diff options
Diffstat (limited to 'net/ipv4/netfilter')
31 files changed, 1655 insertions, 1165 deletions
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index c60fd5c4ea1e..e1d7f5fbc526 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -55,6 +55,18 @@ config IP_NF_CONNTRACK_MARK of packets, but this mark value is kept in the conntrack session instead of the individual packets. +config IP_NF_CONNTRACK_SECMARK + bool 'Connection tracking security mark support' + depends on IP_NF_CONNTRACK && NETWORK_SECMARK + help + This option enables security markings to be applied to + connections. Typically they are copied to connections from + packets using the CONNSECMARK target and copied back from + connections to packets with the same target, with the packets + being originally labeled via SECMARK. + + If unsure, say 'N'. + config IP_NF_CONNTRACK_EVENTS bool "Connection tracking events (EXPERIMENTAL)" depends on EXPERIMENTAL && IP_NF_CONNTRACK @@ -142,6 +154,8 @@ config IP_NF_TFTP config IP_NF_AMANDA tristate "Amanda backup protocol support" depends on IP_NF_CONNTRACK + select TEXTSEARCH + select TEXTSEARCH_KMP help If you are running the Amanda backup package <http://www.amanda.org/> on this machine or machines that will be MASQUERADED through this @@ -170,8 +184,8 @@ config IP_NF_PPTP Documentation/modules.txt. If unsure, say `N'. config IP_NF_H323 - tristate 'H.323 protocol support' - depends on IP_NF_CONNTRACK + tristate 'H.323 protocol support (EXPERIMENTAL)' + depends on IP_NF_CONNTRACK && EXPERIMENTAL help H.323 is a VoIP signalling protocol from ITU-T. As one of the most important VoIP protocols, it is widely used by voice hardware and @@ -181,14 +195,26 @@ config IP_NF_H323 With this module you can support H.323 on a connection tracking/NAT firewall. - This module supports RAS, Fast-start, H.245 tunnelling, RTP/RTCP - and T.120 based data and applications including audio, video, FAX, - chat, whiteboard, file transfer, etc. For more information, please - see http://nath323.sourceforge.net/. + This module supports RAS, Fast Start, H.245 Tunnelling, Call + Forwarding, RTP/RTCP and T.120 based audio, video, fax, chat, + whiteboard, file transfer, etc. For more information, please + visit http://nath323.sourceforge.net/. If you want to compile it as a module, say 'M' here and read Documentation/modules.txt. If unsure, say 'N'. +config IP_NF_SIP + tristate "SIP protocol support (EXPERIMENTAL)" + depends on IP_NF_CONNTRACK && EXPERIMENTAL + help + SIP is an application-layer control protocol that can establish, + modify, and terminate multimedia sessions (conferences) such as + Internet telephony calls. With the ip_conntrack_sip and + the ip_nat_sip modules you can support the protocol on a connection + tracking/NATing firewall. + + To compile it as a module, choose M here. If unsure, say Y. + config IP_NF_QUEUE tristate "IP Userspace queueing via NETLINK (OBSOLETE)" help @@ -345,7 +371,7 @@ config IP_NF_TARGET_LOG To compile it as a module, choose M here. If unsure, say N. config IP_NF_TARGET_ULOG - tristate "ULOG target support (OBSOLETE)" + tristate "ULOG target support" depends on IP_NF_IPTABLES ---help--- @@ -501,6 +527,12 @@ config IP_NF_NAT_H323 default IP_NF_NAT if IP_NF_H323=y default m if IP_NF_H323=m +config IP_NF_NAT_SIP + tristate + depends on IP_NF_IPTABLES!=n && IP_NF_CONNTRACK!=n && IP_NF_NAT!=n + default IP_NF_NAT if IP_NF_SIP=y + default m if IP_NF_SIP=m + # mangle + specific targets config IP_NF_MANGLE tristate "Packet mangling" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 461cb1eb5de7..3ded4a3af59c 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_IP_NF_AMANDA) += ip_conntrack_amanda.o obj-$(CONFIG_IP_NF_TFTP) += ip_conntrack_tftp.o obj-$(CONFIG_IP_NF_FTP) += ip_conntrack_ftp.o obj-$(CONFIG_IP_NF_IRC) += ip_conntrack_irc.o +obj-$(CONFIG_IP_NF_SIP) += ip_conntrack_sip.o obj-$(CONFIG_IP_NF_NETBIOS_NS) += ip_conntrack_netbios_ns.o # NAT helpers @@ -40,6 +41,7 @@ obj-$(CONFIG_IP_NF_NAT_AMANDA) += ip_nat_amanda.o obj-$(CONFIG_IP_NF_NAT_TFTP) += ip_nat_tftp.o obj-$(CONFIG_IP_NF_NAT_FTP) += ip_nat_ftp.o obj-$(CONFIG_IP_NF_NAT_IRC) += ip_nat_irc.o +obj-$(CONFIG_IP_NF_NAT_SIP) += ip_nat_sip.o # generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index c2d92f99a2b8..d0d19192026d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -948,7 +948,7 @@ static int do_add_counters(void __user *user, unsigned int len) write_lock_bh(&t->lock); private = t->private; - if (private->number != paddc->num_counters) { + if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } diff --git a/net/ipv4/netfilter/ip_conntrack_amanda.c b/net/ipv4/netfilter/ip_conntrack_amanda.c index a604b1ccfdaa..0a7bd7f04061 100644 --- a/net/ipv4/netfilter/ip_conntrack_amanda.c +++ b/net/ipv4/netfilter/ip_conntrack_amanda.c @@ -17,33 +17,29 @@ * this value. * */ - -#include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/netfilter.h> -#include <linux/ip.h> #include <linux/moduleparam.h> +#include <linux/textsearch.h> +#include <linux/skbuff.h> +#include <linux/in.h> +#include <linux/ip.h> #include <linux/udp.h> -#include <net/checksum.h> -#include <net/udp.h> +#include <linux/netfilter.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> #include <linux/netfilter_ipv4/ip_conntrack_amanda.h> static unsigned int master_timeout = 300; +static char *ts_algo = "kmp"; MODULE_AUTHOR("Brian J. Murrell <netfilter@interlinx.bc.ca>"); MODULE_DESCRIPTION("Amanda connection tracking module"); MODULE_LICENSE("GPL"); module_param(master_timeout, uint, 0600); MODULE_PARM_DESC(master_timeout, "timeout for the master connection"); - -static const char *conns[] = { "DATA ", "MESG ", "INDEX " }; - -/* This is slow, but it's simple. --RR */ -static char *amanda_buffer; -static DEFINE_SPINLOCK(amanda_buffer_lock); +module_param(ts_algo, charp, 0400); +MODULE_PARM_DESC(ts_algo, "textsearch algorithm to use (default kmp)"); unsigned int (*ip_nat_amanda_hook)(struct sk_buff **pskb, enum ip_conntrack_info ctinfo, @@ -52,12 +48,48 @@ unsigned int (*ip_nat_amanda_hook)(struct sk_buff **pskb, struct ip_conntrack_expect *exp); EXPORT_SYMBOL_GPL(ip_nat_amanda_hook); +enum amanda_strings { + SEARCH_CONNECT, + SEARCH_NEWLINE, + SEARCH_DATA, + SEARCH_MESG, + SEARCH_INDEX, +}; + +static struct { + char *string; + size_t len; + struct ts_config *ts; +} search[] = { + [SEARCH_CONNECT] = { + .string = "CONNECT ", + .len = 8, + }, + [SEARCH_NEWLINE] = { + .string = "\n", + .len = 1, + }, + [SEARCH_DATA] = { + .string = "DATA ", + .len = 5, + }, + [SEARCH_MESG] = { + .string = "MESG ", + .len = 5, + }, + [SEARCH_INDEX] = { + .string = "INDEX ", + .len = 6, + }, +}; + static int help(struct sk_buff **pskb, struct ip_conntrack *ct, enum ip_conntrack_info ctinfo) { + struct ts_state ts; struct ip_conntrack_expect *exp; - char *data, *data_limit, *tmp; - unsigned int dataoff, i; + unsigned int dataoff, start, stop, off, i; + char pbuf[sizeof("65535")], *tmp; u_int16_t port, len; int ret = NF_ACCEPT; @@ -77,29 +109,34 @@ static int help(struct sk_buff **pskb, return NF_ACCEPT; } - spin_lock_bh(&amanda_buffer_lock); - skb_copy_bits(*pskb, dataoff, amanda_buffer, (*pskb)->len - dataoff); - data = amanda_buffer; - data_limit = amanda_buffer + (*pskb)->len - dataoff; - *data_limit = '\0'; - - /* Search for the CONNECT string */ - data = strstr(data, "CONNECT "); - if (!data) + memset(&ts, 0, sizeof(ts)); + start = skb_find_text(*pskb, dataoff, (*pskb)->len, + search[SEARCH_CONNECT].ts, &ts); + if (start == UINT_MAX) goto out; - data += strlen("CONNECT "); + start += dataoff + search[SEARCH_CONNECT].len; - /* Only search first line. */ - if ((tmp = strchr(data, '\n'))) - *tmp = '\0'; + memset(&ts, 0, sizeof(ts)); + stop = skb_find_text(*pskb, start, (*pskb)->len, + search[SEARCH_NEWLINE].ts, &ts); + if (stop == UINT_MAX) + goto out; + stop += start; - for (i = 0; i < ARRAY_SIZE(conns); i++) { - char *match = strstr(data, conns[i]); - if (!match) + for (i = SEARCH_DATA; i <= SEARCH_INDEX; i++) { + memset(&ts, 0, sizeof(ts)); + off = skb_find_text(*pskb, start, stop, search[i].ts, &ts); + if (off == UINT_MAX) continue; - tmp = data = match + strlen(conns[i]); - port = simple_strtoul(data, &data, 10); - len = data - tmp; + off += start + search[i].len; + + len = min_t(unsigned int, sizeof(pbuf) - 1, stop - off); + if (skb_copy_bits(*pskb, off, pbuf, len)) + break; + pbuf[len] = '\0'; + + port = simple_strtoul(pbuf, &tmp, 10); + len = tmp - pbuf; if (port == 0 || len > 5) break; @@ -125,8 +162,7 @@ static int help(struct sk_buff **pskb, exp->mask.dst.u.tcp.port = 0xFFFF; if (ip_nat_amanda_hook) - ret = ip_nat_amanda_hook(pskb, ctinfo, - tmp - amanda_buffer, + ret = ip_nat_amanda_hook(pskb, ctinfo, off - dataoff, len, exp); else if (ip_conntrack_expect_related(exp) != 0) ret = NF_DROP; @@ -134,12 +170,11 @@ static int help(struct sk_buff **pskb, } out: - spin_unlock_bh(&amanda_buffer_lock); return ret; } static struct ip_conntrack_helper amanda_helper = { - .max_expected = ARRAY_SIZE(conns), + .max_expected = 3, .timeout = 180, .me = THIS_MODULE, .help = help, @@ -155,26 +190,36 @@ static struct ip_conntrack_helper amanda_helper = { static void __exit ip_conntrack_amanda_fini(void) { + int i; + ip_conntrack_helper_unregister(&amanda_helper); - kfree(amanda_buffer); + for (i = 0; i < ARRAY_SIZE(search); i++) + textsearch_destroy(search[i].ts); } static int __init ip_conntrack_amanda_init(void) { - int ret; - - amanda_buffer = kmalloc(65536, GFP_KERNEL); - if (!amanda_buffer) - return -ENOMEM; - - ret = ip_conntrack_helper_register(&amanda_helper); - if (ret < 0) { - kfree(amanda_buffer); - return ret; + int ret, i; + + ret = -ENOMEM; + for (i = 0; i < ARRAY_SIZE(search); i++) { + search[i].ts = textsearch_prepare(ts_algo, search[i].string, + search[i].len, + GFP_KERNEL, TS_AUTOLOAD); + if (search[i].ts == NULL) + goto err; } + ret = ip_conntrack_helper_register(&amanda_helper); + if (ret < 0) + goto err; return 0; - +err: + for (; i >= 0; i--) { + if (search[i].ts) + textsearch_destroy(search[i].ts); + } + return ret; } module_init(ip_conntrack_amanda_init); diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c index 979a2eac6f00..7e4cf9a4d15f 100644 --- a/net/ipv4/netfilter/ip_conntrack_core.c +++ b/net/ipv4/netfilter/ip_conntrack_core.c @@ -724,6 +724,9 @@ init_conntrack(struct ip_conntrack_tuple *tuple, /* this is ugly, but there is no other place where to put it */ conntrack->nat.masq_index = exp->master->nat.masq_index; #endif +#ifdef CONFIG_IP_NF_CONNTRACK_SECMARK + conntrack->secmark = exp->master->secmark; +#endif nf_conntrack_get(&conntrack->master->ct_general); CONNTRACK_STAT_INC(expect_new); } else { @@ -1130,6 +1133,12 @@ void __ip_ct_refresh_acct(struct ip_conntrack *ct, write_lock_bh(&ip_conntrack_lock); + /* Only update if this is not a fixed timeout */ + if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) { + write_unlock_bh(&ip_conntrack_lock); + return; + } + /* If not in hash table, timer will not be active yet */ if (!is_confirmed(ct)) { ct->timeout.expires = extra_jiffies; @@ -1318,6 +1327,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) .tuple.dst.u.tcp.port; sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL] .tuple.dst.ip; + memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); DEBUGP("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n", NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port)); diff --git a/net/ipv4/netfilter/ip_conntrack_ftp.c b/net/ipv4/netfilter/ip_conntrack_ftp.c index 3e542bf28a9d..4dcf526c3944 100644 --- a/net/ipv4/netfilter/ip_conntrack_ftp.c +++ b/net/ipv4/netfilter/ip_conntrack_ftp.c @@ -56,37 +56,48 @@ static int try_eprt(const char *, size_t, u_int32_t [], char); static int try_epsv_response(const char *, size_t, u_int32_t [], char); static const struct ftp_search { - enum ip_conntrack_dir dir; const char *pattern; size_t plen; char skip; char term; enum ip_ct_ftp_type ftptype; int (*getnum)(const char *, size_t, u_int32_t[], char); -} search[] = { - { - IP_CT_DIR_ORIGINAL, - "PORT", sizeof("PORT") - 1, ' ', '\r', - IP_CT_FTP_PORT, - try_rfc959, +} search[IP_CT_DIR_MAX][2] = { + [IP_CT_DIR_ORIGINAL] = { + { + .pattern = "PORT", + .plen = sizeof("PORT") - 1, + .skip = ' ', + .term = '\r', + .ftptype = IP_CT_FTP_PORT, + .getnum = try_rfc959, + }, + { + .pattern = "EPRT", + .plen = sizeof("EPRT") - 1, + .skip = ' ', + .term = '\r', + .ftptype = IP_CT_FTP_EPRT, + .getnum = try_eprt, + }, }, - { - IP_CT_DIR_REPLY, - "227 ", sizeof("227 ") - 1, '(', ')', - IP_CT_FTP_PASV, - try_rfc959, - }, - { - IP_CT_DIR_ORIGINAL, - "EPRT", sizeof("EPRT") - 1, ' ', '\r', - IP_CT_FTP_EPRT, - try_eprt, - }, - { - IP_CT_DIR_REPLY, - "229 ", sizeof("229 ") - 1, '(', ')', - IP_CT_FTP_EPSV, - try_epsv_response, + [IP_CT_DIR_REPLY] = { + { + .pattern = "227 ", + .plen = sizeof("227 ") - 1, + .skip = '(', + .term = ')', + .ftptype = IP_CT_FTP_PASV, + .getnum = try_rfc959, + }, + { + .pattern = "229 ", + .plen = sizeof("229 ") - 1, + .skip = '(', + .term = ')', + .ftptype = IP_CT_FTP_EPSV, + .getnum = try_epsv_response, + }, }, }; @@ -346,17 +357,15 @@ static int help(struct sk_buff **pskb, array[2] = (ntohl(ct->tuplehash[dir].tuple.src.ip) >> 8) & 0xFF; array[3] = ntohl(ct->tuplehash[dir].tuple.src.ip) & 0xFF; - for (i = 0; i < ARRAY_SIZE(search); i++) { - if (search[i].dir != dir) continue; - + for (i = 0; i < ARRAY_SIZE(search[dir]); i++) { found = find_pattern(fb_ptr, (*pskb)->len - dataoff, - search[i].pattern, - search[i].plen, - search[i].skip, - search[i].term, + search[dir][i].pattern, + search[dir][i].plen, + search[dir][i].skip, + search[dir][i].term, &matchoff, &matchlen, array, - search[i].getnum); + search[dir][i].getnum); if (found) break; } if (found == -1) { @@ -366,7 +375,7 @@ static int help(struct sk_buff **pskb, this case. */ if (net_ratelimit()) printk("conntrack_ftp: partial %s %u+%u\n", - search[i].pattern, + search[dir][i].pattern, ntohl(th->seq), datalen); ret = NF_DROP; goto out; @@ -426,7 +435,7 @@ static int help(struct sk_buff **pskb, /* Now, NAT might want to mangle the packet, and register the * (possibly changed) expectation itself. */ if (ip_nat_ftp_hook) - ret = ip_nat_ftp_hook(pskb, ctinfo, search[i].ftptype, + ret = ip_nat_ftp_hook(pskb, ctinfo, search[dir][i].ftptype, matchoff, matchlen, exp, &seq); else { /* Can't expect this? Best to drop packet now. */ diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323.c b/net/ipv4/netfilter/ip_conntrack_helper_h323.c index 2c2fb700d835..0665674218c6 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323.c @@ -22,6 +22,8 @@ #include <linux/netfilter_ipv4/ip_conntrack_tuple.h> #include <linux/netfilter_ipv4/ip_conntrack_h323.h> #include <linux/moduleparam.h> +#include <linux/ctype.h> +#include <linux/inet.h> #if 0 #define DEBUGP printk @@ -38,6 +40,12 @@ static int gkrouted_only = 1; module_param(gkrouted_only, int, 0600); MODULE_PARM_DESC(gkrouted_only, "only accept calls from gatekeeper"); +static int callforward_filter = 1; +module_param(callforward_filter, bool, 0600); +MODULE_PARM_DESC(callforward_filter, "only create call forwarding expectations " + "if both endpoints are on different sides " + "(determined by routing information)"); + /* Hooks for NAT */ int (*set_h245_addr_hook) (struct sk_buff ** pskb, unsigned char **data, int dataoff, @@ -77,6 +85,12 @@ int (*nat_h245_hook) (struct sk_buff ** pskb, unsigned char **data, int dataoff, TransportAddress * addr, u_int16_t port, struct ip_conntrack_expect * exp); +int (*nat_callforwarding_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); int (*nat_q931_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, enum ip_conntrack_info ctinfo, @@ -162,6 +176,8 @@ static int get_tpkt_data(struct sk_buff **pskb, struct ip_conntrack *ct, /* Validate TPKT length */ tpktlen = tpkt[2] * 256 + tpkt[3]; + if (tpktlen < 4) + goto clear_out; if (tpktlen > tcpdatalen) { if (tcpdatalen == 4) { /* Separate TPKT header */ /* Netmeeting sends TPKT header and data separately */ @@ -681,6 +697,92 @@ static int expect_h245(struct sk_buff **pskb, struct ip_conntrack *ct, return ret; } +/* Forwarding declaration */ +void ip_conntrack_q931_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this); + +/****************************************************************************/ +static int expect_callforwarding(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp = NULL; + + /* Read alternativeAddress */ + if (!get_h225_addr(*data, addr, &ip, &port) || port == 0) + return 0; + + /* If the calling party is on the same side of the forward-to party, + * we don't need to track the second call */ + if (callforward_filter) { + struct rtable *rt1, *rt2; + struct flowi fl1 = { + .fl4_dst = ip, + }; + struct flowi fl2 = { + .fl4_dst = ct->tuplehash[!dir].tuple.src.ip, + }; + + if (ip_route_output_key(&rt1, &fl1) == 0) { + if (ip_route_output_key(&rt2, &fl2) == 0) { + if (rt1->rt_gateway == rt2->rt_gateway && + rt1->u.dst.dev == rt2->u.dst.dev) + ret = 1; + dst_release(&rt2->u.dst); + } + dst_release(&rt1->u.dst); + } + if (ret) { + DEBUGP("ip_ct_q931: Call Forwarding not tracked\n"); + return 0; + } + } + + /* Create expect for the second call leg */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_TCP; + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = 0; + + if (ct->tuplehash[dir].tuple.src.ip != + ct->tuplehash[!dir].tuple.dst.ip && nat_callforwarding_hook) { + /* Need NAT */ + ret = nat_callforwarding_hook(pskb, ct, ctinfo, data, dataoff, + addr, port, exp); + } else { /* Conntrack only */ + exp->expectfn = ip_conntrack_q931_expect; + + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_q931: expect Call Forwarding " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + } else + ret = -1; + } + + ip_conntrack_expect_put(exp); + + return ret; +} + /****************************************************************************/ static int process_setup(struct sk_buff **pskb, struct ip_conntrack *ct, enum ip_conntrack_info ctinfo, @@ -876,6 +978,15 @@ static int process_facility(struct sk_buff **pskb, struct ip_conntrack *ct, DEBUGP("ip_ct_q931: Facility\n"); + if (facility->reason.choice == eFacilityReason_callForwarded) { + if (facility->options & eFacility_UUIE_alternativeAddress) + return expect_callforwarding(pskb, ct, ctinfo, data, + dataoff, + &facility-> + alternativeAddress); + return 0; + } + if (facility->options & eFacility_UUIE_h245Address) { ret = expect_h245(pskb, ct, ctinfo, data, dataoff, &facility->h245Address); @@ -1675,7 +1786,6 @@ static int __init init(void) fini(); return ret; } - DEBUGP("ip_ct_h323: init success\n"); return 0; } @@ -1694,6 +1804,7 @@ EXPORT_SYMBOL_GPL(set_ras_addr_hook); EXPORT_SYMBOL_GPL(nat_rtp_rtcp_hook); EXPORT_SYMBOL_GPL(nat_t120_hook); EXPORT_SYMBOL_GPL(nat_h245_hook); +EXPORT_SYMBOL_GPL(nat_callforwarding_hook); EXPORT_SYMBOL_GPL(nat_q931_hook); MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>"); diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c index 48078002e450..26dfecadb335 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c @@ -2,7 +2,7 @@ * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323 * conntrack/NAT module. * - * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@hotmail.com> + * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net> * * This source code is licensed under General Public License version 2. * @@ -528,14 +528,15 @@ int decode_seq(bitstr_t * bs, field_t * f, char *base, int level) /* Decode */ if ((err = (Decoders[son->type]) (bs, son, base, - level + 1)) > - H323_ERROR_STOP) + level + 1)) < + H323_ERROR_NONE) return err; bs->cur = beg + len; bs->bit = 0; } else if ((err = (Decoders[son->type]) (bs, son, base, - level + 1))) + level + 1)) < + H323_ERROR_NONE) return err; } @@ -554,7 +555,7 @@ int decode_seq(bitstr_t * bs, field_t * f, char *base, int level) /* Decode the extension components */ for (opt = 0; opt < bmp2_len; opt++, i++, son++) { - if (son->attr & STOP) { + if (i < f->ub && son->attr & STOP) { PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); return H323_ERROR_STOP; @@ -584,8 +585,8 @@ int decode_seq(bitstr_t * bs, field_t * f, char *base, int level) beg = bs->cur; if ((err = (Decoders[son->type]) (bs, son, base, - level + 1)) > - H323_ERROR_STOP) + level + 1)) < + H323_ERROR_NONE) return err; bs->cur = beg + len; @@ -660,18 +661,20 @@ int decode_seqof(bitstr_t * bs, field_t * f, char *base, int level) i < effective_count ? base : NULL, - level + 1)) > - H323_ERROR_STOP) + level + 1)) < + H323_ERROR_NONE) return err; bs->cur = beg + len; bs->bit = 0; } else - if ((err = (Decoders[son->type]) (bs, son, - i < effective_count ? - base : NULL, - level + 1))) - return err; + if ((err = (Decoders[son->type]) (bs, son, + i < + effective_count ? + base : NULL, + level + 1)) < + H323_ERROR_NONE) + return err; if (base) base += son->offset; @@ -703,6 +706,10 @@ int decode_choice(bitstr_t * bs, field_t * f, char *base, int level) type = get_bits(bs, f->sz); } + /* Write Type */ + if (base) + *(unsigned *) base = type; + /* Check Range */ if (type >= f->ub) { /* Newer version? */ BYTE_ALIGN(bs); @@ -712,10 +719,6 @@ int decode_choice(bitstr_t * bs, field_t * f, char *base, int level) return H323_ERROR_NONE; } - /* Write Type */ - if (base) - *(unsigned *) base = type; - /* Transfer to son level */ son = &f->fields[type]; if (son->attr & STOP) { @@ -735,13 +738,14 @@ int decode_choice(bitstr_t * bs, field_t * f, char *base, int level) } beg = bs->cur; - if ((err = (Decoders[son->type]) (bs, son, base, level + 1)) > - H323_ERROR_STOP) + if ((err = (Decoders[son->type]) (bs, son, base, level + 1)) < + H323_ERROR_NONE) return err; bs->cur = beg + len; bs->bit = 0; - } else if ((err = (Decoders[son->type]) (bs, son, base, level + 1))) + } else if ((err = (Decoders[son->type]) (bs, son, base, level + 1)) < + H323_ERROR_NONE) return err; return H323_ERROR_NONE; diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c b/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c index 022c47b9f6c9..4b359618bedd 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c @@ -1,4 +1,4 @@ -/* Generated by Jing Min Zhao's ASN.1 parser, Mar 15 2006 +/* Generated by Jing Min Zhao's ASN.1 parser, Apr 20 2006 * * Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net> * @@ -1069,8 +1069,8 @@ static field_t _Facility_UUIE_fastStart[] = { /* SEQUENCE OF */ static field_t _Facility_UUIE[] = { /* SEQUENCE */ {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, - {FNAME("alternativeAddress") CHOICE, 3, 7, 7, SKIP | EXT | OPT, 0, - _TransportAddress}, + {FNAME("alternativeAddress") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Facility_UUIE, alternativeAddress), _TransportAddress}, {FNAME("alternativeAliasAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, _Facility_UUIE_alternativeAliasAddress}, {FNAME("conferenceID") OCTSTR, FIXD, 16, 0, SKIP | OPT, 0, NULL}, diff --git a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c index 7d3ba4302e9e..8ccfe17bb253 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c @@ -469,8 +469,8 @@ pptp_inbound_pkt(struct sk_buff **pskb, DEBUGP("%s but no session\n", pptp_msg_name[msg]); break; } - if (info->sstate != PPTP_CALL_IN_REP - && info->sstate != PPTP_CALL_IN_CONF) { + if (info->cstate != PPTP_CALL_IN_REP + && info->cstate != PPTP_CALL_IN_CONF) { DEBUGP("%s but never sent IN_CALL_REPLY\n", pptp_msg_name[msg]); break; diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index 01bd7cab9367..33891bb1fde4 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -399,38 +399,54 @@ nfattr_failure: static int ctnetlink_done(struct netlink_callback *cb) { DEBUGP("entered %s\n", __FUNCTION__); + if (cb->args[1]) + ip_conntrack_put((struct ip_conntrack *)cb->args[1]); return 0; } static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { - struct ip_conntrack *ct = NULL; + struct ip_conntrack *ct, *last; struct ip_conntrack_tuple_hash *h; struct list_head *i; - u_int32_t *id = (u_int32_t *) &cb->args[1]; DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, cb->args[0], *id); read_lock_bh(&ip_conntrack_lock); - for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) { + for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++) { +restart: + last = (struct ip_conntrack *)cb->args[1]; list_for_each_prev(i, &ip_conntrack_hash[cb->args[0]]) { h = (struct ip_conntrack_tuple_hash *) i; if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = tuplehash_to_ctrack(h); - if (ct->id <= *id) - continue; + if (last != NULL) { + if (ct == last) { + ip_conntrack_put(last); + cb->args[1] = 0; + last = NULL; + } else + continue; + } if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, IPCTNL_MSG_CT_NEW, - 1, ct) < 0) + 1, ct) < 0) { + nf_conntrack_get(&ct->ct_general); + cb->args[1] = (unsigned long)ct; goto out; - *id = ct->id; + } + } + if (last != NULL) { + ip_conntrack_put(last); + cb->args[1] = 0; + goto restart; } } -out: +out: read_unlock_bh(&ip_conntrack_lock); DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); @@ -629,7 +645,7 @@ static const size_t cta_min_nat[CTA_NAT_MAX] = { }; static inline int -ctnetlink_parse_nat(struct nfattr *cda[], +ctnetlink_parse_nat(struct nfattr *nat, const struct ip_conntrack *ct, struct ip_nat_range *range) { struct nfattr *tb[CTA_NAT_MAX]; @@ -639,7 +655,7 @@ ctnetlink_parse_nat(struct nfattr *cda[], memset(range, 0, sizeof(*range)); - nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]); + nfattr_parse_nested(tb, CTA_NAT_MAX, nat); if (nfattr_bad_size(tb, CTA_NAT_MAX, cta_min_nat)) return -EINVAL; @@ -854,39 +870,30 @@ ctnetlink_change_status(struct ip_conntrack *ct, struct nfattr *cda[]) /* ASSURED bit can only be set */ return -EINVAL; - if (cda[CTA_NAT-1]) { + if (cda[CTA_NAT_SRC-1] || cda[CTA_NAT_DST-1]) { #ifndef CONFIG_IP_NF_NAT_NEEDED return -EINVAL; #else - unsigned int hooknum; struct ip_nat_range range; - if (ctnetlink_parse_nat(cda, ct, &range) < 0) - return -EINVAL; - - DEBUGP("NAT: %u.%u.%u.%u-%u.%u.%u.%u:%u-%u\n", - NIPQUAD(range.min_ip), NIPQUAD(range.max_ip), - htons(range.min.all), htons(range.max.all)); - - /* This is tricky but it works. ip_nat_setup_info needs the - * hook number as parameter, so let's do the correct - * conversion and run away */ - if (status & IPS_SRC_NAT_DONE) - hooknum = NF_IP_POST_ROUTING; /* IP_NAT_MANIP_SRC */ - else if (status & IPS_DST_NAT_DONE) - hooknum = NF_IP_PRE_ROUTING; /* IP_NAT_MANIP_DST */ - else - return -EINVAL; /* Missing NAT flags */ - - DEBUGP("NAT status: %lu\n", - status & (IPS_NAT_MASK | IPS_NAT_DONE_MASK)); - - if (ip_nat_initialized(ct, HOOK2MANIP(hooknum))) - return -EEXIST; - ip_nat_setup_info(ct, &range, hooknum); - - DEBUGP("NAT status after setup_info: %lu\n", - ct->status & (IPS_NAT_MASK | IPS_NAT_DONE_MASK)); + if (cda[CTA_NAT_DST-1]) { + if (ctnetlink_parse_nat(cda[CTA_NAT_DST-1], ct, + &range) < 0) + return -EINVAL; + if (ip_nat_initialized(ct, + HOOK2MANIP(NF_IP_PRE_ROUTING))) + return -EEXIST; + ip_nat_setup_info(ct, &range, NF_IP_PRE_ROUTING); + } + if (cda[CTA_NAT_SRC-1]) { + if (ctnetlink_parse_nat(cda[CTA_NAT_SRC-1], ct, + &range) < 0) + return -EINVAL; + if (ip_nat_initialized(ct, + HOOK2MANIP(NF_IP_POST_ROUTING))) + return -EEXIST; + ip_nat_setup_info(ct, &range, NF_IP_POST_ROUTING); + } #endif } @@ -1106,7 +1113,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, /* implicit 'else' */ /* we only allow nat config for new conntracks */ - if (cda[CTA_NAT-1]) { + if (cda[CTA_NAT_SRC-1] || cda[CTA_NAT_DST-1]) { err = -EINVAL; goto out_unlock; } diff --git a/net/ipv4/netfilter/ip_conntrack_proto_gre.c b/net/ipv4/netfilter/ip_conntrack_proto_gre.c index 56794797d55b..21ee124c0463 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_gre.