Merge tag 'net-7.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Netfilter, IPsec, Bluetooth and WiFi.

  Current release - fix to a fix:

   - ipmr: add __rcu to netns_ipv4.mrt, make sure we hold the RCU lock
     in all relevant places

  Current release - new code bugs:

   - fixes for the recently added resizable hash tables

   - ipv6: make sure we default IPv6 tunnel drivers to =m now that IPv6
     itself is built in

   - drv: octeontx2-af: fixes for parser/CAM fixes

  Previous releases - regressions:

   - phy: micrel: fix LAN8814 QSGMII soft reset

   - wifi:
       - cw1200: revert "Fix locking in error paths"
       - ath12k: fix crash on WCN7850, due to adding the same queue
         buffer to a list multiple times

  Previous releases - always broken:

   - number of info leak fixes

   - ipv6: implement limits on extension header parsing

   - wifi: number of fixes for missing bound checks in the drivers

   - Bluetooth: fixes for races and locking issues

   - af_unix:
       - fix an issue between garbage collection and PEEK
       - fix yet another issue with OOB data

   - xfrm: esp: avoid in-place decrypt on shared skb frags

   - netfilter: replace skb_try_make_writable() by skb_ensure_writable()

   - openvswitch: vport: fix race between tunnel creation and linking
     leading to invalid memory accesses (type confusion)

   - drv: amd-xgbe: fix PTP addend overflow causing frozen clock

  Misc:

   - sched/isolation: make HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN
     (for relevant IPVS change)"

* tag 'net-7.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (190 commits)
  net: sparx5: configure serdes for 1000BASE-X in sparx5_port_init()
  net: sparx5: fix wrong chip ids for TSN SKUs
  net: stmmac: dwmac-nuvoton: fix NULL pointer dereference in nvt_set_phy_intf_sel()
  tcp: Fix dst leak in tcp_v6_connect().
  ipmr: Call ipmr_fib_lookup() under RCU.
  net: phy: broadcom: Save PHY counters during suspend
  net/smc: fix missing sk_err when TCP handshake fails
  af_unix: Reject SIOCATMARK on non-stream sockets
  veth: fix OOB txq access in veth_poll() with asymmetric queue counts
  eth: fbnic: fix double-free of PCS on phylink creation failure
  net: ethernet: cortina: Drop half-assembled SKB
  selftests: mptcp: pm: restrict 'unknown' check to pm_nl_ctl
  selftests: mptcp: check output: catch cmd errors
  mptcp: pm: prio: skip closed subflows
  mptcp: pm: ADD_ADDR rtx: return early if no retrans
  mptcp: pm: ADD_ADDR rtx: skip inactive subflows
  mptcp: pm: ADD_ADDR rtx: resched blocked ADD_ADDR quicker
  mptcp: pm: ADD_ADDR rtx: free sk if last
  mptcp: pm: ADD_ADDR rtx: always decrease sk refcount
  mptcp: pm: ADD_ADDR rtx: fix potential data-race
  ...

5 files changed, 59 insertions, 28 deletions

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 82ec15bcfd7f..082c46c0f50e 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -12,6 +12,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	struct sock *sk, *ssk;
 	struct sk_buff *skb;
 	struct tcp_sock *tp;
+	bool has_rxtstamp;
 
 	/* on early fallback the subflow context is deleted by
 	 * subflow_syn_recv_sock()
@@ -40,12 +41,13 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	 */
 	tp->copied_seq += skb->len;
 	subflow->ssn_offset += skb->len;
+	has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
 
 	/* Only the sequence delta is relevant */
 	MPTCP_SKB_CB(skb)->map_seq = -skb->len;
 	MPTCP_SKB_CB(skb)->end_seq = 0;
 	MPTCP_SKB_CB(skb)->offset = 0;
-	MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+	MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
 	MPTCP_SKB_CB(skb)->cant_coalesce = 1;
 
 	mptcp_data_lock(sk);
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 57a456690406..3c152bf66cd5 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -16,6 +16,7 @@ struct mptcp_pm_add_entry {
 	struct list_head	list;
 	struct mptcp_addr_info	addr;
 	u8			retrans_times;
+	bool			timer_done;
 	struct timer_list	add_timer;
 	struct mptcp_sock	*sock;
 	struct rcu_head		rcu;
@@ -283,6 +284,9 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		struct mptcp_addr_info local, remote;
 
+		if (!__mptcp_subflow_active(subflow))
+			continue;
+
 		mptcp_local_address((struct sock_common *)ssk, &local);
 		if (!mptcp_addresses_equal(&local, addr, addr->port))
 			continue;
@@ -305,18 +309,31 @@ static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk)
 	const struct net *net = sock_net((struct sock *)msk);
 	unsigned int rto = mptcp_get_add_addr_timeout(net);
 	struct mptcp_subflow_context *subflow;
-	unsigned int max = 0;
+	unsigned int max = 0, max_stale = 0;
+
+	if (!rto)
+		return 0;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		struct inet_connection_sock *icsk = inet_csk(ssk);
 
