Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts or adjacent changes.

Link: https://patch.msgid.link/20240808170148.3629934-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 116 insertions, 54 deletions

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index a31d39a821f4..e79cd40bd079 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3019,6 +3019,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev)
 	} else if (hci_is_adv_monitoring(hdev)) {
 		window = hdev->le_scan_window_adv_monitor;
 		interval = hdev->le_scan_int_adv_monitor;
+
+		/* Disable duplicates filter when scanning for advertisement
+		 * monitor for the following reasons.
+		 *
+		 * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm
+		 * controllers ignore RSSI_Sampling_Period when the duplicates
+		 * filter is enabled.
+		 *
+		 * For SW pattern filtering, when we're not doing interleaved
+		 * scanning, it is necessary to disable duplicates filter,
+		 * otherwise hosts can only receive one advertisement and it's
+		 * impossible to know if a peer is still in range.
+		 */
+		filter_dups = LE_SCAN_FILTER_DUP_DISABLE;
 	} else {
 		window = hdev->le_scan_window;
 		interval = hdev->le_scan_interval;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c3c26bbb5dda..9988ba382b68 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6774,6 +6774,7 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
 	bt_cb(skb)->l2cap.psm = psm;
 
 	if (!chan->ops->recv(chan, skb)) {
+		l2cap_chan_unlock(chan);
 		l2cap_chan_put(chan);
 		return;
 	}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 9a1cb5079a7a..b2ae0d2434d2 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port)
 {
 	struct net_bridge *br = port->br;
 	struct net_bridge_port_group *pg;
-	HLIST_HEAD(deleted_head);
 	struct hlist_node *n;
 
 	/* Take care of the remaining groups, only perm ones should be left */
 	spin_lock_bh(&br->multicast_lock);
 	hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
 		br_multicast_find_del_pg(br, pg);
-	hlist_move_list(&br->mcast_gc_list, &deleted_head);
 	spin_unlock_bh(&br->multicast_lock);
-	br_multicast_gc(&deleted_head);
+	flush_work(&br->mcast_gc_work);
 	br_multicast_port_ctx_deinit(&port->multicast_ctx);
 	free_percpu(port->mcast_stats);
 }
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 8ec35194bfcb..ab150641142a 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent)
 	 * override the existing timer.
 	 */
 	if (test_bit(LW_URGENT, &linkwatch_flags))
-		mod_delayed_work(system_wq, &linkwatch_work, 0);
+		mod_delayed_work(system_unbound_wq, &linkwatch_work, 0);
 	else
-		schedule_delayed_work(&linkwatch_work, delay);
+		queue_delayed_work(system_unbound_wq, &linkwatch_work, delay);
 }
 
 
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 8ca13208d240..e18823bf2330 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1369,14 +1369,17 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EOPNOTSUPP;
 	create = rxfh.rss_context == ETH_RXFH_CONTEXT_ALLOC;
 
-	/* If either indir, hash key or function is valid, proceed further.
-	 * Must request at least one change: indir size, hash key, function
-	 * or input transformation.
-	 */
 	if ((rxfh.indir_size &&
 	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
 	     rxfh.indir_size != dev_indir_size) ||
-	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
+	    (rxfh.key_size && rxfh.key_size != dev_key_size))
+		return -EINVAL;
+
+	/* Must request at least one change: indir size, hash key, function
+	 * or input transformation.
+	 * There's no need for any of it in case of context creation.
+	 */
+	if (!create &&
 	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
 	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE &&
 	     rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
@@ -1449,12 +1452,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 
 		if (ops->create_rxfh_context) {
-			u32 limit = ops->rxfh_max_context_id ?: U32_MAX;
+			u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX;
 			u32 ctx_id;
 
 			/* driver uses new API, core allocates ID */
 			ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx,
-				       XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT);
+				       XA_LIMIT(1, limit - 1),
+				       GFP_KERNEL_ACCOUNT);
 			if (ret < 0) {
 				kfree(ctx);
 				goto out;
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 85531437890c..db6516092daf 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -267,32 +267,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head)
 	kfree_sensitive(key);
 }
 
