netfilter: kill the fake untracked conntrack objects

resurrect an old patch from Pablo Neira to remove the untracked objects.

Currently, there are four possible states of an skb wrt. conntrack.

1. No conntrack attached, ct is NULL.
2. Normal (kmem cache allocated) ct attached.
3. a template (kmalloc'd), not in any hash tables at any point in time
4. the 'untracked' conntrack, a percpu nf_conn object, tagged via
   IPS_UNTRACKED_BIT in ct->status.

Untracked is supposed to be identical to case 1.  It exists only
so users can check

-m conntrack --ctstate UNTRACKED vs.
-m conntrack --ctstate INVALID

e.g. attempts to set connmark on INVALID or UNTRACKED conntracks is
supposed to be a no-op.

Thus currently we need to check
 ct == NULL || nf_ct_is_untracked(ct)

in a lot of places in order to avoid altering untracked objects.

The other consequence of the percpu untracked object is that all
-j NOTRACK (and, later, kfree_skb of such skbs) result in an atomic op
(inc/dec the untracked conntracks refcount).

This adds a new kernel-private ctinfo state, IP_CT_UNTRACKED, to
make the distinction instead.

The (few) places that care about packet invalid (ct is NULL) vs.
packet untracked now need to test ct == NULL vs. ctinfo == IP_CT_UNTRACKED,
but all other places can omit the nf_ct_is_untracked() check.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 5 insertions, 43 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index bcf1d2a6539e..03150f60714d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -180,14 +180,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
 
 unsigned int nf_conntrack_max __read_mostly;
 seqcount_t nf_conntrack_generation __read_mostly;
-
-/* nf_conn must be 8 bytes aligned, as the 3 LSB bits are used
- * for the nfctinfo. We cheat by (ab)using the PER CPU cache line
- * alignment to enforce this.
- */
-DEFINE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked);
-EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
-
 static unsigned int nf_conntrack_hash_rnd __read_mostly;
 
 static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
@@ -1314,9 +1306,10 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	int ret;
 
 	tmpl = nf_ct_get(skb, &ctinfo);
-	if (tmpl) {
+	if (tmpl || ctinfo == IP_CT_UNTRACKED) {
 		/* Previously seen (loopback or untracked)?  Ignore. */
-		if (!nf_ct_is_template(tmpl)) {
+		if ((tmpl && !nf_ct_is_template(tmpl)) ||
+		     ctinfo == IP_CT_UNTRACKED) {
 			NF_CT_STAT_INC_ATOMIC(net, ignore);
 			return NF_ACCEPT;
 		}
@@ -1629,18 +1622,6 @@ void nf_ct_free_hashtable(void *hash, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
-static int untrack_refs(void)
-{
-	int cnt = 0, cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
-
-		cnt += atomic_read(&ct->ct_general.use) - 1;
-	}
-	return cnt;
-}
-
 void nf_conntrack_cleanup_start(void)
 {
 	conntrack_gc_work.exiting = true;
@@ -1650,8 +1631,6 @@ void nf_conntrack_cleanup_start(void)
 void nf_conntrack_cleanup_end(void)
 {
 	RCU_INIT_POINTER(nf_ct_destroy, NULL);
-	while (untrack_refs() > 0)
-		schedule();
 
 	cancel_delayed_work_sync(&conntrack_gc_work.dwork);
 	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
@@ -1825,20 +1804,11 @@ 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)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		per_cpu(nf_conntrack_untracked, cpu).status |= bits;
-}
-EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
-
 int nf_conntrack_init_start(void)
 {
 	int max_factor = 8;
 	int ret = -ENOMEM;
-	int i, cpu;
+	int i;
 
 	seqcount_init(&nf_conntrack_generation);
 
@@ -1921,15 +1891,6 @@ int nf_conntrack_init_start(void)
 	if (ret < 0)
 		goto err_proto;
 
-	/* Set up fake conntrack: to never be deleted, not in any hashes */
-	for_each_possible_cpu(cpu) {
-		struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
-		write_pnet(&ct->ct_net, &init_net);
-		atomic_set(&ct->ct_general.use, 1);
-	}
-	/*  - and look it like as a confirmed connection */
-	nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
-
 	conntrack_gc_work_init(&conntrack_gc_work);
 	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);
 
@@ -1977,6 +1938,7 @@ int nf_conntrack_init_net(struct net *net)
 	int ret = -ENOMEM;
 	int cpu;
 
+	BUILD_BUG_ON(IP_CT_UNTRACKED == IP_CT_NUMBER);
 	atomic_set(&net->ct.count, 0);
 
 	net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);