Merge tag 'net-6.12-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Current release - new code bugs:

   - eth: mlx5: HWS, don't destroy more bwc queue locks than allocated

  Previous releases - regressions:

   - ipv4: give an IPv4 dev to blackhole_netdev

   - udp: compute L4 checksum as usual when not segmenting the skb

   - tcp/dccp: don't use timer_pending() in reqsk_queue_unlink().

   - eth: mlx5e: don't call cleanup on profile rollback failure

   - eth: microchip: vcap api: fix memory leaks in
     vcap_api_encode_rule_test()

   - eth: enetc: disable Tx BD rings after they are empty

   - eth: macb: avoid 20s boot delay by skipping MDIO bus registration
     for fixed-link PHY

  Previous releases - always broken:

   - posix-clock: fix missing timespec64 check in pc_clock_settime()

   - genetlink: hold RCU in genlmsg_mcast()

   - mptcp: prevent MPC handshake on port-based signal endpoints

   - eth: vmxnet3: fix packet corruption in vmxnet3_xdp_xmit_frame

   - eth: stmmac: dwmac-tegra: fix link bring-up sequence

   - eth: bcmasp: fix potential memory leak in bcmasp_xmit()

  Misc:

   - add Andrew Lunn as a co-maintainer of all networking drivers"

* tag 'net-6.12-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (47 commits)
  net/mlx5e: Don't call cleanup on profile rollback failure
  net/mlx5: Unregister notifier on eswitch init failure
  net/mlx5: Fix command bitmask initialization
  net/mlx5: Check for invalid vector index on EQ creation
  net/mlx5: HWS, use lock classes for bwc locks
  net/mlx5: HWS, don't destroy more bwc queue locks than allocated
  net/mlx5: HWS, fixed double free in error flow of definer layout
  net/mlx5: HWS, removed wrong access to a number of rules variable
  mptcp: pm: fix UaF read in mptcp_pm_nl_rm_addr_or_subflow
  net: ethernet: mtk_eth_soc: fix memory corruption during fq dma init
  vmxnet3: Fix packet corruption in vmxnet3_xdp_xmit_frame
  net: dsa: vsc73xx: fix reception from VLAN-unaware bridges
  net: ravb: Only advertise Rx/Tx timestamps if hardware supports it
  net: microchip: vcap api: Fix memory leaks in vcap_api_encode_rule_test()
  net: phy: mdio-bcm-unimac: Add BCM6846 support
  dt-bindings: net: brcm,unimac-mdio: Add bcm6846-mdio
  udp: Compute L4 checksum as usual when not segmenting the skb
  genetlink: hold RCU in genlmsg_mcast()
  net: dsa: mv88e6xxx: Fix the max_vid definition for the MV88E6361
  tcp/dccp: Don't use timer_pending() in reqsk_queue_unlink().
  ...

14 files changed, 87 insertions, 42 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ab76744383cf..7cf5f7d0d0de 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -298,17 +298,19 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	/* Account for reference dev->ip_ptr (below) */
 	refcount_set(&in_dev->refcnt, 1);
 
-	err = devinet_sysctl_register(in_dev);
-	if (err) {
-		in_dev->dead = 1;
-		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
-		in_dev_put(in_dev);
-		in_dev = NULL;
-		goto out;
+	if (dev != blackhole_netdev) {
+		err = devinet_sysctl_register(in_dev);
+		if (err) {
+			in_dev->dead = 1;
+			neigh_parms_release(&arp_tbl, in_dev->arp_parms);
+			in_dev_put(in_dev);
+			in_dev = NULL;
+			goto out;
+		}
+		ip_mc_init_dev(in_dev);
+		if (dev->flags & IFF_UP)
+			ip_mc_up(in_dev);
 	}
-	ip_mc_init_dev(in_dev);
-	if (dev->flags & IFF_UP)
-		ip_mc_up(in_dev);
 
 	/* we can receive as soon as ip_ptr is set -- do this last */
 	rcu_assign_pointer(dev->ip_ptr, in_dev);
@@ -347,6 +349,19 @@ static void inetdev_destroy(struct in_device *in_dev)
 	in_dev_put(in_dev);
 }
 
+static int __init inet_blackhole_dev_init(void)
+{
+	int err = 0;
+
+	rtnl_lock();
+	if (!inetdev_init(blackhole_netdev))
+		err = -ENOMEM;
+	rtnl_unlock();
+
+	return err;
+}
+late_initcall(inet_blackhole_dev_init);
+
 int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
 {
 	const struct in_ifaddr *ifa;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2c5632d4fddb..2b698f8419fe 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1045,21 +1045,31 @@ static bool reqsk_queue_unlink(struct request_sock *req)
 		found = __sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
 	}
-	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
-		reqsk_put(req);
+
 	return found;
 }
 
-bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+static bool __inet_csk_reqsk_queue_drop(struct sock *sk,
+					struct request_sock *req,
+					bool from_timer)
 {
 	bool unlinked = reqsk_queue_unlink(req);
 