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_gre.c @@ -77,10 +77,10 @@ static inline int gre_key_cmpfn(const struct ip_ct_gre_keymap *km, } /* look up the source key for a given tuple */ -static u_int32_t gre_keymap_lookup(struct ip_conntrack_tuple *t) +static __be16 gre_keymap_lookup(struct ip_conntrack_tuple *t) { struct ip_ct_gre_keymap *km; - u_int32_t key = 0; + __be16 key = 0; read_lock_bh(&ip_ct_gre_lock); km = LIST_FIND(&gre_keymap_list, gre_key_cmpfn, @@ -190,7 +190,7 @@ static int gre_pkt_to_tuple(const struct sk_buff *skb, struct ip_conntrack_tuple *tuple) { struct gre_hdr_pptp _pgrehdr, *pgrehdr; - u_int32_t srckey; + __be16 srckey; struct gre_hdr _grehdr, *grehdr; /* first only delinearize old RFC1701 GRE header */ diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c index d8b14a9010a6..23f1c504586d 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c @@ -224,7 +224,7 @@ icmp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, } /* See ip_conntrack_proto_tcp.c */ - if (hooknum == NF_IP_PRE_ROUTING && + if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && nf_ip_checksum(skb, hooknum, skb->nh.iph->ihl * 4, 0)) { if (LOG_INVALID(IPPROTO_ICMP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, diff --git a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c index 5259abd0fb42..0416073c5600 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c @@ -235,12 +235,15 @@ static int do_basic_checks(struct ip_conntrack *conntrack, flag = 1; } - /* Cookie Ack/Echo chunks not the first OR - Init / Init Ack / Shutdown compl chunks not the only chunks */ - if ((sch->type == SCTP_CID_COOKIE_ACK + /* + * Cookie Ack/Echo chunks not the first OR + * Init / Init Ack / Shutdown compl chunks not the only chunks + * OR zero-length. + */ + if (((sch->type == SCTP_CID_COOKIE_ACK || sch->type == SCTP_CID_COOKIE_ECHO || flag) - && count !=0 ) { + && count !=0) || !sch->length) { DEBUGP("Basic checks failed\n"); return 1; } diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index 062b252b58ad..c5c2ce5cdeb8 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -870,7 +870,7 @@ static int tcp_error(struct sk_buff *skb, * and moreover root might send raw packets. */ /* FIXME: Source route IP option packets --RR */ - if (hooknum == NF_IP_PRE_ROUTING && + if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && nf_ip_checksum(skb, hooknum, iph->ihl * 4, IPPROTO_TCP)) { if (LOG_INVALID(IPPROTO_TCP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, diff --git a/net/ipv4/netfilter/ip_conntrack_proto_udp.c b/net/ipv4/netfilter/ip_conntrack_proto_udp.c index 70899868783b..9b2c16b4d2ff 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_udp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_udp.c @@ -120,7 +120,7 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, * because the semantic of CHECKSUM_HW is different there * and moreover root might send raw packets. * FIXME: Source route IP option packets --RR */ - if (hooknum == NF_IP_PRE_ROUTING && + if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && nf_ip_checksum(skb, hooknum, iph->ihl * 4, IPPROTO_UDP)) { if (LOG_INVALID(IPPROTO_UDP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, diff --git a/net/ipv4/netfilter/ip_conntrack_sip.c b/net/ipv4/netfilter/ip_conntrack_sip.c new file mode 100644 index 000000000000..fc87ce0da40d --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_sip.c @@ -0,0 +1,471 @@ +/* SIP extension for IP connection tracking. + * + * (C) 2005 by Christian Hentschel <chentschel@arnet.com.ar> + * based on RR's ip_conntrack_ftp.c and other modules. + * + * 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. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/skbuff.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/udp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv4/ip_conntrack_helper.h> +#include <linux/netfilter_ipv4/ip_conntrack_sip.h> + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Christian Hentschel <chentschel@arnet.com.ar>"); +MODULE_DESCRIPTION("SIP connection tracking helper"); + +#define MAX_PORTS 8 +static unsigned short ports[MAX_PORTS]; +static int ports_c; +module_param_array(ports, ushort, &ports_c, 0400); +MODULE_PARM_DESC(ports, "port numbers of sip servers"); + +static unsigned int sip_timeout = SIP_TIMEOUT; +module_param(sip_timeout, uint, 0600); +MODULE_PARM_DESC(sip_timeout, "timeout for the master SIP session"); + +unsigned int (*ip_nat_sip_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack *ct, + const char **dptr); +EXPORT_SYMBOL_GPL(ip_nat_sip_hook); + +unsigned int (*ip_nat_sdp_hook)(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack_expect *exp, + const char *dptr); +EXPORT_SYMBOL_GPL(ip_nat_sdp_hook); + +int ct_sip_get_info(const char *dptr, size_t dlen, + unsigned int *matchoff, + unsigned int *matchlen, + struct sip_header_nfo *hnfo); +EXPORT_SYMBOL_GPL(ct_sip_get_info); + + +static int digits_len(const char *dptr, const char *limit, int *shift); +static int epaddr_len(const char *dptr, const char *limit, int *shift); +static int skp_digits_len(const char *dptr, const char *limit, int *shift); +static int skp_epaddr_len(const char *dptr, const char *limit, int *shift); + +struct sip_header_nfo ct_sip_hdrs[] = { + { /* Via header */ + .lname = "Via:", + .lnlen = sizeof("Via:") - 1, + .sname = "\r\nv:", + .snlen = sizeof("\r\nv:") - 1, /* rfc3261 "\r\n" */ + .ln_str = "UDP ", + .ln_strlen = sizeof("UDP ") - 1, + .match_len = epaddr_len, + }, + { /* Contact header */ + .lname = "Contact:", + .lnlen = sizeof("Contact:") - 1, + .sname = "\r\nm:", + .snlen = sizeof("\r\nm:") - 1, + .ln_str = "sip:", + .ln_strlen = sizeof("sip:") - 1, + .match_len = skp_epaddr_len + }, + { /* Content length header */ + .lname = "Content-Length:", + .lnlen = sizeof("Content-Length:") - 1, + .sname = "\r\nl:", + .snlen = sizeof("\r\nl:") - 1, + .ln_str = ":", + .ln_strlen = sizeof(":") - 1, + .match_len = skp_digits_len + }, + { /* SDP media info */ + .lname = "\nm=", + .lnlen = sizeof("\nm=") - 1, + .sname = "\rm=", + .snlen = sizeof("\rm=") - 1, + .ln_str = "audio ", + .ln_strlen = sizeof("audio ") - 1, + .match_len = digits_len + }, + { /* SDP owner address*/ + .lname = "\no=", + .lnlen = sizeof("\no=") - 1, + .sname = "\ro=", + .snlen = sizeof("\ro=") - 1, + .ln_str = "IN IP4 ", + .ln_strlen = sizeof("IN IP4 ") - 1, + .match_len = epaddr_len + }, + { /* SDP connection info */ + .lname = "\nc=", + .lnlen = sizeof("\nc=") - 1, + .sname = "\rc=", + .snlen = sizeof("\rc=") - 1, + .ln_str = "IN IP4 ", + .ln_strlen = sizeof("IN IP4 ") - 1, + .match_len = epaddr_len + }, + { /* Requests headers */ + .lname = "sip:", + .lnlen = sizeof("sip:") - 1, + .sname = "sip:", + .snlen = sizeof("sip:") - 1, /* yes, i know.. ;) */ + .ln_str = "@", + .ln_strlen = sizeof("@") - 1, + .match_len = epaddr_len + }, + { /* SDP version header */ + .lname = "\nv=", + .lnlen = sizeof("\nv=") - 1, + .sname = "\rv=", + .snlen = sizeof("\rv=") - 1, + .ln_str = "=", + .ln_strlen = sizeof("=") - 1, + .match_len = digits_len + } +}; +EXPORT_SYMBOL_GPL(ct_sip_hdrs); + +/* get line lenght until first CR or LF seen. */ +int ct_sip_lnlen(const char *line, const char *limit) +{ + const char *k = line; + + while ((line <= limit) && (*line == '\r' || *line == '\n')) + line++; + + while (line <= limit) { + if (*line == '\r' || *line == '\n') + break; + line++; + } + return line - k; +} +EXPORT_SYMBOL_GPL(ct_sip_lnlen); + +/* Linear string search, case sensitive. */ +const char *ct_sip_search(const char *needle, const char *haystack, + size_t needle_len, size_t haystack_len) +{ + const char *limit = haystack + (haystack_len - needle_len); + + while (haystack <= limit) { + if (memcmp(haystack, needle, needle_len) == 0) + return haystack; + haystack++; + } + return NULL; +} +EXPORT_SYMBOL_GPL(ct_sip_search); + +static int digits_len(const char *dptr, const char *limit, int *shift) +{ + int len = 0; + while (dptr <= limit && isdigit(*dptr)) { + dptr++; + len++; + } + return len; +} + +/* get digits lenght, skiping blank spaces. */ +static int skp_digits_len(const char *dptr, const char *limit, int *shift) +{ + for (; dptr <= limit && *dptr == ' '; dptr++) + (*shift)++; + + return digits_len(dptr, limit, shift); +} + +/* Simple ipaddr parser.. */ +static int parse_ipaddr(const char *cp, const char **endp, + u_int32_t *ipaddr, const char *limit) +{ + unsigned long int val; + int i, digit = 0; + + for (i = 0, *ipaddr = 0; cp <= limit && i < 4; i++) { + digit = 0; + if (!isdigit(*cp)) + break; + + val = simple_strtoul(cp, (char **)&cp, 10); + if (val > 0xFF) + return -1; + + ((u_int8_t *)ipaddr)[i] = val; + digit = 1; + + if (*cp != '.') + break; + cp++; + } + if (!digit) + return -1; + + if (endp) + *endp = cp; + + return 0; +} + +/* skip ip address. returns it lenght. */ +static int epaddr_len(const char *dptr, const char *limit, int *shift) +{ + const char *aux = dptr; + u_int32_t ip; + + if (parse_ipaddr(dptr, &dptr, &ip, limit) < 0) { + DEBUGP("ip: %s parse failed.!\n", dptr); + return 0; + } + + /* Port number */ + if (*dptr == ':') { + dptr++; + dptr += digits_len(dptr, limit, shift); + } + return dptr - aux; +} + +/* get address length, skiping user info. */ +static int skp_epaddr_len(const char *dptr, const char *limit, int *shift) +{ + int s = *shift; + + for (; dptr <= limit && *dptr != '@'; dptr++) + (*shift)++; + + if (*dptr == '@') { + dptr++; + (*shift)++; + } else + *shift = s; + + return epaddr_len(dptr, limit, shift); +} + +/* Returns 0 if not found, -1 error parsing. */ +int ct_sip_get_info(const char *dptr, size_t dlen, + unsigned int *matchoff, + unsigned int *matchlen, + struct sip_header_nfo *hnfo) +{ + const char *limit, *aux, *k = dptr; + int shift = 0; + + limit = dptr + (dlen - hnfo->lnlen); + + while (dptr <= limit) { + if ((strncmp(dptr, hnfo->lname, hnfo->lnlen) != 0) && + (strncmp(dptr, hnfo->sname, hnfo->snlen) != 0)) { + dptr++; + continue; + } + aux = ct_sip_search(hnfo->ln_str, dptr, hnfo->ln_strlen, + ct_sip_lnlen(dptr, limit)); + if (!aux) { + DEBUGP("'%s' not found in '%s'.\n", hnfo->ln_str, + hnfo->lname); + return -1; + } + aux += hnfo->ln_strlen; + + *matchlen = hnfo->match_len(aux, limit, &shift); + if (!*matchlen) + return -1; + + *matchoff = (aux - k) + shift; + + DEBUGP("%s match succeeded! - len: %u\n", hnfo->lname, + *matchlen); + return 1; + } + DEBUGP("%s header not found.\n", hnfo->lname); + return 0; +} + +static int set_expected_rtp(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + u_int32_t ipaddr, u_int16_t port, + const char *dptr) +{ + struct ip_conntrack_expect *exp; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + int ret; + + exp = ip_conntrack_expect_alloc(ct); + if (exp == NULL) + return NF_DROP; + + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.udp.port = 0; + exp->tuple.dst.ip = ipaddr; + exp->tuple.dst.u.udp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_UDP; + + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.udp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.udp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + + exp->expectfn = NULL; + exp->flags = 0; + + if (ip_nat_sdp_hook) + ret = ip_nat_sdp_hook(pskb, ctinfo, exp, dptr); + else { + if (ip_conntrack_expect_related(exp) != 0) + ret = NF_DROP; + else + ret = NF_ACCEPT; + } + ip_conntrack_expect_put(exp); + + return ret; +} + +static int sip_help(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo) +{ + unsigned int dataoff, datalen; + const char *dptr; + int ret = NF_ACCEPT; + int matchoff, matchlen; + u_int32_t ipaddr; + u_int16_t port; + + /* No Data ? */ + dataoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct udphdr); + if (dataoff >= (*pskb)->len) { + DEBUGP("skb->len = %u\n", (*pskb)->len); + return NF_ACCEPT; + } + + ip_ct_refresh(ct, *pskb, sip_timeout * HZ); + + if (!skb_is_nonlinear(*pskb)) + dptr = (*pskb)->data + dataoff; + else { + DEBUGP("Copy of skbuff not supported yet.