOUT_GRE_MAX - 1) + +#define CTNL_TIMEOUT_NAME_MAX 32 + +#endif diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index c48b67405aa0..90c67c7db7e9 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -83,6 +83,17 @@ struct nf_conntrack_l4proto { size_t nla_size; +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + struct { + size_t obj_size; + int (*nlattr_to_obj)(struct nlattr *tb[], void *data); + int (*obj_to_nlattr)(struct sk_buff *skb, const void *data); + + unsigned int nlattr_max; + const struct nla_policy *nla_policy; + } ctnl_timeout; +#endif + #ifdef CONFIG_SYSCTL struct ctl_table_header **ctl_table_header; struct ctl_table *ctl_table; diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 6b801124b31f..7cbe9cb261c2 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -269,6 +269,44 @@ static int icmp_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; + } else { + /* Set default ICMP timeout. */ + *timeout = nf_ct_icmp_timeout; + } + return 0; +} + +static int +icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { + [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *icmp_sysctl_header; static struct ctl_table icmp_sysctl_table[] = { @@ -315,6 +353,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmp_timeout_nlattr_to_obj, + .obj_to_nlattr = icmp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &icmp_sysctl_header, .ctl_table = icmp_sysctl_table, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 2eb9751eb7a8..92cc9f2931ae 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -276,6 +276,44 @@ static int icmpv6_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; + } else { + /* Set default ICMPv6 timeout. */ + *timeout = nf_ct_icmpv6_timeout; + } + return 0; +} + +static int +icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { + [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *icmpv6_sysctl_header; static struct ctl_table icmpv6_sysctl_table[] = { @@ -308,6 +346,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, + .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmpv6_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &icmpv6_sysctl_header, .ctl_table = icmpv6_sysctl_table, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index b895d8b13215..f3efb6570dd9 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -314,6 +314,17 @@ config NF_CT_NETLINK help This option enables support for a netlink-based userspace interface +config NF_CT_NETLINK_TIMEOUT + tristate 'Connection tracking timeout tuning via Netlink' + select NETFILTER_NETLINK + depends on NETFILTER_ADVANCED + help + This option enables support for connection tracking timeout + fine-grain tuning. This allows you to attach specific timeout + policies to flows, instead of using the global timeout policy. + + If unsure, say `N'. + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a28c2a6563f8..cf7cdd630bdd 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_NF_CT_PROTO_UDPLITE) += nf_conntrack_proto_udplite.o # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o +obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o # connection tracking helpers nf_conntrack_h323-objs := nf_conntrack_h323_main.o nf_conntrack_h323_asn1.o diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 8ea33598a0a7..24fdce256cb0 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -706,8 +706,60 @@ static int dccp_nlattr_size(void) return nla_total_size(0) /* CTA_PROTOINFO_DCCP */ + nla_policy_len(dccp_nla_policy, CTA_PROTOINFO_DCCP_MAX + 1); } + #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + struct dccp_net *dn = dccp_pernet(&init_net); + unsigned int *timeouts = data; + int i; + + /* set default DCCP timeouts. */ + for (i=0; i<CT_DCCP_MAX; i++) + timeouts[i] = dn->dccp_timeout[i]; + + /* there's a 1:1 mapping between attributes and protocol states. */ + for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { + if (tb[i]) { + timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; + } + } + return 0; +} + +static int +dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + int i; + + for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) + NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { + [CTA_TIMEOUT_DCCP_REQUEST] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_RESPOND] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_PARTOPEN] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_OPEN] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_CLOSEREQ] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, + [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL /* template, data assigned later */ static struct ctl_table dccp_sysctl_table[] = { @@ -784,6 +836,15 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = dccp_timeout_nlattr_to_obj, + .obj_to_nlattr = dccp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_DCCP_MAX, + .