From 71c3ebfdb27b50dcaef38b6f70da82b9142c5fb6 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 4 Jan 2010 15:21:31 +0100 Subject: netfilter: SNMP NAT: correct the size argument to kzalloc obj has type struct snmp_object **, not struct snmp_object *. But indeed it is not even clear why kmalloc is needed. The memory is freed by the end of the function, so the local variable of pointer type should be sufficient. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // @disable sizeof_type_expr@ type T; T **x; @@ x = <+...sizeof( - T + *x )...+> // Signed-off-by: Julia Lawall Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_snmp_basic.c | 31 +++++++++++-------------------- 1 file changed, 11 insertions(+), 20 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d9521f6f9ed..0b9c7ce3d6c 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1038,7 +1038,7 @@ static int snmp_parse_mangle(unsigned char *msg, unsigned int cls, con, tag, vers, pdutype; struct asn1_ctx ctx; struct asn1_octstr comm; - struct snmp_object **obj; + struct snmp_object *obj; if (debug > 1) hex_dump(msg, len); @@ -1148,43 +1148,34 @@ static int snmp_parse_mangle(unsigned char *msg, if (cls != ASN1_UNI || con != ASN1_CON || tag != ASN1_SEQ) return 0; - obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC); - if (obj == NULL) { - if (net_ratelimit()) - printk(KERN_WARNING "OOM in bsalg(%d)\n", __LINE__); - return 0; - } - while (!asn1_eoc_decode(&ctx, eoc)) { unsigned int i; - if (!snmp_object_decode(&ctx, obj)) { - if (*obj) { - kfree((*obj)->id); - kfree(*obj); + if (!snmp_object_decode(&ctx, &obj)) { + if (obj) { + kfree(obj->id); + kfree(obj); } - kfree(obj); return 0; } if (debug > 1) { printk(KERN_DEBUG "bsalg: object: "); - for (i = 0; i < (*obj)->id_len; i++) { + for (i = 0; i < obj->id_len; i++) { if (i > 0) printk("."); - printk("%lu", (*obj)->id[i]); + printk("%lu", obj->id[i]); } - printk(": type=%u\n", (*obj)->type); + printk(": type=%u\n", obj->type); } - if ((*obj)->type == SNMP_IPADDR) + if (obj->type == SNMP_IPADDR) mangle_address(ctx.begin, ctx.pointer - 4 , map, check); - kfree((*obj)->id); - kfree(*obj); + kfree(obj->id); + kfree(obj); } - kfree(obj); if (!asn1_eoc_decode(&ctx, eoc)) return 0; -- cgit v1.2.3 From 89bc7a0f64de7bed2e0bc68a23d75699a610cd37 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 4 Jan 2010 16:26:03 +0100 Subject: netfilter: xt_recent: save 8 bytes per htable Moving rnd_inited into the hole after the uint8 lets go of the uint32 rnd_inited was using, plus the padding that would follow the int group. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- net/netfilter/xt_hashlimit.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index dd16e404424..5bdc1fbf3ad 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -81,13 +81,13 @@ struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ atomic_t use; u_int8_t family; + bool rnd_initialized; struct hashlimit_cfg1 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ - int rnd_initialized; unsigned int count; /* number entries in table */ struct timer_list timer; /* timer for gc */ @@ -150,7 +150,7 @@ dsthash_alloc_init(struct xt_hashlimit_htable *ht, * the first hashtable entry */ if (!ht->rnd_initialized) { get_random_bytes(&ht->rnd, sizeof(ht->rnd)); - ht->rnd_initialized = 1; + ht->rnd_initialized = true; } if (ht->cfg.max && ht->count >= ht->cfg.max) { @@ -235,7 +235,7 @@ static int htable_create_v0(struct xt_hashlimit_info *minfo, u_int8_t family) atomic_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; - hinfo->rnd_initialized = 0; + hinfo->rnd_initialized = false; spin_lock_init(&hinfo->lock); hinfo->pde = proc_create_data(minfo->name, 0, (family == NFPROTO_IPV4) ? @@ -296,7 +296,7 @@ static int htable_create(struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) atomic_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; - hinfo->rnd_initialized = 0; + hinfo->rnd_initialized = false; spin_lock_init(&hinfo->lock); hinfo->pde = proc_create_data(minfo->name, 0, -- cgit v1.2.3 From 5191d50192ec1281e51cbcb5248cb2667ff4d896 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 4 Jan 2010 16:27:25 +0100 Subject: netfilter: xtables: do not grab random bytes at __init "It is deliberately not done in the init function, since we might not have sufficient random while booting." Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- net/netfilter/xt_NFQUEUE.c | 6 +++++- net/netfilter/xt_RATEEST.c | 7 ++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index f28f6a5fc02..12dcd7007c3 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -28,6 +28,7 @@ MODULE_ALIAS("ip6t_NFQUEUE"); MODULE_ALIAS("arpt_NFQUEUE"); static u32 jhash_initval __read_mostly; +static bool rnd_inited __read_mostly; static unsigned int nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par) @@ -90,6 +91,10 @@ static bool nfqueue_tg_v1_check(const struct xt_tgchk_param *par) const struct xt_NFQ_info_v1 *info = par->targinfo; u32 maxid; + if (unlikely(!rnd_inited)) { + get_random_bytes(&jhash_initval, sizeof(jhash_initval)); + rnd_inited = true; + } if (info->queues_total == 0) { pr_err("NFQUEUE: number of total queues is 0\n"); return false; @@ -135,7 +140,6 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = { static int __init nfqueue_tg_init(void) { - get_random_bytes(&jhash_initval, sizeof(jhash_initval)); return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index d80b8192e0d..87ae97e5516 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -23,6 +23,7 @@ static DEFINE_MUTEX(xt_rateest_mutex); #define RATEEST_HSIZE 16 static struct hlist_head rateest_hash[RATEEST_HSIZE] __read_mostly; static unsigned int jhash_rnd __read_mostly; +static bool rnd_inited __read_mostly; static unsigned int xt_rateest_hash(const char *name) { @@ -93,6 +94,11 @@ static bool xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) struct gnet_estimator est; } cfg; + if (unlikely(!rnd_inited)) { + get_random_bytes(&jhash_rnd, sizeof(jhash_rnd)); + rnd_inited = true; + } + est = xt_rateest_lookup(info->name); if (est) { /* @@ -164,7 +170,6 @@ static int __init xt_rateest_tg_init(void) for (i = 0; i < ARRAY_SIZE(rateest_hash); i++) INIT_HLIST_HEAD(&rateest_hash[i]); - get_random_bytes(&jhash_rnd, sizeof(jhash_rnd)); return xt_register_target(&xt_rateest_tg_reg); } -- cgit v1.2.3 From 294188ae32f984a072c64c959354b2f6f52f80a7 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 4 Jan 2010 16:28:38 +0100 Subject: netfilter: xtables: obtain random bytes earlier, in checkentry We can initialize the random hash bytes on checkentry. This is preferable since it is outside the hot path. Reference: http://bugzilla.netfilter.org/show_bug.cgi?id=621 Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- net/netfilter/xt_connlimit.c | 17 ++++++----------- net/netfilter/xt_recent.c | 20 ++++++++------------ 2 files changed, 14 insertions(+), 23 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 38f03f75a63..8103bef78e4 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -40,15 +40,11 @@ struct xt_connlimit_data { spinlock_t lock; }; -static u_int32_t connlimit_rnd; -static bool connlimit_rnd_inited; +static u_int32_t connlimit_rnd __read_mostly; +static bool connlimit_rnd_inited __read_mostly; static inline unsigned int connlimit_iphash(__be32 addr) { - if (unlikely(!connlimit_rnd_inited)) { - get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd)); - connlimit_rnd_inited = true; - } return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF; } @@ -59,11 +55,6 @@ connlimit_iphash6(const union nf_inet_addr *addr, union nf_inet_addr res; unsigned int i; - if (unlikely(!connlimit_rnd_inited)) { - get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd)); - connlimit_rnd_inited = true; - } - for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) res.ip6[i] = addr->ip6[i] & mask->ip6[i]; @@ -226,6 +217,10 @@ static bool connlimit_mt_check(const struct xt_mtchk_param *par) struct xt_connlimit_info *info = par->matchinfo; unsigned int i; + if (unlikely(!connlimit_rnd_inited)) { + get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd)); + connlimit_rnd_inited = true; + } if (nf_ct_l3proto_try_module_get(par->family) < 0) { printk(KERN_WARNING "cannot load conntrack support for " "address family %u\n", par->family); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index fc70a49c0af..768d01ff1fe 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -90,25 +90,17 @@ static struct proc_dir_entry *recent_proc_dir; static const struct file_operations recent_old_fops, recent_mt_fops; #endif -static u_int32_t hash_rnd; -static bool hash_rnd_initted; +static u_int32_t hash_rnd __read_mostly; +static bool hash_rnd_inited __read_mostly; -static unsigned int recent_entry_hash4(const union nf_inet_addr *addr) +static inline unsigned int recent_entry_hash4(const union nf_inet_addr *addr) { - if (!hash_rnd_initted) { - get_random_bytes(&hash_rnd, sizeof(hash_rnd)); - hash_rnd_initted = true; - } return jhash_1word((__force u32)addr->ip, hash_rnd) & (ip_list_hash_size - 1); } -static unsigned int recent_entry_hash6(const union nf_inet_addr *addr) +static inline unsigned int recent_entry_hash6(const union nf_inet_addr *addr) { - if (!hash_rnd_initted) { - get_random_bytes(&hash_rnd, sizeof(hash_rnd)); - hash_rnd_initted = true; - } return jhash2((u32 *)addr->ip6, ARRAY_SIZE(addr->ip6), hash_rnd) & (ip_list_hash_size - 1); } @@ -287,6 +279,10 @@ static bool recent_mt_check(const struct xt_mtchk_param *par) unsigned i; bool ret = false; + if (unlikely(!hash_rnd_inited)) { + get_random_bytes(&hash_rnd, sizeof(hash_rnd)); + hash_rnd_inited = true; + } if (hweight8(info->check_set & (XT_RECENT_SET | XT_RECENT_REMOVE | XT_RECENT_CHECK | XT_RECENT_UPDATE)) != 1) -- cgit v1.2.3 From 6f7edb4881bf51300060e89915926e070ace8c4d Mon Sep 17 00:00:00 2001 From: "Catalin(ux) M. BOIE" Date: Tue, 5 Jan 2010 05:50:24 +0100 Subject: IPVS: Allow boot time change of hash size I was very frustrated about the fact that I have to recompile the kernel to change the hash size. So, I created this patch. If IPVS is built-in you can append ip_vs.conn_tab_bits=?? to kernel command line, or, if you built IPVS as modules, you can add options ip_vs conn_tab_bits=??. To keep everything backward compatible, you still can select the size at compile time, and that will be used as default. It has been about a year since this patch was originally posted and subsequently dropped on the basis of insufficient test data. Mark Bergsma has provided the following test results which seem to strongly support the need for larger hash table sizes: We do however run into the same problem with the default setting (212 = 4096 entries), as most of our LVS balancers handle around a million connections/SLAB entries at any point in time (around 100-150 kpps load). With only 4096 hash table entries this implies that each entry consists of a linked list of 256 connections *on average*. To provide some statistics, I did an oprofile run on an 2.6.31 kernel, with both the default 4096 table size, and the same kernel recompiled with IP_VS_CONN_TAB_BITS set to 18 (218 = 262144 entries). I built a quick test setup with a part of Wikimedia/Wikipedia's live traffic mirrored by the switch to the test host. With the default setting, at ~ 120 kpps packet load we saw a typical %si CPU usage of around 30-35%, and oprofile reported a hot spot in ip_vs_conn_in_get: samples % image name app name symbol name 1719761 42.3741 ip_vs.ko ip_vs.ko ip_vs_conn_in_get 302577 7.4554 bnx2 bnx2 /bnx2 181984 4.4840 vmlinux vmlinux __ticket_spin_lock 128636 3.1695 vmlinux vmlinux ip_route_input 74345 1.8318 ip_vs.ko ip_vs.ko ip_vs_conn_out_get 68482 1.6874 vmlinux vmlinux mwait_idle After loading the recompiled kernel with 218 entries, %si CPU usage dropped in half to around 12-18%, and oprofile looks much healthier, with only 7% spent in ip_vs_conn_in_get: samples % image name app name symbol name 265641 14.4616 bnx2 bnx2 /bnx2 143251 7.7986 vmlinux vmlinux __ticket_spin_lock 140661 7.6576 ip_vs.ko ip_vs.ko ip_vs_conn_in_get 94364 5.1372 vmlinux vmlinux mwait_idle 86267 4.6964 vmlinux vmlinux ip_route_input [ horms@verge.net.au: trivial up-port and minor style fixes ] Signed-off-by: Catalin(ux) M. BOIE Cc: Mark Bergsma Signed-off-by: Simon Horman Signed-off-by: Patrick McHardy --- net/netfilter/ipvs/Kconfig | 4 ++++ net/netfilter/ipvs/ip_vs_conn.c | 42 ++++++++++++++++++++++++++++++----------- net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++---- 3 files changed, 39 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 79a69805221..c71e543d254 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -68,6 +68,10 @@ config IP_VS_TAB_BITS each hash entry uses 8 bytes, so you can estimate how much memory is needed for your box. + You can overwrite this number setting conn_tab_bits module parameter + or by appending ip_vs.conn_tab_bits=? to the kernel command line + if IP VS was compiled built-in. + comment "IPVS transport protocol load balancing support" config IP_VS_PROTO_TCP diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 27c30cf933d..60bb41a8d8d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -40,6 +40,21 @@ #include +#ifndef CONFIG_IP_VS_TAB_BITS +#define CONFIG_IP_VS_TAB_BITS 12 +#endif + +/* + * Connection hash size. Default is what was selected at compile time. +*/ +int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; +module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); +MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); + +/* size and mask values */ +int ip_vs_conn_tab_size; +int ip_vs_conn_tab_mask; + /* * Connection hash table: for input and output packets lookups of IPVS */ @@ -125,11 +140,11 @@ static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, if (af == AF_INET6) return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), (__force u32)port, proto, ip_vs_conn_rnd) - & IP_VS_CONN_TAB_MASK; + & ip_vs_conn_tab_mask; #endif return jhash_3words((__force u32)addr->ip, (__force u32)port, proto, ip_vs_conn_rnd) - & IP_VS_CONN_TAB_MASK; + & ip_vs_conn_tab_mask; } @@ -760,7 +775,7 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) int idx; struct ip_vs_conn *cp; - for(idx = 0; idx < IP_VS_CONN_TAB_SIZE; idx++) { + for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { ct_read_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (pos-- == 0) { @@ -797,7 +812,7 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) idx = l - ip_vs_conn_tab; ct_read_unlock_bh(idx); - while (++idx < IP_VS_CONN_TAB_SIZE) { + while (++idx < ip_vs_conn_tab_size) { ct_read_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { seq->private = &ip_vs_conn_tab[idx]; @@ -976,8 +991,8 @@ void ip_vs_random_dropentry(void) /* * Randomly scan 1/32 of the whole table every second */ - for (idx = 0; idx < (IP_VS_CONN_TAB_SIZE>>5); idx++) { - unsigned hash = net_random() & IP_VS_CONN_TAB_MASK; + for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { + unsigned hash = net_random() & ip_vs_conn_tab_mask; /* * Lock is actually needed in this loop. @@ -1029,7 +1044,7 @@ static void ip_vs_conn_flush(void) struct ip_vs_conn *cp; flush_again: - for (idx=0; idx Date: Mon, 11 Jan 2010 11:49:51 +0100 Subject: netfilter: nf_nat_ftp: remove (*mangle[]) array and functions, use %pI4 These functions merely exist to format a buffer and call nf_nat_mangle_tcp_packet. Format the buffer and perform the call in nf_nat_ftp instead. Use %pI4 for the IP address. Saves ~600 bytes of text old: $ size net/ipv4/netfilter/nf_nat_ftp.o text data bss dec hex filename 2187 160 408 2755 ac3 net/ipv4/netfilter/nf_nat_ftp.o new: $ size net/ipv4/netfilter/nf_nat_ftp.o text data bss dec hex filename 1532 112 288 1932 78c net/ipv4/netfilter/nf_nat_ftp.o Signed-off-by: Joe Perches Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_ftp.c | 105 ++++++++++++++-------------------------- 1 file changed, 35 insertions(+), 70 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index a1d5d58a58b..86e0e84ff0a 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -27,76 +27,29 @@ MODULE_ALIAS("ip_nat_ftp"); /* FIXME: Time out? --RR */ -static int -mangle_rfc959_packet(struct sk_buff *skb, - __be32 newip, - u_int16_t port, - unsigned int matchoff, - unsigned int matchlen, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) +static int nf_nat_ftp_fmt_cmd(enum nf_ct_ftp_type type, + char *buffer, size_t buflen, + __be32 addr, u16 port) { - char buffer[sizeof("nnn,nnn,nnn,nnn,nnn,nnn")]; - - sprintf(buffer, "%u,%u,%u,%u,%u,%u", - NIPQUAD(newip), port>>8, port&0xFF); - - pr_debug("calling nf_nat_mangle_tcp_packet\n"); - - return nf_nat_mangle_tcp_packet(skb, ct, ctinfo, matchoff, - matchlen, buffer, strlen(buffer)); -} - -/* |1|132.235.1.2|6275| */ -static int -mangle_eprt_packet(struct sk_buff *skb, - __be32 newip, - u_int16_t port, - unsigned int matchoff, - unsigned int matchlen, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - char buffer[sizeof("|1|255.255.255.255|65535|")]; - - sprintf(buffer, "|1|%u.%u.%u.%u|%u|", NIPQUAD(newip), port); - - pr_debug("calling nf_nat_mangle_tcp_packet\n"); - - return nf_nat_mangle_tcp_packet(skb, ct, ctinfo, matchoff, - matchlen, buffer, strlen(buffer)); -} - -/* |1|132.235.1.2|6275| */ -static int -mangle_epsv_packet(struct sk_buff *skb, - __be32 newip, - u_int16_t port, - unsigned int matchoff, - unsigned int matchlen, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - char buffer[sizeof("|||65535|")]; - - sprintf(buffer, "|||%u|", port); - - pr_debug("calling nf_nat_mangle_tcp_packet\n"); + switch (type) { + case NF_CT_FTP_PORT: + case NF_CT_FTP_PASV: + return snprintf(buffer, buflen, "%u,%u,%u,%u,%u,%u", + ((unsigned char *)&addr)[0], + ((unsigned char *)&addr)[1], + ((unsigned char *)&addr)[2], + ((unsigned char *)&addr)[3], + port >> 8, + port & 0xFF); + case NF_CT_FTP_EPRT: + return snprintf(buffer, buflen, "|1|%pI4|%u|", &addr, port); + case NF_CT_FTP_EPSV: + return snprintf(buffer, buflen, "|||%u|", port); + } - return nf_nat_mangle_tcp_packet(skb, ct, ctinfo, matchoff, - matchlen, buffer, strlen(buffer)); + return 0; } -static int (*mangle[])(struct sk_buff *, __be32, u_int16_t, - unsigned int, unsigned int, struct nf_conn *, - enum ip_conntrack_info) -= { - [NF_CT_FTP_PORT] = mangle_rfc959_packet, - [NF_CT_FTP_PASV] = mangle_rfc959_packet, - [NF_CT_FTP_EPRT] = mangle_eprt_packet, - [NF_CT_FTP_EPSV] = mangle_epsv_packet -}; - /* So, this packet has hit the connection tracking matching code. Mangle it, and change the expectation to match the new version. */ static unsigned int nf_nat_ftp(struct sk_buff *skb, @@ -110,6 +63,8 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, u_int16_t port; int dir = CTINFO2DIR(ctinfo); struct nf_conn *ct = exp->master; + char buffer[sizeof("|1|255.255.255.255|65535|")]; + unsigned int buflen; pr_debug("FTP_NAT: type %i, off %u len %u\n", type, matchoff, matchlen); @@ -132,11 +87,21 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, if (port == 0) return NF_DROP; - if (!mangle[type](skb, newip, port, matchoff, matchlen, ct, ctinfo)) { - nf_ct_unexpect_related(exp); - return NF_DROP; - } + buflen = nf_nat_ftp_fmt_cmd(type, buffer, sizeof(buffer), newip, port); + if (!buflen) + goto out; + + pr_debug("calling nf_nat_mangle_tcp_packet\n"); + + if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, matchoff, + matchlen, buffer, buflen)) + goto out; + return NF_ACCEPT; + +out: + nf_ct_unexpect_related(exp); + return NF_DROP; } static void __exit nf_nat_ftp_fini(void) -- cgit v1.2.3 From a79e7ac4ad77e1833e8f69e99113204d03018255 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 11 Jan 2010 11:53:31 +0100 Subject: ipvs: use standardized format in sprintf Use the same format string as net/ipv4/netfilter/nf_nat_ftp.c to encode an ipv4 address and port. Both uses should be a single common function. Signed-off-by: Joe Perches Acked-by: Simon Horman Signed-off-by: Patrick McHardy --- net/netfilter/ipvs/ip_vs_ftp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 33e2c799cba..73f38ea98f2 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -208,7 +208,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, */ from.ip = n_cp->vaddr.ip; port = n_cp->vport; - sprintf(buf, "%d,%d,%d,%d,%d,%d", NIPQUAD(from.ip), + sprintf(buf, "%u,%u,%u,%u,%u,%u", NIPQUAD(from.ip), (ntohs(port)>>8)&255, ntohs(port)&255); buf_len = strlen(buf); -- cgit v1.2.3 From 7f635d0d1bf84ad7a0032cbce9d902b9384c48b7 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 11 Jan 2010 11:55:36 +0100 Subject: netfilter: xt_osf: change %pi4 to %pI4 commit 8a27f7c90ffcb791eed7574922b51fb60b08fc89 changed the output style of %pi4 to use fixed width leading zero IP addresses "001.002.003.004". It's useful when printing multiple lines of addresses, but was a change in output style for some existing uses. Using %pI4 restores the previous output style. Signed-off-by: Joe Perches Signed-off-by: Patrick McHardy --- net/netfilter/xt_osf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 4d1a41bbd5d..4169e200588 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -334,7 +334,7 @@ static bool xt_osf_match_packet(const struct sk_buff *skb, if (info->flags & XT_OSF_LOG) nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL, - "%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n", + "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", f->genre, f->version, f->subtype, &ip->saddr, ntohs(tcp->source), &ip->daddr, ntohs(tcp->dest), @@ -349,7 +349,7 @@ static bool xt_osf_match_packet(const struct sk_buff *skb, if (!fcount && (info->flags & XT_OSF_LOG)) nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL, - "Remote OS is not known: %pi4:%u -> %pi4:%u\n", + "Remote OS is not known: %pI4:%u -> %pI4:%u\n", &ip->saddr, ntohs(tcp->source), &ip->daddr, ntohs(tcp->dest)); -- cgit v1.2.3 From cd8c20b650f49354722b8cc1f03320b004815a0a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 13 Jan 2010 16:02:14 +0100 Subject: netfilter: nfnetlink: netns support Make nfnl socket per-petns. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 13 ++++---- net/netfilter/nfnetlink.c | 65 +++++++++++++++++++++++------------- net/netfilter/nfnetlink_log.c | 3 +- net/netfilter/nfnetlink_queue.c | 2 +- 4 files changed, 52 insertions(+), 31 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 59d8064eb52..d4c5d06677f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -482,7 +482,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) } else return 0; - if (!item->report && !nfnetlink_has_listeners(group)) + if (!item->report && !nfnetlink_has_listeners(&init_net, group)) return 0; skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); @@ -559,7 +559,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - err = nfnetlink_send(skb, item->pid, group, item->report, GFP_ATOMIC); + err = nfnetlink_send(skb, &init_net, item->pid, group, item->report, + GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; @@ -571,7 +572,7 @@ nla_put_failure: nlmsg_failure: kfree_skb(skb); errout: - nfnetlink_set_err(0, group, -ENOBUFS); + nfnetlink_set_err(&init_net, 0, group, -ENOBUFS); return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ @@ -1539,7 +1540,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) return 0; if (!item->report && - !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) + !nfnetlink_has_listeners(&init_net, NFNLGRP_CONNTRACK_EXP_NEW)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); @@ -1562,7 +1563,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, + nfnetlink_send(skb, &init_net, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, item->report, GFP_ATOMIC); return 0; @@ -1572,7 +1573,7 @@ nla_put_failure: nlmsg_failure: kfree_skb(skb); errout: - nfnetlink_set_err(0, 0, -ENOBUFS); + nfnetlink_set_err(&init_net, 0, 0, -ENOBUFS); return 0; } #endif diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index eedc0c1ac7a..8eb0cc23ada 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -40,7 +40,6 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); static char __initdata nfversion[] = "0.30"; -static struct sock *nfnl = NULL; static const struct nfnetlink_subsystem *subsys_table[NFNL_SUBSYS_COUNT]; static DEFINE_MUTEX(nfnl_mutex); @@ -101,34 +100,35 @@ nfnetlink_find_client(u_int16_t type, const struct nfnetlink_subsystem *ss) return &ss->cb[cb_id]; } -int nfnetlink_has_listeners(unsigned int group) +int nfnetlink_has_listeners(struct net *net, unsigned int group) { - return netlink_has_listeners(nfnl, group); + return netlink_has_listeners(net->nfnl, group); } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); -int nfnetlink_send(struct sk_buff *skb, u32 pid, +int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo, gfp_t flags) { - return nlmsg_notify(nfnl, skb, pid, group, echo, flags); + return nlmsg_notify(net->nfnl, skb, pid, group, echo, flags); } EXPORT_SYMBOL_GPL(nfnetlink_send); -void nfnetlink_set_err(u32 pid, u32 group, int error) +void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error) { - netlink_set_err(nfnl, pid, group, error); + netlink_set_err(net->nfnl, pid, group, error); } EXPORT_SYMBOL_GPL(nfnetlink_set_err); -int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags) +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags) { - return netlink_unicast(nfnl, skb, pid, flags); + return netlink_unicast(net->nfnl, skb, pid, flags); } EXPORT_SYMBOL_GPL(nfnetlink_unicast); /* Process one complete nfnetlink message. */ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); const struct nfnl_callback *nc; const struct nfnetlink_subsystem *ss; int type, err; @@ -170,7 +170,7 @@ replay: if (err < 0) return err; - err = nc->call(nfnl, skb, nlh, (const struct nlattr **)cda); + err = nc->call(net->nfnl, skb, nlh, (const struct nlattr **)cda); if (err == -EAGAIN) goto replay; return err; @@ -184,26 +184,45 @@ static void nfnetlink_rcv(struct sk_buff *skb) nfnl_unlock(); } -static void __exit nfnetlink_exit(void) +static int __net_init nfnetlink_net_init(struct net *net) { - printk("Removing netfilter NETLINK layer.\n"); - netlink_kernel_release(nfnl); - return; + struct sock *nfnl; + + nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, NFNLGRP_MAX, + nfnetlink_rcv, NULL, THIS_MODULE); + if (!nfnl) + return -ENOMEM; + net->nfnl_stash = nfnl; + rcu_assign_pointer(net->nfnl, nfnl); + return 0; } -static int __init nfnetlink_init(void) +static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list) { - printk("Netfilter messages via NETLINK v%s.\n", nfversion); + struct net *net; - nfnl = netlink_kernel_create(&init_net, NETLINK_NETFILTER, NFNLGRP_MAX, - nfnetlink_rcv, NULL, THIS_MODULE); - if (!nfnl) { - printk(KERN_ERR "cannot initialize nfnetlink!\n"); - return -ENOMEM; - } + list_for_each_entry(net, net_exit_list, exit_list) + rcu_assign_pointer(net->nfnl, NULL); + synchronize_net(); + list_for_each_entry(net, net_exit_list, exit_list) + netlink_kernel_release(net->nfnl_stash); +} - return 0; +static struct pernet_operations nfnetlink_net_ops = { + .init = nfnetlink_net_init, + .exit_batch = nfnetlink_net_exit_batch, +}; + +static int __init nfnetlink_init(void) +{ + printk("Netfilter messages via NETLINK v%s.\n", nfversion); + return register_pernet_subsys(&nfnetlink_net_ops); } +static void __exit nfnetlink_exit(void) +{ + printk("Removing netfilter NETLINK layer.\n"); + unregister_pernet_subsys(&nfnetlink_net_ops); +} module_init(nfnetlink_init); module_exit(nfnetlink_exit); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 9de0470d557..285e9029a9f 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -323,7 +323,8 @@ __nfulnl_send(struct nfulnl_instance *inst) NLMSG_DONE, sizeof(struct nfgenmsg)); - status = nfnetlink_unicast(inst->skb, inst->peer_pid, MSG_DONTWAIT); + status = nfnetlink_unicast(inst->skb, &init_net, inst->peer_pid, + MSG_DONTWAIT); inst->qlen = 0; inst->skb = NULL; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7e3fa410641..5c589b27d6e 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -420,7 +420,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } /* nfnetlink_unicast will either free the nskb or add it to a socket */ - err = nfnetlink_unicast(nskb, queue->peer_pid, MSG_DONTWAIT); + err = nfnetlink_unicast(nskb, &init_net, queue->peer_pid, MSG_DONTWAIT); if (err < 0) { queue->queue_user_dropped++; goto err_out_unlock; -- cgit v1.2.3 From 9592a5c01e79dbc59eb56fa26b124e94ffcd0962 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 13 Jan 2010 16:04:18 +0100 Subject: netfilter: ctnetlink: netns support Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 65 +++++++++++++++++++++--------------- 1 file changed, 39 insertions(+), 26 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d4c5d06677f..79478dfba27 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -30,6 +30,7 @@ #include #include +#include #include #include #include @@ -456,6 +457,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) static int ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) { + struct net *net; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; @@ -482,7 +484,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) } else return 0; - if (!item->report && !nfnetlink_has_listeners(&init_net, group)) + net = nf_ct_net(ct); + if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); @@ -559,7 +562,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - err = nfnetlink_send(skb, &init_net, item->pid, group, item->report, + err = nfnetlink_send(skb, net, item->pid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; @@ -572,7 +575,7 @@ nla_put_failure: nlmsg_failure: kfree_skb(skb); errout: - nfnetlink_set_err(&init_net, 0, group, -ENOBUFS); + nfnetlink_set_err(net, 0, group, -ENOBUFS); return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ @@ -587,6 +590,7 @@ static int ctnetlink_done(struct netlink_callback *cb) static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; @@ -597,7 +601,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: - hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]], + hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; @@ -769,6 +773,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(ctnl); struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conn *ct; @@ -782,7 +787,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); else { /* Flush the whole table */ - nf_conntrack_flush_report(&init_net, + nf_conntrack_flush_report(net, NETLINK_CB(skb).pid, nlmsg_report(nlh)); return 0; @@ -791,7 +796,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(&init_net, &tuple); + h = nf_conntrack_find_get(net, &tuple); if (!h) return -ENOENT; @@ -829,6 +834,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(ctnl); struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conn *ct; @@ -851,7 +857,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(&init_net, &tuple); + h = nf_conntrack_find_get(net, &tuple); if (!h) return -ENOENT; @@ -1176,7 +1182,8 @@ ctnetlink_change_conntrack(struct nf_conn *ct, } static struct nf_conn * -ctnetlink_create_conntrack(const struct nlattr * const cda[], +ctnetlink_create_conntrack(struct net *net, + const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, u8 u3) @@ -1185,7 +1192,7 @@ ctnetlink_create_conntrack(const struct nlattr * const cda[], int err = -EINVAL; struct nf_conntrack_helper *helper; - ct = nf_conntrack_alloc(&init_net, otuple, rtuple, GFP_ATOMIC); + ct = nf_conntrack_alloc(net, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); @@ -1286,7 +1293,7 @@ ctnetlink_create_conntrack(const struct nlattr * const cda[], if (err < 0) goto err2; - master_h = nf_conntrack_find_get(&init_net, &master); + master_h = nf_conntrack_find_get(net, &master); if (master_h == NULL) { err = -ENOENT; goto err2; @@ -1314,6 +1321,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(ctnl); struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -1334,9 +1342,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(&init_net, &otuple); + h = __nf_conntrack_find(net, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(&init_net, &rtuple); + h = __nf_conntrack_find(net, &rtuple); if (h == NULL) { err = -ENOENT; @@ -1344,7 +1352,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conn *ct; enum ip_conntrack_events events; - ct = ctnetlink_create_conntrack(cda, &otuple, + ct = ctnetlink_create_conntrack(net, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) { err = PTR_ERR(ct); @@ -1526,9 +1534,10 @@ nla_put_failure: static int ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) { + struct nf_conntrack_expect *exp = item->exp; + struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - struct nf_conntrack_expect *exp = item->exp; struct sk_buff *skb; unsigned int type; int flags = 0; @@ -1540,7 +1549,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) return 0; if (!item->report && - !nfnetlink_has_listeners(&init_net, NFNLGRP_CONNTRACK_EXP_NEW)) + !nfnetlink_has_listeners(net, NFNLGRP_CONNTRACK_EXP_NEW)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); @@ -1563,7 +1572,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - nfnetlink_send(skb, &init_net, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, + nfnetlink_send(skb, net, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, item->report, GFP_ATOMIC); return 0; @@ -1573,7 +1582,7 @@ nla_put_failure: nlmsg_failure: kfree_skb(skb); errout: - nfnetlink_set_err(&init_net, 0, 0, -ENOBUFS); + nfnetlink_set_err(net, 0, 0, -ENOBUFS); return 0; } #endif @@ -1587,7 +1596,7 @@ static int ctnetlink_exp_done(struct netlink_callback *cb) static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = &init_net; + struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct hlist_node *n; @@ -1640,6 +1649,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(ctnl); struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct sk_buff *skb2; @@ -1661,7 +1671,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - exp = nf_ct_expect_find_get(&init_net, &tuple); + exp = nf_ct_expect_find_get(net, &tuple); if (!exp) return -ENOENT; @@ -1701,6 +1711,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(ctnl); struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_helper *h; @@ -1717,7 +1728,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, return err; /* bump usage count to 2 */ - exp = nf_ct_expect_find_get(&init_net, &tuple); + exp = nf_ct_expect_find_get(net, &tuple); if (!exp) return -ENOENT; @@ -1747,7 +1758,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, n, next, - &init_net.ct.expect_hash[i], + &net->ct.expect_hash[i], hnode) { m_help = nfct_help(exp->master); if (m_help->helper == h @@ -1763,7 +1774,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, n, next, - &init_net.ct.expect_hash[i], + &net->ct.expect_hash[i], hnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); @@ -1784,7 +1795,8 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, } static int -ctnetlink_create_expect(const struct nlattr * const cda[], u_int8_t u3, +ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[], + u_int8_t u3, u32 pid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; @@ -1806,7 +1818,7 @@ ctnetlink_create_expect(const struct nlattr * const cda[], u_int8_t u3, return err; /* Look for master conntrack of this expectation */ - h = nf_conntrack_find_get(&init_net, &master_tuple); + h = nf_conntrack_find_get(net, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); @@ -1846,6 +1858,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { + struct net *net = sock_net(ctnl); struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -1862,13 +1875,13 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, return err; spin_lock_bh(&nf_conntrack_lock); - exp = __nf_ct_expect_find(&init_net, &tuple); + exp = __nf_ct_expect_find(net, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_lock); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - err = ctnetlink_create_expect(cda, + err = ctnetlink_create_expect(net, cda, u3, NETLINK_CB(skb).pid, nlmsg_report(nlh)); -- cgit v1.2.3 From 83fc81024bd8572f31db784f8c0079e999a4fa44 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:07:50 +0100 Subject: netfilter: xt_connlimit: netns support Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/xt_connlimit.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 8103bef78e4..0d9d18ea2b0 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -90,7 +90,8 @@ same_source_net(const union nf_inet_addr *addr, } } -static int count_them(struct xt_connlimit_data *data, +static int count_them(struct net *net, + struct xt_connlimit_data *data, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, @@ -113,7 +114,7 @@ static int count_them(struct xt_connlimit_data *data, /* check the saved connections */ list_for_each_entry_safe(conn, tmp, hash, list) { - found = nf_conntrack_find_get(&init_net, &conn->tuple); + found = nf_conntrack_find_get(net, &conn->tuple); found_ct = NULL; if (found != NULL) @@ -171,6 +172,7 @@ static int count_them(struct xt_connlimit_data *data, static bool connlimit_mt(const struct sk_buff *skb, const struct xt_match_param *par) { + struct net *net = dev_net(par->in ? par->in : par->out); const struct xt_connlimit_info *info = par->matchinfo; union nf_inet_addr addr; struct nf_conntrack_tuple tuple; @@ -195,7 +197,7 @@ connlimit_mt(const struct sk_buff *skb, const struct xt_match_param *par) } spin_lock_bh(&info->data->lock); - connections = count_them(info->data, tuple_ptr, &addr, + connections = count_them(net, info->data, tuple_ptr, &addr, &info->mask, par->family); spin_unlock_bh(&info->data->lock); -- cgit v1.2.3 From a1004d8e3d463012f231bab104325ecb15637f78 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:14:50 +0100 Subject: netfilter: xt_hashlimit: simplify seqfile code Simply pass hashtable to seqfile iterators, proc entry itself is not needed. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/xt_hashlimit.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 5bdc1fbf3ad..944fd11c898 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -841,8 +841,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct proc_dir_entry *pde = s->private; - struct xt_hashlimit_htable *htable = pde->data; + struct xt_hashlimit_htable *htable = s->private; unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -859,8 +858,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct proc_dir_entry *pde = s->private; - struct xt_hashlimit_htable *htable = pde->data; + struct xt_hashlimit_htable *htable = s->private; unsigned int *bucket = (unsigned int *)v; *pos = ++(*bucket); @@ -874,8 +872,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct proc_dir_entry *pde = s->private; - struct xt_hashlimit_htable *htable = pde->data; + struct xt_hashlimit_htable *htable = s->private; unsigned int *bucket = (unsigned int *)v; kfree(bucket); @@ -917,8 +914,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show(struct seq_file *s, void *v) { - struct proc_dir_entry *pde = s->private; - struct xt_hashlimit_htable *htable = pde->data; + struct xt_hashlimit_htable *htable = s->private; unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; struct hlist_node *pos; @@ -944,7 +940,7 @@ static int dl_proc_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - sf->private = PDE(inode); + sf->private = PDE(inode)->data; } return ret; } -- cgit v1.2.3 From a83d8e8d099fc373a5ca7112ad08c553bb2c180f Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:21:13 +0100 Subject: netfilter: xtables: add struct xt_mtchk_param::net Some complex match modules (like xt_hashlimit/xt_recent) want netns information at constructor and destructor time. We propably can play games at match destruction time, because netns can be passed in object, but I think it's cleaner to explicitly pass netns. Add ->net, make sure it's set from ebtables/iptables/ip6tables code. