Netfilter zone directions
Subsystems (4)
PATCH v2 1/3 netfilter: nf_conntrack: push zone object into functions
In reply to Daniel BorkmannThis patch replaces the zone id which is pushed down into functions with the actual zone object. It's a bigger one-time change, but needed for later on extending zones with a direction parameter, and thus decoupling this additional information from all call-sites.
It was suggested during NFWS to let the nf_ct_zone() helper store the meta data on the stack as we currently do, but in a similar fashion as skb_header_pointer() does, so we can avoid keeping track of the object lifetime. In general, dealing directly with the object also facilitates for adding other possible meta data in future.
No functional changes in this patch.
--- include/net/netfilter/nf_conntrack.h | 6 +- include/net/netfilter/nf_conntrack_core.h | 3 +- include/net/netfilter/nf_conntrack_expect.h | 11 +++- include/net/netfilter/nf_conntrack_zones.h | 44 +++++++++++--- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 4 +- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 3 +- net/ipv4/netfilter/nf_defrag_ipv4.c | 18 +++--- net/ipv4/netfilter/nf_nat_pptp.c | 3 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 3 +- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 4 +- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 19 +++--- net/netfilter/ipvs/ip_vs_nfct.c | 5 +- net/netfilter/nf_conntrack_core.c | 74 ++++++++++++++--------- net/netfilter/nf_conntrack_expect.c | 22 ++++--- net/netfilter/nf_conntrack_h323_main.c | 4 +- net/netfilter/nf_conntrack_netlink.c | 84 ++++++++++++++------------ net/netfilter/nf_conntrack_pptp.c | 7 ++- net/netfilter/nf_conntrack_sip.c | 3 +- net/netfilter/nf_conntrack_standalone.c | 19 ++++-- net/netfilter/nf_nat_core.c | 22 ++++--- net/netfilter/nf_synproxy_core.c | 6 +- net/netfilter/xt_CT.c | 5 +- net/netfilter/xt_connlimit.c | 13 ++-- net/sched/act_connmark.c | 4 +- 24 files changed, 245 insertions(+), 141 deletions(-)
include/net/netfilter/nf_conntrack.h +5 -1
@@ -250,8 +250,12 @@ void nf_ct_untracked_status_or(unsigned long bits);void nf_ct_iterate_cleanup (struct net *net,int (*iter)(struct nf_conn *i,void *data),void *data,u32 portid,int report); + +struct nf_conntrack_zone ; +void nf_conntrack_free (struct nf_conn *ct); -struct nf_conn *nf_conntrack_alloc (struct net *net,u16 zone, +struct nf_conn *nf_conntrack_alloc (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *orig,const struct nf_conntrack_tuple *repl,gfp_t gfp);
include/net/netfilter/nf_conntrack_core.h +2 -1
@@ -52,7 +52,8 @@ bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,/* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * -nf_conntrack_find_get (struct net *net,u16 zone, +nf_conntrack_find_get (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple);int __nf_conntrack_confirm (struct sk_buff *skb);
include/net/netfilter/nf_conntrack_expect.h +8 -3
@@ -4,7 +4,9 @@#ifndef _NF_CONNTRACK_EXPECT_H#define _NF_CONNTRACK_EXPECT_H +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_zones.h> extern unsigned int nf_ct_expect_hsize;extern unsigned int nf_ct_expect_max;
@@ -76,15 +78,18 @@ int nf_conntrack_expect_init(void);void nf_conntrack_expect_fini (void );struct nf_conntrack_expect * -__nf_ct_expect_find (struct net *net,u16 zone, +__nf_ct_expect_find (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple);struct nf_conntrack_expect * -nf_ct_expect_find_get (struct net *net,u16 zone, +nf_ct_expect_find_get (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple);struct nf_conntrack_expect * -nf_ct_find_expectation (struct net *net,u16 zone, +nf_ct_find_expectation (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple); void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
include/net/netfilter/nf_conntrack_zones.h +36 -8
59 lines not on this page · raw message
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +3 -1
@@ -259,6 +259,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)const struct inet_sock *inet =inet_sk (sk);const struct nf_conntrack_tuple_hash *h;struct nf_conntrack_tuple tuple; +struct nf_conntrack_zone zone;memset (&tuple,0 ,sizeof (tuple)); tuple.src.u3.ip = inet->inet_rcv_saddr;
@@ -280,7 +281,8 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)return -EINVAL ; } - h =nf_conntrack_find_get (sock_net (sk),NF_CT_DEFAULT_ZONE , &tuple); + h =nf_conntrack_find_get (sock_net (sk),nf_ct_zone_dflt (&zone), + &tuple);if (h) {struct sockaddr_in sin;struct nf_conn *ct =nf_ct_tuplehash_to_ctrack (h);
net/ipv4/netfilter/nf_conntrack_proto_icmp.c +2 -1
@@ -134,9 +134,10 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,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 ; +struct nf_conntrack_zone *zone, __zone;NF_CT_ASSERT (skb->nfct ==NULL ); + zone =nf_ct_zone_tmpl (tmpl, &__zone);/* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb,
net/ipv4/netfilter/nf_defrag_ipv4.c +10 -8
@@ -43,22 +43,24 @@ 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 ; - +u16 zone_id =NF_CT_DEFAULT_ZONE ;#if IS_ENABLED (CONFIG_NF_CONNTRACK ) -if (skb->nfct) - zone =nf_ct_zone ((struct nf_conn *)skb->nfct); -#endif +if (skb->nfct) { +struct nf_conntrack_zone *zone, __zone; + zone =nf_ct_zone ((struct nf_conn *)skb->nfct, &__zone); + zone_id = zone->id; + } +#endif #if IS_ENABLED (CONFIG_BRIDGE_NETFILTER )if (skb->nf_bridge && skb->nf_bridge->mask &BRNF_NF_BRIDGE_PREROUTING ) -return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone; +return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;#endif if (hooknum ==NF_INET_PRE_ROUTING ) -return IP_DEFRAG_CONNTRACK_IN + zone; +return IP_DEFRAG_CONNTRACK_IN + zone_id;else -return IP_DEFRAG_CONNTRACK_OUT + zone; +return IP_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
net/ipv4/netfilter/nf_nat_pptp.c +2 -1
@@ -48,6 +48,7 @@ static void pptp_nat_expected(struct nf_conn *ct,struct nf_conntrack_tuple t;const struct nf_ct_pptp_master *ct_pptp_info;const struct nf_nat_pptp *nat_pptp_info; +struct nf_conntrack_zone zone;struct nf_nat_range range; ct_pptp_info =nfct_help_data (master);
@@ -76,7 +77,7 @@ 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,nf_ct_zone (ct), &t); + other_exp =nf_ct_expect_find_get (net,nf_ct_zone (ct, &zone), &t);if (other_exp) {nf_ct_unexpect_related (other_exp);nf_ct_expect_put (other_exp);
net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +2 -1
@@ -235,6 +235,7 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)const struct inet_sock *inet =inet_sk (sk);const struct ipv6_pinfo *inet6 =inet6_sk (sk);const struct nf_conntrack_tuple_hash *h; +struct nf_conntrack_zone zone;struct sockaddr_in6 sin6;struct nf_conntrack_tuple tuple = { .src.l3num =NFPROTO_IPV6 };struct nf_conn *ct;
@@ -251,7 +252,7 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)if (*len <0 || (unsigned int ) *len <sizeof (sin6))return -EINVAL ; - h =nf_conntrack_find_get (sock_net (sk),NF_CT_DEFAULT_ZONE , &tuple); + h =nf_conntrack_find_get (sock_net (sk),nf_ct_zone_dflt (&zone), &tuple);if (!h) { pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +2 -2
