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

Pull networking fixes from David Miller:

 1) BPF verifier signed/unsigned value tracking fix, from Daniel
    Borkmann, Edward Cree, and Josef Bacik.

 2) Fix memory allocation length when setting up calls to
    ->ndo_set_mac_address, from Cong Wang.

 3) Add a new cxgb4 device ID, from Ganesh Goudar.

 4) Fix FIB refcount handling, we have to set it's initial value before
    the configure callback (which can bump it). From David Ahern.

 5) Fix double-free in qcom/emac driver, from Timur Tabi.

 6) A bunch of gcc-7 string format overflow warning fixes from Arnd
    Bergmann.

 7) Fix link level headroom tests in ip_do_fragment(), from Vasily
    Averin.

 8) Fix chunk walking in SCTP when iterating over error and parameter
    headers. From Alexander Potapenko.

 9) TCP BBR congestion control fixes from Neal Cardwell.

10) Fix SKB fragment handling in bcmgenet driver, from Doug Berger.

11) BPF_CGROUP_RUN_PROG_SOCK_OPS needs to check for null __sk, from Cong
    Wang.

12) xmit_recursion in ppp driver needs to be per-device not per-cpu,
    from Gao Feng.

13) Cannot release skb->dst in UDP if IP options processing needs it.
    From Paolo Abeni.

14) Some netdev ioctl ifr_name[] NULL termination fixes. From Alexander
    Levin and myself.

15) Revert some rtnetlink notification changes that are causing
    regressions, from David Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
  net: bonding: Fix transmit load balancing in balance-alb mode
  rds: Make sure updates to cp_send_gen can be observed
  net: ethernet: ti: cpsw: Push the request_irq function to the end of probe
  ipv4: initialize fib_trie prior to register_netdev_notifier call.
  rtnetlink: allocate more memory for dev_set_mac_address()
  net: dsa: b53: Add missing ARL entries for BCM53125
  bpf: more tests for mixed signed and unsigned bounds checks
  bpf: add test for mixed signed and unsigned bounds checks
  bpf: fix up test cases with mixed signed/unsigned bounds
  bpf: allow to specify log level and reduce it for test_verifier
  bpf: fix mixed signed/unsigned derived min/max value bounds
  ipv6: avoid overflow of offset in ip6_find_1stfragopt
  net: tehuti: don't process data if it has not been copied from userspace
  Revert "rtnetlink: Do not generate notifications for CHANGEADDR event"
  net: dsa: mv88e6xxx: Enable CMODE config support for 6390X
  dt-binding: ptp: Add SoC compatibility strings for dte ptp clock
  NET: dwmac: Make dwmac reset unconditional
  net: Zero terminate ifr_name in dev_ifname().
  wireless: wext: terminate ifr name coming from userspace
  netfilter: fix netfilter_net_init() return
  ...

6 files changed, 60 insertions, 23 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4e678fa892dd..044d2a159a3c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1334,13 +1334,14 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
+	fib_trie_init();
 
 	register_pernet_subsys(&fib_net_ops);
+
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_trie_init();
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 7eb252dcecee..50c74cd890bc 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -599,6 +599,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	hlen = iph->ihl * 4;
 	mtu = mtu - hlen;	/* Size of data space */
 	IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;
+	ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
 
 	/* When frag_list is given, use it. First, check its validity:
 	 * some transformers could create wrong frag_list or break existing
@@ -614,14 +615,15 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		if (first_len - hlen > mtu ||
 		    ((first_len - hlen) & 7) ||
 		    ip_is_fragment(iph) ||
-		    skb_cloned(skb))
+		    skb_cloned(skb) ||
+		    skb_headroom(skb) < ll_rs)
 			goto slow_path;
 
 		skb_walk_frags(skb, frag) {
 			/* Correct geometry. */
 			if (frag->len > mtu ||
 			    ((frag->len & 7) && frag->next) ||
-			    skb_headroom(frag) < hlen)
+			    skb_headroom(frag) < hlen + ll_rs)
 				goto slow_path_clean;
 
 			/* Partially cloned skb? */
@@ -711,8 +713,6 @@ slow_path:
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;		/* Where to start from */
 
-	ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
-
 	/*
 	 *	Fragment the datagram.
 	 */
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index 805c8ddfe860..4bbc273b45e8 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -72,8 +72,7 @@ static const struct nf_chain_type filter_arp = {
 	.family		= NFPROTO_ARP,
 	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_ARP_IN) |
-			  (1 << NF_ARP_OUT) |
-			  (1 << NF_ARP_FORWARD),
+			  (1 << NF_ARP_OUT),
 };
 
 static int __init nf_tables_arp_init(void)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 0905cf04c2a4..03ad8778c395 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -335,6 +335,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	treq->ts_off		= 0;
+	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index dbcc9352a48f..69ee877574d0 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -112,7 +112,8 @@ struct bbr {
 		cwnd_gain:10,	/* current gain for setting cwnd */
 		full_bw_cnt:3,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
-		unused_b:6;
+		has_seen_rtt:1, /* have we seen an RTT sample yet? */
+		unused_b:5;
 	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
 	u32	full_bw;	/* recent bw, to estimate if pipe is full */
 };
@@ -211,6 +212,35 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 	return rate >> BW_SCALE;
 }
 
+/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */
+static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
+{
+	u64 rate = bw;
+
+	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
+	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
+	return rate;
+}
+
+/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
+static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u64 bw;
+	u32 rtt_us;
+
+	if (tp->srtt_us) {		/* any RTT sample yet? */
+		rtt_us = max(tp->srtt_us >> 3, 1U);
+		bbr->has_seen_rtt = 1;
+	} else {			 /* no RTT sample yet */
+		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
+	}
+	bw = (u64)tp->snd_cwnd * BW_UNIT;
+	do_div(bw, rtt_us);
+	sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -220,12 +250,13 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 rate = bw;
+	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
-	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
-	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
-	if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate)
+	if (unlikely(!bbr->has_seen_rtt && tp->srtt_us))
+		bbr_init_pacing_rate_from_rtt(sk);
+	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
 
@@ -798,7 +829,6 @@ static void bbr_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 bw;
 
 	bbr->prior_cwnd = 0;
 	bbr->tso_segs_goal = 0;	 /* default segs per skb until first ACK */
@@ -814,11 +844,8 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
-	bw = (u64)tp->snd_cwnd * BW_UNIT;
-	do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC);
-	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
-	bbr_set_pacing_rate(sk, bw, bbr_high_gain);
+	bbr->has_seen_rtt = 0;
+	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 25294d43e147..b057653ceca9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1388,6 +1388,11 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		unlock_sock_fast(sk, slow);
 	}
 
+	/* we cleared the head states previously only if the skb lacks any IP
+	 * options, see __udp_queue_rcv_skb().
+	 */
+	if (unlikely(IPCB(skb)->opt.optlen > 0))
+		skb_release_head_state(skb);
 	consume_stateless_skb(skb);
 }
 EXPORT_SYMBOL_GPL(skb_consume_udp);
@@ -1779,8 +1784,12 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id_once(sk, skb);
 	}
 
-	/* clear all pending head states while they are hot in the cache */
-	skb_release_head_state(skb);
+	/* At recvmsg() time we need skb->dst to process IP options-related
+	 * cmsg, elsewhere can we clear all pending head states while they are
+	 * hot in the cache
+	 */
+	if (likely(IPCB(skb)->opt.optlen == 0))
+		skb_release_head_state(skb);
 
 	rc = __udp_enqueue_schedule_skb(sk, skb);
 	if (rc < 0) {