Merge tag 'nf-26-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter/IPVS fixes for net

The following patchset contains Netfilter/IPVS fixes for net:

1) Fix splat with PREEMPT_RCU because smp_processor_id() in nfqueue,
   from Fernando Fernandez Mancera.

2) Fix possible use of pointer to old IPVS scheduler after RCU grace
   period when editing service, from Julian Anastasov.

3) Fix possible forever RCU walk over rt->fib6_siblings in nft_fib6,
   if rt is unlinked mid-iteration, apparently same issue happens in
   the fib6 core. From Jiayuan Chen.

4) Add mutex to guard refcount in synproxy infrastructure, since
   concurrent hook {un}registration can happen.
   From Fernando Fernandez Mancera.

5) Bail out if IRC conntrack helper fails to parse a command, do not
   try parsing using other command handlers, from Florian Westphal.
   This fixes a possible out-of-bound read.

6) Possible use-after-free in nft_tunnel by releasing template dst
   after all references has been dropped, from Tristan Madani.

7) Ignore conntrack template in nft_ct, from Jiayuan Chen.

8) Missing skb_ensure_writable() in ebt_snat, Yiming Qian.

9) Remove multi-register byteorder support, this allows for kernel
   stack info leak, from Florian Westphal.

* tag 'nf-26-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nft_byteorder: remove multi-register support
  netfilter: bridge: make ebt_snat ARP rewrite writable
  netfilter: nft_ct: bail out on template ct in get eval
  netfilter: nft_tunnel: fix use-after-free on object destroy
  netfilter: conntrack_irc: fix possible out-of-bounds read
  netfilter: synproxy: add mutex to guard hook reference counting
  netfilter: nft_fib_ipv6: bail out of sibling walk if rt got unlinked
  ipvs: clear the svc scheduler ptr early on edit
  netfilter: xt_NFQUEUE: prefer raw_smp_processor_id
====================

Link: https://patch.msgid.link/20260601115923.433946-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

12 files changed, 68 insertions, 61 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a02e569813d2..e517eaaa177b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1824,8 +1824,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 			 struct ip_vs_scheduler *scheduler);
-void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
-			    struct ip_vs_scheduler *sched);
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc);
 struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 struct ip_vs_conn *
diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c
index 7dfbcdfc30e5..c9e229af0366 100644
--- a/net/bridge/netfilter/ebt_snat.c
+++ b/net/bridge/netfilter/ebt_snat.c
@@ -31,6 +31,9 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		const struct arphdr *ap;
 		struct arphdr _ah;
 
+		if (skb_ensure_writable(skb, sizeof(_ah) + ETH_ALEN))
+			return EBT_DROP;
+
 		ap = skb_header_pointer(skb, 0, sizeof(_ah), &_ah);
 		if (ap == NULL)
 			return EBT_DROP;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c0a0075e2590..2dbe44715df3 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -191,6 +191,9 @@ static bool nft_fib6_info_nh_uses_dev(struct fib6_info *rt,
 
 		if (nft_fib6_info_nh_dev_match(nh_dev, dev))
 			return true;
+
+		if (!READ_ONCE(rt->fib6_nsiblings))
+			return false;
 	}
 
 	return false;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index bd9cae44d214..16daba8cac83 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1898,7 +1898,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 	if (ret_hooks >= 0)
 		ip_vs_unregister_hooks(ipvs, u->af);
 	if (svc != NULL) {
-		ip_vs_unbind_scheduler(svc, sched);
+		ip_vs_unbind_scheduler(svc);
 		ip_vs_service_free(svc);
 	}
 	ip_vs_scheduler_put(sched);
@@ -1962,9 +1962,8 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (sched != old_sched) {
 		if (old_sched) {
-			ip_vs_unbind_scheduler(svc, old_sched);
-			RCU_INIT_POINTER(svc->scheduler, NULL);
-			/* Wait all svc->sched_data users */
+			ip_vs_unbind_scheduler(svc);
+			/* Wait all svc->scheduler/sched_data users */
 			synchronize_rcu();
 		}
 		/* Bind the new scheduler */
@@ -1972,6 +1971,10 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 			ret = ip_vs_bind_scheduler(svc, sched);
 			if (ret) {
 				ip_vs_scheduler_put(sched);
+				/* Try to restore the old_sched */
+				if (old_sched &&
+				    !ip_vs_bind_scheduler(svc, old_sched))
+					old_sched = NULL;
 				goto out;
 			}
 		}
@@ -2027,7 +2030,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
 
 	/* Unbind scheduler */
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
-	ip_vs_unbind_scheduler(svc, old_sched);
+	ip_vs_unbind_scheduler(svc);
 	ip_vs_scheduler_put(old_sched);
 
 	/* Unbind persistence engine, keep svc->pe */
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index c6e421c4e299..24adc38942a0 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -56,19 +56,19 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 /*
  *  Unbind a service with its scheduler
  */
-void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
-			    struct ip_vs_scheduler *sched)
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc)
 {
-	struct ip_vs_scheduler *cur_sched;
+	struct ip_vs_scheduler *sched;
 
