Merge tag 'net-6.10-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - core: fix rc7's __skb_datagram_iter() regression

  Current release - new code bugs:

   - eth: bnxt: fix crashes when reducing ring count with active RSS
     contexts

  Previous releases - regressions:

   - sched: fix UAF when resolving a clash

   - skmsg: skip zero length skb in sk_msg_recvmsg2

   - sunrpc: fix kernel free on connection failure in
     xs_tcp_setup_socket

   - tcp: avoid too many retransmit packets

   - tcp: fix incorrect undo caused by DSACK of TLP retransmit

   - udp: Set SOCK_RCU_FREE earlier in udp_lib_get_port().

   - eth: ks8851: fix deadlock with the SPI chip variant

   - eth: i40e: fix XDP program unloading while removing the driver

  Previous releases - always broken:

   - bpf:
       - fix too early release of tcx_entry
       - fail bpf_timer_cancel when callback is being cancelled
       - bpf: fix order of args in call to bpf_map_kvcalloc

   - netfilter: nf_tables: prefer nft_chain_validate

   - ppp: reject claimed-as-LCP but actually malformed packets

   - wireguard: avoid unaligned 64-bit memory accesses"

* tag 'net-6.10-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (33 commits)
  net, sunrpc: Remap EPERM in case of connection failure in xs_tcp_setup_socket
  net/sched: Fix UAF when resolving a clash
  net: ks8851: Fix potential TX stall after interface reopen
  udp: Set SOCK_RCU_FREE earlier in udp_lib_get_port().
  netfilter: nf_tables: prefer nft_chain_validate
  netfilter: nfnetlink_queue: drop bogus WARN_ON
  ethtool: netlink: do not return SQI value if link is down
  ppp: reject claimed-as-LCP but actually malformed packets
  selftests/bpf: Add timer lockup selftest
  net: ethernet: mtk-star-emac: set mac_managed_pm when probing
  e1000e: fix force smbus during suspend flow
  tcp: avoid too many retransmit packets
  bpf: Defer work in bpf_timer_cancel_and_free
  bpf: Fail bpf_timer_cancel when callback is being cancelled
  bpf: fix order of args in call to bpf_map_kvcalloc
  net: ethernet: lantiq_etop: fix double free in detach
  i40e: Fix XDP program unloading while removing the driver
  net: fix rc7's __skb_datagram_iter()
  net: ks8851: Fix deadlock with the SPI chip variant
  octeontx2-af: Fix incorrect value output on error path in rvu_check_rsrc_availability()
  ...

3 files changed, 26 insertions, 6 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 77294fd5fd3e..38da23f991d6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2129,8 +2129,16 @@ void tcp_clear_retrans(struct tcp_sock *tp)
 static inline void tcp_init_undo(struct tcp_sock *tp)
 {
 	tp->undo_marker = tp->snd_una;
+
 	/* Retransmission still in flight may cause DSACKs later. */
-	tp->undo_retrans = tp->retrans_out ? : -1;
+	/* First, account for regular retransmits in flight: */
+	tp->undo_retrans = tp->retrans_out;
+	/* Next, account for TLP retransmits in flight: */
+	if (tp->tlp_high_seq && tp->tlp_retrans)
+		tp->undo_retrans++;
+	/* Finally, avoid 0, because undo_retrans==0 means "can undo now": */
+	if (!tp->undo_retrans)
+		tp->undo_retrans = -1;
 }
 
 static bool tcp_is_rack(const struct sock *sk)
@@ -2209,6 +2217,7 @@ void tcp_enter_loss(struct sock *sk)
 
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
+	tp->tlp_high_seq = 0;
 	tcp_ecn_queue_cwr(tp);
 
 	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 5bfd76a31af6..892c86657fbc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -483,15 +483,26 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
 				     const struct sk_buff *skb,
 				     u32 rtx_delta)
 {
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	const int timeout = TCP_RTO_MAX * 2;
+	int timeout = TCP_RTO_MAX * 2;
 	s32 rcv_delta;
 
+	if (user_timeout) {
+		/* If user application specified a TCP_USER_TIMEOUT,
+		 * it does not want win 0 packets to 'reset the timer'
+		 * while retransmits are not making progress.
+		 */
+		if (rtx_delta > user_timeout)
+			return true;
+		timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout));
+	}
 	/* Note: timer interrupt might have been delayed by at least one jiffy,
 	 * and tp->rcv_tstamp might very well have been written recently.
 	 * rcv_delta can thus be negative.
 	 */
-	rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+	rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp;
 	if (rcv_delta <= timeout)
 		return false;
 
@@ -536,8 +547,6 @@ void tcp_retransmit_timer(struct sock *sk)
 	if (WARN_ON_ONCE(!skb))
 		return;
 
-	tp->tlp_high_seq = 0;
-
 	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
 	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
 		/* Receiver dastardly shrinks window. Our retransmits
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 189c9113fe9a..578668878a85 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -326,6 +326,8 @@ found:
 			goto fail_unlock;
 		}
 
+		sock_set_flag(sk, SOCK_RCU_FREE);
+
 		sk_add_node_rcu(sk, &hslot->head);
 		hslot->count++;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -342,7 +344,7 @@ found:
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}
-	sock_set_flag(sk, SOCK_RCU_FREE);
+
 	error = 0;
 fail_unlock:
 	spin_unlock_bh(&hslot->lock);