Merge tag 'net-6.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from wireless and netfilter

  Current release - regressions:

   - udp: fall back to software USO if IPv6 extension headers are
     present

   - wifi: iwlwifi: correctly lookup DMA address in SG table

  Current release - new code bugs:

   - eth: mlx5e: fix queue stats access to non-existing channels splat

  Previous releases - regressions:

   - eth: mlx5e: take state lock during tx timeout reporter

   - eth: mlxbf_gige: disable RX filters until RX path initialized

   - eth: igc: fix reset adapter logics when tx mode change

  Previous releases - always broken:

   - tcp: update window clamping condition

   - netfilter:
      - nf_queue: drop packets with cloned unconfirmed conntracks
      - nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests

   - vsock: fix recursive ->recvmsg calls

   - dsa: vsc73xx: fix MDIO bus access and PHY opera

   - eth: gtp: pull network headers in gtp_dev_xmit()

   - eth: igc: fix packet still tx after gate close by reducing i226 MAC
     retry buffer

   - eth: mana: fix RX buf alloc_size alignment and atomic op panic

   - eth: hns3: fix a deadlock problem when config TC during resetting"

* tag 'net-6.11-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (58 commits)
  net: hns3: use correct release function during uninitialization
  net: hns3: void array out of bound when loop tnl_num
  net: hns3: fix a deadlock problem when config TC during resetting
  net: hns3: use the user's cfg after reset
  net: hns3: fix wrong use of semaphore up
  selftests: net: lib: kill PIDs before del netns
  pse-core: Conditionally set current limit during PI regulator registration
  net: thunder_bgx: Fix netdev structure allocation
  net: ethtool: Allow write mechanism of LPL and both LPL and EPL
  vsock: fix recursive ->recvmsg calls
  selftest: af_unix: Fix kselftest compilation warnings
  netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests
  netfilter: nf_tables: Introduce nf_tables_getobj_single
  netfilter: nf_tables: Audit log dump reset after the fact
  selftests: netfilter: add test for br_netfilter+conntrack+queue combination
  netfilter: nf_queue: drop packets with cloned unconfirmed conntracks
  netfilter: flowtable: initialise extack before use
  netfilter: nfnetlink: Initialise extack before use in ACKs
  netfilter: allow ipv6 fragments to arrive on different devices
  tcp: Update window clamping condition
  ...

13 files changed, 222 insertions, 101 deletions

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 09f6a773a708..8f9c19d992ac 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -622,8 +622,12 @@ static unsigned int br_nf_local_in(void *priv,
 	if (likely(nf_ct_is_confirmed(ct)))
 		return NF_ACCEPT;
 
+	if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) {
+		nf_reset_ct(skb);
+		return NF_ACCEPT;
+	}
+
 	WARN_ON_ONCE(skb_shared(skb));
-	WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
 
 	/* We can't call nf_confirm here, it would create a dependency
 	 * on nf_conntrack module.
diff --git a/net/core/dev.c b/net/core/dev.c
index 751d9b70e6ad..f66e61407883 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9912,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper,
 	}
 }
 
+static bool netdev_has_ip_or_hw_csum(netdev_features_t features)
+{
+	netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	bool ip_csum = (features & ip_csum_mask) == ip_csum_mask;
+	bool hw_csum = features & NETIF_F_HW_CSUM;
+
+	return ip_csum || hw_csum;
+}
+
 static netdev_features_t netdev_fix_features(struct net_device *dev,
 	netdev_features_t features)
 {
@@ -9993,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		features &= ~NETIF_F_LRO;
 	}
 
-	if (features & NETIF_F_HW_TLS_TX) {
-		bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
-			(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
-		bool hw_csum = features & NETIF_F_HW_CSUM;
-
-		if (!ip_csum && !hw_csum) {
-			netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
-			features &= ~NETIF_F_HW_TLS_TX;
-		}
+	if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) {
+		netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+		features &= ~NETIF_F_HW_TLS_TX;
 	}
 
 	if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) {
@@ -10009,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		features &= ~NETIF_F_HW_TLS_RX;
 	}
 
+	if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) {
+		netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n");
+		features &= ~NETIF_F_GSO_UDP_L4;
+	}
+
 	return features;
 }
 
diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c
index ae4b4b28a601..655ff5224ffa 100644
--- a/net/ethtool/cmis_fw_update.c
+++ b/net/ethtool/cmis_fw_update.c
@@ -35,7 +35,10 @@ struct cmis_cdb_fw_mng_features_rpl {
 	__be16	resv7;
 };
 