-void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
+static void tcp_ao_info_free_rcu(struct rcu_head *head)
 {
-	struct tcp_ao_info *ao;
+	struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu);
 	struct tcp_ao_key *key;
 	struct hlist_node *n;
 
+	hlist_for_each_entry_safe(key, n, &ao->head, node) {
+		hlist_del(&key->node);
+		tcp_sigpool_release(key->tcp_sigpool_id);
+		kfree_sensitive(key);
+	}
+	kfree(ao);
+	static_branch_slow_dec_deferred(&tcp_ao_needed);
+}
+
+static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao)
+{
+	size_t total_ao_sk_mem = 0;
+	struct tcp_ao_key *key;
+
+	hlist_for_each_entry(key,  &ao->head, node)
+		total_ao_sk_mem += tcp_ao_sizeof_key(key);
+	atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc);
+}
+
+void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
+{
+	struct tcp_ao_info *ao;
+
 	if (twsk) {
 		ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1);
-		tcp_twsk(sk)->ao_info = NULL;
+		rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL);
 	} else {
 		ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1);
-		tcp_sk(sk)->ao_info = NULL;
+		rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL);
 	}
 
 	if (!ao || !refcount_dec_and_test(&ao->refcnt))
 		return;
 
-	hlist_for_each_entry_safe(key, n, &ao->head, node) {
-		hlist_del_rcu(&key->node);
-		if (!twsk)
-			atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc);
-		call_rcu(&key->rcu, tcp_ao_key_free_rcu);
-	}
-
-	kfree_rcu(ao, rcu);
-	static_branch_slow_dec_deferred(&tcp_ao_needed);
+	if (!twsk)
+		tcp_ao_sk_omem_free(sk, ao);
+	call_rcu(&ao->rcu, tcp_ao_info_free_rcu);
 }
 
 void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 5d2068b6c778..ce3b316e2327 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -86,6 +86,11 @@
 /* Default trace flags */
 #define L2TP_DEFAULT_DEBUG_FLAGS	0
 
+#define L2TP_DEPTH_NESTING		2
+#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING
+#error "L2TP requires its own lockdep subclass"
+#endif
+
 /* Private data stored for received packets in the skb.
  */
 struct l2tp_skb_cb {
@@ -1171,7 +1176,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
 	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
 	nf_reset_ct(skb);
 
-	bh_lock_sock_nested(sk);
+	/* L2TP uses its own lockdep subclass to avoid lockdep splats caused by
+	 * nested socket calls on the same lockdep socket class. This can
+	 * happen when data from a user socket is routed over l2tp, which uses
+	 * another userspace socket.
+	 */
+	spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING);
+
 	if (sock_owned_by_user(sk)) {
 		kfree_skb(skb);
 		ret = NET_XMIT_DROP;
@@ -1223,7 +1234,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
 	ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl);
 
 out_unlock:
-	bh_unlock_sock(sk);
+	spin_unlock(&sk->sk_lock.slock);
 
 	return ret;
 }
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8a68382a4fe9..ac2f1a54cc43 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 
 	if (subflow->remote_key_valid &&
 	    (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||
-	     ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) {
+	     ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) &&
+	      (!mp_opt->echo || subflow->mp_join)))) {
 		/* subflows are fully established as soon as we get any
 		 * additional ack, including ADD_ADDR.
 		 */
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 37954a0b087d..4cae2aa7be5c 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -348,7 +348,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 	add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
 
 	if (add_entry) {
-		if (mptcp_pm_is_kernel(msk))
+		if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
 			return false;
 
 		sk_reset_timer(sk, &add_entry->add_timer,
@@ -512,8 +512,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
 