+	if (!from_timer && timer_delete_sync(&req->rsk_timer))
+		reqsk_put(req);
+
 	if (unlinked) {
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
 		reqsk_put(req);
 	}
+
 	return unlinked;
 }
+
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+{
+	return __inet_csk_reqsk_queue_drop(sk, req, false);
+}
 EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
 
 void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
@@ -1152,7 +1162,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 
 		if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) {
 			/* delete timer */
-			inet_csk_reqsk_queue_drop(sk_listener, nreq);
+			__inet_csk_reqsk_queue_drop(sk_listener, nreq, true);
 			goto no_ownership;
 		}
 
@@ -1178,7 +1188,8 @@ no_ownership:
 	}
 
 drop:
-	inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
+	__inet_csk_reqsk_queue_drop(sk_listener, oreq, true);
+	reqsk_put(req);
 }
 
 static bool reqsk_queue_hash_req(struct request_sock *req,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8accbf4cb295..2849b273b131 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -951,8 +951,10 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
 			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
 								 cork->gso_size);
+
+			/* Don't checksum the payload, skb will get segmented */
+			goto csum_partial;
 		}
-		goto csum_partial;
 	}
 
 	if (is_udplite)  				 /*     UDP-Lite      */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 52dfbb2ff1a8..0cef8ae5d1ea 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1266,8 +1266,10 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
 			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
 								 cork->gso_size);
+
+			/* Don't checksum the payload, skb will get segmented */
+			goto csum_partial;
 		}
-		goto csum_partial;
 	}
 
 	if (is_udplite)
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 284f1dec1b56..59457c0c14aa 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -116,7 +116,7 @@ static int l2tp_tunnel_notify(struct genl_family *family,
 				  NLM_F_ACK, tunnel, cmd);
 
 	if (ret >= 0) {
-		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		ret = genlmsg_multicast_allns(family, msg, 0, 0);
 		/* We don't care if no one is listening */
 		if (ret == -ESRCH)
 			ret = 0;
@@ -144,7 +144,7 @@ static int l2tp_session_notify(struct genl_family *family,
 				   NLM_F_ACK, session, cmd);
 
 	if (ret >= 0) {
-		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		ret = genlmsg_multicast_allns(family, msg, 0, 0);
 		/* We don't care if no one is listening */
 		if (ret == -ESRCH)
 			ret = 0;
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index ad88bd3c58df..19eb9292bd60 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -17,6 +17,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK),
 	SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP),
 	SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED),
+	SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT),
 	SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT),
 	SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
 	SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 3206cdda8bb1..128282982843 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -12,6 +12,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */
 	MPTCP_MIB_MPCAPABLEACTIVEDROP,	/* Client-side fallback due to a MPC drop */
 	MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */
+	MPTCP_MIB_MPCAPABLEENDPATTEMPT,	/* Prohibited MPC to port-based endp */
 	MPTCP_MIB_TOKENFALLBACKINIT,	/* Could not init/allocate token */
 	MPTCP_MIB_RETRANSSEGS,		/* Segments retransmitted at the MPTCP-level */
 	MPTCP_MIB_JOINNOTOKEN,		/* Received MP_JOIN but the token was not found */
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index f6f0a38a0750..db586a5b3866 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -873,12 +873,12 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
+			removed |= subflow->request_join;
 
 			/* the following takes care of updating the subflows counter */
 			mptcp_close_ssk(sk, ssk, subflow);
 			spin_lock_bh(&msk->pm.lock);
 
-			removed |= subflow->request_join;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW)
 				__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
@@ -1121,6 +1121,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	 */
 	inet_sk_state_store(newsk, TCP_LISTEN);
 	lock_sock(ssk);
+	WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true);
 	err = __inet_listen_sk(ssk, backlog);
 	if (!err)
 		mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 74417aae08d0..568a72702b08 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -535,6 +535,7 @@ struct mptcp_subflow_context {
 		__unused : 8;
 	bool	data_avail;
 	bool	scheduled;
+	bool	pm_listener;	    /* a listener managed by the kernel PM? */
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 25dde81bcb75..6170f2fff71e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -132,6 +132,13 @@ static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
 	}
 }
 
+static int subflow_reset_req_endp(struct request_sock *req, struct sk_buff *skb)
+{
+	SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEENDPATTEMPT);
+	subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+	return -EPERM;
+}
+
 /* Init mptcp request socket.
  *
  * Returns an error code if a JOIN has failed and a TCP reset
@@ -165,6 +172,8 @@ static int subflow_check_req(struct request_sock *req,
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
+		if (unlikely(listener->pm_listener))
+			return subflow_reset_req_endp(req, skb);
 		if (opt_mp_join)
 			return 0;
 	} else if (opt_mp_join) {
@@ -172,6 +181,8 @@ static int subflow_check_req(struct request_sock *req,
 
 		if (mp_opt.backup)
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
+	} else if (unlikely(listener->pm_listener)) {
+		return subflow_reset_req_endp(req, skb);
 	}
 
 	if (opt_mp_capable && listener->request_mptcp) {
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index feb54c63a116..07ad65774fe2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1501,15 +1501,11 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 	if (IS_ERR(msg))
 		return PTR_ERR(msg);
 