@@ -150,7 +150,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,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 ; +struct nf_conntrack_zone zone;NF_CT_ASSERT (skb->nfct ==NULL );
@@ -177,7 +177,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, *ctinfo =IP_CT_RELATED ; - h =nf_conntrack_find_get (net, zone, &intuple); + h =nf_conntrack_find_get (net,nf_ct_zone_tmpl (tmpl, &zone), &intuple);if (!h) {pr_debug ("icmpv6_error: no match\n" );return -NF_ACCEPT ;
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +10 -9
@@ -33,23 +33,24 @@static enum ip6_defrag_users nf_ct6_defrag_user (unsigned int hooknum,struct sk_buff *skb) { -u16 zone =NF_CT_DEFAULT_ZONE ; - +u16 zone_id =NF_CT_DEFAULT_ZONE ;#if IS_ENABLED (CONFIG_NF_CONNTRACK ) -if (skb->nfct) - zone =nf_ct_zone ((struct nf_conn *)skb->nfct); -#endif +if (skb->nfct) { +struct nf_conntrack_zone *zone, __zone; + zone =nf_ct_zone ((struct nf_conn *)skb->nfct, &__zone); + zone_id = zone->id; + } +#endif #if IS_ENABLED (CONFIG_BRIDGE_NETFILTER )if (skb->nf_bridge && skb->nf_bridge->mask &BRNF_NF_BRIDGE_PREROUTING ) -return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; +return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;#endif if (hooknum ==NF_INET_PRE_ROUTING ) -return IP6_DEFRAG_CONNTRACK_IN + zone; +return IP6_DEFRAG_CONNTRACK_IN + zone_id;else -return IP6_DEFRAG_CONNTRACK_OUT + zone; - +return IP6_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
net/netfilter/ipvs/ip_vs_nfct.c +3 -2
@@ -256,8 +256,9 @@ EXPORT_SYMBOL(ip_vs_nfct_expect_related);void ip_vs_conn_drop_conntrack (struct ip_vs_conn *cp) {struct nf_conntrack_tuple_hash *h; -struct nf_conn *ct;struct nf_conntrack_tuple tuple; +struct nf_conntrack_zone zone; +struct nf_conn *ct;if (!cp->cport)return ;
@@ -274,7 +275,7 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)" for conn " FMT_CONN "\n" , __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); - h =nf_conntrack_find_get (ip_vs_conn_net (cp),NF_CT_DEFAULT_ZONE , + h =nf_conntrack_find_get (ip_vs_conn_net (cp),nf_ct_zone_dflt (&zone), &tuple);if (h) { ct =nf_ct_tuplehash_to_ctrack (h);
net/netfilter/nf_conntrack_core.c +44 -30
257 lines not on this page · raw message
net/netfilter/nf_conntrack_expect.c +14 -8
@@ -88,7 +88,8 @@ 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,u16 zone, +__nf_ct_expect_find (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple) {struct nf_conntrack_expect *i;
@@ -100,16 +101,18 @@ __nf_ct_expect_find(struct net *net, u16 zone, h =nf_ct_expect_dst_hash (tuple);hlist_for_each_entry_rcu (i, &net->ct.expect_hash[h], hnode) {if (nf_ct_tuple_mask_cmp (tuple, &i->tuple, &i->mask) && -nf_ct_zone (i->master) == zone) +nf_ct_zone_equal (i->master, zone))return i; } +return NULL ; }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,u16 zone, +nf_ct_expect_find_get (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple) {struct nf_conntrack_expect *i;
@@ -127,7 +130,8 @@ 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,u16 zone, +nf_ct_find_expectation (struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple) {struct nf_conntrack_expect *i, *exp =NULL ;
@@ -140,7 +144,7 @@ nf_ct_find_expectation(struct net *net, u16 zone,hlist_for_each_entry (i, &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_zone (i->master) == zone) { +nf_ct_zone_equal (i->master, zone)) { exp = i;break ; }
@@ -225,10 +229,12 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,static inline int expect_matches (const struct nf_conntrack_expect *a,const struct nf_conntrack_expect *b) { +struct nf_conntrack_zone b_zone; +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_zone (a->master) ==nf_ct_zone (b->master); +nf_ct_tuple_equal (&a->tuple, &b->tuple) && +nf_ct_tuple_mask_equal (&a->mask, &b->mask) && +nf_ct_zone_equal (a->master,nf_ct_zone (b->master, &b_zone)); }/* Generally a bad idea to call this: could have matched already. */
net/netfilter/nf_conntrack_h323_main.c +3 -1
@@ -1259,6 +1259,7 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct,struct net *net =nf_ct_net (ct);struct nf_conntrack_expect *exp;struct nf_conntrack_tuple tuple; +struct nf_conntrack_zone zone;memset (&tuple.src.u3,0 ,sizeof (tuple.src.u3)); tuple.src.u.tcp.port =0 ;
@@ -1266,9 +1267,10 @@ 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,nf_ct_zone (ct), &tuple); + exp =__nf_ct_expect_find (net,nf_ct_zone (ct, &zone), &tuple);if (exp && exp->master == ct)return exp; +return NULL ; }
net/netfilter/nf_conntrack_netlink.c +44 -40
240 lines not on this page · raw message
net/netfilter/nf_conntrack_pptp.c +5 -2
@@ -120,13 +120,15 @@ static void pptp_expectfn(struct nf_conn *ct,else {struct nf_conntrack_tuple inv_t;struct nf_conntrack_expect *exp_other; +struct nf_conntrack_zone zone;/* obviously this tuple inversion only works until you do NAT */ nf_ct_invert_tuplepr (&inv_t, &exp->tuple);pr_debug ("trying to unexpect other dir: " );nf_ct_dump_tuple (&inv_t); - exp_other =nf_ct_expect_find_get (net,nf_ct_zone (ct), &inv_t); + exp_other =nf_ct_expect_find_get (net,nf_ct_zone (ct, &zone), + &inv_t);if (exp_other) {/* delete other expectation. */ pr_debug ("found\n" );
@@ -143,13 +145,14 @@ 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_zone *zone, __zone;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); + zone =nf_ct_zone (ct, &__zone); h =nf_conntrack_find_get (net, zone, t);if (h) { sibling =nf_ct_tuplehash_to_ctrack (h);
net/netfilter/nf_conntrack_sip.c +2 -1
@@ -888,8 +888,9 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,rcu_read_lock (); do { - exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple); + struct nf_conntrack_zone zone; + exp = __nf_ct_expect_find(net, nf_ct_zone(ct, &zone), &tuple); if (!exp || exp->master == ct || nfct_help(exp->master)->helper != nfct_help(ct)->helper || exp->class != class)
net/netfilter/nf_conntrack_standalone.c +14 -5
@@ -140,6 +140,19 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) }#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES +static void ct_show_zone (struct seq_file *s,const struct nf_conn *ct) +{ +struct nf_conntrack_zone __zone, *zone =nf_ct_zone (ct, &__zone); + +seq_printf (s,"zone=%u " , zone->id); +} +#else +static inline void ct_show_zone (struct seq_file *s,const struct nf_conn *ct) +{ +} +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP static void ct_show_delta_time (struct seq_file *s,const struct nf_conn *ct) {
@@ -228,11 +241,7 @@ static int ct_seq_show(struct seq_file *s, void *v)#endif ct_show_secctx (s, ct); - -#ifdef CONFIG_NF_CONNTRACK_ZONES -seq_printf (s,"zone=%u " ,nf_ct_zone (ct)); -#endif - +ct_show_zone (s, ct);ct_show_delta_time (s, ct);seq_printf (s,"use=%u\n" ,atomic_read (&ct->ct_general.use));
net/netfilter/nf_nat_core.c +14 -8