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, + .nla_policy = dccp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ }; static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { @@ -807,6 +868,15 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = dccp_timeout_nlattr_to_obj, + .obj_to_nlattr = dccp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_DCCP_MAX, + .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, + .nla_policy = dccp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ }; static __net_init int dccp_net_init(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 0e6c5451db80..835e24c58f0d 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -65,6 +65,45 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeout = data; + + if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT]) + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_GENERIC_TIMEOUT])) * HZ; + else { + /* Set default generic timeout. */ + *timeout = nf_ct_generic_timeout; + } + + return 0; +} + +static int +generic_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_GENERIC_TIMEOUT, htonl(*timeout / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { + [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static struct ctl_table_header *generic_sysctl_header; static struct ctl_table generic_sysctl_table[] = { @@ -102,6 +141,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly = .packet = generic_packet, .get_timeouts = generic_get_timeouts, .new = generic_new, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = generic_timeout_nlattr_to_obj, + .obj_to_nlattr = generic_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_GENERIC_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = generic_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_header = &generic_sysctl_header, .ctl_table = generic_sysctl_table, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 1bf01c95658b..659648c4b14a 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -292,6 +292,52 @@ static void gre_destroy(struct nf_conn *ct) nf_ct_gre_keymap_destroy(master); } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + + /* set default timeouts for GRE. */ + timeouts[GRE_CT_UNREPLIED] = gre_timeouts[GRE_CT_UNREPLIED]; + timeouts[GRE_CT_REPLIED] = gre_timeouts[GRE_CT_REPLIED]; + + if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) { + timeouts[GRE_CT_UNREPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_GRE_UNREPLIED])) * HZ; + } + if (tb[CTA_TIMEOUT_GRE_REPLIED]) { + timeouts[GRE_CT_REPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_GRE_REPLIED])) * HZ; + } + return 0; +} + +static int +gre_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_GRE_UNREPLIED, + htonl(timeouts[GRE_CT_UNREPLIED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_GRE_REPLIED, + htonl(timeouts[GRE_CT_REPLIED] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { + [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + /* protocol helper struct */ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .l3proto = AF_INET, @@ -312,6 +358,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = gre_timeout_nlattr_to_obj, + .obj_to_nlattr = gre_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_GRE_MAX, + .obj_size = sizeof(unsigned int) * GRE_CT_MAX, + .nla_policy = gre_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ }; static int proto_gre_net_init(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 2a0703371e24..72b5088592dc 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -549,6 +549,57 @@ static int sctp_nlattr_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + int i; + + /* set default SCTP timeouts. */ + for (i=0; i<SCTP_CONNTRACK_MAX; i++) + timeouts[i] = sctp_timeouts[i]; + + /* there's a 1:1 mapping between attributes and protocol states. */ + for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) { + if (tb[i]) { + timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; + } + } + return 0; +} + +static int +sctp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + int i; + + for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) + NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ)); + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { + [CTA_TIMEOUT_SCTP_CLOSED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_COOKIE_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_COOKIE_ECHOED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_ESTABLISHED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + + #ifdef CONFIG_SYSCTL static unsigned int sctp_sysctl_table_users; static struct ctl_table_header *sctp_sysctl_header; @@ -682,6 +733,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = sctp_timeout_nlattr_to_obj, + .obj_to_nlattr = sctp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_SCTP_MAX, + .