Merge tag 'net-6.12-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bluetooth.

  Quite calm week. No new regression under investigation.

  Current release - regressions:

   - eth: revert "igb: Disable threaded IRQ for igb_msix_other"

  Current release - new code bugs:

   - bluetooth: btintel: direct exception event to bluetooth stack

  Previous releases - regressions:

   - core: fix data-races around sk->sk_forward_alloc

   - netlink: terminate outstanding dump on socket close

   - mptcp: error out earlier on disconnect

   - vsock: fix accept_queue memory leak

   - phylink: ensure PHY momentary link-fails are handled

   - eth: mlx5:
      - fix null-ptr-deref in add rule err flow
      - lock FTE when checking if active

   - eth: dwmac-mediatek: fix inverted handling of mediatek,mac-wol

  Previous releases - always broken:

   - sched: fix u32's systematic failure to free IDR entries for hnodes.

   - sctp: fix possible UAF in sctp_v6_available()

   - eth: bonding: add ns target multicast address to slave device

   - eth: mlx5: fix msix vectors to respect platform limit

   - eth: icssg-prueth: fix 1 PPS sync"

* tag 'net-6.12-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (38 commits)
  net: sched: u32: Add test case for systematic hnode IDR leaks
  selftests: bonding: add ns multicast group testing
  bonding: add ns target multicast address to slave device
  net: ti: icssg-prueth: Fix 1 PPS sync
  stmmac: dwmac-intel-plat: fix call balance of tx_clk handling routines
  net: Make copy_safe_from_sockptr() match documentation
  net: stmmac: dwmac-mediatek: Fix inverted handling of mediatek,mac-wol
  ipmr: Fix access to mfc_cache_list without lock held
  samples: pktgen: correct dev to DEV
  net: phylink: ensure PHY momentary link-fails are handled
  mptcp: pm: use _rcu variant under rcu_read_lock
  mptcp: hold pm lock when deleting entry
  mptcp: update local address flags when setting it
  net: sched: cls_u32: Fix u32's systematic failure to free IDR entries for hnodes.
  MAINTAINERS: Re-add cancelled Renesas driver sections
  Revert "igb: Disable threaded IRQ for igb_msix_other"
  Bluetooth: btintel: Direct exception event to bluetooth stack
  Bluetooth: hci_core: Fix calling mgmt_device_connected
  virtio/vsock: Improve MSG_ZEROCOPY error handling
  vsock: Fix sk_error_queue memory leak
  ...

14 files changed, 103 insertions, 66 deletions

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 96d097b21d13..0ac354db8177 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3788,8 +3788,6 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_dev_lock(hdev);
 	conn = hci_conn_hash_lookup_handle(hdev, handle);
-	if (conn && hci_dev_test_flag(hdev, HCI_MGMT))
-		mgmt_device_connected(hdev, conn, NULL, 0);
 	hci_dev_unlock(hdev);
 
 	if (conn) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 039be95c40cf..da50df485090 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1052,32 +1052,34 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 
 #ifdef CONFIG_PAGE_POOL
 
-/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
- * 1 syscall. The limit exists to limit the amount of memory the kernel
- * allocates to copy these tokens.
+/* This is the number of tokens and frags that the user can SO_DEVMEM_DONTNEED
+ * in 1 syscall. The limit exists to limit the amount of memory the kernel
+ * allocates to copy these tokens, and to prevent looping over the frags for
+ * too long.
  */
 #define MAX_DONTNEED_TOKENS 128
+#define MAX_DONTNEED_FRAGS 1024
 
 static noinline_for_stack int
 sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	unsigned int num_tokens, i, j, k, netmem_num = 0;
 	struct dmabuf_token *tokens;
+	int ret = 0, num_frags = 0;
 	netmem_ref netmems[16];
-	int ret = 0;
 
 	if (!sk_is_tcp(sk))
 		return -EBADF;
 
-	if (optlen % sizeof(struct dmabuf_token) ||
+	if (optlen % sizeof(*tokens) ||
 	    optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
 		return -EINVAL;
 
-	tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
+	num_tokens = optlen / sizeof(*tokens);
+	tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
 	if (!tokens)
 		return -ENOMEM;
 