@@ -118,14 +118,15 @@ EXPORT_SYMBOL(nf_xfrm_me_harder);/* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int -hash_by_src (const struct net *net,u16 zone, +hash_by_src (const struct net *net, +const struct nf_conntrack_zone *zone,const struct nf_conntrack_tuple *tuple) {unsigned int hash;/* Original src, to ensure we map it consistently if poss. */ hash =jhash2 ((u32 *)&tuple->src,sizeof (tuple->src) /sizeof (u32), - tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd); + tuple->dst.protonum ^ zone->id ^ nf_conntrack_hash_rnd);return reciprocal_scale (hash, net->ct.nat_htable_size); }
@@ -185,7 +186,8 @@ same_src(const struct nf_conn *ct,/* Only called for SRC manip */ static int -find_appropriate_src(struct net *net, u16 zone, +find_appropriate_src(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_nat_l3proto *l3proto, const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *tuple,
@@ -198,7 +200,7 @@ find_appropriate_src(struct net *net, u16 zone,hlist_for_each_entry_rcu (nat, &net->ct.nat_bysource[h], bysource) { ct = nat->ct; -if (same_src (ct, tuple) &&nf_ct_zone (ct) == zone) { +if (same_src (ct, tuple) &&nf_ct_zone_equal (ct, zone)) {/* Copy source part from reply tuple. */ nf_ct_invert_tuplepr (result, &ct->tuplehash[IP_CT_DIR_REPLY ].tuple);
@@ -218,7 +220,8 @@ find_appropriate_src(struct net *net, u16 zone,* the ip with the lowest src-ip/dst-ip/proto usage. */ static void -find_best_ips_proto (u16 zone,struct nf_conntrack_tuple *tuple, +find_best_ips_proto (const struct nf_conntrack_zone *zone, +struct nf_conntrack_tuple *tuple,const struct nf_nat_range *range,const struct nf_conn *ct,enum nf_nat_manip_type maniptype)
@@ -258,7 +261,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,*/ j =jhash2 ((u32 *)&tuple->src.u3,sizeof (tuple->src.u3) /sizeof (u32), range->flags &NF_NAT_RANGE_PERSISTENT ? -0 : (__force u32 )tuple->dst.u3.all[max] ^ zone); +0 : (__force u32 )tuple->dst.u3.all[max] ^ zone->id); full_range = false;for (i =0 ; i <= max; i++) {
@@ -297,10 +300,12 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,struct nf_conn *ct, enum nf_nat_manip_type maniptype) { + struct nf_conntrack_zone *zone, __zone;const struct nf_nat_l3proto *l3proto;const struct nf_nat_l4proto *l4proto;struct net *net =nf_ct_net (ct); -u16 zone =nf_ct_zone (ct); + + zone =nf_ct_zone (ct, &__zone);rcu_read_lock (); l3proto =__nf_nat_l3proto_find (orig_tuple->src.l3num);
@@ -418,9 +423,10 @@ nf_nat_setup_info(struct nf_conn *ct, }if (maniptype ==NF_NAT_MANIP_SRC ) { +struct nf_conntrack_zone zone;unsigned int srchash; - srchash =hash_by_src (net,nf_ct_zone (ct), + srchash =hash_by_src (net,nf_ct_zone (ct, &zone), &ct->tuplehash[IP_CT_DIR_ORIGINAL ].tuple);spin_lock_bh (&nf_nat_lock);/* nf_conntrack_alter_reply might re-allocate extension aera */
net/netfilter/nf_synproxy_core.c +5 -1
@@ -17,10 +17,12 @@#include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_tcpudp.h> #include <linux/netfilter/xt_SYNPROXY.h> +#include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> +#include <net/netfilter/nf_conntrack_zones.h> int synproxy_net_id;EXPORT_SYMBOL_GPL (synproxy_net_id);
@@ -349,12 +351,14 @@ static void __net_exit synproxy_proc_exit(struct net *net)static int __net_init synproxy_net_init (struct net *net) {struct synproxy_net *snet =synproxy_pernet (net); +struct nf_conntrack_zone zone;struct nf_conntrack_tuple t;struct nf_conn *ct;int err = -ENOMEM ;memset (&t,0 ,sizeof (t)); - ct =nf_conntrack_alloc (net,0 , &t, &t,GFP_KERNEL ); + ct =nf_conntrack_alloc (net,nf_ct_zone_dflt (&zone), + &t, &t,GFP_KERNEL );if (IS_ERR (ct)) { err =PTR_ERR (ct); goto err1;
net/netfilter/xt_CT.c +4 -1
@@ -184,6 +184,7 @@ out:static int xt_ct_tg_check (const struct xt_tgchk_param *par,struct xt_ct_target_info_v1 *info) { +struct nf_conntrack_zone zone;struct nf_conntrack_tuple t;struct nf_conn *ct;int ret = -EOPNOTSUPP ;
@@ -203,7 +204,9 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err1;memset (&t,0 ,sizeof (t)); - ct =nf_conntrack_alloc (par->net, info->zone, &t, &t,GFP_KERNEL ); + zone.id = info->zone; + + ct =nf_conntrack_alloc (par->net, &zone, &t, &t,GFP_KERNEL ); ret =PTR_ERR (ct);if (IS_ERR (ct)) goto err2;
net/netfilter/xt_connlimit.c +8 -5
@@ -134,7 +134,7 @@ static bool add_hlist(struct hlist_head *head,static unsigned int check_hlist (struct net *net,struct hlist_head *head,const struct nf_conntrack_tuple *tuple, -u16 zone, +const struct nf_conntrack_zone *zone,bool *addit) {const struct nf_conntrack_tuple_hash *found;
@@ -201,7 +201,7 @@ static unsigned int count_tree(struct net *net, struct rb_root *root, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, - u8 family, u16 zone) + u8 family, const struct nf_conntrack_zone *zone) { struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];struct rb_node **rbnode, *parent;
@@ -290,7 +290,8 @@ static int count_them(struct net *net,const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, - u_int8_t family, u16 zone) + u_int8_t family, + const struct nf_conntrack_zone *zone) { struct rb_root *root;int count;
@@ -321,15 +322,17 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)union nf_inet_addr addr;struct nf_conntrack_tuple tuple;const struct nf_conntrack_tuple *tuple_ptr = &tuple; +struct nf_conntrack_zone *zone, __zone;enum ip_conntrack_info ctinfo;const struct nf_conn *ct;unsigned int connections; -u16 zone =NF_CT_DEFAULT_ZONE ; + + zone =nf_ct_zone_dflt (&__zone); ct =nf_ct_get (skb, &ctinfo);if (ct !=NULL ) { tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL ].tuple; - zone =nf_ct_zone (ct); + zone =nf_ct_zone (ct, &__zone); }else if (!nf_ct_get_tuplepr (skb,skb_network_offset (skb), par->family, &tuple)) { goto hotdrop;
net/sched/act_connmark.c +3 -1
@@ -37,6 +37,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,struct nf_conntrack_tuple tuple;enum ip_conntrack_info ctinfo;struct tcf_connmark_info *ca = a->priv; +struct nf_conntrack_zone zone;struct nf_conn *c;int proto;
@@ -70,7 +71,8 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, proto, &tuple)) goto out; - thash =nf_conntrack_find_get (dev_net (skb->dev), ca->zone, &tuple); + zone.id = ca->zone; + thash =nf_conntrack_find_get (dev_net (skb->dev), &zone, &tuple);if (!thash) goto out;
Signature · 1 line
1.9.3
PATCH v2 3/3 netfilter: nf_conntrack: add efficient mark to zone mapping
In reply to Daniel BorkmannThis work adds the possibility of deriving the zone id from the skb->mark field in a scalable manner. This allows for having only a single template serving 100s .. 1000s of different zones, for example, instead of needing to have one match for each zone as an extra CT jump target. Note that we'd need to have this information attached to the template as at the time when we're trying to lookup a possible ct object, we already need to know zone information for a possible match when going into __nf_conntrack_find_get(). This work provides a minimal implementation for a possible mapping.