-		if (icsk->icsk_rto > max)
+		if (!__mptcp_subflow_active(subflow))
+			continue;
+
+		if (unlikely(subflow->stale)) {
+			if (icsk->icsk_rto > max_stale)
+				max_stale = icsk->icsk_rto;
+		} else if (icsk->icsk_rto > max) {
 			max = icsk->icsk_rto;
+		}
 	}
 
-	if (max && max < rto)
-		rto = max;
+	if (max)
+		return min(max, rto);
+
+	if (max_stale)
+		return min(max_stale, rto);
 
 	return rto;
 }
@@ -327,26 +344,22 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 							      add_timer);
 	struct mptcp_sock *msk = entry->sock;
 	struct sock *sk = (struct sock *)msk;
-	unsigned int timeout;
+	unsigned int timeout = 0;
 
 	pr_debug("msk=%p\n", msk);
 
-	if (!msk)
-		return;
-
-	if (inet_sk_state_load(sk) == TCP_CLOSE)
-		return;
-
-	if (!entry->addr.id)
-		return;
+	bh_lock_sock(sk);
+	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+		goto out;
 
-	if (mptcp_pm_should_add_signal_addr(msk)) {
-		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
+	if (sock_owned_by_user(sk)) {
+		/* Try again later. */
+		timeout = HZ / 20;
 		goto out;
 	}
 
 	timeout = mptcp_adjust_add_addr_timeout(msk);
-	if (!timeout)
+	if (!timeout || mptcp_pm_should_add_signal_addr(msk))
 		goto out;
 
 	spin_lock_bh(&msk->pm.lock);
@@ -359,8 +372,9 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 	}
 
 	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
-		sk_reset_timer(sk, timer,
-			       jiffies + (timeout << entry->retrans_times));
+		timeout <<= entry->retrans_times;
+	else
+		timeout = 0;
 
 	spin_unlock_bh(&msk->pm.lock);
 
@@ -368,7 +382,13 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 		mptcp_pm_subflow_established(msk);
 
 out:
-	__sock_put(sk);
+	if (timeout)
+		sk_reset_timer(sk, timer, jiffies + timeout);
+	else
+		/* if sock_put calls sk_free: avoid waiting for this timer */
+		entry->timer_done = true;
+	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 struct mptcp_pm_add_entry *
@@ -431,6 +451,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 
 	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
 reset_timer:
+	add_entry->timer_done = false;
 	timeout = mptcp_adjust_add_addr_timeout(msk);
 	if (timeout)
 		sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);
@@ -451,7 +472,8 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->pm.lock);
 
 	list_for_each_entry_safe(entry, tmp, &free_list, list) {
-		sk_stop_timer_sync(sk, &entry->add_timer);
+		if (!entry->timer_done)
+			sk_stop_timer_sync(sk, &entry->add_timer);
 		kfree_rcu(entry, rcu);
 	}
 }
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index c9f1e5af3cd3..fc818b63752e 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -347,6 +347,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 
 	/* check first for announce */
 	if (msk->pm.add_addr_signaled < endp_signal_max) {
+		u8 endp_id;
+
 		/* 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
@@ -360,19 +362,20 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (!select_signal_address(pernet, msk, &local))
 			goto subflow;
 
+		/* Special case for ID0: set the correct ID */
+		endp_id = local.addr.id;
+		if (endp_id == msk->mpc_endpoint_id)
+			local.addr.id = 0;
+
 		/* 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);
+		__clear_bit(endp_id, msk->pm.id_avail_bitmap);
 		msk->pm.add_addr_signaled++;
 
-		/* Special case for ID0: set the correct ID */
-		if (local.addr.id == msk->mpc_endpoint_id)
-			local.addr.id = 0;
-
 		mptcp_pm_announce_addr(msk, &local.addr, false);
 		mptcp_pm_addr_send_ack(msk);
 
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 0efe40be2fde..1cf608e7357b 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -812,6 +812,10 @@ static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level,
 		if (ret)
 			break;
 	}
+
+	if (!ret)
+		sockopt_seq_inc(msk);
+
 	return ret;
 }
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e2cb9d23e4a0..d562e149606f 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -581,7 +581,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			 subflow->backup);
 
 		if (!subflow_thmac_valid(subflow)) {
-			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKMAC);
 			subflow->reset_reason = MPTCP_RST_EMPTCP;
 			goto do_reset;
 		}
@@ -908,7 +908,7 @@ create_child:
 
 			if (!subflow_hmac_valid(subflow_req, &mp_opt)) {
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
-				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+				subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
 				goto dispose_child;
 			}