Merge tag 'nf-24-05-29' 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 syzbot reports that nf_reinject() could be called without
         rcu_read_lock() when flushing pending packets at nfnetlink
         queue removal, from Eric Dumazet.

Patch #2 flushes ipset list:set when canceling garbage collection to
         reference to other lists to fix a race, from Jozsef Kadlecsik.

Patch #3 restores q-in-q matching with nft_payload by reverting
         f6ae9f12 ("netfilter: nft_payload: add C-VLAN support").

Patch #4 fixes vlan mangling in skbuff when vlan offload is present
         in skbuff, without this patch nft_payload corrupts packets
         in this case.

Patch #5 fixes possible nul-deref in tproxy no IP address is found in
         netdevice, reported by syzbot and patch from Florian Westphal.

Patch #6 removes a superfluous restriction which prevents loose fib
         lookups from input and forward hooks, from Eric Garver.

My assessment is that patches #1, #2 and #5 address possible kernel
crash, anything else in this batch fixes broken features.

netfilter pull request 24-05-29

* tag 'nf-24-05-29' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nft_fib: allow from forward/input without iif selector
  netfilter: tproxy: bail out if IP has been disabled on the device
  netfilter: nft_payload: skbuff vlan metadata mangle support
  netfilter: nft_payload: restore vlan q-in-q match support
  netfilter: ipset: Add list flush to cancel_gc
  netfilter: nfnetlink_queue: acquire rcu_read_lock() in instance_destroy_rcu()
====================

Link: https://lore.kernel.org/r/20240528225519.1155786-1-pablo@netfilter.orgSigned-off-by: Paolo Abeni <pabeni@redhat.com>

net/ipv4/netfilter/nf_tproxy_ipv4.c

@@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 
 	laddr = 0;
 	indev = __in_dev_get_rcu(skb->dev);
+	if (!indev)
+		return daddr;
 
 	in_dev_for_each_ifa_rcu(ifa, indev) {
 		if (ifa->ifa_flags & IFA_F_SECONDARY)

net/netfilter/ipset/ip_set_list_set.c

@@ -549,6 +549,9 @@ list_set_cancel_gc(struct ip_set *set)
 
 	if (SET_WITH_TIMEOUT(set))
 		timer_shutdown_sync(&map->gc);
+
+	/* Flush list to drop references to other ipsets */
+	list_set_flush(set);
 }
 
 static const struct ip_set_type_variant set_variant = {

net/netfilter/nfnetlink_queue.c

@@ -169,7 +169,9 @@ instance_destroy_rcu(struct rcu_head *head)
 	struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance,
 						   rcu);
 
+	rcu_read_lock();
 	nfqnl_flush(inst, NULL, 0);
+	rcu_read_unlock();
 	kfree(inst);
 	module_put(THIS_MODULE);
 }

net/netfilter/nft_fib.c

@@ -35,11 +35,9 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
 	case NFT_FIB_RESULT_OIFNAME:
-		hooks = (1 << NF_INET_PRE_ROUTING);
-		if (priv->flags & NFTA_FIB_F_IIF) {
-			hooks |= (1 << NF_INET_LOCAL_IN) |
+		hooks = (1 << NF_INET_PRE_ROUTING) |
+			(1 << NF_INET_LOCAL_IN) |
 			(1 << NF_INET_FORWARD);
-		}
 		break;
 	case NFT_FIB_RESULT_ADDRTYPE:
 		if (priv->flags & NFTA_FIB_F_IIF)

net/netfilter/nft_payload.c

@@ -45,36 +45,27 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
 	int mac_off = skb_mac_header(skb) - skb->data;
 	u8 *vlanh, *dst_u8 = (u8 *) d;
 	struct vlan_ethhdr veth;
-	u8 vlan_hlen = 0;
-
-	if ((skb->protocol == htons(ETH_P_8021AD) ||
-	     skb->protocol == htons(ETH_P_8021Q)) &&
-	    offset >= VLAN_ETH_HLEN && offset < VLAN_ETH_HLEN + VLAN_HLEN)
-		vlan_hlen += VLAN_HLEN;
 
 	vlanh = (u8 *) &veth;
-	if (offset < VLAN_ETH_HLEN + vlan_hlen) {
+	if (offset < VLAN_ETH_HLEN) {
 		u8 ethlen = len;
 