-	num_tokens = optlen / sizeof(struct dmabuf_token);
 	if (copy_from_sockptr(tokens, optval, optlen)) {
 		kvfree(tokens);
 		return -EFAULT;
@@ -1086,24 +1088,28 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
 	xa_lock_bh(&sk->sk_user_frags);
 	for (i = 0; i < num_tokens; i++) {
 		for (j = 0; j < tokens[i].token_count; j++) {
+			if (++num_frags > MAX_DONTNEED_FRAGS)
+				goto frag_limit_reached;
+
 			netmem_ref netmem = (__force netmem_ref)__xa_erase(
 				&sk->sk_user_frags, tokens[i].token_start + j);
 
-			if (netmem &&
-			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
-				netmems[netmem_num++] = netmem;
-				if (netmem_num == ARRAY_SIZE(netmems)) {
-					xa_unlock_bh(&sk->sk_user_frags);
-					for (k = 0; k < netmem_num; k++)
-						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
-					netmem_num = 0;
-					xa_lock_bh(&sk->sk_user_frags);
-				}
-				ret++;
+			if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+				continue;
+
+			netmems[netmem_num++] = netmem;
+			if (netmem_num == ARRAY_SIZE(netmems)) {
+				xa_unlock_bh(&sk->sk_user_frags);
+				for (k = 0; k < netmem_num; k++)
+					WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+				netmem_num = 0;
+				xa_lock_bh(&sk->sk_user_frags);
 			}
+			ret++;
 		}
 	}
 
+frag_limit_reached:
 	xa_unlock_bh(&sk->sk_user_frags);
 	for (k = 0; k < netmem_num; k++)
 		WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index da5dba120bc9..d6649246188d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -618,7 +618,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	   by tcp. Feel free to propose better solution.
 					       --ANK (980728)
 	 */
-	if (np->rxopt.all)
+	if (np->rxopt.all && sk->sk_state != DCCP_LISTEN)
 		opt_skb = skb_clone_and_charge_r(skb, sk);
 
 	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 271dc03fc6db..f0af12a2f70b 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -310,7 +310,8 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb,
 	if (filter->filter_set)
 		flags |= NLM_F_DUMP_FILTERED;
 
-	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
+	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list,
+				lockdep_rtnl_is_held()) {
 		if (e < s_e)
 			goto next_entry;
 		if (filter->dev &&
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d71ab4e1efe1..c9de5ef8f267 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1618,7 +1618,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	   by tcp. Feel free to propose better solution.
 					       --ANK (980728)
 	 */
-	if (np->rxopt.all)
+	if (np->rxopt.all && sk->sk_state != TCP_LISTEN)
 		opt_skb = skb_clone_and_charge_r(skb, sk);
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
@@ -1656,8 +1656,6 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 				if (reason)
 					goto reset;
 			}
-			if (opt_skb)
-				__kfree_skb(opt_skb);
 			return 0;
 		}
 	} else
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index db586a5b3866..45a2b5f05d38 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -524,7 +524,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
 {
 	struct mptcp_pm_addr_entry *entry;
 
-	list_for_each_entry(entry, &pernet->local_addr_list, list) {
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
+				lockdep_is_held(&pernet->lock)) {
 		if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port))
 			return entry;
 	}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 56dfea9862b7..e35178f5205f 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -308,14 +308,17 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 
 	lock_sock(sk);
 
+	spin_lock_bh(&msk->pm.lock);
 	match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val);
 	if (!match) {
 		GENL_SET_ERR_MSG(info, "address with specified id not found");
+		spin_unlock_bh(&msk->pm.lock);
 		release_sock(sk);
 		goto out;
 	}
 
 	list_move(&match->list, &free_list);
+	spin_unlock_bh(&msk->pm.lock);
 
 	mptcp_pm_remove_addrs(msk, &free_list);
 
@@ -560,6 +563,7 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct net *net = sock_net(skb->sk);
+	struct mptcp_pm_addr_entry *entry;
 	struct mptcp_sock *msk;
 	int ret = -EINVAL;
 	struct sock *sk;
@@ -601,6 +605,17 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 	if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
 		bkup = 1;
 
