Merge tag 'net-7.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull  networking fixes from Jakub Kicinski:
 "Including fixes from Netfilter.

  Steady stream of fixes. Last two weeks feel comparable to the two
  weeks before the merge window. Lots of AI-aided bug discovery. A newer
  big source is Sashiko/Gemini (Roman Gushchin's system), which points
  out issues in existing code during patch review (maybe 25% of fixes
  here likely originating from Sashiko). Nice thing is these are often
  fixed by the respective maintainers, not drive-bys.

  Current release - new code bugs:

   - kconfig: MDIO_PIC64HPSC should depend on ARCH_MICROCHIP

  Previous releases - regressions:

   - add async ndo_set_rx_mode and switch drivers which we promised to
     be called under the per-netdev mutex to it

   - dsa: remove duplicate netdev_lock_ops() for conduit ethtool ops

   - hv_sock: report EOF instead of -EIO for FIN

   - vsock/virtio: fix MSG_PEEK calculation on bytes to copy

  Previous releases - always broken:

   - ipv6: fix possible UAF in icmpv6_rcv()

   - icmp: validate reply type before using icmp_pointers

   - af_unix: drop all SCM attributes for SOCKMAP

   - netfilter: fix a number of bugs in the osf (OS fingerprinting)

   - eth: intel: fix timestamp interrupt configuration for E825C

  Misc:

   - bunch of data-race annotations"

* tag 'net-7.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (148 commits)
  rxrpc: Fix error handling in rxgk_extract_token()
  rxrpc: Fix re-decryption of RESPONSE packets
  rxrpc: Fix rxrpc_input_call_event() to only unshare DATA packets
  rxrpc: Fix missing validation of ticket length in non-XDR key preparsing
  rxgk: Fix potential integer overflow in length check
  rxrpc: Fix conn-level packet handling to unshare RESPONSE packets
  rxrpc: Fix potential UAF after skb_unshare() failure
  rxrpc: Fix rxkad crypto unalignment handling
  rxrpc: Fix memory leaks in rxkad_verify_response()
  net: rds: fix MR cleanup on copy error
  m68k: mvme147: Make me the maintainer
  net: txgbe: fix firmware version check
  selftests/bpf: check epoll readiness during reuseport migration
  tcp: call sk_data_ready() after listener migration
  vhost_net: fix sleeping with preempt-disabled in vhost_net_busy_poll()
  ipv6: Cap TLV scan in ip6_tnl_parse_tlv_enc_lim
  tipc: fix double-free in tipc_buf_append()
  llc: Return -EINPROGRESS from llc_ui_connect()
  ipv4: icmp: validate reply type before using icmp_pointers
  selftests/net: packetdrill: cover RFC 5961 5.2 challenge ACK on both edges
  ...

19 files changed, 115 insertions, 86 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 2f4fac22d1ab..7eeff658b467 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -64,6 +64,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/fcntl.h>
+#include <linux/nospec.h>
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/inet.h>
@@ -371,7 +372,9 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
 				      to, len);
 
 	skb->csum = csum_block_add(skb->csum, csum, odd);
-	if (icmp_pointers[icmp_param->data.icmph.type].error)
+	if (icmp_param->data.icmph.type <= NR_ICMP_TYPES &&
+	    icmp_pointers[array_index_nospec(icmp_param->data.icmph.type,
+					     NR_ICMP_TYPES + 1)].error)
 		nf_ct_attach(skb, icmp_param->skb);
 	return 0;
 }
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4ac3ae1bc1af..928654c34156 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1479,16 +1479,19 @@ void inet_csk_listen_stop(struct sock *sk)
 			if (nreq) {
 				refcount_set(&nreq->rsk_refcnt, 1);
 
+				rcu_read_lock();
 				if (inet_csk_reqsk_queue_add(nsk, nreq, child)) {
 					__NET_INC_STATS(sock_net(nsk),
 							LINUX_MIB_TCPMIGRATEREQSUCCESS);
 					reqsk_migrate_reset(req);
+					READ_ONCE(nsk->sk_data_ready)(nsk);
 				} else {
 					__NET_INC_STATS(sock_net(nsk),
 							LINUX_MIB_TCPMIGRATEREQFAILURE);
 					reqsk_migrate_reset(nreq);
 					__reqsk_free(nreq);
 				}
+				rcu_read_unlock();
 