\n"); + goto out; + } + + if (ip_nat_sip_hook) { + if (!ip_nat_sip_hook(pskb, ctinfo, ct, &dptr)) { + ret = NF_DROP; + goto out; + } + } + + /* After this point NAT, could have mangled skb, so + we need to recalculate payload lenght. */ + datalen = (*pskb)->len - dataoff; + + if (datalen < (sizeof("SIP/2.0 200") - 1)) + goto out; + + /* RTP info only in some SDP pkts */ + if (memcmp(dptr, "INVITE", sizeof("INVITE") - 1) != 0 && + memcmp(dptr, "SIP/2.0 200", sizeof("SIP/2.0 200") - 1) != 0) { + goto out; + } + /* Get ip and port address from SDP packet. */ + if (ct_sip_get_info(dptr, datalen, &matchoff, &matchlen, + &ct_sip_hdrs[POS_CONNECTION]) > 0) { + + /* We'll drop only if there are parse problems. */ + if (parse_ipaddr(dptr + matchoff, NULL, &ipaddr, + dptr + datalen) < 0) { + ret = NF_DROP; + goto out; + } + if (ct_sip_get_info(dptr, datalen, &matchoff, &matchlen, + &ct_sip_hdrs[POS_MEDIA]) > 0) { + + port = simple_strtoul(dptr + matchoff, NULL, 10); + if (port < 1024) { + ret = NF_DROP; + goto out; + } + ret = set_expected_rtp(pskb, ct, ctinfo, + ipaddr, port, dptr); + } + } +out: + return ret; +} + +static struct ip_conntrack_helper sip[MAX_PORTS]; +static char sip_names[MAX_PORTS][10]; + +static void fini(void) +{ + int i; + for (i = 0; i < ports_c; i++) { + DEBUGP("unregistering helper for port %d\n", ports[i]); + ip_conntrack_helper_unregister(&sip[i]); + } +} + +static int __init init(void) +{ + int i, ret; + char *tmpname; + + if (ports_c == 0) + ports[ports_c++] = SIP_PORT; + + for (i = 0; i < ports_c; i++) { + /* Create helper structure */ + memset(&sip[i], 0, sizeof(struct ip_conntrack_helper)); + + sip[i].tuple.dst.protonum = IPPROTO_UDP; + sip[i].tuple.src.u.udp.port = htons(ports[i]); + sip[i].mask.src.u.udp.port = 0xFFFF; + sip[i].mask.dst.protonum = 0xFF; + sip[i].max_expected = 1; + sip[i].timeout = 3 * 60; /* 3 minutes */ + sip[i].me = THIS_MODULE; + sip[i].help = sip_help; + + tmpname = &sip_names[i][0]; + if (ports[i] == SIP_PORT) + sprintf(tmpname, "sip"); + else + sprintf(tmpname, "sip-%d", i); + sip[i].name = tmpname; + + DEBUGP("port #%d: %d\n", i, ports[i]); + + ret = ip_conntrack_helper_register(&sip[i]); + if (ret) { + printk("ERROR registering helper for port %d\n", + ports[i]); + fini(); + return ret; + } + } + return 0; +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 929d61f7be91..88445aac3f28 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -189,6 +189,11 @@ static int ct_seq_show(struct seq_file *s, void *v) return -ENOSPC; #endif +#ifdef CONFIG_IP_NF_CONNTRACK_SECMARK + if (seq_printf(s, "secmark=%u ", conntrack->secmark)) + return -ENOSPC; +#endif + if (seq_printf(s, "use=%u\n", atomic_read(&conntrack->ct_general.use))) return -ENOSPC; @@ -417,7 +422,7 @@ static unsigned int ip_conntrack_help(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = ip_conntrack_get(*pskb, &ctinfo); - if (ct && ct->helper) { + if (ct && ct->helper && ctinfo != IP_CT_RELATED + IP_CT_IS_REPLY) { unsigned int ret; ret = ct->helper->help(pskb, ct, ctinfo); if (ret != NF_ACCEPT) @@ -564,6 +569,8 @@ extern unsigned int ip_ct_generic_timeout; static int log_invalid_proto_min = 0; static int log_invalid_proto_max = 255; +int ip_conntrack_checksum = 1; + static struct ctl_table_header *ip_ct_sysctl_header; static ctl_table ip_ct_sysctl_table[] = { @@ -592,6 +599,14 @@ static ctl_table ip_ct_sysctl_table[] = { .proc_handler = &proc_dointvec, }, { + .ctl_name = NET_IPV4_NF_CONNTRACK_CHECKSUM, + .procname = "ip_conntrack_checksum", + .data = &ip_conntrack_checksum, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT, .procname = "ip_conntrack_tcp_timeout_syn_sent", .data = &ip_ct_tcp_timeout_syn_sent, @@ -946,6 +961,7 @@ EXPORT_SYMBOL_GPL(__ip_conntrack_helper_find_byname); EXPORT_SYMBOL_GPL(ip_conntrack_proto_find_get); EXPORT_SYMBOL_GPL(ip_conntrack_proto_put); EXPORT_SYMBOL_GPL(__ip_conntrack_proto_find); +EXPORT_SYMBOL_GPL(ip_conntrack_checksum); #if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) EXPORT_SYMBOL_GPL(ip_ct_port_tuple_to_nfattr); diff --git a/net/ipv4/netfilter/ip_nat_helper_h323.c b/net/ipv4/netfilter/ip_nat_helper_h323.c index d45663d137a7..419b878fb467 100644 --- a/net/ipv4/netfilter/ip_nat_helper_h323.c +++ b/net/ipv4/netfilter/ip_nat_helper_h323.c @@ -487,6 +487,80 @@ static int nat_q931(struct sk_buff **pskb, struct ip_conntrack *ct, } /****************************************************************************/ +static void ip_nat_callforwarding_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this) +{ + struct ip_nat_range range; + + /* This must be a fresh one. */ + BUG_ON(new->status & IPS_NAT_DONE_MASK); + + /* Change src to where master sends to */ + range.flags = IP_NAT_RANGE_MAP_IPS; + range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.ip; + + /* hook doesn't matter, but it has to do source manip */ + ip_nat_setup_info(new, &range, NF_IP_POST_ROUTING); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.min = range.max = this->saved_proto; + range.min_ip = range.max_ip = this->saved_ip; + + /* hook doesn't matter, but it has to do destination manip */ + ip_nat_setup_info(new, &range, NF_IP_PRE_ROUTING); + + ip_conntrack_q931_expect(new, this); +} + +/****************************************************************************/ +static int nat_callforwarding(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect *exp) +{ + int dir = CTINFO2DIR(ctinfo); + u_int16_t nated_port; + + /* Set expectations for NAT */ + exp->saved_ip = exp->tuple.dst.ip; + exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->expectfn = ip_nat_callforwarding_expect; + exp->dir = !dir; + + /* Try to get same port: if not, try to change it. */ + for (nated_port = port; nated_port != 0; nated_port++) { + exp->tuple.dst.u.tcp.port = htons(nated_port); + if (ip_conntrack_expect_related(exp) == 0) + break; + } + + if (nated_port == 0) { /* No port available */ + if (net_ratelimit()) + printk("ip_nat_q931: out of TCP ports\n"); + return 0; + } + + /* Modify signal */ + if (!set_h225_addr(pskb, data, dataoff, addr, + ct->tuplehash[!dir].tuple.dst.ip, + nated_port) == 0) { + ip_conntrack_unexpect_related(exp); + return -1; + } + + /* Success */ + DEBUGP("ip_nat_q931: expect Call Forwarding " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + + return 0; +} + +/****************************************************************************/ static int __init init(void) { BUG_ON(set_h245_addr_hook != NULL); @@ -496,6 +570,7 @@ static int __init init(void) BUG_ON(nat_rtp_rtcp_hook != NULL); BUG_ON(nat_t120_hook != NULL); BUG_ON(nat_h245_hook != NULL); + BUG_ON(nat_callforwarding_hook != NULL); BUG_ON(nat_q931_hook != NULL); set_h245_addr_hook = set_h245_addr; @@ -505,6 +580,7 @@ static int __init init(void) nat_rtp_rtcp_hook = nat_rtp_rtcp; nat_t120_hook = nat_t120; nat_h245_hook = nat_h245; + nat_callforwarding_hook = nat_callforwarding; nat_q931_hook = nat_q931; DEBUGP("ip_nat_h323: init success\n"); @@ -521,6 +597,7 @@ static void __exit fini(void) nat_rtp_rtcp_hook = NULL; nat_t120_hook = NULL; nat_h245_hook = NULL; + nat_callforwarding_hook = NULL; nat_q931_hook = NULL; synchronize_net(); } diff --git a/net/ipv4/netfilter/ip_nat_proto_gre.c b/net/ipv4/netfilter/ip_nat_proto_gre.c index 6c4899d8046a..96ceabaec402 100644 --- a/net/ipv4/netfilter/ip_nat_proto_gre.c +++ b/net/ipv4/netfilter/ip_nat_proto_gre.c @@ -49,15 +49,15 @@ gre_in_range(const struct ip_conntrack_tuple *tuple, const union ip_conntrack_manip_proto *min, const union ip_conntrack_manip_proto *max) { - u_int32_t key; + __be16 key; if (maniptype == IP_NAT_MANIP_SRC) key = tuple->src.u.gre.key; else key = tuple->dst.u.gre.key; - return ntohl(key) >= ntohl(min->gre.key) - && ntohl(key) <= ntohl(max->gre.key); + return ntohs(key) >= ntohs(min->gre.key) + && ntohs(key) <= ntohs(max->gre.key); } /* generate unique tuple ... */ @@ -81,14 +81,14 @@ gre_unique_tuple(struct ip_conntrack_tuple *tuple, min = 1; range_size = 0xffff; } else { - min = ntohl(range->min.gre.key); - range_size = ntohl(range->max.gre.key) - min + 1; + min = ntohs(range->min.gre.key); + range_size = ntohs(range->max.gre.key) - min + 1; } DEBUGP("min = %u, range_size = %u\n", min, range_size); for (i = 0; i < range_size; i++, key++) { - *keyptr = htonl(min + key % range_size); + *keyptr = htons(min + key % range_size); if (!ip_nat_used_tuple(tuple, conntrack)) return 1; } diff --git a/net/ipv4/netfilter/ip_nat_sip.c b/net/ipv4/netfilter/ip_nat_sip.c new file mode 100644 index 000000000000..6ffba63adca2 --- /dev/null +++ b/net/ipv4/netfilter/ip_nat_sip.c @@ -0,0 +1,249 @@ +/* SIP extension for UDP NAT alteration. + * + * (C) 2005 by Christian Hentschel <chentschel@arnet.com.ar> + * based on RR's ip_nat_ftp.c and other modules. + * + * 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. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/udp.h> + +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv4/ip_nat.h> +#include <linux/netfilter_ipv4/ip_nat_helper.h> +#include <linux/netfilter_ipv4/ip_conntrack_helper.h> +#include <linux/netfilter_ipv4/ip_conntrack_sip.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Christian Hentschel <chentschel@arnet.com.ar>"); +MODULE_DESCRIPTION("SIP NAT helper"); + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +extern struct sip_header_nfo ct_sip_hdrs[]; + +static unsigned int mangle_sip_packet(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack *ct, + const char **dptr, size_t dlen, + char *buffer, int bufflen, + struct sip_header_nfo *hnfo) +{ + unsigned int matchlen, matchoff; + + if (ct_sip_get_info(*dptr, dlen, &matchoff, &matchlen, hnfo) <= 0) + return 0; + + if (!ip_nat_mangle_udp_packet(pskb, ct, ctinfo, + matchoff, matchlen, buffer, bufflen)) + return 0; + + /* We need to reload this. Thanks Patrick. */ + *dptr = (*pskb)->data + (*pskb)->nh.iph->ihl*4 + sizeof(struct udphdr); + return 1; +} + +static unsigned int ip_nat_sip(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack *ct, + const char **dptr) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; + unsigned int bufflen, dataoff; + u_int32_t ip; + u_int16_t port; + + dataoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct udphdr); + + ip = ct->tuplehash[!dir].tuple.dst.ip; + port = ct->tuplehash[!dir].tuple.dst.u.udp.port; + bufflen = sprintf(buffer, "%u.%u.%u.%u:%u", NIPQUAD(ip), ntohs(port)); + + /* short packet ? */ + if (((*pskb)->len - dataoff) < (sizeof("SIP/2.0") - 1)) + return 0; + + /* Basic rules: requests and responses. */ + if (memcmp(*dptr, "SIP/2.0", sizeof("SIP/2.0") - 1) == 0) { + const char *aux; + + if ((ctinfo) < IP_CT_IS_REPLY) { + mangle_sip_packet(pskb, ctinfo, ct, dptr, + (*pskb)->len - dataoff, + buffer, bufflen, + &ct_sip_hdrs[POS_CONTACT]); + return 1; + } + + if (!mangle_sip_packet(pskb, ctinfo, ct, dptr, + (*pskb)->len - dataoff, + buffer, bufflen, &ct_sip_hdrs[POS_VIA])) + return 0; + + /* This search should ignore case, but later.. */ + aux = ct_sip_search("CSeq:", *dptr, sizeof("CSeq:") - 1, + (*pskb)->len - dataoff); + if (!aux) + return 0; + + if (!ct_sip_search("REGISTER", aux, sizeof("REGISTER"), + ct_sip_lnlen(aux, *dptr + (*pskb)->len - dataoff))) + return 1; + + return mangle_sip_packet(pskb, ctinfo, ct, dptr, + (*pskb)->len - dataoff, + buffer, bufflen, + &ct_sip_hdrs[POS_CONTACT]); + } + if ((ctinfo) < IP_CT_IS_REPLY) { + if (!mangle_sip_packet(pskb, ctinfo, ct, dptr, + (*pskb)->len - dataoff, + buffer, bufflen, &ct_sip_hdrs[POS_VIA])) + return 0; + + /* Mangle Contact if exists only. - watch udp_nat_mangle()! */ + mangle_sip_packet(pskb, ctinfo, ct, dptr, (*pskb)->len - dataoff, + buffer, bufflen, &ct_sip_hdrs[POS_CONTACT]); + return 1; + } + /* This mangle requests headers. */ + return mangle_sip_packet(pskb, ctinfo, ct, dptr, + ct_sip_lnlen(*dptr, + *dptr + (*pskb)->len - dataoff), + buffer, bufflen, &ct_sip_hdrs[POS_REQ_HEADER]); +} + +static int mangle_content_len(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack *ct, + const char *dptr) +{ + unsigned int dataoff, matchoff, matchlen; + char buffer[sizeof("65536")]; + int bufflen; + + dataoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct udphdr); + + /* Get actual SDP lenght */ + if (ct_sip_get_info(dptr, (*pskb)->len - dataoff, &matchoff, + &matchlen, &ct_sip_hdrs[POS_SDP_HEADER]) > 0) { + + /* since ct_sip_get_info() give us a pointer passing 'v=' + we need to add 2 bytes in this count. */ + int c_len = (*pskb)->len - dataoff - matchoff + 2; + + /* Now, update SDP lenght */ + if (ct_sip_get_info(dptr, (*pskb)->len - dataoff, &matchoff, + &matchlen, &ct_sip_hdrs[POS_CONTENT]) > 0) { + + bufflen = sprintf(buffer, "%u", c_len); + + return ip_nat_mangle_udp_packet(pskb, ct, ctinfo, + matchoff, matchlen, + buffer, bufflen); + } + } + return 0; +} + +static unsigned int mangle_sdp(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack *ct, + u_int32_t newip, u_int16_t port, + const char *dptr) +{ + char buffer[sizeof("nnn.nnn.nnn.nnn")]; + unsigned int dataoff, bufflen; + + dataoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct udphdr); + + /* Mangle owner and contact info. */ + bufflen = sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(newip)); + if (!mangle_sip_packet(pskb, ctinfo, ct, &dptr, (*pskb)->len - dataoff, + buffer, bufflen, &ct_sip_hdrs[POS_OWNER])) + return 0; + + if (!mangle_sip_packet(pskb, ctinfo, ct, &dptr, (*pskb)->len - dataoff, + buffer, bufflen, &ct_sip_hdrs[POS_CONNECTION])) + return 0; + + /* Mangle media port. */ + bufflen = sprintf(buffer, "%u", port); + if (!mangle_sip_packet(pskb, ctinfo, ct, &dptr, (*pskb)->len - dataoff, + buffer, bufflen, &ct_sip_hdrs[POS_MEDIA])) + return 0; + + return mangle_content_len(pskb, ctinfo, ct, dptr); +} + +/* So, this packet has hit the connection tracking matching code. + Mangle it, and change the expectation to match the new version. */ +static unsigned int ip_nat_sdp(struct sk_buff **pskb, + enum ip_conntrack_info ctinfo, + struct ip_conntrack_expect *exp, + const char *dptr) +{ + struct ip_conntrack *ct = exp->master; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + u_int32_t newip; + u_int16_t port; + + DEBUGP("ip_nat_sdp():\n"); + + /* Connection will come from reply */ + newip = ct->tuplehash[!dir].tuple.dst.ip; + + exp->tuple.dst.ip = newip; + exp->saved_proto.udp.port = exp->tuple.dst.u.udp.port; + exp->dir = !dir; + + /* When you see the packet, we need to NAT it the same as the + this one. */ + exp->expectfn = ip_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.udp.port); port != 0; port++) { + exp->tuple.dst.u.udp.port = htons(port); + if (ip_conntrack_expect_related(exp) == 0) + break; + } + + if (port == 0) + return NF_DROP; + + if (!mangle_sdp(pskb, ctinfo, ct, newip, port, dptr)) { + ip_conntrack_unexpect_related(exp); + return NF_DROP; + } + return NF_ACCEPT; +} + +static void __exit fini(void) +{ + ip_nat_sip_hook = NULL; + ip_nat_sdp_hook = NULL; + /* Make sure noone calls it, meanwhile. */ + synchronize_net(); +} + +static int __init init(void) +{ + BUG_ON(ip_nat_sip_hook); + BUG_ON(ip_nat_sdp_hook); + ip_nat_sip_hook = ip_nat_sip; + ip_nat_sdp_hook = ip_nat_sdp; + return 0; +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ip_nat_snmp_basic.c b/net/ipv4/netfilter/ip_nat_snmp_basic.c index c62253845538..d20d557f915a 