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, + .nla_policy = sctp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &sctp_sysctl_table_users, .ctl_table_header = &sctp_sysctl_header, @@ -712,6 +772,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = sctp_timeout_nlattr_to_obj, + .obj_to_nlattr = sctp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_SCTP_MAX, + .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, + .nla_policy = sctp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #endif #ifdef CONFIG_SYSCTL .ctl_table_users = &sctp_sysctl_table_users, diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 8372bb43feb0..361eade62a09 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1244,6 +1244,113 @@ static int tcp_nlattr_tuple_size(void) } #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + int i; + + /* set default TCP timeouts. */ + for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++) + timeouts[i] = tcp_timeouts[i]; + + if (tb[CTA_TIMEOUT_TCP_SYN_SENT]) { + timeouts[TCP_CONNTRACK_SYN_SENT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { + timeouts[TCP_CONNTRACK_SYN_RECV] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_ESTABLISHED]) { + timeouts[TCP_CONNTRACK_ESTABLISHED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_ESTABLISHED]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_FIN_WAIT]) { + timeouts[TCP_CONNTRACK_FIN_WAIT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_FIN_WAIT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]) { + timeouts[TCP_CONNTRACK_CLOSE_WAIT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE_WAIT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_LAST_ACK]) { + timeouts[TCP_CONNTRACK_LAST_ACK] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_LAST_ACK]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_TIME_WAIT]) { + timeouts[TCP_CONNTRACK_TIME_WAIT] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_TIME_WAIT]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_CLOSE]) { + timeouts[TCP_CONNTRACK_CLOSE] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_CLOSE]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_SYN_SENT2]) { + timeouts[TCP_CONNTRACK_SYN_SENT2] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT2]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_RETRANS]) { + timeouts[TCP_CONNTRACK_RETRANS] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_RETRANS]))*HZ; + } + if (tb[CTA_TIMEOUT_TCP_UNACK]) { + timeouts[TCP_CONNTRACK_UNACK] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; + } + return 0; +} + +static int +tcp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT, + htonl(timeouts[TCP_CONNTRACK_SYN_SENT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_RECV, + htonl(timeouts[TCP_CONNTRACK_SYN_RECV] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_ESTABLISHED, + htonl(timeouts[TCP_CONNTRACK_ESTABLISHED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_FIN_WAIT, + htonl(timeouts[TCP_CONNTRACK_FIN_WAIT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE_WAIT, + htonl(timeouts[TCP_CONNTRACK_CLOSE_WAIT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_LAST_ACK, + htonl(timeouts[TCP_CONNTRACK_LAST_ACK] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_TIME_WAIT, + htonl(timeouts[TCP_CONNTRACK_TIME_WAIT] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_CLOSE, + htonl(timeouts[TCP_CONNTRACK_CLOSE] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_SYN_SENT2, + htonl(timeouts[TCP_CONNTRACK_SYN_SENT2] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_RETRANS, + htonl(timeouts[TCP_CONNTRACK_RETRANS] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_TCP_UNACK, + htonl(timeouts[TCP_CONNTRACK_UNACK] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { + [CTA_TIMEOUT_TCP_SYN_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_SYN_RECV] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_ESTABLISHED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_FIN_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_CLOSE_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_LAST_ACK] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_TIME_WAIT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_CLOSE] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_SYN_SENT2] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static