Merge tag 'net-6.12-rc3' 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:

   - dsa: sja1105: fix reception from VLAN-unaware bridges

   - Revert "net: stmmac: set PP_FLAG_DMA_SYNC_DEV only if XDP is
     enabled"

   - eth: fec: don't save PTP state if PTP is unsupported

  Current release - new code bugs:

   - smc: fix lack of icsk_syn_mss with IPPROTO_SMC, prevent null-deref

   - eth: airoha: update Tx CPU DMA ring idx at the end of xmit loop

   - phy: aquantia: AQR115c fix up PMA capabilities

  Previous releases - regressions:

   - tcp: 3 fixes for retrans_stamp and undo logic

  Previous releases - always broken:

   - net: do not delay dst_entries_add() in dst_release()

   - netfilter: restrict xtables extensions to families that are safe,
     syzbot found a way to combine ebtables with extensions that are
     never used by userspace tools

   - sctp: ensure sk_state is set to CLOSED if hashing fails in
     sctp_listen_start

   - mptcp: handle consistently DSS corruption, and prevent corruption
     due to large pmtu xmit"

* tag 'net-6.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (87 commits)
  MAINTAINERS: Add headers and mailing list to UDP section
  MAINTAINERS: consistently exclude wireless files from NETWORKING [GENERAL]
  slip: make slhc_remember() more robust against malicious packets
  net/smc: fix lacks of icsk_syn_mss with IPPROTO_SMC
  ppp: fix ppp_async_encode() illegal access
  docs: netdev: document guidance on cleanup patches
  phonet: Handle error of rtnl_register_module().
  mpls: Handle error of rtnl_register_module().
  mctp: Handle error of rtnl_register_module().
  bridge: Handle error of rtnl_register_module().
  vxlan: Handle error of rtnl_register_module().
  rtnetlink: Add bulk registration helpers for rtnetlink message handlers.
  net: do not delay dst_entries_add() in dst_release()
  mptcp: pm: do not remove closing subflows
  mptcp: fallback when MPTCP opts are dropped after 1st data
  tcp: fix mptcp DSS corruption due to large pmtu xmit
  mptcp: handle consistently DSS corruption
  net: netconsole: fix wrong warning
  net: dsa: refuse cross-chip mirroring operations
  net: fec: don't save PTP state if PTP is unsupported
  ...

3 files changed, 40 insertions, 11 deletions

diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 00da1332bbf1..09fff5d424ef 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		.flowi4_scope = RT_SCOPE_UNIVERSE,
 		.flowi4_iif = LOOPBACK_IFINDEX,
 		.flowi4_uid = sock_net_uid(nft_net(pkt), NULL),
+		.flowi4_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)),
 	};
 	const struct net_device *oif;
 	const struct net_device *found;
@@ -83,9 +84,6 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	else
 		oif = NULL;
 
-	if (priv->flags & NFTA_FIB_F_IIF)
-		fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(oif);
-
 	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
 	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
 		nft_fib_store_result(dest, priv, nft_in(pkt));
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc05ec1faac8..2d844e1f867f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2473,8 +2473,22 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp,
  */
 static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
 {
-	return tp->retrans_stamp &&
-	       tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
+	const struct sock *sk = (const struct sock *)tp;
+
+	if (tp->retrans_stamp &&
+	    tcp_tsopt_ecr_before(tp, tp->retrans_stamp))
+		return true;  /* got echoed TS before first retransmission */
+
+	/* Check if nothing was retransmitted (retrans_stamp==0), which may
+	 * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp
+	 * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear
+	 * retrans_stamp even if we had retransmitted the SYN.
+	 */
+	if (!tp->retrans_stamp &&	   /* no record of a retransmit/SYN? */
+	    sk->sk_state != TCP_SYN_SENT)  /* not the FLAG_SYN_ACKED case? */
+		return true;  /* nothing was retransmitted */
+
+	return false;
 }
 
 /* Undo procedures. */
@@ -2508,6 +2522,16 @@ static bool tcp_any_retrans_done(const struct sock *sk)
 	return false;
 }
 
+/* If loss recovery is finished and there are no retransmits out in the
+ * network, then we clear retrans_stamp so that upon the next loss recovery
+ * retransmits_timed_out() and timestamp-undo are using the correct value.
+ */
+static void tcp_retrans_stamp_cleanup(struct sock *sk)
+{
+	if (!tcp_any_retrans_done(sk))
+		tcp_sk(sk)->retrans_stamp = 0;
+}
+
 static void DBGUNDO(struct sock *sk, const char *msg)
 {
 #if FASTRETRANS_DEBUG > 1
@@ -2875,6 +2899,9 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int mib_idx;
 
+	/* Start the clock with our fast retransmit, for undo and ETIMEDOUT. */
+	tcp_retrans_stamp_cleanup(sk);
+
 	if (tcp_is_reno(tp))
 		mib_idx = LINUX_MIB_TCPRENORECOVERY;
 	else
@@ -6657,10 +6684,17 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss && !tp->packets_out)
 		tcp_try_undo_recovery(sk);
 
-	/* Reset rtx states to prevent spurious retransmits_timed_out() */
 	tcp_update_rto_time(tp);
-	tp->retrans_stamp = 0;
 	inet_csk(sk)->icsk_retransmits = 0;
+	/* In tcp_fastopen_synack_timer() on the first SYNACK RTO we set
+	 * retrans_stamp but don't enter CA_Loss, so in case that happened we
+	 * need to zero retrans_stamp here to prevent spurious
+	 * retransmits_timed_out(). However, if the ACK of our SYNACK caused us
+	 * to enter CA_Recovery then we need to leave retrans_stamp as it was
+	 * set entering CA_Recovery, for correct retransmits_timed_out() and
+	 * undo behavior.
+	 */
+	tcp_retrans_stamp_cleanup(sk);
 
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4fd746bd4d54..68804fd01daf 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2342,10 +2342,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor) ||
-		    tcp_has_tx_tstamp(skb) ||
-		    !skb_pure_zcopy_same(skb, next) ||
-		    skb_frags_readable(skb) != skb_frags_readable(next))
+		if (tcp_has_tx_tstamp(skb) || !tcp_skb_can_collapse(skb, next))
 			return false;
 
 		len -= skb->len;