Merge tag 'net-6.3-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter and bpf.

  There are a few fixes for new code bugs, including the Mellanox one
  noted in the last networking pull. No known regressions outstanding.

  Current release - regressions:

   - sched: clear actions pointer in miss cookie init fail

   - mptcp: fix accept vs worker race

   - bpf: fix bpf_arch_text_poke() with new_addr == NULL on s390

   - eth: bnxt_en: fix a possible NULL pointer dereference in unload
     path

   - eth: veth: take into account peer device for
     NETDEV_XDP_ACT_NDO_XMIT xdp_features flag

  Current release - new code bugs:

   - eth: revert "net/mlx5: Enable management PF initialization"

  Previous releases - regressions:

   - netfilter: fix recent physdev match breakage

   - bpf: fix incorrect verifier pruning due to missing register
     precision taints

   - eth: virtio_net: fix overflow inside xdp_linearize_page()

   - eth: cxgb4: fix use after free bugs caused by circular dependency
     problem

   - eth: mlxsw: pci: fix possible crash during initialization

  Previous releases - always broken:

   - sched: sch_qfq: prevent slab-out-of-bounds in qfq_activate_agg

   - netfilter: validate catch-all set elements

   - bridge: don't notify FDB entries with "master dynamic"

   - eth: bonding: fix memory leak when changing bond type to ethernet

   - eth: i40e: fix accessing vsi->active_filters without holding lock

  Misc:

   - Mat is back as MPTCP co-maintainer"

* tag 'net-6.3-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (33 commits)
  net: bridge: switchdev: don't notify FDB entries with "master dynamic"
  Revert "net/mlx5: Enable management PF initialization"
  MAINTAINERS: Resume MPTCP co-maintainer role
  mailmap: add entries for Mat Martineau
  e1000e: Disable TSO on i219-LM card to increase speed
  bnxt_en: fix free-runnig PHC mode
  net: dsa: microchip: ksz8795: Correctly handle huge frame configuration
  bpf: Fix incorrect verifier pruning due to missing register precision taints
  hamradio: drop ISA_DMA_API dependency
  mlxsw: pci: Fix possible crash during initialization
  mptcp: fix accept vs worker race
  mptcp: stops worker on unaccepted sockets at listener close
  net: rpl: fix rpl header size calculation
  net: vmxnet3: Fix NULL pointer dereference in vmxnet3_rq_rx_complete()
  bonding: Fix memory leak when changing bond type to Ethernet
  veth: take into account peer device for NETDEV_XDP_ACT_NDO_XMIT xdp_features flag
  mlxfw: fix null-ptr-deref in mlxfw_mfa2_tlv_next()
  bnxt_en: Fix a possible NULL pointer dereference in unload path
  bnxt_en: Do not initialize PTP on older P3/P4 chips
  netfilter: nf_tables: tighten netlink attribute requirements for catch-all elements
  ...

1 files changed, 77 insertions, 3 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index d34588850545..281c1cc8dc8d 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -723,9 +723,12 @@ void mptcp_subflow_drop_ctx(struct sock *ssk)
 	if (!ctx)
 		return;
 
-	subflow_ulp_fallback(ssk, ctx);
-	if (ctx->conn)
-		sock_put(ctx->conn);
+	list_del(&mptcp_subflow_ctx(ssk)->node);
+	if (inet_csk(ssk)->icsk_ulp_ops) {
+		subflow_ulp_fallback(ssk, ctx);
+		if (ctx->conn)
+			sock_put(ctx->conn);
+	}
 
 	kfree_rcu(ctx, rcu);
 }
@@ -1819,6 +1822,77 @@ static void subflow_state_change(struct sock *sk)
 	}
 }
 
+void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
+{
+	struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
+	struct mptcp_sock *msk, *next, *head = NULL;
+	struct request_sock *req;
+	struct sock *sk;
+
+	/* build a list of all unaccepted mptcp sockets */
+	spin_lock_bh(&queue->rskq_lock);
+	for (req = queue->rskq_accept_head; req; req = req->dl_next) {
+		struct mptcp_subflow_context *subflow;
+		struct sock *ssk = req->sk;
+
+		if (!sk_is_mptcp(ssk))
+			continue;
+
+		subflow = mptcp_subflow_ctx(ssk);
+		if (!subflow || !subflow->conn)
+			continue;
+
+		/* skip if already in list */
+		sk = subflow->conn;
+		msk = mptcp_sk(sk);
+		if (msk->dl_next || msk == head)
+			continue;
+
+		sock_hold(sk);
+		msk->dl_next = head;
+		head = msk;
+	}
+	spin_unlock_bh(&queue->rskq_lock);
+	if (!head)
+		return;
+
+	/* can't acquire the msk socket lock under the subflow one,
+	 * or will cause ABBA deadlock
+	 */
+	release_sock(listener_ssk);
+
+	for (msk = head; msk; msk = next) {
+		sk = (struct sock *)msk;
+
+		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+		next = msk->dl_next;
+		msk->dl_next = NULL;
+
+		__mptcp_unaccepted_force_close(sk);
+		release_sock(sk);
+
+		/* lockdep will report a false positive ABBA deadlock
+		 * between cancel_work_sync and the listener socket.
+		 * The involved locks belong to different sockets WRT
+		 * the existing AB chain.
+		 * Using a per socket key is problematic as key
+		 * deregistration requires process context and must be
+		 * performed at socket disposal time, in atomic
+		 * context.
+		 * Just tell lockdep to consider the listener socket
+		 * released here.
+		 */
+		mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
+		mptcp_cancel_work(sk);
+		mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+
+		sock_put(sk);
+	}
+
+	/* we are still under the listener msk socket lock */
+	lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);
+}
+
 static int subflow_ulp_init(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);