Skip to contentSkip to conversation

netfilter: nf_conntrack_expect: use conntrack GC to reap expectations

PATCH Superseded Pablo Neira Ayuso 1 participant 1 message Jun 17

Subsystems (2)

v4 of 6 Superseded Latest is v6 →

lore
Share & tools
lore

Pablo Neira Ayuso

author maintainer
#0 lore raw

PATCH v4 1/1 netfilter: nf_conntrack_expect: use conntrack GC to reap expectations

This patch replaces the timer API by GC worker approach for expectations, as it already happened in many other subsystems.

Use the existing conntrack GC worker to iterate over the local list of expectations in the master conntrack to reap expired expectations. Check IPS_HELPER_BIT to run GC for expectations, set it on for nft_ct expectation which nevers sets it. Hold the expectation spinlock while iterating over the master conntrack expectation list to synchronize with nf_ct_remove_expectations(). This also performs runtime packet path garbage collection through the expectation insertion and lookup functions while walking over one of the chains of the global expectation hashtables. Unconfirmed conntrack entries are skipped since ct->ext can be reallocated and dying are skipped since those will be gone soon. Set on IPS_HELPER_BIT if the helper ct extension is added, then the new GC worker does not need to bump the ct refcount to check if the ct->ext helper is available.

This removes the extra bump on the refcount for expectation timers, this allows to remove several nf_ct_expect_put() calls after the unlink, after this update only refcount remains at 1 while on the expectation hashes.

This patch implicitly addresses a race with the existing timer API allowing an expectation to access a stale exp->master pointer which has been already released when expectation removal loses races with an expiring timer, ie. timer_del() reporting false.

Add a new NF_CT_EXPECT_DEAD flag to reap this expectation via GC. This is needed by nf_conntrack_unexpect_related() which is called in error paths to invalidate newly created expectations that has been added into the hashes. These expectactions cannot be inmediately released as GC or nf_ct_remove_expectations() could race to make it. On expectation insert, the runtime GC reaps stale expectations before checking the expectation limit set by policy.

Set current timestamp in nf_ct_expect_alloc(), then add the expectation policy timeout (or custom timeout specified added on top of this) to specify the expectation lifetime.

Fixes bffcaad9afdf ("netfilter: ctnetlink: ensure safe access to master conntrack")

---
v4: - use WRITE,READ_ONCE for _is_expired() to access exp->flags as suggested by LLM
- move IPS_HELPER_BIT to nf_ct_helper_ext_add() to set it on for OVS, act_ct and nft_ct expectation, needed by GC.

 include/net/netfilter/nf_conntrack_expect.h   |  16 +-
 .../linux/netfilter/nf_conntrack_common.h     |   1 +
 net/netfilter/nf_conntrack_core.c             |  21 ++-
 net/netfilter/nf_conntrack_expect.c           | 145 +++++++++---------
 net/netfilter/nf_conntrack_h323_main.c        |   4 +-
 net/netfilter/nf_conntrack_helper.c           |  10 +-
 net/netfilter/nf_conntrack_netlink.c          |  22 ++-
 net/netfilter/nf_conntrack_sip.c              |  13 +-
 net/netfilter/nft_ct.c                        |   6 +-
 9 files changed, 129 insertions(+), 109 deletions(-)
include/net/netfilter/nf_conntrack_expect.h +13 -3
index 80f50fd0f7ad..be4a120d549e 100644
@@ -54,8 +54,8 @@ struct nf_conntrack_expect {
 	/* The conntrack of the master connection */
 	struct nf_conn *master;
 
-	/* Timer function; deletes the expectation. */
-	struct timer_list timeout;
+	/* jiffies32 when this expectation expires */
+	u32 timeout;
 
 #if IS_ENABLED(CONFIG_NF_NAT)
 	union nf_inet_addr saved_addr;
@@ -69,6 +69,14 @@ struct nf_conntrack_expect {
 	struct rcu_head rcu;
 };
 