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtables.c | 14 +++++++++----- net/ipv4/netfilter/ip_tables.c | 24 ++++++++++++++---------- net/ipv6/netfilter/ip6_tables.c | 14 ++++++++------ 3 files changed, 31 insertions(+), 21 deletions(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bd1c65425d4..c77bab98669 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -619,7 +619,9 @@ ebt_cleanup_entry(struct ebt_entry *e, unsigned int *cnt) } static inline int -ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, +ebt_check_entry(struct ebt_entry *e, + struct net *net, + struct ebt_table_info *newinfo, const char *name, unsigned int *cnt, struct ebt_cl_stack *cl_s, unsigned int udc_cnt) { @@ -671,6 +673,7 @@ ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, } i = 0; + mtpar.net = net; mtpar.table = tgpar.table = name; mtpar.entryinfo = tgpar.entryinfo = e; mtpar.hook_mask = tgpar.hook_mask = hookmask; @@ -808,7 +811,8 @@ letscontinue: } /* do the parsing of the table/chains/entries/matches/watchers/targets, heh */ -static int translate_table(char *name, struct ebt_table_info *newinfo) +static int translate_table(struct net *net, char *name, + struct ebt_table_info *newinfo) { unsigned int i, j, k, udc_cnt; int ret; @@ -917,7 +921,7 @@ static int translate_table(char *name, struct ebt_table_info *newinfo) /* used to know what we need to clean up if something goes wrong */ i = 0; ret = EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, - ebt_check_entry, newinfo, name, &i, cl_s, udc_cnt); + ebt_check_entry, net, newinfo, name, &i, cl_s, udc_cnt); if (ret != 0) { EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, ebt_cleanup_entry, &i); @@ -1017,7 +1021,7 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) if (ret != 0) goto free_counterstmp; - ret = translate_table(tmp.name, newinfo); + ret = translate_table(net, tmp.name, newinfo); if (ret != 0) goto free_counterstmp; @@ -1154,7 +1158,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table) newinfo->hook_entry[i] = p + ((char *)repl->hook_entry[i] - repl->entries); } - ret = translate_table(repl->name, newinfo); + ret = translate_table(net, repl->name, newinfo); if (ret != 0) { BUGPRINT("Translate_table failed\n"); goto free_chainstack; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 572330a552e..a069d72d948 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -661,8 +661,8 @@ static int check_target(struct ipt_entry *e, const char *name) } static int -find_check_entry(struct ipt_entry *e, const char *name, unsigned int size, - unsigned int *i) +find_check_entry(struct ipt_entry *e, struct net *net, const char *name, + unsigned int size, unsigned int *i) { struct ipt_entry_target *t; struct xt_target *target; @@ -675,6 +675,7 @@ find_check_entry(struct ipt_entry *e, const char *name, unsigned int size, return ret; j = 0; + mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ip; mtpar.hook_mask = e->comefrom; @@ -798,7 +799,8 @@ cleanup_entry(struct ipt_entry *e, unsigned int *i) /* Checks and translates the user-supplied table segment (held in newinfo) */ static int -translate_table(const char *name, +translate_table(struct net *net, + const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, void *entry0, @@ -860,7 +862,7 @@ translate_table(const char *name, /* Finally, each sanity check must pass */ i = 0; ret = IPT_ENTRY_ITERATE(entry0, newinfo->size, - find_check_entry, name, size, &i); + find_check_entry, net, name, size, &i); if (ret != 0) { IPT_ENTRY_ITERATE(entry0, newinfo->size, @@ -1303,7 +1305,7 @@ do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_table(tmp.name, tmp.valid_hooks, + ret = translate_table(net, tmp.name, tmp.valid_hooks, newinfo, loc_cpu_entry, tmp.size, tmp.num_entries, tmp.hook_entry, tmp.underflow); if (ret != 0) @@ -1655,7 +1657,7 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, } static int -compat_check_entry(struct ipt_entry *e, const char *name, +compat_check_entry(struct ipt_entry *e, struct net *net, const char *name, unsigned int *i) { struct xt_mtchk_param mtpar; @@ -1663,6 +1665,7 @@ compat_check_entry(struct ipt_entry *e, const char *name, int ret; j = 0; + mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ip; mtpar.hook_mask = e->comefrom; @@ -1684,7 +1687,8 @@ compat_check_entry(struct ipt_entry *e, const char *name, } static int -translate_compat_table(const char *name, +translate_compat_table(struct net *net, + const char *name, unsigned int valid_hooks, struct xt_table_info **pinfo, void **pentry0, @@ -1773,7 +1777,7 @@ translate_compat_table(const char *name, i = 0; ret = IPT_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry, - name, &i); + net, name, &i); if (ret) { j -= i; COMPAT_IPT_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i, @@ -1833,7 +1837,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_compat_table(tmp.name, tmp.valid_hooks, + ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, &newinfo, &loc_cpu_entry, tmp.size, tmp.num_entries, tmp.hook_entry, tmp.underflow); @@ -2086,7 +2090,7 @@ struct xt_table *ipt_register_table(struct net *net, loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(table->name, table->valid_hooks, + ret = translate_table(net, table->name, table->valid_hooks, newinfo, loc_cpu_entry, repl->size, repl->num_entries, repl->hook_entry, diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 480d7f8c980..a825940a92e 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -693,8 +693,8 @@ static int check_target(struct ip6t_entry *e, const char *name) } static int -find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size, - unsigned int *i) +find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, + unsigned int size, unsigned int *i) { struct ip6t_entry_target *t; struct xt_target *target; @@ -707,6 +707,7 @@ find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size, return ret; j = 0; + mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; @@ -830,7 +831,8 @@ cleanup_entry(struct ip6t_entry *e, unsigned int *i) /* Checks and translates the user-supplied table segment (held in newinfo) */ static int -translate_table(const char *name, +translate_table(struct net *net, + const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, void *entry0, @@ -892,7 +894,7 @@ translate_table(const char *name, /* Finally, each sanity check must pass */ i = 0; ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size, - find_check_entry, name, size, &i); + find_check_entry, net, name, size, &i); if (ret != 0) { IP6T_ENTRY_ITERATE(entry0, newinfo->size, @@ -1336,7 +1338,7 @@ do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_table(tmp.name, tmp.valid_hooks, + ret = translate_table(net, tmp.name, tmp.valid_hooks, newinfo, loc_cpu_entry, tmp.size, tmp.num_entries, tmp.hook_entry, tmp.underflow); if (ret != 0) @@ -2121,7 +2123,7 @@ struct xt_table *ip6t_register_table(struct net *net, loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(table->name, table->valid_hooks, + ret = translate_table(net, table->name, table->valid_hooks, newinfo, loc_cpu_entry, repl->size, repl->num_entries, repl->hook_entry, -- cgit v1.2.3 From f54e9367f8499a9bf6b2afbc0dce63e1d53c525a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:25:47 +0100 Subject: netfilter: xtables: add struct xt_mtdtor_param::net Add ->net to match destructor list like ->net in constructor list. Make sure it's set in ebtables/iptables/ip6tables, this requires to propagate netns up to *_unregister_table(). Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtable_broute.c | 2 +- net/bridge/netfilter/ebtable_filter.c | 2 +- net/bridge/netfilter/ebtable_nat.c | 2 +- net/bridge/netfilter/ebtables.c | 19 ++++++++--------- net/ipv4/netfilter/ip_tables.c | 25 ++++++++++++----------- net/ipv4/netfilter/iptable_filter.c | 2 +- net/ipv4/netfilter/iptable_mangle.c | 2 +- net/ipv4/netfilter/iptable_raw.c | 2 +- net/ipv4/netfilter/iptable_security.c | 2 +- net/ipv4/netfilter/nf_nat_rule.c | 2 +- net/ipv6/netfilter/ip6_tables.c | 37 ++++++++++++++++++---------------- net/ipv6/netfilter/ip6table_filter.c | 2 +- net/ipv6/netfilter/ip6table_mangle.c | 2 +- net/ipv6/netfilter/ip6table_raw.c | 2 +- net/ipv6/netfilter/ip6table_security.c | 2 +- 15 files changed, 55 insertions(+), 50 deletions(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index d32ab13e728..ae3f106c390 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -71,7 +71,7 @@ static int __net_init broute_net_init(struct net *net) static void __net_exit broute_net_exit(struct net *net) { - ebt_unregister_table(net->xt.broute_table); + ebt_unregister_table(net, net->xt.broute_table); } static struct pernet_operations broute_net_ops = { diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 60b1a6ca718..42e6bd09457 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -107,7 +107,7 @@ static int __net_init frame_filter_net_init(struct net *net) static void __net_exit frame_filter_net_exit(struct net *net) { - ebt_unregister_table(net->xt.frame_filter); + ebt_unregister_table(net, net->xt.frame_filter); } static struct pernet_operations frame_filter_net_ops = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 4a98804203b..6dc2f878ae0 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -107,7 +107,7 @@ static int __net_init frame_nat_net_init(struct net *net) static void __net_exit frame_nat_net_exit(struct net *net) { - ebt_unregister_table(net->xt.frame_nat); + ebt_unregister_table(net, net->xt.frame_nat); } static struct pernet_operations frame_nat_net_ops = { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index c77bab98669..1aa0e4c1f52 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -561,13 +561,14 @@ ebt_get_udc_positions(struct ebt_entry *e, struct ebt_table_info *newinfo, } static inline int -ebt_cleanup_match(struct ebt_entry_match *m, unsigned int *i) +ebt_cleanup_match(struct ebt_entry_match *m, struct net *net, unsigned int *i) { struct xt_mtdtor_param par; if (i && (*i)-- == 0) return 1; + par.net = net; par.match = m->u.match; par.matchinfo = m->data; par.family = NFPROTO_BRIDGE; @@ -595,7 +596,7 @@ ebt_cleanup_watcher(struct ebt_entry_watcher *w, unsigned int *i) } static inline int -ebt_cleanup_entry(struct ebt_entry *e, unsigned int *cnt) +ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) { struct xt_tgdtor_param par; struct ebt_entry_target *t; @@ -606,7 +607,7 @@ ebt_cleanup_entry(struct ebt_entry *e, unsigned int *cnt) if (cnt && (*cnt)-- == 0) return 1; EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, NULL); - EBT_MATCH_ITERATE(e, ebt_cleanup_match, NULL); + EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, NULL); t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); par.target = t->u.target; @@ -731,7 +732,7 @@ ebt_check_entry(struct ebt_entry *e, cleanup_watchers: EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, &j); cleanup_matches: - EBT_MATCH_ITERATE(e, ebt_cleanup_match, &i); + EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, &i); return ret; } @@ -924,7 +925,7 @@ static int translate_table(struct net *net, char *name, ebt_check_entry, net, newinfo, name, &i, cl_s, udc_cnt); if (ret != 0) { EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, - ebt_cleanup_entry, &i); + ebt_cleanup_entry, net, &i); } vfree(cl_s); return ret; @@ -1074,7 +1075,7 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) /* decrease module count and free resources */ EBT_ENTRY_ITERATE(table->entries, table->entries_size, - ebt_cleanup_entry, NULL); + ebt_cleanup_entry, net, NULL); vfree(table->entries); if (table->chainstack) { @@ -1091,7 +1092,7 @@ free_unlock: mutex_unlock(&ebt_mutex); free_iterate: EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, - ebt_cleanup_entry, NULL); + ebt_cleanup_entry, net, NULL); free_counterstmp: vfree(counterstmp); /* can be initialized in translate_table() */ @@ -1208,7 +1209,7 @@ out: return ERR_PTR(ret); } -void ebt_unregister_table(struct ebt_table *table) +void ebt_unregister_table(struct net *net, struct ebt_table *table) { int i; @@ -1220,7 +1221,7 @@ void ebt_unregister_table(struct ebt_table *table) list_del(&table->list); mutex_unlock(&ebt_mutex); EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size, - ebt_cleanup_entry, NULL); + ebt_cleanup_entry, net, NULL); if (table->private->nentries) module_put(table->me); vfree(table->private->entries); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index a069d72d948..cfaba0e2e6f 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -553,13 +553,14 @@ mark_source_chains(struct xt_table_info *newinfo, } static int -cleanup_match(struct ipt_entry_match *m, unsigned int *i) +cleanup_match(struct ipt_entry_match *m, struct net *net, unsigned int *i) { struct xt_mtdtor_param par; if (i && (*i)-- == 0) return 1; + par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV4; @@ -705,7 +706,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, err: module_put(t->u.kernel.target->me); cleanup_matches: - IPT_MATCH_ITERATE(e, cleanup_match, &j); + IPT_MATCH_ITERATE(e, cleanup_match, net, &j); return ret; } @@ -775,7 +776,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, } static int -cleanup_entry(struct ipt_entry *e, unsigned int *i) +cleanup_entry(struct ipt_entry *e, struct net *net, unsigned int *i) { struct xt_tgdtor_param par; struct ipt_entry_target *t; @@ -784,7 +785,7 @@ cleanup_entry(struct ipt_entry *e, unsigned int *i) return 1; /* Cleanup all matches */ - IPT_MATCH_ITERATE(e, cleanup_match, NULL); + IPT_MATCH_ITERATE(e, cleanup_match, net, NULL); t = ipt_get_target(e); par.target = t->u.kernel.target; @@ -866,7 +867,7 @@ translate_table(struct net *net, if (ret != 0) { IPT_ENTRY_ITERATE(entry0, newinfo->size, - cleanup_entry, &i); + cleanup_entry, net, &i); return ret; } @@ -1260,7 +1261,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, - NULL); + net, NULL); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) @@ -1320,7 +1321,7 @@ do_replace(struct net *net, void __user *user, unsigned int len) return 0; free_newinfo_untrans: - IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); + IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, net, NULL); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1682,7 +1683,7 @@ compat_check_entry(struct ipt_entry *e, struct net *net, const char *name, return 0; cleanup_matches: - IPT_MATCH_ITERATE(e, cleanup_match, &j); + IPT_MATCH_ITERATE(e, cleanup_match, net, &j); return ret; } @@ -1782,7 +1783,7 @@ translate_compat_table(struct net *net, j -= i; COMPAT_IPT_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i, compat_release_entry, &j); - IPT_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, &i); + IPT_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, net, &i); xt_free_table_info(newinfo); return ret; } @@ -1853,7 +1854,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return 0; free_newinfo_untrans: - IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); + IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, net, NULL); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -2112,7 +2113,7 @@ out: return ERR_PTR(ret); } -void ipt_unregister_table(struct xt_table *table) +void ipt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; @@ -2122,7 +2123,7 @@ void ipt_unregister_table(struct xt_table *table) /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries[raw_smp_processor_id()]; - IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); + IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, net, NULL); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index df566cbd68e..dee90eb8aa4 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -138,7 +138,7 @@ static int __net_init iptable_filter_net_init(struct net *net) static void __net_exit iptable_filter_net_exit(struct net *net) { - ipt_unregister_table(net->ipv4.iptable_filter); + ipt_unregister_table(net, net->ipv4.iptable_filter); } static struct pernet_operations iptable_filter_net_ops = { diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index fae78c3076c..e07bf242343 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -208,7 +208,7 @@ static int __net_init iptable_mangle_net_init(struct net *net) static void __net_exit iptable_mangle_net_exit(struct net *net) { - ipt_unregister_table(net->ipv4.iptable_mangle); + ipt_unregister_table(net, net->ipv4.iptable_mangle); } static struct pernet_operations iptable_mangle_net_ops = { diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 993edc23be0..40f2b9f611a 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -100,7 +100,7 @@ static int __net_init iptable_raw_net_init(struct net *net) static void __net_exit iptable_raw_net_exit(struct net *net) { - ipt_unregister_table(net->ipv4.iptable_raw); + ipt_unregister_table(net, net->ipv4.iptable_raw); } static struct pernet_operations iptable_raw_net_ops = { diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 3bd3d6388da..7ce2366e430 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -138,7 +138,7 @@ static int __net_init iptable_security_net_init(struct net *net) static void __net_exit iptable_security_net_exit(struct net *net) { - ipt_unregister_table(net->ipv4.iptable_security); + ipt_unregister_table(net, net->ipv4.iptable_security); } static struct pernet_operations iptable_security_net_ops = { diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 9e81e0dfb4e..85da34fdc75 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -195,7 +195,7 @@ static int __net_init nf_nat_rule_net_init(struct net *net) static void __net_exit nf_nat_rule_net_exit(struct net *net) { - ipt_unregister_table(net->ipv4.nat_table); + ipt_unregister_table(net, net->ipv4.nat_table); } static struct pernet_operations nf_nat_rule_net_ops = { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index a825940a92e..9f1d45f2ba8 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -585,13 +585,14 @@ mark_source_chains(struct xt_table_info *newinfo, } static int -cleanup_match(struct ip6t_entry_match *m, unsigned int *i) +cleanup_match(struct ip6t_entry_match *m, struct net *net, unsigned int *i) { struct xt_mtdtor_param par; if (i && (*i)-- == 0) return 1; + par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; @@ -737,7 +738,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, err: module_put(t->u.kernel.target->me); cleanup_matches: - IP6T_MATCH_ITERATE(e, cleanup_match, &j); + IP6T_MATCH_ITERATE(e, cleanup_match, net, &j); return ret; } @@ -807,7 +808,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, } static int -cleanup_entry(struct ip6t_entry *e, unsigned int *i) +cleanup_entry(struct ip6t_entry *e, struct net *net, unsigned int *i) { struct xt_tgdtor_param par; struct ip6t_entry_target *t; @@ -816,7 +817,7 @@ cleanup_entry(struct ip6t_entry *e, unsigned int *i) return 1; /* Cleanup all matches */ - IP6T_MATCH_ITERATE(e, cleanup_match, NULL); + IP6T_MATCH_ITERATE(e, cleanup_match, net, NULL); t = ip6t_get_target(e); par.target = t->u.kernel.target; @@ -898,7 +899,7 @@ translate_table(struct net *net, if (ret != 0) { IP6T_ENTRY_ITERATE(entry0, newinfo->size, - cleanup_entry, &i); + cleanup_entry, net, &i); return ret; } @@ -1293,7 +1294,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, - NULL); + net, NULL); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) @@ -1353,7 +1354,7 @@ do_replace(struct net *net, void __user *user, unsigned int len) return 0; free_newinfo_untrans: - IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); + IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, net, NULL); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1692,14 +1693,15 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, return ret; } -static int compat_check_entry(struct ip6t_entry *e, const char *name, - unsigned int *i) +static int compat_check_entry(struct ip6t_entry *e, struct net *net, + const char *name, unsigned int *i) { unsigned int j; int ret; struct xt_mtchk_param mtpar; j = 0; + mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; @@ -1716,12 +1718,13 @@ static int compat_check_entry(struct ip6t_entry *e, const char *name, return 0; cleanup_matches: - IP6T_MATCH_ITERATE(e, cleanup_match, &j); + IP6T_MATCH_ITERATE(e, cleanup_match, net, &j); return ret; } static int -translate_compat_table(const char *name, +translate_compat_table(struct net *net, + const char *name, unsigned int valid_hooks, struct xt_table_info **pinfo, void **pentry0, @@ -1810,12 +1813,12 @@ translate_compat_table(const char *name, i = 0; ret = IP6T_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry, - name, &i); + net, name, &i); if (ret) { j -= i; COMPAT_IP6T_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i, compat_release_entry, &j); - IP6T_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, &i); + IP6T_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, net, &i); xt_free_table_info(newinfo); return ret; } @@ -1870,7 +1873,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_compat_table(tmp.name, tmp.valid_hooks, + ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, &newinfo, &loc_cpu_entry, tmp.size, tmp.num_entries, tmp.hook_entry, tmp.underflow); @@ -1886,7 +1889,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return 0; free_newinfo_untrans: - IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); + IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, net, NULL); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -2144,7 +2147,7 @@ out: return ERR_PTR(ret); } -void ip6t_unregister_table(struct xt_table *table) +void ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; @@ -2154,7 +2157,7 @@ void ip6t_unregister_table(struct xt_table *table) /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries[raw_smp_processor_id()]; - IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); + IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, net, NULL); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index ad378efd0eb..33ddfe53e18 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -131,7 +131,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) static void __net_exit ip6table_filter_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_filter); + ip6t_unregister_table(net, net->ipv6.ip6table_filter); } static struct pernet_operations ip6table_filter_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index a929c19d30e..9bc483f000e 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -182,7 +182,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net) static void __net_exit ip6table_mangle_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_mangle); + ip6t_unregister_table(net, net->ipv6.ip6table_mangle); } static struct pernet_operations ip6table_mangle_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index ed1a1180f3b..4c90b552e43 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -94,7 +94,7 @@ static int __net_init ip6table_raw_net_init(struct net *net) static void __net_exit ip6table_raw_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_raw); + ip6t_unregister_table(net, net->ipv6.ip6table_raw); } static struct pernet_operations ip6table_raw_net_ops = { diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 41b444c6093..baa8d4ef3b0 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -134,7 +134,7 @@ static int __net_init ip6table_security_net_init(struct net *net) static void __net_exit ip6table_security_net_exit(struct net *net) { - ip6t_unregister_table(net->ipv6.ip6table_security); + ip6t_unregister_table(net, net->ipv6.ip6table_security); } static struct pernet_operations ip6table_security_net_ops = { -- cgit v1.2.3 From 7d07d5632b672c892a65882c2a119345fd9596c9 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:31:00 +0100 Subject: netfilter: xt_recent: netns support Make recent table list per-netns. Make proc files per-netns. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/xt_recent.c | 136 ++++++++++++++++++++++++++++++++-------------- 1 file changed, 95 insertions(+), 41 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 768d01ff1fe..20333310736 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -78,15 +79,26 @@ struct recent_table { struct list_head iphash[0]; }; -static LIST_HEAD(tables); +struct recent_net { + struct list_head tables; +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *xt_recent; +#ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT + struct proc_dir_entry *ipt_recent; +#endif +#endif +}; + +static int recent_net_id; +static inline struct recent_net *recent_pernet(struct net *net) +{ + return net_generic(net, recent_net_id); +} + static DEFINE_SPINLOCK(recent_lock); static DEFINE_MUTEX(recent_mutex); #ifdef CONFIG_PROC_FS -#ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT -static struct proc_dir_entry *proc_old_dir; -#endif -static struct proc_dir_entry *recent_proc_dir; static const struct file_operations recent_old_fops, recent_mt_fops; #endif @@ -172,11 +184,12 @@ static void recent_entry_update(struct recent_table *t, struct recent_entry *e) list_move_tail(&e->lru_list, &t->lru_list); } -static struct recent_table *recent_table_lookup(const char *name) +static struct recent_table *recent_table_lookup(struct recent_net *recent_net, + const char *name) { struct recent_table *t; - list_for_each_entry(t, &tables, list) + list_for_each_entry(t, &recent_net->tables, list) if (!strcmp(t->name, name)) return t; return NULL; @@ -195,6 +208,8 @@ static void recent_table_flush(struct recent_table *t) static bool recent_mt(const struct sk_buff *skb, const struct xt_match_param *par) { + struct net *net = dev_net(par->in ? par->in : par->out); + struct recent_net *recent_net = recent_pernet(net); const struct xt_recent_mtinfo *info = par->matchinfo; struct recent_table *t; struct recent_entry *e; @@ -227,7 +242,7 @@ recent_mt(const struct sk_buff *skb, const struct xt_match_param *par) ttl++; spin_lock_bh(&recent_lock); - t = recent_table_lookup(info->name); + t = recent_table_lookup(recent_net, info->name); e = recent_entry_lookup(t, &addr, par->match->family, (info->check_set & XT_RECENT_TTL) ? ttl : 0); if (e == NULL) { @@ -271,6 +286,7 @@ out: static bool recent_mt_check(const struct xt_mtchk_param *par) { + struct recent_net *recent_net = recent_pernet(par->net); const struct xt_recent_mtinfo *info = par->matchinfo; struct recent_table *t; #ifdef CONFIG_PROC_FS @@ -297,7 +313,7 @@ static bool recent_mt_check(const struct xt_mtchk_param *par) return false; mutex_lock(&recent_mutex); - t = recent_table_lookup(info->name); + t = recent_table_lookup(recent_net, info->name); if (t != NULL) { t->refcnt++; ret = true; @@ -314,7 +330,7 @@ static bool recent_mt_check(const struct xt_mtchk_param *par) for (i = 0; i < ip_list_hash_size; i++) INIT_LIST_HEAD(&t->iphash[i]); #ifdef CONFIG_PROC_FS - pde = proc_create_data(t->name, ip_list_perms, recent_proc_dir, + pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent, &recent_mt_fops, t); if (pde == NULL) { kfree(t); @@ -323,10 +339,10 @@ static bool recent_mt_check(const struct xt_mtchk_param *par) pde->uid = ip_list_uid; pde->gid = ip_list_gid; #ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT - pde = proc_create_data(t->name, ip_list_perms, proc_old_dir, + pde = proc_create_data(t->name, ip_list_perms, recent_net->ipt_recent, &recent_old_fops, t); if (pde == NULL) { - remove_proc_entry(t->name, proc_old_dir); + remove_proc_entry(t->name, recent_net->xt_recent); kfree(t); goto out; } @@ -335,7 +351,7 @@ static bool recent_mt_check(const struct xt_mtchk_param *par) #endif #endif spin_lock_bh(&recent_lock); - list_add_tail(&t->list, &tables); + list_add_tail(&t->list, &recent_net->tables); spin_unlock_bh(&recent_lock); ret = true; out: @@ -345,20 +361,21 @@ out: static void recent_mt_destroy(const struct xt_mtdtor_param *par) { + struct recent_net *recent_net = recent_pernet(par->net); const struct xt_recent_mtinfo *info = par->matchinfo; struct recent_table *t; mutex_lock(&recent_mutex); - t = recent_table_lookup(info->name); + t = recent_table_lookup(recent_net, info->name); if (--t->refcnt == 0) { spin_lock_bh(&recent_lock); list_del(&t->list); spin_unlock_bh(&recent_lock); #ifdef CONFIG_PROC_FS #ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT - remove_proc_entry(t->name, proc_old_dir); + remove_proc_entry(t->name, recent_net->ipt_recent); #endif - remove_proc_entry(t->name, recent_proc_dir); + remove_proc_entry(t->name, recent_net->xt_recent); #endif recent_table_flush(t); kfree(t); @@ -607,8 +624,65 @@ static const struct file_operations recent_mt_fops = { .release = seq_release_private, .owner = THIS_MODULE, }; + +static int __net_init recent_proc_net_init(struct net *net) +{ + struct recent_net *recent_net = recent_pernet(net); + + recent_net->xt_recent = proc_mkdir("xt_recent", net->proc_net); + if (!recent_net->xt_recent) + return -ENOMEM; +#ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT + recent_net->ipt_recent = proc_mkdir("ipt_recent", net->proc_net); + if (!recent_net->ipt_recent) { + proc_net_remove(net, "xt_recent"); + return -ENOMEM; + } +#endif + return 0; +} + +static void __net_exit recent_proc_net_exit(struct net *net) +{ +#ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT + proc_net_remove(net, "ipt_recent"); +#endif + proc_net_remove(net, "xt_recent"); +} +#else +static inline int recent_proc_net_init(struct net *net) +{ + return 0; +} + +static inline void recent_proc_net_exit(struct net *net) +{ +} #endif /* CONFIG_PROC_FS */ +static int __net_init recent_net_init(struct net *net) +{ + struct recent_net *recent_net = recent_pernet(net); + + INIT_LIST_HEAD(&recent_net->tables); + return recent_proc_net_init(net); +} + +static void __net_exit recent_net_exit(struct net *net) +{ + struct recent_net *recent_net = recent_pernet(net); + + BUG_ON(!list_empty(&recent_net->tables)); + recent_proc_net_exit(net); +} + +static struct pernet_operations recent_net_ops = { + .init = recent_net_init, + .exit = recent_net_exit, + .id = &recent_net_id, + .size = sizeof(struct recent_net), +}; + static struct xt_match recent_mt_reg[] __read_mostly = { { .name = "recent", @@ -640,39 +714,19 @@ static int __init recent_mt_init(void) return -EINVAL; ip_list_hash_size = 1 << fls(ip_list_tot); - err = xt_register_matches(recent_mt_reg, ARRAY_SIZE(recent_mt_reg)); -#ifdef CONFIG_PROC_FS + err = register_pernet_subsys(&recent_net_ops); if (err) return err; - recent_proc_dir = proc_mkdir("xt_recent", init_net.proc_net); - if (recent_proc_dir == NULL) { - xt_unregister_matches(recent_mt_reg, ARRAY_SIZE(recent_mt_reg)); - err = -ENOMEM; - } -#ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT - if (err < 0) - return err; - proc_old_dir = proc_mkdir("ipt_recent", init_net.proc_net); - if (proc_old_dir == NULL) { - remove_proc_entry("xt_recent", init_net.proc_net); - xt_unregister_matches(recent_mt_reg, ARRAY_SIZE(recent_mt_reg)); - err = -ENOMEM; - } -#endif -#endif + err = xt_register_matches(recent_mt_reg, ARRAY_SIZE(recent_mt_reg)); + if (err) + unregister_pernet_subsys(&recent_net_ops); return err; } static void __exit recent_mt_exit(void) { - BUG_ON(!list_empty(&tables)); xt_unregister_matches(recent_mt_reg, ARRAY_SIZE(recent_mt_reg)); -#ifdef CONFIG_PROC_FS -#ifdef CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT - remove_proc_entry("ipt_recent", init_net.proc_net); -#endif - remove_proc_entry("xt_recent", init_net.proc_net); -#endif + unregister_pernet_subsys(&recent_net_ops); } module_init(recent_mt_init); -- cgit v1.2.3 From e89fc3f1b06d9241f65e580b002789abaa6d11ac Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 18 Jan 2010 08:33:28 +0100 Subject: netfilter: xt_hashlimit: netns support Make hashtable per-netns. Make proc files per-netns. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/xt_hashlimit.c | 141 ++++++++++++++++++++++++++++++------------- 1 file changed, 98 insertions(+), 43 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 944fd11c898..fb7fcb773a3 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -26,6 +26,7 @@ #endif #include +#include #include #include @@ -40,9 +41,19 @@ MODULE_DESCRIPTION("Xtables: per hash-bucket rate-limit match"); MODULE_ALIAS("ipt_hashlimit"); MODULE_ALIAS("ip6t_hashlimit"); +struct hashlimit_net { + struct hlist_head htables; + struct proc_dir_entry *ipt_hashlimit; + struct proc_dir_entry *ip6t_hashlimit; +}; + +static int hashlimit_net_id; +static inline struct hashlimit_net *hashlimit_pernet(struct net *net) +{ + return net_generic(net, hashlimit_net_id); +} + /* need to declare this at the top */ -static struct proc_dir_entry *hashlimit_procdir4; -static struct proc_dir_entry *hashlimit_procdir6; static const struct file_operations dl_file_ops; /* hash table crap */ @@ -93,13 +104,13 @@ struct xt_hashlimit_htable { /* seq_file stuff */ struct proc_dir_entry *pde; + struct net *net; struct hlist_head hash[0]; /* hashtable itself */ }; static DEFINE_SPINLOCK(hashlimit_lock); /* protects htables list */ static DEFINE_MUTEX(hlimit_mutex); /* additional checkentry protection */ -static HLIST_HEAD(hashlimit_htables); static struct kmem_cache *hashlimit_cachep __read_mostly; static inline bool dst_cmp(const struct dsthash_ent *ent, @@ -185,8 +196,9 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) } static void htable_gc(unsigned long htlong); -static int htable_create_v0(struct xt_hashlimit_info *minfo, u_int8_t family) +static int htable_create_v0(struct net *net, struct xt_hashlimit_info *minfo, u_int8_t family) { + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; unsigned int size; unsigned int i; @@ -239,26 +251,29 @@ static int htable_create_v0(struct xt_hashlimit_info *minfo, u_int8_t family) spin_lock_init(&hinfo->lock); hinfo->pde = proc_create_data(minfo->name, 0, (family == NFPROTO_IPV4) ? - hashlimit_procdir4 : hashlimit_procdir6, + hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, &dl_file_ops, hinfo); if (!hinfo->pde) { vfree(hinfo); return -1; } + hinfo->net = net; setup_timer(&hinfo->timer, htable_gc, (unsigned long )hinfo); hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); add_timer(&hinfo->timer); spin_lock_bh(&hashlimit_lock); - hlist_add_head(&hinfo->node, &hashlimit_htables); + hlist_add_head(&hinfo->node, &hashlimit_net->htables); spin_unlock_bh(&hashlimit_lock); return 0; } -static int htable_create(struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) +static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, + u_int8_t family) { + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; unsigned int size; unsigned int i; @@ -301,19 +316,20 @@ static int htable_create(struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) hinfo->pde = proc_create_data(minfo->name, 0, (family == NFPROTO_IPV4) ? - hashlimit_procdir4 : hashlimit_procdir6, + hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, &dl_file_ops, hinfo); if (hinfo->pde == NULL) { vfree(hinfo); return -1; } + hinfo->net = net; setup_timer(&hinfo->timer, htable_gc, (unsigned long)hinfo); hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); add_timer(&hinfo->timer); spin_lock_bh(&hashlimit_lock); - hlist_add_head(&hinfo->node, &hashlimit_htables); + hlist_add_head(&hinfo->node, &hashlimit_net->htables); spin_unlock_bh(&hashlimit_lock); return 0; @@ -364,24 +380,30 @@ static void htable_gc(unsigned long htlong) static void htable_destroy(struct xt_hashlimit_htable *hinfo) { + struct hashlimit_net *hashlimit_net = hashlimit_pernet(hinfo->net); + struct proc_dir_entry *parent; + del_timer_sync(&hinfo->timer); - /* remove proc entry */ - remove_proc_entry(hinfo->pde->name, - hinfo->family == NFPROTO_IPV4 ? hashlimit_procdir4 : - hashlimit_procdir6); + if (hinfo->family == NFPROTO_IPV4) + parent = hashlimit_net->ipt_hashlimit; + else + parent = hashlimit_net->ip6t_hashlimit; + remove_proc_entry(hinfo->pde->name, parent); htable_selective_cleanup(hinfo, select_all); vfree(hinfo); } -static struct xt_hashlimit_htable *htable_find_get(const char *name, +static struct xt_hashlimit_htable *htable_find_get(struct net *net, + const char *name, u_int8_t family) { + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; struct hlist_node *pos; spin_lock_bh(&hashlimit_lock); - hlist_for_each_entry(hinfo, pos, &hashlimit_htables, node) { + hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->pde->name) && hinfo->family == family) { atomic_inc(&hinfo->use); @@ -665,6 +687,7 @@ hashlimit_mt(const struct sk_buff *skb, const struct xt_match_param *par) static bool hashlimit_mt_check_v0(const struct xt_mtchk_param *par) { + struct net *net = par->net; struct xt_hashlimit_info *r = par->matchinfo; /* Check for overflow. */ @@ -694,8 +717,8 @@ static bool hashlimit_mt_check_v0(const struct xt_mtchk_param *par) * the list of htable's in htable_create(), since then we would * create duplicate proc files. -HW */ mutex_lock(&hlimit_mutex); - r->hinfo = htable_find_get(r->name, par->match->family); - if (!r->hinfo && htable_create_v0(r, par->match->family) != 0) { + r->hinfo = htable_find_get(net, r->name, par->match->family); + if (!r->hinfo && htable_create_v0(net, r, par->match->family) != 0) { mutex_unlock(&hlimit_mutex); return false; } @@ -706,6 +729,7 @@ static bool hashlimit_mt_check_v0(const struct xt_mtchk_param *par) static bool hashlimit_mt_check(const struct xt_mtchk_param *par) { + struct net *net = par->net; struct xt_hashlimit_mtinfo1 *info = par->matchinfo; /* Check for overflow. */ @@ -735,8 +759,8 @@ static bool hashlimit_mt_check(const struct xt_mtchk_param *par) * the list of htable's in htable_create(), since then we would * create duplicate proc files. -HW */ mutex_lock(&hlimit_mutex); - info->hinfo = htable_find_get(info->name, par->match->family); - if (!info->hinfo && htable_create(info, par->match->family) != 0) { + info->hinfo = htable_find_get(net, info->name, par->match->family); + if (!info->hinfo && htable_create(net, info, par->match->family) != 0) { mutex_unlock(&hlimit_mutex); return false; } @@ -953,10 +977,61 @@ static const struct file_operations dl_file_ops = { .release = seq_release }; +static int __net_init hashlimit_proc_net_init(struct net *net) +{ + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); + + hashlimit_net->ipt_hashlimit = proc_mkdir("ipt_hashlimit", net->proc_net); + if (!hashlimit_net->ipt_hashlimit) + return -ENOMEM; +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) + hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net); + if (!hashlimit_net->ip6t_hashlimit) { + proc_net_remove(net, "ipt_hashlimit"); + return -ENOMEM; + } +#endif + return 0; +} + +static void __net_exit hashlimit_proc_net_exit(struct net *net) +{ + proc_net_remove(net, "ipt_hashlimit"); +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) + proc_net_remove(net, "ip6t_hashlimit"); +#endif +} + +static int __net_init hashlimit_net_init(struct net *net) +{ + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); + + INIT_HLIST_HEAD(&hashlimit_net->htables); + return hashlimit_proc_net_init(net); +} + +static void __net_exit hashlimit_net_exit(struct net *net) +{ + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); + + BUG_ON(!hlist_empty(&hashlimit_net->htables)); + hashlimit_proc_net_exit(net); +} + +static struct pernet_operations hashlimit_net_ops = { + .init = hashlimit_net_init, + .exit = hashlimit_net_exit, + .id = &hashlimit_net_id, + .size = sizeof(struct hashlimit_net), +}; + static int __init hashlimit_mt_init(void) { int err; + err = register_pernet_subsys(&hashlimit_net_ops); + if (err < 0) + return err; err = xt_register_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); if (err < 0) @@ -970,41 +1045,21 @@ static int __init hashlimit_mt_init(void) printk(KERN_ERR "xt_hashlimit: unable to create slab cache\n"); goto err2; } - hashlimit_procdir4 = proc_mkdir("ipt_hashlimit", init_net.proc_net); - if (!hashlimit_procdir4) { - printk(KERN_ERR "xt_hashlimit: unable to create proc dir " - "entry\n"); - goto err3; - } - err = 0; -#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) - hashlimit_procdir6 = proc_mkdir("ip6t_hashlimit", init_net.proc_net); - if (!hashlimit_procdir6) { - printk(KERN_ERR "xt_hashlimit: unable to create proc dir " - "entry\n"); - err = -ENOMEM; - } -#endif - if (!err) - return 0; - remove_proc_entry("ipt_hashlimit", init_net.proc_net); -err3: - kmem_cache_destroy(hashlimit_cachep); + return 0; + err2: xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); err1: + unregister_pernet_subsys(&hashlimit_net_ops); return err; } static void __exit hashlimit_mt_exit(void) { - remove_proc_entry("ipt_hashlimit", init_net.proc_net); -#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) - remove_proc_entry("ip6t_hashlimit", init_net.proc_net); -#endif kmem_cache_destroy(hashlimit_cachep); xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); + unregister_pernet_subsys(&hashlimit_net_ops); } module_init(hashlimit_mt_init); -- cgit v1.2.3 From a5d896adf019143adf72d08826fe5359b6a8762c Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Mon, 18 Jan 2010 09:44:39 +0100 Subject: netfilter: nfnetlink_queue: simplify warning message This patch remove variable part from a debug message to have message concatenation from syslog. Signed-off-by: Eric Leblond Signed-off-by: Patrick McHardy --- net/netfilter/nfnetlink_queue.