 				/* inet_csk_reqsk_queue_add() has already
 				 * called inet_child_forget() on failure case.
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index a5db7c67d61b..625a1ca13b1b 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -79,7 +79,7 @@ static int ipt_nat_register_lookups(struct net *net)
 			while (i)
 				nf_nat_ipv4_unregister_fn(net, &ops[--i]);
 
-			kfree(ops);
+			kfree_rcu(ops, rcu);
 			return ret;
 		}
 	}
@@ -100,7 +100,7 @@ static void ipt_nat_unregister_lookups(struct net *net)
 	for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++)
 		nf_nat_ipv4_unregister_fn(net, &ops[i]);
 
-	kfree(ops);
+	kfree_rcu(ops, rcu);
 }
 
 static int iptable_nat_table_init(struct net *net)
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 904a060a7330..f92fcc39fc4c 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2469,10 +2469,10 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old,
 			goto err_notify;
 	}
 
-	/* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially
+	/* When replacing a nexthop with one of a different family, potentially
 	 * update IPv4 indication in all the groups using the nexthop.
 	 */
-	if (oldi->family == AF_INET && newi->family == AF_INET6) {
+	if (oldi->family != newi->family) {
 		list_for_each_entry(nhge, &old->grp_list, nh_list) {
 			struct nexthop *nhp = nhge->nh_parent;
 			struct nh_group *nhg;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2014a6408e93..432fa28e47d4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3424,7 +3424,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
 	WRITE_ONCE(icsk->icsk_delack_max, TCP_DELACK_MAX);
-	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	WRITE_ONCE(tp->snd_ssthresh, TCP_INFINITE_SSTHRESH);
 	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 	tp->snd_cwnd_cnt = 0;
 	tp->is_cwnd_limited = 0;
@@ -3622,7 +3622,8 @@ static void tcp_enable_tx_delay(struct sock *sk, int val)
 	if (delta && sk->sk_state == TCP_ESTABLISHED) {
 		s64 srtt = (s64)tp->srtt_us + delta;
 
-		tp->srtt_us = clamp_t(s64, srtt, 1, ~0U);
+		WRITE_ONCE(tp->srtt_us,
+			   clamp_t(s64, srtt, 1, ~0U));
 
 		/* Note: does not deal with non zero icsk_backoff */
 		tcp_set_rto(sk);
@@ -4190,12 +4191,18 @@ static void tcp_get_info_chrono_stats(const struct tcp_sock *tp,
 				      struct tcp_info *info)
 {
 	u64 stats[__TCP_CHRONO_MAX], total = 0;
-	enum tcp_chrono i;
+	enum tcp_chrono i, cur;
 
+	/* Following READ_ONCE()s pair with WRITE_ONCE()s in tcp_chrono_set().
+	 * This is because socket lock might not be owned by us at this point.
+	 * This is best effort, tcp_get_timestamping_opt_stats() can
+	 * see wrong values. A real fix would be too costly for TCP fast path.
+	 */
+	cur = READ_ONCE(tp->chrono_type);
 	for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) {
-		stats[i] = tp->chrono_stat[i - 1];
-		if (i == tp->chrono_type)
-			stats[i] += tcp_jiffies32 - tp->chrono_start;
+		stats[i] = READ_ONCE(tp->chrono_stat[i - 1]);
+		if (i == cur)
+			stats[i] += tcp_jiffies32 - READ_ONCE(tp->chrono_start);
 		stats[i] *= USEC_PER_SEC / HZ;
 		total += stats[i];
 	}
@@ -4427,9 +4434,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 	nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED,
 			  info.tcpi_sndbuf_limited, TCP_NLA_PAD);
 	nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT,
-			  tp->data_segs_out, TCP_NLA_PAD);
+			  READ_ONCE(tp->data_segs_out), TCP_NLA_PAD);
 	nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS,
-			  tp->total_retrans, TCP_NLA_PAD);
+			  READ_ONCE(tp->total_retrans), TCP_NLA_PAD);
 
 	rate = READ_ONCE(sk->sk_pacing_rate);
 	rate64 = (rate != ~0UL) ? rate : ~0ULL;
@@ -4438,37 +4445,42 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 	rate64 = tcp_compute_delivery_rate(tp);
 	nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD);
 