+static inline bool nf_ct_exp_is_expired(const struct nf_conntrack_expect *exp)
+{
+	if (READ_ONCE(exp->flags) & NF_CT_EXPECT_DEAD)
+		return true;
+
+	return (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) <= 0;
+}
+
 static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp)
 {
 	return read_pnet(&exp->net);
@@ -130,7 +138,6 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
 
 void nf_ct_remove_expectations(struct nf_conn *ct);
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp);
-bool nf_ct_remove_expect(struct nf_conntrack_expect *exp);
 
 void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data);
 void nf_ct_expect_iterate_net(struct net *net,
@@ -153,5 +160,8 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect,
 	return nf_ct_expect_related_report(expect, 0, 0, flags);
 }
 
+struct nf_conn_help;
+void nf_ct_expectation_gc(struct nf_conn_help *master_help);
+
 #endif /*_NF_CONNTRACK_EXPECT_H*/
 
include/uapi/linux/netfilter/nf_conntrack_common.h +1 -0
index 56b6b60a814f..ee51045ae1d6 100644
@@ -160,6 +160,7 @@ enum ip_conntrack_expect_events {
 #define NF_CT_EXPECT_USERSPACE		0x4
 
 #ifdef __KERNEL__
+#define NF_CT_EXPECT_DEAD		0x8
 #define NF_CT_EXPECT_MASK	(NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \
 				 NF_CT_EXPECT_USERSPACE)
 #endif
net/netfilter/nf_conntrack_core.c +20 -1
index 4fb3a2d18631..c2602133a289 100644
@@ -1471,6 +1471,19 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
 	return false;
 }
 
+static void nf_ct_help_gc(struct nf_conn *ct)
+{
+	if (!refcount_inc_not_zero(&ct->ct_general.use))
+		return;
+
+	/* load ->ext after refcount increase */
+	smp_acquire__after_ctrl_dep();
+
+	nf_ct_expectation_gc(nfct_help(ct));
+
+	nf_ct_put(ct);
+}
+
 static void gc_worker(struct work_struct *work)
 {
 	unsigned int i, hashsz, nf_conntrack_max95 = 0;
@@ -1543,7 +1556,13 @@ static void gc_worker(struct work_struct *work)
 			expires = (expires - (long)next_run) / ++count;
 			next_run += expires;
 
-			if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
+			if (gc_worker_skip_ct(tmp))
+				continue;
+
+			if (test_bit(IPS_HELPER_BIT, &tmp->status))
+				nf_ct_help_gc(tmp);
+
+			if (nf_conntrack_max95 == 0)
 				continue;
 
 			net = nf_ct_net(tmp);
net/netfilter/nf_conntrack_expect.c +72 -73

293 lines not on this page · raw message

net/netfilter/nf_conntrack_h323_main.c +2 -2
index 7f189dceb3c4..24931e379985 100644
@@ -1388,8 +1388,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
 				 "timeout to %u seconds for",
 				 info->timeout);
 			nf_ct_dump_tuple(&exp->tuple);
-			mod_timer_pending(&exp->timeout,
-					  jiffies + info->timeout * HZ);
+			WRITE_ONCE(exp->timeout,
+				   nfct_time_stamp + (info->timeout * HZ));
 		}
 		spin_unlock_bh(&nf_conntrack_expect_lock);
 	}
net/netfilter/nf_conntrack_helper.c +4 -6
index 2f35bdd0d7d7..8b94001c2430 100644
@@ -181,10 +181,10 @@ nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp)
 	struct nf_conn_help *help;
 
 	help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp);
-	if (help)
+	if (help) {
+		__set_bit(IPS_HELPER_BIT, &ct->status);
 		INIT_HLIST_HEAD(&help->expectations);
-	else
-		pr_debug("failed to add helper extension area");
+	}
 	return help;
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add);
@@ -203,10 +203,8 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 		return 0;
 
 	help = nfct_help(tmpl);
-	if (help != NULL) {
+	if (help)
 		helper = rcu_dereference(help->helper);
-		set_bit(IPS_HELPER_BIT, &ct->status);
-	}
 
 	help = nfct_help(ct);
 
net/netfilter/nf_conntrack_netlink.c +9 -13
index b429e648f06c..4e78d2482989 100644
@@ -3014,8 +3014,8 @@ static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
 {
+	__s32 timeout = (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) / HZ;
 	struct nf_conn *master = exp->master;
-	long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
 	struct nf_conntrack_helper *helper;
 #if IS_ENABLED(CONFIG_NF_NAT)
 	struct nlattr *nest_parms;
@@ -3178,6 +3178,9 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 restart:
 		hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]],
 					 hnode) {
+			if (nf_ct_exp_is_expired(exp))
+				continue;
+
 			if (l3proto && exp->tuple.src.l3num != l3proto)
 				continue;
 