--- include/net/netfilter/nf_conntrack_zones.h | 14 ++++++++++++-- include/uapi/linux/netfilter/nf_conntrack_common.h | 4 ++++ include/uapi/linux/netfilter/xt_CT.h | 4 +++- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 2 +- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 3 ++- net/netfilter/nf_conntrack_core.c | 4 ++-- net/netfilter/xt_CT.c | 8 ++++++-- 7 files changed, 30 insertions(+), 9 deletions(-)
include/net/netfilter/nf_conntrack_zones.h +12 -2
@@ -48,9 +48,19 @@ nf_ct_zone(const struct nf_conn *ct, struct nf_conntrack_zone *ptr) }static inline struct nf_conntrack_zone * -nf_ct_zone_tmpl (const struct nf_conn *tmpl,struct nf_conntrack_zone *ptr) +nf_ct_zone_tmpl (const struct nf_conn *tmpl,const struct sk_buff *skb, +struct nf_conntrack_zone *ptr) { -return tmpl ?nf_ct_zone (tmpl, ptr) :nf_ct_zone_dflt (ptr); +struct nf_conntrack_zone *zone; + +if (!tmpl) +return nf_ct_zone_dflt (ptr); + + zone =nf_ct_zone (tmpl, ptr); +if (tmpl->status &IPS_TEMPLATE_MARK ) + zone->id = skb->mark; + +return zone; } static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone,
include/uapi/linux/netfilter/nf_conntrack_common.h +4 -0
@@ -91,6 +91,10 @@ enum ip_conntrack_status {/* Conntrack got a helper explicitly attached via CT target. */ IPS_HELPER_BIT =13 ,IPS_HELPER = (1 <<IPS_HELPER_BIT ), + +/* Template is marked dynamically. */ +IPS_TEMPLATE_MARK_BIT =14 , + IPS_TEMPLATE_MARK = (1 << IPS_TEMPLATE_MARK_BIT), };/* Connection tracking event types */
include/uapi/linux/netfilter/xt_CT.h +3 -1
@@ -8,9 +8,11 @@ enum {XT_CT_NOTRACK_ALIAS =1 <<1 ,XT_CT_ZONE_DIR_ORIG =1 <<2 ,XT_CT_ZONE_DIR_REPL =1 <<3 , +XT_CT_ZONE_MARK =1 <<4 ,XT_CT_MASK =XT_CT_NOTRACK |XT_CT_NOTRACK_ALIAS | - XT_CT_ZONE_DIR_ORIG | XT_CT_ZONE_DIR_REPL, +XT_CT_ZONE_DIR_ORIG |XT_CT_ZONE_DIR_REPL | + XT_CT_ZONE_MARK, }; struct xt_ct_target_info {
net/ipv4/netfilter/nf_conntrack_proto_icmp.c +1 -1
@@ -137,7 +137,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,struct nf_conntrack_zone *zone, __zone;NF_CT_ASSERT (skb->nfct ==NULL ); - zone =nf_ct_zone_tmpl (tmpl, &__zone); + zone =nf_ct_zone_tmpl (tmpl, skb, &__zone);/* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb,
net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +2 -1
@@ -177,7 +177,8 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, *ctinfo =IP_CT_RELATED ; - h =nf_conntrack_find_get (net,nf_ct_zone_tmpl (tmpl, &zone), &intuple); + h =nf_conntrack_find_get (net,nf_ct_zone_tmpl (tmpl, skb, &zone), + &intuple);if (!h) {pr_debug ("icmpv6_error: no match\n" );return -NF_ACCEPT ;
net/netfilter/nf_conntrack_core.c +2 -2
@@ -919,7 +919,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,return NULL ; } - zone =nf_ct_zone_tmpl (tmpl, &__zone); + zone =nf_ct_zone_tmpl (tmpl, skb, &__zone); ct =__nf_conntrack_alloc (net, zone, tuple, &repl_tuple,GFP_ATOMIC , hash);if (IS_ERR (ct))
@@ -1028,7 +1028,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, }/* look for tuple match */ - zone =nf_ct_zone_tmpl (tmpl, &__zone); + zone =nf_ct_zone_tmpl (tmpl, skb, &__zone); hash =hash_conntrack_raw (&tuple); h =__nf_conntrack_find_get (net, zone, &tuple, hash);if (!h) {
net/netfilter/xt_CT.c +6 -2
@@ -20,6 +20,8 @@#include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> +#define XT_CT_ZONE_FLAGS (XT_CT_ZONE_DIR_ORIG | XT_CT_ZONE_DIR_REPL | XT_CT_ZONE_MARK) +static inline int xt_ct_target (struct sk_buff *skb,struct nf_conn *ct) {/* Previously seen (loopback)? Ignore. */
@@ -207,8 +209,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, }#ifndef CONFIG_NF_CONNTRACK_ZONES -if (info->zone || info->flags & (XT_CT_ZONE_DIR_ORIG | -XT_CT_ZONE_DIR_REPL )) +if (info->zone || info->flags &XT_CT_ZONE_FLAGS ) goto err1;#endif
@@ -225,6 +226,9 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,if (IS_ERR (ct)) goto err2; +if (info->flags &XT_CT_ZONE_MARK ) + ct->status |=IPS_TEMPLATE_MARK ; + ret =0 ;if ((info->ct_events || info->exp_events) && !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events,
Signature · 1 line
1.9.3
PATCH v2 2/3 netfilter: nf_conntrack: add direction support for zones
In reply to Daniel BorkmannThis work adds a direction parameter to netfilter zones, so identity separation can be performed only in original/reply or both directions (default). This basically opens up the possibility of doing NAT with conflicting IP address/port tuples from multiple, isolated tenants on a host (e.g. from a netns) without requiring each tenant to NAT twice resp. to use its own dedicated IP address to SNAT to, meaning overlapping tuples can be made unique with the zone identifier in original direction, where the NAT engine will then allocate a unique tuple in the commonly shared default zone for the reply direction. In some restricted, local DNAT cases, also port redirection could be used for making the reply traffic unique w/o requiring SNAT.
The consensus we've reached and discussed at NFWS and since the initial implementation [1] was to directly integrate the direction meta data into the existing zones infrastructure, as opposed to the ct->mark approach we proposed initially.
