[for-next 6/9] linux/dim: Move implementation to .c files

[Saeed Mahameed <saeedm@mellanox.com>]

From: Tal Gilboa <talgi@mellanox.com>

Moved all logic from dim.h and net_dim.h to dim.c and net_dim.c.
This is both more structurally appealing and would allow to only
expose externally used functions.

Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 MAINTAINERS                                   |   1 +
 drivers/net/ethernet/broadcom/Kconfig         |   1 +
 .../net/ethernet/mellanox/mlx5/core/Kconfig   |   1 +
 include/linux/dim.h                           | 238 ++++++++++++------
 include/linux/net_dim.h                       | 216 +++-------------
 lib/Kconfig                                   |   8 +
 lib/Makefile                                  |   1 +
 lib/dim/Makefile                              |   9 +
 lib/dim/dim.c                                 |  74 ++++++
 lib/dim/net_dim.c                             | 191 ++++++++++++++
 10 files changed, 491 insertions(+), 249 deletions(-)
 create mode 100644 lib/dim/Makefile
 create mode 100644 lib/dim/dim.c
 create mode 100644 lib/dim/net_dim.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 5d4b852d9d39..cb621d5cf223 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5590,6 +5590,7 @@ M:	Tal Gilboa <talgi@mellanox.com>
 S:	Maintained
 F:	include/linux/net_dim.h
 F:	include/linux/dim.h
+F:	lib/dim/
 
 DZ DECSTATION DZ11 SERIAL DRIVER
 M:	"Maciej W. Rozycki" <macro@linux-mips.org>
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index b123509d385f..2e4a8c7237ef 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -8,6 +8,7 @@ config NET_VENDOR_BROADCOM
 	default y
 	depends on (SSB_POSSIBLE && HAS_DMA) || PCI || BCM63XX || \
 		   SIBYTE_SB1xxx_SOC
+	select DIMLIB
 	---help---
 	  If you have a network (Ethernet) chipset belonging to this class,
 	  say Y.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 2391e3cfb56b..7845aa5bf6be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -34,6 +34,7 @@ config MLX5_CORE_EN
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	depends on IPV6=y || IPV6=n || MLX5_CORE=m
 	select PAGE_POOL
+	select DIMLIB
 	default n
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
diff --git a/include/linux/dim.h b/include/linux/dim.h
index 60e5074a7cc0..a6bf84f61dfb 100644
--- a/include/linux/dim.h
+++ b/include/linux/dim.h
@@ -6,20 +6,49 @@
 
 #include <linux/module.h>
 
+/**
+ * Number of events between DIM iterations.
+ * Causes a moderation of the algorithm run.
+ */
 #define DIM_NEVENTS 64
 
-/* more than 10% difference */
+/**
+ * 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)
-#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \
-& (BIT_ULL(bits) - 1))
 
+/**
+ * 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;
 	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;
@@ -27,13 +56,36 @@ struct dim_sample {
 	u16 event_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 ppms;
+	int bpms;
+	int epms;
 };
 
-struct dim { /* Dynamic Interrupt Moderation */
+/**
+ * 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;
@@ -46,18 +98,49 @@ struct dim { /* Dynamic Interrupt Moderation */
 	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,
@@ -65,63 +148,95 @@ enum {
 	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,
 };
 
-static inline bool dim_on_top(struct dim *dim)
-{
-	switch (dim->tune_state) {
-	case DIM_PARKING_ON_TOP:
-	case DIM_PARKING_TIRED:
-		return true;
-	case DIM_GOING_RIGHT:
-		return (dim->steps_left > 1) && (dim->steps_right == 1);
-	default: /* DIM_GOING_LEFT */
-		return (dim->steps_right > 1) && (dim->steps_left == 1);
-	}
-}
-
-static inline void dim_turn(struct dim *dim)
-{
-	switch (dim->tune_state) {
-	case DIM_PARKING_ON_TOP:
-	case DIM_PARKING_TIRED:
-		break;
-	case DIM_GOING_RIGHT:
-		dim->tune_state = DIM_GOING_LEFT;
-		dim->steps_left = 0;
-		break;
-	case DIM_GOING_LEFT:
-		dim->tune_state = DIM_GOING_RIGHT;
-		dim->steps_right = 0;
-		break;
-	}
-}
-
-static inline void dim_park_on_top(struct dim *dim)
-{
-	dim->steps_right  = 0;
-	dim->steps_left   = 0;
-	dim->tired        = 0;
-	dim->tune_state   = DIM_PARKING_ON_TOP;
-}
-
-static inline void dim_park_tired(struct dim *dim)
-{
-	dim->steps_right  = 0;
-	dim->steps_left   = 0;
-	dim->tune_state   = DIM_PARKING_TIRED;
-}
-
+/**
+ *	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)
 {
@@ -131,23 +246,4 @@ dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s)
 	s->event_ctr = event_ctr;
 }
 
