Merge tag 'net-6.11-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth and netfilter.

  Current release - regressions:

   - virtio_net: avoid crash on resume - move netdev_tx_reset_queue()
     call before RX napi enable

  Current release - new code bugs:

   - net/mlx5e: fix page leak and incorrect header release w/ HW GRO

  Previous releases - regressions:

   - udp: fix receiving fraglist GSO packets

   - tcp: prevent refcount underflow due to concurrent execution of
     tcp_sk_exit_batch()

  Previous releases - always broken:

   - ipv6: fix possible UAF when incrementing error counters on output

   - ip6: tunnel: prevent merging of packets with different L2

   - mptcp: pm: fix IDs not being reusable

   - bonding: fix potential crashes in IPsec offload handling

   - Bluetooth: HCI:
      - MGMT: add error handling to pair_device() to avoid a crash
      - invert LE State quirk to be opt-out rather then opt-in
      - fix LE quote calculation

   - drv: dsa: VLAN fixes for Ocelot driver

   - drv: igb: cope with large MAX_SKB_FRAGS Kconfig settings

   - drv: ice: fi Rx data path on architectures with PAGE_SIZE >= 8192

  Misc:

   - netpoll: do not export netpoll_poll_[disable|enable]()

   - MAINTAINERS: update the list of networking headers"

* tag 'net-6.11-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (82 commits)
  s390/iucv: Fix vargs handling in iucv_alloc_device()
  net: ovs: fix ovs_drop_reasons error
  net: xilinx: axienet: Fix dangling multicast addresses
  net: xilinx: axienet: Always disable promiscuous mode
  MAINTAINERS: Mark JME Network Driver as Odd Fixes
  MAINTAINERS: Add header files to NETWORKING sections
  MAINTAINERS: Add limited globs for Networking headers
  MAINTAINERS: Add net_tstamp.h to SOCKET TIMESTAMPING section
  MAINTAINERS: Add sonet.h to ATM section of MAINTAINERS
  octeontx2-af: Fix CPT AF register offset calculation
  net: phy: realtek: Fix setting of PHY LEDs Mode B bit on RTL8211F
  net: ngbe: Fix phy mode set to external phy
  netfilter: flowtable: validate vlan header
  bnxt_en: Fix double DMA unmapping for XDP_REDIRECT
  ipv6: prevent possible UAF in ip6_xmit()
  ipv6: fix possible UAF in ip6_finish_output2()
  ipv6: prevent UAF in ip6_send_skb()
  netpoll: do not export netpoll_poll_[disable|enable]()
  selftests: mlxsw: ethtool_lanes: Source ethtool lib from correct path
  udp: fix receiving fraglist GSO packets
  ...

3 files changed, 94 insertions, 64 deletions

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 23bb89c94e90..3e6e0f5510bb 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -60,16 +60,6 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	return 0;
 }
 
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list)
-{
-	pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
-
-	spin_lock_bh(&msk->pm.lock);
-	mptcp_pm_nl_rm_subflow_received(msk, rm_list);
-	spin_unlock_bh(&msk->pm.lock);
-	return 0;
-}
-
 /* path manager event handlers */
 
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side)
@@ -444,9 +434,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id
 	*flags = 0;
 	*ifindex = 0;
 
-	if (!id)
-		return 0;
-
 	if (mptcp_pm_is_userspace(msk))
 		return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
 	return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 4cae2aa7be5c..3e4ad801786f 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -143,11 +143,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
 	return false;
 }
 
-static struct mptcp_pm_addr_entry *
+static bool
 select_local_address(const struct pm_nl_pernet *pernet,
-		     const struct mptcp_sock *msk)
+		     const struct mptcp_sock *msk,
+		     struct mptcp_pm_addr_entry *new_entry)
 {
-	struct mptcp_pm_addr_entry *entry, *ret = NULL;
+	struct mptcp_pm_addr_entry *entry;
+	bool found = false;
 
 	msk_owned_by_me(msk);
 
@@ -159,17 +161,21 @@ select_local_address(const struct pm_nl_pernet *pernet,
 		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
 			continue;
 