-#define CMIS_CDB_FW_WRITE_MECHANISM_LPL	0x01
+enum cmis_cdb_fw_write_mechanism {
+	CMIS_CDB_FW_WRITE_MECHANISM_LPL		= 0x01,
+	CMIS_CDB_FW_WRITE_MECHANISM_BOTH	= 0x11,
+};
 
 static int
 cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb,
@@ -64,7 +67,8 @@ cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb,
 	}
 
 	rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload;
-	if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL)) {
+	if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL ||
+	      rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) {
 		ethnl_module_fw_flash_ntf_err(dev, ntf_params,
 					      "Write LPL is not supported",
 					      NULL);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e2b9583ed96a..e37488d3453f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 		 */
 		if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
 			u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
+			u8 old_ratio = tcp_sk(sk)->scaling_ratio;
 
 			do_div(val, skb->truesize);
 			tcp_sk(sk)->scaling_ratio = val ? val : 1;
+
+			if (old_ratio != tcp_sk(sk)->scaling_ratio)
+				WRITE_ONCE(tcp_sk(sk)->window_clamp,
+					   tcp_win_from_space(sk, sk->sk_rcvbuf));
 		}
 		icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
 					       tcp_sk(sk)->advmss);
@@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	 * <prev RTT . ><current RTT .. ><next RTT .... >
 	 */
 
-	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
+	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		u64 rcvwin, grow;
 		int rcvbuf;
 
@@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 		rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
 			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-			if (rcvbuf > sk->sk_rcvbuf) {
-				WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
-
-				/* Make the window clamp follow along.  */
-				WRITE_ONCE(tp->window_clamp,
-					   tcp_win_from_space(sk, rcvbuf));
-			}
-		} else {
-			/* Make the window clamp follow along while being bounded
-			 * by SO_RCVBUF.
-			 */
-			int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
+		if (rcvbuf > sk->sk_rcvbuf) {
+			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
-			if (clamp > tp->window_clamp)
-				WRITE_ONCE(tp->window_clamp, clamp);
+			/* Make the window clamp follow along.  */
+			WRITE_ONCE(tp->window_clamp,
+				   tcp_win_from_space(sk, rcvbuf));
 		}
 	}
 	tp->rcvq_space.space = copied;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index bc8a9da750fe..b254a5dadfcf 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -282,6 +282,12 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 		     skb_transport_header(gso_skb)))
 		return ERR_PTR(-EINVAL);
 
+	/* We don't know if egress device can segment and checksum the packet
+	 * when IPv6 extension headers are present. Fall back to software GSO.
+	 */
+	if (gso_skb->ip_summed != CHECKSUM_PARTIAL)
+		features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK);
+
 	if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
 		/* Packet is from an untrusted source, reset gso_segs. */
 		skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6f0844c9315d..4120e67a8ce6 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
 	};
 	struct inet_frag_queue *q;
 
+	if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+					    IPV6_ADDR_LINKLOCAL)))
+		key.iif = 0;
+
 	q = inet_frag_find(nf_frag->fqdir, &key);
 	if (!q)
 		return NULL;
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index 3ae46b545d2c..2d3efb405437 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk)
 		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
 		nla_total_size_64bit(8) +	/* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
 		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
-		nla_total_size(2) +	/* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
 		nla_total_size(2) +	/* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
 		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_FLAGS */
 		nla_total_size(1) +	/* MPTCP_SUBFLOW_ATTR_ID_REM */
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index ff1a4e36c2b5..e06bc36f49fe 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
 				 struct list_head *block_cb_list)
 {
 	struct flow_cls_offload cls_flow = {};
+	struct netlink_ext_ack extack = {};
 	struct flow_block_cb *block_cb;
-	struct netlink_ext_ack extack;
 	__be16 proto = ETH_P_ALL;
 	int err, i = 0;
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 481ee78e77bc..0a2f79346958 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8020,6 +8020,19 @@ cont:
 	return skb->len;
 }
 
+static int nf_tables_dumpreset_obj(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk));
+	int ret;
+
+	mutex_lock(&nft_net->commit_mutex);
+	ret = nf_tables_dump_obj(skb, cb);
+	mutex_unlock(&nft_net->commit_mutex);
+
+	return ret;
+}
+
 static int nf_tables_dump_obj_start(struct netlink_callback *cb)
 {
 	struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -8036,12 +8049,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)
 	if (nla[NFTA_OBJ_TYPE])
 		ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 
-	if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
-		ctx->reset = true;
-
 	return 0;
 }
 
+static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb)
+{
+	struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
+
+	ctx->reset = true;
+
+	return nf_tables_dump_obj_start(cb);
+}
+
 static int nf_tables_dump_obj_done(struct netlink_callback *cb)
 {
 	struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -8052,8 +8071,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb)
 }
 