-	nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp));
-	nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering);
-	nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp));
+	nla_put_u32(stats, TCP_NLA_SND_CWND, READ_ONCE(tp->snd_cwnd));
+	nla_put_u32(stats, TCP_NLA_REORDERING, READ_ONCE(tp->reordering));
+	nla_put_u32(stats, TCP_NLA_MIN_RTT, data_race(tcp_min_rtt(tp)));
 
 	nla_put_u8(stats, TCP_NLA_RECUR_RETRANS,
 		   READ_ONCE(inet_csk(sk)->icsk_retransmits));
-	nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited);
-	nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh);
-	nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered);
-	nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce);
-
-	nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una);
+	nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, data_race(!!tp->rate_app_limited));
+	nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, READ_ONCE(tp->snd_ssthresh));
+	nla_put_u32(stats, TCP_NLA_DELIVERED, READ_ONCE(tp->delivered));
+	nla_put_u32(stats, TCP_NLA_DELIVERED_CE, READ_ONCE(tp->delivered_ce));
+
+	nla_put_u32(stats, TCP_NLA_SNDQ_SIZE,
+		    max_t(int, 0,
+			  READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_una)));
 	nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state);
 
-	nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
-			  TCP_NLA_PAD);
-	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
+	nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, READ_ONCE(tp->bytes_sent),
 			  TCP_NLA_PAD);
-	nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
-	nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
-	nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3);
-	nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash);
+	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS,
+			  READ_ONCE(tp->bytes_retrans), TCP_NLA_PAD);
+	nla_put_u32(stats, TCP_NLA_DSACK_DUPS, READ_ONCE(tp->dsack_dups));
+	nla_put_u32(stats, TCP_NLA_REORD_SEEN, READ_ONCE(tp->reord_seen));
+	nla_put_u32(stats, TCP_NLA_SRTT, READ_ONCE(tp->srtt_us) >> 3);
+	nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH,
+		    READ_ONCE(tp->timeout_rehash));
 	nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT,
-		    max_t(int, 0, tp->write_seq - tp->snd_nxt));
+		    max_t(int, 0,
+			  READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt)));
 	nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns,
 			  TCP_NLA_PAD);
 	if (ack_skb)
 		nla_put_u8(stats, TCP_NLA_TTL,
 			   tcp_skb_ttl_or_hop_limit(ack_skb));
 
-	nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash);
+	nla_put_u32(stats, TCP_NLA_REHASH,
+		    READ_ONCE(tp->plb_rehash) + READ_ONCE(tp->timeout_rehash));
 	return stats;
 }
 
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 1ddc20a399b0..aec7805b1d37 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -897,8 +897,8 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs)
 
 	if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) {
 		bbr->mode = BBR_DRAIN;	/* drain queue we created */
-		tcp_sk(sk)->snd_ssthresh =
-				bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT);
+		WRITE_ONCE(tcp_sk(sk)->snd_ssthresh,
+			   bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT));
 	}	/* fall through to check if in-flight is already small: */
 	if (bbr->mode == BBR_DRAIN &&
 	    bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <=
@@ -1043,7 +1043,7 @@ __bpf_kfunc static void bbr_init(struct sock *sk)
 	struct bbr *bbr = inet_csk_ca(sk);
 
 	bbr->prior_cwnd = 0;
-	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	WRITE_ONCE(tp->snd_ssthresh, TCP_INFINITE_SSTHRESH);
 	bbr->rtt_cnt = 0;
 	bbr->next_rtt_delivered = tp->delivered;
 	bbr->prev_ca_state = TCP_CA_Open;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 58358bf92e1b..65444ff14241 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -74,7 +74,7 @@ static void bictcp_init(struct sock *sk)
 	bictcp_reset(ca);
 
 	if (initial_ssthresh)
-		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+		WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, initial_ssthresh);
 }
 