As we pass the nf_conntrack_zone object directly around, we don't have to touch all call-sites, but only those, that contain equality checks of zones. Thus, based on the current direction (original or reply), we either return the actual id, or the default NF_CT_DEFAULT_ZONE. CT expectations are direction-agnostic entities when expectations are being compared among themselves, so we can only used the identifier in this case.
Note that zone identifiers can not be included into the hash mix anymore as they don't contain a "stable" value that would be equal for both directions at all times, f.e. if only zone->id would unconditionally be xor'ed into the table slot hash, then replies won't find the corresponding conntracking entry anymore.
If no particular direction is specified when configuring zones, the behaviour is exactly as we expect currently (both directions).
Support has been added for the CT netlink interface as well as the x_tables raw CT target, which both already offer existing interfaces to user space for the configuration of zones.
Below a minimal, simplified collision example (script in [2]) with netperf sessions:
+--- tenant-1 ---+ mark := 1
| netperf |--+
+----------------+ | CT zone := mark [ORIGINAL]
[ip,sport] := X +--------------+ +--- gateway ---+
| mark routing |--| SNAT |-- ... +
+--------------+ +---------------+ |
+--- tenant-2 ---+ | ~~~|~~~
| netperf |--+ +-----------+ |
+----------------+ mark := 2 | netserver |------ ... +
[ip,sport] := X +-----------+
[ip,port] := YOn the gateway netns, example:
iptables -t raw -A PREROUTING -j CT --zone mark --direction ORIGINAL iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark
conntrack -L from gateway netns:
netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns
tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865
src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024
[ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0
zone=1 use=1 zone-dir=original
tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865
src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555
[ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0
zone=2 use=1 zone-dir=original
tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768
src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438
[ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0
zone=1 use=1 zone-dir=original
tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206
src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889
[ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0
zone=2 use=2 zone-dir=original
Taking this further, test script in [2] creates 200 tenants and runs original-tuple colliding netperf sessions each. A conntrack -L dump in the gateway netns also shows 200 out of 400 overlapping entries, all in ESTABLISHED state as expected. I also did run various other tests with some permutations of the script, to mention some: no zones + no overlaps, single static zone + no overlaps (original, reply, both directions), etc.
[1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/
[2] https://paste.fedoraproject.org/242835/65657871/
--- include/net/netfilter/nf_conntrack_zones.h | 35 +++++++++++- include/uapi/linux/netfilter/nfnetlink_conntrack.h | 9 +++ include/uapi/linux/netfilter/xt_CT.h | 6 +- net/ipv4/netfilter/nf_defrag_ipv4.c | 6 +- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 6 +- net/netfilter/nf_conntrack_core.c | 53 +++++++++--------- net/netfilter/nf_conntrack_expect.c | 6 +- net/netfilter/nf_conntrack_netlink.c | 64 ++++++++++++++++++---- net/netfilter/nf_conntrack_standalone.c | 7 ++- net/netfilter/nf_nat_core.c | 14 ++--- net/netfilter/xt_CT.c | 16 +++++- net/sched/act_connmark.c | 2 + 12 files changed, 166 insertions(+), 58 deletions(-)
include/net/netfilter/nf_conntrack_zones.h +34 -1
@@ -1,19 +1,28 @@#ifndef _NF_CONNTRACK_ZONES_H#define _NF_CONNTRACK_ZONES_H +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#define NF_CT_DEFAULT_ZONE 0 +#define NF_CT_ORIG_DIR (1 << IP_CT_DIR_ORIGINAL) +#define NF_CT_REPL_DIR (1 << IP_CT_DIR_REPLY) +#define NF_CT_DEFAULT_DIR (NF_CT_ORIG_DIR | NF_CT_REPL_DIR) +#if IS_ENABLED (CONFIG_NF_CONNTRACK )#include <net/netfilter/nf_conntrack_extend.h> struct nf_conntrack_zone {u16 id; +u16 dir; };static __always_inline struct nf_conntrack_zone *nf_ct_zone_dflt(struct nf_conntrack_zone *ptr) { ptr->id =NF_CT_DEFAULT_ZONE ; + ptr->dir =NF_CT_DEFAULT_DIR ; +return ptr; }
@@ -22,6 +31,8 @@ struct nf_conntrack_zone *nf_ct_zone_get(const struct nf_conntrack_zone *zone, struct nf_conntrack_zone *ptr) { ptr->id = zone->id; + ptr->dir = zone->dir; +return ptr; }
@@ -42,8 +53,30 @@ nf_ct_zone_tmpl(const struct nf_conn *tmpl, struct nf_conntrack_zone *ptr)return tmpl ?nf_ct_zone (tmpl, ptr) :nf_ct_zone_dflt (ptr); } +static inline bool nf_ct_zone_matches_dir (const struct nf_conntrack_zone *zone, +enum ip_conntrack_dir dir) +{ +return zone->dir & (1 << dir); +} + +static inline u16 nf_ct_zone_id (const struct nf_conntrack_zone *zone, +enum ip_conntrack_dir dir) +{ +return nf_ct_zone_matches_dir (zone, dir) ? + zone->id :NF_CT_DEFAULT_ZONE ; +} +static inline bool nf_ct_zone_equal (const struct nf_conn *ct_a, -const struct nf_conntrack_zone *b) +const struct nf_conntrack_zone *b, +enum ip_conntrack_dir dir) +{ +struct nf_conntrack_zone zone_a, *a =nf_ct_zone (ct_a, &zone_a); + +return nf_ct_zone_id (a, dir) ==nf_ct_zone_id (b, dir); +} + +static inline bool nf_ct_zone_equal_any (const struct nf_conn *ct_a, +const struct nf_conntrack_zone *b) {struct nf_conntrack_zone zone_a, *a =nf_ct_zone (ct_a, &zone_a);
include/uapi/linux/netfilter/nfnetlink_conntrack.h +9 -0
@@ -53,6 +53,7 @@ enum ctattr_type {CTA_MARK_MASK ,CTA_LABELS ,CTA_LABELS_MASK , +CTA_DIR , __CTA_MAX };#define CTA_MAX (__CTA_MAX - 1)
@@ -260,4 +261,12 @@ enum ctattr_expect_stats { };#define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1) +enum ctattr_dir { +CTA_DIR_UNSPEC , +CTA_DIR_ORIG , +CTA_DIR_REPL , + __CTA_DIR_MAX +}; +#define CTA_DIR_MAX (__CTA_DIR_MAX - 1) +#endif /* _IPCONNTRACK_NETLINK_H */