100644 --- a/net/ipv4/netfilter/ip_nat_snmp_basic.c +++ b/net/ipv4/netfilter/ip_nat_snmp_basic.c @@ -768,6 +768,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, len *= sizeof(unsigned long); *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); if (*obj == NULL) { + kfree(lp); kfree(id); if (net_ratelimit()) printk("OOM in bsalg (%d)\n", __LINE__); @@ -1003,12 +1004,12 @@ static unsigned char snmp_trap_decode(struct asn1_ctx *ctx, return 1; +err_addr_free: + kfree((unsigned long *)trap->ip_address); + err_id_free: kfree(trap->id); -err_addr_free: - kfree((unsigned long *)trap->ip_address); - return 0; } @@ -1126,11 +1127,10 @@ static int snmp_parse_mangle(unsigned char *msg, struct snmp_v1_trap trap; unsigned char ret = snmp_trap_decode(&ctx, &trap, map, check); - /* Discard trap allocations regardless */ - kfree(trap.id); - kfree((unsigned long *)trap.ip_address); - - if (!ret) + if (ret) { + kfree(trap.id); + kfree((unsigned long *)trap.ip_address); + } else return ret; } else { @@ -1348,4 +1348,4 @@ static void __exit ip_nat_snmp_basic_fini(void) module_init(ip_nat_snmp_basic_init); module_exit(ip_nat_snmp_basic_fini); -module_param(debug, bool, 0600); +module_param(debug, int, 0600); diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 8f760b28617e..67e676783da9 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -219,8 +219,10 @@ ip_nat_out(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { +#ifdef CONFIG_XFRM struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; +#endif unsigned int ret; /* root is playing with raw sockets. */ diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d25ac8ba6eba..cee3397ec277 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -956,15 +956,16 @@ struct compat_ipt_standard_target compat_int_t verdict; }; -#define IPT_ST_OFFSET (sizeof(struct ipt_standard_target) - \ - sizeof(struct compat_ipt_standard_target)) - struct compat_ipt_standard { struct compat_ipt_entry entry; struct compat_ipt_standard_target target; }; +#define IPT_ST_LEN XT_ALIGN(sizeof(struct ipt_standard_target)) +#define IPT_ST_COMPAT_LEN COMPAT_XT_ALIGN(sizeof(struct compat_ipt_standard_target)) +#define IPT_ST_OFFSET (IPT_ST_LEN - IPT_ST_COMPAT_LEN) + static int compat_ipt_standard_fn(void *target, void **dstptr, int *size, int convert) { @@ -975,35 +976,29 @@ static int compat_ipt_standard_fn(void *target, ret = 0; switch (convert) { case COMPAT_TO_USER: - pst = (struct ipt_standard_target *)target; + pst = target; memcpy(&compat_st.target, &pst->target, - sizeof(struct ipt_entry_target)); + sizeof(compat_st.target)); compat_st.verdict = pst->verdict; if (compat_st.verdict > 0) compat_st.verdict -= compat_calc_jump(compat_st.verdict); - compat_st.target.u.user.target_size = - sizeof(struct compat_ipt_standard_target); - if (__copy_to_user(*dstptr, &compat_st, - sizeof(struct compat_ipt_standard_target))) + compat_st.target.u.user.target_size = IPT_ST_COMPAT_LEN; + if (copy_to_user(*dstptr, &compat_st, IPT_ST_COMPAT_LEN)) ret = -EFAULT; *size -= IPT_ST_OFFSET; - *dstptr += sizeof(struct compat_ipt_standard_target); + *dstptr += IPT_ST_COMPAT_LEN; break; case COMPAT_FROM_USER: - pcompat_st = - (struct compat_ipt_standard_target *)target; - memcpy(&st.target, &pcompat_st->target, - sizeof(struct ipt_entry_target)); + pcompat_st = target; + memcpy(&st.target, &pcompat_st->target, IPT_ST_COMPAT_LEN); st.verdict = pcompat_st->verdict; if (st.verdict > 0) st.verdict += compat_calc_jump(st.verdict); - st.target.u.user.target_size = - sizeof(struct ipt_standard_target); - memcpy(*dstptr, &st, - sizeof(struct ipt_standard_target)); + st.target.u.user.target_size = IPT_ST_LEN; + memcpy(*dstptr, &st, IPT_ST_LEN); *size += IPT_ST_OFFSET; - *dstptr += sizeof(struct ipt_standard_target); + *dstptr += IPT_ST_LEN; break; case COMPAT_CALC_SIZE: *size += IPT_ST_OFFSET; @@ -1446,7 +1441,7 @@ static int compat_copy_entry_to_user(struct ipt_entry *e, ret = -EFAULT; origsize = *size; ce = (struct compat_ipt_entry __user *)*dstptr; - if (__copy_to_user(ce, e, sizeof(struct ipt_entry))) + if (copy_to_user(ce, e, sizeof(struct ipt_entry))) goto out; *dstptr += sizeof(struct compat_ipt_entry); @@ -1464,9 +1459,9 @@ static int compat_copy_entry_to_user(struct ipt_entry *e, goto out; ret = -EFAULT; next_offset = e->next_offset - (origsize - *size); - if (__put_user(target_offset, &ce->target_offset)) + if (put_user(target_offset, &ce->target_offset)) goto out; - if (__put_user(next_offset, &ce->next_offset)) + if (put_user(next_offset, &ce->next_offset)) goto out; return 0; out: diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index aad9d28c8d71..dbc83c5d7aa6 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -241,25 +241,17 @@ clusterip_hashfn(struct sk_buff *skb, struct clusterip_config *config) struct iphdr *iph = skb->nh.iph; unsigned long hashval; u_int16_t sport, dport; - struct tcphdr *th; - struct udphdr *uh; - struct icmphdr *ih; + u_int16_t *ports; switch (iph->protocol) { case IPPROTO_TCP: - th = (void *)iph+iph->ihl*4; - sport = ntohs(th->source); - dport = ntohs(th->dest); - break; case IPPROTO_UDP: - uh = (void *)iph+iph->ihl*4; - sport = ntohs(uh->source); - dport = ntohs(uh->dest); - break; + case IPPROTO_SCTP: + case IPPROTO_DCCP: case IPPROTO_ICMP: - ih = (void *)iph+iph->ihl*4; - sport = ntohs(ih->un.echo.id); - dport = (ih->type<<8)|ih->code; + ports = (void *)iph+iph->ihl*4; + sport = ports[0]; + dport = ports[1]; break; default: if (net_ratelimit()) { diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 39fd4c2a2386..b98f7b08b084 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -428,7 +428,7 @@ ipt_log_target(struct sk_buff **pskb, if (loginfo->logflags & IPT_LOG_NFLOG) nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li, - loginfo->prefix); + "%s", loginfo->prefix); else ipt_log_packet(PF_INET, hooknum, *pskb, in, out, &li, loginfo->prefix); diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 0bba3c2bb786..431a3ce6f7b7 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -147,6 +147,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* This packet will not be the same as the other: clear nf fields */ nf_reset(nskb); nskb->nfmark = 0; + skb_init_secmark(nskb); tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl); diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 7c6836c4646e..92980ab8ce48 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -28,9 +28,6 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/sctp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/list.h> @@ -83,6 +80,7 @@ struct ipt_hashlimit_htable { /* used internally */ spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ + int rnd_initialized; struct timer_list timer; /* timer for gc */ atomic_t count; /* number entries in table */ @@ -137,8 +135,10 @@ __dsthash_alloc_init(struct ipt_hashlimit_htable *ht, struct dsthash_dst *dst) /* initialize hash with random val at the time we allocate * the first hashtable entry */ - if (!ht->rnd) + if (!ht->rnd_initialized) { get_random_bytes(&ht->rnd, 4); + ht->rnd_initialized = 1; + } if (ht->cfg.max && atomic_read(&ht->count) >= ht->cfg.max) { @@ -217,7 +217,7 @@ static int htable_create(struct ipt_hashlimit_info *minfo) atomic_set(&hinfo->count, 0); atomic_set(&hinfo->use, 1); - hinfo->rnd = 0; + hinfo->rnd_initialized = 0; spin_lock_init(&hinfo->lock); hinfo->pde = create_proc_entry(minfo->name, 0, hashlimit_procdir); if (!hinfo->pde) { @@ -381,49 +381,6 @@ static inline void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now) dh->rateinfo.credit = dh->rateinfo.credit_cap; } -static inline int get_ports(const struct sk_buff *skb, int offset, - u16 ports[2]) -{ - union { - struct tcphdr th; - struct udphdr uh; - sctp_sctphdr_t sctph; - } hdr_u, *ptr_u; - - /* Must not be a fragment. */ - if (offset) - return 1; - - /* Must be big enough to read ports (both UDP and TCP have - them at the start). */ - ptr_u = skb_header_pointer(skb, skb->nh.iph->ihl*4, 8, &hdr_u); - if (!ptr_u) - return 1; - - switch (skb->nh.iph->protocol) { - case IPPROTO_TCP: - ports[0] = ptr_u->th.source; - ports[1] = ptr_u->th.dest; - break; - case IPPROTO_UDP: - ports[0] = ptr_u->uh.source; - ports[1] = ptr_u->uh.dest; - break; - case IPPROTO_SCTP: - ports[0] = ptr_u->sctph.source; - ports[1] = ptr_u->sctph.dest; - break; - default: - /* all other protocols don't supprot per-port hash - * buckets */ - ports[0] = ports[1] = 0; - break; - } - - return 0; -} - - static int hashlimit_match(const struct sk_buff *skb, const struct net_device *in, @@ -449,8 +406,22 @@ hashlimit_match(const struct sk_buff *skb, dst.src_ip = skb->nh.iph->saddr; if (hinfo->cfg.mode & IPT_HASHLIMIT_HASH_DPT ||hinfo->cfg.mode & IPT_HASHLIMIT_HASH_SPT) { - u_int16_t ports[2]; - if (get_ports(skb, offset, ports)) { + u_int16_t _ports[2], *ports; + + switch (skb->nh.iph->protocol) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_SCTP: + case IPPROTO_DCCP: + ports = skb_header_pointer(skb, skb->nh.iph->ihl*4, + sizeof(_ports), &_ports); + break; + default: + _ports[0] = _ports[1] = 0; + ports = _ports; + break; + } + if (!ports) { /* We've been asked to examine this packet, and we can't. Hence, no choice but to drop. */ *hotdrop = 1; @@ -561,7 +532,7 @@ static void hashlimit_destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) { - struct ipt_hashlimit_info *r = (struct ipt_hashlimit_info *) matchinfo; + struct ipt_hashlimit_info *r = matchinfo; htable_put(r->hinfo); } diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 143843285702..61a2139f9cfd 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -1,1007 +1,499 @@ -/* Kernel module to check if the source address has been seen recently. */ -/* Copyright 2002-2003, Stephen Frost, 2.5.x port by laforge@netfilter.org */ -/* Author: Stephen Frost <sfrost@snowman.net> */ -/* Project Page: http://snowman.net/projects/ipt_recent/ */ -/* This software is distributed under the terms of the GPL, Version 2 */ -/* This copyright does not cover user programs that use kernel services - * by normal system calls. */ - -#include <linux/module.h> -#include <linux/skbuff.h> +/* + * Copyright (c) 2006 Patrick McHardy <kaber@trash.net> + * + * 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. + * + * This is a replacement of the old ipt_recent module, which carried the + * following copyright notice: + * + * Author: Stephen Frost <sfrost@snowman.net> + * Copyright 2002-2003, Stephen Frost, 2.5.x port by laforge@netfilter.org + */ +#include <linux/init.h> +#include <linux/moduleparam.h> #include <linux/proc_fs.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> -#include <asm/uaccess.h> +#include <linux/seq_file.h> +#include <linux/string.h> #include <linux/ctype.h> -#include <linux/ip.h> -#include <linux/vmalloc.h> -#include <linux/moduleparam.h> +#include <linux/list.h> +#include <linux/random.h> +#include <linux/jhash.h> +#include <linux/bitops.h> +#include <linux/skbuff.h> +#include <linux/inet.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_recent.h> -#undef DEBUG -#define HASH_LOG 9 +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("IP tables recently seen matching module"); +MODULE_LICENSE("GPL"); -/* Defaults, these can be overridden on the module command-line. */ static unsigned int ip_list_tot = 100; static unsigned int ip_pkt_list_tot = 20; static unsigned int ip_list_hash_size = 0; static unsigned int ip_list_perms = 0644; -#ifdef DEBUG -static int debug = 1; -#endif - -static char version[] = -KERN_INFO RECENT_NAME " " RECENT_VER ": Stephen Frost <sfrost@snowman.net>. http://snowman.net/projects/ipt_recent/\n"; - -MODULE_AUTHOR("Stephen Frost <sfrost@snowman.net>"); -MODULE_DESCRIPTION("IP tables recently seen matching module " RECENT_VER); -MODULE_LICENSE("GPL"); module_param(ip_list_tot, uint, 0400); module_param(ip_pkt_list_tot, uint, 0400); module_param(ip_list_hash_size, uint, 0400); module_param(ip_list_perms, uint, 0400); -#ifdef DEBUG -module_param(debug, bool, 0600); -MODULE_PARM_DESC(debug,"enable debugging output"); -#endif -MODULE_PARM_DESC(ip_list_tot,"number of IPs to remember per list"); -MODULE_PARM_DESC(ip_pkt_list_tot,"number of packets per IP to remember"); -MODULE_PARM_DESC(ip_list_hash_size,"size of hash table used to look up IPs"); -MODULE_PARM_DESC(ip_list_perms,"permissions on /proc/net/ipt_recent/* files"); - -/* Structure of our list of recently seen addresses. */ -struct recent_ip_list { - u_int32_t addr; - u_int8_t ttl; - unsigned long last_seen; - unsigned long *last_pkts; - u_int32_t oldest_pkt; - u_int32_t hash_entry; - u_int32_t time_pos; -}; - -struct time_info_list { - u_int32_t position; - u_int32_t time; +MODULE_PARM_DESC(ip_list_tot, "number of IPs to remember per list"); +MODULE_PARM_DESC(ip_pkt_list_tot, "number of packets per IP to remember (max. 255)"); +MODULE_PARM_DESC(ip_list_hash_size, "size of hash table used to look up IPs"); +MODULE_PARM_DESC(ip_list_perms, "permissions on /proc/net/ipt_recent/* files"); + + +struct recent_entry { + struct list_head list; + struct list_head lru_list; + u_int32_t addr; + u_int8_t ttl; + u_int8_t index; + u_int16_t nstamps; + unsigned long stamps[0]; }; -/* Structure of our linked list of tables of recent lists. */ -struct recent_ip_tables { - char name[IPT_RECENT_NAME_LEN]; - int count; - int time_pos; - struct recent_ip_list *table; - struct recent_ip_tables *next; - spinlock_t list_lock; - int *hash_table; - struct time_info_list *time_info; +struct recent_table { + struct list_head list; + char name[IPT_RECENT_NAME_LEN]; #ifdef CONFIG_PROC_FS - struct proc_dir_entry *status_proc; -#endif /* CONFIG_PROC_FS */ + struct proc_dir_entry *proc; +#endif + unsigned int refcnt; + unsigned int entries; + struct list_head lru_list; + struct list_head iphash[0]; }; -/* Our current list of addresses we have recently seen. - * Only added to on a --set, and only updated on --set || --update - */ -static struct recent_ip_tables *r_tables = NULL; - -/* We protect r_list with this spinlock so two processors are not modifying - * the list at the same time. - */ +static LIST_HEAD(tables); static DEFINE_SPINLOCK(recent_lock); +static DEFINE_MUTEX(recent_mutex); #ifdef CONFIG_PROC_FS -/* Our /proc/net/ipt_recent entry */ -static struct proc_dir_entry *proc_net_ipt_recent = NULL; -#endif - -/* Function declaration for later. */ -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct xt_match *match, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop); - -/* Function to hash a given address into the hash table of table_size size */ -static int hash_func(unsigned int addr, int table_size) -{ - int result = 0; - unsigned int value = addr; - do { result ^= value; } while((value >>= HASH_LOG)); - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": %d = hash_func(%u,%d)\n", - result & (table_size - 1), - addr, - table_size); +static struct proc_dir_entry *proc_dir; +static struct file_operations recent_fops; #endif - return(result & (table_size - 1)); -} +static u_int32_t hash_rnd; +static int hash_rnd_initted; -#ifdef CONFIG_PROC_FS -/* This is the function which produces the output for our /proc output - * interface which lists each IP address, the last seen time and the - * other recent times the address was seen. - */ - -static int ip_recent_get_info(char *buffer, char **start, off_t offset, int length, int *eof, void *data) +static unsigned int recent_entry_hash(u_int32_t addr) { - int len = 0, count, last_len = 0, pkt_count; - off_t pos = 0; - off_t begin = 0; - struct recent_ip_tables *curr_table; - - curr_table = (struct recent_ip_tables*) data; - - spin_lock_bh(&curr_table->list_lock); - for(count = 0; count < ip_list_tot; count++) { - if(!curr_table->table[count].addr) continue; - last_len = len; - len += sprintf(buffer+len,"src=%u.