Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

No conflicts.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 62 insertions, 50 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 46e8a5125853..452ff177e4da 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1042,6 +1042,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
 
 void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 {
+	u8 fib_notify_on_flag_change;
 	struct fib_alias *fa_match;
 	struct sk_buff *skb;
 	int err;
@@ -1063,14 +1064,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
 	WRITE_ONCE(fa_match->offload, fri->offload);
 	WRITE_ONCE(fa_match->trap, fri->trap);
 
+	fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change);
+
 	/* 2 means send notifications only if offload_failed was changed. */
-	if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
+	if (fib_notify_on_flag_change == 2 &&
 	    READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
 		goto out;
 
 	WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
 
-	if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+	if (!fib_notify_on_flag_change)
 		goto out;
 
 	skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc7cc3ce6a53..970e9a2cca4a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -454,8 +454,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
-	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
 
 	sk_sockets_allocated_inc(sk);
 }
@@ -688,7 +688,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
-	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+	       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
 	       !tcp_rtx_queue_empty(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize &&
 	       tcp_skb_can_collapse_to(skb);
@@ -1842,7 +1842,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
 	else
-		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 	val = min(val, cap);
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
@@ -4573,9 +4573,18 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
 	}
 
-	/* check the signature */
-	genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected,
-						 NULL, skb);
+	/* Check the signature.
+	 * To support dual stack listeners, we need to handle
+	 * IPv4-mapped case.
+	 */
+	if (family == AF_INET)
+		genhash = tcp_v4_md5_hash_skb(newhash,
+					      hash_expected,
+					      NULL, skb);
+	else
+		genhash = tp->af_specific->calc_md5_hash(newhash,
+							 hash_expected,
+							 NULL, skb);
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ae73b34d32e9..ab5f0ea166f1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,7 +426,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
 
 	if (sk->sk_sndbuf < sndmem)
 		WRITE_ONCE(sk->sk_sndbuf,
-			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+			   min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -461,7 +461,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
 	int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
-	int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+	int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
 
 	while (tp->rcv_ssthresh <= window) {
 		if (truesize <= skb->len)
@@ -534,7 +534,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
  */
 static void tcp_init_buffer_space(struct sock *sk)
 {
-	int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+	int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int maxwin;
 
@@ -574,16 +574,17 @@ static void tcp_clamp_window(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
+	int rmem2;
 
 	icsk->icsk_ack.quick = 0;
+	rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
 
-	if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+	if (sk->sk_rcvbuf < rmem2 &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
 		WRITE_ONCE(sk->sk_rcvbuf,
-			   min(atomic_read(&sk->sk_rmem_alloc),
-			       net->ipv4.sysctl_tcp_rmem[2]));
+			   min(atomic_read(&sk->sk_rmem_alloc), rmem2));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -724,7 +725,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	 * <prev RTT . ><current RTT .. ><next RTT .... >
 	 */
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
@@ -745,7 +746,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 		do_div(rcvwin, tp->advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		if (rcvbuf > sk->sk_rcvbuf) {
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
@@ -909,9 +910,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	 *	 end of slow start and should slow down.
 	 */
 	if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
-		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
+		rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio);
 	else
-		rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
+		rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);
 
 	rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
 
@@ -2174,7 +2175,7 @@ void tcp_enter_loss(struct sock *sk)
 	 * loss recovery is underway except recurring timeout(s) on
 	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
 	 */
-	tp->frto = net->ipv4.sysctl_tcp_frto &&
+	tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
 		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
@@ -3057,7 +3058,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 
 static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
 {
-	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+	u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3580,7 +3581,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
 	if (*last_oow_ack_time) {
 		s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
 