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5c589b27d6e..90cf36decea 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -414,8 +414,8 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) queue->queue_dropped++; if (net_ratelimit()) printk(KERN_WARNING "nf_queue: full at %d entries, " - "dropping packets(s). Dropped: %d\n", - queue->queue_total, queue->queue_dropped); + "dropping packets(s).\n", + queue->queue_total); goto err_out_free_nskb; } -- cgit v1.2.3 From b38f6eddeee510ce8178c2d2db54ed25f1d7cb63 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 20 Jan 2010 10:39:14 +0100 Subject: netfilter: nf_conntrack_ipv6: delete the redundant macro definitions The following three macro definitions are never used, so delete them. Signed-off-by: Shan Wei Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- net/ipv6/netfilter/nf_conntrack_reasm.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'net') diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 312c20adc83..1030ce1e6c7 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -45,9 +45,6 @@ #include #include -#define NF_CT_FRAG6_HIGH_THRESH 262144 /* == 256*1024 */ -#define NF_CT_FRAG6_LOW_THRESH 196608 /* == 192*1024 */ -#define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT struct nf_ct_frag6_skb_cb { -- cgit v1.2.3 From 7c070aa947d1a4105742378579c267f6e7fd08a1 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 20 Jan 2010 10:42:41 +0100 Subject: IPv6: reassembly: replace magic number with macro definitions Use macro to define high/low thresh value, refer to IPV6_FRAG_TIMEOUT. Signed-off-by: Shan Wei Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++-- net/ipv6/reassembly.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 1030ce1e6c7..744ea49de35 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -666,8 +666,8 @@ int nf_ct_frag6_init(void) nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.secret_interval = 10 * 60 * HZ; nf_init_frags.timeout = IPV6_FRAG_TIMEOUT; - nf_init_frags.high_thresh = 256 * 1024; - nf_init_frags.low_thresh = 192 * 1024; + nf_init_frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + nf_init_frags.low_thresh = IPV6_FRAG_LOW_THRESH; inet_frags_init_net(&nf_init_frags); inet_frags_init(&nf_frags); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2cddea3bd6b..15bb122e1ce 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -747,8 +747,8 @@ static inline void ip6_frags_sysctl_unregister(void) static int ipv6_frags_init_net(struct net *net) { - net->ipv6.frags.high_thresh = 256 * 1024; - net->ipv6.frags.low_thresh = 192 * 1024; + net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH; net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT; inet_frags_init_net(&net->ipv6.frags); -- cgit v1.2.3 From 477781477a88f60c89003c852def4aedc6f78101 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 22 Jan 2010 22:21:18 +0100 Subject: netfiltr: ipt_CLUSTERIP: simplify seq_file codeA Pass "struct clusterip_config" itself to seq_file iterators and save one dereference. Proc entry itself isn't interesting. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/ipt_CLUSTERIP.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 40ca2d240ab..0886f96c736 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -560,8 +560,7 @@ struct clusterip_seq_position { static void *clusterip_seq_start(struct seq_file *s, loff_t *pos) { - const struct proc_dir_entry *pde = s->private; - struct clusterip_config *c = pde->data; + struct clusterip_config *c = s->private; unsigned int weight; u_int32_t local_nodes; struct clusterip_seq_position *idx; @@ -632,10 +631,9 @@ static int clusterip_proc_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - struct proc_dir_entry *pde = PDE(inode); - struct clusterip_config *c = pde->data; + struct clusterip_config *c = PDE(inode)->data; - sf->private = pde; + sf->private = c; clusterip_config_get(c); } @@ -645,8 +643,7 @@ static int clusterip_proc_open(struct inode *inode, struct file *file) static int clusterip_proc_release(struct inode *inode, struct file *file) { - struct proc_dir_entry *pde = PDE(inode); - struct clusterip_config *c = pde->data; + struct clusterip_config *c = PDE(inode)->data; int ret; ret = seq_release(inode, file); @@ -660,10 +657,9 @@ static int clusterip_proc_release(struct inode *inode, struct file *file) static ssize_t clusterip_proc_write(struct file *file, const char __user *input, size_t size, loff_t *ofs) { + struct clusterip_config *c = PDE(file->f_path.dentry->d_inode)->data; #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; - const struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); - struct clusterip_config *c = pde->data; unsigned long nodenum; if (copy_from_user(buffer, input, PROC_WRITELEN)) -- cgit v1.2.3 From 10a199394b8f9b4c4e0be6e14a61109a7d891b1b Mon Sep 17 00:00:00 2001 From: Simon Arlott Date: Tue, 2 Feb 2010 15:33:38 +0100 Subject: netfilter: xt_TCPMSS: SYN packets are allowed to contain data The TCPMSS target is dropping SYN packets where: 1) There is data, or 2) The data offset makes the TCP header larger than the packet. Both of these result in an error level printk. This printk has been removed. This change avoids dropping SYN packets containing data. If there is also no MSS option (as well as data), one will not be added because of possible complications due to the increased packet size. Signed-off-by: Simon Arlott Signed-off-by: Patrick McHardy --- net/netfilter/xt_TCPMSS.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index eda64c1cb1e..6f21b4377db 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -60,17 +60,9 @@ tcpmss_mangle_packet(struct sk_buff *skb, tcplen = skb->len - tcphoff; tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); - /* Since it passed flags test in tcp match, we know it is is - not a fragment, and has data >= tcp header length. SYN - packets should not contain data: if they did, then we risk - running over MTU, sending Frag Needed and breaking things - badly. --RR */ - if (tcplen != tcph->doff*4) { - if (net_ratelimit()) - printk(KERN_ERR "xt_TCPMSS: bad length (%u bytes)\n", - skb->len); + /* Header cannot be larger than the packet */ + if (tcplen < tcph->doff*4) return -1; - } if (info->mss == XT_TCPMSS_CLAMP_PMTU) { if (dst_mtu(skb_dst(skb)) <= minlen) { @@ -115,6 +107,12 @@ tcpmss_mangle_packet(struct sk_buff *skb, } } + /* There is data after the header so the option can't be added + without moving it, and doing so may make the SYN packet + itself too large. Accept the packet unmodified instead. */ + if (tcplen > tcph->doff*4) + return 0; + /* * MSS Option not found ?! add it.. */ -- cgit v1.2.3 From 2eff25c18c3d332d3c4dd98f2ac9b7114e9771b0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:24:54 +0100 Subject: netfilter: xt_hashlimit: fix race condition and simplify locking As noticed by Shin Hong , there is a race between htable_find_get() and htable_put(): htable_put(): htable_find_get(): spin_lock_bh(&hashlimit_lock); atomic_dec_and_test(&hinfo->use) atomic_inc(&hinfo->use) spin_unlock_bh(&hashlimit_lock) return hinfo; spin_lock_bh(&hashlimit_lock); hlist_del(&hinfo->node); spin_unlock_bh(&hashlimit_lock); htable_destroy(hinfo); The entire locking concept is overly complicated, tables are only created/referenced and released in process context, so a single mutex works just fine. Remove the hashinfo_spinlock and atomic reference count and use the mutex to protect table lookups/creation and reference count changes. Signed-off-by: Patrick McHardy --- net/netfilter/xt_hashlimit.c | 52 +++++++++++++++----------------------------- 1 file changed, 18 insertions(+), 34 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index fb7fcb773a3..017c95966aa 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -90,7 +90,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - atomic_t use; + int use; u_int8_t family; bool rnd_initialized; @@ -109,8 +109,7 @@ struct xt_hashlimit_htable { struct hlist_head hash[0]; /* hashtable itself */ }; -static DEFINE_SPINLOCK(hashlimit_lock); /* protects htables list */ -static DEFINE_MUTEX(hlimit_mutex); /* additional checkentry protection */ +static DEFINE_MUTEX(hashlimit_mutex); /* protects htables list */ static struct kmem_cache *hashlimit_cachep __read_mostly; static inline bool dst_cmp(const struct dsthash_ent *ent, @@ -244,7 +243,7 @@ static int htable_create_v0(struct net *net, struct xt_hashlimit_info *minfo, u_ for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - atomic_set(&hinfo->use, 1); + hinfo->use = 1; hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -263,9 +262,9 @@ static int htable_create_v0(struct net *net, struct xt_hashlimit_info *minfo, u_ hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); add_timer(&hinfo->timer); - spin_lock_bh(&hashlimit_lock); + mutex_lock(&hashlimit_mutex); hlist_add_head(&hinfo->node, &hashlimit_net->htables); - spin_unlock_bh(&hashlimit_lock); + mutex_unlock(&hashlimit_mutex); return 0; } @@ -308,7 +307,7 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - atomic_set(&hinfo->use, 1); + hinfo->use = 1; hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -328,9 +327,9 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); add_timer(&hinfo->timer); - spin_lock_bh(&hashlimit_lock); + mutex_lock(&hashlimit_mutex); hlist_add_head(&hinfo->node, &hashlimit_net->htables); - spin_unlock_bh(&hashlimit_lock); + mutex_unlock(&hashlimit_mutex); return 0; } @@ -402,27 +401,24 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, struct xt_hashlimit_htable *hinfo; struct hlist_node *pos; - spin_lock_bh(&hashlimit_lock); hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->pde->name) && hinfo->family == family) { - atomic_inc(&hinfo->use); - spin_unlock_bh(&hashlimit_lock); + hinfo->use++; return hinfo; } } - spin_unlock_bh(&hashlimit_lock); return NULL; } static void htable_put(struct xt_hashlimit_htable *hinfo) { - if (atomic_dec_and_test(&hinfo->use)) { - spin_lock_bh(&hashlimit_lock); + mutex_lock(&hashlimit_mutex); + if (--hinfo->use == 0) { hlist_del(&hinfo->node); - spin_unlock_bh(&hashlimit_lock); htable_destroy(hinfo); } + mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) @@ -710,19 +706,13 @@ static bool hashlimit_mt_check_v0(const struct xt_mtchk_param *par) if (r->name[sizeof(r->name) - 1] != '\0') return false; - /* This is the best we've got: We cannot release and re-grab lock, - * since checkentry() is called before x_tables.c grabs xt_mutex. - * We also cannot grab the hashtable spinlock, since htable_create will - * call vmalloc, and that can sleep. And we cannot just re-search - * the list of htable's in htable_create(), since then we would - * create duplicate proc files. -HW */ - mutex_lock(&hlimit_mutex); + mutex_lock(&hashlimit_mutex); r->hinfo = htable_find_get(net, r->name, par->match->family); if (!r->hinfo && htable_create_v0(net, r, par->match->family) != 0) { - mutex_unlock(&hlimit_mutex); + mutex_unlock(&hashlimit_mutex); return false; } - mutex_unlock(&hlimit_mutex); + mutex_unlock(&hashlimit_mutex); return true; } @@ -752,19 +742,13 @@ static bool hashlimit_mt_check(const struct xt_mtchk_param *par) return false; } - /* This is the best we've got: We cannot release and re-grab lock, - * since checkentry() is called before x_tables.c grabs xt_mutex. - * We also cannot grab the hashtable spinlock, since htable_create will - * call vmalloc, and that can sleep. And we cannot just re-search - * the list of htable's in htable_create(), since then we would - * create duplicate proc files. -HW */ - mutex_lock(&hlimit_mutex); + mutex_lock(&hashlimit_mutex); info->hinfo = htable_find_get(net, info->name, par->match->family); if (!info->hinfo && htable_create(net, info, par->match->family) != 0) { - mutex_unlock(&hlimit_mutex); + mutex_unlock(&hashlimit_mutex); return false; } - mutex_unlock(&hlimit_mutex); + mutex_unlock(&hashlimit_mutex); return true; } -- cgit v1.2.3 From 794e68716bab578ae8f8912dc934496d7c7abc90 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:41:29 +0100 Subject: netfilter: ctnetlink: only assign helpers for matching protocols Make sure not to assign a helper for a different network or transport layer protocol to a connection. Additionally change expectation deletion by helper to compare the name directly - there might be multiple helper registrations using the same name, currently one of them is chosen in an unpredictable manner and only those expectations are removed. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_helper.c | 8 +++++--- net/netfilter/nf_conntrack_netlink.c | 23 +++++++++++------------ 2 files changed, 16 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 65c2a7bc3af..c0e461f466a 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -65,7 +65,7 @@ __nf_ct_helper_find(const struct nf_conntrack_tuple *tuple) } struct nf_conntrack_helper * -__nf_conntrack_helper_find_byname(const char *name) +__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; struct hlist_node *n; @@ -73,13 +73,15 @@ __nf_conntrack_helper_find_byname(const char *name) for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry_rcu(h, n, &nf_ct_helper_hash[i], hnode) { - if (!strcmp(h->name, name)) + if (!strcmp(h->name, name) && + h->tuple.src.l3num == l3num && + h->tuple.dst.protonum == protonum) return h; } } return NULL; } -EXPORT_SYMBOL_GPL(__nf_conntrack_helper_find_byname); +EXPORT_SYMBOL_GPL(__nf_conntrack_helper_find); struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 79478dfba27..16f86d61e5d 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1001,7 +1001,8 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) return 0; } - helper = __nf_conntrack_helper_find_byname(helpname); + helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), + nf_ct_protonum(ct)); if (helper == NULL) { #ifdef CONFIG_MODULES spin_unlock_bh(&nf_conntrack_lock); @@ -1012,7 +1013,8 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) } spin_lock_bh(&nf_conntrack_lock); - helper = __nf_conntrack_helper_find_byname(helpname); + helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), + nf_ct_protonum(ct)); if (helper) return -EAGAIN; #endif @@ -1211,7 +1213,8 @@ ctnetlink_create_conntrack(struct net *net, if (err < 0) goto err2; - helper = __nf_conntrack_helper_find_byname(helpname); + helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), + nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES @@ -1221,7 +1224,9 @@ ctnetlink_create_conntrack(struct net *net, } rcu_read_lock(); - helper = __nf_conntrack_helper_find_byname(helpname); + helper = __nf_conntrack_helper_find(helpname, + nf_ct_l3num(ct), + nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err2; @@ -1714,7 +1719,6 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct net *net = sock_net(ctnl); struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; - struct nf_conntrack_helper *h; struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct hlist_node *n, *next; u_int8_t u3 = nfmsg->nfgen_family; @@ -1751,18 +1755,13 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* delete all expectations for this helper */ spin_lock_bh(&nf_conntrack_lock); - h = __nf_conntrack_helper_find_byname(name); - if (!h) { - spin_unlock_bh(&nf_conntrack_lock); - return -EOPNOTSUPP; - } for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, n, next, &net->ct.expect_hash[i], hnode) { m_help = nfct_help(exp->master); - if (m_help->helper == h - && del_timer(&exp->timeout)) { + if (!strcmp(m_help->helper->name, name) && + del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } -- cgit v1.2.3 From add67461240c1dadc7c8d97e66f8f92b556ca523 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:45:12 +0100 Subject: netfilter: add struct net * to target parameters Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtables.c | 10 ++++++---- net/ipv4/netfilter/ip_tables.c | 8 +++++--- net/ipv6/netfilter/ip6_tables.c | 8 +++++--- 3 files changed, 16 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 1aa0e4c1f52..12beb580aa2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -579,13 +579,14 @@ ebt_cleanup_match(struct ebt_entry_match *m, struct net *net, unsigned int *i) } static inline int -ebt_cleanup_watcher(struct ebt_entry_watcher *w, unsigned int *i) +ebt_cleanup_watcher(struct ebt_entry_watcher *w, struct net *net, unsigned int *i) { struct xt_tgdtor_param par; if (i && (*i)-- == 0) return 1; + par.net = net; par.target = w->u.watcher; par.targinfo = w->data; par.family = NFPROTO_BRIDGE; @@ -606,10 +607,11 @@ ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) /* we're done */ if (cnt && (*cnt)-- == 0) return 1; - EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, NULL); + EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, NULL); EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, NULL); t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + par.net = net; par.target = t->u.target; par.targinfo = t->data; par.family = NFPROTO_BRIDGE; @@ -674,7 +676,7 @@ ebt_check_entry(struct ebt_entry *e, } i = 0; - mtpar.net = net; + mtpar.net = tgpar.net = net; mtpar.table = tgpar.table = name; mtpar.entryinfo = tgpar.entryinfo = e; mtpar.hook_mask = tgpar.hook_mask = hookmask; @@ -730,7 +732,7 @@ ebt_check_entry(struct ebt_entry *e, (*cnt)++; return 0; cleanup_watchers: - EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, &j); + EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, &j); cleanup_matches: EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, &i); return ret; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cfaba0e2e6f..7fde8f6950d 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -638,10 +638,11 @@ err: return ret; } -static int check_target(struct ipt_entry *e, const char *name) +static int check_target(struct ipt_entry *e, struct net *net, const char *name) { struct ipt_entry_target *t = ipt_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -697,7 +698,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; @@ -788,6 +789,7 @@ cleanup_entry(struct ipt_entry *e, struct net *net, unsigned int *i) IPT_MATCH_ITERATE(e, cleanup_match, net, NULL); t = ipt_get_target(e); + par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV4; @@ -1675,7 +1677,7 @@ compat_check_entry(struct ipt_entry *e, struct net *net, const char *name, if (ret) goto cleanup_matches; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto cleanup_matches; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 9f1d45f2ba8..0376ed6d559 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -669,10 +669,11 @@ err: return ret; } -static int check_target(struct ip6t_entry *e, const char *name) +static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct ip6t_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -729,7 +730,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; @@ -820,6 +821,7 @@ cleanup_entry(struct ip6t_entry *e, struct net *net, unsigned int *i) IP6T_MATCH_ITERATE(e, cleanup_match, net, NULL); t = ip6t_get_target(e); + par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; @@ -1710,7 +1712,7 @@ static int compat_check_entry(struct ip6t_entry *e, struct net *net, if (ret) goto cleanup_matches; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto cleanup_matches; -- cgit v1.2.3 From 858b31330054a9ad259feceea0ad1ce5385c47f0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:48:53 +0100 Subject: netfilter: nf_conntrack: split up IPCT_STATUS event Split up the IPCT_STATUS event into an IPCT_REPLY event, which is generated when the IPS_SEEN_REPLY bit is set, and an IPCT_ASSURED event, which is generated when the IPS_ASSURED bit is set. In combination with a following patch to support selective event delivery, this can be used for "sparse" conntrack replication: start replicating the conntrack entry after it reached the ASSURED state and that way it's SYN-flood resistant. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 6 ++++-- net/netfilter/nf_conntrack_proto_gre.c | 2 +- net/netfilter/nf_conntrack_proto_sctp.c | 2 +- net/netfilter/nf_conntrack_proto_tcp.c | 2 +- net/netfilter/nf_conntrack_proto_udp.c | 2 +- net/netfilter/nf_conntrack_proto_udplite.c | 2 +- 7 files changed, 10 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0e98c3282d4..091ff770eb7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -825,7 +825,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, } if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) - nf_conntrack_event_cache(IPCT_STATUS, ct); + nf_conntrack_event_cache(IPCT_REPLY, ct); return ret; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 16f86d61e5d..ff594eb138c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1371,7 +1371,8 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, else events = IPCT_NEW; - nf_conntrack_eventmask_report((1 << IPCT_STATUS) | + nf_conntrack_eventmask_report((1 << IPCT_REPLY) | + (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | @@ -1396,7 +1397,8 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err == 0) { nf_conntrack_get(&ct->ct_general); spin_unlock_bh(&nf_conntrack_lock); - nf_conntrack_eventmask_report((1 << IPCT_STATUS) | + nf_conntrack_eventmask_report((1 << IPCT_REPLY) | + (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index c99cfba64dd..d899b1a6994 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -241,7 +241,7 @@ static int gre_packet(struct nf_conn *ct, ct->proto.gre.stream_timeout); /* Also, more likely to be important, and not a probe. */ set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_STATUS, ct); + nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.timeout); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index f9d930f8027..b68ff15ed97 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -377,7 +377,7 @@ static int sctp_packet(struct nf_conn *ct, new_state == SCTP_CONNTRACK_ESTABLISHED) { pr_debug("Setting assured bit\n"); set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_STATUS, ct); + nf_conntrack_event_cache(IPCT_ASSURED, ct); } return NF_ACCEPT; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3c96437b45a..ad118053971 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1045,7 +1045,7 @@ static int tcp_packet(struct nf_conn *ct, after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_STATUS, ct); + nf_conntrack_event_cache(IPCT_ASSURED, ct); } nf_ct_refresh_acct(ct, ctinfo, skb, timeout); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 5c5518bedb4..8d38f9a4bed 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -77,7 +77,7 @@ static int udp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout_stream); /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) - nf_conntrack_event_cache(IPCT_STATUS, ct); + nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udp_timeout); diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 458655bb210..0b1bc9ba667 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -75,7 +75,7 @@ static int udplite_packet(struct nf_conn *ct, nf_ct_udplite_timeout_stream); /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) - nf_conntrack_event_cache(IPCT_STATUS, ct); + nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_udplite_timeout); -- cgit v1.2.3 From 0cebe4b4163b6373c9d24c1a192939777bc27e55 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 13:51:51 +0100 Subject: netfilter: ctnetlink: support selective event delivery Add two masks for conntrack end expectation events to struct nf_conntrack_ecache and use them to filter events. Their default value is "all events" when the event sysctl is on and "no events" when it is off. A following patch will add specific initializations. Expectation events depend on the ecache struct of their master conntrack. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 091ff770eb7..53b8da6ad6b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -648,7 +648,7 @@ init_conntrack(struct net *net, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); - nf_ct_ecache_ext_add(ct, GFP_ATOMIC); + nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); spin_lock_bh(&nf_conntrack_lock); exp = nf_ct_find_expectation(net, tuple); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index ff594eb138c..f5c0b09e12f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1281,7 +1281,7 @@ ctnetlink_create_conntrack(struct net *net, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); - nf_ct_ecache_ext_add(ct, GFP_ATOMIC); + nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) -- cgit v1.2.3 From b2a15a604d379af323645e330638e2cfcc696aff Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 14:13:03 +0100 Subject: netfilter: nf_conntrack: support conntrack templates Support initializing selected parameters of new conntrack entries from a "conntrack template", which is a specially marked conntrack entry attached to the skb. Currently the helper and the event delivery masks can be initialized this way. Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_defrag_ipv4.c | 2 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 2 +- net/netfilter/nf_conntrack_core.c | 50 +++++++++++++++++--------- net/netfilter/nf_conntrack_helper.c | 17 ++++++--- net/netfilter/nf_conntrack_netlink.c | 2 +- 5 files changed, 50 insertions(+), 23 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 331ead3ebd1..77627fa8056 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -59,7 +59,7 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #if !defined(CONFIG_NF_NAT) && !defined(CONFIG_NF_NAT_MODULE) /* Previously seen (loopback)? Ignore. Do this before fragment check. */ - if (skb->nfct) + if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) return NF_ACCEPT; #endif #endif diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 0956ebabbff..55ce22e5de4 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -212,7 +212,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, struct sk_buff *reasm; /* Previously seen (loopback)? */ - if (skb->nfct) + if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) return NF_ACCEPT; reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 53b8da6ad6b..471e2a79d26 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -618,7 +618,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free); /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ static struct nf_conntrack_tuple_hash * -init_conntrack(struct net *net, +init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, @@ -628,6 +628,7 @@ init_conntrack(struct net *net, struct nf_conn *ct; struct nf_conn_help *help; struct nf_conntrack_tuple repl_tuple; + struct nf_conntrack_ecache *ecache; struct nf_conntrack_expect *exp; if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) { @@ -648,7 +649,11 @@ init_conntrack(struct net *net, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); - nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); + + ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; + nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, + ecache ? ecache->expmask : 0, + GFP_ATOMIC); spin_lock_bh(&nf_conntrack_lock); exp = nf_ct_find_expectation(net, tuple); @@ -673,7 +678,7 @@ init_conntrack(struct net *net, nf_conntrack_get(&ct->master->ct_general); NF_CT_STAT_INC(net, expect_new); } else { - __nf_ct_try_assign_helper(ct, GFP_ATOMIC); + __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); NF_CT_STAT_INC(net, new); } @@ -694,7 +699,7 @@ init_conntrack(struct net *net, /* On success, returns conntrack ptr, sets skb->nfct and ctinfo */ static inline struct nf_conn * -resolve_normal_ct(struct net *net, +resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int16_t l3num, @@ -718,7 +723,8 @@ resolve_normal_ct(struct net *net, /* look for tuple match */ h = nf_conntrack_find_get(net, &tuple); if (!h) { - h = init_conntrack(net, &tuple, l3proto, l4proto, skb, dataoff); + h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, + skb, dataoff); if (!h) return NULL; if (IS_ERR(h)) @@ -755,7 +761,7 @@ unsigned int nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, struct sk_buff *skb) { - struct nf_conn *ct; + struct nf_conn *ct, *tmpl = NULL; enum ip_conntrack_info ctinfo; struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; @@ -764,10 +770,14 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, int set_reply = 0; int ret; - /* Previously seen (loopback or untracked)? Ignore. */ if (skb->nfct) { - NF_CT_STAT_INC_ATOMIC(net, ignore); - return NF_ACCEPT; + /* Previously seen (loopback or untracked)? Ignore. */ + tmpl = (struct nf_conn *)skb->nfct; + if (!nf_ct_is_template(tmpl)) { + NF_CT_STAT_INC_ATOMIC(net, ignore); + return NF_ACCEPT; + } + skb->nfct = NULL; } /* rcu_read_lock()ed by nf_hook_slow */ @@ -778,7 +788,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, pr_debug("not prepared to track yet or error occured\n"); NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); - return -ret; + ret = -ret; + goto out; } l4proto = __nf_ct_l4proto_find(pf, protonum); @@ -791,22 +802,25 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, if (ret <= 0) { NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); - return -ret; + ret = -ret; + goto out; } } - ct = resolve_normal_ct(net, skb, dataoff, pf, protonum, + ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, l3proto, l4proto, &set_reply, &ctinfo); if (!ct) { /* Not valid part of a connection */ NF_CT_STAT_INC_ATOMIC(net, invalid); - return NF_ACCEPT; + ret = NF_ACCEPT; + goto out; } if (IS_ERR(ct)) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(net, drop); - return NF_DROP; + ret = NF_DROP; + goto out; } NF_CT_ASSERT(skb->nfct); @@ -821,11 +835,15 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, NF_CT_STAT_INC_ATOMIC(net, invalid); if (ret == -NF_DROP) NF_CT_STAT_INC_ATOMIC(net, drop); - return -ret; + ret = -ret; + goto out; } if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_REPLY, ct); +out: + if (tmpl) + nf_ct_put(tmpl); return ret; } @@ -864,7 +882,7 @@ void nf_conntrack_alter_reply(struct nf_conn *ct, return; rcu_read_lock(); - __nf_ct_try_assign_helper(ct, GFP_ATOMIC); + __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index c0e461f466a..8144b0da551 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -96,13 +96,22 @@ struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) } EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); -int __nf_ct_try_assign_helper(struct nf_conn *ct, gfp_t flags) +int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, + gfp_t flags) { + struct nf_conntrack_helper *helper = NULL; + struct nf_conn_help *help; int ret = 0; - struct nf_conntrack_helper *helper; - struct nf_conn_help *help = nfct_help(ct); - helper = __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + if (tmpl != NULL) { + help = nfct_help(tmpl); + if (help != NULL) + helper = help->helper; + } + + help = nfct_help(ct); + if (helper == NULL) + helper = __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); if (helper == NULL) { if (help) rcu_assign_pointer(help->helper, NULL); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f5c0b09e12f..09044f9f4b2 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1249,7 +1249,7 @@ ctnetlink_create_conntrack(struct net *net, } } else { /* try an implicit helper assignation */ - err = __nf_ct_try_assign_helper(ct, GFP_ATOMIC); + err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC); if (err < 0) goto err2; } -- cgit v1.2.3 From 84f3bb9ae9db90f7fb15d98b55279a58ab1b2363 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 3 Feb 2010 17:17:06 +0100 Subject: netfilter: xtables: add CT target Add a new target for the raw table, which can be used to specify conntrack parameters for specific connections, f.i. the conntrack helper. The target attaches a "template" connection tracking entry to the skb, which is used by the conntrack core when initializing a new conntrack. Signed-off-by: Patrick McHardy --- net/netfilter/Kconfig | 12 +++ net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_helper.c | 19 +++++ net/netfilter/xt_CT.c | 158 ++++++++++++++++++++++++++++++++++++ 4 files changed, 190 insertions(+) create mode 100644 net/netfilter/xt_CT.c (limited to 'net') diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 634d14affc8..4469d45261f 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -341,6 +341,18 @@ config NETFILTER_XT_TARGET_CONNSECMARK To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_TARGET_CT + tristate '"CT" target support' + depends on NF_CONNTRACK + depends on IP_NF_RAW || IP6_NF_RAW + depends on NETFILTER_ADVANCED + help + This options adds a `CT' target, which allows to specify initial + connection tracking parameters like events to be delivered and + the helper to be used. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_DSCP tristate '"DSCP" and "TOS" target support' depends on IP_NF_MANGLE || IP6_NF_MANGLE diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 49f62ee4e9f..f873644f02f 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o obj-$(CONFIG_NETFILTER_XT_TARGET_CONNMARK) += xt_CONNMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o +obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 8144b0da551..a74a5769877 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -83,6 +83,25 @@ __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) } EXPORT_SYMBOL_GPL(__nf_conntrack_helper_find); +struct nf_conntrack_helper * +nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) +{ + struct nf_conntrack_helper *h; + + h = __nf_conntrack_helper_find(name, l3num, protonum); +#ifdef CONFIG_MODULES + if (h == NULL) { + if (request_module("nfct-helper-%s", name) == 0) + h = __nf_conntrack_helper_find(name, l3num, protonum); + } +#endif + if (h != NULL && !try_module_get(h->me)) + h = NULL; + + return h; +} +EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); + struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) { struct nf_conn_help *help; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c new file mode 100644 index 00000000000..8183a054256 --- /dev/null +++ b/net/netfilter/xt_CT.c @@ -0,0 +1,158 @@ +/* + * Copyright (c) 2010 Patrick McHardy + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned int xt_ct_target(struct sk_buff *skb, + const struct xt_target_param *par) +{ + const struct xt_ct_target_info *info = par->targinfo; + struct nf_conn *ct = info->ct; + + /* Previously seen (loopback)? Ignore. */ + if (skb->nfct != NULL) + return XT_CONTINUE; + + atomic_inc(&ct->ct_general.use); + skb->nfct = &ct->ct_general; + skb->nfctinfo = IP_CT_NEW; + + return XT_CONTINUE; +} + +static u8 xt_ct_find_proto(const struct xt_tgchk_param *par) +{ + if (par->family == AF_INET) { + const struct ipt_entry *e = par->entryinfo; + + if (e->ip.invflags & IPT_INV_PROTO) + return 0; + return e->ip.proto; + } else if (par->family == AF_INET6) { + const struct ip6t_entry *e = par->entryinfo; + + if (e->ipv6.invflags & IP6T_INV_PROTO) + return 0; + return e->ipv6.proto; + } else + return 0; +} + +static bool xt_ct_tg_check(const struct xt_tgchk_param *par) +{ + struct xt_ct_target_info *info = par->targinfo; + struct nf_conntrack_tuple t; + struct nf_conn_help *help; + struct nf_conn *ct; + u8 proto; + + if (info->flags & ~XT_CT_NOTRACK) + return false; + + if (info->flags & XT_CT_NOTRACK) { + ct = &nf_conntrack_untracked; + atomic_inc(&ct->ct_general.use); + goto out; + } + + if (nf_ct_l3proto_try_module_get(par->family) < 0) + goto err1; + + memset(&t, 0, sizeof(t)); + ct = nf_conntrack_alloc(par->net, &t, &t, GFP_KERNEL); + if (IS_ERR(ct)) + goto err2; + + if ((info->ct_events || info->exp_events) && + !