-		if (vlan_hlen &&
-		    skb_copy_bits(skb, mac_off, &veth, VLAN_ETH_HLEN) < 0)
-			return false;
-		else if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth))
+		if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth))
 			return false;
 
-		if (offset + len > VLAN_ETH_HLEN + vlan_hlen)
-			ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen;
+		if (offset + len > VLAN_ETH_HLEN)
+			ethlen -= offset + len - VLAN_ETH_HLEN;
 
-		memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen);
+		memcpy(dst_u8, vlanh + offset, ethlen);
 
 		len -= ethlen;
 		if (len == 0)
 			return true;
 
 		dst_u8 += ethlen;
-		offset = ETH_HLEN + vlan_hlen;
+		offset = ETH_HLEN;
 	} else {
-		offset -= VLAN_HLEN + vlan_hlen;
+		offset -= VLAN_HLEN;
 	}
 
 	return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0;
@@ -154,12 +145,12 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
 	return pkt->inneroff;
 }
 
-static bool nft_payload_need_vlan_copy(const struct nft_payload *priv)
+static bool nft_payload_need_vlan_adjust(u32 offset, u32 len)
 {
-	unsigned int len = priv->offset + priv->len;
+	unsigned int boundary = offset + len;
 
 	/* data past ether src/dst requested, copy needed */
-	if (len > offsetof(struct ethhdr, h_proto))
+	if (boundary > offsetof(struct ethhdr, h_proto))
 		return true;
 
 	return false;
@@ -183,7 +174,7 @@ void nft_payload_eval(const struct nft_expr *expr,
 			goto err;
 
 		if (skb_vlan_tag_present(skb) &&
-		    nft_payload_need_vlan_copy(priv)) {
+		    nft_payload_need_vlan_adjust(priv->offset, priv->len)) {
 			if (!nft_payload_copy_vlan(dest, skb,
 						   priv->offset, priv->len))
 				goto err;
@@ -810,21 +801,79 @@ struct nft_payload_set {
 	u8			csum_flags;
 };
 
+/* This is not struct vlan_hdr. */
+struct nft_payload_vlan_hdr {
+	__be16			h_vlan_proto;
+	__be16			h_vlan_TCI;
+};
+
+static bool
+nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len,
+		     int *vlan_hlen)
+{
+	struct nft_payload_vlan_hdr *vlanh;
+	__be16 vlan_proto;
+	u16 vlan_tci;
+
+	if (offset >= offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto)) {
+		*vlan_hlen = VLAN_HLEN;
+		return true;
+	}
+
+	switch (offset) {
+	case offsetof(struct vlan_ethhdr, h_vlan_proto):
+		if (len == 2) {
+			vlan_proto = nft_reg_load_be16(src);
+			skb->vlan_proto = vlan_proto;
+		} else if (len == 4) {
+			vlanh = (struct nft_payload_vlan_hdr *)src;
+			__vlan_hwaccel_put_tag(skb, vlanh->h_vlan_proto,
+					       ntohs(vlanh->h_vlan_TCI));
+		} else {
+			return false;
+		}
+		break;
+	case offsetof(struct vlan_ethhdr, h_vlan_TCI):
+		if (len != 2)
+			return false;
+
+		vlan_tci = ntohs(nft_reg_load_be16(src));
+		skb->vlan_tci = vlan_tci;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
 static void nft_payload_set_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
 {
 	const struct nft_payload_set *priv = nft_expr_priv(expr);
-	struct sk_buff *skb = pkt->skb;
 	const u32 *src = &regs->data[priv->sreg];
-	int offset, csum_offset;
+	int offset, csum_offset, vlan_hlen = 0;
+	struct sk_buff *skb = pkt->skb;
 	__wsum fsum, tsum;
 
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
 		if (!skb_mac_header_was_set(skb))
 			goto err;
-		offset = skb_mac_header(skb) - skb->data;
+
+		if (skb_vlan_tag_present(skb) &&
+		    nft_payload_need_vlan_adjust(priv->offset, priv->len)) {
+			if (!nft_payload_set_vlan(src, skb,
+						  priv->offset, priv->len,
+						  &vlan_hlen))
+				goto err;
+
+			if (!vlan_hlen)
+				return;
+		}
+
+		offset = skb_mac_header(skb) - skb->data - vlan_hlen;
 		break;
 	case NFT_PAYLOAD_NETWORK_HEADER:
 		offset = skb_network_offset(skb);