netfilter: nf_conntrack: IPS_UNTRACKED bit

NOTRACK makes all cpus share a cache line on nf_conntrack_untracked
twice per packet. This is bad for performance.
__read_mostly annotation is also a bad choice.

This patch introduces IPS_UNTRACKED bit so that we can use later a
per_cpu untrack structure more easily.

A new helper, nf_ct_untracked_get() returns a pointer to
nf_conntrack_untracked.

Another one, nf_ct_untracked_status_or() is used by nf_nat_init() to add
IPS_NAT_DONE_MASK bits to untracked status.

nf_ct_is_untracked() prototype is changed to work on a nf_conn pointer.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 14e6d32..1afd18c 100644 (file)
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -76,6 +76,10 @@ enum ip_conntrack_status {
        /* Conntrack is a template */
        IPS_TEMPLATE_BIT = 11,
        IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT),
+
+       /* Conntrack is a fake untracked entry */
+       IPS_UNTRACKED_BIT = 12,
+       IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
 };
 
 /* Connection tracking event types */

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index bde095f..3bc38c7 100644 (file)
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -261,7 +261,13 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
                               u32 seq);
 
 /* Fake conntrack entry for untracked connections */
-extern struct nf_conn nf_conntrack_untracked;
+static inline struct nf_conn *nf_ct_untracked_get(void)
+{
+       extern struct nf_conn nf_conntrack_untracked;
+
+       return &nf_conntrack_untracked;
+}
+extern void nf_ct_untracked_status_or(unsigned long bits);
 
 /* Iterate over all conntracks: if iter returns true, it's deleted. */
 extern void
@@ -289,9 +295,9 @@ static inline int nf_ct_is_dying(struct nf_conn *ct)
        return test_bit(IPS_DYING_BIT, &ct->status);
 }
 
-static inline int nf_ct_is_untracked(const struct sk_buff *skb)
+static inline int nf_ct_is_untracked(const struct nf_conn *ct)
 {
-       return (skb->nfct == &nf_conntrack_untracked.ct_general);
+       return test_bit(IPS_UNTRACKED_BIT, &ct->status);
 }
 
 extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 3d7524f..aced085 100644 (file)
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
        struct nf_conn *ct = (struct nf_conn *)skb->nfct;
        int ret = NF_ACCEPT;
 
-       if (ct && ct != &nf_conntrack_untracked) {
+       if (ct && !nf_ct_is_untracked(ct)) {
                if (!nf_ct_is_confirmed(ct))
                        ret = __nf_conntrack_confirm(skb);
                if (likely(ret == NF_ACCEPT))

diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 4f8bddb..c7719b2 100644 (file)
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -742,7 +742,7 @@ static int __init nf_nat_init(void)
        spin_unlock_bh(&nf_nat_lock);
 
        /* Initialize fake conntrack so that NAT will skip it */
-       nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK;
+       nf_ct_untracked_status_or(IPS_NAT_DONE_MASK);
 
        l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET);
 

diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index beb2581..6723c68 100644 (file)
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -98,7 +98,7 @@ nf_nat_fn(unsigned int hooknum,
                return NF_ACCEPT;
 
        /* Don't try to NAT if this packet is not conntracked */
-       if (ct == &nf_conntrack_untracked)
+       if (nf_ct_is_untracked(ct))
                return NF_ACCEPT;
 
        nat = nfct_nat(ct);

diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 9be8177..1df3c8b 100644 (file)
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -208,7 +208,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl,
        type = icmp6h->icmp6_type - 130;
        if (type >= 0 && type < sizeof(noct_valid_new) &&
            noct_valid_new[type]) {
-               skb->nfct = &nf_conntrack_untracked.ct_general;
+               skb->nfct = &nf_ct_untracked_get()->ct_general;
                skb->nfctinfo = IP_CT_NEW;
                nf_conntrack_get(skb->nfct);
                return NF_ACCEPT;

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index eeeb8bc..6c1da21 100644 (file)
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -62,7 +62,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
 unsigned int nf_conntrack_max __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_max);
 
-struct nf_conn nf_conntrack_untracked __read_mostly;
+struct nf_conn nf_conntrack_untracked;
 EXPORT_SYMBOL_GPL(nf_conntrack_untracked);
 
 static int nf_conntrack_hash_rnd_initted;
@@ -1321,6 +1321,12 @@ EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
 module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
                  &nf_conntrack_htable_size, 0600);
 
+void nf_ct_untracked_status_or(unsigned long bits)
+{
+       nf_conntrack_untracked.status |= bits;
+}
+EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
+
 static int nf_conntrack_init_init_net(void)
 {
        int max_factor = 8;
@@ -1368,8 +1374,7 @@ static int nf_conntrack_init_init_net(void)
 #endif
        atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
        /*  - and look it like as a confirmed connection */
-       set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status);
-
+       nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
        return 0;
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c42ff6a..5bae1cd 100644 (file)
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -480,7 +480,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
        int err;
 
