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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 50 insertions, 8 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index cd3ecda9386a..d196901c9dba 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -36,6 +36,7 @@
 #include <net/inet_hashtables.h>
 #include <net/checksum.h>
 #include <net/request_sock.h>
+#include <net/sock_reuseport.h>
 #include <net/sock.h>
 #include <net/snmp.h>
 #include <net/ip.h>
@@ -473,19 +474,45 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
  */
 static inline void tcp_synq_overflow(const struct sock *sk)
 {
-	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	unsigned long now = jiffies;
+	unsigned int last_overflow;
+	unsigned int now = jiffies;
 
-	if (time_after(now, last_overflow + HZ))
+	if (sk->sk_reuseport) {
+		struct sock_reuseport *reuse;
+
+		reuse = rcu_dereference(sk->sk_reuseport_cb);
+		if (likely(reuse)) {
+			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
+			if (time_after32(now, last_overflow + HZ))
+				WRITE_ONCE(reuse->synq_overflow_ts, now);
+			return;
+		}
+	}
+
+	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	if (time_after32(now, last_overflow + HZ))
 		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
 }
 
 /* syncookies: no recent synqueue overflow on this listening socket? */
 static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 {
-	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int last_overflow;
+	unsigned int now = jiffies;
+
+	if (sk->sk_reuseport) {
+		struct sock_reuseport *reuse;
+
+		reuse = rcu_dereference(sk->sk_reuseport_cb);
+		if (likely(reuse)) {
+			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
+			return time_after32(now, last_overflow +
+					    TCP_SYNCOOKIE_VALID);
+		}
+	}
 
-	return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID);
+	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
 static inline u32 tcp_cookie_time(void)
@@ -963,6 +990,8 @@ struct rate_sample {
 	u32  prior_delivered;	/* tp->delivered at "prior_mstamp" */
 	s32  delivered;		/* number of packets delivered over interval */
 	long interval_us;	/* time for tp->delivered to incr "delivered" */
+	u32 snd_interval_us;	/* snd interval for delivered packets */
+	u32 rcv_interval_us;	/* rcv interval for delivered packets */
 	long rtt_us;		/* RTT of last (S)ACKed packet (or -1) */
 	int  losses;		/* number of packets marked lost upon ACK */
 	u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */
@@ -1194,6 +1223,17 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	return tp->is_cwnd_limited;
 }
 
+/* BBR congestion control needs pacing.
+ * Same remark for SO_MAX_PACING_RATE.
+ * sch_fq packet scheduler is efficiently handling pacing,
+ * but is not always installed/used.
+ * Return true if TCP stack should pace packets itself.
+ */
+static inline bool tcp_needs_internal_pacing(const struct sock *sk)
+{
+	return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
+}
+
 /* Something is really bad, we could not queue an additional packet,
  * because qdisc is full or receiver sent a 0 window.
  * We do not want to add fuel to the fire, or abort too early,
@@ -1371,7 +1411,8 @@ static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt,
 {
 	if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
 		return true;
-	if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))
+	if (unlikely(!time_before32(ktime_get_seconds(),
+				    rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)))
 		return true;
 	/*
 	 * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0,
@@ -1401,7 +1442,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
 
 	   However, we can relax time bounds for RST segments to MSL.
 	 */
-	if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
+	if (rst && !time_before32(ktime_get_seconds(),
+				  rx_opt->ts_recent_stamp + TCP_PAWS_MSL))
 		return false;
 	return true;
 }
@@ -1787,7 +1829,7 @@ void tcp_v4_destroy_sock(struct sock *sk);
 
 struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features);
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
 int tcp_gro_complete(struct sk_buff *skb);
 
 void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);