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

Pull networking updates from David Miller:

 1) Add WireGuard

 2) Add HE and TWT support to ath11k driver, from John Crispin.

 3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.

 4) Add variable window congestion control to TIPC, from Jon Maloy.

 5) Add BCM84881 PHY driver, from Russell King.

 6) Start adding netlink support for ethtool operations, from Michal
    Kubecek.

 7) Add XDP drop and TX action support to ena driver, from Sameeh
    Jubran.

 8) Add new ipv4 route notifications so that mlxsw driver does not have
    to handle identical routes itself. From Ido Schimmel.

 9) Add BPF dynamic program extensions, from Alexei Starovoitov.

10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.

11) Add support for macsec HW offloading, from Antoine Tenart.

12) Add initial support for MPTCP protocol, from Christoph Paasch,
    Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.

13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
    Cherian, and others.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
  net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
  udp: segment looped gso packets correctly
  netem: change mailing list
  qed: FW 8.42.2.0 debug features
  qed: rt init valid initialization changed
  qed: Debug feature: ilt and mdump
  qed: FW 8.42.2.0 Add fw overlay feature
  qed: FW 8.42.2.0 HSI changes
  qed: FW 8.42.2.0 iscsi/fcoe changes
  qed: Add abstraction for different hsi values per chip
  qed: FW 8.42.2.0 Additional ll2 type
  qed: Use dmae to write to widebus registers in fw_funcs
  qed: FW 8.42.2.0 Parser offsets modified
  qed: FW 8.42.2.0 Queue Manager changes
  qed: FW 8.42.2.0 Expose new registers and change windows
  qed: FW 8.42.2.0 Internal ram offsets modifications
  MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
  Documentation: net: octeontx2: Add RVU HW and drivers overview
  octeontx2-pf: ethtool RSS config support
  octeontx2-pf: Add basic ethtool support
  ...

1 files changed, 54 insertions, 29 deletions

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 1b3d032a4df2..8f8eefd3a3ce 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -40,8 +40,8 @@
 
 /* Number of delay samples for detecting the increase of delay */
 #define HYSTART_MIN_SAMPLES	8
-#define HYSTART_DELAY_MIN	(4U<<3)
-#define HYSTART_DELAY_MAX	(16U<<3)
+#define HYSTART_DELAY_MIN	(4000U)	/* 4 ms */
+#define HYSTART_DELAY_MAX	(16000U)	/* 16 ms */
 #define HYSTART_DELAY_THRESH(x)	clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
 
 static int fast_convergence __read_mostly = 1;
@@ -53,7 +53,7 @@ static int tcp_friendliness __read_mostly = 1;
 static int hystart __read_mostly = 1;
 static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY;
 static int hystart_low_window __read_mostly = 16;
-static int hystart_ack_delta __read_mostly = 2;
+static int hystart_ack_delta_us __read_mostly = 2000;
 
 static u32 cube_rtt_scale __read_mostly;
 static u32 beta_scale __read_mostly;
@@ -77,8 +77,8 @@ MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms"
 		 " 1: packet-train 2: delay 3: both packet-train and delay");
 module_param(hystart_low_window, int, 0644);
 MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start");
-module_param(hystart_ack_delta, int, 0644);
-MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)");
+module_param(hystart_ack_delta_us, int, 0644);
+MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)");
 
 /* BIC TCP Parameters */
 struct bictcp {
@@ -89,7 +89,7 @@ struct bictcp {
 	u32	bic_origin_point;/* origin point of bic function */
 	u32	bic_K;		/* time to origin point
 				   from the beginning of the current epoch */
-	u32	delay_min;	/* min delay (msec << 3) */
+	u32	delay_min;	/* min delay (usec) */
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
@@ -117,13 +117,9 @@ static inline void bictcp_reset(struct bictcp *ca)
 	ca->found = 0;
 }
 