%u.%u.%u ",NIPQUAD(curr_table->table[count].addr)); - len += sprintf(buffer+len,"ttl: %u ",curr_table->table[count].ttl); - len += sprintf(buffer+len,"last_seen: %lu ",curr_table->table[count].last_seen); - len += sprintf(buffer+len,"oldest_pkt: %u ",curr_table->table[count].oldest_pkt); - len += sprintf(buffer+len,"last_pkts: %lu",curr_table->table[count].last_pkts[0]); - for(pkt_count = 1; pkt_count < ip_pkt_list_tot; pkt_count++) { - if(!curr_table->table[count].last_pkts[pkt_count]) break; - len += sprintf(buffer+len,", %lu",curr_table->table[count].last_pkts[pkt_count]); - } - len += sprintf(buffer+len,"\n"); - pos = begin + len; - if(pos < offset) { len = 0; begin = pos; } - if(pos > offset + length) { len = last_len; break; } + if (!hash_rnd_initted) { + get_random_bytes(&hash_rnd, 4); + hash_rnd_initted = 1; } - - *start = buffer + (offset - begin); - len -= (offset - begin); - if(len > length) len = length; - - spin_unlock_bh(&curr_table->list_lock); - return len; + return jhash_1word(addr, hash_rnd) & (ip_list_hash_size - 1); } -/* ip_recent_ctrl provides an interface for users to modify the table - * directly. This allows adding entries, removing entries, and - * flushing the entire table. - * This is done by opening up the appropriate table for writing and - * sending one of: - * xx.xx.xx.xx -- Add entry to table with current time - * +xx.xx.xx.xx -- Add entry to table with current time - * -xx.xx.xx.xx -- Remove entry from table - * clear -- Flush table, remove all entries - */ - -static int ip_recent_ctrl(struct file *file, const char __user *input, unsigned long size, void *data) +static struct recent_entry * +recent_entry_lookup(const struct recent_table *table, u_int32_t addr, u_int8_t ttl) { - static const u_int32_t max[4] = { 0xffffffff, 0xffffff, 0xffff, 0xff }; - u_int32_t val; - int base, used = 0; - char c, *cp; - union iaddr { - uint8_t bytes[4]; - uint32_t word; - } res; - uint8_t *pp = res.bytes; - int digit; - - char buffer[20]; - int len, check_set = 0, count; - u_int32_t addr = 0; - struct sk_buff *skb; - struct ipt_recent_info *info; - struct recent_ip_tables *curr_table; - - curr_table = (struct recent_ip_tables*) data; - - if(size > 20) len = 20; else len = size; - - if(copy_from_user(buffer,input,len)) return -EFAULT; - - if(len < 20) buffer[len] = '\0'; - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": ip_recent_ctrl len: %d, input: `%.20s'\n",len,buffer); -#endif + struct recent_entry *e; + unsigned int h; + + h = recent_entry_hash(addr); + list_for_each_entry(e, &table->iphash[h], list) + if (e->addr == addr && (ttl == e->ttl || !ttl || !e->ttl)) + return e; + return NULL; +} - cp = buffer; - while(isspace(*cp)) { cp++; used++; if(used >= len-5) return used; } +static void recent_entry_remove(struct recent_table *t, struct recent_entry *e) +{ + list_del(&e->list); + list_del(&e->lru_list); + kfree(e); + t->entries--; +} - /* Check if we are asked to flush the entire table */ - if(!memcmp(cp,"clear",5)) { - used += 5; - spin_lock_bh(&curr_table->list_lock); - curr_table->time_pos = 0; - for(count = 0; count < ip_list_hash_size; count++) { - curr_table->hash_table[count] = -1; - } - for(count = 0; count < ip_list_tot; count++) { - curr_table->table[count].last_seen = 0; - curr_table->table[count].addr = 0; - curr_table->table[count].ttl = 0; - memset(curr_table->table[count].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long)); - curr_table->table[count].oldest_pkt = 0; - curr_table->table[count].time_pos = 0; - curr_table->time_info[count].position = count; - curr_table->time_info[count].time = 0; - } - spin_unlock_bh(&curr_table->list_lock); - return used; - } +static struct recent_entry * +recent_entry_init(struct recent_table *t, u_int32_t addr, u_int8_t ttl) +{ + struct recent_entry *e; - check_set = IPT_RECENT_SET; - switch(*cp) { - case '+': check_set = IPT_RECENT_SET; cp++; used++; break; - case '-': check_set = IPT_RECENT_REMOVE; cp++; used++; break; - default: if(!isdigit(*cp)) return (used+1); break; + if (t->entries >= ip_list_tot) { + e = list_entry(t->lru_list.next, struct recent_entry, lru_list); + recent_entry_remove(t, e); } + e = kmalloc(sizeof(*e) + sizeof(e->stamps[0]) * ip_pkt_list_tot, + GFP_ATOMIC); + if (e == NULL) + return NULL; + e->addr = addr; + e->ttl = ttl; + e->stamps[0] = jiffies; + e->nstamps = 1; + e->index = 1; + list_add_tail(&e->list, &t->iphash[recent_entry_hash(addr)]); + list_add_tail(&e->lru_list, &t->lru_list); + t->entries++; + return e; +} -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": ip_recent_ctrl cp: `%c', check_set: %d\n",*cp,check_set); -#endif - /* Get addr (effectively inet_aton()) */ - /* Shamelessly stolen from libc, a function in the kernel for doing - * this would, of course, be greatly preferred, but our options appear - * to be rather limited, so we will just do it ourselves here. - */ - res.word = 0; - - c = *cp; - for(;;) { - if(!isdigit(c)) return used; - val = 0; base = 10; digit = 0; - if(c == '0') { - c = *++cp; - if(c == 'x' || c == 'X') base = 16, c = *++cp; - else { base = 8; digit = 1; } - } - for(;;) { - if(isascii(c) && isdigit(c)) { - if(base == 8 && (c == '8' || c == '0')) return used; - val = (val * base) + (c - '0'); - c = *++cp; - digit = 1; - } else if(base == 16 && isascii(c) && isxdigit(c)) { - val = (val << 4) | (c + 10 - (islower(c) ? 'a' : 'A')); - c = *++cp; - digit = 1; - } else break; - } - if(c == '.') { - if(pp > res.bytes + 2 || val > 0xff) return used; - *pp++ = val; - c = *++cp; - } else break; - } - used = cp - buffer; - if(c != '\0' && (!isascii(c) || !isspace(c))) return used; - if(c == '\n') used++; - if(!digit) return used; +static void recent_entry_update(struct recent_table *t, struct recent_entry *e) +{ + e->stamps[e->index++] = jiffies; + if (e->index > e->nstamps) + e->nstamps = e->index; + e->index %= ip_pkt_list_tot; + list_move_tail(&e->lru_list, &t->lru_list); +} - if(val > max[pp - res.bytes]) return used; - addr = res.word | htonl(val); +static struct recent_table *recent_table_lookup(const char *name) +{ + struct recent_table *t; - if(!addr && check_set == IPT_RECENT_SET) return used; + list_for_each_entry(t, &tables, list) + if (!strcmp(t->name, name)) + return t; + return NULL; +} -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": ip_recent_ctrl c: %c, addr: %u used: %d\n",c,addr,used); -#endif +static void recent_table_flush(struct recent_table *t) +{ + struct recent_entry *e, *next; + unsigned int i; - /* Set up and just call match */ - info = kmalloc(sizeof(struct ipt_recent_info),GFP_KERNEL); - if(!info) { return -ENOMEM; } - info->seconds = 0; - info->hit_count = 0; - info->check_set = check_set; - info->invert = 0; - info->side = IPT_RECENT_SOURCE; - strncpy(info->name,curr_table->name,IPT_RECENT_NAME_LEN); - info->name[IPT_RECENT_NAME_LEN-1] = '\0'; - - skb = kmalloc(sizeof(struct sk_buff),GFP_KERNEL); - if (!skb) { - used = -ENOMEM; - goto out_free_info; - } - skb->nh.iph = kmalloc(sizeof(struct iphdr),GFP_KERNEL); - if (!skb->nh.iph) { - used = -ENOMEM; - goto out_free_skb; + for (i = 0; i < ip_list_hash_size; i++) { + list_for_each_entry_safe(e, next, &t->iphash[i], list) + recent_entry_remove(t, e); } - - skb->nh.iph->saddr = addr; - skb->nh.iph->daddr = 0; - /* Clear ttl since we have no way of knowing it */ - skb->nh.iph->ttl = 0; - match(skb,NULL,NULL,NULL,info,0,0,NULL); - - kfree(skb->nh.iph); -out_free_skb: - kfree(skb); -out_free_info: - kfree(info); - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": Leaving ip_recent_ctrl addr: %u used: %d\n",addr,used); -#endif - return used; } -#endif /* CONFIG_PROC_FS */ - -/* 'match' is our primary function, called by the kernel whenever a rule is - * hit with our module as an option to it. - * What this function does depends on what was specifically asked of it by - * the user: - * --set -- Add or update last seen time of the source address of the packet - * -- matchinfo->check_set == IPT_RECENT_SET - * --rcheck -- Just check if the source address is in the list - * -- matchinfo->check_set == IPT_RECENT_CHECK - * --update -- If the source address is in the list, update last_seen - * -- matchinfo->check_set == IPT_RECENT_UPDATE - * --remove -- If the source address is in the list, remove it - * -- matchinfo->check_set == IPT_RECENT_REMOVE - * --seconds -- Option to --rcheck/--update, only match if last_seen within seconds - * -- matchinfo->seconds - * --hitcount -- Option to --rcheck/--update, only match if seen hitcount times - * -- matchinfo->hit_count - * --seconds and --hitcount can be combined - */ static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct xt_match *match, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +ipt_recent_match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, + int offset, unsigned int protoff, int *hotdrop) { - int pkt_count, hits_found, ans; - unsigned long now; const struct ipt_recent_info *info = matchinfo; - u_int32_t addr = 0, time_temp; - u_int8_t ttl = skb->nh.iph->ttl; - int *hash_table; - int orig_hash_result, hash_result, temp, location = 0, time_loc, end_collision_chain = -1; - struct time_info_list *time_info; - struct recent_ip_tables *curr_table; - struct recent_ip_tables *last_table; - struct recent_ip_list *r_list; - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match() called\n"); -#endif - - /* Default is false ^ info->invert */ - ans = info->invert; + struct recent_table *t; + struct recent_entry *e; + u_int32_t addr; + u_int8_t ttl; + int ret = info->invert; -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): name = '%s'\n",info->name); -#endif + if (info->side == IPT_RECENT_DEST) + addr = skb->nh.iph->daddr; + else + addr = skb->nh.iph->saddr; - /* if out != NULL then routing has been done and TTL changed. - * We change it back here internally for match what came in before routing. */ - if(out) ttl++; + ttl = skb->nh.iph->ttl; + /* use TTL as seen before forwarding */ + if (out && !skb->sk) + ttl++; - /* Find the right table */ spin_lock_bh(&recent_lock); - curr_table = r_tables; - while( (last_table = curr_table) && strncmp(info->name,curr_table->name,IPT_RECENT_NAME_LEN) && (curr_table = curr_table->next) ); - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): table found('%s')\n",info->name); -#endif - - spin_unlock_bh(&recent_lock); - - /* Table with this name not found, match impossible */ - if(!curr_table) { return ans; } - - /* Make sure no one is changing the list while we work with it */ - spin_lock_bh(&curr_table->list_lock); - - r_list = curr_table->table; - if(info->side == IPT_RECENT_DEST) addr = skb->nh.iph->daddr; else addr = skb->nh.iph->saddr; - - if(!addr) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match() address (%u) invalid, leaving.\n",addr); -#endif - spin_unlock_bh(&curr_table->list_lock); - return ans; - } - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): checking table, addr: %u, ttl: %u, orig_ttl: %u\n",addr,ttl,skb->nh.iph->ttl); -#endif - - /* Get jiffies now in case they changed while we were waiting for a lock */ - now = jiffies; - hash_table = curr_table->hash_table; - time_info = curr_table->time_info; - - orig_hash_result = hash_result = hash_func(addr,ip_list_hash_size); - /* Hash entry at this result used */ - /* Check for TTL match if requested. If TTL is zero then a match would never - * happen, so match regardless of existing TTL in that case. Zero means the - * entry was added via the /proc interface anyway, so we will just use the - * first TTL we get for that IP address. */ - if(info->check_set & IPT_RECENT_TTL) { - while(hash_table[hash_result] != -1 && !