+	spin_lock_bh(&msk->pm.lock);
+	list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, &loc.addr, false)) {
+			if (bkup)
+				entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
+			else
+				entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;
+		}
+	}
+	spin_unlock_bh(&msk->pm.lock);
+
 	lock_sock(sk);
 	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup);
 	release_sock(sk);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d263091659e0..48d480982b78 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2082,7 +2082,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 				slow = lock_sock_fast(ssk);
 				WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
 				WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp);
-				tcp_cleanup_rbuf(ssk, 1);
+				if (tcp_can_send_ack(ssk))
+					tcp_cleanup_rbuf(ssk, 1);
 				unlock_sock_fast(ssk, slow);
 			}
 		}
@@ -2205,7 +2206,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		cmsg_flags = MPTCP_CMSG_INQ;
 
 	while (copied < len) {
-		int bytes_read;
+		int err, bytes_read;
 
 		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags);
 		if (unlikely(bytes_read < 0)) {
@@ -2267,9 +2268,16 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		pr_debug("block timeout %ld\n", timeo);
-		sk_wait_data(sk, &timeo, NULL);
+		mptcp_rcv_space_adjust(msk, copied);
+		err = sk_wait_data(sk, &timeo, NULL);
+		if (err < 0) {
+			err = copied ? : err;
+			goto out_err;
+		}
 	}
 
+	mptcp_rcv_space_adjust(msk, copied);
+
 out_err:
 	if (cmsg_flags && copied >= 0) {
 		if (cmsg_flags & MPTCP_CMSG_TS)
@@ -2285,8 +2293,6 @@ out_err:
 	pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n",
 		 msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
 		 skb_queue_empty(&msk->receive_queue), copied);
-	if (!(flags & MSG_PEEK))
-		mptcp_rcv_space_adjust(msk, copied);
 
 	release_sock(sk);
 	return copied;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0a9287fadb47..f84aad420d44 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -393,15 +393,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 
 static void netlink_sock_destruct(struct sock *sk)
 {
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->cb_running) {
-		if (nlk->cb.done)
-			nlk->cb.done(&nlk->cb);
-		module_put(nlk->cb.module);
-		kfree_skb(nlk->cb.skb);
-	}
-
 	skb_queue_purge(&sk->sk_receive_queue);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
@@ -414,14 +405,6 @@ static void netlink_sock_destruct(struct sock *sk)
 	WARN_ON(nlk_sk(sk)->groups);
 }
 
-static void netlink_sock_destruct_work(struct work_struct *work)
-{
-	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
-						work);
-
-	sk_free(&nlk->sk);
-}
-
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
  * SMP. Look, when several writers sleep and reader wakes them up, all but one
  * immediately hit write lock and grab all the cpus. Exclusive sleep solves
@@ -731,12 +714,6 @@ static void deferred_put_nlk_sk(struct rcu_head *head)
 	if (!refcount_dec_and_test(&sk->sk_refcnt))
 		return;
 
-	if (nlk->cb_running && nlk->cb.done) {
-		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
-		schedule_work(&nlk->work);
-		return;
-	}
-
 	sk_free(sk);
 }
 
@@ -788,6 +765,14 @@ static int netlink_release(struct socket *sock)
 				NETLINK_URELEASE, &n);
 	}
 
+	/* Terminate any outstanding dump */
+	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
+		module_put(nlk->cb.module);
+		kfree_skb(nlk->cb.skb);
+	}
+
 	module_put(nlk->module);
 
 	if (netlink_is_kernel(sk)) {
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 5b0e4e62ab8b..778a3809361f 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -4,7 +4,6 @@
 
 #include <linux/rhashtable.h>
 #include <linux/atomic.h>
-#include <linux/workqueue.h>
 #include <net/sock.h>
 
 /* flags */
@@ -50,7 +49,6 @@ struct netlink_sock {
 
 	struct rhash_head	node;
 	struct rcu_head		rcu;
-	struct work_struct	work;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 9412d88a99bc..d3a03c57545b 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -92,6 +92,16 @@ struct tc_u_common {
 	long			knodes;
 };
 
