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

Pull networking fixes from David Miller:

 1) Sanity check URB networking device parameters to avoid divide by
    zero, from Oliver Neukum.

 2) Disable global multicast filter in NCSI, otherwise LLDP and IPV6
    don't work properly. Longer term this needs a better fix tho. From
    Vijay Khemka.

 3) Small fixes to selftests (use ping when ping6 is not present, etc.)
    from David Ahern.

 4) Bring back rt_uses_gateway member of struct rtable, it's semantics
    were not well understood and trying to remove it broke things. From
    David Ahern.

 5) Move usbnet snaity checking, ignore endpoints with invalid
    wMaxPacketSize. From Bjørn Mork.

 6) Missing Kconfig deps for sja1105 driver, from Mao Wenan.

 7) Various small fixes to the mlx5 DR steering code, from Alaa Hleihel,
    Alex Vesker, and Yevgeny Kliteynik

 8) Missing CAP_NET_RAW checks in various places, from Ori Nimron.

 9) Fix crash when removing sch_cbs entry while offloading is enabled,
    from Vinicius Costa Gomes.

10) Signedness bug fixes, generally in looking at the result given by
    of_get_phy_mode() and friends. From Dan Crapenter.

11) Disable preemption around BPF_PROG_RUN() calls, from Eric Dumazet.

12) Don't create VRF ipv6 rules if ipv6 is disabled, from David Ahern.

13) Fix quantization code in tcp_bbr, from Kevin Yang.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (127 commits)
  net: tap: clean up an indentation issue
  nfp: abm: fix memory leak in nfp_abm_u32_knode_replace
  tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state
  sk_buff: drop all skb extensions on free and skb scrubbing
  tcp_bbr: fix quantization code to not raise cwnd if not probing bandwidth
  mlxsw: spectrum_flower: Fail in case user specifies multiple mirror actions
  Documentation: Clarify trap's description
  mlxsw: spectrum: Clear VLAN filters during port initialization
  net: ena: clean up indentation issue
  NFC: st95hf: clean up indentation issue
  net: phy: micrel: add Asym Pause workaround for KSZ9021
  net: socionext: ave: Avoid using netdev_err() before calling register_netdev()
  ptp: correctly disable flags on old ioctls
  lib: dimlib: fix help text typos
  net: dsa: microchip: Always set regmap stride to 1
  nfp: flower: fix memory leak in nfp_flower_spawn_vnic_reprs
  nfp: flower: prevent memory leak in nfp_flower_spawn_phy_reprs
  net/sched: Set default of CONFIG_NET_TC_SKB_EXT to N
  vrf: Do not attempt to create IPv6 mcast rule if IPv6 is disabled
  net: sched: sch_sfb: don't call qdisc_put() while holding tree lock
  ...

10 files changed, 40 insertions, 28 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 974de4d20f25..03381f3e12ba 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -492,8 +492,8 @@ config TCP_CONG_WESTWOOD
 	wired networks and throughput over wireless links.
 
 config TCP_CONG_HTCP
-        tristate "H-TCP"
-        default m
+	tristate "H-TCP"
+	default m
 	---help---
 	H-TCP is a send-side only modifications of the TCP Reno
 	protocol stack that optimizes the performance of TCP
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f5c163d4771b..a9183543ca30 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -560,7 +560,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	rcu_read_unlock();
 	return &rt->dst;
@@ -598,7 +598,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	return &rt->dst;
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 06f6f280b9ff..00ec819f949b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -123,7 +123,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && rt->rt_gw_family)
+	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
 	IPCB(skb)->flags |= IPSKB_FORWARDED;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5eb73775c3f7..28fca408812c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -499,7 +499,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
@@ -1694,7 +1694,6 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	inet_sk(sk)->tos = arg->tos;
 
-	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b6a6f18c3dd1..7dcce724c78b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -635,6 +635,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 
 	if (fnhe->fnhe_gw) {
 		rt->rt_flags |= RTCF_REDIRECTED;
+		rt->rt_uses_gateway = 1;
 		rt->rt_gw_family = AF_INET;
 		rt->rt_gw4 = fnhe->fnhe_gw;
 	}
@@ -1313,7 +1314,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
-		if (rt->rt_gw_family && mtu > 576)
+		if (rt->rt_uses_gateway && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1569,6 +1570,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
 
