Merge tag 'nf-24-06-11' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for net:

Patch #1 fixes insufficient sanitization of netlink attributes for the
	 inner expression which can trigger nul-pointer dereference,
	 from Davide Ornaghi.

Patch #2 address a report that there is a race condition between
         namespace cleanup and the garbage collection of the list:set
         type. This patch resolves this issue with other minor issues
	 as well, from Jozsef Kadlecsik.

Patch #3 ip6_route_me_harder() ignores flowlabel/dsfield when ip dscp
	 has been mangled, this unbreaks ip6 dscp set $v,
	 from Florian Westphal.

All of these patches address issues that are present in several releases.

* tag 'nf-24-06-11' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: Use flowlabel flow key when re-routing mangled packets
  netfilter: ipset: Fix race between namespace cleanup and gc in the list:set type
  netfilter: nft_inner: validate mandatory meta and payload
====================

Link: https://lore.kernel.org/r/20240611220323.413713-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 68 insertions, 51 deletions

diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 53d255838e6a..5d989d803009 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -36,6 +36,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff
 		.flowi6_uid = sock_net_uid(net, sk),
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
+		.flowlabel = ip6_flowinfo(iph),
 	};
 	int err;
 
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 3184cc6be4c9..c7ae4d9bf3d2 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1172,23 +1172,50 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
 				    .len = IPSET_MAXNAMELEN - 1 },
 };
 
+/* In order to return quickly when destroying a single set, it is split
+ * into two stages:
+ * - Cancel garbage collector
+ * - Destroy the set itself via call_rcu()
+ */
+
 static void
-ip_set_destroy_set(struct ip_set *set)
+ip_set_destroy_set_rcu(struct rcu_head *head)
 {
-	pr_debug("set: %s\n",  set->name);
+	struct ip_set *set = container_of(head, struct ip_set, rcu);
 
-	/* Must call it without holding any lock */
 	set->variant->destroy(set);
 	module_put(set->type->me);
 	kfree(set);
 }
 
 static void
-ip_set_destroy_set_rcu(struct rcu_head *head)
+_destroy_all_sets(struct ip_set_net *inst)
 {
-	struct ip_set *set = container_of(head, struct ip_set, rcu);
+	struct ip_set *set;
+	ip_set_id_t i;
+	bool need_wait = false;
 
-	ip_set_destroy_set(set);
+	/* First cancel gc's: set:list sets are flushed as well */
+	for (i = 0; i < inst->ip_set_max; i++) {
+		set = ip_set(inst, i);
+		if (set) {
+			set->variant->cancel_gc(set);
+			if (set->type->features & IPSET_TYPE_NAME)
+				need_wait = true;
+		}
+	}
+	/* Must wait for flush to be really finished  */
+	if (need_wait)
+		rcu_barrier();
+	for (i = 0; i < inst->ip_set_max; i++) {
+		set = ip_set(inst, i);
+		if (set) {
+			ip_set(inst, i) = NULL;
+			set->variant->destroy(set);
+			module_put(set->type->me);
+			kfree(set);
+		}
+	}
 }
 
 static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
@@ -1202,11 +1229,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-
 	/* Commands are serialized and references are
 	 * protected by the ip_set_ref_lock.
 	 * External systems (i.e. xt_set) must call
-	 * ip_set_put|get_nfnl_* functions, that way we
+	 * ip_set_nfnl_get_* functions, that way we
 	 * can safely check references here.
 	 *
 	 * list:set timer can only decrement the reference
@@ -1214,8 +1240,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	 * without holding the lock.
 	 */
 	if (!attr[IPSET_ATTR_SETNAME]) {
-		/* Must wait for flush to be really finished in list:set */
-		rcu_barrier();
 		read_lock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
 			s = ip_set(inst, i);
@@ -1226,15 +1250,7 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		}
 		inst->is_destroyed = true;
 		read_unlock_bh(&ip_set_ref_lock);
-		for (i = 0; i < inst->ip_set_max; i++) {
-			s = ip_set(inst, i);
-			if (s) {
-				ip_set(inst, i) = NULL;
-				/* Must cancel garbage collectors */
-				s->variant->cancel_gc(s);
-				ip_set_destroy_set(s);
-			}
-		}
+		_destroy_all_sets(inst);
 		/* Modified by ip_set_destroy() only, which is serialized */
 		inst->is_destroyed = false;
 	} else {
@@ -1255,12 +1271,12 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		features = s->type->features;
 		ip_set(inst, i) = NULL;
 		read_unlock_bh(&ip_set_ref_lock);
+		/* Must cancel garbage collectors */
+		s->variant->cancel_gc(s);
 		if (features & IPSET_TYPE_NAME) {
 			/* Must wait for flush to be really finished  */
 			rcu_barrier();
 		}
-		/* Must cancel garbage collectors */
-		s->variant->cancel_gc(s);
 		call_rcu(&s->rcu, ip_set_destroy_set_rcu);
 	}
 	return 0;
@@ -2365,30 +2381,25 @@ ip_set_net_init(struct net *net)
 }
 
 static void __net_exit
-ip_set_net_exit(struct net *net)
+ip_set_net_pre_exit(struct net *net)
 {
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	struct ip_set *set = NULL;
-	ip_set_id_t i;
-
 	inst->is_deleted = true; /* flag for ip_set_nfnl_put */
+}
 
