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

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

1 files changed, 159 insertions, 21 deletions

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 0f497fc49c3f..56be7d27f208 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -115,6 +115,14 @@ struct bbr {
 		unused_b:5;
 	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
 	u32	full_bw;	/* recent bw, to estimate if pipe is full */
+
+	/* For tracking ACK aggregation: */
+	u64	ack_epoch_mstamp;	/* start of ACK sampling epoch */
+	u16	extra_acked[2];		/* max excess data ACKed in epoch */
+	u32	ack_epoch_acked:20,	/* packets (S)ACKed in sampling epoch */
+		extra_acked_win_rtts:5,	/* age of extra_acked, in round trips */
+		extra_acked_win_idx:1,	/* current index in extra_acked array */
+		unused_c:6;
 };
 
 #define CYCLE_LEN	8	/* number of phases in a pacing gain cycle */
@@ -182,6 +190,15 @@ static const u32 bbr_lt_bw_diff = 4000 / 8;
 /* If we estimate we're policed, use lt_bw for this many round trips: */
 static const u32 bbr_lt_bw_max_rtts = 48;
 
+/* Gain factor for adding extra_acked to target cwnd: */
+static const int bbr_extra_acked_gain = BBR_UNIT;
+/* Window length of extra_acked window. */
+static const u32 bbr_extra_acked_win_rtts = 5;
+/* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */
+static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20;
+/* Time period for clamping cwnd increment due to ack aggregation */
+static const u32 bbr_extra_acked_max_us = 100 * 1000;
+
 static void bbr_check_probe_rtt_done(struct sock *sk);
 
 /* Do we estimate that STARTUP filled the pipe? */
@@ -208,6 +225,16 @@ static u32 bbr_bw(const struct sock *sk)
 	return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk);
 }
 
+/* Return maximum extra acked in past k-2k round trips,
+ * where k = bbr_extra_acked_win_rtts.
+ */
+static u16 bbr_extra_acked(const struct sock *sk)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	return max(bbr->extra_acked[0], bbr->extra_acked[1]);
+}
+
 /* Return rate in bytes per second, optionally with a gain.
  * The order here is chosen carefully to avoid overflow of u64. This should
  * work for input rates of up to 2.9Tbit/sec and gain of 2.89x.
@@ -305,6 +332,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 
 	if (event == CA_EVENT_TX_START && tp->app_limited) {
 		bbr->idle_restart = 1;
+		bbr->ack_epoch_mstamp = tp->tcp_mstamp;
+		bbr->ack_epoch_acked = 0;
 		/* Avoid pointless buffer overflows: pace at est. bw if we don't
 		 * need more speed (we're restarting from idle and app-limited).
 		 */
@@ -315,30 +344,19 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 	}
 }
 
-/* Find target cwnd. Right-size the cwnd based on min RTT and the
- * estimated bottleneck bandwidth:
+/* Calculate bdp based on min RTT and the estimated bottleneck bandwidth:
  *
- * cwnd = bw * min_rtt * gain = BDP * gain
+ * bdp = bw * min_rtt * gain
  *
  * The key factor, gain, controls the amount of queue. While a small gain
  * builds a smaller queue, it becomes more vulnerable to noise in RTT
  * measurements (e.g., delayed ACKs or other ACK compression effects). This
  * noise may cause BBR to under-estimate the rate.
- *
- * To achieve full performance in high-speed paths, we budget enough cwnd to
- * fit full-sized skbs in-flight on both end hosts to fully utilize the path:
- *   - one skb in sending host Qdisc,
- *   - one skb in sending host TSO/GSO engine
- *   - one skb being received by receiver host LRO/GRO/delayed-ACK engine
- * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because
- * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets,
- * which allows 2 outstanding 2-packet sequences, to try to keep pipe
- * full even with ACK-every-other-packet delayed ACKs.
  */
-static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
+static u32 bbr_bdp(struct sock *sk, u32 bw, int gain)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
-	u32 cwnd;
+	u32 bdp;
 	u64 w;
 
 	/* If we've never had a valid RTT sample, cap cwnd at the initial
@@ -353,7 +371,24 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
 	w = (u64)bw * bbr->min_rtt_us;
 
 	/* Apply a gain to the given value, then remove the BW_SCALE shift. */
-	cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT;
+	bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT;
+
+	return bdp;
+}
+
+/* To achieve full performance in high-speed paths, we budget enough cwnd to
+ * fit full-sized skbs in-flight on both end hosts to fully utilize the path:
+ *   - one skb in sending host Qdisc,
+ *   - one skb in sending host TSO/GSO engine
+ *   - one skb being received by receiver host LRO/GRO/delayed-ACK engine
+ * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because
+ * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets,
+ * 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)
+{
+	struct bbr *bbr = inet_csk_ca(sk);
 
 	/* Allow enough full-sized skbs in flight to utilize end systems. */
 	cwnd += 3 * bbr_tso_segs_goal(sk);
@@ -368,6 +403,17 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
 	return cwnd;
 }
 
+/* Find inflight based on min RTT and the estimated bottleneck bandwidth. */
+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);
+
+	return inflight;
+}
+
 /* With pacing at lower layers, there's often less data "in the network" than
  * "in flight". With TSQ and departure time pacing at lower layers (e.g. fq),
  * we often have several skbs queued in the pacing layer with a pre-scheduled
@@ -401,6 +447,22 @@ static u32 bbr_packets_in_net_at_edt(struct sock *sk, u32 inflight_now)
 	return inflight_at_edt - interval_delivered;
 }
 