 /*
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index ceabfd690a29..0812c390aee5 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -162,7 +162,7 @@ static void tcp_cdg_hystart_update(struct sock *sk)
 				NET_ADD_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTTRAINCWND,
 					      tcp_snd_cwnd(tp));
-				tp->snd_ssthresh = tcp_snd_cwnd(tp);
+				WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp));
 				return;
 			}
 		}
@@ -181,7 +181,7 @@ static void tcp_cdg_hystart_update(struct sock *sk)
 				NET_ADD_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTDELAYCWND,
 					      tcp_snd_cwnd(tp));
-				tp->snd_ssthresh = tcp_snd_cwnd(tp);
+				WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp));
 			}
 		}
 	}
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index ab78b5ae8d0e..119bf8cbb007 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -136,7 +136,7 @@ __bpf_kfunc static void cubictcp_init(struct sock *sk)
 		bictcp_hystart_reset(sk);
 
 	if (!hystart && initial_ssthresh)
-		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+		WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, initial_ssthresh);
 }
 
 __bpf_kfunc static void cubictcp_cwnd_event_tx_start(struct sock *sk)
@@ -420,7 +420,7 @@ static void hystart_update(struct sock *sk, u32 delay)
 				NET_ADD_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTTRAINCWND,
 					      tcp_snd_cwnd(tp));
-				tp->snd_ssthresh = tcp_snd_cwnd(tp);
+				WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp));
 			}
 		}
 	}
@@ -440,7 +440,7 @@ static void hystart_update(struct sock *sk, u32 delay)
 				NET_ADD_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTDELAYCWND,
 					      tcp_snd_cwnd(tp));
-				tp->snd_ssthresh = tcp_snd_cwnd(tp);
+				WRITE_ONCE(tp->snd_ssthresh, tcp_snd_cwnd(tp));
 			}
 		}
 	}
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 96c99999e09d..274e628e7cf8 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -177,7 +177,7 @@ static void dctcp_react_to_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	ca->loss_cwnd = tcp_snd_cwnd(tp);
-	tp->snd_ssthresh = max(tcp_snd_cwnd(tp) >> 1U, 2U);
+	WRITE_ONCE(tp->snd_ssthresh, max(tcp_snd_cwnd(tp) >> 1U, 2U));
 }
 
 __bpf_kfunc static void dctcp_state(struct sock *sk, u8 new_state)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 021f745747c5..d5c9e65d9760 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -476,14 +476,14 @@ static bool tcp_accecn_process_option(struct tcp_sock *tp,
 
 static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count)
 {
-	tp->delivered_ce += ecn_count;
+	WRITE_ONCE(tp->delivered_ce, tp->delivered_ce + ecn_count);
 }
 
 /* Updates the delivered and delivered_ce counts */
 static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
 				bool ece_ack)
 {
-	tp->delivered += delivered;
+	WRITE_ONCE(tp->delivered, tp->delivered + delivered);
 	if (tcp_ecn_mode_rfc3168(tp) && ece_ack)
 		tcp_count_delivered_ce(tp, delivered);
 }
@@ -1132,7 +1132,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 
 		tcp_bpf_rtt(sk, mrtt_us, srtt);
 	}
-	tp->srtt_us = max(1U, srtt);
+	WRITE_ONCE(tp->srtt_us, max(1U, srtt));
 }
 
 void tcp_update_pacing_rate(struct sock *sk)
@@ -1246,7 +1246,7 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
 	else if (tp->tlp_high_seq && tp->tlp_high_seq == end_seq)
 		state->flag |= FLAG_DSACK_TLP;
 
-	tp->dsack_dups += dup_segs;
+	WRITE_ONCE(tp->dsack_dups, tp->dsack_dups + dup_segs);
 	/* Skip the DSACK if dup segs weren't retransmitted by sender */
 	if (tp->dsack_dups > tp->total_retrans)
 		return 0;
@@ -1293,12 +1293,13 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 			 tp->sacked_out,
 			 tp->undo_marker ? tp->undo_retrans : 0);
 #endif
-		tp->reordering = min_t(u32, (metric + mss - 1) / mss,
-				       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
+		WRITE_ONCE(tp->reordering,
+			   min_t(u32, (metric + mss - 1) / mss,
+				 READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)));
 	}
 