-	cur_sched = rcu_dereference_protected(svc->scheduler, 1);
-	/* This check proves that old 'sched' was installed */
-	if (!cur_sched)
+	sched = rcu_dereference_protected(svc->scheduler, 1);
+	if (!sched)
 		return;
 
+	/* Reset the scheduler before initiating any RCU callbacks */
+	rcu_assign_pointer(svc->scheduler, NULL);
+	smp_wmb();	/* paired with smp_rmb() in ip_vs_schedule() */
 	if (sched->done_service)
 		sched->done_service(svc);
-	/* svc->scheduler can be set to NULL only by caller */
 }
 
 
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 522183b9a604..2ebe4cb47cf6 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -203,7 +203,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 			if (parse_dcc(data, data_limit, &dcc_ip,
 				       &dcc_port, &addr_beg_p, &addr_end_p)) {
 				pr_debug("unable to parse dcc command\n");
-				continue;
+				goto out;
 			}
 
 			pr_debug("DCC bound ip/port: %pI4:%u\n",
@@ -217,7 +217,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 				net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n",
 						     &tuple->src.u3.ip,
 						     &dcc_ip, dcc_port);
-				continue;
+				goto out;
 			}
 
 			exp = nf_ct_expect_alloc(ct);
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 036c8586f49b..ed00114f65f3 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -22,6 +22,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_synproxy.h>
 
+static DEFINE_MUTEX(synproxy_mutex);
+
 unsigned int synproxy_net_id;
 EXPORT_SYMBOL_GPL(synproxy_net_id);
 
@@ -769,26 +771,31 @@ static const struct nf_hook_ops ipv4_synproxy_ops[] = {
 
 int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net)
 {
-	int err;
+	int err = 0;
 
+	mutex_lock(&synproxy_mutex);
 	if (snet->hook_ref4 == 0) {
 		err = nf_register_net_hooks(net, ipv4_synproxy_ops,
 					    ARRAY_SIZE(ipv4_synproxy_ops));
 		if (err)
-			return err;
+			goto out;
 	}
 
 	snet->hook_ref4++;
-	return 0;
+out:
+	mutex_unlock(&synproxy_mutex);
+	return err;
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_init);
 
 void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net)
 {
+	mutex_lock(&synproxy_mutex);
 	snet->hook_ref4--;
 	if (snet->hook_ref4 == 0)
 		nf_unregister_net_hooks(net, ipv4_synproxy_ops,
 					ARRAY_SIZE(ipv4_synproxy_ops));
+	mutex_unlock(&synproxy_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_fini);
 
@@ -1193,27 +1200,32 @@ static const struct nf_hook_ops ipv6_synproxy_ops[] = {
 int
 nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net)
 {
-	int err;
+	int err = 0;
 
+	mutex_lock(&synproxy_mutex);
 	if (snet->hook_ref6 == 0) {
 		err = nf_register_net_hooks(net, ipv6_synproxy_ops,
 					    ARRAY_SIZE(ipv6_synproxy_ops));
 		if (err)
-			return err;
+			goto out;
 	}
 
 	snet->hook_ref6++;
-	return 0;
+out:
+	mutex_unlock(&synproxy_mutex);
+	return err;
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_init);
 
 void
 nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net)
 {
+	mutex_lock(&synproxy_mutex);
 	snet->hook_ref6--;
 	if (snet->hook_ref6 == 0)
 		nf_unregister_net_hooks(net, ipv6_synproxy_ops,
 					ARRAY_SIZE(ipv6_synproxy_ops));
+	mutex_unlock(&synproxy_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_fini);
 #endif /* CONFIG_IPV6 */
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 2316c77f4228..dfd41fc8d9b8 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -19,7 +19,6 @@ struct nft_byteorder {
 	u8			sreg;
 	u8			dreg;
 	enum nft_byteorder_ops	op:8;
-	u8			len;
 	u8			size;
 };
 
@@ -28,13 +27,8 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 			const struct nft_pktinfo *pkt)
 {
 	const struct nft_byteorder *priv = nft_expr_priv(expr);
-	u32 *src = &regs->data[priv->sreg];
+	const u32 *src = &regs->data[priv->sreg];
 	u32 *dst = &regs->data[priv->dreg];
-	u16 *s16, *d16;
-	unsigned int i;
-
-	s16 = (void *)src;
-	d16 = (void *)dst;
 
