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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 42 insertions, 5 deletions

diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 125fc1450b01..0b5a05bd82e3 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -39,7 +39,7 @@
  * nv_cong_dec_mult	Decrease cwnd by X% (30%) of congestion when detected
  * nv_ssthresh_factor	On congestion set ssthresh to this * <desired cwnd> / 8
  * nv_rtt_factor	RTT averaging factor
- * nv_loss_dec_factor	Decrease cwnd by this (50%) when losses occur
+ * nv_loss_dec_factor	Decrease cwnd to this (80%) when losses occur
  * nv_dec_eval_min_calls	Wait this many RTT measurements before dec cwnd
  * nv_inc_eval_min_calls	Wait this many RTT measurements before inc cwnd
  * nv_ssthresh_eval_min_calls	Wait this many RTT measurements before stopping
@@ -61,7 +61,7 @@ static int nv_min_cwnd __read_mostly = 2;
 static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */
 static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */
 static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */
-static int nv_loss_dec_factor __read_mostly = 512; /* => 50% */
+static int nv_loss_dec_factor __read_mostly = 819; /* => 80% */
 static int nv_cwnd_growth_rate_neg __read_mostly = 8;
 static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */
 static int nv_dec_eval_min_calls __read_mostly = 60;
@@ -101,6 +101,11 @@ struct tcpnv {
 	u32 nv_last_rtt;	/* last rtt */
 	u32 nv_min_rtt;		/* active min rtt. Used to determine slope */
 	u32 nv_min_rtt_new;	/* min rtt for future use */
+	u32 nv_base_rtt;        /* If non-zero it represents the threshold for
+				 * congestion */
+	u32 nv_lower_bound_rtt; /* Used in conjunction with nv_base_rtt. It is
+				 * set to 80% of nv_base_rtt. It helps reduce
+				 * unfairness between flows */
 	u32 nv_rtt_max_rate;	/* max rate seen during current RTT */
 	u32 nv_rtt_start_seq;	/* current RTT ends when packet arrives
 				 * acking beyond nv_rtt_start_seq */
@@ -132,9 +137,24 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
 static void tcpnv_init(struct sock *sk)
 {
 	struct tcpnv *ca = inet_csk_ca(sk);
+	int base_rtt;
 
 	tcpnv_reset(ca, sk);
 
+	/* See if base_rtt is available from socket_ops bpf program.
+	 * It is meant to be used in environments, such as communication
+	 * within a datacenter, where we have reasonable estimates of
+	 * RTTs
+	 */
+	base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+	if (base_rtt > 0) {
+		ca->nv_base_rtt = base_rtt;
+		ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
+	} else {
+		ca->nv_base_rtt = 0;
+		ca->nv_lower_bound_rtt = 0;
+	}
+
 	ca->nv_allow_cwnd_growth = 1;
 	ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ;
 	ca->nv_min_rtt = NV_INIT_RTT;
@@ -144,6 +164,19 @@ static void tcpnv_init(struct sock *sk)
 	ca->cwnd_growth_factor = 0;
 }
 
+/* If provided, apply upper (base_rtt) and lower (lower_bound_rtt)
+ * bounds to RTT.
+ */
+inline u32 nv_get_bounded_rtt(struct tcpnv *ca, u32 val)
+{
+	if (ca->nv_lower_bound_rtt > 0 && val < ca->nv_lower_bound_rtt)
+		return ca->nv_lower_bound_rtt;
+	else if (ca->nv_base_rtt > 0 && val > ca->nv_base_rtt)
+		return ca->nv_base_rtt;
+	else
+		return val;
+}
+
 static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -209,7 +242,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcpnv *ca = inet_csk_ca(sk);
 	unsigned long now = jiffies;
-	s64 rate64 = 0;
+	u64 rate64;
 	u32 rate, max_win, cwnd_by_slope;
 	u32 avg_rtt;
 	u32 bytes_acked = 0;
@@ -251,8 +284,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	}
 
 	/* rate in 100's bits per second */
-	rate64 = ((u64)sample->in_flight) * 8000000;
-	rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100);
+	rate64 = ((u64)sample->in_flight) * 80000;
+	do_div(rate64, avg_rtt ?: 1);
+	rate = (u32)rate64;
 
 	/* Remember the maximum rate seen during this RTT
 	 * Note: It may be more than one RTT. This function should be
@@ -265,6 +299,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 	if (ca->nv_eval_call_cnt < 255)
 		ca->nv_eval_call_cnt++;
 
+	/* Apply bounds to rtt. Only used to update min_rtt */
+	avg_rtt = nv_get_bounded_rtt(ca, avg_rtt);
+
 	/* update min rtt if necessary */
 	if (avg_rtt < ca->nv_min_rtt)
 		ca->nv_min_rtt = avg_rtt;