1 files changed, 113 insertions, 152 deletions

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index b38d91d6b249..0ca2bb8ed026 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -24,6 +24,7 @@
 #include <net/ipv6_frag.h>
 #include <uapi/linux/tc_act/tc_ct.h>
 #include <net/tc_act/tc_ct.h>
+#include <net/tc_wrapper.h>
 
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_conntrack.h>
@@ -33,6 +34,7 @@
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include <net/netfilter/nf_conntrack_act_ct.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <uapi/linux/netfilter/nf_nat.h>
 
 static struct workqueue_struct *act_ct_wq;
@@ -178,7 +180,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
 	entry = tcf_ct_flow_table_flow_action_get_next(action);
 	entry->id = FLOW_ACTION_CT_METADATA;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
-	entry->ct_metadata.mark = ct->mark;
+	entry->ct_metadata.mark = READ_ONCE(ct->mark);
 #endif
 	ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
 					     IP_CT_ESTABLISHED_REPLY;
@@ -345,11 +347,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 	module_put(THIS_MODULE);
 }
 
-static void tcf_ct_flow_table_put(struct tcf_ct_params *params)
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft)
 {
-	struct tcf_ct_flow_table *ct_ft = params->ct_ft;
-
-	if (refcount_dec_and_test(&params->ct_ft->ref)) {
+	if (refcount_dec_and_test(&ct_ft->ref)) {
 		rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
 		INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work);
 		queue_rcu_work(act_ct_wq, &ct_ft->rwork);
@@ -657,7 +657,7 @@ struct tc_ct_action_net {
 
 /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
 static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
-				   u16 zone_id, bool force)
+				   struct tcf_ct_params *p)
 {
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
@@ -667,11 +667,19 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
 		return false;
 	if (!net_eq(net, read_pnet(&ct->ct_net)))
 		goto drop_ct;
-	if (nf_ct_zone(ct)->id != zone_id)
+	if (nf_ct_zone(ct)->id != p->zone)
 		goto drop_ct;
+	if (p->helper) {
+		struct nf_conn_help *help;
+
+		help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
+		if (help && rcu_access_pointer(help->helper) != p->helper)
+			goto drop_ct;
+	}
 
 	/* Force conntrack entry direction. */
-	if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
+	if ((p->ct_action & TCA_CT_ACT_FORCE) &&
+	    CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
 		if (nf_ct_is_confirmed(ct))
 			nf_ct_kill(ct);
 
@@ -832,101 +840,29 @@ out_free:
 	return err;
 }
 
-static void tcf_ct_params_free(struct rcu_head *head)
+static void tcf_ct_params_free(struct tcf_ct_params *params)
 {
-	struct tcf_ct_params *params = container_of(head,
-						    struct tcf_ct_params, rcu);
-
-	tcf_ct_flow_table_put(params);
-
+	if (params->helper) {
+#if IS_ENABLED(CONFIG_NF_NAT)
+		if (params->ct_action & TCA_CT_ACT_NAT)
+			nf_nat_helper_put(params->helper);
+#endif
+		nf_conntrack_helper_put(params->helper);
+	}
+	if (params->ct_ft)
+		tcf_ct_flow_table_put(params->ct_ft);
 	if (params->tmpl)
 		nf_ct_put(params->tmpl);
 	kfree(params);
 }
 
-#if IS_ENABLED(CONFIG_NF_NAT)
-/* Modelled after nf_nat_ipv[46]_fn().
- * range is only used for new, uninitialized NAT state.
- * Returns either NF_ACCEPT or NF_DROP.
- */
-static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
-			  enum ip_conntrack_info ctinfo,
-			  const struct nf_nat_range2 *range,
-			  enum nf_nat_manip_type maniptype)
+static void tcf_ct_params_free_rcu(struct rcu_head *head)
 {
-	__be16 proto = skb_protocol(skb, true);
-	int hooknum, err = NF_ACCEPT;
-
-	/* See HOOK2MANIP(). */
-	if (maniptype == NF_NAT_MANIP_SRC)
-		hooknum = NF_INET_LOCAL_IN; /* Source NAT */
-	else
-		hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		if (proto == htons(ETH_P_IP) &&
-		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   hooknum))
-				err = NF_DROP;
-			goto out;
-		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {
-			__be16 frag_off;
-			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
-			int hdrlen = ipv6_skip_exthdr(skb,
-						      sizeof(struct ipv6hdr),
-						      &nexthdr, &frag_off);
-
-			if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-				if (!nf_nat_icmpv6_reply_translation(skb, ct,
-								     ctinfo,
-								     hooknum,
-								     hdrlen))
-					err = NF_DROP;
-				goto out;
-			}
-		}
-		/* Non-ICMP, fall thru to initialize if needed. */
-		fallthrough;
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			/* Initialize according to the NAT action. */
-			err = (range && range->flags & NF_NAT_RANGE_MAP_IPS)
-				/* Action is set up to establish a new
-				 * mapping.
-				 */
-				? nf_nat_setup_info(ct, range, maniptype)
-				: nf_nat_alloc_null_binding(ct, hooknum);
-			if (err != NF_ACCEPT)
-				goto out;
-		}
-		break;
-
-	case IP_CT_ESTABLISHED:
-	case IP_CT_ESTABLISHED_REPLY:
-		break;
-
-	default:
-		err = NF_DROP;
-		goto out;
-	}
+	struct tcf_ct_params *params;
 