include/uapi/linux/netfilter/xt_CT.h +5 -1
@@ -6,7 +6,11 @@enum {XT_CT_NOTRACK =1 <<0 ,XT_CT_NOTRACK_ALIAS =1 <<1 , -XT_CT_MASK =XT_CT_NOTRACK |XT_CT_NOTRACK_ALIAS , +XT_CT_ZONE_DIR_ORIG =1 <<2 , +XT_CT_ZONE_DIR_REPL =1 <<3 , + +XT_CT_MASK =XT_CT_NOTRACK |XT_CT_NOTRACK_ALIAS | +XT_CT_ZONE_DIR_ORIG |XT_CT_ZONE_DIR_REPL , };struct xt_ct_target_info {
net/ipv4/netfilter/nf_defrag_ipv4.c +4 -2
@@ -46,10 +46,12 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,u16 zone_id =NF_CT_DEFAULT_ZONE ;#if IS_ENABLED (CONFIG_NF_CONNTRACK )if (skb->nfct) { +enum ip_conntrack_info ctinfo;struct nf_conntrack_zone *zone, __zone; +const struct nf_conn *ct =nf_ct_get (skb, &ctinfo); - zone =nf_ct_zone ((struct nf_conn *)skb->nfct, &__zone); - zone_id = zone->id; + zone =nf_ct_zone (ct, &__zone); + zone_id =nf_ct_zone_id (zone,CTINFO2DIR (ctinfo)); }#endif #if IS_ENABLED (CONFIG_BRIDGE_NETFILTER )
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +4 -2
@@ -36,10 +36,12 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,u16 zone_id =NF_CT_DEFAULT_ZONE ;#if IS_ENABLED (CONFIG_NF_CONNTRACK )if (skb->nfct) { +enum ip_conntrack_info ctinfo;struct nf_conntrack_zone *zone, __zone; +const struct nf_conn *ct =nf_ct_get (skb, &ctinfo); - zone =nf_ct_zone ((struct nf_conn *)skb->nfct, &__zone); - zone_id = zone->id; + zone =nf_ct_zone (ct, &__zone); + zone_id =nf_ct_zone_id (zone,CTINFO2DIR (ctinfo)); }#endif #if IS_ENABLED (CONFIG_BRIDGE_NETFILTER )
net/netfilter/nf_conntrack_core.c +25 -28
180 lines not on this page · raw message
net/netfilter/nf_conntrack_expect.c +3 -3
@@ -101,7 +101,7 @@ __nf_ct_expect_find(struct net *net, h =nf_ct_expect_dst_hash (tuple);hlist_for_each_entry_rcu (i, &net->ct.expect_hash[h], hnode) {if (nf_ct_tuple_mask_cmp (tuple, &i->tuple, &i->mask) && -nf_ct_zone_equal (i->master, zone)) +nf_ct_zone_equal_any (i->master, zone))return i; }
@@ -144,7 +144,7 @@ nf_ct_find_expectation(struct net *net,hlist_for_each_entry (i, &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_zone_equal (i->master, zone)) { +nf_ct_zone_equal_any (i->master, zone)) { exp = i;break ; }
@@ -234,7 +234,7 @@ 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_zone_equal (a->master,nf_ct_zone (b->master, &b_zone)); +nf_ct_zone_equal_any (a->master,nf_ct_zone (b->master, &b_zone)); }/* Generally a bad idea to call this: could have matched already. */
net/netfilter/nf_conntrack_netlink.c +53 -11
160 lines not on this page · raw message
net/netfilter/nf_conntrack_standalone.c +6 -1
@@ -144,8 +144,13 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)static void ct_show_zone (struct seq_file *s,const struct nf_conn *ct) {struct nf_conntrack_zone __zone, *zone =nf_ct_zone (ct, &__zone); +static const char *const dir_to_name[] = { + [NF_CT_ORIG_DIR ] ="original" , + [NF_CT_REPL_DIR ] ="reply" , + [NF_CT_DEFAULT_DIR ] ="both" , + }; -seq_printf (s,"zone=%u " , zone->id); +seq_printf (s,"zone=%u zone-dir=%s " , zone->id, dir_to_name[zone->dir]); }#else static inline void ct_show_zone (struct seq_file *s,const struct nf_conn *ct)
net/netfilter/nf_nat_core.c +6 -8
@@ -118,15 +118,13 @@ EXPORT_SYMBOL(nf_xfrm_me_harder);/* 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_zone *zone, -const struct nf_conntrack_tuple *tuple) +hash_by_src (const struct net *net,const struct nf_conntrack_tuple *tuple) {unsigned int hash;/* Original src, to ensure we map it consistently if poss. */ hash =jhash2 ((u32 *)&tuple->src,sizeof (tuple->src) /sizeof (u32), - tuple->dst.protonum ^ zone->id ^ nf_conntrack_hash_rnd); + tuple->dst.protonum ^ nf_conntrack_hash_rnd);return reciprocal_scale (hash, net->ct.nat_htable_size); }
@@ -194,13 +192,14 @@ find_appropriate_src(struct net *net,struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(net, zone, tuple); + unsigned int h = hash_by_src(net, tuple);const struct nf_conn_nat *nat;const struct nf_conn *ct;hlist_for_each_entry_rcu (nat, &net->ct.nat_bysource[h], bysource) { ct = nat->ct; -if (same_src (ct, tuple) &&nf_ct_zone_equal (ct, zone)) { +if (same_src (ct, tuple) && +nf_ct_zone_equal (ct, zone,IP_CT_DIR_ORIGINAL )) {/* Copy source part from reply tuple. */ nf_ct_invert_tuplepr (result, &ct->tuplehash[IP_CT_DIR_REPLY ].tuple);
@@ -423,10 +422,9 @@ nf_nat_setup_info(struct nf_conn *ct, }if (maniptype ==NF_NAT_MANIP_SRC ) { -struct nf_conntrack_zone zone;unsigned int srchash; - srchash =hash_by_src (net,nf_ct_zone (ct, &zone), + srchash =hash_by_src (net, &ct->tuplehash[IP_CT_DIR_ORIGINAL ].tuple);spin_lock_bh (&nf_nat_lock);/* nf_conntrack_alter_reply might re-allocate extension aera */
net/netfilter/xt_CT.c +15 -1
@@ -181,6 +181,18 @@ out:#endif } +static u16 xt_ct_flags_to_dir (const struct xt_ct_target_info_v1 *info) +{ +switch (info->flags & (XT_CT_ZONE_DIR_ORIG |XT_CT_ZONE_DIR_REPL )) { +case XT_CT_ZONE_DIR_ORIG : +return NF_CT_ORIG_DIR ; +case XT_CT_ZONE_DIR_REPL : +return NF_CT_REPL_DIR ; +default : +return NF_CT_DEFAULT_DIR ; + } +} +static int xt_ct_tg_check (const struct xt_tgchk_param *par,struct xt_ct_target_info_v1 *info) {
@@ -195,7 +207,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, }#ifndef CONFIG_NF_CONNTRACK_ZONES -if (info->zone) +if (info->zone || info->flags & (XT_CT_ZONE_DIR_ORIG | +XT_CT_ZONE_DIR_REPL )) goto err1;#endif
@@ -205,6 +218,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,memset (&t,0 ,sizeof (t)); zone.id = info->zone; + zone.dir =xt_ct_flags_to_dir (info); ct =nf_conntrack_alloc (par->net, &zone, &t, &t,GFP_KERNEL ); ret =PTR_ERR (ct);
net/sched/act_connmark.c +2 -0
@@ -72,6 +72,8 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, goto out; zone.id = ca->zone; + zone.dir =NF_CT_DEFAULT_DIR ; + thash =nf_conntrack_find_get (dev_net (skb->dev), &zone, &tuple);if (!thash) goto out;
Signature · 1 line
1.9.3
v2 cover Netfilter zone directions
This is v2 of the originally named flextuples [1] patch set, but this time after discussions from NFWS completely reworked towards integration into the existing zones infrastructure. Please see individual patches for details.
Thanks!