-		ret = entry;
+		*new_entry = *entry;
+		found = true;
 		break;
 	}
 	rcu_read_unlock();
-	return ret;
+
+	return found;
 }
 
-static struct mptcp_pm_addr_entry *
-select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
+static bool
+select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
+		      struct mptcp_pm_addr_entry *new_entry)
 {
-	struct mptcp_pm_addr_entry *entry, *ret = NULL;
+	struct mptcp_pm_addr_entry *entry;
+	bool found = false;
 
 	rcu_read_lock();
 	/* do not keep any additional per socket state, just signal
@@ -184,11 +190,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
 			continue;
 
-		ret = entry;
+		*new_entry = *entry;
+		found = true;
 		break;
 	}
 	rcu_read_unlock();
-	return ret;
+
+	return found;
 }
 
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
@@ -512,9 +520,10 @@ __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;
+	bool signal_and_subflow = false;
 	unsigned int local_addr_max;
 	struct pm_nl_pernet *pernet;
 	unsigned int subflows_max;
@@ -565,23 +574,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
 			return;
 
-		local = select_signal_address(pernet, msk);
-		if (!local)
+		if (!select_signal_address(pernet, msk, &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))
+		if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
 			return;
 
-		__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+		__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_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;
+		if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+			signal_and_subflow = true;
 	}
 
 subflow:
@@ -592,26 +600,22 @@ subflow:
 		bool fullmesh;
 		int i, nr;
 
-		if (signal_and_subflow) {
-			local = signal_and_subflow;
-			signal_and_subflow = NULL;
-		} else {
-			local = select_local_address(pernet, msk);
-			if (!local)
-				break;
-		}
+		if (signal_and_subflow)
+			signal_and_subflow = false;
+		else if (!select_local_address(pernet, msk, &local))
+			break;
 
-		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+		fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
 
 		msk->pm.local_addr_used++;
-		__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
-		nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
+		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+		nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
 		if (nr == 0)
 			continue;
 
 		spin_unlock_bh(&msk->pm.lock);
 		for (i = 0; i < nr; i++)
-			__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
+			__mptcp_subflow_connect(sk, &local.addr, &addrs[i]);
 		spin_lock_bh(&msk->pm.lock);
 	}
 	mptcp_pm_nl_check_work_pending(msk);
@@ -636,6 +640,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 {
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *entry;
+	struct mptcp_addr_info mpc_addr;
 	struct pm_nl_pernet *pernet;
 	unsigned int subflows_max;
 	int i = 0;
@@ -643,6 +648,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 	pernet = pm_nl_get_pernet_from_msk(msk);
 	subflows_max = mptcp_pm_get_subflows_max(msk);
 
+	mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
@@ -653,7 +660,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 
 		if (msk->pm.subflows < subflows_max) {
 			msk->pm.subflows++;
-			addrs[i++] = entry->addr;
+			addrs[i] = entry->addr;
+
+			/* Special case for ID0: set the correct ID */
+			if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port))
+				addrs[i].id = 0;
+
+			i++;
 		}
 	}
 	rcu_read_unlock();
@@ -829,25 +842,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			mptcp_close_ssk(sk, ssk, subflow);
 			spin_lock_bh(&msk->pm.lock);
 
-			removed = true;
+			removed |= subflow->request_join;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW)
 				__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
-		if (rm_type == MPTCP_MIB_RMSUBFLOW)
-			__set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
-		else if (rm_type == MPTCP_MIB_RMADDR)
+
+		if (rm_type == MPTCP_MIB_RMADDR)
 			__MPTCP_INC_STATS(sock_net(sk), rm_type);
+
 		if (!removed)
 			continue;
 
 		if (!mptcp_pm_is_kernel(msk))
 			continue;
 
-		if (rm_type == MPTCP_MIB_RMADDR) {
-			msk->pm.add_addr_accepted--;
-			WRITE_ONCE(msk->pm.accept_addr, true);
-		} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
-			msk->pm.local_addr_used--;
+		if (rm_type == MPTCP_MIB_RMADDR && rm_id &&
+		    !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+			/* Note: if the subflow has been closed before, this
+			 * add_addr_accepted counter will not be decremented.
+			 */
+			if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+				WRITE_ONCE(msk->pm.accept_addr, true);
 		}
 	}
 }
@@ -857,8 +872,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
 	mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
 }
 