unsigned int tcp_sysctl_table_users; static struct ctl_table_header *tcp_sysctl_header; @@ -1462,6 +1569,16 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = tcp_timeout_nlattr_to_obj, + .obj_to_nlattr = tcp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_TCP_MAX, + .obj_size = sizeof(unsigned int) * + TCP_CONNTRACK_TIMEOUT_MAX, + .nla_policy = tcp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &tcp_sysctl_table_users, .ctl_table_header = &tcp_sysctl_header, @@ -1495,6 +1612,16 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = tcp_timeout_nlattr_to_obj, + .obj_to_nlattr = tcp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_TCP_MAX, + .obj_size = sizeof(unsigned int) * + TCP_CONNTRACK_TIMEOUT_MAX, + .nla_policy = tcp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &tcp_sysctl_table_users, .ctl_table_header = &tcp_sysctl_header, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 70e005992d5b..a9073dc1548d 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -152,6 +152,52 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + + /* set default timeouts for UDP. */ + timeouts[UDP_CT_UNREPLIED] = udp_timeouts[UDP_CT_UNREPLIED]; + timeouts[UDP_CT_REPLIED] = udp_timeouts[UDP_CT_REPLIED]; + + if (tb[CTA_TIMEOUT_UDP_UNREPLIED]) { + timeouts[UDP_CT_UNREPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDP_UNREPLIED])) * HZ; + } + if (tb[CTA_TIMEOUT_UDP_REPLIED]) { + timeouts[UDP_CT_REPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDP_REPLIED])) * HZ; + } + return 0; +} + +static int +udp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDP_UNREPLIED, + htonl(timeouts[UDP_CT_UNREPLIED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDP_REPLIED, + htonl(timeouts[UDP_CT_REPLIED] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { + [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static unsigned int udp_sysctl_table_users; static struct ctl_table_header *udp_sysctl_header; @@ -211,6 +257,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udp_timeout_nlattr_to_obj, + .obj_to_nlattr = udp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDP_MAX, + .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, + .nla_policy = udp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udp_sysctl_table_users, .ctl_table_header = &udp_sysctl_header, @@ -240,6 +295,15 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udp_timeout_nlattr_to_obj, + .obj_to_nlattr = udp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDP_MAX, + .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, + .nla_policy = udp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udp_sysctl_table_users, .ctl_table_header = &udp_sysctl_header, diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 0b32ccb1d515..e0606392cda0 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -156,6 +156,52 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int udplite_timeout_nlattr_to_obj(struct nlattr *tb[], void *data) +{ + unsigned int *timeouts = data; + + /* set default timeouts for UDPlite. */ + timeouts[UDPLITE_CT_UNREPLIED] = udplite_timeouts[UDPLITE_CT_UNREPLIED]; + timeouts[UDPLITE_CT_REPLIED] = udplite_timeouts[UDPLITE_CT_REPLIED]; + + if (tb[CTA_TIMEOUT_UDPLITE_UNREPLIED]) { + timeouts[UDPLITE_CT_UNREPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDPLITE_UNREPLIED])) * HZ; + } + if (tb[CTA_TIMEOUT_UDPLITE_REPLIED]) { + timeouts[UDPLITE_CT_REPLIED] = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDPLITE_REPLIED])) * HZ; + } + return 0; +} + +static int +udplite_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeouts = data; + + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDPLITE_UNREPLIED, + htonl(timeouts[UDPLITE_CT_UNREPLIED] / HZ)); + NLA_PUT_BE32(skb, CTA_TIMEOUT_UDPLITE_REPLIED, + htonl(timeouts[UDPLITE_CT_REPLIED] / HZ)); + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +udplite_timeout_nla_policy[CTA_TIMEOUT_UDPLITE_MAX+1] = { + [CTA_TIMEOUT_UDPLITE_UNREPLIED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_UDPLITE_REPLIED] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + #ifdef CONFIG_SYSCTL static unsigned int udplite_sysctl_table_users; static struct ctl_table_header *udplite_sysctl_header; @@ -196,6 +242,16 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udplite_timeout_nlattr_to_obj, + .obj_to_nlattr = udplite_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDPLITE_MAX, + .obj_size = sizeof(unsigned int) * + CTA_TIMEOUT_UDPLITE_MAX, + .nla_policy = udplite_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udplite_sysctl_table_users, .ctl_table_header = &udplite_sysctl_header, @@ -221,6 +277,16 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = udplite_timeout_nlattr_to_obj, + .obj_to_nlattr = udplite_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_UDPLITE_MAX, + .obj_size = sizeof(unsigned int) * + CTA_TIMEOUT_UDPLITE_MAX, + .nla_policy = udplite_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ #ifdef CONFIG_SYSCTL .ctl_table_users = &udplite_sysctl_table_users, .ctl_table_header = &udplite_sysctl_header, diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c new file mode 100644 index 000000000000..b860d5217189 --- /dev/null +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -0,0 +1,398 @@ +/* + * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2012 by Vyatta Inc. <http://www.vyatta.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation (or any later at your option). + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/rculist.h> +#include <linux/rculist_nulls.h> +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/security.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/netlink.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/slab.h> + +#include <linux/netfilter.h> +#include <net/netlink.h> +#include <net/sock.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_tuple.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("cttimeout: Extended Netfilter Connection Tracking timeout tuning"); + +struct ctnl_timeout { + struct list_head head; + struct rcu_head rcu_head; + atomic_t refcnt; + char name[CTNL_TIMEOUT_NAME_MAX]; + __u16 l3num; + __u8 l4num; + char data[0]; +}; + +static LIST_HEAD(cttimeout_list); + +static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { + [CTA_TIMEOUT_NAME] = { .type = NLA_NUL_STRING }, + [CTA_TIMEOUT_L3PROTO] = { .type = NLA_U16 }, + [CTA_TIMEOUT_L4PROTO] = { .type = NLA_U8 }, + [CTA_TIMEOUT_DATA] = { .type = NLA_NESTED }, +}; + +static int +ctnl_timeout_parse_policy(struct ctnl_timeout *timeout, + struct nf_conntrack_l4proto *l4proto, + const struct nlattr *attr) +{ + int ret = 0; + + if (likely(l4proto->ctnl_timeout.nlattr_to_obj)) { + struct nlattr *tb[l4proto->ctnl_timeout.nlattr_max+1]; + + nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, + attr, l4proto->ctnl_timeout.nla_policy); + + ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, &timeout->data); + } + return ret; +} + +static int +cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + __u16 l3num; + __u8 l4num; + struct nf_conntrack_l4proto *l4proto; + struct ctnl_timeout *timeout, *matching = NULL; + char *name; + int ret; + + if (!cda[CTA_TIMEOUT_NAME] || + !cda[CTA_TIMEOUT_L3PROTO] || + !cda[CTA_TIMEOUT_L4PROTO] || + !cda[CTA_TIMEOUT_DATA]) + return -EINVAL; + + name = nla_data(cda[CTA_TIMEOUT_NAME]); + l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); + l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); + + list_for_each_entry(timeout, &cttimeout_list, head) { + if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + if (nlh->nlmsg_flags & NLM_F_EXCL) + return -EEXIST; + + matching = timeout; + break; + } + + l4proto = __nf_ct_l4proto_find(l3num, l4num); + + /* This protocol is not supportted, skip. */ + if (l4proto->l4proto != l4num) + return -EOPNOTSUPP; + + if (matching) { + if (nlh->nlmsg_flags & NLM_F_REPLACE) { + /* You cannot replace one timeout policy by another of + * different kind, sorry. + */ + if (matching->l3num != l3num || + matching->l4num != l4num) + return -EINVAL; + + ret = ctnl_timeout_parse_policy(matching, l4proto, + cda[CTA_TIMEOUT_DATA]); + return ret; + } + return -EBUSY; + } + + timeout = kzalloc(sizeof(struct ctnl_timeout) + + l4proto->ctnl_timeout.obj_size, GFP_KERNEL); + if (timeout == NULL) + return -ENOMEM; + + ret = ctnl_timeout_parse_policy(timeout, l4proto, + cda[CTA_TIMEOUT_DATA]); + if (ret < 0) + goto err; + + strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME])); + timeout->l3num = l3num; + timeout->l4num = l4num; + atomic_set(&timeout->refcnt, 1); + list_add_tail_rcu(&timeout->head, &cttimeout_list); + + return 0; +err: + kfree(timeout); + return ret; +} + +static int +ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, + int event, struct ctnl_timeout *timeout) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0; + struct nf_conntrack_l4proto *l4proto; + + event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8; + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + NLA_PUT_STRING(skb, CTA_TIMEOUT_NAME, timeout->name); + NLA_PUT_BE16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)); + NLA_PUT_U8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4num); + NLA_PUT_BE32(skb, CTA_TIMEOUT_USE, + htonl(atomic_read(&timeout->refcnt))); + + l4proto = __nf_ct_l4proto_find(timeout->l3num, timeout->l4num); + + /* If the timeout object does not match the layer 4 protocol tracker, + * then skip dumping the data part since we don't know how to + * interpret it. This may happen for UPDlite, SCTP and DCCP since + * you can unload the module. + */ + if (timeout->l4num != l4proto->l4proto) + goto out; + + if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) { + struct nlattr *nest_parms; + int ret; + + nest_parms = nla_nest_start(skb, + CTA_TIMEOUT_DATA | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->data); + if (ret < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + } +out: + nlmsg_end(skb, nlh); + return skb->len; + +nlmsg_failure: +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ctnl_timeout *cur, *last; + + if (cb->args[2]) + return 0; + + last = (struct ctnl_timeout *)cb->args[1]; + if (cb->args[1]) + cb->args[1] = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(cur, &cttimeout_list, head) { + if (last && cur != last) + continue; + + if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + IPCTNL_MSG_TIMEOUT_NEW, cur) < 0) { + cb->args[1] = (unsigned long)cur; + break; + } + } + if (!cb->args[1]) + cb->args[2] = 1; + rcu_read_unlock(); + return skb->len; +} + +static int +cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + int ret = -ENOENT; + char *name; + struct ctnl_timeout *cur; + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnl_timeout_dump, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + if (!cda[CTA_TIMEOUT_NAME]) + return -EINVAL; + name = nla_data(cda[CTA_TIMEOUT_NAME]); + + list_for_each_entry(cur, &cttimeout_list, head) { + struct sk_buff *skb2; + + if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) { + ret = -ENOMEM; + break; + } + + ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + IPCTNL_MSG_TIMEOUT_NEW, cur); + if (ret <= 0) { + kfree_skb(skb2); + break; + } + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, + MSG_DONTWAIT); + if (ret > 0) + ret = 0; + + /* this avoids a loop in nfnetlink. */ + return ret == -EAGAIN ? -ENOBUFS : ret; + } + return ret; +} + +/* try to delete object, fail if it is still in use. */ +static int ctnl_timeout_try_del(struct ctnl_timeout *timeout) +{ + int ret = 0; + + /* we want to avoid races with nf_ct_timeout_find_get. */ + if (atomic_dec_and_test(&timeout->refcnt)) { + /* We are protected by nfnl mutex. */ + list_del_rcu(&timeout->head); + kfree_rcu(timeout, rcu_head); + } else { + /* still in use, restore reference counter. */ + atomic_inc(&timeout->refcnt); + ret = -EBUSY; + } + return ret; +} + +static int +cttimeout_del_timeout(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + char *name; + struct ctnl_timeout *cur; + int ret = -ENOENT; + + if (!cda[CTA_TIMEOUT_NAME]) { + list_for_each_entry(cur, &cttimeout_list, head) + ctnl_timeout_try_del(cur); + + return 0; + } + name = nla_data(cda[CTA_TIMEOUT_NAME]); + + list_for_each_entry(cur, &cttimeout_list, head) { + if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) + continue; + + ret = ctnl_timeout_try_del(cur); + if (ret < 0) + return ret; + + break; + } + return ret; +} + +static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = { + [IPCTNL_MSG_TIMEOUT_NEW] = { .call = cttimeout_new_timeout, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy }, + [IPCTNL_MSG_TIMEOUT_GET] = { .call = cttimeout_get_timeout, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy }, + [IPCTNL_MSG_TIMEOUT_DELETE] = { .call = cttimeout_del_timeout, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy }, +}; + +static const struct nfnetlink_subsystem cttimeout_subsys = { + .name = "conntrack_timeout", + .subsys_id = NFNL_SUBSYS_CTNETLINK_TIMEOUT, + .cb_count = IPCTNL_MSG_TIMEOUT_MAX, + .cb = cttimeout_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_TIMEOUT); + +static int __init cttimeout_init(void) +{ + int ret; + + ret = nfnetlink_subsys_register(&cttimeout_subsys); + if (ret < 0) { + pr_err("cttimeout_init: cannot register cttimeout with " + "nfnetlink.\n"); + goto err_out; + } + return 0; + +err_out: + return ret; +} + +static void __exit cttimeout_exit(void) +{ + struct ctnl_timeout *cur, *tmp; + + pr_info("cttimeout: unregistering from nfnetlink.\n"); + + nfnetlink_subsys_unregister(&cttimeout_subsys); + list_for_each_entry_safe(cur, tmp, &cttimeout_list, head) { + list_del_rcu(&cur->head); + /* We are sure that our objects have no clients at this point, + * it's safe to release them all without checking refcnt. + */ + kfree_rcu(cur, rcu_head); + } +} + +module_init(cttimeout_init); +module_exit(cttimeout_exit); -- cgit