-		if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+		if (0 <= elapsed &&
+		    elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
 			NET_INC_STATS(net, mib_idx);
 			return true;	/* rate-limited: don't send yet! */
 		}
@@ -3628,7 +3630,7 @@ static void tcp_send_challenge_ack(struct sock *sk)
 	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
-		u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+		u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
 		u32 half = (ack_limit + 1) >> 1;
 
 		challenge_timestamp = now;
@@ -4425,7 +4427,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+	if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
 		int mib_idx;
 
 		if (before(seq, tp->rcv_nxt))
@@ -4472,7 +4474,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 
-		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+		if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
 			tcp_rcv_spurious_retrans(sk, skb);
@@ -5516,7 +5518,7 @@ send_now:
 	}
 
 	if (!tcp_is_sack(tp) ||
-	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+	    tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
 		goto send_now;
 
 	if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5537,11 +5539,12 @@ send_now:
 	if (tp->srtt_us && tp->srtt_us < rtt)
 		rtt = tp->srtt_us;
 
-	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+	delay = min_t(unsigned long,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
 		      rtt * (NSEC_PER_USEC >> 3)/20);
 	sock_hold(sk);
 	hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
-			       sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
 			       HRTIMER_MODE_REL_PINNED_SOFT);
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c7e7101647dc..0c83780dc9bf 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1008,7 +1008,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
-		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+		tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
 				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
 				(inet_sk(sk)->tos & INET_ECN_MASK) :
 				inet_sk(sk)->tos;
@@ -1528,7 +1528,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	/* Set ToS of the new socket based upon the value of incoming SYN.
 	 * ECT bits are set later in tcp_init_transfer().
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
 		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
 	if (!dst) {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a501150deaa3..d58e672be31c 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
 	int m;
 
 	sk_dst_confirm(sk);
-	if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
 		return;
 
 	rcu_read_lock();
@@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk)
 
 	if (tcp_in_initial_slowstart(tp)) {
 		/* Slow start still did not finish. */
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
 			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 			if (val && (tcp_snd_cwnd(tp) >> 1) > val)
@@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk)
 	} else if (!tcp_in_slow_start(tp) &&
 		   icsk->icsk_ca_state == TCP_CA_Open) {
 		/* Cong. avoidance phase, cwnd is reliable. */
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
 			tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
 				       max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh));
@@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk)
 			tcp_metric_set(tm, TCP_METRIC_CWND,
 				       (val + tp->snd_ssthresh) >> 1);
 		}
-		if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
 		    !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
 			val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
 			if (val && tp->snd_ssthresh > val)
@@ -463,7 +463,7 @@ void tcp_init_metrics(struct sock *sk)
 	if (tcp_metric_locked(tm, TCP_METRIC_CWND))
 		tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
 
-	val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+	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;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2b72ccd2e651..78b654ff421b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	if (tcp_packets_in_flight(tp) == 0)
 		tcp_ca_event(sk, CA_EVENT_TX_START);
 
-	/* If this is the first data packet sent in response to the
-	 * previous received data,
-	 * and it is a reply for ato after last received packet,
-	 * increase pingpong count.
-	 */
-	if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
-	    (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		inet_csk_inc_pingpong_cnt(sk);
-
 	tp->lsndtime = now;
+
+	/* If it is a reply for ato after last received
+	 * packet, enter pingpong mode.
+	 */
+	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+		inet_csk_enter_pingpong_mode(sk);
 }
 
 /* Account for an ACK we sent. */
@@ -230,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	 * which we interpret as a sign the remote TCP is not
 	 * misinterpreting the window field as a signed quantity.
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
 		(*rcv_wnd) = min_t(u32, space, U16_MAX);
@@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
@@ -285,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk)
 	 * scaled window.
 	 */
 	if (!tp->rx_opt.rcv_wscale &&
-	    sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		new_win = min(new_win, MAX_TCP_WINDOW);
 	else
 		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -1976,7 +1973,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 
 	bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
 
-	r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log;
+	r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
 	if (r < BITS_PER_TYPE(sk->sk_gso_max_size))
 		bytes += sk->sk_gso_max_size >> r;
 
@@ -1995,7 +1992,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 
 	min_tso = ca_ops->min_tso_segs ?
 			ca_ops->min_tso_segs(sk) :
-			sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 
 	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2507,7 +2504,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
-			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
 	limit <<= factor;
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&