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events, + GFP_KERNEL)) + goto err3; + + if (info->helper[0]) { + proto = xt_ct_find_proto(par); + if (!proto) + goto err3; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (help == NULL) + goto err3; + + help->helper = nf_conntrack_helper_try_module_get(info->helper, + par->family, + proto); + if (help->helper == NULL) + goto err3; + } + + __set_bit(IPS_TEMPLATE_BIT, &ct->status); + __set_bit(IPS_CONFIRMED_BIT, &ct->status); +out: + info->ct = ct; + return true; + +err3: + nf_conntrack_free(ct); +err2: + nf_ct_l3proto_module_put(par->family); +err1: + return false; +} + +static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par) +{ + struct xt_ct_target_info *info = par->targinfo; + struct nf_conn *ct = info->ct; + struct nf_conn_help *help; + + if (ct != &nf_conntrack_untracked) { + help = nfct_help(ct); + if (help) + module_put(help->helper->me); + + nf_ct_l3proto_module_put(par->family); + } + nf_ct_put(info->ct); +} + +static struct xt_target xt_ct_tg __read_mostly = { + .name = "CT", + .family = NFPROTO_UNSPEC, + .targetsize = XT_ALIGN(sizeof(struct xt_ct_target_info)), + .checkentry = xt_ct_tg_check, + .destroy = xt_ct_tg_destroy, + .target = xt_ct_target, + .table = "raw", + .me = THIS_MODULE, +}; + +static int __init xt_ct_tg_init(void) +{ + return xt_register_target(&xt_ct_tg); +} + +static void __exit xt_ct_tg_exit(void) +{ + xt_unregister_target(&xt_ct_tg); +} + +module_init(xt_ct_tg_init); +module_exit(xt_ct_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: connection tracking target"); +MODULE_ALIAS("ipt_CT"); +MODULE_ALIAS("ip6t_CT"); -- cgit v1.2.3 From 76780373190d7e8ddfb6fed06aef068e2445c743 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 8 Feb 2010 15:39:16 +0100 Subject: netfilter: fix build failure with CONNTRACK=y NAT=n net/ipv4/netfilter/nf_defrag_ipv4.c: In function 'ipv4_conntrack_defrag': net/ipv4/netfilter/nf_defrag_ipv4.c:62: error: implicit declaration of function 'nf_ct_is_template' Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_defrag_ipv4.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 77627fa8056..f6f46686cbc 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -17,6 +17,7 @@ #include #include #include +#include /* Returns new sk_buff, or NULL */ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) -- cgit v1.2.3 From 42107f5009da223daa800d6da6904d77297ae829 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 10 Feb 2010 15:03:27 +0100 Subject: netfilter: xtables: symmetric COMPAT_XT_ALIGN definition Rewrite COMPAT_XT_ALIGN in terms of dummy structure hack. Compat counters logically have nothing to do with it. Use ALIGN() macro while I'm at it for same types. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/netfilter/x_tables.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index f01955cce31..5c564ff10a3 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -364,7 +364,7 @@ int xt_check_match(struct xt_mtchk_param *par, * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ - pr_err("%s_tables: %s match: invalid size %Zu != %u\n", + pr_err("%s_tables: %s match: invalid size %u != %u\n", xt_prefix[par->family], par->match->name, XT_ALIGN(par->match->matchsize), size); return -EINVAL; @@ -514,7 +514,7 @@ int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { if (XT_ALIGN(par->target->targetsize) != size) { - pr_err("%s_tables: %s target: invalid size %Zu != %u\n", + pr_err("%s_tables: %s target: invalid size %u != %u\n", xt_prefix[par->family], par->target->name, XT_ALIGN(par->target->targetsize), size); return -EINVAL; -- cgit v1.2.3 From d0b0268fddea3235a8df35e52167c3b206bf2f5a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 10 Feb 2010 15:38:33 +0100 Subject: netfilter: ctnetlink: add missing netlink attribute policies Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 41 +++++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 327c5174440..5c103b8c7df 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -708,6 +708,11 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr, return ret; } +static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { + [CTA_TUPLE_IP] = { .type = NLA_NESTED }, + [CTA_TUPLE_PROTO] = { .type = NLA_NESTED }, +}; + static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, @@ -718,7 +723,7 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], memset(tuple, 0, sizeof(*tuple)); - nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], NULL); + nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy); if (!tb[CTA_TUPLE_IP]) return -EINVAL; @@ -745,12 +750,16 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], return 0; } +static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { + [CTA_HELP_NAME] = { .type = NLA_NUL_STRING }, +}; + static inline int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) { struct nlattr *tb[CTA_HELP_MAX+1]; - nla_parse_nested(tb, CTA_HELP_MAX, attr, NULL); + nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy); if (!tb[CTA_HELP_NAME]) return -EINVAL; @@ -761,11 +770,17 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) } static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { + [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, + [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, [CTA_STATUS] = { .type = NLA_U32 }, + [CTA_PROTOINFO] = { .type = NLA_NESTED }, + [CTA_HELP] = { .type = NLA_NESTED }, + [CTA_NAT_SRC] = { .type = NLA_NESTED }, [CTA_TIMEOUT] = { .type = NLA_U32 }, [CTA_MARK] = { .type = NLA_U32 }, - [CTA_USE] = { .type = NLA_U32 }, [CTA_ID] = { .type = NLA_U32 }, + [CTA_NAT_DST] = { .type = NLA_NESTED }, + [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, }; static int @@ -1053,6 +1068,12 @@ ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) return 0; } +static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = { + [CTA_PROTOINFO_TCP] = { .type = NLA_NESTED }, + [CTA_PROTOINFO_DCCP] = { .type = NLA_NESTED }, + [CTA_PROTOINFO_SCTP] = { .type = NLA_NESTED }, +}; + static inline int ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[]) { @@ -1061,7 +1082,7 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[] struct nf_conntrack_l4proto *l4proto; int err = 0; - nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, NULL); + nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy); rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); @@ -1073,12 +1094,18 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[] } #ifdef CONFIG_NF_NAT_NEEDED +static const struct nla_policy nat_seq_policy[CTA_NAT_SEQ_MAX+1] = { + [CTA_NAT_SEQ_CORRECTION_POS] = { .type = NLA_U32 }, + [CTA_NAT_SEQ_OFFSET_BEFORE] = { .type = NLA_U32 }, + [CTA_NAT_SEQ_OFFSET_AFTER] = { .type = NLA_U32 }, +}; + static inline int change_nat_seq_adj(struct nf_nat_seq *natseq, const struct nlattr * const attr) { struct nlattr *cda[CTA_NAT_SEQ_MAX+1]; - nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, NULL); + nla_parse_nested(cda, CTA_NAT_SEQ_MAX, attr, nat_seq_policy); if (!cda[CTA_NAT_SEQ_CORRECTION_POS]) return -EINVAL; @@ -1648,8 +1675,12 @@ out: } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { + [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, + [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, + [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, + [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING }, }; static int -- cgit v1.2.3 From 737535c5cf3524e4bfaa91e22edefd52eccabbce Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 13 Jun 2009 06:46:36 +0200 Subject: netfilter: xtables: compact table hook functions (1/2) This patch combines all the per-hook functions in a given table into a single function. Together with the 2nd patch, further simplifications are possible up to the point of output code reduction. Signed-off-by: Jan Engelhardt --- net/ipv4/netfilter/arptable_filter.c | 30 ++++++-------- net/ipv4/netfilter/iptable_filter.c | 50 ++++++++---------------- net/ipv4/netfilter/iptable_mangle.c | 71 ++++++++++------------------------ net/ipv4/netfilter/iptable_raw.c | 26 +++++-------- net/ipv4/netfilter/iptable_security.c | 50 ++++++++---------------- net/ipv6/netfilter/ip6table_filter.c | 40 ++++++------------- net/ipv6/netfilter/ip6table_mangle.c | 50 ++++++++++-------------- net/ipv6/netfilter/ip6table_raw.c | 26 +++++-------- net/ipv6/netfilter/ip6table_security.c | 41 ++++++-------------- 9 files changed, 126 insertions(+), 258 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 97337601827..e9d823b149c 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -53,43 +53,37 @@ static const struct xt_table packet_filter = { }; /* The work comes in here from netfilter.c */ -static unsigned int arpt_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int +arptable_filter_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return arpt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.arptable_filter); -} + if (hook == NF_ARP_OUT) + return arpt_do_table(skb, hook, in, out, + dev_net(out)->ipv4.arptable_filter); -static unsigned int arpt_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ + /* INPUT/FORWARD: */ return arpt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.arptable_filter); + dev_net(in)->ipv4.arptable_filter); } static struct nf_hook_ops arpt_ops[] __read_mostly = { { - .hook = arpt_in_hook, + .hook = arptable_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_ARP, .hooknum = NF_ARP_IN, .priority = NF_IP_PRI_FILTER, }, { - .hook = arpt_out_hook, + .hook = arptable_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_ARP, .hooknum = NF_ARP_OUT, .priority = NF_IP_PRI_FILTER, }, { - .hook = arpt_in_hook, + .hook = arptable_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_ARP, .hooknum = NF_ARP_FORWARD, diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index dee90eb8aa4..5369833ad56 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -60,61 +60,43 @@ static const struct xt_table packet_filter = { .af = NFPROTO_IPV4, }; -/* The work comes in here from netfilter.c. */ static unsigned int -ipt_local_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +iptable_filter_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_filter); -} + if (hook == NF_INET_LOCAL_OUT) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) + /* root is playing with raw sockets. */ + return NF_ACCEPT; + + return ipt_do_table(skb, hook, in, out, + dev_net(out)->ipv4.iptable_filter); + } -static unsigned int -ipt_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ + /* LOCAL_IN/FORWARD: */ return ipt_do_table(skb, hook, in, out, dev_net(in)->ipv4.iptable_filter); } -static unsigned int -ipt_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) - return NF_ACCEPT; - return ipt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.iptable_filter); -} - static struct nf_hook_ops ipt_ops[] __read_mostly = { { - .hook = ipt_local_in_hook, + .hook = iptable_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_FILTER, }, { - .hook = ipt_hook, + .hook = iptable_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_FILTER, }, { - .hook = ipt_local_out_hook, + .hook = iptable_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index e07bf242343..4e699cd275c 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -71,51 +71,6 @@ static const struct xt_table packet_mangler = { .af = NFPROTO_IPV4, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ipt_pre_routing_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_mangle); -} - -static unsigned int -ipt_post_routing_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ipt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.iptable_mangle); -} - -static unsigned int -ipt_local_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_mangle); -} - -static unsigned int -ipt_forward_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_mangle); -} - static unsigned int ipt_local_hook(unsigned int hook, struct sk_buff *skb, @@ -158,37 +113,53 @@ ipt_local_hook(unsigned int hook, return ret; } +/* The work comes in here from netfilter.c. */ +static unsigned int +iptable_mangle_hook(unsigned int hook, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (hook == NF_INET_LOCAL_OUT) + return ipt_local_hook(hook, skb, in, out, okfn); + + /* PREROUTING/INPUT/FORWARD: */ + return ipt_do_table(skb, hook, in, out, + dev_net(in)->ipv4.iptable_mangle); +} + static struct nf_hook_ops ipt_ops[] __read_mostly = { { - .hook = ipt_pre_routing_hook, + .hook = iptable_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_MANGLE, }, { - .hook = ipt_local_in_hook, + .hook = iptable_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_MANGLE, }, { - .hook = ipt_forward_hook, + .hook = iptable_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_MANGLE, }, { - .hook = ipt_local_hook, + .hook = iptable_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_MANGLE, }, { - .hook = ipt_post_routing_hook, + .hook = iptable_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 40f2b9f611a..2c55575e89f 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -45,23 +45,15 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -ipt_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +iptable_raw_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_raw); -} + if (hook == NF_INET_PRE_ROUTING) + return ipt_do_table(skb, hook, in, out, + dev_net(in)->ipv4.iptable_raw); -static unsigned int -ipt_local_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ + /* OUTPUT: */ /* root is playing with raw sockets. */ if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) @@ -73,14 +65,14 @@ ipt_local_hook(unsigned int hook, /* 'raw' is the very first table. */ static struct nf_hook_ops ipt_ops[] __read_mostly = { { - .hook = ipt_hook, + .hook = iptable_raw_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_RAW, .owner = THIS_MODULE, }, { - .hook = ipt_local_hook, + .hook = iptable_raw_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_RAW, diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 7ce2366e430..1c666bab326 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -65,59 +65,43 @@ static const struct xt_table security_table = { }; static unsigned int -ipt_local_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +iptable_security_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_security); -} + if (hook == NF_INET_LOCAL_OUT) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) + /* Somebody is playing with raw sockets. */ + return NF_ACCEPT; -static unsigned int -ipt_forward_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_security); -} + return ipt_do_table(skb, hook, in, out, + dev_net(out)->ipv4.iptable_security); + } -static unsigned int -ipt_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - /* Somebody is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) - return NF_ACCEPT; + /* INPUT/FORWARD: */ return ipt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.iptable_security); + dev_net(in)->ipv4.iptable_security); } static struct nf_hook_ops ipt_ops[] __read_mostly = { { - .hook = ipt_local_in_hook, + .hook = iptable_security_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_SECURITY, }, { - .hook = ipt_forward_hook, + .hook = iptable_security_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SECURITY, }, { - .hook = ipt_local_out_hook, + .hook = iptable_security_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 33ddfe53e18..38074e933f6 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -60,54 +60,36 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6t_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_filter); -} - -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ -#if 0 - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) { - if (net_ratelimit()) - printk("ip6t_hook: happy cracking.\n"); - return NF_ACCEPT; - } -#endif + if (hook == NF_INET_LOCAL_OUT) + return ip6t_do_table(skb, hook, in, out, + dev_net(out)->ipv6.ip6table_filter); + /* INPUT/FORWARD: */ return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_filter); + dev_net(in)->ipv6.ip6table_filter); } static struct nf_hook_ops ip6t_ops[] __read_mostly = { { - .hook = ip6t_in_hook, + .hook = ip6table_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_FILTER, }, { - .hook = ip6t_in_hook, + .hook = ip6table_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_FILTER, }, { - .hook = ip6t_local_out_hook, + .hook = ip6table_filter_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 9bc483f000e..405ac1f7639 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -64,33 +64,9 @@ static const struct xt_table packet_mangler = { .af = NFPROTO_IPV6, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6t_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_mangle); -} - -static unsigned int -ip6t_post_routing_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_mangle); -} - static unsigned int ip6t_local_out_hook(unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { @@ -119,7 +95,7 @@ ip6t_local_out_hook(unsigned int hook, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, hook, in, out, + ret = ip6t_do_table(skb, hook, NULL, out, dev_net(out)->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && @@ -132,37 +108,51 @@ ip6t_local_out_hook(unsigned int hook, return ret; } +/* The work comes in here from netfilter.c. */ +static unsigned int +ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (hook == NF_INET_LOCAL_OUT) + return ip6t_local_out_hook(hook, skb, out, okfn); + + /* INPUT/FORWARD */ + return ip6t_do_table(skb, hook, in, out, + dev_net(in)->ipv6.ip6table_mangle); +} + static struct nf_hook_ops ip6t_ops[] __read_mostly = { { - .hook = ip6t_in_hook, + .hook = ip6table_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_MANGLE, }, { - .hook = ip6t_in_hook, + .hook = ip6table_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_MANGLE, }, { - .hook = ip6t_in_hook, + .hook = ip6table_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_MANGLE, }, { - .hook = ip6t_local_out_hook, + .hook = ip6table_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_MANGLE, }, { - .hook = ip6t_post_routing_hook, + .hook = ip6table_mangle_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 4c90b552e43..985e27cf1e0 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -44,37 +44,29 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6t_pre_routing_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_raw_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_raw); -} + if (hook == NF_INET_PRE_ROUTING) + return ip6t_do_table(skb, hook, in, out, + dev_net(in)->ipv6.ip6table_raw); -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ + /* OUTPUT: */ return ip6t_do_table(skb, hook, in, out, dev_net(out)->ipv6.ip6table_raw); } static struct nf_hook_ops ip6t_ops[] __read_mostly = { { - .hook = ip6t_pre_routing_hook, + .hook = ip6table_raw_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, .owner = THIS_MODULE, }, { - .hook = ip6t_local_out_hook, + .hook = ip6table_raw_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_FIRST, diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index baa8d4ef3b0..83585892935 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -64,56 +64,37 @@ static const struct xt_table security_table = { }; static unsigned int -ip6t_local_in_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_security_hook(unsigned int hook, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_security); -} + if (hook == NF_INET_LOCAL_OUT) + return ip6t_do_table(skb, hook, in, out, + dev_net(out)->ipv6.ip6table_security); -static unsigned int -ip6t_forward_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ + /* INPUT/FORWARD: */ return ip6t_do_table(skb, hook, in, out, dev_net(in)->ipv6.ip6table_security); } -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - /* TBD: handle short packets via raw socket */ - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_security); -} - static struct nf_hook_ops ip6t_ops[] __read_mostly = { { - .hook = ip6t_local_in_hook, + .hook = ip6table_security_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_SECURITY, }, { - .hook = ip6t_forward_hook, + .hook = ip6table_security_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SECURITY, }, { - .hook = ip6t_local_out_hook, + .hook = ip6table_security_hook, .owner = THIS_MODULE, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, -- cgit v1.2.3 From 2b21e051472fdb4680076278b2ccf63ebc1cc3bc Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 13 Jun 2009 06:57:10 +0200 Subject: netfilter: xtables: compact table hook functions (2/2) The calls to ip6t_do_table only show minimal differences, so it seems like a good cleanup to merge them to a single one too. Space saving obtained by both patches: 6807725->6807373 ("Total" column from `size -A`.) Signed-off-by: Jan Engelhardt --- net/ipv4/netfilter/arptable_filter.c | 8 ++------ net/ipv4/netfilter/iptable_filter.c | 21 +++++++++------------ net/ipv4/netfilter/iptable_raw.c | 19 +++++++++---------- net/ipv4/netfilter/iptable_security.c | 23 ++++++++++------------- net/ipv6/netfilter/ip6table_filter.c | 8 ++------ net/ipv6/netfilter/ip6table_raw.c | 8 ++------ net/ipv6/netfilter/ip6table_security.c | 8 ++------ 7 files changed, 36 insertions(+), 59 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index e9d823b149c..deeda9b2cf0 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -58,13 +58,9 @@ arptable_filter_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_ARP_OUT) - return arpt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.arptable_filter); + const struct net *net = dev_net((in != NULL) ? in : out); - /* INPUT/FORWARD: */ - return arpt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.arptable_filter); + return arpt_do_table(skb, hook, in, out, net->ipv4.arptable_filter); } static struct nf_hook_ops arpt_ops[] __read_mostly = { diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 5369833ad56..1bfeaae6f62 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -65,19 +65,16 @@ iptable_filter_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) { - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) - /* root is playing with raw sockets. */ - return NF_ACCEPT; - - return ipt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.iptable_filter); - } + const struct net *net; + + if (hook == NF_INET_LOCAL_OUT && + (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr))) + /* root is playing with raw sockets. */ + return NF_ACCEPT; - /* LOCAL_IN/FORWARD: */ - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_filter); + net = dev_net((in != NULL) ? in : out); + return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_filter); } static struct nf_hook_ops ipt_ops[] __read_mostly = { diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 2c55575e89f..d16e43777c3 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -49,17 +49,16 @@ iptable_raw_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_PRE_ROUTING) - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_raw); - - /* OUTPUT: */ - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) + const struct net *net; + + if (hook == NF_INET_LOCAL_OUT && + (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr))) + /* root is playing with raw sockets. */ return NF_ACCEPT; - return ipt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.iptable_raw); + + net = dev_net((in != NULL) ? in : out); + return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_raw); } /* 'raw' is the very first table. */ diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 1c666bab326..324505aaaa7 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -70,19 +70,16 @@ iptable_security_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) { - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) - /* Somebody is playing with raw sockets. */ - return NF_ACCEPT; - - return ipt_do_table(skb, hook, in, out, - dev_net(out)->ipv4.iptable_security); - } - - /* INPUT/FORWARD: */ - return ipt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.iptable_security); + const struct net *net; + + if (hook == NF_INET_LOCAL_OUT && + (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr))) + /* Somebody is playing with raw sockets. */ + return NF_ACCEPT; + + net = dev_net((in != NULL) ? in : out); + return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_security); } static struct nf_hook_ops ipt_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 38074e933f6..866f34ae236 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -64,13 +64,9 @@ ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_filter); + const struct net *net = dev_net((in != NULL) ? in : out); - /* INPUT/FORWARD: */ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_filter); + return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter); } static struct nf_hook_ops ip6t_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 985e27cf1e0..5451a36fbc2 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -48,13 +48,9 @@ ip6table_raw_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_PRE_ROUTING) - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_raw); + const struct net *net = dev_net((in != NULL) ? in : out); - /* OUTPUT: */ - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_raw); + return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw); } static struct nf_hook_ops ip6t_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 83585892935..841ea77f521 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -69,13 +69,9 @@ ip6table_security_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) - return ip6t_do_table(skb, hook, in, out, - dev_net(out)->ipv6.ip6table_security); + const struct net *net = dev_net((in != NULL) ? in : out); - /* INPUT/FORWARD: */ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_security); + return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security); } static struct nf_hook_ops ip6t_ops[] __read_mostly = { -- cgit v1.2.3 From 2b95efe7f6bb750256a702cc32d33b0cb2cd8223 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 17 Jun 2009 13:57:48 +0200 Subject: netfilter: xtables: use xt_table for hook instantiation The respective xt_table structures already have most of the metadata needed for hook setup. Add a 'priority' field to struct xt_table so that xt_hook_link() can be called with a reduced number of arguments. So should we be having more tables in the future, it comes at no static cost (only runtime, as before) - space saved: 6807373->6806555. Signed-off-by: Jan Engelhardt --- net/ipv4/netfilter/arptable_filter.c | 33 +++++---------------- net/ipv4/netfilter/iptable_filter.c | 33 +++++---------------- net/ipv4/netfilter/iptable_mangle.c | 47 +++++------------------------ net/ipv4/netfilter/iptable_raw.c | 27 +++++------------ net/ipv4/netfilter/iptable_security.c | 33 +++++---------------- net/ipv6/netfilter/ip6table_filter.c | 33 +++++---------------- net/ipv6/netfilter/ip6table_mangle.c | 48 +++++------------------------- net/ipv6/netfilter/ip6table_raw.c | 26 +++++----------- net/ipv6/netfilter/ip6table_security.c | 33 +++++---------------- net/netfilter/x_tables.c | 54 ++++++++++++++++++++++++++++++++++ 10 files changed, 117 insertions(+), 250 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index deeda9b2cf0..b361de0dac4 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -50,6 +50,7 @@ static const struct xt_table packet_filter = { .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_ARP, + .priority = NF_IP_PRI_FILTER, }; /* The work comes in here from netfilter.c */ @@ -63,29 +64,7 @@ arptable_filter_hook(unsigned int hook, struct sk_buff *skb, return arpt_do_table(skb, hook, in, out, net->ipv4.arptable_filter); } -static struct nf_hook_ops arpt_ops[] __read_mostly = { - { - .hook = arptable_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_ARP, - .hooknum = NF_ARP_IN, - .priority = NF_IP_PRI_FILTER, - }, - { - .hook = arptable_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_ARP, - .hooknum = NF_ARP_OUT, - .priority = NF_IP_PRI_FILTER, - }, - { - .hook = arptable_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_ARP, - .hooknum = NF_ARP_FORWARD, - .priority = NF_IP_PRI_FILTER, - }, -}; +static struct nf_hook_ops *arpfilter_ops __read_mostly; static int __net_init arptable_filter_net_init(struct net *net) { @@ -115,9 +94,11 @@ static int __init arptable_filter_init(void) if (ret < 0) return ret; - ret = nf_register_hooks(arpt_ops, ARRAY_SIZE(arpt_ops)); - if (ret < 0) + arpfilter_ops = xt_hook_link(&packet_filter, arptable_filter_hook); + if (IS_ERR(arpfilter_ops)) { + ret = PTR_ERR(arpfilter_ops); goto cleanup_table; + } return ret; cleanup_table: @@ -127,7 +108,7 @@ cleanup_table: static void __exit arptable_filter_fini(void) { - nf_unregister_hooks(arpt_ops, ARRAY_SIZE(arpt_ops)); + xt_hook_unlink(&packet_filter, arpfilter_ops); unregister_pernet_subsys(&arptable_filter_net_ops); } diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 1bfeaae6f62..c14bb85db1d 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -58,6 +58,7 @@ static const struct xt_table packet_filter = { .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, + .priority = NF_IP_PRI_FILTER, }; static unsigned int @@ -77,29 +78,7 @@ iptable_filter_hook(unsigned int hook, struct sk_buff *skb, return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_filter); } -static struct nf_hook_ops ipt_ops[] __read_mostly = { - { - .hook = iptable_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_FILTER, - }, - { - .hook = iptable_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP_PRI_FILTER, - }, - { - .hook = iptable_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_FILTER, - }, -}; +static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ static int forward = NF_ACCEPT; @@ -142,9 +121,11 @@ static int __init iptable_filter_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); - if (ret < 0) + filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook); + if (IS_ERR(filter_ops)) { + ret = PTR_ERR(filter_ops); goto cleanup_table; + } return ret; @@ -155,7 +136,7 @@ static int __init iptable_filter_init(void) static void __exit iptable_filter_fini(void) { - nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); + xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&iptable_filter_net_ops); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 4e699cd275c..2355a229f8e 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -69,6 +69,7 @@ static const struct xt_table packet_mangler = { .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, + .priority = NF_IP_PRI_MANGLE, }; static unsigned int @@ -129,43 +130,7 @@ iptable_mangle_hook(unsigned int hook, dev_net(in)->ipv4.iptable_mangle); } -static struct nf_hook_ops ipt_ops[] __read_mostly = { - { - .hook = iptable_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP_PRI_MANGLE, - }, - { - .hook = iptable_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_MANGLE, - }, - { - .hook = iptable_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP_PRI_MANGLE, - }, - { - .hook = iptable_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_MANGLE, - }, - { - .hook = iptable_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_MANGLE, - }, -}; +static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init iptable_mangle_net_init(struct net *net) { @@ -196,9 +161,11 @@ static int __init iptable_mangle_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); - if (ret < 0) + mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook); + if (IS_ERR(mangle_ops)) { + ret = PTR_ERR(mangle_ops); goto cleanup_table; + } return ret; @@ -209,7 +176,7 @@ static int __init iptable_mangle_init(void) static void __exit iptable_mangle_fini(void) { - nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); + xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&iptable_mangle_net_ops); } diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index d16e43777c3..62a99154f14 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -41,6 +41,7 @@ static const struct xt_table packet_raw = { .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, + .priority = NF_IP_PRI_RAW, }; /* The work comes in here from netfilter.c. */ @@ -61,23 +62,7 @@ iptable_raw_hook(unsigned int hook, struct sk_buff *skb, return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_raw); } -/* 'raw' is the very first table. */ -static struct nf_hook_ops ipt_ops[] __read_mostly = { - { - .hook = iptable_raw_hook, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP_PRI_RAW, - .owner = THIS_MODULE, - }, - { - .hook = iptable_raw_hook, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_RAW, - .owner = THIS_MODULE, - }, -}; +static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init iptable_raw_net_init(struct net *net) { @@ -108,9 +93,11 @@ static int __init iptable_raw_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); - if (ret < 0) + rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook); + if (IS_ERR(rawtable_ops)) { + ret = PTR_ERR(rawtable_ops); goto cleanup_table; + } return ret; @@ -121,7 +108,7 @@ static int __init iptable_raw_init(void) static void __exit iptable_raw_fini(void) { - nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); + xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&iptable_raw_net_ops); } diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 324505aaaa7..b1bf3ca2c6c 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -62,6 +62,7 @@ static const struct xt_table security_table = { .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, + .priority = NF_IP_PRI_SECURITY, }; static unsigned int @@ -82,29 +83,7 @@ iptable_security_hook(unsigned int hook, struct sk_buff *skb, return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_security); } -static struct nf_hook_ops ipt_ops[] __read_mostly = { - { - .hook = iptable_security_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_SECURITY, - }, - { - .hook = iptable_security_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP_PRI_SECURITY, - }, - { - .hook = iptable_security_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_SECURITY, - }, -}; +static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init iptable_security_net_init(struct net *net) { @@ -135,9 +114,11 @@ static int __init iptable_security_init(void) if (ret < 0) return ret; - ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); - if (ret < 0) + sectbl_ops = xt_hook_link(&security_table, iptable_security_hook); + if (IS_ERR(sectbl_ops)) { + ret = PTR_ERR(sectbl_ops); goto cleanup_table; + } return ret; @@ -148,7 +129,7 @@ cleanup_table: static void __exit iptable_security_fini(void) { - nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); + xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&iptable_security_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 866f34ae236..6e95d0614ca 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -56,6 +56,7 @@ static const struct xt_table packet_filter = { .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_FILTER, }; /* The work comes in here from netfilter.c. */ @@ -69,29 +70,7 @@ ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6table_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_FILTER, - }, - { - .hook = ip6table_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP6_PRI_FILTER, - }, - { - .hook = ip6table_filter_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_FILTER, - }, -}; +static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ static int forward = NF_ACCEPT; @@ -134,9 +113,11 @@ static int __init ip6table_filter_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook); + if (IS_ERR(filter_ops)) { + ret = PTR_ERR(filter_ops); goto cleanup_table; + } return ret; @@ -147,7 +128,7 @@ static int __init ip6table_filter_init(void) static void __exit ip6table_filter_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&packet_filter, filter_ops); unregister_pernet_subsys(&ip6table_filter_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 405ac1f7639..5023ac52ffe 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -62,6 +62,7 @@ static const struct xt_table packet_mangler = { .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_MANGLE, }; static unsigned int @@ -122,44 +123,7 @@ ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, dev_net(in)->ipv6.ip6table_mangle); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6table_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6table_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6table_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6table_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6table_mangle_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_MANGLE, - }, -}; - +static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init ip6table_mangle_net_init(struct net *net) { /* Register table */ @@ -189,9 +153,11 @@ static int __init ip6table_mangle_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook); + if (IS_ERR(mangle_ops)) { + ret = PTR_ERR(mangle_ops); goto cleanup_table; + } return ret; @@ -202,7 +168,7 @@ static int __init ip6table_mangle_init(void) static void __exit ip6table_mangle_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&packet_mangler, mangle_ops); unregister_pernet_subsys(&ip6table_mangle_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 5451a36fbc2..3bfa6951164 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -40,6 +40,7 @@ static const struct xt_table packet_raw = { .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_FIRST, }; /* The work comes in here from netfilter.c. */ @@ -53,22 +54,7 @@ ip6table_raw_hook(unsigned int hook, struct sk_buff *skb, return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6table_raw_hook, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_FIRST, - .owner = THIS_MODULE, - }, - { - .hook = ip6table_raw_hook, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_FIRST, - .owner = THIS_MODULE, - }, -}; +static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init ip6table_raw_net_init(struct net *net) { @@ -99,9 +85,11 @@ static int __init ip6table_raw_init(void) return ret; /* Register hooks */ - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook); + if (IS_ERR(rawtable_ops)) { + ret = PTR_ERR(rawtable_ops); goto cleanup_table; + } return ret; @@ -112,7 +100,7 @@ static int __init ip6table_raw_init(void) static void __exit ip6table_raw_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&packet_raw, rawtable_ops); unregister_pernet_subsys(&ip6table_raw_net_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 841ea77f521..dd2200f17a6 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -61,6 +61,7 @@ static const struct xt_table security_table = { .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_SECURITY, }; static unsigned int @@ -74,29 +75,7 @@ ip6table_security_hook(unsigned int hook, struct sk_buff *skb, return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security); } -static struct nf_hook_ops ip6t_ops[] __read_mostly = { - { - .hook = ip6table_security_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_SECURITY, - }, - { - .hook = ip6table_security_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_FORWARD, - .priority = NF_IP6_PRI_SECURITY, - }, - { - .hook = ip6table_security_hook, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_SECURITY, - }, -}; +static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init ip6table_security_net_init(struct net *net) { @@ -127,9 +106,11 @@ static int __init ip6table_security_init(void) if (ret < 0) return ret; - ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); - if (ret < 0) + sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook); + if (IS_ERR(sectbl_ops)) { + ret = PTR_ERR(sectbl_ops); goto cleanup_table; + } return ret; @@ -140,7 +121,7 @@ cleanup_table: static void __exit ip6table_security_fini(void) { - nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); + xt_hook_unlink(&security_table, sectbl_ops); unregister_pernet_subsys(&ip6table_security_net_ops); } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index f01955cce31..b51cb0d7234 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1091,6 +1091,60 @@ static const struct file_operations xt_target_ops = { #endif /* CONFIG_PROC_FS */ +/** + * xt_hook_link - set up hooks for a new table + * @table: table with metadata needed to set up hooks + * @fn: Hook function + * + * This function will take care of creating and registering the necessary + * Netfilter hooks for XT tables. + */ +struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn) +{ + unsigned int hook_mask = table->valid_hooks; + uint8_t i, num_hooks = hweight32(hook_mask); + uint8_t hooknum; + struct nf_hook_ops *ops; + int ret; + + ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0; + hook_mask >>= 1, ++hooknum) { + if (!(hook_mask & 1)) + continue; + ops[i].hook = fn; + ops[i].owner = table->me; + ops[i].pf = table->af; + ops[i].hooknum = hooknum; + ops[i].priority = table->priority; + ++i; + } + + ret = nf_register_hooks(ops, num_hooks); + if (ret < 0) { + kfree(ops); + return ERR_PTR(ret); + } + + return ops; +} +EXPORT_SYMBOL_GPL(xt_hook_link); + +/** + * xt_hook_unlink - remove hooks for a table + * @ops: nf_hook_ops array as returned by nf_hook_link + * @hook_mask: the very same mask that was passed to nf_hook_link + */ +void xt_hook_unlink(const struct xt_table *table, struct nf_hook_ops *ops) +{ + nf_unregister_hooks(ops, hweight32(table->valid_hooks)); + kfree(ops); +} +EXPORT_SYMBOL_GPL(xt_hook_unlink); + int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From e3eaa9910b380530cfd2c0670fcd3f627674da8a Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 17 Jun 2009 22:14:54 +0200 Subject: netfilter: xtables: generate initial table on-demand The static initial tables are pretty large, and after the net namespace has been instantiated, they just hang around for nothing. This commit removes them and creates tables on-demand at runtime when needed. Size shrinks by 7735 bytes (x86_64). Signed-off-by: Jan Engelhardt --- net/ipv4/netfilter/arp_tables.c | 7 ++++++ net/ipv4/netfilter/arptable_filter.c | 40 ++++++----------------------- net/ipv4/netfilter/ip_tables.c | 7 ++++++ net/ipv4/netfilter/iptable_filter.c | 46 ++++++++-------------------------- net/ipv4/netfilter/iptable_mangle.c | 46 ++++++---------------------------- net/ipv4/netfilter/iptable_raw.c | 36 ++++++-------------------- net/ipv4/netfilter/iptable_security.c | 39 ++++++---------------------- net/ipv4/netfilter/nf_nat_rule.c | 39 ++++++---------------------- net/ipv6/netfilter/ip6_tables.c | 7 ++++++ net/ipv6/netfilter/ip6table_filter.c | 46 ++++++++-------------------------- net/ipv6/netfilter/ip6table_mangle.c | 45 ++++++--------------------------- net/ipv6/netfilter/ip6table_raw.c | 36 ++++++-------------------- net/ipv6/netfilter/ip6table_security.c | 39 ++++++---------------------- net/netfilter/x_tables.c | 4 ++- net/netfilter/xt_repldata.h | 35 ++++++++++++++++++++++++++ 15 files changed, 138 insertions(+), 334 deletions(-) create mode 100644 net/netfilter/xt_repldata.h (limited to 'net') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 90203e1b918..72723ea1054 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -27,6 +27,7 @@ #include #include +#include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("David S. Miller "); @@ -58,6 +59,12 @@ do { \ #define ARP_NF_ASSERT(x) #endif +void *arpt_alloc_initial_table(const struct xt_table *info) +{ + return xt_alloc_initial_table(arpt, ARPT); +} +EXPORT_SYMBOL_GPL(arpt_alloc_initial_table); + static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, const char *hdr_addr, int len) { diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index b361de0dac4..bfe26f32b93 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -6,6 +6,7 @@ */ #include +#include #include MODULE_LICENSE("GPL"); @@ -15,36 +16,6 @@ MODULE_DESCRIPTION("arptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \ (1 << NF_ARP_FORWARD)) -static const struct -{ - struct arpt_replace repl; - struct arpt_standard entries[3]; - struct arpt_error term; -} initial_table __net_initdata = { - .repl = { - .name = "filter", - .valid_hooks = FILTER_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct arpt_standard) * 3 + sizeof(struct arpt_error), - .hook_entry = { - [NF_ARP_IN] = 0, - [NF_ARP_OUT] = sizeof(struct arpt_standard), - [NF_ARP_FORWARD] = 2 * sizeof(struct arpt_standard), - }, - .underflow = { - [NF_ARP_IN] = 0, - [NF_ARP_OUT] = sizeof(struct arpt_standard), - [NF_ARP_FORWARD] = 2 * sizeof(struct arpt_standard), - }, - }, - .entries = { - ARPT_STANDARD_INIT(NF_ACCEPT), /* ARP_IN */ - ARPT_STANDARD_INIT(NF_ACCEPT), /* ARP_OUT */ - ARPT_STANDARD_INIT(NF_ACCEPT), /* ARP_FORWARD */ - }, - .term = ARPT_ERROR_INIT, -}; - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, @@ -68,9 +39,14 @@ static struct nf_hook_ops *arpfilter_ops __read_mostly; static int __net_init arptable_filter_net_init(struct net *net) { - /* Register table */ + struct arpt_replace *repl; + + repl = arpt_alloc_initial_table(&packet_filter); + if (repl == NULL) + return -ENOMEM; net->ipv4.arptable_filter = - arpt_register_table(net, &packet_filter, &initial_table.repl); + arpt_register_table(net, &packet_filter, repl); + kfree(repl); if (IS_ERR(net->ipv4.arptable_filter)) return PTR_ERR(net->ipv4.arptable_filter); return 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 5bf7de1527a..2057b1bb617 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -28,6 +28,7 @@ #include #include #include +#include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team "); @@ -66,6 +67,12 @@ do { \ #define inline #endif +void *ipt_alloc_initial_table(const struct xt_table *info) +{ + return xt_alloc_initial_table(ipt, IPT); +} +EXPORT_SYMBOL_GPL(ipt_alloc_initial_table); + /* We keep a set of rules for each CPU, so we can avoid write-locking them in the softirq when updating the counters and therefore diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index c14bb85db1d..c8dc9800d62 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -23,36 +23,6 @@ MODULE_DESCRIPTION("iptables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static struct -{ - struct ipt_replace repl; - struct ipt_standard entries[3]; - struct ipt_error term; -} initial_table __net_initdata = { - .repl = { - .name = "filter", - .valid_hooks = FILTER_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error), - .hook_entry = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ipt_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2, - }, - .underflow = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ipt_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2, - }, - }, - .entries = { - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IPT_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, @@ -86,9 +56,18 @@ module_param(forward, bool, 0000); static int __net_init iptable_filter_net_init(struct net *net) { - /* Register table */ + struct ipt_replace *repl; + + repl = ipt_alloc_initial_table(&packet_filter); + if (repl == NULL) + return -ENOMEM; + /* Entry 1 is the FORWARD hook */ + ((struct ipt_standard *)repl->entries)[1].target.verdict = + -forward - 1; + net->ipv4.iptable_filter = - ipt_register_table(net, &packet_filter, &initial_table.repl); + ipt_register_table(net, &packet_filter, repl); + kfree(repl); if (IS_ERR(net->ipv4.iptable_filter)) return PTR_ERR(net->ipv4.iptable_filter); return 0; @@ -113,9 +92,6 @@ static int __init iptable_filter_init(void) return -EINVAL; } - /* Entry 1 is the FORWARD hook */ - initial_table.entries[1].target.verdict = -forward - 1; - ret = register_pernet_subsys(&iptable_filter_net_ops); if (ret < 0) return ret; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 2355a229f8e..58d7097baa3 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -27,43 +27,6 @@ MODULE_DESCRIPTION("iptables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -/* Ouch - five different hooks? Maybe this should be a config option..... -- BC */ -static const struct -{ - struct ipt_replace repl; - struct ipt_standard entries[5]; - struct ipt_error term; -} initial_table __net_initdata = { - .repl = { - .name = "mangle", - .valid_hooks = MANGLE_VALID_HOOKS, - .num_entries = 6, - .size = sizeof(struct ipt_standard) * 5 + sizeof(struct ipt_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_IN] = sizeof(struct ipt_standard), - [NF_INET_FORWARD] = sizeof(struct ipt_standard) * 2, - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 3, - [NF_INET_POST_ROUTING] = sizeof(struct ipt_standard) * 4, - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_IN] = sizeof(struct ipt_standard), - [NF_INET_FORWARD] = sizeof(struct ipt_standard) * 2, - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 3, - [NF_INET_POST_ROUTING] = sizeof(struct ipt_standard) * 4, - }, - }, - .entries = { - IPT_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - IPT_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */ - }, - .term = IPT_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, @@ -134,9 +97,14 @@ static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init iptable_mangle_net_init(struct net *net) { - /* Register table */ + struct ipt_replace *repl; + + repl = ipt_alloc_initial_table(&packet_mangler); + if (repl == NULL) + return -ENOMEM; net->ipv4.iptable_mangle = - ipt_register_table(net, &packet_mangler, &initial_table.repl); + ipt_register_table(net, &packet_mangler, repl); + kfree(repl); if (IS_ERR(net->ipv4.iptable_mangle)) return PTR_ERR(net->ipv4.iptable_mangle); return 0; diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 62a99154f14..06fb9d11953 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -9,33 +9,6 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static const struct -{ - struct ipt_replace repl; - struct ipt_standard entries[2]; - struct ipt_error term; -} initial_table __net_initdata = { - .repl = { - .name = "raw", - .valid_hooks = RAW_VALID_HOOKS, - .num_entries = 3, - .size = sizeof(struct ipt_standard) * 2 + sizeof(struct ipt_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) - }, - }, - .entries = { - IPT_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IPT_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, @@ -66,9 +39,14 @@ static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init iptable_raw_net_init(struct net *net) { - /* Register table */ + struct ipt_replace *repl; + + repl = ipt_alloc_initial_table(&packet_raw); + if (repl == NULL) + return -ENOMEM; net->ipv4.iptable_raw = - ipt_register_table(net, &packet_raw, &initial_table.repl); + ipt_register_table(net, &packet_raw, repl); + kfree(repl); if (IS_ERR(net->ipv4.iptable_raw)) return PTR_ERR(net->ipv4.iptable_raw); return 0; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index b1bf3ca2c6c..cce2f64e6f2 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -27,36 +27,6 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static const struct -{ - struct ipt_replace repl; - struct ipt_standard entries[3]; - struct ipt_error term; -} initial_table __net_initdata = { - .repl = { - .name = "security", - .valid_hooks = SECURITY_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error), - .hook_entry = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ipt_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2, - }, - .underflow = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ipt_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2, - }, - }, - .entries = { - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IPT_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, @@ -87,9 +57,14 @@ static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init iptable_security_net_init(struct net *net) { - net->ipv4.iptable_security = - ipt_register_table(net, &security_table, &initial_table.repl); + struct ipt_replace *repl; + repl = ipt_alloc_initial_table(&security_table); + if (repl == NULL) + return -ENOMEM; + net->ipv4.iptable_security = + ipt_register_table(net, &security_table, repl); + kfree(repl); if (IS_ERR(net->ipv4.iptable_security)) return PTR_ERR(net->ipv4.iptable_security); diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 85da34fdc75..ab74cc0535e 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -28,36 +28,6 @@ (1 << NF_INET_POST_ROUTING) | \ (1 << NF_INET_LOCAL_OUT)) -static const struct -{ - struct ipt_replace repl; - struct ipt_standard entries[3]; - struct ipt_error term; -} nat_initial_table __net_initdata = { - .repl = { - .name = "nat", - .valid_hooks = NAT_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_POST_ROUTING] = sizeof(struct ipt_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2 - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_POST_ROUTING] = sizeof(struct ipt_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2 - }, - }, - .entries = { - IPT_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IPT_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */ - IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IPT_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table nat_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, @@ -186,8 +156,13 @@ static struct xt_target ipt_dnat_reg __read_mostly = { static int __net_init nf_nat_rule_net_init(struct net *net) { - net->ipv4.nat_table = ipt_register_table(net, &nat_table, - &nat_initial_table.repl); + struct ipt_replace *repl; + + repl = ipt_alloc_initial_table(&nat_table); + if (repl == NULL) + return -ENOMEM; + net->ipv4.nat_table = ipt_register_table(net, &nat_table, repl); + kfree(repl); if (IS_ERR(net->ipv4.nat_table)) return PTR_ERR(net->ipv4.nat_table); return 0; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 4332f459148..dcd7825fe7b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -29,6 +29,7 @@ #include #include #include +#include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team "); @@ -67,6 +68,12 @@ do { \ #define inline #endif +void *ip6t_alloc_initial_table(const struct xt_table *info) +{ + return xt_alloc_initial_table(ip6t, IP6T); +} +EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); + /* We keep a set of rules for each CPU, so we can avoid write-locking them in the softirq when updating the counters and therefore diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 6e95d0614ca..36b72cafc22 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -21,36 +21,6 @@ MODULE_DESCRIPTION("ip6tables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[3]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "filter", - .valid_hooks = FILTER_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 - }, - .underflow = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, @@ -78,9 +48,18 @@ module_param(forward, bool, 0000); static int __net_init ip6table_filter_net_init(struct net *net) { - /* Register table */ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_filter); + if (repl == NULL) + return -ENOMEM; + /* Entry 1 is the FORWARD hook */ + ((struct ip6t_standard *)repl->entries)[1].target.verdict = + -forward - 1; + net->ipv6.ip6table_filter = - ip6t_register_table(net, &packet_filter, &initial_table.repl); + ip6t_register_table(net, &packet_filter, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_filter)) return PTR_ERR(net->ipv6.ip6table_filter); return 0; @@ -105,9 +84,6 @@ static int __init ip6table_filter_init(void) return -EINVAL; } - /* Entry 1 is the FORWARD hook */ - initial_table.entries[1].target.verdict = -forward - 1; - ret = register_pernet_subsys(&ip6table_filter_net_ops); if (ret < 0) return ret; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 5023ac52ffe..dc803b7e8e5 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -21,42 +21,6 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static const struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[5]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "mangle", - .valid_hooks = MANGLE_VALID_HOOKS, - .num_entries = 6, - .size = sizeof(struct ip6t_standard) * 5 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_IN] = sizeof(struct ip6t_standard), - [NF_INET_FORWARD] = sizeof(struct ip6t_standard) * 2, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3, - [NF_INET_POST_ROUTING] = sizeof(struct ip6t_standard) * 4, - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_IN] = sizeof(struct ip6t_standard), - [NF_INET_FORWARD] = sizeof(struct ip6t_standard) * 2, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3, - [NF_INET_POST_ROUTING] = sizeof(struct ip6t_standard) * 4, - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, @@ -126,9 +90,14 @@ ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, static struct nf_hook_ops *mangle_ops __read_mostly; static int __net_init ip6table_mangle_net_init(struct net *net) { - /* Register table */ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_mangler); + if (repl == NULL) + return -ENOMEM; net->ipv6.ip6table_mangle = - ip6t_register_table(net, &packet_mangler, &initial_table.repl); + ip6t_register_table(net, &packet_mangler, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_mangle)) return PTR_ERR(net->ipv6.ip6table_mangle); return 0; diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 3bfa6951164..aef31a29de9 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -8,33 +8,6 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static const struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[2]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "raw", - .valid_hooks = RAW_VALID_HOOKS, - .num_entries = 3, - .size = sizeof(struct ip6t_standard) * 2 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) - }, - .underflow = { - [NF_INET_PRE_ROUTING] = 0, - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, @@ -58,9 +31,14 @@ static struct nf_hook_ops *rawtable_ops __read_mostly; static int __net_init ip6table_raw_net_init(struct net *net) { - /* Register table */ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_raw); + if (repl == NULL) + return -ENOMEM; net->ipv6.ip6table_raw = - ip6t_register_table(net, &packet_raw, &initial_table.repl); + ip6t_register_table(net, &packet_raw, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_raw)) return PTR_ERR(net->ipv6.ip6table_raw); return 0; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index dd2200f17a6..0824d865aa9 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -26,36 +26,6 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static const struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[3]; - struct ip6t_error term; -} initial_table __net_initdata = { - .repl = { - .name = "security", - .valid_hooks = SECURITY_VALID_HOOKS, - .num_entries = 4, - .size = sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2, - }, - .underflow = { - [NF_INET_LOCAL_IN] = 0, - [NF_INET_FORWARD] = sizeof(struct ip6t_standard), - [NF_INET_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2, - }, - }, - .entries = { - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* FORWARD */ - IP6T_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */ - }, - .term = IP6T_ERROR_INIT, /* ERROR */ -}; - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, @@ -79,9 +49,14 @@ static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init ip6table_security_net_init(struct net *net) { - net->ipv6.ip6table_security = - ip6t_register_table(net, &security_table, &initial_table.repl); + struct ip6t_replace *repl; + repl = ip6t_alloc_initial_table(&security_table); + if (repl == NULL) + return -ENOMEM; + net->ipv6.ip6table_security = + ip6t_register_table(net, &security_table, repl); + kfree(repl); if (IS_ERR(net->ipv6.ip6table_security)) return PTR_ERR(net->ipv6.ip6table_security); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index b51cb0d7234..dc2e05cb54c 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -26,7 +26,9 @@ #include #include - +#include +#include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte "); diff --git a/net/netfilter/xt_repldata.h b/net/netfilter/xt_repldata.h new file mode 100644 index 00000000000..6efe4e5a81c --- /dev/null +++ b/net/netfilter/xt_repldata.h @@ -0,0 +1,35 @@ +/* + * Today's hack: quantum tunneling in structs + * + * 'entries' and 'term' are never anywhere referenced by word in code. In fact, + * they serve as the hanging-off data accessed through repl.data[]. + */ + +#define xt_alloc_initial_table(type, typ2) ({ \ + unsigned int hook_mask = info->valid_hooks; \ + unsigned int nhooks = hweight32(hook_mask); \ + unsigned int bytes = 0, hooknum = 0, i = 0; \ + struct { \ + struct type##_replace repl; \ + struct type##_standard entries[nhooks]; \ + struct type##_error term; \ + } *tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); \ + if (tbl == NULL) \ + return NULL; \ + strncpy(tbl->repl.name, info->name, sizeof(tbl->repl.name)); \ + tbl->term = (struct type##_error)typ2##_ERROR_INIT; \ + tbl->repl.valid_hooks = hook_mask; \ + tbl->repl.num_entries = nhooks + 1; \ + tbl->repl.size = nhooks * sizeof(struct type##_standard) + \ + sizeof(struct type##_error); \ + for (; hook_mask != 0; hook_mask >>= 1, ++hooknum) { \ + if (!(hook_mask & 1)) \ + continue; \ + tbl->repl.hook_entry[hooknum] = bytes; \ + tbl->repl.underflow[hooknum] = bytes; \ + tbl->entries[i++] = (struct type##_standard) \ + typ2##_STANDARD_INIT(NF_ACCEPT); \ + bytes += sizeof(struct type##_standard); \ + } \ + tbl; \ +}) -- cgit v1.2.3 From d1e7a03f4fee4059ee3fa7ce0edb7c48c1a75fcf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:22:28 +0100 Subject: netfilter: ctnetlink: dump expectation helper name Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 5c103b8c7df..db35edac307 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1512,6 +1512,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; + struct nf_conntrack_helper *helper; long timeout = (exp->timeout.expires - jiffies) / HZ; if (timeout < 0) @@ -1528,6 +1529,9 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, NLA_PUT_BE32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)); NLA_PUT_BE32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)); + helper = rcu_dereference(nfct_help(master)->helper); + if (helper) + NLA_PUT_STRING(skb, CTA_EXPECT_HELP_NAME, helper->name); return 0; -- cgit v1.2.3 From b87921bdf25485afd8f5a5f25e86b5acef32a9cf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:22:48 +0100 Subject: netfilter: nf_conntrack: show helper and class in /proc/net/nf_conntrack_expect Make the output a bit more informative by showing the helper an expectation belongs to and the expectation class. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_expect.c | 9 +++++++++ net/netfilter/nf_conntrack_sip.c | 3 +++ 2 files changed, 12 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 2f25ff61098..33b85f834c0 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -500,6 +500,7 @@ static void exp_seq_stop(struct seq_file *seq, void *v) static int exp_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_expect *expect; + struct nf_conntrack_helper *helper; struct hlist_node *n = v; char *delim = ""; @@ -525,6 +526,14 @@ static int exp_seq_show(struct seq_file *s, void *v) if (expect->flags & NF_CT_EXPECT_INACTIVE) seq_printf(s, "%sINACTIVE", delim); + helper = rcu_dereference(nfct_help(expect->master)->helper); + if (helper) { + seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); + if (helper->expect_policy[expect->class].name) + seq_printf(s, "/%s", + helper->expect_policy[expect->class].name); + } + return seq_putc(s, '\n'); } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 023966b569b..419c5cabb33 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1305,14 +1305,17 @@ static char sip_names[MAX_PORTS][2][sizeof("sip-65535")] __read_mostly; static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = { [SIP_EXPECT_SIGNALLING] = { + .name = "signalling", .max_expected = 1, .timeout = 3 * 60, }, [SIP_EXPECT_AUDIO] = { + .name = "audio", .max_expected = 2 * IP_CT_DIR_MAX, .timeout = 3 * 60, }, [SIP_EXPECT_VIDEO] = { + .name = "video", .max_expected = 2 * IP_CT_DIR_MAX, .timeout = 3 * 60, }, -- cgit v1.2.3 From 54101f4f3bed87fa968b57f77f8ff3b09fd88bcf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:23:12 +0100 Subject: netfilter: nf_conntrack_sip: fix ct_sip_parse_request() REGISTER request parsing When requests are parsed, the "sip:" part of the SIP URI should be skipped. Usually this doesn't matter because address parsing skips forward until after the username part, but in case REGISTER requests it doesn't contain a username and the address can not be parsed. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_sip.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 419c5cabb33..0ca2f2b5c2f 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -236,12 +236,13 @@ int ct_sip_parse_request(const struct nf_conn *ct, return 0; /* Find SIP URI */ - limit -= strlen("sip:"); - for (; dptr < limit; dptr++) { + for (; dptr < limit - strlen("sip:"); dptr++) { if (*dptr == '\r' || *dptr == '\n') return -1; - if (strnicmp(dptr, "sip:", strlen("sip:")) == 0) + if (strnicmp(dptr, "sip:", strlen("sip:")) == 0) { + dptr += strlen("sip:"); break; + } } if (!skp_epaddr_len(ct, dptr, limit, &shift)) return 0; -- cgit v1.2.3 From 3b6b9fab42fe98358d70735cf98d43fc18dc79c9 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:23:53 +0100 Subject: netfilter: nf_conntrack_sip: pass data offset to NAT functions When using TCP multiple SIP messages might be present in a single packet. A following patch will parse them by setting the dptr to the beginning of each message. The NAT helper needs to reload the dptr value after mangling the packet however, so it needs to know the offset of the message to the beginning of the packet. Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_sip.c | 101 ++++++++++++++++++++------------------- net/netfilter/nf_conntrack_sip.c | 82 ++++++++++++++++--------------- 2 files changed, 95 insertions(+), 88 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 07d61a57613..2454ea5abb7 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -29,7 +29,7 @@ MODULE_DESCRIPTION("SIP NAT helper"); MODULE_ALIAS("ip_nat_sip"); -static unsigned int mangle_packet(struct sk_buff *skb, +static unsigned int mangle_packet(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, const char *buffer, unsigned int buflen) @@ -42,12 +42,12 @@ static unsigned int mangle_packet(struct sk_buff *skb, return 0; /* Reload data pointer and adjust datalen value */ - *dptr = skb->data + ip_hdrlen(skb) + sizeof(struct udphdr); + *dptr = skb->data + dataoff; *datalen += buflen - matchlen; return 1; } -static int map_addr(struct sk_buff *skb, +static int map_addr(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, union nf_inet_addr *addr, __be16 port) @@ -76,11 +76,11 @@ static int map_addr(struct sk_buff *skb, buflen = sprintf(buffer, "%pI4:%u", &newaddr, ntohs(newport)); - return mangle_packet(skb, dptr, datalen, matchoff, matchlen, + return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen); } -static int map_sip_addr(struct sk_buff *skb, +static int map_sip_addr(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, enum sip_header_types type) { @@ -93,16 +93,17 @@ static int map_sip_addr(struct sk_buff *skb, if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, type, NULL, &matchoff, &matchlen, &addr, &port) <= 0) return 1; - return map_addr(skb, dptr, datalen, matchoff, matchlen, &addr, port); + return map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, + &addr, port); } -static unsigned int ip_nat_sip(struct sk_buff *skb, +static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - unsigned int dataoff, matchoff, matchlen; + unsigned int coff, matchoff, matchlen; union nf_inet_addr addr; __be16 port; int request, in_header; @@ -112,7 +113,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, if (ct_sip_parse_request(ct, *dptr, *datalen, &matchoff, &matchlen, &addr, &port) > 0 && - !map_addr(skb, dptr, datalen, matchoff, matchlen, + !map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, &addr, port)) return NF_DROP; request = 1; @@ -138,7 +139,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, goto next; } - if (!map_addr(skb, dptr, datalen, matchoff, matchlen, + if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, &addr, port)) return NF_DROP; @@ -153,8 +154,8 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) { buflen = sprintf(buffer, "%pI4", &ct->tuplehash[!dir].tuple.dst.u3.ip); - if (!mangle_packet(skb, dptr, datalen, poff, plen, - buffer, buflen)) + if (!mangle_packet(skb, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) return NF_DROP; } @@ -167,8 +168,8 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { buflen = sprintf(buffer, "%pI4", &ct->tuplehash[!dir].tuple.src.u3.ip); - if (!mangle_packet(skb, dptr, datalen, poff, plen, - buffer, buflen)) + if (!mangle_packet(skb, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) return NF_DROP; } @@ -181,27 +182,27 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; buflen = sprintf(buffer, "%u", ntohs(p)); - if (!mangle_packet(skb, dptr, datalen, poff, plen, - buffer, buflen)) + if (!mangle_packet(skb, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) return NF_DROP; } } next: /* Translate Contact headers */ - dataoff = 0; + coff = 0; in_header = 0; - while (ct_sip_parse_header_uri(ct, *dptr, &dataoff, *datalen, + while (ct_sip_parse_header_uri(ct, *dptr, &coff, *datalen, SIP_HDR_CONTACT, &in_header, &matchoff, &matchlen, &addr, &port) > 0) { - if (!map_addr(skb, dptr, datalen, matchoff, matchlen, + if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, &addr, port)) return NF_DROP; } - if (!map_sip_addr(skb, dptr, datalen, SIP_HDR_FROM) || - !map_sip_addr(skb, dptr, datalen, SIP_HDR_TO)) + if (!map_sip_addr(skb, dataoff, dptr, datalen, SIP_HDR_FROM) || + !map_sip_addr(skb, dataoff, dptr, datalen, SIP_HDR_TO)) return NF_DROP; return NF_ACCEPT; } @@ -232,7 +233,7 @@ static void ip_nat_sip_expected(struct nf_conn *ct, } } -static unsigned int ip_nat_sip_expect(struct sk_buff *skb, +static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *exp, unsigned int matchoff, @@ -279,8 +280,8 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, if (exp->tuple.dst.u3.ip != exp->saved_ip || exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { buflen = sprintf(buffer, "%pI4:%u", &newip, port); - if (!mangle_packet(skb, dptr, datalen, matchoff, matchlen, - buffer, buflen)) + if (!mangle_packet(skb, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen)) goto err; } return NF_ACCEPT; @@ -290,7 +291,7 @@ err: return NF_DROP; } -static int mangle_content_len(struct sk_buff *skb, +static int mangle_content_len(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -312,12 +313,13 @@ static int mangle_content_len(struct sk_buff *skb, return 0; buflen = sprintf(buffer, "%u", c_len); - return mangle_packet(skb, dptr, datalen, matchoff, matchlen, + return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen); } -static int mangle_sdp_packet(struct sk_buff *skb, const char **dptr, - unsigned int dataoff, unsigned int *datalen, +static int mangle_sdp_packet(struct sk_buff *skb, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, enum sdp_header_types type, enum sdp_header_types term, char *buffer, int buflen) @@ -326,16 +328,16 @@ static int mangle_sdp_packet(struct sk_buff *skb, const char **dptr, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); unsigned int matchlen, matchoff; - if (ct_sip_get_sdp_header(ct, *dptr, dataoff, *datalen, type, term, + if (ct_sip_get_sdp_header(ct, *dptr, sdpoff, *datalen, type, term, &matchoff, &matchlen) <= 0) return -ENOENT; - return mangle_packet(skb, dptr, datalen, matchoff, matchlen, + return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen) ? 0 : -EINVAL; } -static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, const char **dptr, - unsigned int dataoff, - unsigned int *datalen, +static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, enum sdp_header_types type, enum sdp_header_types term, const union nf_inet_addr *addr) @@ -344,16 +346,15 @@ static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, const char **dptr, unsigned int buflen; buflen = sprintf(buffer, "%pI4", &addr->ip); - if (mangle_sdp_packet(skb, dptr, dataoff, datalen, type, term, + if (mangle_sdp_packet(skb, dataoff, dptr, datalen, sdpoff, type, term, buffer, buflen)) return 0; - return mangle_content_len(skb, dptr, datalen); + return mangle_content_len(skb, dataoff, dptr, datalen); } -static unsigned int ip_nat_sdp_port(struct sk_buff *skb, - const char **dptr, - unsigned int *datalen, +static unsigned int ip_nat_sdp_port(struct sk_buff *skb, unsigned int dataoff, + const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, u_int16_t port) @@ -362,16 +363,16 @@ static unsigned int ip_nat_sdp_port(struct sk_buff *skb, unsigned int buflen; buflen = sprintf(buffer, "%u", port); - if (!mangle_packet(skb, dptr, datalen, matchoff, matchlen, + if (!mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen)) return 0; - return mangle_content_len(skb, dptr, datalen); + return mangle_content_len(skb, dataoff, dptr, datalen); } -static unsigned int ip_nat_sdp_session(struct sk_buff *skb, const char **dptr, - unsigned int dataoff, - unsigned int *datalen, +static unsigned int ip_nat_sdp_session(struct sk_buff *skb, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, const union nf_inet_addr *addr) { char buffer[sizeof("nnn.nnn.nnn.nnn")]; @@ -379,12 +380,12 @@ static unsigned int ip_nat_sdp_session(struct sk_buff *skb, const char **dptr, /* Mangle session description owner and contact addresses */ buflen = sprintf(buffer, "%pI4", &addr->ip); - if (mangle_sdp_packet(skb, dptr, dataoff, datalen, + if (mangle_sdp_packet(skb, dataoff, dptr, datalen, sdpoff, SDP_HDR_OWNER_IP4, SDP_HDR_MEDIA, buffer, buflen)) return 0; - switch (mangle_sdp_packet(skb, dptr, dataoff, datalen, + switch (mangle_sdp_packet(skb, dataoff, dptr, datalen, sdpoff, SDP_HDR_CONNECTION_IP4, SDP_HDR_MEDIA, buffer, buflen)) { case 0: @@ -401,14 +402,13 @@ static unsigned int ip_nat_sdp_session(struct sk_buff *skb, const char **dptr, return 0; } - return mangle_content_len(skb, dptr, datalen); + return mangle_content_len(skb, dataoff, dptr, datalen); } /* 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_media(struct sk_buff *skb, - const char **dptr, - unsigned int *datalen, +static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff, + const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp, unsigned int mediaoff, @@ -456,7 +456,8 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, /* Update media port. */ if (rtp_exp->tuple.dst.u.udp.port != rtp_exp->saved_proto.udp.port && - !ip_nat_sdp_port(skb, dptr, datalen, mediaoff, medialen, port)) + !ip_nat_sdp_port(skb, dataoff, dptr, datalen, + mediaoff, medialen, port)) goto err2; return NF_ACCEPT; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 0ca2f2b5c2f..0ec37d6a2df 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -50,12 +50,13 @@ module_param(sip_direct_media, int, 0600); MODULE_PARM_DESC(sip_direct_media, "Expect Media streams between signalling " "endpoints only (default 1)"); -unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, +unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_hook); unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *exp, @@ -63,17 +64,17 @@ unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int matchlen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_expect_hook); -unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, +unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, - unsigned int dataoff, unsigned int *datalen, + unsigned int sdpoff, enum sdp_header_types type, enum sdp_header_types term, const union nf_inet_addr *addr) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sdp_addr_hook); -unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, +unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, @@ -82,14 +83,15 @@ unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_sdp_port_hook); unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, - const char **dptr, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, const union nf_inet_addr *addr) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sdp_session_hook); -unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, +unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *rtp_exp, @@ -729,7 +731,7 @@ static void flush_expectations(struct nf_conn *ct, bool media) spin_unlock_bh(&nf_conntrack_lock); } -static int set_expected_rtp_rtcp(struct sk_buff *skb, +static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, union nf_inet_addr *daddr, __be16 port, enum sip_expectation_classes class, @@ -806,7 +808,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, if (direct_rtp) { nf_nat_sdp_port = rcu_dereference(nf_nat_sdp_port_hook); if (nf_nat_sdp_port && - !nf_nat_sdp_port(skb, dptr, datalen, + !nf_nat_sdp_port(skb, dataoff, dptr, datalen, mediaoff, medialen, ntohs(rtp_port))) goto err1; } @@ -828,7 +830,8 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, nf_nat_sdp_media = rcu_dereference(nf_nat_sdp_media_hook); if (nf_nat_sdp_media && ct->status & IPS_NAT_MASK && !direct_rtp) - ret = nf_nat_sdp_media(skb, dptr, datalen, rtp_exp, rtcp_exp, + ret = nf_nat_sdp_media(skb, dataoff, dptr, datalen, + rtp_exp, rtcp_exp, mediaoff, medialen, daddr); else { if (nf_ct_expect_related(rtp_exp) == 0) { @@ -867,7 +870,7 @@ static const struct sdp_media_type *sdp_media_type(const char *dptr, return NULL; } -static int process_sdp(struct sk_buff *skb, +static int process_sdp(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -942,7 +945,7 @@ static int process_sdp(struct sk_buff *skb, else return NF_DROP; - ret = set_expected_rtp_rtcp(skb, dptr, datalen, + ret = set_expected_rtp_rtcp(skb, dataoff, dptr, datalen, &rtp_addr, htons(port), t->class, mediaoff, medialen); if (ret != NF_ACCEPT) @@ -950,8 +953,9 @@ static int process_sdp(struct sk_buff *skb, /* Update media connection address if present */ if (maddr_len && nf_nat_sdp_addr && ct->status & IPS_NAT_MASK) { - ret = nf_nat_sdp_addr(skb, dptr, mediaoff, datalen, - c_hdr, SDP_HDR_MEDIA, &rtp_addr); + ret = nf_nat_sdp_addr(skb, dataoff, dptr, datalen, + mediaoff, c_hdr, SDP_HDR_MEDIA, + &rtp_addr); if (ret != NF_ACCEPT) return ret; } @@ -961,14 +965,15 @@ static int process_sdp(struct sk_buff *skb, /* Update session connection and owner addresses */ nf_nat_sdp_session = rcu_dereference(nf_nat_sdp_session_hook); if (nf_nat_sdp_session && ct->status & IPS_NAT_MASK) - ret = nf_nat_sdp_session(skb, dptr, sdpoff, datalen, &rtp_addr); + ret = nf_nat_sdp_session(skb, dataoff, dptr, datalen, sdpoff, + &rtp_addr); if (ret == NF_ACCEPT && i > 0) help->help.ct_sip_info.invite_cseq = cseq; return ret; } -static int process_invite_response(struct sk_buff *skb, +static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -978,13 +983,13 @@ static int process_invite_response(struct sk_buff *skb, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dptr, datalen, cseq); + return process_sdp(skb, dataoff, dptr, datalen, cseq); else if (help->help.ct_sip_info.invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_update_response(struct sk_buff *skb, +static int process_update_response(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -994,13 +999,13 @@ static int process_update_response(struct sk_buff *skb, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dptr, datalen, cseq); + return process_sdp(skb, dataoff, dptr, datalen, cseq); else if (help->help.ct_sip_info.invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_prack_response(struct sk_buff *skb, +static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1010,13 +1015,13 @@ static int process_prack_response(struct sk_buff *skb, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dptr, datalen, cseq); + return process_sdp(skb, dataoff, dptr, datalen, cseq); else if (help->help.ct_sip_info.invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_bye_request(struct sk_buff *skb, +static int process_bye_request(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1031,7 +1036,7 @@ static int process_bye_request(struct sk_buff *skb, * signalling connections. The expectation is marked inactive and is activated * when receiving a response indicating success from the registrar. */ -static int process_register_request(struct sk_buff *skb, +static int process_register_request(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1101,7 +1106,7 @@ static int process_register_request(struct sk_buff *skb, nf_nat_sip_expect = rcu_dereference(nf_nat_sip_expect_hook); if (nf_nat_sip_expect && ct->status & IPS_NAT_MASK) - ret = nf_nat_sip_expect(skb, dptr, datalen, exp, + ret = nf_nat_sip_expect(skb, dataoff, dptr, datalen, exp, matchoff, matchlen); else { if (nf_ct_expect_related(exp) != 0) @@ -1117,7 +1122,7 @@ store_cseq: return ret; } -static int process_register_response(struct sk_buff *skb, +static int process_register_response(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1127,7 +1132,7 @@ static int process_register_response(struct sk_buff *skb, enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); union nf_inet_addr addr; __be16 port; - unsigned int matchoff, matchlen, dataoff = 0; + unsigned int matchoff, matchlen, coff = 0; unsigned int expires = 0; int in_contact = 0, ret; @@ -1154,7 +1159,7 @@ static int process_register_response(struct sk_buff *skb, while (1) { unsigned int c_expires = expires; - ret = ct_sip_parse_header_uri(ct, *dptr, &dataoff, *datalen, + ret = ct_sip_parse_header_uri(ct, *dptr, &coff, *datalen, SIP_HDR_CONTACT, &in_contact, &matchoff, &matchlen, &addr, &port); @@ -1193,13 +1198,13 @@ static const struct sip_handler sip_handlers[] = { SIP_HANDLER("REGISTER", process_register_request, process_register_response), }; -static int process_sip_response(struct sk_buff *skb, +static int process_sip_response(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - unsigned int matchoff, matchlen; - unsigned int code, cseq, dataoff, i; + unsigned int matchoff, matchlen, matchend; + unsigned int code, cseq, i; if (*datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; @@ -1213,7 +1218,7 @@ static int process_sip_response(struct sk_buff *skb, cseq = simple_strtoul(*dptr + matchoff, NULL, 10); if (!cseq) return NF_DROP; - dataoff = matchoff + matchlen + 1; + matchend = matchoff + matchlen + 1; for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { const struct sip_handler *handler; @@ -1221,15 +1226,16 @@ static int process_sip_response(struct sk_buff *skb, handler = &sip_handlers[i]; if (handler->response == NULL) continue; - if (*datalen < dataoff + handler->len || - strnicmp(*dptr + dataoff, handler->method, handler->len)) + if (*datalen < matchend + handler->len || + strnicmp(*dptr + matchend, handler->method, handler->len)) continue; - return handler->response(skb, dptr, datalen, cseq, code); + return handler->response(skb, dataoff, dptr, datalen, + cseq, code); } return NF_ACCEPT; } -static int process_sip_request(struct sk_buff *skb, +static int process_sip_request(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -1254,7 +1260,7 @@ static int process_sip_request(struct sk_buff *skb, if (!cseq) return NF_DROP; - return handler->request(skb, dptr, datalen, cseq); + return handler->request(skb, dataoff, dptr, datalen, cseq); } return NF_ACCEPT; } @@ -1288,13 +1294,13 @@ static int sip_help(struct sk_buff *skb, return NF_ACCEPT; if (strnicmp(dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0) - ret = process_sip_request(skb, &dptr, &datalen); + ret = process_sip_request(skb, dataoff, &dptr, &datalen); else - ret = process_sip_response(skb, &dptr, &datalen); + ret = process_sip_response(skb, dataoff, &dptr, &datalen); if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { nf_nat_sip = rcu_dereference(nf_nat_sip_hook); - if (nf_nat_sip && !nf_nat_sip(skb, &dptr, &datalen)) + if (nf_nat_sip && !nf_nat_sip(skb, dataoff, &dptr, &datalen)) ret = NF_DROP; } -- cgit v1.2.3 From f5b321bd37fbec9188feb1f721ab46a5ac0b35da Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:26:19 +0100 Subject: netfilter: nf_conntrack_sip: add TCP support Add TCP support, which is mandated by RFC3261 for all SIP elements. SIP over TCP is similar to UDP, except that messages are delimited by Content-Length: headers and multiple messages may appear in one packet. Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_sip.c | 2 +- net/netfilter/nf_conntrack_sip.c | 205 +++++++++++++++++++++++++++++++++------ 2 files changed, 177 insertions(+), 30 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 2454ea5abb7..b232e4040dc 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -122,7 +122,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, /* Translate topmost Via header and parameters */ if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, - SIP_HDR_VIA, NULL, &matchoff, &matchlen, + SIP_HDR_VIA_UDP, NULL, &matchoff, &matchlen, &addr, &port) > 0) { unsigned int matchend, poff, plen, buflen, n; char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 0ec37d6a2df..1cc75c5a822 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -287,7 +288,8 @@ static const struct sip_header ct_sip_hdrs[] = { [SIP_HDR_FROM] = SIP_HDR("From", "f", "sip:", skp_epaddr_len), [SIP_HDR_TO] = SIP_HDR("To", "t", "sip:", skp_epaddr_len), [SIP_HDR_CONTACT] = SIP_HDR("Contact", "m", "sip:", skp_epaddr_len), - [SIP_HDR_VIA] = SIP_HDR("Via", "v", "UDP ", epaddr_len), + [SIP_HDR_VIA_UDP] = SIP_HDR("Via", "v", "UDP ", epaddr_len), + [SIP_HDR_VIA_TCP] = SIP_HDR("Via", "v", "TCP ", epaddr_len), [SIP_HDR_EXPIRES] = SIP_HDR("Expires", NULL, NULL, digits_len), [SIP_HDR_CONTENT_LENGTH] = SIP_HDR("Content-Length", "l", NULL, digits_len), }; @@ -519,6 +521,33 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr, } EXPORT_SYMBOL_GPL(ct_sip_parse_header_uri); +static int ct_sip_parse_param(const struct nf_conn *ct, const char *dptr, + unsigned int dataoff, unsigned int datalen, + const char *name, + unsigned int *matchoff, unsigned int *matchlen) +{ + const char *limit = dptr + datalen; + const char *start; + const char *end; + + limit = ct_sip_header_search(dptr + dataoff, limit, ",", strlen(",")); + if (!limit) + limit = dptr + datalen; + + start = ct_sip_header_search(dptr + dataoff, limit, name, strlen(name)); + if (!start) + return 0; + start += strlen(name); + + end = ct_sip_header_search(start, limit, ";", strlen(";")); + if (!end) + end = limit; + + *matchoff = start - dptr; + *matchlen = end - start; + return 1; +} + /* Parse address from header parameter and return address, offset and length */ int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr, unsigned int dataoff, unsigned int datalen, @@ -577,6 +606,29 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, } EXPORT_SYMBOL_GPL(ct_sip_parse_numerical_param); +static int ct_sip_parse_transport(struct nf_conn *ct, const char *dptr, + unsigned int dataoff, unsigned int datalen, + u8 *proto) +{ + unsigned int matchoff, matchlen; + + if (ct_sip_parse_param(ct, dptr, dataoff, datalen, "transport=", + &matchoff, &matchlen)) { + if (!strnicmp(dptr + matchoff, "TCP", strlen("TCP"))) + *proto = IPPROTO_TCP; + else if (!strnicmp(dptr + matchoff, "UDP", strlen("UDP"))) + *proto = IPPROTO_UDP; + else + return 0; + + if (*proto != nf_ct_protonum(ct)) + return 0; + } else + *proto = nf_ct_protonum(ct); + + return 1; +} + /* SDP header parsing: a SDP session description contains an ordered set of * headers, starting with a section containing general session parameters, * optionally followed by multiple media descriptions. @@ -685,7 +737,7 @@ static int ct_sip_parse_sdp_addr(const struct nf_conn *ct, const char *dptr, static int refresh_signalling_expectation(struct nf_conn *ct, union nf_inet_addr *addr, - __be16 port, + u8 proto, __be16 port, unsigned int expires) { struct nf_conn_help *help = nfct_help(ct); @@ -697,6 +749,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct, hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { if (exp->class != SIP_EXPECT_SIGNALLING || !nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) || + exp->tuple.dst.protonum != proto || exp->tuple.dst.u.udp.port != port) continue; if (!del_timer(&exp->timeout)) @@ -1048,6 +1101,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_expect *exp; union nf_inet_addr *saddr, daddr; __be16 port; + u8 proto; unsigned int expires = 0; int ret; typeof(nf_nat_sip_expect_hook) nf_nat_sip_expect; @@ -1080,6 +1134,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &daddr)) return NF_ACCEPT; + if (ct_sip_parse_transport(ct, *dptr, matchoff + matchlen, *datalen, + &proto) == 0) + return NF_ACCEPT; + if (ct_sip_parse_numerical_param(ct, *dptr, matchoff + matchlen, *datalen, "expires=", NULL, NULL, &expires) < 0) @@ -1099,7 +1157,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, saddr = &ct->tuplehash[!dir].tuple.src.u3; nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), - saddr, &daddr, IPPROTO_UDP, NULL, &port); + saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; exp->helper = nfct_help(ct)->helper; exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; @@ -1132,6 +1190,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); union nf_inet_addr addr; __be16 port; + u8 proto; unsigned int matchoff, matchlen, coff = 0; unsigned int expires = 0; int in_contact = 0, ret; @@ -1172,6 +1231,10 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &addr)) continue; + if (ct_sip_parse_transport(ct, *dptr, matchoff + matchlen, + *datalen, &proto) == 0) + continue; + ret = ct_sip_parse_numerical_param(ct, *dptr, matchoff + matchlen, *datalen, "expires=", @@ -1180,7 +1243,8 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, return NF_DROP; if (c_expires == 0) break; - if (refresh_signalling_expectation(ct, &addr, port, c_expires)) + if (refresh_signalling_expectation(ct, &addr, proto, port, + c_expires)) return NF_ACCEPT; } @@ -1265,50 +1329,123 @@ static int process_sip_request(struct sk_buff *skb, unsigned int dataoff, return NF_ACCEPT; } -static int sip_help(struct sk_buff *skb, - unsigned int protoff, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) +static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct, + unsigned int dataoff, const char **dptr, + unsigned int *datalen) +{ + typeof(nf_nat_sip_hook) nf_nat_sip; + int ret; + + if (strnicmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0) + ret = process_sip_request(skb, dataoff, dptr, datalen); + else + ret = process_sip_response(skb, dataoff, dptr, datalen); + + if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { + nf_nat_sip = rcu_dereference(nf_nat_sip_hook); + if (nf_nat_sip && !nf_nat_sip(skb, dataoff, dptr, datalen)) + ret = NF_DROP; + } + + return ret; +} + +static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) { + struct tcphdr *th, _tcph; unsigned int dataoff, datalen; - const char *dptr; + unsigned int matchoff, matchlen, clen; + unsigned int msglen, origlen; + const char *dptr, *end; + s16 diff, tdiff = 0; int ret; - typeof(nf_nat_sip_hook) nf_nat_sip; + + if (ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + return NF_ACCEPT; /* No Data ? */ - dataoff = protoff + sizeof(struct udphdr); + th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph); + if (th == NULL) + return NF_ACCEPT; + dataoff = protoff + th->doff * 4; if (dataoff >= skb->len) return NF_ACCEPT; nf_ct_refresh(ct, skb, sip_timeout * HZ); - if (!skb_is_nonlinear(skb)) - dptr = skb->data + dataoff; - else { + if (skb_is_nonlinear(skb)) { pr_debug("Copy of skbuff not supported yet.\n"); return NF_ACCEPT; } + dptr = skb->data + dataoff; datalen = skb->len - dataoff; if (datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; - if (strnicmp(dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0) - ret = process_sip_request(skb, dataoff, &dptr, &datalen); - else - ret = process_sip_response(skb, dataoff, &dptr, &datalen); + while (1) { + if (ct_sip_get_header(ct, dptr, 0, datalen, + SIP_HDR_CONTENT_LENGTH, + &matchoff, &matchlen) <= 0) + break; - if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { - nf_nat_sip = rcu_dereference(nf_nat_sip_hook); - if (nf_nat_sip && !nf_nat_sip(skb, dataoff, &dptr, &datalen)) - ret = NF_DROP; + clen = simple_strtoul(dptr + matchoff, (char **)&end, 10); + if (dptr + matchoff == end) + break; + + if (end + strlen("\r\n\r\n") > dptr + datalen) + break; + if (end[0] != '\r' || end[1] != '\n' || + end[2] != '\r' || end[3] != '\n') + break; + end += strlen("\r\n\r\n") + clen; + + msglen = origlen = end - dptr; + + ret = process_sip_msg(skb, ct, dataoff, &dptr, &msglen); + if (ret != NF_ACCEPT) + break; + diff = msglen - origlen; + tdiff += diff; + + dataoff += msglen; + dptr += msglen; + datalen = datalen + diff - msglen; } return ret; } -static struct nf_conntrack_helper sip[MAX_PORTS][2] __read_mostly; -static char sip_names[MAX_PORTS][2][sizeof("sip-65535")] __read_mostly; +static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + unsigned int dataoff, datalen; + const char *dptr; + + /* No Data ? */ + dataoff = protoff + sizeof(struct udphdr); + if (dataoff >= skb->len) + return NF_ACCEPT; + + nf_ct_refresh(ct, skb, sip_timeout * HZ); + + if (skb_is_nonlinear(skb)) { + pr_debug("Copy of skbuff not supported yet.\n"); + return NF_ACCEPT; + } + + dptr = skb->data + dataoff; + datalen = skb->len - dataoff; + if (datalen < strlen("SIP/2.0 200")) + return NF_ACCEPT; + + return process_sip_msg(skb, ct, dataoff, &dptr, &datalen); +} + +static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly; +static char sip_names[MAX_PORTS][4][sizeof("sip-65535")] __read_mostly; static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = { [SIP_EXPECT_SIGNALLING] = { @@ -1333,7 +1470,7 @@ static void nf_conntrack_sip_fini(void) int i, j; for (i = 0; i < ports_c; i++) { - for (j = 0; j < 2; j++) { + for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { if (sip[i][j].me == NULL) continue; nf_conntrack_helper_unregister(&sip[i][j]); @@ -1353,14 +1490,24 @@ static int __init nf_conntrack_sip_init(void) memset(&sip[i], 0, sizeof(sip[i])); sip[i][0].tuple.src.l3num = AF_INET; - sip[i][1].tuple.src.l3num = AF_INET6; - for (j = 0; j < 2; j++) { - sip[i][j].tuple.dst.protonum = IPPROTO_UDP; + sip[i][0].tuple.dst.protonum = IPPROTO_UDP; + sip[i][0].help = sip_help_udp; + sip[i][1].tuple.src.l3num = AF_INET; + sip[i][1].tuple.dst.protonum = IPPROTO_TCP; + sip[i][1].help = sip_help_tcp; + + sip[i][2].tuple.src.l3num = AF_INET6; + sip[i][2].tuple.dst.protonum = IPPROTO_UDP; + sip[i][2].help = sip_help_udp; + sip[i][3].tuple.src.l3num = AF_INET6; + sip[i][3].tuple.dst.protonum = IPPROTO_TCP; + sip[i][3].help = sip_help_tcp; + + for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { sip[i][j].tuple.src.u.udp.port = htons(ports[i]); sip[i][j].expect_policy = sip_exp_policy; sip[i][j].expect_class_max = SIP_EXPECT_MAX; sip[i][j].me = THIS_MODULE; - sip[i][j].help = sip_help; tmpname = &sip_names[i][j][0]; if (ports[i] == SIP_PORT) -- cgit v1.2.3 From 010c0b9f34a4c567b431f8b49a58b7332ed42e47 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:27:09 +0100 Subject: netfilter: nf_nat: support mangling a single TCP packet multiple times nf_nat_mangle_tcp_packet() can currently only handle a single mangling per window because it only maintains two sequence adjustment positions: the one before the last adjustment and the one after. This patch makes sequence number adjustment tracking in nf_nat_mangle_tcp_packet() optional and allows a helper to manually update the offsets after the packet has been fully handled. Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_helper.c | 39 ++++++++++++++++++++++---------------- 1 file changed, 23 insertions(+), 16 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 7f10a6be019..4b6af4bb1f5 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -141,6 +141,17 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra) return 1; } +void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + __be32 seq, s16 off) +{ + if (!off) + return; + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo); + nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); +} +EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); + /* Generic function for mangling variable-length address changes inside * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX * command in FTP). @@ -149,14 +160,13 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra) * skb enlargement, ... * * */ -int -nf_nat_mangle_tcp_packet(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int match_offset, - unsigned int match_len, - const char *rep_buffer, - unsigned int rep_len) +int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len, bool adjust) { struct rtable *rt = skb_rtable(skb); struct iphdr *iph; @@ -202,16 +212,13 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, inet_proto_csum_replace2(&tcph->check, skb, htons(oldlen), htons(datalen), 1); - if (rep_len != match_len) { - set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); - adjust_tcp_sequence(ntohl(tcph->seq), - (int)rep_len - (int)match_len, - ct, ctinfo); - nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); - } + if (adjust && rep_len != match_len) + nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, + (int)rep_len - (int)match_len); + return 1; } -EXPORT_SYMBOL(nf_nat_mangle_tcp_packet); +EXPORT_SYMBOL(__nf_nat_mangle_tcp_packet); /* Generic function for mangling variable-length address changes inside * NATed UDP connections (like the CONNECT DATA XXXXX MESG XXXXX INDEX XXXXX -- cgit v1.2.3 From 48f8ac26537c1b7b1a2422f5232f45d06c945348 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:29:38 +0100 Subject: netfilter: nf_nat_sip: add TCP support Add support for mangling TCP SIP packets. Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_sip.c | 53 +++++++++++++++++++++++++++++++++++----- net/netfilter/nf_conntrack_sip.c | 10 ++++++++ 2 files changed, 57 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index b232e4040dc..11b538deaae 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -1,4 +1,4 @@ -/* SIP extension for UDP NAT alteration. +/* SIP extension for NAT alteration. * * (C) 2005 by Christian Hentschel * based on RR's ip_nat_ftp.c and other modules. @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -36,10 +37,27 @@ static unsigned int mangle_packet(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - - if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, matchoff, matchlen, - buffer, buflen)) - return 0; + struct tcphdr *th; + unsigned int baseoff; + + if (nf_ct_protonum(ct) == IPPROTO_TCP) { + th = (struct tcphdr *)(skb->data + ip_hdrlen(skb)); + baseoff = ip_hdrlen(skb) + th->doff * 4; + matchoff += dataoff - baseoff; + + if (!__nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + matchoff, matchlen, + buffer, buflen, false)) + return 0; + } else { + baseoff = ip_hdrlen(skb) + sizeof(struct udphdr); + matchoff += dataoff - baseoff; + + if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, + matchoff, matchlen, + buffer, buflen)) + return 0; + } /* Reload data pointer and adjust datalen value */ *dptr = skb->data + dataoff; @@ -104,6 +122,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int coff, matchoff, matchlen; + enum sip_header_types hdr; union nf_inet_addr addr; __be16 port; int request, in_header; @@ -120,9 +139,14 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, } else request = 0; + if (nf_ct_protonum(ct) == IPPROTO_TCP) + hdr = SIP_HDR_VIA_TCP; + else + hdr = SIP_HDR_VIA_UDP; + /* Translate topmost Via header and parameters */ if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, - SIP_HDR_VIA_UDP, NULL, &matchoff, &matchlen, + hdr, NULL, &matchoff, &matchlen, &addr, &port) > 0) { unsigned int matchend, poff, plen, buflen, n; char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; @@ -204,9 +228,23 @@ next: if (!map_sip_addr(skb, dataoff, dptr, datalen, SIP_HDR_FROM) || !map_sip_addr(skb, dataoff, dptr, datalen, SIP_HDR_TO)) return NF_DROP; + return NF_ACCEPT; } +static void ip_nat_sip_seq_adjust(struct sk_buff *skb, s16 off) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP || off == 0) + return; + + th = (struct tcphdr *)(skb->data + ip_hdrlen(skb)); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} + /* Handles expected signalling connections and media streams */ static void ip_nat_sip_expected(struct nf_conn *ct, struct nf_conntrack_expect *exp) @@ -472,6 +510,7 @@ err1: static void __exit nf_nat_sip_fini(void) { rcu_assign_pointer(nf_nat_sip_hook, NULL); + rcu_assign_pointer(nf_nat_sip_seq_adjust_hook, NULL); rcu_assign_pointer(nf_nat_sip_expect_hook, NULL); rcu_assign_pointer(nf_nat_sdp_addr_hook, NULL); rcu_assign_pointer(nf_nat_sdp_port_hook, NULL); @@ -483,12 +522,14 @@ static void __exit nf_nat_sip_fini(void) static int __init nf_nat_sip_init(void) { BUG_ON(nf_nat_sip_hook != NULL); + BUG_ON(nf_nat_sip_seq_adjust_hook != NULL); BUG_ON(nf_nat_sip_expect_hook != NULL); BUG_ON(nf_nat_sdp_addr_hook != NULL); BUG_ON(nf_nat_sdp_port_hook != NULL); BUG_ON(nf_nat_sdp_session_hook != NULL); BUG_ON(nf_nat_sdp_media_hook != NULL); rcu_assign_pointer(nf_nat_sip_hook, ip_nat_sip); + rcu_assign_pointer(nf_nat_sip_seq_adjust_hook, ip_nat_sip_seq_adjust); rcu_assign_pointer(nf_nat_sip_expect_hook, ip_nat_sip_expect); rcu_assign_pointer(nf_nat_sdp_addr_hook, ip_nat_sdp_addr); rcu_assign_pointer(nf_nat_sdp_port_hook, ip_nat_sdp_port); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 1cc75c5a822..3bb3aaff76e 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -56,6 +56,9 @@ unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, unsigned int *datalen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_hook); +void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off) __read_mostly; +EXPORT_SYMBOL_GPL(nf_nat_sip_seq_adjust_hook); + unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, @@ -1360,6 +1363,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, const char *dptr, *end; s16 diff, tdiff = 0; int ret; + typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) @@ -1415,6 +1419,12 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, datalen = datalen + diff - msglen; } + if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { + nf_nat_sip_seq_adjust = rcu_dereference(nf_nat_sip_seq_adjust_hook); + if (nf_nat_sip_seq_adjust) + nf_nat_sip_seq_adjust(skb, tdiff); + } + return ret; } -- cgit v1.2.3 From 9d288dffe3a276e1f06ba556845c456d696c5a4f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 11 Feb 2010 12:30:21 +0100 Subject: netfilter: nf_conntrack_sip: add T.38 FAX support Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_sip.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 3bb3aaff76e..fbe8ff5a420 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -907,6 +907,7 @@ err1: static const struct sdp_media_type sdp_media_types[] = { SDP_MEDIA_TYPE("audio ", SIP_EXPECT_AUDIO), SDP_MEDIA_TYPE("video ", SIP_EXPECT_VIDEO), + SDP_MEDIA_TYPE("image ", SIP_EXPECT_IMAGE), }; static const struct sdp_media_type *sdp_media_type(const char *dptr, @@ -932,7 +933,6 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); unsigned int matchoff, matchlen; unsigned int mediaoff, medialen; unsigned int sdpoff; @@ -1024,9 +1024,6 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, ret = nf_nat_sdp_session(skb, dataoff, dptr, datalen, sdpoff, &rtp_addr); - if (ret == NF_ACCEPT && i > 0) - help->help.ct_sip_info.invite_cseq = cseq; - return ret; } static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, @@ -1077,6 +1074,22 @@ static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, return NF_ACCEPT; } +static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int cseq) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_conn_help *help = nfct_help(ct); + unsigned int ret; + + flush_expectations(ct, true); + ret = process_sdp(skb, dataoff, dptr, datalen, cseq); + if (ret == NF_ACCEPT) + help->help.ct_sip_info.invite_cseq = cseq; + return ret; +} + static int process_bye_request(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) @@ -1257,7 +1270,7 @@ flush: } static const struct sip_handler sip_handlers[] = { - SIP_HANDLER("INVITE", process_sdp, process_invite_response), + SIP_HANDLER("INVITE", process_invite_request, process_invite_response), SIP_HANDLER("UPDATE", process_sdp, process_update_response), SIP_HANDLER("ACK", process_sdp, NULL), SIP_HANDLER("PRACK", process_sdp, process_prack_response), @@ -1473,6 +1486,11 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1 .max_expected = 2 * IP_CT_DIR_MAX, .timeout = 3 * 60, }, + [SIP_EXPECT_IMAGE] = { + .name = "image", + .max_expected = IP_CT_DIR_MAX, + .timeout = 3 * 60, + }, }; static void nf_conntrack_sip_fini(void) -- cgit v1.2.3 From b2907e501945d5d13326a6a7441c13e41cd0e799 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 11 Feb 2010 18:41:35 +0100 Subject: netfilter: xtables: fix mangle tables In POST_ROUTING hook, calling dev_net(in) is going to oops. Signed-off-by: Alexey Dobriyan Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/iptable_mangle.c | 4 +++- net/ipv6/netfilter/ip6table_mangle.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 58d7097baa3..c8333305d63 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -87,7 +87,9 @@ iptable_mangle_hook(unsigned int hook, { if (hook == NF_INET_LOCAL_OUT) return ipt_local_hook(hook, skb, in, out, okfn); - + if (hook == NF_INET_POST_ROUTING) + return ipt_do_table(skb, hook, in, out, + dev_net(out)->ipv4.iptable_mangle); /* PREROUTING/INPUT/FORWARD: */ return ipt_do_table(skb, hook, in, out, dev_net(in)->ipv4.iptable_mangle); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index dc803b7e8e5..b6216dede52 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -81,7 +81,9 @@ ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, { if (hook == NF_INET_LOCAL_OUT) return ip6t_local_out_hook(hook, skb, out, okfn); - + if (hook == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, hook, in, out, + dev_net(out)->ipv6.ip6table_mangle); /* INPUT/FORWARD */ return ip6t_do_table(skb, hook, in, out, dev_net(in)->ipv6.ip6table_mangle); -- cgit v1.2.3 From ca1c2e2da9637c131436bf6d6ae41b58f5353afe Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 12 Feb 2010 06:25:36 +0100 Subject: netfilter: don't use INIT_RCU_HEAD() call_rcu() will unconditionally reinitialize RCU head anyway. Signed-off-by: Alexey Dobriyan Reviewed-by: Paul E. McKenney Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_expect.c | 1 - net/netfilter/nf_conntrack_extend.c | 1 - net/netfilter/nfnetlink_queue.c | 1 - 3 files changed, 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 33b85f834c0..6182fb1b55d 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -232,7 +232,6 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me) new->master = me; atomic_set(&new->use, 1); - INIT_RCU_HEAD(&new->rcu); return new; } EXPORT_SYMBOL_GPL(nf_ct_expect_alloc); diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index fef95be334b..fdc8fb4ae10 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -59,7 +59,6 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) if (!*ext) return NULL; - INIT_RCU_HEAD(&(*ext)->rcu); (*ext)->offset[id] = off; (*ext)->len = len; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 90cf36decea..7ba4abc405c 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -112,7 +112,6 @@ instance_create(u_int16_t queue_num, int pid) inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); - INIT_RCU_HEAD(&inst->rcu); if (!try_module_get(THIS_MODULE)) { err = -EAGAIN; -- cgit v1.2.3 From 98e6d2d5ee26bf56850a10eb64139c68fb09ba19 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 15 Feb 2010 16:31:35 +0100 Subject: netfilter: xt_recent: inform user when hitcount is too large It is one of these things that iptables cannot catch and which can cause "Invalid argument" to be printed. Without a hint in dmesg, it is not going to be helpful. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- net/netfilter/xt_recent.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 20333310736..132cfaa84cd 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -53,7 +53,7 @@ module_param(ip_list_perms, uint, 0400); module_param(ip_list_uid, uint, 0400); module_param(ip_list_gid, uint, 0400); 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_pkt_list_tot, "number of packets per IP address 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/xt_recent/* files"); MODULE_PARM_DESC(ip_list_uid,"owner of /proc/net/xt_recent/* files"); @@ -306,8 +306,12 @@ static bool recent_mt_check(const struct xt_mtchk_param *par) if ((info->check_set & (XT_RECENT_SET | XT_RECENT_REMOVE)) && (info->seconds || info->hit_count)) return false; - if (info->hit_count > ip_pkt_list_tot) + if (info->hit_count > ip_pkt_list_tot) { + pr_info(KBUILD_MODNAME ": hitcount (%u) is larger than " + "packets to be remembered (%u)\n", + info->hit_count, ip_pkt_list_tot); return false; + } if (info->name[0] == '\0' || strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN) return false; -- cgit v1.2.3 From fa96a0e2e67fe34a3d994e3f354a5c229dd14286 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sun, 1 Nov 2009 00:36:40 +0100 Subject: netfilter: iptables: remove unused function arguments Signed-off-by: Jan Engelhardt --- net/ipv4/netfilter/iptable_mangle.c | 10 +++------- net/ipv6/netfilter/ip6table_mangle.c | 10 +++------- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index c8333305d63..b9b83464cbf 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -36,11 +36,7 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ipt_local_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) { unsigned int ret; const struct iphdr *iph; @@ -60,7 +56,7 @@ ipt_local_hook(unsigned int hook, daddr = iph->daddr; tos = iph->tos; - ret = ipt_do_table(skb, hook, in, out, + ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, dev_net(out)->ipv4.iptable_mangle); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN && ret != NF_QUEUE) { @@ -86,7 +82,7 @@ iptable_mangle_hook(unsigned int hook, int (*okfn)(struct sk_buff *)) { if (hook == NF_INET_LOCAL_OUT) - return ipt_local_hook(hook, skb, in, out, okfn); + return ipt_mangle_out(skb, out); if (hook == NF_INET_POST_ROUTING) return ipt_do_table(skb, hook, in, out, dev_net(out)->ipv4.iptable_mangle); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index b6216dede52..7844e557c0e 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -30,12 +30,8 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) { - unsigned int ret; struct in6_addr saddr, daddr; u_int8_t hop_limit; @@ -60,7 +56,7 @@ ip6t_local_out_hook(unsigned int hook, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, hook, NULL, out, + ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, dev_net(out)->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && @@ -80,7 +76,7 @@ ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { if (hook == NF_INET_LOCAL_OUT) - return ip6t_local_out_hook(hook, skb, out, okfn); + return ip6t_mangle_out(skb, out); if (hook == NF_INET_POST_ROUTING) return ip6t_do_table(skb, hook, in, out, dev_net(out)->ipv6.ip6table_mangle); -- cgit v1.2.3 From b402405d71beed8e4df354844353f66b4e18269f Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Thu, 25 Jun 2009 18:32:12 +0200 Subject: netfilter: xtables: print details on size mismatch Print which revision has been used and which size are which (kernel/user) for easier debugging. Signed-off-by: Jan Engelhardt --- net/netfilter/x_tables.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 255ab0657ce..12503199826 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -366,8 +366,10 @@ int xt_check_match(struct xt_mtchk_param *par, * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ - pr_err("%s_tables: %s match: invalid size %u != %u\n", + pr_err("%s_tables: %s.%u match: invalid size " + "%u (kernel) != (user) %u\n", xt_prefix[par->family], par->match->name, + par->match->revision, XT_ALIGN(par->match->matchsize), size); return -EINVAL; } @@ -516,8 +518,10 @@ int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { if (XT_ALIGN(par->target->targetsize) != size) { - pr_err("%s_tables: %s target: invalid size %u != %u\n", + pr_err("%s_tables: %s.%u target: invalid size " + "%u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, + par->target->revision, XT_ALIGN(par->target->targetsize), size); return -EINVAL; } -- cgit v1.2.3 From 739674fb7febf116e7d647031fab16989a08a965 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 26 Jun 2009 08:23:19 +0200 Subject: netfilter: xtables: constify args in compat copying functions Signed-off-by: Jan Engelhardt --- net/ipv4/netfilter/arp_tables.c | 4 ++-- net/ipv4/netfilter/ip_tables.c | 4 ++-- net/ipv4/netfilter/ipt_ULOG.c | 4 ++-- net/ipv6/netfilter/ip6_tables.c | 4 ++-- net/netfilter/x_tables.c | 8 ++++---- net/netfilter/xt_hashlimit.c | 4 ++-- net/netfilter/xt_limit.c | 4 ++-- 7 files changed, 16 insertions(+), 16 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 72723ea1054..2303dc92a27 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -842,7 +842,7 @@ static int copy_entries_to_user(unsigned int total_size, } #ifdef CONFIG_COMPAT -static void compat_standard_from_user(void *dst, void *src) +static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; @@ -851,7 +851,7 @@ static void compat_standard_from_user(void *dst, void *src) memcpy(dst, &v, sizeof(v)); } -static int compat_standard_to_user(void __user *dst, void *src) +static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2057b1bb617..2a4f745ce36 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1047,7 +1047,7 @@ copy_entries_to_user(unsigned int total_size, } #ifdef CONFIG_COMPAT -static void compat_standard_from_user(void *dst, void *src) +static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; @@ -1056,7 +1056,7 @@ static void compat_standard_from_user(void *dst, void *src) memcpy(dst, &v, sizeof(v)); } -static int compat_standard_to_user(void __user *dst, void *src) +static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 399061c3fd7..09a5d3f7cc4 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -338,7 +338,7 @@ struct compat_ipt_ulog_info { char prefix[ULOG_PREFIX_LEN]; }; -static void ulog_tg_compat_from_user(void *dst, void *src) +static void ulog_tg_compat_from_user(void *dst, const void *src) { const struct compat_ipt_ulog_info *cl = src; struct ipt_ulog_info l = { @@ -351,7 +351,7 @@ static void ulog_tg_compat_from_user(void *dst, void *src) memcpy(dst, &l, sizeof(l)); } -static int ulog_tg_compat_to_user(void __user *dst, void *src) +static int ulog_tg_compat_to_user(void __user *dst, const void *src) { const struct ipt_ulog_info *l = src; struct compat_ipt_ulog_info cl = { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index dcd7825fe7b..3ff4fd50e96 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1079,7 +1079,7 @@ copy_entries_to_user(unsigned int total_size, } #ifdef CONFIG_COMPAT -static void compat_standard_from_user(void *dst, void *src) +static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; @@ -1088,7 +1088,7 @@ static void compat_standard_from_user(void *dst, void *src) memcpy(dst, &v, sizeof(v)); } -static int compat_standard_to_user(void __user *dst, void *src) +static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 12503199826..69c56287d51 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -485,8 +485,8 @@ int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); -int xt_compat_match_to_user(struct xt_entry_match *m, void __user **dstptr, - unsigned int *size) +int xt_compat_match_to_user(const struct xt_entry_match *m, + void __user **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match __user *cm = *dstptr; @@ -588,8 +588,8 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, } EXPORT_SYMBOL_GPL(xt_compat_target_from_user); -int xt_compat_target_to_user(struct xt_entry_target *t, void __user **dstptr, - unsigned int *size) +int xt_compat_target_to_user(const struct xt_entry_target *t, + void __user **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target __user *ct = *dstptr; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 017c95966aa..e47fb805ffb 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -775,7 +775,7 @@ struct compat_xt_hashlimit_info { compat_uptr_t master; }; -static void hashlimit_mt_compat_from_user(void *dst, void *src) +static void hashlimit_mt_compat_from_user(void *dst, const void *src) { int off = offsetof(struct compat_xt_hashlimit_info, hinfo); @@ -783,7 +783,7 @@ static void hashlimit_mt_compat_from_user(void *dst, void *src) memset(dst + off, 0, sizeof(struct compat_xt_hashlimit_info) - off); } -static int hashlimit_mt_compat_to_user(void __user *dst, void *src) +static int hashlimit_mt_compat_to_user(void __user *dst, const void *src) { int off = offsetof(struct compat_xt_hashlimit_info, hinfo); diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 2773be6a71d..a0ca5339af4 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -148,7 +148,7 @@ struct compat_xt_rateinfo { /* To keep the full "prev" timestamp, the upper 32 bits are stored in the * master pointer, which does not need to be preserved. */ -static void limit_mt_compat_from_user(void *dst, void *src) +static void limit_mt_compat_from_user(void *dst, const void *src) { const struct compat_xt_rateinfo *cm = src; struct xt_rateinfo m = { @@ -162,7 +162,7 @@ static void limit_mt_compat_from_user(void *dst, void *src) memcpy(dst, &m, sizeof(m)); } -static int limit_mt_compat_to_user(void __user *dst, void *src) +static int limit_mt_compat_to_user(void __user *dst, const void *src) { const struct xt_rateinfo *m = src; struct compat_xt_rateinfo cm = { -- cgit v1.2.3 From d5d1baa15f5b05e9110403724d5dc72d6d541e04 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 26 Jun 2009 07:51:59 +0200 Subject: netfilter: xtables: add const qualifiers This should make it easier to remove redundant arguments later. Signed-off-by: Jan Engelhardt --- net/bridge/netfilter/ebtables.c | 59 ++++++++++++++------------- net/ipv4/netfilter/arp_tables.c | 69 ++++++++++++++++++-------------- net/ipv4/netfilter/ip_tables.c | 88 +++++++++++++++++++++++------------------ net/ipv6/netfilter/ip6_tables.c | 88 ++++++++++++++++++++++------------------- 4 files changed, 168 insertions(+), 136 deletions(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 208f4e32e73..bcdf02d866b 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -82,7 +82,8 @@ static inline int ebt_do_match (struct ebt_entry_match *m, return m->u.match->match(skb, par) ? EBT_MATCH : EBT_NOMATCH; } -static inline int ebt_dev_check(char *entry, const struct net_device *device) +static inline int +ebt_dev_check(const char *entry, const struct net_device *device) { int i = 0; const char *devname; @@ -100,8 +101,9 @@ static inline int ebt_dev_check(char *entry, const struct net_device *device) #define FWINV2(bool,invflg) ((bool) ^ !!