 /* called with rcu_read_lock held */
-static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
-			    const struct nlattr * const nla[])
+static struct sk_buff *
+nf_tables_getobj_single(u32 portid, const struct nfnl_info *info,
+			const struct nlattr * const nla[], bool reset)
 {
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_cur(info->net);
@@ -8062,72 +8082,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
 	struct net *net = info->net;
 	struct nft_object *obj;
 	struct sk_buff *skb2;
-	bool reset = false;
 	u32 objtype;
 	int err;
 
-	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
-		struct netlink_dump_control c = {
-			.start = nf_tables_dump_obj_start,
-			.dump = nf_tables_dump_obj,
-			.done = nf_tables_dump_obj_done,
-			.module = THIS_MODULE,
-			.data = (void *)nla,
-		};
-
-		return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
-	}
-
 	if (!nla[NFTA_OBJ_NAME] ||
 	    !nla[NFTA_OBJ_TYPE])
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0);
 	if (IS_ERR(table)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
-		return PTR_ERR(table);
+		return ERR_CAST(table);
 	}
 
 	objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 	obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
 	if (IS_ERR(obj)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
-		return PTR_ERR(obj);
+		return ERR_CAST(obj);
 	}
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (!skb2)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
-		reset = true;
+	err = nf_tables_fill_obj_info(skb2, net, portid,
+				      info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
+				      family, table, obj, reset);
+	if (err < 0) {
+		kfree_skb(skb2);
+		return ERR_PTR(err);
+	}
 
-	if (reset) {
-		const struct nftables_pernet *nft_net;
-		char *buf;
+	return skb2;
+}
 
-		nft_net = nft_pernet(net);
-		buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq);
+static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
+			    const struct nlattr * const nla[])
+{
+	u32 portid = NETLINK_CB(skb).portid;
+	struct sk_buff *skb2;
 
-		audit_log_nfcfg(buf,
-				family,
-				1,
-				AUDIT_NFT_OP_OBJ_RESET,
-				GFP_ATOMIC);
-		kfree(buf);
+	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.start = nf_tables_dump_obj_start,
+			.dump = nf_tables_dump_obj,
+			.done = nf_tables_dump_obj_done,
+			.module = THIS_MODULE,
+			.data = (void *)nla,
+		};
+
+		return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
 	}
 
-	err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid,
-				      info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
-				      family, table, obj, reset);
-	if (err < 0)
-		goto err_fill_obj_info;
+	skb2 = nf_tables_getobj_single(portid, info, nla, false);
+	if (IS_ERR(skb2))
+		return PTR_ERR(skb2);
 
-	return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
+	return nfnetlink_unicast(skb2, info->net, portid);
+}
 
-err_fill_obj_info:
-	kfree_skb(skb2);
-	return err;
+static int nf_tables_getobj_reset(struct sk_buff *skb,
+				  const struct nfnl_info *info,
+				  const struct nlattr * const nla[])
+{
+	struct nftables_pernet *nft_net = nft_pernet(info->net);
+	u32 portid = NETLINK_CB(skb).portid;
+	struct net *net = info->net;
+	struct sk_buff *skb2;
+	char *buf;
+
+	if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.start = nf_tables_dumpreset_obj_start,
+			.dump = nf_tables_dumpreset_obj,
+			.done = nf_tables_dump_obj_done,
+			.module = THIS_MODULE,
+			.data = (void *)nla,
+		};
+
+		return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+	}
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+	rcu_read_unlock();
+	mutex_lock(&nft_net->commit_mutex);
+	skb2 = nf_tables_getobj_single(portid, info, nla, true);
+	mutex_unlock(&nft_net->commit_mutex);
+	rcu_read_lock();
+	module_put(THIS_MODULE);
+
+	if (IS_ERR(skb2))
+		return PTR_ERR(skb2);
+
+	buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
+			nla_len(nla[NFTA_OBJ_TABLE]),
+			(char *)nla_data(nla[NFTA_OBJ_TABLE]),
+			nft_net->base_seq);
+	audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
+			AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
+	kfree(buf);
+
+	return nfnetlink_unicast(skb2, net, portid);
 }
 
 static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
@@ -9410,7 +9467,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_obj_policy,
 	},
 	[NFT_MSG_GETOBJ_RESET] = {
-		.call		= nf_tables_getobj,
+		.call		= nf_tables_getobj_reset,
 		.type		= NFNL_CB_RCU,
 		.attr_count	= NFTA_OBJ_MAX,
 		.policy		= nft_obj_policy,
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4abf660c7baf..932b3ddb34f1 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -427,8 +427,10 @@ replay_abort:
 
 	nfnl_unlock(subsys_id);
 