 	/* This exciting event is worth to be remembered. 8) */
-	tp->reord_seen++;
+	WRITE_ONCE(tp->reord_seen, tp->reord_seen + 1);
 	NET_INC_STATS(sock_net(sk),
 		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
@@ -2439,9 +2440,10 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 	if (!tcp_limit_reno_sacked(tp))
 		return;
 
-	tp->reordering = min_t(u32, tp->packets_out + addend,
-			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
-	tp->reord_seen++;
+	WRITE_ONCE(tp->reordering,
+		   min_t(u32, tp->packets_out + addend,
+			 READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)));
+	WRITE_ONCE(tp->reord_seen, tp->reord_seen + 1);
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
 }
 
@@ -2565,7 +2567,7 @@ void tcp_enter_loss(struct sock *sk)
 	    (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
 		tp->prior_ssthresh = tcp_current_ssthresh(sk);
 		tp->prior_cwnd = tcp_snd_cwnd(tp);
-		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+		WRITE_ONCE(tp->snd_ssthresh, icsk->icsk_ca_ops->ssthresh(sk));
 		tcp_ca_event(sk, CA_EVENT_LOSS);
 		tcp_init_undo(tp);
 	}
@@ -2579,8 +2581,8 @@ void tcp_enter_loss(struct sock *sk)
 	reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering);
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
 	    tp->sacked_out >= reordering)
-		tp->reordering = min_t(unsigned int, tp->reordering,
-				       reordering);
+		WRITE_ONCE(tp->reordering,
+			   min_t(unsigned int, tp->reordering, reordering));
 
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
@@ -2858,7 +2860,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 		tcp_snd_cwnd_set(tp, icsk->icsk_ca_ops->undo_cwnd(sk));
 
 		if (tp->prior_ssthresh > tp->snd_ssthresh) {
-			tp->snd_ssthresh = tp->prior_ssthresh;
+			WRITE_ONCE(tp->snd_ssthresh, tp->prior_ssthresh);
 			tcp_ecn_withdraw_cwr(tp);
 		}
 	}
@@ -2976,7 +2978,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk)
 	tp->prior_cwnd = tcp_snd_cwnd(tp);
 	tp->prr_delivered = 0;
 	tp->prr_out = 0;
-	tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk);
+	WRITE_ONCE(tp->snd_ssthresh, inet_csk(sk)->icsk_ca_ops->ssthresh(sk));
 	tcp_ecn_queue_cwr(tp);
 }
 
@@ -3118,7 +3120,7 @@ static void tcp_non_congestion_loss_retransmit(struct sock *sk)
 
 	if (icsk->icsk_ca_state != TCP_CA_Loss) {
 		tp->high_seq = tp->snd_nxt;
-		tp->snd_ssthresh = tcp_current_ssthresh(sk);
+		WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk));
 		tp->prior_ssthresh = 0;
 		tp->undo_marker = 0;
 		tcp_set_ca_state(sk, TCP_CA_Loss);
@@ -3910,7 +3912,7 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_acked += delta;
 	tcp_snd_sne_update(tp, ack);
-	tp->snd_una = ack;
+	WRITE_ONCE(tp->snd_una, ack);
 }
 
 static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq)
@@ -4284,11 +4286,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		goto old_ack;
 	}
 
-	/* If the ack includes data we haven't sent yet, discard
-	 * this segment (RFC793 Section 3.9).
+	/* If the ack includes data we haven't sent yet, drop the
+	 * segment.  RFC 793 Section 3.9 and RFC 5961 Section 5.2
+	 * require us to send an ACK back in that case.
 	 */
-	if (after(ack, tp->snd_nxt))
+	if (after(ack, tp->snd_nxt)) {
+		if (!(flag & FLAG_NO_CHALLENGE_ACK))
+			tcp_send_challenge_ack(sk, false);
 		return -SKB_DROP_REASON_TCP_ACK_UNSENT_DATA;
+	}
 