(e->invflags & invflg)) /* process standard matches */ -static inline int ebt_basic_match(struct ebt_entry *e, struct ethhdr *h, - const struct net_device *in, const struct net_device *out) +static inline int +ebt_basic_match(const struct ebt_entry *e, const struct ethhdr *h, + const struct net_device *in, const struct net_device *out) { int verdict, i; @@ -156,12 +158,12 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, int i, nentries; struct ebt_entry *point; struct ebt_counter *counter_base, *cb_base; - struct ebt_entry_target *t; + const struct ebt_entry_target *t; int verdict, sp = 0; struct ebt_chainstack *cs; struct ebt_entries *chaininfo; - char *base; - struct ebt_table_info *private; + const char *base; + const struct ebt_table_info *private; bool hotdrop = false; struct xt_match_param mtpar; struct xt_target_param tgpar; @@ -395,7 +397,7 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par, return 0; } -static int ebt_verify_pointers(struct ebt_replace *repl, +static int ebt_verify_pointers(const struct ebt_replace *repl, struct ebt_table_info *newinfo) { unsigned int limit = repl->entries_size; @@ -466,8 +468,8 @@ static int ebt_verify_pointers(struct ebt_replace *repl, * to parse the userspace data */ static inline int -ebt_check_entry_size_and_hooks(struct ebt_entry *e, - struct ebt_table_info *newinfo, +ebt_check_entry_size_and_hooks(const struct ebt_entry *e, + const struct ebt_table_info *newinfo, unsigned int *n, unsigned int *cnt, unsigned int *totalcnt, unsigned int *udc_cnt) { @@ -622,9 +624,8 @@ ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) } static inline int -ebt_check_entry(struct ebt_entry *e, - struct net *net, - struct ebt_table_info *newinfo, +ebt_check_entry(struct ebt_entry *e, struct net *net, + const struct ebt_table_info *newinfo, const char *name, unsigned int *cnt, struct ebt_cl_stack *cl_s, unsigned int udc_cnt) { @@ -743,12 +744,12 @@ cleanup_matches: * the hook mask for udc tells us from which base chains the udc can be * accessed. This mask is a parameter to the check() functions of the extensions */ -static int check_chainloops(struct ebt_entries *chain, struct ebt_cl_stack *cl_s, +static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack *cl_s, unsigned int udc_cnt, unsigned int hooknr, char *base) { int i, chain_nr = -1, pos = 0, nentries = chain->nentries, verdict; - struct ebt_entry *e = (struct ebt_entry *)chain->data; - struct ebt_entry_target *t; + const struct ebt_entry *e = (struct ebt_entry *)chain->data; + const struct ebt_entry_target *t; while (pos < nentries || chain_nr != -1) { /* end of udc, go back one 'recursion' step */ @@ -814,7 +815,7 @@ letscontinue: } /* do the parsing of the table/chains/entries/matches/watchers/targets, heh */ -static int translate_table(struct net *net, char *name, +static int translate_table(struct net *net, const char *name, struct ebt_table_info *newinfo) { unsigned int i, j, k, udc_cnt; @@ -934,7 +935,7 @@ static int translate_table(struct net *net, char *name, } /* called under write_lock */ -static void get_counters(struct ebt_counter *oldcounters, +static void get_counters(const struct ebt_counter *oldcounters, struct ebt_counter *counters, unsigned int nentries) { int i, cpu; @@ -957,7 +958,8 @@ static void get_counters(struct ebt_counter *oldcounters, } /* replace the table */ -static int do_replace(struct net *net, void __user *user, unsigned int len) +static int do_replace(struct net *net, const void __user *user, + unsigned int len) { int ret, i, countersize; struct ebt_table_info *newinfo; @@ -1237,7 +1239,8 @@ void ebt_unregister_table(struct net *net, struct ebt_table *table) } /* userspace just supplied us with counters */ -static int update_counters(struct net *net, void __user *user, unsigned int len) +static int update_counters(struct net *net, const void __user *user, + unsigned int len) { int i, ret; struct ebt_counter *tmp; @@ -1292,8 +1295,8 @@ free_tmp: return ret; } -static inline int ebt_make_matchname(struct ebt_entry_match *m, - char *base, char __user *ubase) +static inline int ebt_make_matchname(const struct ebt_entry_match *m, + const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)m - base); if (copy_to_user(hlp, m->u.match->name, EBT_FUNCTION_MAXNAMELEN)) @@ -1301,8 +1304,8 @@ static inline int ebt_make_matchname(struct ebt_entry_match *m, return 0; } -static inline int ebt_make_watchername(struct ebt_entry_watcher *w, - char *base, char __user *ubase) +static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, + const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)w - base); if (copy_to_user(hlp , w->u.watcher->name, EBT_FUNCTION_MAXNAMELEN)) @@ -1310,11 +1313,12 @@ static inline int ebt_make_watchername(struct ebt_entry_watcher *w, return 0; } -static inline int ebt_make_names(struct ebt_entry *e, char *base, char __user *ubase) +static inline int +ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) { int ret; char __user *hlp; - struct ebt_entry_target *t; + const struct ebt_entry_target *t; if (e->bitmask == 0) return 0; @@ -1335,10 +1339,11 @@ static inline int ebt_make_names(struct ebt_entry *e, char *base, char __user *u /* called with ebt_mutex locked */ static int copy_everything_to_user(struct ebt_table *t, void __user *user, - int *len, int cmd) + const int *len, int cmd) { struct ebt_replace tmp; - struct ebt_counter *counterstmp, *oldcounters; + struct ebt_counter *counterstmp; + const struct ebt_counter *oldcounters; unsigned int entries_size, nentries; char *entries; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 2303dc92a27..4db5c1ece0f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -233,7 +233,14 @@ arpt_error(struct sk_buff *skb, const struct xt_target_param *par) return NF_DROP; } -static inline struct arpt_entry *get_entry(void *base, unsigned int offset) +static inline const struct arpt_entry_target * +arpt_get_target_c(const struct arpt_entry *e) +{ + return arpt_get_target((struct arpt_entry *)e); +} + +static inline struct arpt_entry * +get_entry(const void *base, unsigned int offset) { return (struct arpt_entry *)(base + offset); } @@ -280,7 +287,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, arp = arp_hdr(skb); do { - struct arpt_entry_target *t; + const struct arpt_entry_target *t; int hdr_len; if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { @@ -292,7 +299,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, (2 * skb->dev->addr_len); ADD_COUNTER(e->counters, hdr_len, 1); - t = arpt_get_target(e); + t = arpt_get_target_c(e); /* Standard target? */ if (!t->u.kernel.target->target) { @@ -358,7 +365,7 @@ static inline bool unconditional(const struct arpt_arp *arp) /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ -static int mark_source_chains(struct xt_table_info *newinfo, +static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -379,7 +386,7 @@ static int mark_source_chains(struct xt_table_info *newinfo, for (;;) { const struct arpt_standard_target *t - = (void *)arpt_get_target(e); + = (void *)arpt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_ARP_NUMHOOKS)) { @@ -463,7 +470,7 @@ static int mark_source_chains(struct xt_table_info *newinfo, return 1; } -static inline int check_entry(struct arpt_entry *e, const char *name) +static inline int check_entry(const struct arpt_entry *e, const char *name) { const struct arpt_entry_target *t; @@ -475,7 +482,7 @@ static inline int check_entry(struct arpt_entry *e, const char *name) if (e->target_offset + sizeof(struct arpt_entry_target) > e->next_offset) return -EINVAL; - t = arpt_get_target(e); + t = arpt_get_target_c(e); if (e->target_offset + t->u.target_size > e->next_offset) return -EINVAL; @@ -540,14 +547,14 @@ out: return ret; } -static bool check_underflow(struct arpt_entry *e) +static bool check_underflow(const struct arpt_entry *e) { const struct arpt_entry_target *t; unsigned int verdict; if (!unconditional(&e->arp)) return false; - t = arpt_get_target(e); + t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct arpt_standard_target *)t)->verdict; @@ -557,8 +564,8 @@ static bool check_underflow(struct arpt_entry *e) static inline int check_entry_size_and_hooks(struct arpt_entry *e, struct xt_table_info *newinfo, - unsigned char *base, - unsigned char *limit, + const unsigned char *base, + const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks, @@ -768,11 +775,11 @@ static void get_counters(const struct xt_table_info *t, local_bh_enable(); } -static struct xt_counters *alloc_counters(struct xt_table *table) +static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - struct xt_table_info *private = table->private; + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -790,11 +797,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) } static int copy_entries_to_user(unsigned int total_size, - struct xt_table *table, + const struct xt_table *table, void __user *userptr) { unsigned int off, num; - struct arpt_entry *e; + const struct arpt_entry *e; struct xt_counters *counters; struct xt_table_info *private = table->private; int ret = 0; @@ -814,7 +821,7 @@ static int copy_entries_to_user(unsigned int total_size, /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ - struct arpt_entry_target *t; + const struct arpt_entry_target *t; e = (struct arpt_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -825,7 +832,7 @@ static int copy_entries_to_user(unsigned int total_size, goto free_counters; } - t = arpt_get_target(e); + t = arpt_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset + offsetof(struct arpt_entry_target, u.user.name), @@ -860,18 +867,18 @@ static int compat_standard_to_user(void __user *dst, const void *src) return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } -static int compat_calc_entry(struct arpt_entry *e, +static int compat_calc_entry(const struct arpt_entry *e, const struct xt_table_info *info, - void *base, struct xt_table_info *newinfo) + const void *base, struct xt_table_info *newinfo) { - struct arpt_entry_target *t; + const struct arpt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); entry_offset = (void *)e - base; - t = arpt_get_target(e); + t = arpt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); @@ -907,7 +914,8 @@ static int compat_table_info(const struct xt_table_info *info, } #endif -static int get_info(struct net *net, void __user *user, int *len, int compat) +static int get_info(struct net *net, void __user *user, + const int *len, int compat) { char name[ARPT_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -966,7 +974,7 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) } static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, - int *len) + const int *len) { int ret; struct arpt_get_entries get; @@ -1080,7 +1088,8 @@ static int __do_replace(struct net *net, const char *name, return ret; } -static int do_replace(struct net *net, void __user *user, unsigned int len) +static int do_replace(struct net *net, const void __user *user, + unsigned int len) { int ret; struct arpt_replace tmp; @@ -1140,8 +1149,8 @@ add_counter_to_entry(struct arpt_entry *e, return 0; } -static int do_add_counters(struct net *net, void __user *user, unsigned int len, - int compat) +static int do_add_counters(struct net *net, const void __user *user, + unsigned int len, int compat) { unsigned int i, curcpu; struct xt_counters_info tmp; @@ -1245,10 +1254,10 @@ static inline int check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, struct xt_table_info *newinfo, unsigned int *size, - unsigned char *base, - unsigned char *limit, - unsigned int *hook_entries, - unsigned int *underflows, + const unsigned char *base, + const unsigned char *limit, + const unsigned int *hook_entries, + const unsigned int *underflows, unsigned int *i, const char *name) { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2a4f745ce36..e94c18bdfc6 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -176,7 +176,7 @@ ipt_error(struct sk_buff *skb, const struct xt_target_param *par) /* Performance critical - called for every packet */ static inline bool -do_match(struct ipt_entry_match *m, const struct sk_buff *skb, +do_match(const struct ipt_entry_match *m, const struct sk_buff *skb, struct xt_match_param *par) { par->match = m->u.kernel.match; @@ -191,7 +191,7 @@ do_match(struct ipt_entry_match *m, const struct sk_buff *skb, /* Performance critical */ static inline struct ipt_entry * -get_entry(void *base, unsigned int offset) +get_entry(const void *base, unsigned int offset) { return (struct ipt_entry *)(base + offset); } @@ -206,6 +206,13 @@ static inline bool unconditional(const struct ipt_ip *ip) #undef FWINV } +/* for const-correctness */ +static inline const struct ipt_entry_target * +ipt_get_target_c(const struct ipt_entry *e) +{ + return ipt_get_target((struct ipt_entry *)e); +} + #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) static const char *const hooknames[] = { @@ -240,11 +247,11 @@ static struct nf_loginfo trace_loginfo = { /* Mildly perf critical (only if packet tracing is on) */ static inline int -get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, +get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - struct ipt_standard_target *t = (void *)ipt_get_target(s); + const struct ipt_standard_target *t = (void *)ipt_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, IPT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ @@ -270,15 +277,15 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, return 0; } -static void trace_packet(struct sk_buff *skb, +static void trace_packet(const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, - struct xt_table_info *private, - struct ipt_entry *e) + const struct xt_table_info *private, + const struct ipt_entry *e) { - void *table_base; + const void *table_base; const struct ipt_entry *root; const char *hookname, *chainname, *comment; unsigned int rulenum = 0; @@ -322,9 +329,9 @@ ipt_do_table(struct sk_buff *skb, /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; - void *table_base; + const void *table_base; struct ipt_entry *e, *back; - struct xt_table_info *private; + const struct xt_table_info *private; struct xt_match_param mtpar; struct xt_target_param tgpar; @@ -357,7 +364,7 @@ ipt_do_table(struct sk_buff *skb, back = get_entry(table_base, private->underflow[hook]); do { - struct ipt_entry_target *t; + const struct ipt_entry_target *t; IP_NF_ASSERT(e); IP_NF_ASSERT(back); @@ -450,7 +457,7 @@ ipt_do_table(struct sk_buff *skb, /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct xt_table_info *newinfo, +mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -468,8 +475,8 @@ mark_source_chains(struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - struct ipt_standard_target *t - = (void *)ipt_get_target(e); + const struct ipt_standard_target *t + = (void *)ipt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) { @@ -578,9 +585,9 @@ cleanup_match(struct ipt_entry_match *m, struct net *net, unsigned int *i) } static int -check_entry(struct ipt_entry *e, const char *name) +check_entry(const struct ipt_entry *e, const char *name) { - struct ipt_entry_target *t; + const struct ipt_entry_target *t; if (!ip_checkentry(&e->ip)) { duprintf("ip_tables: ip check failed %p %s.\n", e, name); @@ -591,7 +598,7 @@ check_entry(struct ipt_entry *e, const char *name) e->next_offset) return -EINVAL; - t = ipt_get_target(e); + t = ipt_get_target_c(e); if (e->target_offset + t->u.target_size > e->next_offset) return -EINVAL; @@ -718,14 +725,14 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, return ret; } -static bool check_underflow(struct ipt_entry *e) +static bool check_underflow(const struct ipt_entry *e) { const struct ipt_entry_target *t; unsigned int verdict; if (!unconditional(&e->ip)) return false; - t = ipt_get_target(e); + t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct ipt_standard_target *)t)->verdict; @@ -736,8 +743,8 @@ static bool check_underflow(struct ipt_entry *e) static int check_entry_size_and_hooks(struct ipt_entry *e, struct xt_table_info *newinfo, - unsigned char *base, - unsigned char *limit, + const unsigned char *base, + const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks, @@ -952,11 +959,11 @@ get_counters(const struct xt_table_info *t, local_bh_enable(); } -static struct xt_counters * alloc_counters(struct xt_table *table) +static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - struct xt_table_info *private = table->private; + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -974,11 +981,11 @@ static struct xt_counters * alloc_counters(struct xt_table *table) static int copy_entries_to_user(unsigned int total_size, - struct xt_table *table, + const struct xt_table *table, void __user *userptr) { unsigned int off, num; - struct ipt_entry *e; + const struct ipt_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; @@ -1030,7 +1037,7 @@ copy_entries_to_user(unsigned int total_size, } } - t = ipt_get_target(e); + t = ipt_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset + offsetof(struct ipt_entry_target, u.user.name), @@ -1066,24 +1073,24 @@ static int compat_standard_to_user(void __user *dst, const void *src) } static inline int -compat_calc_match(struct ipt_entry_match *m, int *size) +compat_calc_match(const struct ipt_entry_match *m, int *size) { *size += xt_compat_match_offset(m->u.kernel.match); return 0; } -static int compat_calc_entry(struct ipt_entry *e, +static int compat_calc_entry(const struct ipt_entry *e, const struct xt_table_info *info, - void *base, struct xt_table_info *newinfo) + const void *base, struct xt_table_info *newinfo) { - struct ipt_entry_target *t; + const struct ipt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - base; IPT_MATCH_ITERATE(e, compat_calc_match, &off); - t = ipt_get_target(e); + t = ipt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); @@ -1119,7 +1126,8 @@ static int compat_table_info(const struct xt_table_info *info, } #endif -static int get_info(struct net *net, void __user *user, int *len, int compat) +static int get_info(struct net *net, void __user *user, + const int *len, int compat) { char name[IPT_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -1179,7 +1187,8 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) } static int -get_entries(struct net *net, struct ipt_get_entries __user *uptr, int *len) +get_entries(struct net *net, struct ipt_get_entries __user *uptr, + const int *len) { int ret; struct ipt_get_entries get; @@ -1289,7 +1298,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, } static int -do_replace(struct net *net, void __user *user, unsigned int len) +do_replace(struct net *net, const void __user *user, unsigned int len) { int ret; struct ipt_replace tmp; @@ -1350,7 +1359,8 @@ add_counter_to_entry(struct ipt_entry *e, } static int -do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) +do_add_counters(struct net *net, const void __user *user, + unsigned int len, int compat) { unsigned int i, curcpu; struct xt_counters_info tmp; @@ -1546,10 +1556,10 @@ static int check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, struct xt_table_info *newinfo, unsigned int *size, - unsigned char *base, - unsigned char *limit, - unsigned int *hook_entries, - unsigned int *underflows, + const unsigned char *base, + const unsigned char *limit, + const unsigned int *hook_entries, + const unsigned int *underflows, unsigned int *i, const char *name) { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 3ff4fd50e96..4185099c294 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -208,7 +208,7 @@ ip6t_error(struct sk_buff *skb, const struct xt_target_param *par) /* Performance critical - called for every packet */ static inline bool -do_match(struct ip6t_entry_match *m, const struct sk_buff *skb, +do_match(const struct ip6t_entry_match *m, const struct sk_buff *skb, struct xt_match_param *par) { par->match = m->u.kernel.match; @@ -222,7 +222,7 @@ do_match(struct ip6t_entry_match *m, const struct sk_buff *skb, } static inline struct ip6t_entry * -get_entry(void *base, unsigned int offset) +get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } @@ -236,6 +236,12 @@ static inline bool unconditional(const struct ip6t_ip6 *ipv6) return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; } +static inline const struct ip6t_entry_target * +ip6t_get_target_c(const struct ip6t_entry *e) +{ + return ip6t_get_target((struct ip6t_entry *)e); +} + #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) /* This cries for unification! */ @@ -271,11 +277,11 @@ static struct nf_loginfo trace_loginfo = { /* Mildly perf critical (only if packet tracing is on) */ static inline int -get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, +get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - struct ip6t_standard_target *t = (void *)ip6t_get_target(s); + const struct ip6t_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, IP6T_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ @@ -301,15 +307,15 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, return 0; } -static void trace_packet(struct sk_buff *skb, +static void trace_packet(const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, - struct xt_table_info *private, - struct ip6t_entry *e) + const struct xt_table_info *private, + const struct ip6t_entry *e) { - void *table_base; + const void *table_base; const struct ip6t_entry *root; const char *hookname, *chainname, *comment; unsigned int rulenum = 0; @@ -352,9 +358,9 @@ ip6t_do_table(struct sk_buff *skb, /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; - void *table_base; + const void *table_base; struct ip6t_entry *e, *back; - struct xt_table_info *private; + const struct xt_table_info *private; struct xt_match_param mtpar; struct xt_target_param tgpar; @@ -385,7 +391,7 @@ ip6t_do_table(struct sk_buff *skb, back = get_entry(table_base, private->underflow[hook]); do { - struct ip6t_entry_target *t; + const struct ip6t_entry_target *t; IP_NF_ASSERT(e); IP_NF_ASSERT(back); @@ -400,7 +406,7 @@ ip6t_do_table(struct sk_buff *skb, ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr), 1); - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); IP_NF_ASSERT(t->u.kernel.target); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ @@ -482,7 +488,7 @@ ip6t_do_table(struct sk_buff *skb, /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct xt_table_info *newinfo, +mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -500,8 +506,8 @@ mark_source_chains(struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - struct ip6t_standard_target *t - = (void *)ip6t_get_target(e); + const struct ip6t_standard_target *t + = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) { @@ -610,9 +616,9 @@ cleanup_match(struct ip6t_entry_match *m, struct net *net, unsigned int *i) } static int -check_entry(struct ip6t_entry *e, const char *name) +check_entry(const struct ip6t_entry *e, const char *name) { - struct ip6t_entry_target *t; + const struct ip6t_entry_target *t; if (!ip6_checkentry(&e->ipv6)) { duprintf("ip_tables: ip check failed %p %s.\n", e, name); @@ -623,7 +629,7 @@ check_entry(struct ip6t_entry *e, const char *name) e->next_offset) return -EINVAL; - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (e->target_offset + t->u.target_size > e->next_offset) return -EINVAL; @@ -750,14 +756,14 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, return ret; } -static bool check_underflow(struct ip6t_entry *e) +static bool check_underflow(const struct ip6t_entry *e) { const struct ip6t_entry_target *t; unsigned int verdict; if (!unconditional(&e->ipv6)) return false; - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct ip6t_standard_target *)t)->verdict; @@ -768,8 +774,8 @@ static bool check_underflow(struct ip6t_entry *e) static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, - unsigned char *base, - unsigned char *limit, + const unsigned char *base, + const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks, @@ -984,11 +990,11 @@ get_counters(const struct xt_table_info *t, local_bh_enable(); } -static struct xt_counters *alloc_counters(struct xt_table *table) +static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - struct xt_table_info *private = table->private; + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -1006,11 +1012,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) static int copy_entries_to_user(unsigned int total_size, - struct xt_table *table, + const struct xt_table *table, void __user *userptr) { unsigned int off, num; - struct ip6t_entry *e; + const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; @@ -1062,7 +1068,7 @@ copy_entries_to_user(unsigned int total_size, } } - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset + offsetof(struct ip6t_entry_target, u.user.name), @@ -1098,24 +1104,24 @@ static int compat_standard_to_user(void __user *dst, const void *src) } static inline int -compat_calc_match(struct ip6t_entry_match *m, int *size) +compat_calc_match(const struct ip6t_entry_match *m, int *size) { *size += xt_compat_match_offset(m->u.kernel.match); return 0; } -static int compat_calc_entry(struct ip6t_entry *e, +static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, - void *base, struct xt_table_info *newinfo) + const void *base, struct xt_table_info *newinfo) { - struct ip6t_entry_target *t; + const struct ip6t_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; IP6T_MATCH_ITERATE(e, compat_calc_match, &off); - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); @@ -1151,7 +1157,8 @@ static int compat_table_info(const struct xt_table_info *info, } #endif -static int get_info(struct net *net, void __user *user, int *len, int compat) +static int get_info(struct net *net, void __user *user, + const int *len, int compat) { char name[IP6T_TABLE_MAXNAMELEN]; struct xt_table *t; @@ -1211,7 +1218,8 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) } static int -get_entries(struct net *net, struct ip6t_get_entries __user *uptr, int *len) +get_entries(struct net *net, struct ip6t_get_entries __user *uptr, + const int *len) { int ret; struct ip6t_get_entries get; @@ -1322,7 +1330,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, } static int -do_replace(struct net *net, void __user *user, unsigned int len) +do_replace(struct net *net, const void __user *user, unsigned int len) { int ret; struct ip6t_replace tmp; @@ -1383,7 +1391,7 @@ add_counter_to_entry(struct ip6t_entry *e, } static int -do_add_counters(struct net *net, void __user *user, unsigned int len, +do_add_counters(struct net *net, const void __user *user, unsigned int len, int compat) { unsigned int i, curcpu; @@ -1582,10 +1590,10 @@ static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, - unsigned char *base, - unsigned char *limit, - unsigned int *hook_entries, - unsigned int *underflows, + const unsigned char *base, + const unsigned char *limit, + const unsigned int *hook_entries, + const unsigned int *underflows, unsigned int *i, const char *name) { -- cgit v1.2.3 From 8fea97ec1772bbf553d89187340ef624d548e115 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Feb 2010 17:45:08 +0100 Subject: netfilter: nf_conntrack: pass template to l4proto ->error() handler The error handlers might need the template to get the conntrack zone introduced in the next patches to perform a conntrack lookup. Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 3 ++- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 3 ++- net/netfilter/nf_conntrack_core.c | 3 ++- net/netfilter/nf_conntrack_proto_dccp.c | 5 +++-- net/netfilter/nf_conntrack_proto_tcp.c | 2 +- net/netfilter/nf_conntrack_proto_udp.c | 4 ++-- net/netfilter/nf_conntrack_proto_udplite.c | 2 +- 7 files changed, 13 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 7afd39b5b78..327826a968a 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -163,7 +163,8 @@ icmp_error_message(struct net *net, struct sk_buff *skb, /* Small and modified version of icmp_rcv */ static int -icmp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, +icmp_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { const struct icmphdr *icmph; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index c7b8bd1d798..d772dc21857 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -179,7 +179,8 @@ icmpv6_error_message(struct net *net, } static int -icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, +icmpv6_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { const struct icmp6hdr *icmp6h; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index bd831410a39..65351ed5d81 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -799,7 +799,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, * inverse of the return code tells to the netfilter * core what to do with the packet. */ if (l4proto->error != NULL) { - ret = l4proto->error(net, skb, dataoff, &ctinfo, pf, hooknum); + ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo, + pf, hooknum); if (ret <= 0) { NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index dd375500dcc..9a281554937 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -561,8 +561,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, return NF_ACCEPT; } -static int dccp_error(struct net *net, struct sk_buff *skb, - unsigned int dataoff, enum ip_conntrack_info *ctinfo, +static int dccp_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, + enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { struct dccp_hdr _dh, *dh; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ad118053971..9dd8cd4fb6e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -760,7 +760,7 @@ static const u8 tcp_valid_flags[(TH_FIN|TH_SYN|TH_RST|TH_ACK|TH_URG) + 1] = }; /* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */ -static int tcp_error(struct net *net, +static int tcp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 8d38f9a4bed..8289088b821 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -91,8 +91,8 @@ static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } -static int udp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, - enum ip_conntrack_info *ctinfo, +static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) { diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 0b1bc9ba667..263b5a72588 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -89,7 +89,7 @@ static bool udplite_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } -static int udplite_error(struct net *net, +static int udplite_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, -- cgit v1.2.3 From 5d0aa2ccd4699a01cfdf14886191c249d7b45a01 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Feb 2010 18:13:33 +0100 Subject: netfilter: nf_conntrack: add support for "conntrack zones" Normally, each connection needs a unique identity. Conntrack zones allow to specify a numerical zone using the CT target, connections in different zones can use the same identity. Example: iptables -t raw -A PREROUTING -i veth0 -j CT --zone 1 iptables -t raw -A OUTPUT -o veth1 -j CT --zone 1 Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 3 +- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 8 +- net/ipv4/netfilter/nf_defrag_ipv4.c | 12 ++- net/ipv4/netfilter/nf_nat_core.c | 24 +++--- net/ipv4/netfilter/nf_nat_pptp.c | 3 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 12 ++- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 8 +- net/netfilter/Kconfig | 13 +++ net/netfilter/nf_conntrack_core.c | 109 +++++++++++++++++++------ net/netfilter/nf_conntrack_expect.c | 21 +++-- net/netfilter/nf_conntrack_h323_main.c | 3 +- net/netfilter/nf_conntrack_netlink.c | 20 ++--- net/netfilter/nf_conntrack_pptp.c | 14 ++-- net/netfilter/nf_conntrack_sip.c | 3 +- net/netfilter/nf_conntrack_standalone.c | 6 ++ net/netfilter/xt_CT.c | 8 +- net/netfilter/xt_connlimit.c | 4 +- 17 files changed, 193 insertions(+), 78 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index d1ea38a7c49..2bb1f87051c 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -266,7 +267,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) return -EINVAL; } - h = nf_conntrack_find_get(sock_net(sk), &tuple); + h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); if (h) { struct sockaddr_in sin; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 327826a968a..7404bde9599 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -18,6 +18,7 @@ #include #include #include +#include #include static unsigned int nf_ct_icmp_timeout __read_mostly = 30*HZ; @@ -114,13 +115,14 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, /* Returns conntrack if it dealt with ICMP, and filled in skb fields */ static int -icmp_error_message(struct net *net, struct sk_buff *skb, +icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, enum ip_conntrack_info *ctinfo, unsigned int hooknum) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_l4proto *innerproto; const struct nf_conntrack_tuple_hash *h; + u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; NF_CT_ASSERT(skb->nfct == NULL); @@ -146,7 +148,7 @@ icmp_error_message(struct net *net, struct sk_buff *skb, *ctinfo = IP_CT_RELATED; - h = nf_conntrack_find_get(net, &innertuple); + h = nf_conntrack_find_get(net, zone, &innertuple); if (!h) { pr_debug("icmp_error_message: no match\n"); return -NF_ACCEPT; @@ -209,7 +211,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl, icmph->type != ICMP_REDIRECT) return NF_ACCEPT; - return icmp_error_message(net, skb, ctinfo, hooknum); + return icmp_error_message(net, tmpl, skb, ctinfo, hooknum); } #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index f6f46686cbc..d498a704d45 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -16,6 +16,7 @@ #include #include +#include #include #include @@ -39,15 +40,20 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, struct sk_buff *skb) { + u16 zone = NF_CT_DEFAULT_ZONE; + + if (skb->nfct) + zone = nf_ct_zone((struct nf_conn *)skb->nfct); + #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge && skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP_DEFRAG_CONNTRACK_BRIDGE_IN; + return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone; #endif if (hooknum == NF_INET_PRE_ROUTING) - return IP_DEFRAG_CONNTRACK_IN; + return IP_DEFRAG_CONNTRACK_IN + zone; else - return IP_DEFRAG_CONNTRACK_OUT; + return IP_DEFRAG_CONNTRACK_OUT + zone; } static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 26066a2327a..4595281c286 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -30,6 +30,7 @@ #include #include #include +#include static DEFINE_SPINLOCK(nf_nat_lock); @@ -69,13 +70,14 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put); /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int -hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) { unsigned int hash; /* Original src, to ensure we map it consistently if poss. */ hash = jhash_3words((__force u32)tuple->src.u3.ip, - (__force u32)tuple->src.u.all, + (__force u32)tuple->src.u.all ^ zone, tuple->dst.protonum, 0); return ((u64)hash * net->ipv4.nat_htable_size) >> 32; } @@ -139,12 +141,12 @@ same_src(const struct nf_conn *ct, /* Only called for SRC manip */ static int -find_appropriate_src(struct net *net, +find_appropriate_src(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(net, tuple); + unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn_nat *nat; const struct nf_conn *ct; const struct hlist_node *n; @@ -152,7 +154,7 @@ find_appropriate_src(struct net *net, rcu_read_lock(); hlist_for_each_entry_rcu(nat, n, &net->ipv4.nat_bysource[h], bysource) { ct = nat->ct; - if (same_src(ct, tuple)) { + if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { /* Copy source part from reply tuple. */ nf_ct_invert_tuplepr(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); @@ -175,7 +177,7 @@ find_appropriate_src(struct net *net, the ip with the lowest src-ip/dst-ip/proto usage. */ static void -find_best_ips_proto(struct nf_conntrack_tuple *tuple, +find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, const struct nf_nat_range *range, const struct nf_conn *ct, enum nf_nat_manip_type maniptype) @@ -209,7 +211,7 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple, maxip = ntohl(range->max_ip); j = jhash_2words((__force u32)tuple->src.u3.ip, range->flags & IP_NAT_RANGE_PERSISTENT ? - 0 : (__force u32)tuple->dst.u3.ip, 0); + 0 : (__force u32)tuple->dst.u3.ip ^ zone, 0); j = ((u64)j * (maxip - minip + 1)) >> 32; *var_ipp = htonl(minip + j); } @@ -229,6 +231,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, { struct net *net = nf_ct_net(ct); const struct nf_nat_protocol *proto; + u16 zone = nf_ct_zone(ct); /* 1) If this srcip/proto/src-proto-part is currently mapped, and that same mapping gives a unique tuple within the given @@ -239,7 +242,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, manips not an issue. */ if (maniptype == IP_NAT_MANIP_SRC && !