1 files changed, 88 insertions, 29 deletions

diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 8ec7d13d2860..f9d76d85d04f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -23,6 +23,11 @@
 #include <net/ip6_fib.h>
 #include <net/rtnh.h>
 
+#include "dev.h"
+
+DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled);
+EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled);
+
 #ifdef CONFIG_MODULES
 
 static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
@@ -43,6 +48,11 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "SEG6LOCAL";
 	case LWTUNNEL_ENCAP_RPL:
 		return "RPL";
+	case LWTUNNEL_ENCAP_IOAM6:
+		return "IOAM6";
+	case LWTUNNEL_ENCAP_XFRM:
+		/* module autoload not supported for encap type */
+		return NULL;
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
 	case LWTUNNEL_ENCAP_NONE:
@@ -150,21 +160,14 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
 		return ret;
 	}
 
-	rcu_read_lock();
-	ops = rcu_dereference(lwtun_encaps[encap_type]);
-	rcu_read_unlock();
+	ops = rcu_access_pointer(lwtun_encaps[encap_type]);
 #ifdef CONFIG_MODULES
 	if (!ops) {
 		const char *encap_type_str = lwtunnel_encap_str(encap_type);
 
 		if (encap_type_str) {
-			__rtnl_unlock();
 			request_module("rtnl-lwt-%s", encap_type_str);
-			rtnl_lock();
-
-			rcu_read_lock();
-			ops = rcu_dereference(lwtun_encaps[encap_type]);
-			rcu_read_unlock();
+			ops = rcu_access_pointer(lwtun_encaps[encap_type]);
 		}
 	}
 #endif
@@ -192,10 +195,13 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
 			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 
 			if (nla_entype) {
+				if (nla_len(nla_entype) < sizeof(u16)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE");
+					return -EINVAL;
+				}
 				encap_type = nla_get_u16(nla_entype);
 
-				if (lwtunnel_valid_encap_type(encap_type,
-							      extack) != 0)
+				if (lwtunnel_valid_encap_type(encap_type, extack))
 					return -EOPNOTSUPP;
 			}
 		}
@@ -313,82 +319,132 @@ EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap);
 
 int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
 
-	if (!dst)
+	local_bh_disable();
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
 		goto drop;
+	}
+
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
+		goto drop;
+	}
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->output))
+	if (likely(ops && ops->output)) {
+		dev_xmit_recursion_inc();
 		ret = ops->output(net, sk, skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
 		goto drop;
 
-	return ret;
+	goto out;
 
 drop:
 	kfree_skb(skb);
 
+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_output);
 
 int lwtunnel_xmit(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
+
+	local_bh_disable();
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
+		goto drop;
+	}
 
-	if (!dst)
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
 		goto drop;
+	}
 
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->xmit))
+	if (likely(ops && ops->xmit)) {
+		dev_xmit_recursion_inc();
 		ret = ops->xmit(skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
 		goto drop;
 
-	return ret;
+	goto out;
 
 drop:
 	kfree_skb(skb);
 
+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_xmit);
 
 int lwtunnel_input(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
 
-	if (!dst)
+	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
 		goto drop;
+	}
+
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
+		goto drop;
+	}
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
@@ -398,8 +454,11 @@ int lwtunnel_input(struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->input))
+	if (likely(ops && ops->input)) {
+		dev_xmit_recursion_inc();
 		ret = ops->input(skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)