-	if (nlh->nlmsg_flags & NLM_F_ACK)
+	if (nlh->nlmsg_flags & NLM_F_ACK) {
+		memset(&extack, 0, sizeof(extack));
 		nfnl_err_add(&err_list, nlh, 0, &extack);
+	}
 
 	while (skb->len >= nlmsg_total_size(0)) {
 		int msglen, type;
@@ -577,6 +579,7 @@ done:
 			ss->abort(net, oskb, NFNL_ABORT_NONE);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		} else if (nlh->nlmsg_flags & NLM_F_ACK) {
+			memset(&extack, 0, sizeof(extack));
 			nfnl_err_add(&err_list, nlh, 0, &extack);
 		}
 	} else {
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 55e28e1da66e..e0716da256bf 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry)
 {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	static const unsigned long flags = IPS_CONFIRMED | IPS_DYING;
-	const struct nf_conn *ct = (void *)skb_nfct(entry->skb);
+	struct nf_conn *ct = (void *)skb_nfct(entry->skb);
+	unsigned long status;
+	unsigned int use;
 
-	if (ct && ((ct->status & flags) == IPS_DYING))
+	if (!ct)
+		return false;
+
+	status = READ_ONCE(ct->status);
+	if ((status & flags) == IPS_DYING)
 		return true;
+
+	if (status & IPS_CONFIRMED)
+		return false;
+
+	/* in some cases skb_clone() can occur after initial conntrack
+	 * pickup, but conntrack assumes exclusive skb->_nfct ownership for
+	 * unconfirmed entries.
+	 *
+	 * This happens for br_netfilter and with ip multicast routing.
+	 * We can't be solved with serialization here because one clone could
+	 * have been queued for local delivery.
+	 */
+	use = refcount_read(&ct->ct_general.use);
+	if (likely(use == 1))
+		return false;
+
+	/* Can't decrement further? Exclusive ownership. */
+	if (!refcount_dec_not_one(&ct->ct_general.use))
+		return false;
+
+	skb_set_nfct(entry->skb, 0);
+	/* No nf_ct_put(): we already decremented .use and it cannot
+	 * drop down to 0.
+	 */
+	return true;
 #endif
 	return false;
 }
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 4b040285aa78..0ff9b2dd86ba 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1270,25 +1270,28 @@ out:
 	return err;
 }
 
+int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+			  size_t len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct vsock_sock *vsk = vsock_sk(sk);
+
+	return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+}
+
 int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 			size_t len, int flags)
 {
 #ifdef CONFIG_BPF_SYSCALL
+	struct sock *sk = sock->sk;
 	const struct proto *prot;
-#endif
-	struct vsock_sock *vsk;
-	struct sock *sk;
 
-	sk = sock->sk;
-	vsk = vsock_sk(sk);
-
-#ifdef CONFIG_BPF_SYSCALL
 	prot = READ_ONCE(sk->sk_prot);
 	if (prot != &vsock_proto)
 		return prot->recvmsg(sk, msg, len, flags, NULL);
 #endif
 
-	return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+	return __vsock_dgram_recvmsg(sock, msg, len, flags);
 }
 EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
 
@@ -2174,15 +2177,12 @@ out:
 }
 
 int
-vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
-			  int flags)
+__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			    int flags)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
 	const struct vsock_transport *transport;
-#ifdef CONFIG_BPF_SYSCALL
-	const struct proto *prot;
-#endif
 	int err;
 
 	sk = sock->sk;
@@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		goto out;
 	}
 
-#ifdef CONFIG_BPF_SYSCALL
-	prot = READ_ONCE(sk->sk_prot);
-	if (prot != &vsock_proto) {
-		release_sock(sk);
-		return prot->recvmsg(sk, msg, len, flags, NULL);
-	}
-#endif
-
 	if (sk->sk_type == SOCK_STREAM)
 		err = __vsock_stream_recvmsg(sk, msg, len, flags);
 	else
@@ -2250,6 +2242,22 @@ out:
 	release_sock(sk);
 	return err;
 }
+
+int
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	struct sock *sk = sock->sk;
+	const struct proto *prot;
+
+	prot = READ_ONCE(sk->sk_prot);
+	if (prot != &vsock_proto)
+		return prot->recvmsg(sk, msg, len, flags, NULL);
+#endif
+
+	return __vsock_connectible_recvmsg(sock, msg, len, flags);
+}
 EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg);
 
 static int vsock_set_rcvlowat(struct sock *sk, int val)
diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c
index a3c97546ab84..c42c5cc18f32 100644
--- a/net/vmw_vsock/vsock_bpf.c
+++ b/net/vmw_vsock/vsock_bpf.c
@@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int
 	int err;
 
 	if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)
-		err = vsock_connectible_recvmsg(sock, msg, len, flags);
+		err = __vsock_connectible_recvmsg(sock, msg, len, flags);
 	else if (sk->sk_type == SOCK_DGRAM)
-		err = vsock_dgram_recvmsg(sock, msg, len, flags);
+		err = __vsock_dgram_recvmsg(sock, msg, len, flags);
 	else
 		err = -EPROTOTYPE;