@@ -3456,11 +3459,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
 		}
 
 		/* after list removal, usage count == 1 */
-		if (timer_delete(&exp->timeout)) {
-			nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
-						   nlmsg_report(info->nlh));
-			nf_ct_expect_put(exp);
-		}
+		nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
+					   nlmsg_report(info->nlh));
 		spin_unlock_bh(&nf_conntrack_expect_lock);
 		/* have to put what we 'get' above.
 		 * after this line usage count == 0 */
@@ -3484,14 +3484,10 @@ static int
 ctnetlink_change_expect(struct nf_conntrack_expect *x,
 			const struct nlattr * const cda[])
 {
-	if (cda[CTA_EXPECT_TIMEOUT]) {
-		if (!timer_delete(&x->timeout))
-			return -ETIME;
+	if (cda[CTA_EXPECT_TIMEOUT])
+		WRITE_ONCE(x->timeout, nfct_time_stamp +
+			   ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ);
 
-		x->timeout.expires = jiffies +
-			ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ;
-		add_timer(&x->timeout);
-	}
 	return 0;
 }
 
net/netfilter/nf_conntrack_sip.c +5 -8
index c606d1f60b58..5ec3a4a4bbd7 100644
@@ -897,11 +897,10 @@ static int refresh_signalling_expectation(struct nf_conn *ct,
 		    exp->tuple.dst.protonum != proto ||
 		    exp->tuple.dst.u.udp.port != port)
 			continue;
-		if (mod_timer_pending(&exp->timeout, jiffies + expires * HZ)) {
-			exp->flags &= ~NF_CT_EXPECT_INACTIVE;
-			found = 1;
-			break;
-		}
+		WRITE_ONCE(exp->timeout, nfct_time_stamp + (expires * HZ));
+		WRITE_ONCE(exp->flags, exp->flags & ~NF_CT_EXPECT_INACTIVE);
+		found = 1;
+		break;
 	}
 	spin_unlock_bh(&nf_conntrack_expect_lock);
 	return found;
@@ -920,8 +919,7 @@ static void flush_expectations(struct nf_conn *ct, bool media)
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media)
 			continue;
-		if (!nf_ct_remove_expect(exp))
-			continue;
+		nf_ct_unlink_expect(exp);
 		if (!media)
 			break;
 	}
@@ -1413,7 +1411,6 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 
 	nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct),
 			  saddr, &daddr, proto, NULL, &port);
-	exp->timeout.expires = sip_timeout * HZ;
 	rcu_assign_pointer(exp->assign_helper, helper);
 	exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
 
net/netfilter/nft_ct.c +3 -3
index 25934c6f01fb..72cabadc5cfc 100644
@@ -1145,7 +1145,6 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj,
 	help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 	if (help && refcount_inc_not_zero(&to_assign->ct_refcnt)) {
 		rcu_assign_pointer(help->helper, to_assign);
-		set_bit(IPS_HELPER_BIT, &ct->status);
 
 		if ((ct->status & IPS_NAT_MASK) && !nfct_seqadj(ct))
 			if (!nfct_seqadj_ext_add(ct))
@@ -1296,7 +1295,8 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 	struct nf_conn *ct;
 
 	ct = nf_ct_get(pkt->skb, &ctinfo);
-	if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) {
+	if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct) ||
+	    test_bit(IPS_HELPER_BIT, &ct->status)) {
 		regs->verdict.code = NFT_BREAK;
 		return;
 	}
@@ -1326,7 +1326,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 		          &ct->tuplehash[!dir].tuple.src.u3,
 		          &ct->tuplehash[!dir].tuple.dst.u3,
 		          priv->l4proto, NULL, &priv->dport);
-	exp->timeout.expires = jiffies + priv->timeout * HZ;
+	exp->timeout += priv->timeout * HZ;
 
 	if (nf_ct_expect_related(exp, 0) != 0)
 		regs->verdict.code = NF_DROP;
Signature · 1 line
2.47.3