 		if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
+			rt->rt_uses_gateway = 1;
 			rt->rt_gw_family = nhc->nhc_gw_family;
 			/* only INET and INET6 are supported */
 			if (likely(nhc->nhc_gw_family == AF_INET))
@@ -1634,6 +1636,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_iif = 0;
 		rt->rt_pmtu = 0;
 		rt->rt_mtu_locked = 0;
+		rt->rt_uses_gateway = 0;
 		rt->rt_gw_family = 0;
 		rt->rt_gw4 = 0;
 		INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2694,6 +2697,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_genid = rt_genid_ipv4(net);
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
+		rt->rt_uses_gateway = ort->rt_uses_gateway;
 		rt->rt_gw_family = ort->rt_gw_family;
 		if (rt->rt_gw_family == AF_INET)
 			rt->rt_gw4 = ort->rt_gw4;
@@ -2778,21 +2782,23 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 		if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (rt->rt_gw_family == AF_INET &&
-	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
-		goto nla_put_failure;
-	} else if (rt->rt_gw_family == AF_INET6) {
-		int alen = sizeof(struct in6_addr);
-		struct nlattr *nla;
-		struct rtvia *via;
-
-		nla = nla_reserve(skb, RTA_VIA, alen + 2);
-		if (!nla)
+	if (rt->rt_uses_gateway) {
+		if (rt->rt_gw_family == AF_INET &&
+		    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
 			goto nla_put_failure;
-
-		via = nla_data(nla);
-		via->rtvia_family = AF_INET6;
-		memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+		} else if (rt->rt_gw_family == AF_INET6) {
+			int alen = sizeof(struct in6_addr);
+			struct nlattr *nla;
+			struct rtvia *via;
+
+			nla = nla_reserve(skb, RTA_VIA, alen + 2);
+			if (!nla)
+				goto nla_put_failure;
+
+			via = nla_data(nla);
+			via->rtvia_family = AF_INET6;
+			memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+		}
 	}
 
 	expires = rt->dst.expires;
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 95b59540eee1..32772d6ded4e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -388,7 +388,7 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain)
  * which allows 2 outstanding 2-packet sequences, to try to keep pipe
  * full even with ACK-every-other-packet delayed ACKs.
  */
-static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain)
+static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
@@ -399,7 +399,7 @@ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain)
 	cwnd = (cwnd + 1) & ~1U;
 
 	/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
-	if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+	if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0)
 		cwnd += 2;
 
 	return cwnd;
@@ -411,7 +411,7 @@ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain)
 	u32 inflight;
 
 	inflight = bbr_bdp(sk, bw, gain);
-	inflight = bbr_quantization_budget(sk, inflight, gain);
+	inflight = bbr_quantization_budget(sk, inflight);
 
 	return inflight;
 }
@@ -531,7 +531,7 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs,
 	 * due to aggregation (of data and/or ACKs) visible in the ACK stream.
 	 */
 	target_cwnd += bbr_ack_aggregation_cwnd(sk);
-	target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain);
+	target_cwnd = bbr_quantization_budget(sk, target_cwnd);
 
 	/* If we're below target cwnd, slow start cwnd toward target cwnd. */
 	if (bbr_full_bw_reached(sk))  /* only cut cwnd if we filled the pipe */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fd394ad179a0..2ee45e3755e9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -771,6 +771,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_mark : sk->sk_mark;
+		ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+				   inet_twsk(sk)->tw_priority : sk->sk_priority;
 		transmit_time = tcp_transmit_time(sk);
 	}
 	ip_send_unicast_reply(ctl_sk,
@@ -866,6 +868,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : sk->sk_mark;
+	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
+			   inet_twsk(sk)->tw_priority : sk->sk_priority;
 	transmit_time = tcp_transmit_time(sk);
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 8bcaf2586b68..bb140a5db8c0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -266,6 +266,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 
 		tw->tw_transparent	= inet->transparent;
 		tw->tw_mark		= sk->sk_mark;
+		tw->tw_priority		= sk->sk_priority;
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index dbd9d2d0ee63..40de2d2364a1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -210,7 +210,7 @@ static int tcp_write_timeout(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
-	bool expired, do_reset;
+	bool expired = false, do_reset;
 	int retry_until;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
@@ -242,9 +242,10 @@ static int tcp_write_timeout(struct sock *sk)
 			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
+	}
+	if (!expired)
 		expired = retransmits_timed_out(sk, retry_until,
 						icsk->icsk_user_timeout);
-	}
 	tcp_fastopen_active_detect_blackhole(sk, expired);
 
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index cdef8f9a3b01..35b84b52b702 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -85,6 +85,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
 					      RTCF_LOCAL);
 	xdst->u.rt.rt_type = rt->rt_type;
+	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
 	xdst->u.rt.rt_gw_family = rt->rt_gw_family;
 	if (rt->rt_gw_family == AF_INET)
 		xdst->u.rt.rt_gw4 = rt->rt_gw4;