 	switch (priv->size) {
 	case 8: {
@@ -43,18 +37,14 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
-			for (i = 0; i < priv->len / 8; i++) {
-				src64 = nft_reg_load64(&src[i]);
-				nft_reg_store64(&dst64[i],
-						be64_to_cpu((__force __be64)src64));
-			}
+			src64 = nft_reg_load64(src);
+
+			nft_reg_store64(dst64, be64_to_cpu((__force __be64)src64));
 			break;
 		case NFT_BYTEORDER_HTON:
-			for (i = 0; i < priv->len / 8; i++) {
-				src64 = (__force __u64)
-					cpu_to_be64(nft_reg_load64(&src[i]));
-				nft_reg_store64(&dst64[i], src64);
-			}
+			src64 = (__force __u64)cpu_to_be64(nft_reg_load64(src));
+
+			nft_reg_store64(dst64, src64);
 			break;
 		}
 		break;
@@ -62,24 +52,20 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 	case 4:
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
-			for (i = 0; i < priv->len / 4; i++)
-				dst[i] = ntohl((__force __be32)src[i]);
+			*dst = ntohl((__force __be32)*src);
 			break;
 		case NFT_BYTEORDER_HTON:
-			for (i = 0; i < priv->len / 4; i++)
-				dst[i] = (__force __u32)htonl(src[i]);
+			*dst = (__force __u32)htonl(*src);
 			break;
 		}
 		break;
 	case 2:
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
-			for (i = 0; i < priv->len / 2; i++)
-				d16[i] = ntohs((__force __be16)s16[i]);
+			nft_reg_store16(dst, ntohs(nft_reg_load_be16(src)));
 			break;
 		case NFT_BYTEORDER_HTON:
-			for (i = 0; i < priv->len / 2; i++)
-				d16[i] = (__force __u16)htons(s16[i]);
+			nft_reg_store_be16(dst, htons(nft_reg_load16(src)));
 			break;
 		}
 		break;
@@ -137,20 +123,22 @@ static int nft_byteorder_init(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
-	priv->len = len;
+	/* no longer support multi-reg conversions */
+	if (len != size)
+		return -EOPNOTSUPP;
 
 	err = nft_parse_register_load(ctx, tb[NFTA_BYTEORDER_SREG], &priv->sreg,
-				      priv->len);
+				      len);
 	if (err < 0)
 		return err;
 
 	err = nft_parse_register_store(ctx, tb[NFTA_BYTEORDER_DREG],
 				       &priv->dreg, NULL, NFT_DATA_VALUE,
-				       priv->len);
+				       len);
 	if (err < 0)
 		return err;
 
-	if (nft_reg_overlap(priv->sreg, priv->dreg, priv->len))
+	if (nft_reg_overlap(priv->sreg, priv->dreg, len))
 		return -EINVAL;
 
 	return 0;
@@ -167,10 +155,11 @@ static int nft_byteorder_dump(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_BYTEORDER_OP, htonl(priv->op)))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_BYTEORDER_LEN, htonl(priv->len)))
-		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_BYTEORDER_SIZE, htonl(priv->size)))
 		goto nla_put_failure;
+	/* compatibility for old userspace which permitted size != len */
+	if (nla_put_be32(skb, NFTA_BYTEORDER_LEN, htonl(priv->size)))
+		goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index fa2cc556331c..357513c6dcea 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -78,7 +78,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		break;
 	}
 
-	if (ct == NULL)
+	if (!ct || nf_ct_is_template(ct))
 		goto err;
 
 	switch (priv->key) {
@@ -180,12 +180,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 	tuple = &ct->tuplehash[priv->dir].tuple;
 	switch (priv->key) {
 	case NFT_CT_SRC:
-		memcpy(dest, tuple->src.u3.all,
-		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
+		memcpy(dest, tuple->src.u3.all, priv->len);
 		return;
 	case NFT_CT_DST:
-		memcpy(dest, tuple->dst.u3.all,
-		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
+		memcpy(dest, tuple->dst.u3.all, priv->len);
 		return;
 	case NFT_CT_PROTO_SRC:
 		nft_reg_store16(dest, (__force u16)tuple->src.u.all);
diff --git a/net/netfilter/nft_ct_fast.c b/net/netfilter/nft_ct_fast.c
index e684c8a91848..ecf7b3a404be 100644
--- a/net/netfilter/nft_ct_fast.c
+++ b/net/netfilter/nft_ct_fast.c
@@ -30,7 +30,7 @@ void nft_ct_get_fast_eval(const struct nft_expr *expr,
 		break;
 	}
 
-	if (!ct) {
+	if (!ct || nf_ct_is_template(ct)) {
 		regs->verdict.code = NFT_BREAK;
 		return;
 	}
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 0b987bc2132a..68f7cfbbee06 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -676,7 +676,7 @@ static void nft_tunnel_obj_destroy(const struct nft_ctx *ctx,
 {
 	struct nft_tunnel_obj *priv = nft_obj_data(obj);
 
-	metadata_dst_free(priv->md);
+	dst_release(&priv->md->dst);
 }
 
 static struct nft_object_type nft_tunnel_obj_type;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 466da23e36ff..b32d153e3a18 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -91,7 +91,7 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par)
 
 	if (info->queues_total > 1) {
 		if (info->flags & NFQ_FLAG_CPU_FANOUT) {
-			int cpu = smp_processor_id();
+			int cpu = raw_smp_processor_id();
 
 			queue = info->queuenum + cpu % info->queues_total;
 		} else {