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { - if (find_appropriate_src(net, orig_tuple, tuple, range)) { + if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) { pr_debug("get_unique_tuple: Found current src map\n"); if (!nf_nat_used_tuple(tuple, ct)) return; @@ -249,7 +252,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, /* 2) Select the least-used IP/proto combination in the given range. */ *tuple = *orig_tuple; - find_best_ips_proto(tuple, range, ct, maniptype); + find_best_ips_proto(zone, tuple, range, ct, maniptype); /* 3) The per-protocol part of the manip is made to map into the range to make a unique tuple. */ @@ -327,7 +330,8 @@ nf_nat_setup_info(struct nf_conn *ct, if (have_to_hash) { unsigned int srchash; - srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + srchash = hash_by_src(net, nf_ct_zone(ct), + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_lock); /* nf_conntrack_alter_reply might re-allocate exntension aera */ nat = nfct_nat(ct); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 9eb171056c6..4c060038d29 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -74,7 +75,7 @@ static void pptp_nat_expected(struct nf_conn *ct, pr_debug("trying to unexpect other dir: "); nf_ct_dump_tuple_ip(&t); - other_exp = nf_ct_expect_find_get(net, &t); + other_exp = nf_ct_expect_find_get(net, nf_ct_zone(ct), &t); if (other_exp) { nf_ct_unexpect_related(other_exp); nf_ct_expect_put(other_exp); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 55ce22e5de4..996c3f41fec 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -191,15 +192,20 @@ out: static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, struct sk_buff *skb) { + u16 zone = NF_CT_DEFAULT_ZONE; + + if (skb->nfct) + zone = nf_ct_zone((struct nf_conn *)skb->nfct); + #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge && skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP6_DEFRAG_CONNTRACK_BRIDGE_IN; + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; #endif if (hooknum == NF_INET_PRE_ROUTING) - return IP6_DEFRAG_CONNTRACK_IN; + return IP6_DEFRAG_CONNTRACK_IN + zone; else - return IP6_DEFRAG_CONNTRACK_OUT; + return IP6_DEFRAG_CONNTRACK_OUT + zone; } diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index d772dc21857..9be81776415 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -128,7 +129,7 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, } static int -icmpv6_error_message(struct net *net, +icmpv6_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int icmp6off, enum ip_conntrack_info *ctinfo, @@ -137,6 +138,7 @@ icmpv6_error_message(struct net *net, struct nf_conntrack_tuple intuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_l4proto *inproto; + u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; NF_CT_ASSERT(skb->nfct == NULL); @@ -163,7 +165,7 @@ icmpv6_error_message(struct net *net, *ctinfo = IP_CT_RELATED; - h = nf_conntrack_find_get(net, &intuple); + h = nf_conntrack_find_get(net, zone, &intuple); if (!h) { pr_debug("icmpv6_error: no match\n"); return -NF_ACCEPT; @@ -216,7 +218,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; - return icmpv6_error_message(net, skb, dataoff, ctinfo, hooknum); + return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum); } #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 4469d45261f..18d77b5c351 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -83,6 +83,19 @@ config NF_CONNTRACK_SECMARK If unsure, say 'N'. +config NF_CONNTRACK_ZONES + bool 'Connection tracking zones' + depends on NETFILTER_ADVANCED + depends on NETFILTER_XT_TARGET_CT + help + This option enables support for connection tracking zones. + Normally, each connection needs to have a unique system wide + identity. Connection tracking zones allow to have multiple + connections using the same identity, as long as they are + contained in different zones. + + If unsure, say `N'. + config NF_CONNTRACK_EVENTS bool "Connection tracking events" depends on NETFILTER_ADVANCED diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 65351ed5d81..0c9bbe93cc1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -68,7 +69,7 @@ static int nf_conntrack_hash_rnd_initted; static unsigned int nf_conntrack_hash_rnd; static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, - unsigned int size, unsigned int rnd) + u16 zone, unsigned int size, unsigned int rnd) { unsigned int n; u_int32_t h; @@ -79,16 +80,16 @@ static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, */ n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32); h = jhash2((u32 *)tuple, n, - rnd ^ (((__force __u16)tuple->dst.u.all << 16) | - tuple->dst.protonum)); + zone ^ rnd ^ (((__force __u16)tuple->dst.u.all << 16) | + tuple->dst.protonum)); return ((u64)h * size) >> 32; } -static inline u_int32_t hash_conntrack(const struct net *net, +static inline u_int32_t hash_conntrack(const struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { - return __hash_conntrack(tuple, net->ct.htable_size, + return __hash_conntrack(tuple, zone, net->ct.htable_size, nf_conntrack_hash_rnd); } @@ -292,11 +293,12 @@ static void death_by_timeout(unsigned long ul_conntrack) * - Caller must lock nf_conntrack_lock before calling this function */ struct nf_conntrack_tuple_hash * -__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple) +__nf_conntrack_find(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(net, tuple); + unsigned int hash = hash_conntrack(net, zone, tuple); /* Disable BHs the entire time since we normally need to disable them * at least once for the stats anyway. @@ -304,7 +306,8 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple) local_bh_disable(); begin: hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { - if (nf_ct_tuple_equal(tuple, &h->tuple)) { + if (nf_ct_tuple_equal(tuple, &h->tuple) && + nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) { NF_CT_STAT_INC(net, found); local_bh_enable(); return h; @@ -326,21 +329,23 @@ EXPORT_SYMBOL_GPL(__nf_conntrack_find); /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * -nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple) +nf_conntrack_find_get(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; rcu_read_lock(); begin: - h = __nf_conntrack_find(net, tuple); + h = __nf_conntrack_find(net, zone, tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); if (unlikely(nf_ct_is_dying(ct) || !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { - if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) { + if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) || + nf_ct_zone(ct) != zone)) { nf_ct_put(ct); goto begin; } @@ -368,9 +373,11 @@ void nf_conntrack_hash_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; + u16 zone; - hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + zone = nf_ct_zone(ct); + hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); __nf_conntrack_hash_insert(ct, hash, repl_hash); } @@ -387,6 +394,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; + u16 zone; ct = nf_ct_get(skb, &ctinfo); net = nf_ct_net(ct); @@ -398,8 +406,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) return NF_ACCEPT; - hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + zone = nf_ct_zone(ct); + hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); /* We're not in hash table, and we refuse to set up related connections for unconfirmed conns. But packet copies and @@ -418,11 +427,13 @@ __nf_conntrack_confirm(struct sk_buff *skb) not in the hash. If there is, we lost race. */ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - &h->tuple)) + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, - &h->tuple)) + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; /* Remove from unconfirmed list */ @@ -469,15 +480,19 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, struct net *net = nf_ct_net(ignored_conntrack); struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(net, tuple); + struct nf_conn *ct; + u16 zone = nf_ct_zone(ignored_conntrack); + unsigned int hash = hash_conntrack(net, zone, tuple); /* Disable BHs the entire time since we need to disable them at * least once for the stats anyway. */ rcu_read_lock_bh(); hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { - if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack && - nf_ct_tuple_equal(tuple, &h->tuple)) { + ct = nf_ct_tuplehash_to_ctrack(h); + if (ct != ignored_conntrack && + nf_ct_tuple_equal(tuple, &h->tuple) && + nf_ct_zone(ct) == zone) { NF_CT_STAT_INC(net, found); rcu_read_unlock_bh(); return 1; @@ -540,7 +555,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) return dropped; } -struct nf_conn *nf_conntrack_alloc(struct net *net, +struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, gfp_t gfp) @@ -558,7 +573,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { - unsigned int hash = hash_conntrack(net, orig); + unsigned int hash = hash_conntrack(net, zone, orig); if (!early_drop(net, hash)) { atomic_dec(&net->ct.count); if (net_ratelimit()) @@ -595,13 +610,28 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, #ifdef CONFIG_NET_NS ct->ct_net = net; #endif - +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (zone) { + struct nf_conntrack_zone *nf_ct_zone; + + nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, GFP_ATOMIC); + if (!nf_ct_zone) + goto out_free; + nf_ct_zone->id = zone; + } +#endif /* * changes to lookup keys must be done before setting refcnt to 1 */ smp_wmb(); atomic_set(&ct->ct_general.use, 1); return ct; + +#ifdef CONFIG_NF_CONNTRACK_ZONES +out_free: + kmem_cache_free(net->ct.nf_conntrack_cachep, ct); + return ERR_PTR(-ENOMEM); +#endif } EXPORT_SYMBOL_GPL(nf_conntrack_alloc); @@ -631,13 +661,14 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_tuple repl_tuple; struct nf_conntrack_ecache *ecache; struct nf_conntrack_expect *exp; + u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) { pr_debug("Can't invert tuple.\n"); return NULL; } - ct = nf_conntrack_alloc(net, tuple, &repl_tuple, GFP_ATOMIC); + ct = nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC); if (IS_ERR(ct)) { pr_debug("Can't allocate conntrack.\n"); return (struct nf_conntrack_tuple_hash *)ct; @@ -657,7 +688,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, GFP_ATOMIC); spin_lock_bh(&nf_conntrack_lock); - exp = nf_ct_find_expectation(net, tuple); + exp = nf_ct_find_expectation(net, zone, tuple); if (exp) { pr_debug("conntrack: expectation arrives ct=%p exp=%p\n", ct, exp); @@ -713,6 +744,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; + u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, protonum, &tuple, l3proto, @@ -722,7 +754,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, } /* look for tuple match */ - h = nf_conntrack_find_get(net, &tuple); + h = nf_conntrack_find_get(net, zone, &tuple); if (!h) { h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, skb, dataoff); @@ -958,6 +990,14 @@ bool __nf_ct_kill_acct(struct nf_conn *ct, } EXPORT_SYMBOL_GPL(__nf_ct_kill_acct); +#ifdef CONFIG_NF_CONNTRACK_ZONES +static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = { + .len = sizeof(struct nf_conntrack_zone), + .align = __alignof__(struct nf_conntrack_zone), + .id = NF_CT_EXT_ZONE, +}; +#endif + #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) #include @@ -1139,6 +1179,9 @@ static void nf_conntrack_cleanup_init_net(void) nf_conntrack_helper_fini(); nf_conntrack_proto_fini(); +#ifdef CONFIG_NF_CONNTRACK_ZONES + nf_ct_extend_unregister(&nf_ct_zone_extend); +#endif } static void nf_conntrack_cleanup_net(struct net *net) @@ -1214,6 +1257,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) unsigned int hashsize, old_size; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; + struct nf_conn *ct; if (current->nsproxy->net_ns != &init_net) return -EOPNOTSUPP; @@ -1240,8 +1284,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) while (!hlist_nulls_empty(&init_net.ct.hash[i])) { h = hlist_nulls_entry(init_net.ct.hash[i].first, struct nf_conntrack_tuple_hash, hnnode); + ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); - bucket = __hash_conntrack(&h->tuple, hashsize, + bucket = __hash_conntrack(&h->tuple, nf_ct_zone(ct), + hashsize, nf_conntrack_hash_rnd); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } @@ -1299,6 +1345,11 @@ static int nf_conntrack_init_init_net(void) if (ret < 0) goto err_helper; +#ifdef CONFIG_NF_CONNTRACK_ZONES + ret = nf_ct_extend_register(&nf_ct_zone_extend); + if (ret < 0) + goto err_extend; +#endif /* Set up fake conntrack: to never be deleted, not in any hashes */ #ifdef CONFIG_NET_NS nf_conntrack_untracked.ct_net = &init_net; @@ -1309,6 +1360,10 @@ static int nf_conntrack_init_init_net(void) return 0; +#ifdef CONFIG_NF_CONNTRACK_ZONES +err_extend: + nf_conntrack_helper_fini(); +#endif err_helper: nf_conntrack_proto_fini(); err_proto: diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 6182fb1b55d..acb29ccaa41 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -27,6 +27,7 @@ #include #include #include +#include unsigned int nf_ct_expect_hsize __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_expect_hsize); @@ -84,7 +85,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple } struct nf_conntrack_expect * -__nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple) +__nf_ct_expect_find(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; struct hlist_node *n; @@ -95,7 +97,8 @@ __nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple) h = nf_ct_expect_dst_hash(tuple); hlist_for_each_entry_rcu(i, n, &net->ct.expect_hash[h], hnode) { - if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)) + if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && + nf_ct_zone(i->master) == zone) return i; } return NULL; @@ -104,12 +107,13 @@ EXPORT_SYMBOL_GPL(__nf_ct_expect_find); /* Just find a expectation corresponding to a tuple. */ struct nf_conntrack_expect * -nf_ct_expect_find_get(struct net *net, const struct nf_conntrack_tuple *tuple) +nf_ct_expect_find_get(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; rcu_read_lock(); - i = __nf_ct_expect_find(net, tuple); + i = __nf_ct_expect_find(net, zone, tuple); if (i && !atomic_inc_not_zero(&i->use)) i = NULL; rcu_read_unlock(); @@ -121,7 +125,8 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get); /* If an expectation for this connection is found, it gets delete from * global list then returned. */ struct nf_conntrack_expect * -nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple) +nf_ct_find_expectation(struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i, *exp = NULL; struct hlist_node *n; @@ -133,7 +138,8 @@ nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple) h = nf_ct_expect_dst_hash(tuple); hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) { if (!(i->flags & NF_CT_EXPECT_INACTIVE) && - nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)) { + nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && + nf_ct_zone(i->master) == zone) { exp = i; break; } @@ -204,7 +210,8 @@ static inline int expect_matches(const struct nf_conntrack_expect *a, { return a->master == b->master && a->class == b->class && nf_ct_tuple_equal(&a->tuple, &b->tuple) && - nf_ct_tuple_mask_equal(&a->mask, &b->mask); + nf_ct_tuple_mask_equal(&a->mask, &b->mask) && + nf_ct_zone(a->master) == nf_ct_zone(b->master); } /* Generally a bad idea to call this: could have matched already. */ diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 66369490230..a1c8dd917e1 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -29,6 +29,7 @@ #include #include #include +#include #include /* Parameters */ @@ -1216,7 +1217,7 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct, tuple.dst.u.tcp.port = port; tuple.dst.protonum = IPPROTO_TCP; - exp = __nf_ct_expect_find(net, &tuple); + exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple); if (exp && exp->master == ct) return exp; return NULL; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index db35edac307..51089cfe116 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -811,7 +811,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(net, &tuple); + h = nf_conntrack_find_get(net, 0, &tuple); if (!h) return -ENOENT; @@ -872,7 +872,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(net, &tuple); + h = nf_conntrack_find_get(net, 0, &tuple); if (!h) return -ENOENT; @@ -1221,7 +1221,7 @@ ctnetlink_create_conntrack(struct net *net, int err = -EINVAL; struct nf_conntrack_helper *helper; - ct = nf_conntrack_alloc(net, otuple, rtuple, GFP_ATOMIC); + ct = nf_conntrack_alloc(net, 0, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); @@ -1325,7 +1325,7 @@ ctnetlink_create_conntrack(struct net *net, if (err < 0) goto err2; - master_h = nf_conntrack_find_get(net, &master); + master_h = nf_conntrack_find_get(net, 0, &master); if (master_h == NULL) { err = -ENOENT; goto err2; @@ -1374,9 +1374,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(net, &otuple); + h = __nf_conntrack_find(net, 0, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(net, &rtuple); + h = __nf_conntrack_find(net, 0, &rtuple); if (h == NULL) { err = -ENOENT; @@ -1714,7 +1714,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - exp = nf_ct_expect_find_get(net, &tuple); + exp = nf_ct_expect_find_get(net, 0, &tuple); if (!exp) return -ENOENT; @@ -1770,7 +1770,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, return err; /* bump usage count to 2 */ - exp = nf_ct_expect_find_get(net, &tuple); + exp = nf_ct_expect_find_get(net, 0, &tuple); if (!exp) return -ENOENT; @@ -1855,7 +1855,7 @@ ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[], return err; /* Look for master conntrack of this expectation */ - h = nf_conntrack_find_get(net, &master_tuple); + h = nf_conntrack_find_get(net, 0, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); @@ -1912,7 +1912,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, return err; spin_lock_bh(&nf_conntrack_lock); - exp = __nf_ct_expect_find(net, &tuple); + exp = __nf_ct_expect_find(net, 0, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_lock); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 3807ac7faf4..088944824e1 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -123,7 +124,7 @@ static void pptp_expectfn(struct nf_conn *ct, pr_debug("trying to unexpect other dir: "); nf_ct_dump_tuple(&inv_t); - exp_other = nf_ct_expect_find_get(net, &inv_t); + exp_other = nf_ct_expect_find_get(net, nf_ct_zone(ct), &inv_t); if (exp_other) { /* delete other expectation. */ pr_debug("found\n"); @@ -136,17 +137,18 @@ static void pptp_expectfn(struct nf_conn *ct, rcu_read_unlock(); } -static int destroy_sibling_or_exp(struct net *net, +static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct, const struct nf_conntrack_tuple *t) { const struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; struct nf_conn *sibling; + u16 zone = nf_ct_zone(ct); pr_debug("trying to timeout ct or exp for tuple "); nf_ct_dump_tuple(t); - h = nf_conntrack_find_get(net, t); + h = nf_conntrack_find_get(net, zone, t); if (h) { sibling = nf_ct_tuplehash_to_ctrack(h); pr_debug("setting timeout of conntrack %p to 0\n", sibling); @@ -157,7 +159,7 @@ static int destroy_sibling_or_exp(struct net *net, nf_ct_put(sibling); return 1; } else { - exp = nf_ct_expect_find_get(net, t); + exp = nf_ct_expect_find_get(net, zone, t); if (exp) { pr_debug("unexpect_related of expect %p\n", exp); nf_ct_unexpect_related(exp); @@ -182,7 +184,7 @@ static void pptp_destroy_siblings(struct nf_conn *ct) t.dst.protonum = IPPROTO_GRE; t.src.u.gre.key = help->help.ct_pptp_info.pns_call_id; t.dst.u.gre.key = help->help.ct_pptp_info.pac_call_id; - if (!destroy_sibling_or_exp(net, &t)) + if (!destroy_sibling_or_exp(net, ct, &t)) pr_debug("failed to timeout original pns->pac ct/exp\n"); /* try reply (pac->pns) tuple */ @@ -190,7 +192,7 @@ static void pptp_destroy_siblings(struct nf_conn *ct) t.dst.protonum = IPPROTO_GRE; t.src.u.gre.key = help->help.ct_pptp_info.pac_call_id; t.dst.u.gre.key = help->help.ct_pptp_info.pns_call_id; - if (!destroy_sibling_or_exp(net, &t)) + if (!destroy_sibling_or_exp(net, ct, &t)) pr_debug("failed to timeout reply pac->pns ct/exp\n"); } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index fbe8ff5a420..8dd75d90efc 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -23,6 +23,7 @@ #include #include #include +#include #include MODULE_LICENSE("GPL"); @@ -836,7 +837,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, rcu_read_lock(); do { - exp = __nf_ct_expect_find(net, &tuple); + exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple); if (!exp || exp->master == ct || nfct_help(exp->master)->helper != nfct_help(ct)->helper || diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e310f1561bb..24a42efe62e 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -26,6 +26,7 @@ #include #include #include +#include MODULE_LICENSE("GPL"); @@ -171,6 +172,11 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #endif +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (seq_printf(s, "zone=%u ", nf_ct_zone(ct))) + goto release; +#endif + if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) goto release; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 8183a054256..61c50fa8470 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -16,6 +16,7 @@ #include #include #include +#include static unsigned int xt_ct_target(struct sk_buff *skb, const struct xt_target_param *par) @@ -69,11 +70,16 @@ static bool xt_ct_tg_check(const struct xt_tgchk_param *par) goto out; } +#ifndef CONFIG_NF_CONNTRACK_ZONES + if (info->zone) + goto err1; +#endif + if (nf_ct_l3proto_try_module_get(par->family) < 0) goto err1; memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(par->net, &t, &t, GFP_KERNEL); + ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); if (IS_ERR(ct)) goto err2; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 0d9d18ea2b0..26997ce90e4 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -28,6 +28,7 @@ #include #include #include +#include /* we will save the tuples of all connections we care about */ struct xt_connlimit_conn { @@ -114,7 +115,8 @@ static int count_them(struct net *net, /* check the saved connections */ list_for_each_entry_safe(conn, tmp, hash, list) { - found = nf_conntrack_find_get(net, &conn->tuple); + found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE, + &conn->tuple); found_ct = NULL; if (found != NULL) -- cgit v1.2.3 From ef00f89f1eb7e056aab9dfe068521e6f2320c94a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 15 Feb 2010 18:14:57 +0100 Subject: netfilter: ctnetlink: add zone support Parse and dump the conntrack zone in ctnetlink. Signed-off-by: Patrick McHardy --- net/netfilter/nf_conntrack_netlink.c | 92 ++++++++++++++++++++++++++++-------- 1 file changed, 73 insertions(+), 19 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 51089cfe116..8b05f364b2f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -39,6 +39,7 @@ #include #include #include +#include #ifdef CONFIG_NF_NAT_NEEDED #include #include @@ -379,6 +380,9 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, goto nla_put_failure; nla_nest_end(skb, nest_parms); + if (nf_ct_zone(ct)) + NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct))); + if (ctnetlink_dump_status(skb, ct) < 0 || ctnetlink_dump_timeout(skb, ct) < 0 || ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || @@ -517,6 +521,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto nla_put_failure; nla_nest_end(skb, nest_parms); + if (nf_ct_zone(ct)) + NLA_PUT_BE16(skb, CTA_ZONE, htons(nf_ct_zone(ct))); + if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; @@ -750,6 +757,21 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], return 0; } +static int +ctnetlink_parse_zone(const struct nlattr *attr, u16 *zone) +{ + if (attr) +#ifdef CONFIG_NF_CONNTRACK_ZONES + *zone = ntohs(nla_get_be16(attr)); +#else + return -EOPNOTSUPP; +#endif + else + *zone = 0; + + return 0; +} + static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING }, }; @@ -781,6 +803,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_ID] = { .type = NLA_U32 }, [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, + [CTA_ZONE] = { .type = NLA_U16 }, }; static int @@ -794,7 +817,12 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conn *ct; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - int err = 0; + u16 zone; + int err; + + err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); + if (err < 0) + return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); @@ -811,7 +839,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(net, 0, &tuple); + h = nf_conntrack_find_get(net, zone, &tuple); if (!h) return -ENOENT; @@ -856,12 +884,17 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, struct sk_buff *skb2 = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - int err = 0; + u16 zone; + int err; if (nlh->nlmsg_flags & NLM_F_DUMP) return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table, ctnetlink_done); + err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); + if (err < 0) + return err; + if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); else if (cda[CTA_TUPLE_REPLY]) @@ -872,7 +905,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(net, 0, &tuple); + h = nf_conntrack_find_get(net, zone, &tuple); if (!h) return -ENOENT; @@ -1211,7 +1244,7 @@ ctnetlink_change_conntrack(struct nf_conn *ct, } static struct nf_conn * -ctnetlink_create_conntrack(struct net *net, +ctnetlink_create_conntrack(struct net *net, u16 zone, const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, @@ -1221,7 +1254,7 @@ ctnetlink_create_conntrack(struct net *net, int err = -EINVAL; struct nf_conntrack_helper *helper; - ct = nf_conntrack_alloc(net, 0, otuple, rtuple, GFP_ATOMIC); + ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); @@ -1325,7 +1358,7 @@ ctnetlink_create_conntrack(struct net *net, if (err < 0) goto err2; - master_h = nf_conntrack_find_get(net, 0, &master); + master_h = nf_conntrack_find_get(net, zone, &master); if (master_h == NULL) { err = -ENOENT; goto err2; @@ -1358,7 +1391,12 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - int err = 0; + u16 zone; + int err; + + err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); + if (err < 0) + return err; if (cda[CTA_TUPLE_ORIG]) { err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3); @@ -1374,9 +1412,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(net, 0, &otuple); + h = __nf_conntrack_find(net, zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(net, 0, &rtuple); + h = __nf_conntrack_find(net, zone, &rtuple); if (h == NULL) { err = -ENOENT; @@ -1384,7 +1422,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conn *ct; enum ip_conntrack_events events; - ct = ctnetlink_create_conntrack(net, cda, &otuple, + ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) { err = PTR_ERR(ct); @@ -1698,7 +1736,8 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, struct sk_buff *skb2; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - int err = 0; + u16 zone; + int err; if (nlh->nlmsg_flags & NLM_F_DUMP) { return netlink_dump_start(ctnl, skb, nlh, @@ -1706,6 +1745,10 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, ctnetlink_exp_done); } + err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); + if (err < 0) + return err; + if (cda[CTA_EXPECT_MASTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3); else @@ -1714,7 +1757,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - exp = nf_ct_expect_find_get(net, 0, &tuple); + exp = nf_ct_expect_find_get(net, zone, &tuple); if (!exp) return -ENOENT; @@ -1761,16 +1804,21 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct hlist_node *n, *next; u_int8_t u3 = nfmsg->nfgen_family; unsigned int i; + u16 zone; int err; if (cda[CTA_EXPECT_TUPLE]) { /* delete a single expect by tuple */ + err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); if (err < 0) return err; /* bump usage count to 2 */ - exp = nf_ct_expect_find_get(net, 0, &tuple); + exp = nf_ct_expect_find_get(net, zone, &tuple); if (!exp) return -ENOENT; @@ -1832,7 +1880,8 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, } static int -ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[], +ctnetlink_create_expect(struct net *net, u16 zone, + const struct nlattr * const cda[], u_int8_t u3, u32 pid, int report) { @@ -1855,7 +1904,7 @@ ctnetlink_create_expect(struct net *net, const struct nlattr * const cda[], return err; /* Look for master conntrack of this expectation */ - h = nf_conntrack_find_get(net, 0, &master_tuple); + h = nf_conntrack_find_get(net, zone, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); @@ -1900,25 +1949,30 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_expect *exp; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - int err = 0; + u16 zone; + int err; if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK] || !cda[CTA_EXPECT_MASTER]) return -EINVAL; + err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); if (err < 0) return err; spin_lock_bh(&nf_conntrack_lock); - exp = __nf_ct_expect_find(net, 0, &tuple); + exp = __nf_ct_expect_find(net, zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_lock); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - err = ctnetlink_create_expect(net, cda, + err = ctnetlink_create_expect(net, zone, cda, u3, NETLINK_CB(skb).pid, nlmsg_report(nlh)); -- cgit v1.2.3 From 1756de262e41112a8a8927808eb2f03d21fd4786 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 15 Feb 2010 18:15:55 +0100 Subject: netfilter: ebtables: abort if next_offset is too small next_offset must be > 0, otherwise this loops forever. The offset also contains the size of the ebt_entry structure itself, so anything smaller is invalid. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebtables.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bcdf02d866b..4370e968048 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -444,6 +444,8 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, break; if (left < e->next_offset) break; + if (e->next_offset < sizeof(struct ebt_entry)) + return -EINVAL; offset += e->next_offset; } } -- cgit v1.2.3 From fc0e3df4f00a5f62c2f2fce84bf496136b58c474 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 15 Feb 2010 18:16:26 +0100 Subject: netfilter: ebtables: avoid explicit XT_ALIGN() in match/targets This will cause trouble once CONFIG_COMPAT support is added to ebtables. xt_compat_*_offset() calculate the kernel/userland structure size delta using: XT_ALIGN(size) - COMPAT_XT_ALIGN(size) If the match/target sizes are aligned at registration time, delta is always zero. Should have zero effect for existing systems: xtables uses XT_ALIGN() whenever it deals with match/target sizes. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- net/bridge/netfilter/ebt_802_3.c | 2 +- net/bridge/netfilter/ebt_arp.c | 2 +- net/bridge/netfilter/ebt_arpreply.c | 2 +- net/bridge/netfilter/ebt_dnat.c | 2 +- net/bridge/netfilter/ebt_ip.c | 2 +- net/bridge/netfilter/ebt_ip6.c | 2 +- net/bridge/netfilter/ebt_limit.c | 2 +- net/bridge/netfilter/ebt_log.c | 2 +- net/bridge/netfilter/ebt_mark.c | 2 +- net/bridge/netfilter/ebt_mark_m.c | 2 +- net/bridge/netfilter/ebt_nflog.c | 2 +- net/bridge/netfilter/ebt_pkttype.c | 2 +- net/bridge/netfilter/ebt_redirect.c | 2 +- net/bridge/netfilter/ebt_snat.c | 2 +- net/bridge/netfilter/ebt_stp.c | 2 +- net/bridge/netfilter/ebt_ulog.c | 2 +- net/bridge/netfilter/ebt_vlan.c | 2 +- 17 files changed, 17 insertions(+), 17 deletions(-) (limited to 'net') diff --git a/net/bridge/netfilter/ebt_802_3.c b/net/bridge/netfilter/ebt_802_3.c index bd91dc58d49..5d1176758ca 100644 --- a/net/bridge/netfilter/ebt_802_3.c +++ b/net/bridge/netfilter/ebt_802_3.c @@ -52,7 +52,7 @@ static struct xt_match ebt_802_3_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_802_3_mt, .checkentry = ebt_802_3_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_802_3_info)), + .matchsize = sizeof(struct ebt_802_3_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_arp.c b/net/bridge/netfilter/ebt_arp.c index b7ad60419f9..e727697c584 100644 --- a/net/bridge/netfilter/ebt_arp.c +++ b/net/bridge/netfilter/ebt_arp.c @@ -120,7 +120,7 @@ static struct xt_match ebt_arp_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_arp_mt, .checkentry = ebt_arp_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_arp_info)), + .matchsize = sizeof(struct ebt_arp_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_arpreply.c b/net/bridge/netfilter/ebt_arpreply.c index 76584cd72e5..f392e9d93f5 100644 --- a/net/bridge/netfilter/ebt_arpreply.c +++ b/net/bridge/netfilter/ebt_arpreply.c @@ -78,7 +78,7 @@ static struct xt_target ebt_arpreply_tg_reg __read_mostly = { .hooks = (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_PRE_ROUTING), .target = ebt_arpreply_tg, .checkentry = ebt_arpreply_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_arpreply_info)), + .targetsize = sizeof(struct ebt_arpreply_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 6b49ea9e31f..2bb40d728a3 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -54,7 +54,7 @@ static struct xt_target ebt_dnat_tg_reg __read_mostly = { (1 << NF_BR_LOCAL_OUT) | (1 << NF_BR_BROUTING), .target = ebt_dnat_tg, .checkentry = ebt_dnat_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_nat_info)), + .targetsize = sizeof(struct ebt_nat_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_ip.c b/net/bridge/netfilter/ebt_ip.c index d771bbfbcbe..5de6df6f86b 100644 --- a/net/bridge/netfilter/ebt_ip.c +++ b/net/bridge/netfilter/ebt_ip.c @@ -110,7 +110,7 @@ static struct xt_match ebt_ip_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_ip_mt, .checkentry = ebt_ip_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_ip_info)), + .matchsize = sizeof(struct ebt_ip_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c index 784a6573876..bbf2534ef02 100644 --- a/net/bridge/netfilter/ebt_ip6.c +++ b/net/bridge/netfilter/ebt_ip6.c @@ -122,7 +122,7 @@ static struct xt_match ebt_ip6_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_ip6_mt, .checkentry = ebt_ip6_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_ip6_info)), + .matchsize = sizeof(struct ebt_ip6_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_limit.c b/net/bridge/netfilter/ebt_limit.c index f7bd9192ff0..9dd16e6b10e 100644 --- a/net/bridge/netfilter/ebt_limit.c +++ b/net/bridge/netfilter/ebt_limit.c @@ -90,7 +90,7 @@ static struct xt_match ebt_limit_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_limit_mt, .checkentry = ebt_limit_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_limit_info)), + .matchsize = sizeof(struct ebt_limit_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index e4ea3fdd1d4..e873924ddb5 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -195,7 +195,7 @@ static struct xt_target ebt_log_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_log_tg, .checkentry = ebt_log_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_log_info)), + .targetsize = sizeof(struct ebt_log_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_mark.c b/net/bridge/netfilter/ebt_mark.c index 2fee7e8e2e9..153e167374a 100644 --- a/net/bridge/netfilter/ebt_mark.c +++ b/net/bridge/netfilter/ebt_mark.c @@ -59,7 +59,7 @@ static struct xt_target ebt_mark_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_mark_tg, .checkentry = ebt_mark_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_mark_t_info)), + .targetsize = sizeof(struct ebt_mark_t_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_mark_m.c b/net/bridge/netfilter/ebt_mark_m.c index ea570f214b1..89abf403039 100644 --- a/net/bridge/netfilter/ebt_mark_m.c +++ b/net/bridge/netfilter/ebt_mark_m.c @@ -41,7 +41,7 @@ static struct xt_match ebt_mark_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_mark_mt, .checkentry = ebt_mark_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_mark_m_info)), + .matchsize = sizeof(struct ebt_mark_m_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index 2a63d996dd4..40dbd248b9a 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -51,7 +51,7 @@ static struct xt_target ebt_nflog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_nflog_tg, .checkentry = ebt_nflog_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_nflog_info)), + .targetsize = sizeof(struct ebt_nflog_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_pkttype.c b/net/bridge/netfilter/ebt_pkttype.c index 883e96e2a54..e2a07e6cbef 100644 --- a/net/bridge/netfilter/ebt_pkttype.c +++ b/net/bridge/netfilter/ebt_pkttype.c @@ -36,7 +36,7 @@ static struct xt_match ebt_pkttype_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_pkttype_mt, .checkentry = ebt_pkttype_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_pkttype_info)), + .matchsize = sizeof(struct ebt_pkttype_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index c8a49f7a57b..9be8fbcd370 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -59,7 +59,7 @@ static struct xt_target ebt_redirect_tg_reg __read_mostly = { (1 << NF_BR_BROUTING), .target = ebt_redirect_tg, .checkentry = ebt_redirect_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_redirect_info)), + .targetsize = sizeof(struct ebt_redirect_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 8d04d4c302b..9c7b520765a 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -67,7 +67,7 @@ static struct xt_target ebt_snat_tg_reg __read_mostly = { .hooks = (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_POST_ROUTING), .target = ebt_snat_tg, .checkentry = ebt_snat_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_nat_info)), + .targetsize = sizeof(struct ebt_nat_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 75e29a9cebd..92a93d36376 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -177,7 +177,7 @@ static struct xt_match ebt_stp_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_stp_mt, .checkentry = ebt_stp_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_stp_info)), + .matchsize = sizeof(struct ebt_stp_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index ce50688a643..c6ac657074a 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -275,7 +275,7 @@ static struct xt_target ebt_ulog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_ulog_tg, .checkentry = ebt_ulog_tg_check, - .targetsize = XT_ALIGN(sizeof(struct ebt_ulog_info)), + .targetsize = sizeof(struct ebt_ulog_info), .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c index 3dddd489328..be1dd2e1f61 100644 --- a/net/bridge/netfilter/ebt_vlan.c +++ b/net/bridge/netfilter/ebt_vlan.c @@ -163,7 +163,7 @@ static struct xt_match ebt_vlan_mt_reg __read_mostly = { .family = NFPROTO_BRIDGE, .match = ebt_vlan_mt, .checkentry = ebt_vlan_mt_check, - .matchsize = XT_ALIGN(sizeof(struct ebt_vlan_info)), + .matchsize = sizeof(struct ebt_vlan_info), .me = THIS_MODULE, }; -- cgit v1.2.3 From 3e5e524ffb5fcf2447eb5dd9f8e54ad22dd9baa7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 15 Feb 2010 18:17:10 +0100 Subject: netfilter: CONFIG_COMPAT: allow delta to exceed 32767 with 32 bit userland and 64 bit kernels, it is unlikely but possible that insertion of new rules fails even tough there are only about 2000 iptables rules. This happens because the compat delta is using a short int. Easily reproducible via "iptables -m limit" ; after about 2050 rules inserting new ones fails with -ELOOP. Note that compat_delta included 2 bytes of padding on x86_64, so structure size remains the same. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- net/netfilter/x_tables.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 69c56287d51..0a12cedfe9e 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -39,7 +39,7 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); struct compat_delta { struct compat_delta *next; unsigned int offset; - short delta; + int delta; }; struct xt_af { @@ -439,10 +439,10 @@ void xt_compat_flush_offsets(u_int8_t af) } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); -short xt_compat_calc_jump(u_int8_t af, unsigned int offset) +int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { struct compat_delta *tmp; - short delta; + int delta; for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next) if (tmp->offset < offset) -- cgit v1.2.3