+/* Find the cwnd increment based on estimate of ack aggregation */
+static u32 bbr_ack_aggregation_cwnd(struct sock *sk)
+{
+	u32 max_aggr_cwnd, aggr_cwnd = 0;
+
+	if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) {
+		max_aggr_cwnd = ((u64)bbr_bw(sk) * bbr_extra_acked_max_us)
+				/ BW_UNIT;
+		aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk))
+			     >> BBR_SCALE;
+		aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd);
+	}
+
+	return aggr_cwnd;
+}
+
 /* An optimization in BBR to reduce losses: On the first round of recovery, we
  * follow the packet conservation principle: send P packets per P packets acked.
  * After that, we slow-start and send at most 2*P packets per P packets acked.
@@ -461,8 +523,15 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs,
 	if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd))
 		goto done;
 
+	target_cwnd = bbr_bdp(sk, bw, gain);
+
+	/* Increment the cwnd to account for excess ACKed data that seems
+	 * 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);
+
 	/* If we're below target cwnd, slow start cwnd toward target cwnd. */
-	target_cwnd = bbr_target_cwnd(sk, bw, gain);
 	if (bbr_full_bw_reached(sk))  /* only cut cwnd if we filled the pipe */
 		cwnd = min(cwnd + acked, target_cwnd);
 	else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND)
@@ -503,14 +572,14 @@ static bool bbr_is_next_cycle_phase(struct sock *sk,
 	if (bbr->pacing_gain > BBR_UNIT)
 		return is_full_length &&
 			(rs->losses ||  /* perhaps pacing_gain*BDP won't fit */
-			 inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain));
+			 inflight >= bbr_inflight(sk, bw, bbr->pacing_gain));
 
 	/* A pacing_gain < 1.0 tries to drain extra queue we added if bw
 	 * probing didn't find more bw. If inflight falls to match BDP then we
 	 * estimate queue is drained; persisting would underutilize the pipe.
 	 */
 	return is_full_length ||
-		inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT);
+		inflight <= bbr_inflight(sk, bw, BBR_UNIT);
 }
 
 static void bbr_advance_cycle_phase(struct sock *sk)
@@ -727,6 +796,67 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
 	}
 }
 
+/* Estimates the windowed max degree of ack aggregation.
+ * This is used to provision extra in-flight data to keep sending during
+ * inter-ACK silences.
+ *
+ * Degree of ack aggregation is estimated as extra data acked beyond expected.
+ *
+ * max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval"
+ * cwnd += max_extra_acked
+ *
+ * Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms).
+ * Max filter is an approximate sliding window of 5-10 (packet timed) round
+ * trips.
+ */
+static void bbr_update_ack_aggregation(struct sock *sk,
+				       const struct rate_sample *rs)
+{
+	u32 epoch_us, expected_acked, extra_acked;
+	struct bbr *bbr = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 ||
+	    rs->delivered < 0 || rs->interval_us <= 0)
+		return;
+
+	if (bbr->round_start) {
+		bbr->extra_acked_win_rtts = min(0x1F,
+						bbr->extra_acked_win_rtts + 1);
+		if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) {
+			bbr->extra_acked_win_rtts = 0;
+			bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ?
+						   0 : 1;
+			bbr->extra_acked[bbr->extra_acked_win_idx] = 0;
+		}
+	}
+
+	/* Compute how many packets we expected to be delivered over epoch. */
+	epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp,
+				      bbr->ack_epoch_mstamp);
+	expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT;
+
+	/* Reset the aggregation epoch if ACK rate is below expected rate or
+	 * significantly large no. of ack received since epoch (potentially
+	 * quite old epoch).
+	 */
+	if (bbr->ack_epoch_acked <= expected_acked ||
+	    (bbr->ack_epoch_acked + rs->acked_sacked >=
+	     bbr_ack_epoch_acked_reset_thresh)) {
+		bbr->ack_epoch_acked = 0;
+		bbr->ack_epoch_mstamp = tp->delivered_mstamp;
+		expected_acked = 0;
+	}
+
+	/* Compute excess data delivered, beyond what was expected. */
+	bbr->ack_epoch_acked = min_t(u32, 0xFFFFF,
+				     bbr->ack_epoch_acked + rs->acked_sacked);
+	extra_acked = bbr->ack_epoch_acked - expected_acked;
+	extra_acked = min(extra_acked, tp->snd_cwnd);
+	if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx])
+		bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked;
+}
+
 /* Estimate when the pipe is full, using the change in delivery rate: BBR
  * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by
  * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited
@@ -762,11 +892,11 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs)
 	if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) {
 		bbr->mode = BBR_DRAIN;	/* drain queue we created */
 		tcp_sk(sk)->snd_ssthresh =
-				bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT);
+				bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT);
 	}	/* fall through to check if in-flight is already small: */
 	if (bbr->mode == BBR_DRAIN &&
 	    bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <=
-	    bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT))
+	    bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT))
 		bbr_reset_probe_bw_mode(sk);  /* we estimate queue is drained */
 }
 
@@ -881,6 +1011,7 @@ static void bbr_update_gains(struct sock *sk)
 static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
 {
 	bbr_update_bw(sk, rs);
+	bbr_update_ack_aggregation(sk, rs);
 	bbr_update_cycle_phase(sk, rs);
 	bbr_check_full_bw_reached(sk, rs);
 	bbr_check_drain(sk, rs);
@@ -932,6 +1063,13 @@ static void bbr_init(struct sock *sk)
 	bbr_reset_lt_bw_sampling(sk);
 	bbr_reset_startup_mode(sk);
 
+	bbr->ack_epoch_mstamp = tp->tcp_mstamp;
+	bbr->ack_epoch_acked = 0;
+	bbr->extra_acked_win_rtts = 0;
+	bbr->extra_acked_win_idx = 0;
+	bbr->extra_acked[0] = 0;
+	bbr->extra_acked[1] = 0;
+
 	cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED);
 }