-static inline u32 bictcp_clock(void)
+static inline u32 bictcp_clock_us(const struct sock *sk)
 {
-#if HZ < 1000
-	return ktime_to_ms(ktime_get_real());
-#else
-	return jiffies_to_msecs(jiffies);
-#endif
+	return tcp_sk(sk)->tcp_mstamp;
 }
 
 static inline void bictcp_hystart_reset(struct sock *sk)
@@ -131,9 +127,9 @@ static inline void bictcp_hystart_reset(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	ca->round_start = ca->last_ack = bictcp_clock();
+	ca->round_start = ca->last_ack = bictcp_clock_us(sk);
 	ca->end_seq = tp->snd_nxt;
-	ca->curr_rtt = 0;
+	ca->curr_rtt = ~0U;
 	ca->sample_cnt = 0;
 }
 
@@ -276,7 +272,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
 	 */
 
 	t = (s32)(tcp_jiffies32 - ca->epoch_start);
-	t += msecs_to_jiffies(ca->delay_min >> 3);
+	t += usecs_to_jiffies(ca->delay_min);
 	/* change the unit from HZ to bictcp_HZ */
 	t <<= BICTCP_HZ;
 	do_div(t, HZ);
@@ -376,22 +372,54 @@ static void bictcp_state(struct sock *sk, u8 new_state)
 	}
 }
 
+/* Account for TSO/GRO delays.
+ * Otherwise short RTT flows could get too small ssthresh, since during
+ * slow start we begin with small TSO packets and ca->delay_min would
+ * not account for long aggregation delay when TSO packets get bigger.
+ * Ideally even with a very small RTT we would like to have at least one
+ * TSO packet being sent and received by GRO, and another one in qdisc layer.
+ * We apply another 100% factor because @rate is doubled at this point.
+ * We cap the cushion to 1ms.
+ */
+static u32 hystart_ack_delay(struct sock *sk)
+{
+	unsigned long rate;
+
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	if (!rate)
+		return 0;
+	return min_t(u64, USEC_PER_MSEC,
+		     div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
+}
+
 static void hystart_update(struct sock *sk, u32 delay)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
-
-	if (ca->found & hystart_detect)
-		return;
+	u32 threshold;
 
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
-		u32 now = bictcp_clock();
+		u32 now = bictcp_clock_us(sk);
 
 		/* first detection parameter - ack-train detection */
-		if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
+		if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) {
 			ca->last_ack = now;
-			if ((s32)(now - ca->round_start) > ca->delay_min >> 4) {
-				ca->found |= HYSTART_ACK_TRAIN;
+
+			threshold = ca->delay_min + hystart_ack_delay(sk);
+
+			/* Hystart ack train triggers if we get ack past
+			 * ca->delay_min/2.
+			 * Pacing might have delayed packets up to RTT/2
+			 * during slow start.
+			 */
+			if (sk->sk_pacing_status == SK_PACING_NONE)
+				threshold >>= 1;
+
+			if ((s32)(now - ca->round_start) > threshold) {
+				ca->found = 1;
+				pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n",
+					 now - ca->round_start, threshold,
+					 ca->delay_min, hystart_ack_delay(sk), tp->snd_cwnd);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTTRAINDETECT);
 				NET_ADD_STATS(sock_net(sk),
@@ -405,14 +433,14 @@ static void hystart_update(struct sock *sk, u32 delay)
 	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
-			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
+			if (ca->curr_rtt > delay)
 				ca->curr_rtt = delay;
 
 			ca->sample_cnt++;
 		} else {
 			if (ca->curr_rtt > ca->delay_min +
 			    HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
-				ca->found |= HYSTART_DELAY;
+				ca->found = 1;
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTDELAYDETECT);
 				NET_ADD_STATS(sock_net(sk),
@@ -424,9 +452,6 @@ static void hystart_update(struct sock *sk, u32 delay)
 	}
 }
 
-/* Track delayed acknowledgment ratio using sliding window
- * ratio = (15*ratio + sample) / 16
- */
 static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -441,7 +466,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
 	if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ)
 		return;
 
-	delay = (sample->rtt_us << 3) / USEC_PER_MSEC;
+	delay = sample->rtt_us;
 	if (delay == 0)
 		delay = 1;
 
@@ -450,7 +475,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
 		ca->delay_min = delay;
 
 	/* hystart triggers when cwnd is larger than some threshold */
-	if (hystart && tcp_in_slow_start(tp) &&
+	if (!ca->found && tcp_in_slow_start(tp) && hystart &&
 	    tp->snd_cwnd >= hystart_low_window)
 		hystart_update(sk, delay);
 }