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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 366 insertions, 0 deletions

diff --git a/include/linux/dim.h b/include/linux/dim.h
new file mode 100644
index 000000000000..aa9bdd47a648
--- /dev/null
+++ b/include/linux/dim.h
@@ -0,0 +1,366 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef DIM_H
+#define DIM_H
+
+#include <linux/module.h>
+
+/**
+ * Number of events between DIM iterations.
+ * Causes a moderation of the algorithm run.
+ */
+#define DIM_NEVENTS 64
+
+/**
+ * Is a difference between values justifies taking an action.
+ * We consider 10% difference as significant.
+ */
+#define IS_SIGNIFICANT_DIFF(val, ref) \
+	(((100UL * abs((val) - (ref))) / (ref)) > 10)
+
+/**
+ * Calculate the gap between two values.
+ * Take wrap-around and variable size into consideration.
+ */
+#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \
+		& (BIT_ULL(bits) - 1))
+
+/**
+ * Structure for CQ moderation values.
+ * Used for communications between DIM and its consumer.
+ *
+ * @usec: CQ timer suggestion (by DIM)
+ * @pkts: CQ packet counter suggestion (by DIM)
+ * @cq_period_mode: CQ priod count mode (from CQE/EQE)
+ */
+struct dim_cq_moder {
+	u16 usec;
+	u16 pkts;
+	u16 comps;
+	u8 cq_period_mode;
+};
+
+/**
+ * Structure for DIM sample data.
+ * Used for communications between DIM and its consumer.
+ *
+ * @time: Sample timestamp
+ * @pkt_ctr: Number of packets
+ * @byte_ctr: Number of bytes
+ * @event_ctr: Number of events
+ */
+struct dim_sample {
+	ktime_t time;
+	u32 pkt_ctr;
+	u32 byte_ctr;
+	u16 event_ctr;
+	u32 comp_ctr;
+};
+
+/**
+ * Structure for DIM stats.
+ * Used for holding current measured rates.
+ *
+ * @ppms: Packets per msec
+ * @bpms: Bytes per msec
+ * @epms: Events per msec
+ */
+struct dim_stats {
+	int ppms; /* packets per msec */
+	int bpms; /* bytes per msec */
+	int epms; /* events per msec */
+	int cpms; /* completions per msec */
+	int cpe_ratio; /* ratio of completions to events */
+};
+
+/**
+ * Main structure for dynamic interrupt moderation (DIM).
+ * Used for holding all information about a specific DIM instance.
+ *
+ * @state: Algorithm state (see below)
+ * @prev_stats: Measured rates from previous iteration (for comparison)
+ * @start_sample: Sampled data at start of current iteration
+ * @work: Work to perform on action required
+ * @profile_ix: Current moderation profile
+ * @mode: CQ period count mode
+ * @tune_state: Algorithm tuning state (see below)
+ * @steps_right: Number of steps taken towards higher moderation
+ * @steps_left: Number of steps taken towards lower moderation
+ * @tired: Parking depth counter
+ */
+struct dim {
+	u8 state;
+	struct dim_stats prev_stats;
+	struct dim_sample start_sample;
+	struct dim_sample measuring_sample;
+	struct work_struct work;
+	u8 profile_ix;
+	u8 mode;
+	u8 tune_state;
+	u8 steps_right;
+	u8 steps_left;
+	u8 tired;
+};
+
+/**
+ * enum dim_cq_period_mode
+ *
+ * These are the modes for CQ period count.
+ *
+ * @DIM_CQ_PERIOD_MODE_START_FROM_EQE: Start counting from EQE
+ * @DIM_CQ_PERIOD_MODE_START_FROM_CQE: Start counting from CQE (implies timer reset)
+ * @DIM_CQ_PERIOD_NUM_MODES: Number of modes
+ */
+enum {
+	DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0,
+	DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1,
+	DIM_CQ_PERIOD_NUM_MODES
+};
+
+/**
+ * enum dim_state
+ *
+ * These are the DIM algorithm states.
+ * These will determine if the algorithm is in a valid state to start an iteration.
+ *
+ * @DIM_START_MEASURE: This is the first iteration (also after applying a new profile)
+ * @DIM_MEASURE_IN_PROGRESS: Algorithm is already in progress - check if
+ * need to perform an action
+ * @DIM_APPLY_NEW_PROFILE: DIM consumer is currently applying a profile - no need to measure
+ */
+enum {
+	DIM_START_MEASURE,
+	DIM_MEASURE_IN_PROGRESS,
+	DIM_APPLY_NEW_PROFILE,
+};
+
+/**
+ * enum dim_tune_state
+ *
+ * These are the DIM algorithm tune states.
+ * These will determine which action the algorithm should perform.
+ *
+ * @DIM_PARKING_ON_TOP: Algorithm found a local top point - exit on significant difference
+ * @DIM_PARKING_TIRED: Algorithm found a deep top point - don't exit if tired > 0
+ * @DIM_GOING_RIGHT: Algorithm is currently trying higher moderation levels
+ * @DIM_GOING_LEFT: Algorithm is currently trying lower moderation levels
+ */
+enum {
+	DIM_PARKING_ON_TOP,
+	DIM_PARKING_TIRED,
+	DIM_GOING_RIGHT,
+	DIM_GOING_LEFT,
+};
+
+/**
+ * enum dim_stats_state
+ *
+ * These are the DIM algorithm statistics states.
+ * These will determine the verdict of current iteration.
+ *
+ * @DIM_STATS_WORSE: Current iteration shows worse performance than before
+ * @DIM_STATS_WORSE: Current iteration shows same performance than before
+ * @DIM_STATS_WORSE: Current iteration shows better performance than before
+ */
+enum {
+	DIM_STATS_WORSE,
+	DIM_STATS_SAME,
+	DIM_STATS_BETTER,
+};
+
+/**
+ * enum dim_step_result
+ *
+ * These are the DIM algorithm step results.
+ * These describe the result of a step.
+ *
+ * @DIM_STEPPED: Performed a regular step
+ * @DIM_TOO_TIRED: Same kind of step was done multiple times - should go to
+ * tired parking
+ * @DIM_ON_EDGE: Stepped to the most left/right profile
+ */
+enum {
+	DIM_STEPPED,
+	DIM_TOO_TIRED,
+	DIM_ON_EDGE,
+};
+
+/**
+ *	dim_on_top - check if current state is a good place to stop (top location)
+ *	@dim: DIM context
+ *
+ * Check if current profile is a good place to park at.
+ * This will result in reducing the DIM checks frequency as we assume we
+ * shouldn't probably change profiles, unless traffic pattern wasn't changed.
+ */
+bool dim_on_top(struct dim *dim);
+
+/**
+ *	dim_turn - change profile alterning direction
+ *	@dim: DIM context
+ *
+ * Go left if we were going right and vice-versa.
+ * Do nothing if currently parking.
+ */
+void dim_turn(struct dim *dim);
+
+/**
+ *	dim_park_on_top - enter a parking state on a top location
+ *	@dim: DIM context
+ *
+ * Enter parking state.
+ * Clear all movement history.
+ */
+void dim_park_on_top(struct dim *dim);
+
+/**
+ *	dim_park_tired - enter a tired parking state
+ *	@dim: DIM context
+ *
+ * Enter parking state.
+ * Clear all movement history and cause DIM checks frequency to reduce.
+ */
+void dim_park_tired(struct dim *dim);
+
+/**
+ *	dim_calc_stats - calculate the difference between two samples
+ *	@start: start sample
+ *	@end: end sample
+ *	@curr_stats: delta between samples
+ *
+ * Calculate the delta between two samples (in data rates).
+ * Takes into consideration counter wrap-around.
+ */
+void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+		    struct dim_stats *curr_stats);
+
+/**
+ *	dim_update_sample - set a sample's fields with give values
+ *	@event_ctr: number of events to set
+ *	@packets: number of packets to set
+ *	@bytes: number of bytes to set
+ *	@s: DIM sample
+ */
+static inline void
+dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s)
+{
+	s->time	     = ktime_get();
+	s->pkt_ctr   = packets;
+	s->byte_ctr  = bytes;
+	s->event_ctr = event_ctr;
+}
+
+/**
+ *	dim_update_sample_with_comps - set a sample's fields with given
+ *	values including the completion parameter
+ *	@event_ctr: number of events to set
+ *	@packets: number of packets to set
+ *	@bytes: number of bytes to set
+ *	@comps: number of completions to set
+ *	@s: DIM sample
+ */
+static inline void
+dim_update_sample_with_comps(u16 event_ctr, u64 packets, u64 bytes, u64 comps,
+			     struct dim_sample *s)
+{
+	dim_update_sample(event_ctr, packets, bytes, s);
+	s->comp_ctr = comps;
+}
+
+/* Net DIM */
+
+/*
+ * Net DIM profiles:
+ *        There are different set of profiles for each CQ period mode.
+ *        There are different set of profiles for RX/TX CQs.
+ *        Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES
+ */
+#define NET_DIM_PARAMS_NUM_PROFILES 5
+#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256
+#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128
+#define NET_DIM_DEF_PROFILE_CQE 1
+#define NET_DIM_DEF_PROFILE_EQE 1
+
+#define NET_DIM_RX_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_RX_CQE_PROFILES { \
+	{2,  256},             \
+	{8,  128},             \
+	{16, 64},              \
+	{32, 64},              \
+	{64, 64}               \
+}
+
+#define NET_DIM_TX_EQE_PROFILES { \
+	{1,   NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE},  \
+	{8,   NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE},  \
+	{32,  NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE},  \
+	{64,  NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE},  \
+	{128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}   \
+}
+
+#define NET_DIM_TX_CQE_PROFILES { \
+	{5,  128},  \
+	{8,  64},  \
+	{16, 32},  \
+	{32, 32},  \
+	{64, 32}   \
+}
+
+static const struct dim_cq_moder
+rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+	NET_DIM_RX_EQE_PROFILES,
+	NET_DIM_RX_CQE_PROFILES,
+};
+
+static const struct dim_cq_moder
+tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+	NET_DIM_TX_EQE_PROFILES,
+	NET_DIM_TX_CQE_PROFILES,
+};
+
+/**
+ *	net_dim_get_rx_moderation - provide a CQ moderation object for the given RX profile
+ *	@cq_period_mode: CQ period mode
+ *	@ix: Profile index
+ */
+struct dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix);
+
+/**
+ *	net_dim_get_def_rx_moderation - provide the default RX moderation
+ *	@cq_period_mode: CQ period mode
+ */
+struct dim_cq_moder net_dim_get_def_rx_moderation(u8 cq_period_mode);
+
+/**
+ *	net_dim_get_tx_moderation - provide a CQ moderation object for the given TX profile
+ *	@cq_period_mode: CQ period mode
+ *	@ix: Profile index
+ */
+struct dim_cq_moder net_dim_get_tx_moderation(u8 cq_period_mode, int ix);
+
+/**
+ *	net_dim_get_def_tx_moderation - provide the default TX moderation
+ *	@cq_period_mode: CQ period mode
+ */
+struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode);
+
+/**
+ *	net_dim - main DIM algorithm entry point
+ *	@dim: DIM instance information
+ *	@end_sample: Current data measurement
+ *
+ * Called by the consumer.
+ * This is the main logic of the algorithm, where data is processed in order to decide on next
+ * required action.
+ */
+void net_dim(struct dim *dim, struct dim_sample end_sample);
+
+#endif /* DIM_H */