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
-				     const struct mptcp_rm_list *rm_list)
+static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
+					    const struct mptcp_rm_list *rm_list)
 {
 	mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
 }
@@ -1393,6 +1408,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int
 	struct sock *sk = (struct sock *)msk;
 	struct net *net = sock_net(sk);
 
+	/* No entries with ID 0 */
+	if (id == 0)
+		return 0;
+
 	rcu_read_lock();
 	entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
 	if (entry) {
@@ -1431,13 +1450,24 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
 	ret = remove_anno_list_by_saddr(msk, addr);
 	if (ret || force) {
 		spin_lock_bh(&msk->pm.lock);
-		msk->pm.add_addr_signaled -= ret;
+		if (ret) {
+			__set_bit(addr->id, msk->pm.id_avail_bitmap);
+			msk->pm.add_addr_signaled--;
+		}
 		mptcp_pm_remove_addr(msk, &list);
 		spin_unlock_bh(&msk->pm.lock);
 	}
 	return ret;
 }
 
+static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
+{
+	/* If it was marked as used, and not ID 0, decrement local_addr_used */
+	if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
+	    id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
+		msk->pm.local_addr_used--;
+}
+
 static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 						   const struct mptcp_pm_addr_entry *entry)
 {
@@ -1466,8 +1496,19 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
 		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
 					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
-		if (remove_subflow)
-			mptcp_pm_remove_subflow(msk, &list);
+
+		if (remove_subflow) {
+			spin_lock_bh(&msk->pm.lock);
+			mptcp_pm_nl_rm_subflow_received(msk, &list);
+			spin_unlock_bh(&msk->pm.lock);
+		}
+
+		if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+			spin_lock_bh(&msk->pm.lock);
+			__mark_subflow_endp_available(msk, list.ids[0]);
+			spin_unlock_bh(&msk->pm.lock);
+		}
+
 		release_sock(sk);
 
 next:
@@ -1502,6 +1543,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
 		spin_lock_bh(&msk->pm.lock);
 		mptcp_pm_remove_addr(msk, &list);
 		mptcp_pm_nl_rm_subflow_received(msk, &list);
+		__mark_subflow_endp_available(msk, 0);
 		spin_unlock_bh(&msk->pm.lock);
 		release_sock(sk);
 
@@ -1605,14 +1647,17 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
+	spin_lock_bh(&msk->pm.lock);
 	if (alist.nr) {
-		spin_lock_bh(&msk->pm.lock);
 		msk->pm.add_addr_signaled -= alist.nr;
 		mptcp_pm_remove_addr(msk, &alist);
-		spin_unlock_bh(&msk->pm.lock);
 	}
 	if (slist.nr)
-		mptcp_pm_remove_subflow(msk, &slist);
+		mptcp_pm_nl_rm_subflow_received(msk, &slist);
+	/* Reset counters: maybe some subflows have been removed before */
+	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+	msk->pm.local_addr_used = 0;
+	spin_unlock_bh(&msk->pm.lock);
 }
 
 static void mptcp_nl_remove_addrs_list(struct net *net,
@@ -1900,6 +1945,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 
 	spin_lock_bh(&msk->pm.lock);
 	mptcp_pm_nl_rm_subflow_received(msk, &list);
+	__mark_subflow_endp_available(msk, list.ids[0]);
 	mptcp_pm_create_subflow_or_signal_addr(msk);
 	spin_unlock_bh(&msk->pm.lock);
 }
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 60c6b073d65f..a1c1b0ff1ce1 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1026,7 +1026,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
 			   bool echo);
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
 void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
 
 void mptcp_free_local_addr_list(struct mptcp_sock *msk);
@@ -1133,8 +1132,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_work(struct mptcp_sock *msk);
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
-				     const struct mptcp_rm_list *rm_list);
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);