-	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
-	if (err == NF_ACCEPT) {
-		if (maniptype == NF_NAT_MANIP_SRC)
-			tc_skb_cb(skb)->post_ct_snat = 1;
-		if (maniptype == NF_NAT_MANIP_DST)
-			tc_skb_cb(skb)->post_ct_dnat = 1;
-	}
-out:
-	return err;
+	params = container_of(head, struct tcf_ct_params, rcu);
+	tcf_ct_params_free(params);
 }
-#endif /* CONFIG_NF_NAT */
 
 static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
 {
@@ -936,9 +872,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
 	if (!mask)
 		return;
 
-	new_mark = mark | (ct->mark & ~(mask));
-	if (ct->mark != new_mark) {
-		ct->mark = new_mark;
+	new_mark = mark | (READ_ONCE(ct->mark) & ~(mask));
+	if (READ_ONCE(ct->mark) != new_mark) {
+		WRITE_ONCE(ct->mark, new_mark);
 		if (nf_ct_is_confirmed(ct))
 			nf_conntrack_event_cache(IPCT_MARK, ct);
 	}
@@ -967,69 +903,40 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
 			  bool commit)
 {
 #if IS_ENABLED(CONFIG_NF_NAT)
-	int err;
-	enum nf_nat_manip_type maniptype;
+	int err, action = 0;
 
 	if (!(ct_action & TCA_CT_ACT_NAT))
 		return NF_ACCEPT;
+	if (ct_action & TCA_CT_ACT_NAT_SRC)
+		action |= BIT(NF_NAT_MANIP_SRC);
+	if (ct_action & TCA_CT_ACT_NAT_DST)
+		action |= BIT(NF_NAT_MANIP_DST);
 
-	/* Add NAT extension if not confirmed yet. */
-	if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct))
-		return NF_DROP;   /* Can't NAT. */
-
-	if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) &&
-	    (ctinfo != IP_CT_RELATED || commit)) {
-		/* NAT an established or related connection like before. */
-		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
-			/* This is the REPLY direction for a connection
-			 * for which NAT was applied in the forward
-			 * direction.  Do the reverse NAT.
-			 */
-			maniptype = ct->status & IPS_SRC_NAT
-				? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC;
-		else
-			maniptype = ct->status & IPS_SRC_NAT
-				? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST;
-	} else if (ct_action & TCA_CT_ACT_NAT_SRC) {
-		maniptype = NF_NAT_MANIP_SRC;
-	} else if (ct_action & TCA_CT_ACT_NAT_DST) {
-		maniptype = NF_NAT_MANIP_DST;
-	} else {
-		return NF_ACCEPT;
-	}
+	err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
+
+	if (action & BIT(NF_NAT_MANIP_SRC))
+		tc_skb_cb(skb)->post_ct_snat = 1;
+	if (action & BIT(NF_NAT_MANIP_DST))
+		tc_skb_cb(skb)->post_ct_dnat = 1;
 
-	err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
-	if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
-		if (ct->status & IPS_SRC_NAT) {
-			if (maniptype == NF_NAT_MANIP_SRC)
-				maniptype = NF_NAT_MANIP_DST;
-			else
-				maniptype = NF_NAT_MANIP_SRC;
-
-			err = ct_nat_execute(skb, ct, ctinfo, range,
-					     maniptype);
-		} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
-			err = ct_nat_execute(skb, ct, ctinfo, NULL,
-					     NF_NAT_MANIP_SRC);
-		}
-	}
 	return err;
 #else
 	return NF_ACCEPT;
 #endif
 }
 