 	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
@@ -6777,7 +6783,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
 		/* SYN-data is counted as two separate packets in tcp_ack() */
 		if (tp->delivered > 1)
-			--tp->delivered;
+			WRITE_ONCE(tp->delivered, tp->delivered - 1);
 	}
 
 	tcp_fastopen_add_skb(sk, synack);
@@ -7210,7 +7216,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	SKB_DR_SET(reason, NOT_SPECIFIED);
 	switch (sk->sk_state) {
 	case TCP_SYN_RECV:
-		tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */
+		WRITE_ONCE(tp->delivered, tp->delivered + 1); /* SYN-ACK delivery isn't tracked in tcp_ack */
 		if (!tp->srtt_us)
 			tcp_synack_rtt_meas(sk, req);
 
@@ -7238,7 +7244,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (sk->sk_socket)
 			sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
 
-		tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
+		WRITE_ONCE(tp->snd_una, TCP_SKB_CB(skb)->ack_seq);
 		tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
 		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
 
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 06b1d5d3b6df..dc0c081fc1f3 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -490,13 +490,13 @@ void tcp_init_metrics(struct sock *sk)
 	val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
 	      0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 	if (val) {
-		tp->snd_ssthresh = val;
+		WRITE_ONCE(tp->snd_ssthresh, val);
 		if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
-			tp->snd_ssthresh = tp->snd_cwnd_clamp;
+			WRITE_ONCE(tp->snd_ssthresh, tp->snd_cwnd_clamp);
 	}
 	val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
 	if (val && tp->reordering != val)
-		tp->reordering = val;
+		WRITE_ONCE(tp->reordering, val);
 
 	crtt = tcp_metric_get(tm, TCP_METRIC_RTT);
 	rcu_read_unlock();
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index a60662f4bdf9..f345897a68df 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -396,8 +396,8 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 
 			/* We have enough data to determine we are congested */
 			ca->nv_allow_cwnd_growth = 0;
-			tp->snd_ssthresh =
-				(nv_ssthresh_factor * max_win) >> 3;
+			WRITE_ONCE(tp->snd_ssthresh,
+				   (nv_ssthresh_factor * max_win) >> 3);
 			if (tcp_snd_cwnd(tp) - max_win > 2) {
 				/* gap > 2, we do exponential cwnd decrease */
 				int dec;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e99687526a6..f9d8755705f7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -171,7 +171,7 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta)
 
 	tcp_ca_event(sk, CA_EVENT_CWND_RESTART);
 
-	tp->snd_ssthresh = tcp_current_ssthresh(sk);
+	WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk));
 	restart_cwnd = min(restart_cwnd, cwnd);
 
 	while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
@@ -1688,8 +1688,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
-		tp->data_segs_out += tcp_skb_pcount(skb);
-		tp->bytes_sent += skb->len - tcp_header_size;
+		WRITE_ONCE(tp->data_segs_out,
+			   tp->data_segs_out + tcp_skb_pcount(skb));
+		WRITE_ONCE(tp->bytes_sent,
+			   tp->bytes_sent + skb->len - tcp_header_size);
 	}
 
 	if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
@@ -2142,7 +2144,7 @@ static void tcp_cwnd_application_limited(struct sock *sk)
 		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
 		u32 win_used = max(tp->snd_cwnd_used, init_win);
 		if (win_used < tcp_snd_cwnd(tp)) {
-			tp->snd_ssthresh = tcp_current_ssthresh(sk);
+			WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk));
 			tcp_snd_cwnd_set(tp, (tcp_snd_cwnd(tp) + win_used) >> 1);
 		}
 		tp->snd_cwnd_used = 0;
@@ -3642,8 +3644,8 @@ start:
 	TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs);
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
-	tp->total_retrans += segs;
-	tp->bytes_retrans += skb->len;
+	WRITE_ONCE(tp->total_retrans, tp->total_retrans + segs);
+	WRITE_ONCE(tp->bytes_retrans, tp->bytes_retrans + skb->len);
 