-	if (!family->netnsok) {
+	if (!family->netnsok)
 		genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0,
 					0, GFP_KERNEL);
-	} else {
-		rcu_read_lock();
-		genlmsg_multicast_allns(&genl_ctrl, msg, 0,
-					0, GFP_ATOMIC);
-		rcu_read_unlock();
-	}
+	else
+		genlmsg_multicast_allns(&genl_ctrl, msg, 0, 0);
 
 	return 0;
 }
@@ -1929,23 +1925,23 @@ problem:
 
 core_initcall(genl_init);
 
-static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
-			 gfp_t flags)
+static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group)
 {
 	struct sk_buff *tmp;
 	struct net *net, *prev = NULL;
 	bool delivered = false;
 	int err;
 
+	rcu_read_lock();
 	for_each_net_rcu(net) {
 		if (prev) {
-			tmp = skb_clone(skb, flags);
+			tmp = skb_clone(skb, GFP_ATOMIC);
 			if (!tmp) {
 				err = -ENOMEM;
 				goto error;
 			}
 			err = nlmsg_multicast(prev->genl_sock, tmp,
-					      portid, group, flags);
+					      portid, group, GFP_ATOMIC);
 			if (!err)
 				delivered = true;
 			else if (err != -ESRCH)
@@ -1954,27 +1950,31 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 
 		prev = net;
 	}
+	err = nlmsg_multicast(prev->genl_sock, skb, portid, group, GFP_ATOMIC);
+
+	rcu_read_unlock();
 
-	err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
 	if (!err)
 		delivered = true;
 	else if (err != -ESRCH)
 		return err;
 	return delivered ? 0 : -ESRCH;
  error:
+	rcu_read_unlock();
+
 	kfree_skb(skb);
 	return err;
 }
 
 int genlmsg_multicast_allns(const struct genl_family *family,
 			    struct sk_buff *skb, u32 portid,
-			    unsigned int group, gfp_t flags)
+			    unsigned int group)
 {
 	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return -EINVAL;
 
 	group = family->mcgrp_offset + group;
-	return genlmsg_mcast(skb, portid, group, flags);
+	return genlmsg_mcast(skb, portid, group);
 }
 EXPORT_SYMBOL(genlmsg_multicast_allns);
 
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 1dd362326c0a..a04aa0e882f8 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -753,7 +753,7 @@ static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid)
 
 	write_lock(&sn->pnetids_ndev.lock);
 	list_for_each_entry(pi, &sn->pnetids_ndev.list, list) {
-		if (smc_pnet_match(pnetid, pe->pnetid)) {
+		if (smc_pnet_match(pnetid, pi->pnetid)) {
 			refcount_inc(&pi->refcnt);
 			kfree(pe);
 			goto unlock;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 0021065a600a..994c0cd4fddb 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -648,8 +648,10 @@ void smc_wr_free_link(struct smc_link *lnk)
 	smc_wr_tx_wait_no_pending_sends(lnk);
 	percpu_ref_kill(&lnk->wr_reg_refs);
 	wait_for_completion(&lnk->reg_ref_comp);
+	percpu_ref_exit(&lnk->wr_reg_refs);
 	percpu_ref_kill(&lnk->wr_tx_refs);
 	wait_for_completion(&lnk->tx_ref_comp);
+	percpu_ref_exit(&lnk->wr_tx_refs);
 
 	if (lnk->wr_rx_dma_addr) {
 		ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
@@ -912,11 +914,13 @@ int smc_wr_create_link(struct smc_link *lnk)
 	init_waitqueue_head(&lnk->wr_reg_wait);
 	rc = percpu_ref_init(&lnk->wr_reg_refs, smcr_wr_reg_refs_free, 0, GFP_KERNEL);
 	if (rc)
-		goto dma_unmap;
+		goto cancel_ref;
 	init_completion(&lnk->reg_ref_comp);
 	init_waitqueue_head(&lnk->wr_rx_empty_wait);
 	return rc;
 
+cancel_ref:
+	percpu_ref_exit(&lnk->wr_tx_refs);
 dma_unmap:
 	if (lnk->wr_rx_v2_dma_addr) {
 		ib_dma_unmap_single(ibdev, lnk->wr_rx_v2_dma_addr,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 9ab777e0bd4d..d7d099f7118a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -17986,10 +17986,8 @@ void nl80211_common_reg_change_event(enum nl80211_commands cmd_id,
 
 	genlmsg_end(msg, hdr);
 
-	rcu_read_lock();
 	genlmsg_multicast_allns(&nl80211_fam, msg, 0,
-				NL80211_MCGRP_REGULATORY, GFP_ATOMIC);
-	rcu_read_unlock();
+				NL80211_MCGRP_REGULATORY);
 
 	return;
 
@@ -18722,10 +18720,8 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy,
 
 	genlmsg_end(msg, hdr);
 
-	rcu_read_lock();
 	genlmsg_multicast_allns(&nl80211_fam, msg, 0,
-				NL80211_MCGRP_REGULATORY, GFP_ATOMIC);
-	rcu_read_unlock();
+				NL80211_MCGRP_REGULATORY);
 
 	return;