        /* ignore our fake conntrack entry */
-       if (ct == &nf_conntrack_untracked)
+       if (nf_ct_is_untracked(ct))
                return 0;
 
        if (events & (1 << IPCT_DESTROY)) {

diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 562bf32..0cb6053 100644 (file)
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -67,7 +67,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par)
                return -EINVAL;
 
        if (info->flags & XT_CT_NOTRACK) {
-               ct = &nf_conntrack_untracked;
+               ct = nf_ct_untracked_get();
                atomic_inc(&ct->ct_general.use);
                goto out;
        }
@@ -132,7 +132,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par)
        struct nf_conn *ct = info->ct;
        struct nf_conn_help *help;
 
-       if (ct != &nf_conntrack_untracked) {
+       if (!nf_ct_is_untracked(ct)) {
                help = nfct_help(ct);
                if (help)
                        module_put(help->helper->me);

diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c
index 512b912..9d78218 100644 (file)
--- a/net/netfilter/xt_NOTRACK.c
+++ b/net/netfilter/xt_NOTRACK.c
@@ -23,7 +23,7 @@ notrack_tg(struct sk_buff *skb, const struct xt_action_param *par)
           If there is a real ct entry correspondig to this packet,
           it'll hang aroun till timing out. We don't deal with it
           for performance reasons. JK */
-       skb->nfct = &nf_conntrack_untracked.ct_general;
+       skb->nfct = &nf_ct_untracked_get()->ct_general;
        skb->nfctinfo = IP_CT_NEW;
        nf_conntrack_get(skb->nfct);
 

diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 859d9fd..7a11826 100644 (file)
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -104,7 +104,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 #ifdef WITH_CONNTRACK
        /* Avoid counting cloned packets towards the original connection. */
        nf_conntrack_put(skb->nfct);
-       skb->nfct     = &nf_conntrack_untracked.ct_general;
+       skb->nfct     = &nf_ct_untracked_get()->ct_general;
        skb->nfctinfo = IP_CT_NEW;
        nf_conntrack_get(skb->nfct);
 #endif
@@ -177,7 +177,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 
 #ifdef WITH_CONNTRACK
        nf_conntrack_put(skb->nfct);
-       skb->nfct     = &nf_conntrack_untracked.ct_general;
+       skb->nfct     = &nf_ct_untracked_get()->ct_general;
        skb->nfctinfo = IP_CT_NEW;
        nf_conntrack_get(skb->nfct);
 #endif

diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 30b95a1..f4af1bf 100644 (file)
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -120,7 +120,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par)
        if (ct == NULL)
                return false;
 
-       if (ct == &nf_conntrack_untracked)
+       if (nf_ct_is_untracked(ct))
                return false;
 
        if (ct->master)

diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 39681f1..e536710 100644 (file)
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -123,11 +123,12 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
 
        ct = nf_ct_get(skb, &ctinfo);
 
-       if (ct == &nf_conntrack_untracked)
-               statebit = XT_CONNTRACK_STATE_UNTRACKED;
-       else if (ct != NULL)
-               statebit = XT_CONNTRACK_STATE_BIT(ctinfo);
-       else
+       if (ct) {
+               if (nf_ct_is_untracked(ct))
+                       statebit = XT_CONNTRACK_STATE_UNTRACKED;
+               else
+                       statebit = XT_CONNTRACK_STATE_BIT(ctinfo);
+       } else
                statebit = XT_CONNTRACK_STATE_INVALID;
 
        if (info->match_flags & XT_CONNTRACK_STATE) {

diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 3d54c23..1ca8990 100644 (file)
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -127,7 +127,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
         * reply packet of an established SNAT-ted connection. */
 
        ct = nf_ct_get(skb, &ctinfo);
-       if (ct && (ct != &nf_conntrack_untracked) &&
+       if (ct && !nf_ct_is_untracked(ct) &&
            ((iph->protocol != IPPROTO_ICMP &&
              ctinfo == IP_CT_IS_REPLY + IP_CT_ESTABLISHED) ||
             (iph->protocol == IPPROTO_ICMP &&

diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c
index e12e053..a507922 100644 (file)
--- a/net/netfilter/xt_state.c
+++ b/net/netfilter/xt_state.c
@@ -26,14 +26,16 @@ state_mt(const struct sk_buff *skb, struct xt_action_param *par)
        const struct xt_state_info *sinfo = par->matchinfo;
        enum ip_conntrack_info ctinfo;
        unsigned int statebit;
+       struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
-       if (nf_ct_is_untracked(skb))
-               statebit = XT_STATE_UNTRACKED;
-       else if (!nf_ct_get(skb, &ctinfo))
+       if (!ct)
                statebit = XT_STATE_INVALID;
-       else
-               statebit = XT_STATE_BIT(ctinfo);
-
+       else {
+               if (nf_ct_is_untracked(ct))
+                       statebit = XT_STATE_UNTRACKED;
+               else
+                       statebit = XT_STATE_BIT(ctinfo);
+       }
        return (sinfo->statemask & statebit);
 }