-	nfnl_lock(NFNL_SUBSYS_IPSET);
-	for (i = 0; i < inst->ip_set_max; i++) {
-		set = ip_set(inst, i);
-		if (set) {
-			ip_set(inst, i) = NULL;
-			set->variant->cancel_gc(set);
-			ip_set_destroy_set(set);
-		}
-	}
-	nfnl_unlock(NFNL_SUBSYS_IPSET);
+static void __net_exit
+ip_set_net_exit(struct net *net)
+{
+	struct ip_set_net *inst = ip_set_pernet(net);
+
+	_destroy_all_sets(inst);
 	kvfree(rcu_dereference_protected(inst->ip_set_list, 1));
 }
 
 static struct pernet_operations ip_set_net_ops = {
 	.init	= ip_set_net_init,
+	.pre_exit = ip_set_net_pre_exit,
 	.exit   = ip_set_net_exit,
 	.id	= &ip_set_net_id,
 	.size	= sizeof(struct ip_set_net),
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 54e2a1dd7f5f..bfae7066936b 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -79,7 +79,7 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb,
 	struct set_elem *e;
 	int ret;
 
-	list_for_each_entry(e, &map->members, list) {
+	list_for_each_entry_rcu(e, &map->members, list) {
 		if (SET_WITH_TIMEOUT(set) &&
 		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
@@ -99,7 +99,7 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb,
 	struct set_elem *e;
 	int ret;
 
-	list_for_each_entry(e, &map->members, list) {
+	list_for_each_entry_rcu(e, &map->members, list) {
 		if (SET_WITH_TIMEOUT(set) &&
 		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
@@ -188,9 +188,10 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	struct list_set *map = set->data;
 	struct set_adt_elem *d = value;
 	struct set_elem *e, *next, *prev = NULL;
-	int ret;
+	int ret = 0;
 
-	list_for_each_entry(e, &map->members, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &map->members, list) {
 		if (SET_WITH_TIMEOUT(set) &&
 		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
@@ -201,6 +202,7 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 		if (d->before == 0) {
 			ret = 1;
+			goto out;
 		} else if (d->before > 0) {
 			next = list_next_entry(e, list);
 			ret = !list_is_last(&e->list, &map->members) &&
@@ -208,9 +210,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		} else {
 			ret = prev && prev->id == d->refid;
 		}
-		return ret;
+		goto out;
 	}
-	return 0;
+out:
+	rcu_read_unlock();
+	return ret;
 }
 
 static void
@@ -239,7 +243,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 	/* Find where to add the new entry */
 	n = prev = next = NULL;
-	list_for_each_entry(e, &map->members, list) {
+	list_for_each_entry_rcu(e, &map->members, list) {
 		if (SET_WITH_TIMEOUT(set) &&
 		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
@@ -316,9 +320,9 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 {
 	struct list_set *map = set->data;
 	struct set_adt_elem *d = value;
-	struct set_elem *e, *next, *prev = NULL;
+	struct set_elem *e, *n, *next, *prev = NULL;
 
-	list_for_each_entry(e, &map->members, list) {
+	list_for_each_entry_safe(e, n, &map->members, list) {
 		if (SET_WITH_TIMEOUT(set) &&
 		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
@@ -424,14 +428,8 @@ static void
 list_set_destroy(struct ip_set *set)
 {
 	struct list_set *map = set->data;
-	struct set_elem *e, *n;
 
-	list_for_each_entry_safe(e, n, &map->members, list) {
-		list_del(&e->list);
-		ip_set_put_byindex(map->net, e->id);
-		ip_set_ext_destroy(set, e);
-		kfree(e);
-	}
+	WARN_ON_ONCE(!list_empty(&map->members));
 	kfree(map);
 
 	set->data = NULL;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index ba0d3683a45d..9139ce38ea7b 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -839,6 +839,9 @@ static int nft_meta_inner_init(const struct nft_ctx *ctx,
 	struct nft_meta *priv = nft_expr_priv(expr);
 	unsigned int len;
 
+	if (!tb[NFTA_META_KEY] || !tb[NFTA_META_DREG])
+		return -EINVAL;
+
 	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
 	switch (priv->key) {
 	case NFT_META_PROTOCOL:
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 0c43d748e23a..50429cbd42da 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -650,6 +650,10 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx,
 	struct nft_payload *priv = nft_expr_priv(expr);
 	u32 base;
 
+	if (!tb[NFTA_PAYLOAD_BASE] || !tb[NFTA_PAYLOAD_OFFSET] ||
+	    !tb[NFTA_PAYLOAD_LEN] || !tb[NFTA_PAYLOAD_DREG])
+		return -EINVAL;
+
 	base   = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
 	switch (base) {
 	case NFT_PAYLOAD_TUN_HEADER: