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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 380 insertions, 0 deletions

diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h
new file mode 100644
index 0000000..bebeaad
--- /dev/null
+++ b/include/linux/net_dim.h
@@ -0,0 +1,380 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018, Broadcom Limited. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef NET_DIM_H
+#define NET_DIM_H
+
+#include <linux/module.h>
+
+struct net_dim_cq_moder {
+	u16 usec;
+	u16 pkts;
+	u8 cq_period_mode;
+};
+
+struct net_dim_sample {
+	ktime_t time;
+	u32     pkt_ctr;
+	u32     byte_ctr;
+	u16     event_ctr;
+};
+
+struct net_dim_stats {
+	int ppms; /* packets per msec */
+	int bpms; /* bytes per msec */
+	int epms; /* events per msec */
+};
+
+struct net_dim { /* Adaptive Moderation */
+	u8                                      state;
+	struct net_dim_stats                    prev_stats;
+	struct net_dim_sample                   start_sample;
+	struct work_struct                      work;
+	u8                                      profile_ix;
+	u8                                      mode;
+	u8                                      tune_state;
+	u8                                      steps_right;
+	u8                                      steps_left;
+	u8                                      tired;
+};
+
+enum {
+	NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0,
+	NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1,
+	NET_DIM_CQ_PERIOD_NUM_MODES
+};
+
+/* Adaptive moderation logic */
+enum {
+	NET_DIM_START_MEASURE,
+	NET_DIM_MEASURE_IN_PROGRESS,
+	NET_DIM_APPLY_NEW_PROFILE,
+};
+
+enum {
+	NET_DIM_PARKING_ON_TOP,
+	NET_DIM_PARKING_TIRED,
+	NET_DIM_GOING_RIGHT,
+	NET_DIM_GOING_LEFT,
+};
+
+enum {
+	NET_DIM_STATS_WORSE,
+	NET_DIM_STATS_SAME,
+	NET_DIM_STATS_BETTER,
+};
+
+enum {
+	NET_DIM_STEPPED,
+	NET_DIM_TOO_TIRED,
+	NET_DIM_ON_EDGE,
+};
+
+#define NET_DIM_PARAMS_NUM_PROFILES 5
+/* Adaptive moderation profiles */
+#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256
+#define NET_DIM_DEF_PROFILE_CQE 1
+#define NET_DIM_DEF_PROFILE_EQE 1
+
+/* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */
+#define NET_DIM_EQE_PROFILES { \
+	{1,   NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{8,   NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{64,  NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+	{256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+}
+
+#define NET_DIM_CQE_PROFILES { \
+	{2,  256},             \
+	{8,  128},             \
+	{16, 64},              \
+	{32, 64},              \
+	{64, 64}               \
+}
+
+static const struct net_dim_cq_moder
+profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+	NET_DIM_EQE_PROFILES,
+	NET_DIM_CQE_PROFILES,
+};
+
+static inline struct net_dim_cq_moder net_dim_get_profile(u8 cq_period_mode,
+							  int ix)
+{
+	struct net_dim_cq_moder cq_moder;
+
+	cq_moder = profile[cq_period_mode][ix];
+	cq_moder.cq_period_mode = cq_period_mode;
+	return cq_moder;
+}
+
+static inline struct net_dim_cq_moder net_dim_get_def_profile(u8 rx_cq_period_mode)
+{
+	int default_profile_ix;
+
+	if (rx_cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE)
+		default_profile_ix = NET_DIM_DEF_PROFILE_CQE;
+	else /* NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE */
+		default_profile_ix = NET_DIM_DEF_PROFILE_EQE;
+
+	return net_dim_get_profile(rx_cq_period_mode, default_profile_ix);
+}
+
+static inline bool net_dim_on_top(struct net_dim *dim)
+{
+	switch (dim->tune_state) {
+	case NET_DIM_PARKING_ON_TOP:
+	case NET_DIM_PARKING_TIRED:
+		return true;
+	case NET_DIM_GOING_RIGHT:
+		return (dim->steps_left > 1) && (dim->steps_right == 1);
+	default: /* NET_DIM_GOING_LEFT */
+		return (dim->steps_right > 1) && (dim->steps_left == 1);
+	}
+}
+
+static inline void net_dim_turn(struct net_dim *dim)
+{
+	switch (dim->tune_state) {
+	case NET_DIM_PARKING_ON_TOP:
+	case NET_DIM_PARKING_TIRED:
+		break;
+	case NET_DIM_GOING_RIGHT:
+		dim->tune_state = NET_DIM_GOING_LEFT;
+		dim->steps_left = 0;
+		break;
+	case NET_DIM_GOING_LEFT:
+		dim->tune_state = NET_DIM_GOING_RIGHT;
+		dim->steps_right = 0;
+		break;
+	}
+}
+
+static inline int net_dim_step(struct net_dim *dim)
+{
+	if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2))
+		return NET_DIM_TOO_TIRED;
+
+	switch (dim->tune_state) {
+	case NET_DIM_PARKING_ON_TOP:
+	case NET_DIM_PARKING_TIRED:
+		break;
+	case NET_DIM_GOING_RIGHT:
+		if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1))
+			return NET_DIM_ON_EDGE;
+		dim->profile_ix++;
+		dim->steps_right++;
+		break;
+	case NET_DIM_GOING_LEFT:
+		if (dim->profile_ix == 0)
+			return NET_DIM_ON_EDGE;
+		dim->profile_ix--;
+		dim->steps_left++;
+		break;
+	}
+
+	dim->tired++;
+	return NET_DIM_STEPPED;
+}
+
+static inline void net_dim_park_on_top(struct net_dim *dim)
+{
+	dim->steps_right  = 0;
+	dim->steps_left   = 0;
+	dim->tired        = 0;
+	dim->tune_state   = NET_DIM_PARKING_ON_TOP;
+}
+
+static inline void net_dim_park_tired(struct net_dim *dim)
+{
+	dim->steps_right  = 0;
+	dim->steps_left   = 0;
+	dim->tune_state   = NET_DIM_PARKING_TIRED;
+}
+
+static inline void net_dim_exit_parking(struct net_dim *dim)
+{
+	dim->tune_state = dim->profile_ix ? NET_DIM_GOING_LEFT :
+					  NET_DIM_GOING_RIGHT;
+	net_dim_step(dim);
+}
+
+#define IS_SIGNIFICANT_DIFF(val, ref) \
+	(((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
+
+static inline int net_dim_stats_compare(struct net_dim_stats *curr,
+					struct net_dim_stats *prev)
+{
+	if (!prev->bpms)
+		return curr->bpms ? NET_DIM_STATS_BETTER :
+				    NET_DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms))
+		return (curr->bpms > prev->bpms) ? NET_DIM_STATS_BETTER :
+						   NET_DIM_STATS_WORSE;
+
+	if (!prev->ppms)
+		return curr->ppms ? NET_DIM_STATS_BETTER :
+				    NET_DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
+		return (curr->ppms > prev->ppms) ? NET_DIM_STATS_BETTER :
+						   NET_DIM_STATS_WORSE;
+
+	if (!prev->epms)
+		return NET_DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
+		return (curr->epms < prev->epms) ? NET_DIM_STATS_BETTER :
+						   NET_DIM_STATS_WORSE;
+
+	return NET_DIM_STATS_SAME;
+}
+
+static inline bool net_dim_decision(struct net_dim_stats *curr_stats,
+				    struct net_dim *dim)
+{
+	int prev_state = dim->tune_state;
+	int prev_ix = dim->profile_ix;
+	int stats_res;
+	int step_res;
+
+	switch (dim->tune_state) {
+	case NET_DIM_PARKING_ON_TOP:
+		stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats);
+		if (stats_res != NET_DIM_STATS_SAME)
+			net_dim_exit_parking(dim);
+		break;
+
+	case NET_DIM_PARKING_TIRED:
+		dim->tired--;
+		if (!dim->tired)
+			net_dim_exit_parking(dim);
+		break;
+
+	case NET_DIM_GOING_RIGHT:
+	case NET_DIM_GOING_LEFT:
+		stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats);
+		if (stats_res != NET_DIM_STATS_BETTER)
+			net_dim_turn(dim);
+
+		if (net_dim_on_top(dim)) {
+			net_dim_park_on_top(dim);
+			break;
+		}
+
+		step_res = net_dim_step(dim);
+		switch (step_res) {
+		case NET_DIM_ON_EDGE:
+			net_dim_park_on_top(dim);
+			break;
+		case NET_DIM_TOO_TIRED:
+			net_dim_park_tired(dim);
+			break;
+		}
+
+		break;
+	}
+
+	if ((prev_state      != NET_DIM_PARKING_ON_TOP) ||
+	    (dim->tune_state != NET_DIM_PARKING_ON_TOP))
+		dim->prev_stats = *curr_stats;
+
+	return dim->profile_ix != prev_ix;
+}
+
+static inline void net_dim_sample(u16 event_ctr,
+				  u64 packets,
+				  u64 bytes,
+				  struct net_dim_sample *s)
+{
+	s->time	     = ktime_get();
+	s->pkt_ctr   = packets;
+	s->byte_ctr  = bytes;
+	s->event_ctr = event_ctr;
+}
+
+#define NET_DIM_NEVENTS 64
+#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
+#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1))
+
+static inline void net_dim_calc_stats(struct net_dim_sample *start,
+				      struct net_dim_sample *end,
+				      struct net_dim_stats *curr_stats)
+{
+	/* u32 holds up to 71 minutes, should be enough */
+	u32 delta_us = ktime_us_delta(end->time, start->time);
+	u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr);
+	u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr,
+			     start->byte_ctr);
+
+	if (!delta_us)
+		return;
+
+	curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
+	curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
+	curr_stats->epms = DIV_ROUND_UP(NET_DIM_NEVENTS * USEC_PER_MSEC,
+					delta_us);
+}
+
+static inline void net_dim(struct net_dim *dim,
+			   struct net_dim_sample end_sample)
+{
+	struct net_dim_stats curr_stats;
+	u16 nevents;
+
+	switch (dim->state) {
+	case NET_DIM_MEASURE_IN_PROGRESS:
+		nevents = BIT_GAP(BITS_PER_TYPE(u16),
+				  end_sample.event_ctr,
+				  dim->start_sample.event_ctr);
+		if (nevents < NET_DIM_NEVENTS)
+			break;
+		net_dim_calc_stats(&dim->start_sample, &end_sample,
+				   &curr_stats);
+		if (net_dim_decision(&curr_stats, dim)) {
+			dim->state = NET_DIM_APPLY_NEW_PROFILE;
+			schedule_work(&dim->work);
+			break;
+		}
+		/* fall through */
+	case NET_DIM_START_MEASURE:
+		dim->state = NET_DIM_MEASURE_IN_PROGRESS;
+		break;
+	case NET_DIM_APPLY_NEW_PROFILE:
+		break;
+	}
+}
+
+#endif /* NET_DIM_H */