 	/* make sure skb->data is aligned on arches that require it
 	 * and check if ack-trimming & collapsing extended the headroom
@@ -4152,7 +4154,7 @@ static void tcp_connect_init(struct sock *sk)
 	tp->snd_wnd = 0;
 	tcp_init_wl(tp, 0);
 	tcp_write_queue_purge(sk);
-	tp->snd_una = tp->write_seq;
+	WRITE_ONCE(tp->snd_una, tp->write_seq);
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
 	WRITE_ONCE(tp->snd_nxt, tp->write_seq);
@@ -4646,7 +4648,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 			 * However in this case, we are dealing with a passive fastopen
 			 * socket thus we can change total_retrans value.
 			 */
-			tcp_sk_rw(sk)->total_retrans++;
+			WRITE_ONCE(tcp_sk_rw(sk)->total_retrans,
+				   tcp_sk_rw(sk)->total_retrans + 1);
 		}
 		trace_tcp_retransmit_synack(sk, req);
 		WRITE_ONCE(req->num_retrans, req->num_retrans + 1);
diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c
index 68ccdb9a5412..c11a0cd3f8fe 100644
--- a/net/ipv4/tcp_plb.c
+++ b/net/ipv4/tcp_plb.c
@@ -80,7 +80,7 @@ void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb)
 
 	sk_rethink_txhash(sk);
 	plb->consec_cong_rounds = 0;
-	tcp_sk(sk)->plb_rehash++;
+	WRITE_ONCE(tcp_sk(sk)->plb_rehash, tcp_sk(sk)->plb_rehash + 1);
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH);
 }
 EXPORT_SYMBOL_GPL(tcp_plb_check_rehash);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index ea99988795e7..8d791a954cd6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -297,7 +297,7 @@ static int tcp_write_timeout(struct sock *sk)
 	}
 
 	if (sk_rethink_txhash(sk)) {
-		tp->timeout_rehash++;
+		WRITE_ONCE(tp->timeout_rehash, tp->timeout_rehash + 1);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH);
 	}
 
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 950a66966059..574453af6bc0 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -245,7 +245,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 				 */
 				tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp),
 							 (u32)target_cwnd + 1));
-				tp->snd_ssthresh = tcp_vegas_ssthresh(tp);
+				WRITE_ONCE(tp->snd_ssthresh,
+					   tcp_vegas_ssthresh(tp));
 
 			} else if (tcp_in_slow_start(tp)) {
 				/* Slow start.  */
@@ -261,8 +262,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 					 * we slow down.
 					 */
 					tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1);
-					tp->snd_ssthresh
-						= tcp_vegas_ssthresh(tp);
+					WRITE_ONCE(tp->snd_ssthresh,
+						   tcp_vegas_ssthresh(tp));
 				} else if (diff < alpha) {
 					/* We don't have enough extra packets
 					 * in the network, so speed up.
@@ -280,7 +281,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 			else if (tcp_snd_cwnd(tp) > tp->snd_cwnd_clamp)
 				tcp_snd_cwnd_set(tp, tp->snd_cwnd_clamp);
 
-			tp->snd_ssthresh = tcp_current_ssthresh(sk);
+			WRITE_ONCE(tp->snd_ssthresh, tcp_current_ssthresh(sk));
 		}
 
 		/* Wipe the slate clean for the next RTT. */
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index c6e97141eef2..b5a42adfd6ca 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -244,11 +244,11 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
 
 	switch (event) {
 	case CA_EVENT_COMPLETE_CWR:
-		tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
+		WRITE_ONCE(tp->snd_ssthresh, tcp_westwood_bw_rttmin(sk));
 		tcp_snd_cwnd_set(tp, tp->snd_ssthresh);
 		break;
 	case CA_EVENT_LOSS:
-		tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
+		WRITE_ONCE(tp->snd_ssthresh, tcp_westwood_bw_rttmin(sk));
 		/* Update RTT_min when next ack arrives */
 		w->reset_rtt_min = 1;
 		break;
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index b22b3dccd05e..9e581154f18f 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -147,7 +147,8 @@ do_vegas:
 					tcp_snd_cwnd_set(tp, max(tcp_snd_cwnd(tp),
 								 yeah->reno_count));
 
-					tp->snd_ssthresh = tcp_snd_cwnd(tp);
+					WRITE_ONCE(tp->snd_ssthresh,
+						   tcp_snd_cwnd(tp));
 				}
 
 				if (yeah->reno_count <= 2)