-static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
-		      struct tcf_result *res)
+TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
+				 struct tcf_result *res)
 {
 	struct net *net = dev_net(skb->dev);
-	bool cached, commit, clear, force;
 	enum ip_conntrack_info ctinfo;
 	struct tcf_ct *c = to_ct(a);
 	struct nf_conn *tmpl = NULL;
 	struct nf_hook_state state;
+	bool cached, commit, clear;
 	int nh_ofs, err, retval;
 	struct tcf_ct_params *p;
+	bool add_helper = false;
 	bool skip_add = false;
 	bool defrag = false;
 	struct nf_conn *ct;
@@ -1040,7 +947,6 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	retval = READ_ONCE(c->tcf_action);
 	commit = p->ct_action & TCA_CT_ACT_COMMIT;
 	clear = p->ct_action & TCA_CT_ACT_CLEAR;
-	force = p->ct_action & TCA_CT_ACT_FORCE;
 	tmpl = p->tmpl;
 
 	tcf_lastuse_update(&c->tcf_tm);
@@ -1083,7 +989,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	 * actually run the packet through conntrack twice unless it's for a
 	 * different zone.
 	 */
-	cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
+	cached = tcf_ct_skb_nfct_cached(net, skb, p);
 	if (!cached) {
 		if (tcf_ct_flow_table_lookup(p, skb, family)) {
 			skip_add = true;
@@ -1116,6 +1022,22 @@ do_nat:
 	if (err != NF_ACCEPT)
 		goto drop;
 
+	if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) {
+		err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC);
+		if (err)
+			goto drop;
+		add_helper = true;
+		if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) {
+			if (!nfct_seqadj_ext_add(ct))
+				goto drop;
+		}
+	}
+
+	if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) {
+		if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT)
+			goto drop;
+	}
+
 	if (commit) {
 		tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
 		tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
@@ -1164,6 +1086,9 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
 	[TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
 	[TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
+	[TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN },
+	[TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 },
+	[TCA_CT_HELPER_PROTO] = { .type = NLA_U8 },
 };
 
 static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
@@ -1253,8 +1178,9 @@ static int tcf_ct_fill_params(struct net *net,
 {
 	struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
 	struct nf_conntrack_zone zone;
+	int err, family, proto, len;
 	struct nf_conn *tmpl;
-	int err;
+	char *name;
 
 	p->zone = NF_CT_DEFAULT_ZONE_ID;
 
@@ -1315,10 +1241,31 @@ static int tcf_ct_fill_params(struct net *net,
 		NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
 		return -ENOMEM;
 	}
-	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
 	p->tmpl = tmpl;
+	if (tb[TCA_CT_HELPER_NAME]) {
+		name = nla_data(tb[TCA_CT_HELPER_NAME]);
+		len = nla_len(tb[TCA_CT_HELPER_NAME]);
+		if (len > 16 || name[len - 1] != '\0') {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name.");
+			err = -EINVAL;
+			goto err;
+		}
+		family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET;
+		proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP;
+		err = nf_ct_add_helper(tmpl, name, family, proto,
+				       p->ct_action & TCA_CT_ACT_NAT, &p->helper);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to add helper");
+			goto err;
+		}
+	}
 
+	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
 	return 0;
+err:
+	nf_ct_put(p->tmpl);
+	p->tmpl = NULL;
+	return err;
 }
 
 static int tcf_ct_init(struct net *net, struct nlattr *nla,
@@ -1390,7 +1337,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 
 	err = tcf_ct_flow_table_get(net, params);
 	if (err)
-		goto cleanup_params;
+		goto cleanup;
 
 	spin_lock_bh(&c->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
@@ -1401,17 +1348,15 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 	if (params)
-		call_rcu(&params->rcu, tcf_ct_params_free);
+		call_rcu(&params->rcu, tcf_ct_params_free_rcu);
 
 	return res;
 
-cleanup_params:
-	if (params->tmpl)
-		nf_ct_put(params->tmpl);
 cleanup:
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
-	kfree(params);
+	if (params)
+		tcf_ct_params_free(params);
 	tcf_idr_release(*a, bind);
 	return err;
 }
@@ -1423,7 +1368,7 @@ static void tcf_ct_cleanup(struct tc_action *a)
 
 	params = rcu_dereference_protected(c->params, 1);
 	if (params)
-		call_rcu(&params->rcu, tcf_ct_params_free);
+		call_rcu(&params->rcu, tcf_ct_params_free_rcu);
 }
 
 static int tcf_ct_dump_key_val(struct sk_buff *skb,
@@ -1489,6 +1434,19 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
 	return 0;
 }
 
+static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper)
+{
+	if (!helper)
+		return 0;
+
+	if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) ||
+	    nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) ||
+	    nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum))
+		return -1;
+
+	return 0;
+}
+
 static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
 			      int bind, int ref)
 {
@@ -1541,6 +1499,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
 	if (tcf_ct_dump_nat(skb, p))
 		goto nla_put_failure;
 
+	if (tcf_ct_dump_helper(skb, p->helper))
+		goto nla_put_failure;
+
 skip_dump:
 	if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;