(r_list[hash_table[hash_result]].addr == addr && - (!r_list[hash_table[hash_result]].ttl || r_list[hash_table[hash_result]].ttl == ttl))) { - /* Collision in hash table */ - hash_result = (hash_result + 1) % ip_list_hash_size; - } - } else { - while(hash_table[hash_result] != -1 && r_list[hash_table[hash_result]].addr != addr) { - /* Collision in hash table */ - hash_result = (hash_result + 1) % ip_list_hash_size; - } - } - - if(hash_table[hash_result] == -1 && !(info->check_set & IPT_RECENT_SET)) { - /* IP not in list and not asked to SET */ - spin_unlock_bh(&curr_table->list_lock); - return ans; - } - - /* Check if we need to handle the collision, do not need to on REMOVE */ - if(orig_hash_result != hash_result && !(info->check_set & IPT_RECENT_REMOVE)) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): Collision in hash table. (or: %d,hr: %d,oa: %u,ha: %u)\n", - orig_hash_result, - hash_result, - r_list[hash_table[orig_hash_result]].addr, - addr); -#endif - - /* We had a collision. - * orig_hash_result is where we started, hash_result is where we ended up. - * So, swap them because we are likely to see the same guy again sooner */ -#ifdef DEBUG - if(debug) { - printk(KERN_INFO RECENT_NAME ": match(): Collision; hash_table[orig_hash_result] = %d\n",hash_table[orig_hash_result]); - printk(KERN_INFO RECENT_NAME ": match(): Collision; r_list[hash_table[orig_hash_result]].hash_entry = %d\n", - r_list[hash_table[orig_hash_result]].hash_entry); - } -#endif - - r_list[hash_table[orig_hash_result]].hash_entry = hash_result; - - - temp = hash_table[orig_hash_result]; -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): Collision; hash_table[hash_result] = %d\n",hash_table[hash_result]); -#endif - hash_table[orig_hash_result] = hash_table[hash_result]; - hash_table[hash_result] = temp; - temp = hash_result; - hash_result = orig_hash_result; - orig_hash_result = temp; - time_info[r_list[hash_table[orig_hash_result]].time_pos].position = hash_table[orig_hash_result]; - if(hash_table[hash_result] != -1) { - r_list[hash_table[hash_result]].hash_entry = hash_result; - time_info[r_list[hash_table[hash_result]].time_pos].position = hash_table[hash_result]; - } - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): Collision handled.\n"); -#endif + t = recent_table_lookup(info->name); + e = recent_entry_lookup(t, addr, + info->check_set & IPT_RECENT_TTL ? ttl : 0); + if (e == NULL) { + if (!(info->check_set & IPT_RECENT_SET)) + goto out; + e = recent_entry_init(t, addr, ttl); + if (e == NULL) + *hotdrop = 1; + ret ^= 1; + goto out; } - if(hash_table[hash_result] == -1) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): New table entry. (hr: %d,ha: %u)\n", - hash_result, addr); -#endif - - /* New item found and IPT_RECENT_SET, so we need to add it */ - location = time_info[curr_table->time_pos].position; - hash_table[r_list[location].hash_entry] = -1; - hash_table[hash_result] = location; - memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long)); - r_list[location].time_pos = curr_table->time_pos; - r_list[location].addr = addr; - r_list[location].ttl = ttl; - r_list[location].last_seen = now; - r_list[location].oldest_pkt = 1; - r_list[location].last_pkts[0] = now; - r_list[location].hash_entry = hash_result; - time_info[curr_table->time_pos].time = r_list[location].last_seen; - curr_table->time_pos = (curr_table->time_pos + 1) % ip_list_tot; - - ans = !info->invert; - } else { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): Existing table entry. (hr: %d,ha: %u)\n", - hash_result, - addr); -#endif - - /* Existing item found */ - location = hash_table[hash_result]; - /* We have a match on address, now to make sure it meets all requirements for a - * full match. */ - if(info->check_set & IPT_RECENT_CHECK || info->check_set & IPT_RECENT_UPDATE) { - if(!info->seconds && !info->hit_count) ans = !info->invert; else ans = info->invert; - if(info->seconds && !info->hit_count) { - if(time_before_eq(now,r_list[location].last_seen+info->seconds*HZ)) ans = !info->invert; else ans = info->invert; - } - if(info->seconds && info->hit_count) { - for(pkt_count = 0, hits_found = 0; pkt_count < ip_pkt_list_tot; pkt_count++) { - if(r_list[location].last_pkts[pkt_count] == 0) break; - if(time_before_eq(now,r_list[location].last_pkts[pkt_count]+info->seconds*HZ)) hits_found++; - } - if(hits_found >= info->hit_count) ans = !info->invert; else ans = info->invert; - } - if(info->hit_count && !info->seconds) { - for(pkt_count = 0, hits_found = 0; pkt_count < ip_pkt_list_tot; pkt_count++) { - if(r_list[location].last_pkts[pkt_count] == 0) break; - hits_found++; - } - if(hits_found >= info->hit_count) ans = !info->invert; else ans = info->invert; + if (info->check_set & IPT_RECENT_SET) + ret ^= 1; + else if (info->check_set & IPT_RECENT_REMOVE) { + recent_entry_remove(t, e); + ret ^= 1; + } else if (info->check_set & (IPT_RECENT_CHECK | IPT_RECENT_UPDATE)) { + unsigned long t = jiffies - info->seconds * HZ; + unsigned int i, hits = 0; + + for (i = 0; i < e->nstamps; i++) { + if (info->seconds && time_after(t, e->stamps[i])) + continue; + if (++hits >= info->hit_count) { + ret ^= 1; + break; } } -#ifdef DEBUG - if(debug) { - if(ans) - printk(KERN_INFO RECENT_NAME ": match(): match addr: %u\n",addr); - else - printk(KERN_INFO RECENT_NAME ": match(): no match addr: %u\n",addr); - } -#endif - - /* If and only if we have been asked to SET, or to UPDATE (on match) do we add the - * current timestamp to the last_seen. */ - if((info->check_set & IPT_RECENT_SET && (ans = !info->invert)) || (info->check_set & IPT_RECENT_UPDATE && ans)) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): SET or UPDATE; updating time info.\n"); -#endif - /* Have to update our time info */ - time_loc = r_list[location].time_pos; - time_info[time_loc].time = now; - time_info[time_loc].position = location; - while((time_info[(time_loc+1) % ip_list_tot].time < time_info[time_loc].time) && ((time_loc+1) % ip_list_tot) != curr_table->time_pos) { - time_temp = time_info[time_loc].time; - time_info[time_loc].time = time_info[(time_loc+1)%ip_list_tot].time; - time_info[(time_loc+1)%ip_list_tot].time = time_temp; - time_temp = time_info[time_loc].position; - time_info[time_loc].position = time_info[(time_loc+1)%ip_list_tot].position; - time_info[(time_loc+1)%ip_list_tot].position = time_temp; - r_list[time_info[time_loc].position].time_pos = time_loc; - r_list[time_info[(time_loc+1)%ip_list_tot].position].time_pos = (time_loc+1)%ip_list_tot; - time_loc = (time_loc+1) % ip_list_tot; - } - r_list[location].time_pos = time_loc; - r_list[location].ttl = ttl; - r_list[location].last_pkts[r_list[location].oldest_pkt] = now; - r_list[location].oldest_pkt = ++r_list[location].oldest_pkt % ip_pkt_list_tot; - r_list[location].last_seen = now; - } - /* If we have been asked to remove the entry from the list, just set it to 0 */ - if(info->check_set & IPT_RECENT_REMOVE) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): REMOVE; clearing entry (or: %d, hr: %d).\n",orig_hash_result,hash_result); -#endif - /* Check if this is part of a collision chain */ - while(hash_table[(orig_hash_result+1) % ip_list_hash_size] != -1) { - orig_hash_result++; - if(hash_func(r_list[hash_table[orig_hash_result]].addr,ip_list_hash_size) == hash_result) { - /* Found collision chain, how deep does this rabbit hole go? */ -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): REMOVE; found collision chain.\n"); -#endif - end_collision_chain = orig_hash_result; - } - } - if(end_collision_chain != -1) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match(): REMOVE; part of collision chain, moving to end.\n"); -#endif - /* Part of a collision chain, swap it with the end of the chain - * before removing. */ - r_list[hash_table[end_collision_chain]].hash_entry = hash_result; - temp = hash_table[end_collision_chain]; - hash_table[end_collision_chain] = hash_table[hash_result]; - hash_table[hash_result] = temp; - time_info[r_list[hash_table[hash_result]].time_pos].position = hash_table[hash_result]; - hash_result = end_collision_chain; - r_list[hash_table[hash_result]].hash_entry = hash_result; - time_info[r_list[hash_table[hash_result]].time_pos].position = hash_table[hash_result]; - } - location = hash_table[hash_result]; - hash_table[r_list[location].hash_entry] = -1; - time_loc = r_list[location].time_pos; - time_info[time_loc].time = 0; - time_info[time_loc].position = location; - while((time_info[(time_loc+1) % ip_list_tot].time < time_info[time_loc].time) && ((time_loc+1) % ip_list_tot) != curr_table->time_pos) { - time_temp = time_info[time_loc].time; - time_info[time_loc].time = time_info[(time_loc+1)%ip_list_tot].time; - time_info[(time_loc+1)%ip_list_tot].time = time_temp; - time_temp = time_info[time_loc].position; - time_info[time_loc].position = time_info[(time_loc+1)%ip_list_tot].position; - time_info[(time_loc+1)%ip_list_tot].position = time_temp; - r_list[time_info[time_loc].position].time_pos = time_loc; - r_list[time_info[(time_loc+1)%ip_list_tot].position].time_pos = (time_loc+1)%ip_list_tot; - time_loc = (time_loc+1) % ip_list_tot; - } - r_list[location].time_pos = time_loc; - r_list[location].last_seen = 0; - r_list[location].addr = 0; - r_list[location].ttl = 0; - memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long)); - r_list[location].oldest_pkt = 0; - ans = !info->invert; - } - spin_unlock_bh(&curr_table->list_lock); - return ans; } - spin_unlock_bh(&curr_table->list_lock); -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": match() left.\n"); -#endif - return ans; + if (info->check_set & IPT_RECENT_SET || + (info->check_set & IPT_RECENT_UPDATE && ret)) { + recent_entry_update(t, e); + e->ttl = ttl; + } +out: + spin_unlock_bh(&recent_lock); + return ret; } -/* This function is to verify that the rule given during the userspace iptables - * command is correct. - * If the command is valid then we check if the table name referred to by the - * rule exists, if not it is created. - */ static int -checkentry(const char *tablename, - const void *ip, - const struct xt_match *match, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) +ipt_recent_checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, + unsigned int matchsize, unsigned int hook_mask) { - int flag = 0, c; - unsigned long *hold; const struct ipt_recent_info *info = matchinfo; - struct recent_ip_tables *curr_table, *find_table, *last_table; - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry() entered.\n"); -#endif - - /* seconds and hit_count only valid for CHECK/UPDATE */ - if(info->check_set & IPT_RECENT_SET) { flag++; if(info->seconds || info->hit_count) return 0; } - if(info->check_set & IPT_RECENT_REMOVE) { flag++; if(info->seconds || info->hit_count) return 0; } - if(info->check_set & IPT_RECENT_CHECK) flag++; - if(info->check_set & IPT_RECENT_UPDATE) flag++; - - /* One and only one of these should ever be set */ - if(flag != 1) return 0; - - /* Name must be set to something */ - if(!info->name || !info->name[0]) return 0; + struct recent_table *t; + unsigned i; + int ret = 0; - /* Things look good, create a list for this if it does not exist */ - /* Lock the linked list while we play with it */ - spin_lock_bh(&recent_lock); - - /* Look for an entry with this name already created */ - /* Finds the end of the list and the entry before the end if current name does not exist */ - find_table = r_tables; - while( (last_table = find_table) && strncmp(info->name,find_table->name,IPT_RECENT_NAME_LEN) && (find_table = find_table->next) ); + if (hweight8(info->check_set & + (IPT_RECENT_SET | IPT_RECENT_REMOVE | + IPT_RECENT_CHECK | IPT_RECENT_UPDATE)) != 1) + return 0; + if ((info->check_set & (IPT_RECENT_SET | IPT_RECENT_REMOVE)) && + (info->seconds || info->hit_count)) + return 0; + if (info->name[0] == '\0' || + strnlen(info->name, IPT_RECENT_NAME_LEN) == IPT_RECENT_NAME_LEN) + return 0; - /* If a table already exists just increment the count on that table and return */ - if(find_table) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: table found (%s), incrementing count.\n",info->name); -#endif - find_table->count++; - spin_unlock_bh(&recent_lock); - return 1; + mutex_lock(&recent_mutex); + t = recent_table_lookup(info->name); + if (t != NULL) { + t->refcnt++; + ret = 1; + goto out; } - spin_unlock_bh(&recent_lock); - - /* Table with this name not found */ - /* Allocate memory for new linked list item */ - -#ifdef DEBUG - if(debug) { - printk(KERN_INFO RECENT_NAME ": checkentry: no table found (%s)\n",info->name); - printk(KERN_INFO RECENT_NAME ": checkentry: Allocationg %d for link-list entry.\n",sizeof(struct recent_ip_tables)); + t = kzalloc(sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size, + GFP_KERNEL); + if (t == NULL) + goto out; + t->refcnt = 1; + strcpy(t->name, info->name); + INIT_LIST_HEAD(&t->lru_list); + for (i = 0; i < ip_list_hash_size; i++) + INIT_LIST_HEAD(&t->iphash[i]); +#ifdef CONFIG_PROC_FS + t->proc = create_proc_entry(t->name, ip_list_perms, proc_dir); + if (t->proc == NULL) { + kfree(t); + goto out; } + t->proc->proc_fops = &recent_fops; + t->proc->data = t; #endif + spin_lock_bh(&recent_lock); + list_add_tail(&t->list, &tables); + spin_unlock_bh(&recent_lock); + ret = 1; +out: + mutex_unlock(&recent_mutex); + return ret; +} - curr_table = vmalloc(sizeof(struct recent_ip_tables)); - if(curr_table == NULL) return 0; - - spin_lock_init(&curr_table->list_lock); - curr_table->next = NULL; - curr_table->count = 1; - curr_table->time_pos = 0; - strncpy(curr_table->name,info->name,IPT_RECENT_NAME_LEN); - curr_table->name[IPT_RECENT_NAME_LEN-1] = '\0'; - - /* Allocate memory for this table and the list of packets in each entry. */ -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: Allocating %d for table (%s).