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
+	struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
 	struct sock *sk = (struct sock *)msk;
-	struct mptcp_pm_addr_entry *local;
 	unsigned int add_addr_signal_max;
 	unsigned int local_addr_max;
 	struct pm_nl_pernet *pernet;
@@ -555,8 +555,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 
 	/* check first for announce */
 	if (msk->pm.add_addr_signaled < add_addr_signal_max) {
-		local = select_signal_address(pernet, msk);
-
 		/* due to racing events on both ends we can reach here while
 		 * previous add address is still running: if we invoke now
 		 * mptcp_pm_announce_addr(), that will fail and the
@@ -567,16 +565,26 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
 			return;
 
-		if (local) {
-			if (mptcp_pm_alloc_anno_list(msk, &local->addr)) {
-				__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
-				msk->pm.add_addr_signaled++;
-				mptcp_pm_announce_addr(msk, &local->addr, false);
-				mptcp_pm_nl_addr_send_ack(msk);
-			}
-		}
+		local = select_signal_address(pernet, msk);
+		if (!local)
+			goto subflow;
+
+		/* If the alloc fails, we are on memory pressure, not worth
+		 * continuing, and trying to create subflows.
+		 */
+		if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
+			return;
+
+		__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+		msk->pm.add_addr_signaled++;
+		mptcp_pm_announce_addr(msk, &local->addr, false);
+		mptcp_pm_nl_addr_send_ack(msk);
+
+		if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+			signal_and_subflow = local;
 	}
 
+subflow:
 	/* check if should create a new subflow */
 	while (msk->pm.local_addr_used < local_addr_max &&
 	       msk->pm.subflows < subflows_max) {
@@ -584,9 +592,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		bool fullmesh;
 		int i, nr;
 
-		local = select_local_address(pernet, msk);
-		if (!local)
-			break;
+		if (signal_and_subflow) {
+			local = signal_and_subflow;
+			signal_and_subflow = NULL;
+		} else {
+			local = select_local_address(pernet, msk);
+			if (!local)
+				break;
+		}
 
 		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
 
@@ -1328,8 +1341,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		return ret;
 
-	if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
-		GENL_SET_ERR_MSG(info, "flags must have signal when using port");
+	if (addr.addr.port && !address_use_port(&addr)) {
+		GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port");
 		return -EINVAL;
 	}
 
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 17fcaa9b0df9..a8a254a5008e 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
 	struct sock *sk = ep->base.sk;
 	struct net *net = sock_net(sk);
 	struct sctp_hashbucket *head;
+	int err = 0;
 
 	ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port);
 	head = &sctp_ep_hashtable[ep->hashent];
 
+	write_lock(&head->lock);
 	if (sk->sk_reuseport) {
 		bool any = sctp_is_ep_boundall(sk);
 		struct sctp_endpoint *ep2;
 		struct list_head *list;
-		int cnt = 0, err = 1;
+		int cnt = 0;
+
+		err = 1;
 
 		list_for_each(list, &ep->base.bind_addr.address_list)
 			cnt++;
@@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
 			if (!err) {
 				err = reuseport_add_sock(sk, sk2, any);
 				if (err)
-					return err;
+					goto out;
 				break;
 			} else if (err < 0) {
-				return err;
+				goto out;
 			}
 		}
 
 		if (err) {
 			err = reuseport_alloc(sk, any);
 			if (err)
-				return err;
+				goto out;
 		}
 	}
 
-	write_lock(&head->lock);
 	hlist_add_head(&ep->node, &head->chain);
+out:
 	write_unlock(&head->lock);
-	return 0;
+	return err;
 }
 
 /* Add an endpoint to the hash. Local BH-safe. */
@@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
 
 	head = &sctp_ep_hashtable[ep->hashent];
 
+	write_lock(&head->lock);
 	if (rcu_access_pointer(sk->sk_reuseport_cb))
 		reuseport_detach_sock(sk);
-
-	write_lock(&head->lock);
 	hlist_del_init(&ep->node);
 	write_unlock(&head->lock);
 }
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index 9d32058db2b5..e19177ce4092 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -19,7 +19,7 @@
 
 #include "smc_clc.h"
 
-#define SMC_MAX_FBACK_RSN_CNT 30
+#define SMC_MAX_FBACK_RSN_CNT 36
 
 enum {
 	SMC_BUF_8K,