+static u32 handle2id(u32 h)
+{
+	return ((h & 0x80000000) ? ((h >> 20) & 0x7FF) : h);
+}
+
+static u32 id2handle(u32 id)
+{
+	return (id | 0x800U) << 20;
+}
+
 static inline unsigned int u32_hash_fold(__be32 key,
 					 const struct tc_u32_sel *sel,
 					 u8 fshift)
@@ -310,7 +320,7 @@ static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr)
 	int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL);
 	if (id < 0)
 		return 0;
-	return (id | 0x800U) << 20;
+	return id2handle(id);
 }
 
 static struct hlist_head *tc_u_common_hash;
@@ -360,7 +370,7 @@ static int u32_init(struct tcf_proto *tp)
 		return -ENOBUFS;
 
 	refcount_set(&root_ht->refcnt, 1);
-	root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000;
+	root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0);
 	root_ht->prio = tp->prio;
 	root_ht->is_root = true;
 	idr_init(&root_ht->handle_idr);
@@ -612,7 +622,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 		if (phn == ht) {
 			u32_clear_hw_hnode(tp, ht, extack);
 			idr_destroy(&ht->handle_idr);
-			idr_remove(&tp_c->handle_idr, ht->handle);
+			idr_remove(&tp_c->handle_idr, handle2id(ht->handle));
 			RCU_INIT_POINTER(*hn, ht->next);
 			kfree_rcu(ht, rcu);
 			return 0;
@@ -989,7 +999,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 
 		err = u32_replace_hw_hnode(tp, ht, userflags, extack);
 		if (err) {
-			idr_remove(&tp_c->handle_idr, handle);
+			idr_remove(&tp_c->handle_idr, handle2id(handle));
 			kfree(ht);
 			return err;
 		}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f7b809c0d142..38e2fbdcbeac 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -683,7 +683,7 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp)
 	struct sock *sk = &sp->inet.sk;
 	struct net *net = sock_net(sk);
 	struct net_device *dev = NULL;
-	int type;
+	int type, res, bound_dev_if;
 
 	type = ipv6_addr_type(in6);
 	if (IPV6_ADDR_ANY == type)
@@ -697,14 +697,21 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp)
 	if (!(type & IPV6_ADDR_UNICAST))
 		return 0;
 
-	if (sk->sk_bound_dev_if) {
-		dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+	rcu_read_lock();
+	bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
+	if (bound_dev_if) {
+		res = 0;
+		dev = dev_get_by_index_rcu(net, bound_dev_if);
 		if (!dev)
-			return 0;
+			goto out;
 	}
 
-	return ipv6_can_nonlocal_bind(net, &sp->inet) ||
-	       ipv6_chk_addr(net, in6, dev, 0);
+	res = ipv6_can_nonlocal_bind(net, &sp->inet) ||
+	      ipv6_chk_addr(net, in6, dev, 0);
+
+out:
+	rcu_read_unlock();
+	return res;
 }
 
 /* This function checks if the address is a valid address to be used for
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 35681adedd9a..dfd29160fe11 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -836,6 +836,9 @@ static void vsock_sk_destruct(struct sock *sk)
 {
 	struct vsock_sock *vsk = vsock_sk(sk);
 
+	/* Flush MSG_ZEROCOPY leftovers. */
+	__skb_queue_purge(&sk->sk_error_queue);
+
 	vsock_deassign_transport(vsk);
 
 	/* When clearing these addresses, there's no need to set the family and
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index fc5666c8298f..9acc13ab3f82 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -400,6 +400,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 			if (virtio_transport_init_zcopy_skb(vsk, skb,
 							    info->msg,
 							    can_zcopy)) {
+				kfree_skb(skb);
 				ret = -ENOMEM;
 				break;
 			}
@@ -1513,6 +1514,14 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
 		return -ENOMEM;
 	}
 
+	/* __vsock_release() might have already flushed accept_queue.
+	 * Subsequent enqueues would lead to a memory leak.
+	 */
+	if (sk->sk_shutdown == SHUTDOWN_MASK) {
+		virtio_transport_reset_no_sock(t, skb);
+		return -ESHUTDOWN;
+	}
+
 	child = vsock_create_connected(sk);
 	if (!child) {
 		virtio_transport_reset_no_sock(t, skb);