\n", - sizeof(struct recent_ip_list)*ip_list_tot, - info->name); -#endif - - curr_table->table = vmalloc(sizeof(struct recent_ip_list)*ip_list_tot); - if(curr_table->table == NULL) { vfree(curr_table); return 0; } - memset(curr_table->table,0,sizeof(struct recent_ip_list)*ip_list_tot); -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: Allocating %d for pkt_list.\n", - sizeof(unsigned long)*ip_pkt_list_tot*ip_list_tot); -#endif - - hold = vmalloc(sizeof(unsigned long)*ip_pkt_list_tot*ip_list_tot); -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: After pkt_list allocation.\n"); -#endif - if(hold == NULL) { - printk(KERN_INFO RECENT_NAME ": checkentry: unable to allocate for pkt_list.\n"); - vfree(curr_table->table); - vfree(curr_table); - return 0; - } - for(c = 0; c < ip_list_tot; c++) { - curr_table->table[c].last_pkts = hold + c*ip_pkt_list_tot; - } +static void +ipt_recent_destroy(const struct xt_match *match, void *matchinfo, + unsigned int matchsize) +{ + const struct ipt_recent_info *info = matchinfo; + struct recent_table *t; - /* Allocate memory for the hash table */ -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: Allocating %d for hash_table.\n", - sizeof(int)*ip_list_hash_size); + mutex_lock(&recent_mutex); + t = recent_table_lookup(info->name); + if (--t->refcnt == 0) { + spin_lock_bh(&recent_lock); + list_del(&t->list); + spin_unlock_bh(&recent_lock); + recent_table_flush(t); +#ifdef CONFIG_PROC_FS + remove_proc_entry(t->name, proc_dir); #endif - - curr_table->hash_table = vmalloc(sizeof(int)*ip_list_hash_size); - if(!curr_table->hash_table) { - printk(KERN_INFO RECENT_NAME ": checkentry: unable to allocate for hash_table.\n"); - vfree(hold); - vfree(curr_table->table); - vfree(curr_table); - return 0; - } - - for(c = 0; c < ip_list_hash_size; c++) { - curr_table->hash_table[c] = -1; + kfree(t); } + mutex_unlock(&recent_mutex); +} - /* Allocate memory for the time info */ -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: Allocating %d for time_info.\n", - sizeof(struct time_info_list)*ip_list_tot); -#endif +#ifdef CONFIG_PROC_FS +struct recent_iter_state { + struct recent_table *table; + unsigned int bucket; +}; - curr_table->time_info = vmalloc(sizeof(struct time_info_list)*ip_list_tot); - if(!curr_table->time_info) { - printk(KERN_INFO RECENT_NAME ": checkentry: unable to allocate for time_info.\n"); - vfree(curr_table->hash_table); - vfree(hold); - vfree(curr_table->table); - vfree(curr_table); - return 0; - } - for(c = 0; c < ip_list_tot; c++) { - curr_table->time_info[c].position = c; - curr_table->time_info[c].time = 0; - } +static void *recent_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct recent_iter_state *st = seq->private; + struct recent_table *t = st->table; + struct recent_entry *e; + loff_t p = *pos; - /* Put the new table in place */ spin_lock_bh(&recent_lock); - find_table = r_tables; - while( (last_table = find_table) && strncmp(info->name,find_table->name,IPT_RECENT_NAME_LEN) && (find_table = find_table->next) ); - - /* If a table already exists just increment the count on that table and return */ - if(find_table) { - find_table->count++; - spin_unlock_bh(&recent_lock); -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: table found (%s), created by other process.\n",info->name); -#endif - vfree(curr_table->time_info); - vfree(curr_table->hash_table); - vfree(hold); - vfree(curr_table->table); - vfree(curr_table); - return 1; - } - if(!last_table) r_tables = curr_table; else last_table->next = curr_table; - - spin_unlock_bh(&recent_lock); -#ifdef CONFIG_PROC_FS - /* Create our proc 'status' entry. */ - curr_table->status_proc = create_proc_entry(curr_table->name, ip_list_perms, proc_net_ipt_recent); - if (!curr_table->status_proc) { - printk(KERN_INFO RECENT_NAME ": checkentry: unable to allocate for /proc entry.\n"); - /* Destroy the created table */ - spin_lock_bh(&recent_lock); - last_table = NULL; - curr_table = r_tables; - if(!curr_table) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry() create_proc failed, no tables.\n"); -#endif - spin_unlock_bh(&recent_lock); - return 0; - } - while( strncmp(info->name,curr_table->name,IPT_RECENT_NAME_LEN) && (last_table = curr_table) && (curr_table = curr_table->next) ); - if(!curr_table) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry() create_proc failed, table already destroyed.\n"); -#endif - spin_unlock_bh(&recent_lock); - return 0; + for (st->bucket = 0; st->bucket < ip_list_hash_size; st->bucket++) { + list_for_each_entry(e, &t->iphash[st->bucket], list) { + if (p-- == 0) + return e; } - if(last_table) last_table->next = curr_table->next; else r_tables = curr_table->next; - spin_unlock_bh(&recent_lock); - vfree(curr_table->time_info); - vfree(curr_table->hash_table); - vfree(hold); - vfree(curr_table->table); - vfree(curr_table); - return 0; } - - curr_table->status_proc->owner = THIS_MODULE; - curr_table->status_proc->data = curr_table; - wmb(); - curr_table->status_proc->read_proc = ip_recent_get_info; - curr_table->status_proc->write_proc = ip_recent_ctrl; -#endif /* CONFIG_PROC_FS */ - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": checkentry() left.\n"); -#endif + return NULL; +} - return 1; +static void *recent_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct recent_iter_state *st = seq->private; + struct recent_table *t = st->table; + struct recent_entry *e = v; + struct list_head *head = e->list.next; + + while (head == &t->iphash[st->bucket]) { + if (++st->bucket >= ip_list_hash_size) + return NULL; + head = t->iphash[st->bucket].next; + } + (*pos)++; + return list_entry(head, struct recent_entry, list); } -/* This function is called in the event that a rule matching this module is - * removed. - * When this happens we need to check if there are no other rules matching - * the table given. If that is the case then we remove the table and clean - * up its memory. - */ -static void -destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) +static void recent_seq_stop(struct seq_file *s, void *v) { - const struct ipt_recent_info *info = matchinfo; - struct recent_ip_tables *curr_table, *last_table; + spin_unlock_bh(&recent_lock); +} -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": destroy() entered.\n"); -#endif +static int recent_seq_show(struct seq_file *seq, void *v) +{ + struct recent_entry *e = v; + unsigned int i; + + i = (e->index - 1) % ip_pkt_list_tot; + seq_printf(seq, "src=%u.%u.%u.%u ttl: %u last_seen: %lu oldest_pkt: %u", + NIPQUAD(e->addr), e->ttl, e->stamps[i], e->index); + for (i = 0; i < e->nstamps; i++) + seq_printf(seq, "%s %lu", i ? "," : "", e->stamps[i]); + seq_printf(seq, "\n"); + return 0; +} - if(matchsize != IPT_ALIGN(sizeof(struct ipt_recent_info))) return; +static struct seq_operations recent_seq_ops = { + .start = recent_seq_start, + .next = recent_seq_next, + .stop = recent_seq_stop, + .show = recent_seq_show, +}; - /* Lock the linked list while we play with it */ - spin_lock_bh(&recent_lock); +static int recent_seq_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *pde = PDE(inode); + struct seq_file *seq; + struct recent_iter_state *st; + int ret; + + st = kzalloc(sizeof(*st), GFP_KERNEL); + if (st == NULL) + return -ENOMEM; + ret = seq_open(file, &recent_seq_ops); + if (ret) + kfree(st); + st->table = pde->data; + seq = file->private_data; + seq->private = st; + return ret; +} - /* Look for an entry with this name already created */ - /* Finds the end of the list and the entry before the end if current name does not exist */ - last_table = NULL; - curr_table = r_tables; - if(!curr_table) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": destroy() No tables found, leaving.\n"); -#endif +static ssize_t recent_proc_write(struct file *file, const char __user *input, + size_t size, loff_t *loff) +{ + struct proc_dir_entry *pde = PDE(file->f_dentry->d_inode); + struct recent_table *t = pde->data; + struct recent_entry *e; + char buf[sizeof("+255.255.255.255")], *c = buf; + u_int32_t addr; + int add; + + if (size > sizeof(buf)) + size = sizeof(buf); + if (copy_from_user(buf, input, size)) + return -EFAULT; + while (isspace(*c)) + c++; + + if (size - (c - buf) < 5) + return c - buf; + if (!strncmp(c, "clear", 5)) { + c += 5; + spin_lock_bh(&recent_lock); + recent_table_flush(t); spin_unlock_bh(&recent_lock); - return; + return c - buf; } - while( strncmp(info->name,curr_table->name,IPT_RECENT_NAME_LEN) && (last_table = curr_table) && (curr_table = curr_table->next) ); - /* If a table does not exist then do nothing and return */ - if(!curr_table) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": destroy() table not found, leaving.\n"); -#endif - spin_unlock_bh(&recent_lock); - return; + switch (*c) { + case '-': + add = 0; + c++; + break; + case '+': + c++; + default: + add = 1; + break; } + addr = in_aton(c); - curr_table->count--; - - /* If count is still non-zero then there are still rules referenceing it so we do nothing */ - if(curr_table->count) { -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": destroy() table found, non-zero count, leaving.\n"); -#endif - spin_unlock_bh(&recent_lock); - return; + spin_lock_bh(&recent_lock); + e = recent_entry_lookup(t, addr, 0); + if (e == NULL) { + if (add) + recent_entry_init(t, addr, 0); + } else { + if (add) + recent_entry_update(t, e); + else + recent_entry_remove(t, e); } - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": destroy() table found, zero count, removing.\n"); -#endif - - /* Count must be zero so we remove this table from the list */ - if(last_table) last_table->next = curr_table->next; else r_tables = curr_table->next; - spin_unlock_bh(&recent_lock); + return size; +} - /* lock to make sure any late-runners still using this after we removed it from - * the list finish up then remove everything */ - spin_lock_bh(&curr_table->list_lock); - spin_unlock_bh(&curr_table->list_lock); - -#ifdef CONFIG_PROC_FS - if(curr_table->status_proc) remove_proc_entry(curr_table->name,proc_net_ipt_recent); +static struct file_operations recent_fops = { + .open = recent_seq_open, + .read = seq_read, + .write = recent_proc_write, + .release = seq_release_private, + .owner = THIS_MODULE, +}; #endif /* CONFIG_PROC_FS */ - vfree(curr_table->table[0].last_pkts); - vfree(curr_table->table); - vfree(curr_table->hash_table); - vfree(curr_table->time_info); - vfree(curr_table); - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": destroy() left.\n"); -#endif - return; -} - -/* This is the structure we pass to ipt_register to register our - * module with iptables. - */ static struct ipt_match recent_match = { .name = "recent", - .match = match, + .match = ipt_recent_match, .matchsize = sizeof(struct ipt_recent_info), - .checkentry = checkentry, - .destroy = destroy, - .me = THIS_MODULE + .checkentry = ipt_recent_checkentry, + .destroy = ipt_recent_destroy, + .me = THIS_MODULE, }; -/* Kernel module initialization. */ static int __init ipt_recent_init(void) { - int err, count; + int err; - printk(version); -#ifdef CONFIG_PROC_FS - proc_net_ipt_recent = proc_mkdir("ipt_recent",proc_net); - if(!proc_net_ipt_recent) return -ENOMEM; -#endif - - if(ip_list_hash_size && ip_list_hash_size <= ip_list_tot) { - printk(KERN_WARNING RECENT_NAME ": ip_list_hash_size too small, resetting to default.\n"); - ip_list_hash_size = 0; - } - - if(!ip_list_hash_size) { - ip_list_hash_size = ip_list_tot*3; - count = 2*2; - while(ip_list_hash_size > count) count = count*2; - ip_list_hash_size = count; - } - -#ifdef DEBUG - if(debug) printk(KERN_INFO RECENT_NAME ": ip_list_hash_size: %d\n",ip_list_hash_size); -#endif + if (!ip_list_tot || !ip_pkt_list_tot || ip_pkt_list_tot > 255) + return -EINVAL; + ip_list_hash_size = 1 << fls(ip_list_tot); err = ipt_register_match(&recent_match); +#ifdef CONFIG_PROC_FS if (err) - remove_proc_entry("ipt_recent", proc_net); + return err; + proc_dir = proc_mkdir("ipt_recent", proc_net); + if (proc_dir == NULL) { + ipt_unregister_match(&recent_match); + err = -ENOMEM; + } +#endif return err; } -/* Kernel module destruction. */ -static void __exit ipt_recent_fini(void) +static void __exit ipt_recent_exit(void) { + BUG_ON(!list_empty(&tables)); ipt_unregister_match(&recent_match); - - remove_proc_entry("ipt_recent",proc_net); +#ifdef CONFIG_PROC_FS + remove_proc_entry("ipt_recent", proc_net); +#endif } -/* Register our module with the kernel. */ module_init(ipt_recent_init); -module_exit(ipt_recent_fini); +module_exit(ipt_recent_exit); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 5bc9f64d7b5b..8cc8e1b36778 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -145,7 +145,7 @@ static unsigned int ipv4_conntrack_help(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(*pskb, &ctinfo); - if (!ct) + if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY) return NF_ACCEPT; help = nfct_help(ct); @@ -348,6 +348,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) .tuple.dst.u.tcp.port; sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL] .tuple.dst.u3.ip; + memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); DEBUGP("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n", NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port)); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 4b0d361cc6e6..663a73ee3f2f 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -235,7 +235,7 @@ icmp_error(struct sk_buff *skb, unsigned int dataoff, } /* See ip_conntrack_proto_tcp.c */ - if (hooknum == NF_IP_PRE_ROUTING && + if (nf_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && nf_ip_checksum(skb, hooknum, dataoff, 0)) { if (LOG_INVALID(IPPROTO_ICMP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, |