[1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/
v1 -> v2:
- Reworked entire set, integration into zones
- Rebased onto latest nf-next
Daniel Borkmann (3):
netfilter: nf_conntrack: push zone object into functions
netfilter: nf_conntrack: add direction support for zones
netfilter: nf_conntrack: add efficient mark to zone mapping
include/net/netfilter/nf_conntrack.h | 6 +- include/net/netfilter/nf_conntrack_core.h | 3 +- include/net/netfilter/nf_conntrack_expect.h | 11 +- include/net/netfilter/nf_conntrack_zones.h | 87 +++++++++++-- include/uapi/linux/netfilter/nf_conntrack_common.h | 4 + include/uapi/linux/netfilter/nfnetlink_conntrack.h | 9 ++ include/uapi/linux/netfilter/xt_CT.h | 8 +- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 4 +- net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 3 +- net/ipv4/netfilter/nf_defrag_ipv4.c | 20 +-- net/ipv4/netfilter/nf_nat_pptp.c | 3 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 3 +- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 5 +- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 21 ++-- net/netfilter/ipvs/ip_vs_nfct.c | 5 +- net/netfilter/nf_conntrack_core.c | 93 ++++++++------ net/netfilter/nf_conntrack_expect.c | 22 ++-- net/netfilter/nf_conntrack_h323_main.c | 4 +- net/netfilter/nf_conntrack_netlink.c | 138 ++++++++++++++------- net/netfilter/nf_conntrack_pptp.c | 7 +- net/netfilter/nf_conntrack_sip.c | 3 +- net/netfilter/nf_conntrack_standalone.c | 24 +++- net/netfilter/nf_nat_core.c | 24 ++-- net/netfilter/nf_synproxy_core.c | 6 +- net/netfilter/xt_CT.c | 25 +++- net/netfilter/xt_connlimit.c | 13 +- net/sched/act_connmark.c | 6 +- 27 files changed, 395 insertions(+), 162 deletions(-)
Signature · 1 line
1.9.3
Pablo Neira Ayuso
maintainerRe: [PATCH nf-next v2 1/3] netfilter: nf_conntrack: push zone object into functions
In reply to Daniel BorkmannQuoted 12 lines · Daniel Borkmann
This patch replaces the zone id which is pushed down into functions with the actual zone object. It's a bigger one-time change, but needed for later on extending zones with a direction parameter, and thus decoupling this additional information from all call-sites.
It was suggested during NFWS to let the
nf_ct_zone()helper store the meta data on the stack as we currently do, but in a similar fashion asskb_header_pointer()does, so we can avoid keeping track of the object lifetime. In general, dealing directly with the object also facilitates for adding other possible meta data in future.No functional changes in this patch.
[...]
net/ipv4/netfilter/nf_conntrack_proto_icmp.c icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, · line 140
Quoted 13 lines
net/ipv4/netfilter/nf_conntrack_proto_icmp.c +2
-1@@ -134,9 +134,10 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,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 ; +struct nf_conntrack_zone *zone, __zone;NF_CT_ASSERT (skb->nfct ==NULL ); + zone =nf_ct_zone_tmpl (tmpl, &__zone);
This was one possible idea, but I also suggested to have a dummy:
static const struct nf_ct_zone nf_ct_zone_dflt = {
.zone_id = NF_CT_DEFAULT_ZONE,
};
that we return in case no zone extension is set, and use it instead of your nf_ct_zone_dflt() function.
Pablo Neira Ayuso
maintainerRe: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
In reply to Daniel BorkmannQuoted 8 lines · Daniel Borkmann
This work adds the possibility of deriving the zone id from the
skb->markfield in a scalable manner. This allows for having only a single template serving 100s .. 1000s of different zones, for example, instead of needing to have one match for each zone as an extra CT jump target. Note that we'd need to have this information attached to the template as at the time when we're trying to lookup a possible ct object, we already need to know zone information for a possible match when going into__nf_conntrack_find_get(). This work provides a minimal implementation for a possible mapping.
I think connmark is a better place for this feature, given that the zone is a ct extension. Moreover, I guess it will not take long until someone sends us a patch to perform some bitwise operation to only fetch some of the skb->mark bits into the zone.
Re: [PATCH nf-next v2 1/3] netfilter: nf_conntrack: push zone object into functions
In reply to Pablo Neira AyusoQuoted 30 lines · Pablo Neira Ayuso
Quoted 12 lines · Daniel Borkmann
This patch replaces the zone id which is pushed down into functions with the actual zone object. It's a bigger one-time change, but needed for later on extending zones with a direction parameter, and thus decoupling this additional information from all call-sites.
It was suggested during NFWS to let the
nf_ct_zone()helper store the meta data on the stack as we currently do, but in a similar fashion asskb_header_pointer()does, so we can avoid keeping track of the object lifetime. In general, dealing directly with the object also facilitates for adding other possible meta data in future.No functional changes in this patch.
[...]
net/ipv4/netfilter/nf_conntrack_proto_icmp.c icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, · line 140
Quoted 13 lines
net/ipv4/netfilter/nf_conntrack_proto_icmp.c +2
-1@@ -134,9 +134,10 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,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 ; +struct nf_conntrack_zone *zone, __zone;NF_CT_ASSERT (skb->nfct ==NULL ); + zone =nf_ct_zone_tmpl (tmpl, &__zone);This was one possible idea, but I also suggested to have a dummy:
Quoted 6 lines
static const struct
nf_ct_zonenf_ct_zone_dflt= {
.zone_id =NF_CT_DEFAULT_ZONE,
};that we return in case no zone extension is set, and use it instead of your
nf_ct_zone_dflt()function.
There are multiple possibilities, no doubt, I liked this one better and therefore took that path as it integrated nicely with the 3rd patch in this series, and it also consumed less stack space, it's 4 byte after all.
Re: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
In reply to Pablo Neira AyusoQuoted 10 lines · Pablo Neira Ayuso
Quoted 8 lines · Daniel Borkmann
This work adds the possibility of deriving the zone id from the
skb->markfield in a scalable manner. This allows for having only a single template serving 100s .. 1000s of different zones, for example, instead of needing to have one match for each zone as an extra CT jump target. Note that we'd need to have this information attached to the template as at the time when we're trying to lookup a possible ct object, we already need to know zone information for a possible match when going into__nf_conntrack_find_get(). This work provides a minimal implementation for a possible mapping.
Quoted 4 lines
I think connmark is a better place for this feature, given that the zone is a ct extension. Moreover, I guess it will not take long until someone sends us a patch to perform some bitwise operation to only fetch some of the
skb->markbits into the zone.
Hm, we do need the zoning information *before* we do the actual lookup for a ct object (non-template I mean), otherwise we don't know in which zone to find it. When I looked into this, the connmark target is applied afterwards on the actual ct object.
So you mean to add this to the raw table, so that someone could for each skb assign ct->mark := skb->mark on the template and then have zone := ct->mark, so we can use it for looking up? I would also need more than a single template for that, right, as otherwise if I'd have arbitrary ct->mark := skb->mark assignments in parallel, then we'd race. The current seems rather simple.
Thanks,
Daniel
Re: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
Quoted 21 lines · Daniel Borkmann
Quoted 10 lines · Pablo Neira Ayuso
Quoted 8 lines · Daniel Borkmann
This work adds the possibility of deriving the zone id from the
skb->markfield in a scalable manner. This allows for having only a single template serving 100s .. 1000s of different zones, for example, instead of needing to have one match for each zone as an extra CT jump target. Note that we'd need to have this information attached to the template as at the time when we're trying to lookup a possible ct object, we already need to know zone information for a possible match when going into__nf_conntrack_find_get(). This work provides a minimal implementation for a possible mapping.Quoted 4 lines
I think connmark is a better place for this feature, given that the zone is a ct extension. Moreover, I guess it will not take long until someone sends us a patch to perform some bitwise operation to only fetch some of the
skb->markbits into the zone.Hm, we do need the zoning information *before* we do the actual lookup for a ct object (non-template I mean), otherwise we don't know in which zone to find it. When I looked into this, the connmark target is applied afterwards on the actual ct object.
Quoted 5 lines
So you mean to add this to the raw table, so that someone could for each skb assign
ct->mark:=skb->markon the template and then have zone :=ct->mark, so we can use it for looking up? I would also need more than a single template for that, right, as otherwise if I'd have arbitraryct->mark:=skb->markassignments in parallel, then we'd race. The current seems rather simple.
Sorry to bug you again on this patchset. I've been thinking a bit more about your suggestion, my previous thoughts/reply on this, and how to move forward. Lets presume for a moment, we would indeed place this into the connmark target.
That would mean, we want to store the mark from the skb first into ct->mark and then into the zone of the ct. We would need to do this on the template itself, so that when the packet comes in, we know in which zone we're going to do the actual lookup of a ct entry. When using a single, global template, this seems racy, you would at least need to make sure that during the lookup it's not being overwritten by other incoming skbs. If you say, the ct->mark assignment should be skipped and the skb->mark should directly be assigned to the zone, then why putting this into connmark as it has nothing to do with the connection mark anymore (it would also avoid further unnecessary dependency of NF_CONNTRACK_ZONES on NF_CONNTRACK_MARK and NETFILTER_XT_CONNMARK). But also here, we'd have the same race issues as mentioned with ct->mark when overwriting zone ids. The only thing I could imagine would be for the template to hold a possible mask in the ct->mark itself, which could be user configured, and then does in pseudocode, tmpl_zone->id := skb->mark & tmpl->mark. If someone would really have such a use case (?), fair enough, this could be followed-up.
The current approach implemented here that I found so far most appealing and having the least complexity, was to just have a /single/ template and to overwrite the zone->id with skb->mark on the ptr we have sitting on the stack. It avoids all the issues mentioned. But perhaps you mean something entirely different and I just seem to misinterpret your answer, hmm.
Thanks again, Pablo.
Pablo Neira Ayuso
maintainerRe: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
On Mon, Jul 20, 2015 at 06:18:55PM +0200, Daniel Borkmann wrote:
[...]
Quoted 5 lines
The current approach implemented here that I found so far most appealing and having the least complexity, was to just have a /single/ template and to overwrite the
zone->idwithskb->markon the ptr we have sitting on the stack. It avoids all the issues mentioned. But perhaps you mean something entirely different and I just seem to misinterpret your answer, hmm.
You mean something that from command line would look like:
iptables -A PREROUTING -t raw -j CT --zone mark
So we set the zone ID in the CT target based on the existing mark, right?
Re: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
Quoted 8 lines · Pablo Neira Ayuso
On Mon, Jul 20, 2015 at 06:18:55PM +0200, Daniel Borkmann wrote:
[...]Quoted 5 lines
The current approach implemented here that I found so far most appealing and having the least complexity, was to just have a /single/ template and to overwrite the
zone->idwithskb->markon the ptr we have sitting on the stack. It avoids all the issues mentioned. But perhaps you mean something entirely different and I just seem to misinterpret your answer, hmm.
Quoted 6 lines
You mean something that from command line would look like:
iptables -A PREROUTING -t raw -j CT --zone markSo we set the zone ID in the CT target based on the existing mark, right?
Not in the target callback, in the example script and patches I've provided, I'm indeed configuring ...
iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL
... which in nf_ct_zone_tmpl() call-sites will return the skb->mark mapped zone ID, that is then used f.e. directly for the lookup in the hash table resp. following ct entry allocation in case a lookup didn't return a ct entry.
Thanks,
Daniel
Pablo Neira Ayuso
maintainerRe: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
Quoted 16 lines · Daniel Borkmann
Quoted 8 lines · Pablo Neira Ayuso
On Mon, Jul 20, 2015 at 06:18:55PM +0200, Daniel Borkmann wrote:
[...]Quoted 5 lines
The current approach implemented here that I found so far most appealing and having the least complexity, was to just have a /single/ template and to overwrite the
zone->idwithskb->markon the ptr we have sitting on the stack. It avoids all the issues mentioned. But perhaps you mean something entirely different and I just seem to misinterpret your answer, hmm.Quoted 6 lines
You mean something that from command line would look like:
iptables -A PREROUTING -t raw -j CT --zone markSo we set the zone ID in the CT target based on the existing mark, right?
Quoted 8 lines
Not in the target callback, in the example script and patches I've provided, I'm indeed configuring ...
iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL... which in
nf_ct_zone_tmpl()call-sites will return theskb->markmapped zone ID, that is then used f.e. directly for the lookup in the hash table resp. following ct entry allocation in case a lookup didn't return a ct entry.
I see, thanks for explaining.
I would like to avoid the use of the ct->status bit to set this. Can you see a clean way to store this bit in the zone extension instead?
Re: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
On 07/20/2015 08:24 PM, Pablo Neira Ayuso wrote:
...
Quoted 4 lines
I see, thanks for explaining.
I would like to avoid the use of the
ct->statusbit to set this. Can you see a clean way to store this bit in the zone extension instead?
Okay, understood, i.e. since it's unfortunately exported through UAPI and there's limited space. I'm thinking of renaming the u16 for the direction in the zones structure into 'flags' and just add an indicator there [as we still have unused bits there] ... would that seem better?
Thanks,
Daniel
Pablo Neira Ayuso
maintainerRe: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
Quoted 11 lines · Daniel Borkmann
On 07/20/2015 08:24 PM, Pablo Neira Ayuso wrote:
...Quoted 4 lines
I see, thanks for explaining.
I would like to avoid the use of the
ct->statusbit to set this. Can you see a clean way to store this bit in the zone extension instead?Okay, understood, i.e. since it's unfortunately exported through UAPI and there's limited space. I'm thinking of renaming the u16 for the direction in the zones structure into 'flags' and just add an indicator there [as we still have unused bits there] ... would that seem better?
Grab u8 for flags. u8 to store directions should be sufficient I'd suggest.
BTW, did you consider replacing NF_CT_DEFAULT_ZONE by a global object? It looks like a natural way in the patch that replaces the u16 by struct nf_conntrack_zone.
Re: [PATCH nf-next v2 3/3] netfilter: nf_conntrack: add efficient mark to zone mapping
Quoted 8 lines · Pablo Neira Ayuso
Quoted 7 lines · Daniel Borkmann
On 07/20/2015 08:24 PM, Pablo Neira Ayuso wrote:
...Quoted 4 lines
I see, thanks for explaining.
I would like to avoid the use of the
ct->statusbit to set this. Can you see a clean way to store this bit in the zone extension instead?
Quoted 7 lines
Quoted 4 lines
Okay, understood, i.e. since it's unfortunately exported through UAPI and there's limited space. I'm thinking of renaming the u16 for the direction in the zones structure into 'flags' and just add an indicator there [as we still have unused bits there] ... would that seem better?
Grab u8 for flags. u8 to store directions should be sufficient I'd suggest.
That's fine as well, will do.
Quoted 3 lines
BTW, did you consider replacing
NF_CT_DEFAULT_ZONEby a global object? It looks like a natural way in the patch that replaces the u16 by structnf_conntrack_zone.
We still need the NF_CT_DEFAULT_ZONE itself, the ID I mean, in a couple of places, but I'll look into having a global default struct and replace it in these places that don't have zone support.
Thanks,
Daniel