-static inline void
-dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
-	       struct 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(DIM_NEVENTS * USEC_PER_MSEC,
-					delta_us);
-}
-
 #endif /* DIM_H */
diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h
index 4e009ec193ef..e3278cb8c392 100644
--- a/include/linux/net_dim.h
+++ b/include/linux/net_dim.h
@@ -37,14 +37,18 @@
 #include <linux/module.h>
 #include <linux/dim.h>
 
+/*
+ * 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
-/* Netdev dynamic interrupt moderation profiles */
 #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
 
-/* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */
 #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}, \
@@ -89,185 +93,41 @@ tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
 	NET_DIM_TX_CQE_PROFILES,
 };
 
-static inline struct dim_cq_moder
-net_dim_get_rx_moderation(u8 cq_period_mode, int ix)
-{
-	struct dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix];
-
-	cq_moder.cq_period_mode = cq_period_mode;
-	return cq_moder;
-}
-
-static inline struct dim_cq_moder
-net_dim_get_def_rx_moderation(u8 cq_period_mode)
-{
-	u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
-			NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
-
-	return net_dim_get_rx_moderation(cq_period_mode, profile_ix);
-}
-
-static inline struct dim_cq_moder
-net_dim_get_tx_moderation(u8 cq_period_mode, int ix)
-{
-	struct dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix];
-
-	cq_moder.cq_period_mode = cq_period_mode;
-	return cq_moder;
-}
-
-static inline struct dim_cq_moder
-net_dim_get_def_tx_moderation(u8 cq_period_mode)
-{
-	u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
-			NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
-
-	return net_dim_get_tx_moderation(cq_period_mode, profile_ix);
-}
-
-static inline int net_dim_step(struct dim *dim)
-{
-	if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2))
-		return DIM_TOO_TIRED;
-
-	switch (dim->tune_state) {
-	case DIM_PARKING_ON_TOP:
-	case DIM_PARKING_TIRED:
-		break;
-	case DIM_GOING_RIGHT:
-		if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1))
-			return DIM_ON_EDGE;
-		dim->profile_ix++;
-		dim->steps_right++;
-		break;
-	case DIM_GOING_LEFT:
-		if (dim->profile_ix == 0)
-			return DIM_ON_EDGE;
-		dim->profile_ix--;
-		dim->steps_left++;
-		break;
-	}
-
-	dim->tired++;
-	return DIM_STEPPED;
-}
-
-static inline void net_dim_exit_parking(struct dim *dim)
-{
-	dim->tune_state = dim->profile_ix ? DIM_GOING_LEFT :
-					  DIM_GOING_RIGHT;
-	net_dim_step(dim);
-}
-
-static inline int net_dim_stats_compare(struct dim_stats *curr,
-					struct dim_stats *prev)
-{
-	if (!prev->bpms)
-		return curr->bpms ? DIM_STATS_BETTER :
-				    DIM_STATS_SAME;
-
-	if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms))
-		return (curr->bpms > prev->bpms) ? DIM_STATS_BETTER :
-						   DIM_STATS_WORSE;
-
-	if (!prev->ppms)
-		return curr->ppms ? DIM_STATS_BETTER :
-				    DIM_STATS_SAME;
-
-	if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
-		return (curr->ppms > prev->ppms) ? DIM_STATS_BETTER :
-						   DIM_STATS_WORSE;
-
-	if (!prev->epms)
-		return DIM_STATS_SAME;
-
-	if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
-		return (curr->epms < prev->epms) ? DIM_STATS_BETTER :
-						   DIM_STATS_WORSE;
-
-	return DIM_STATS_SAME;
-}
-
-static inline bool net_dim_decision(struct dim_stats *curr_stats,
-				    struct 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 DIM_PARKING_ON_TOP:
-		stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats);
-		if (stats_res != DIM_STATS_SAME)
-			net_dim_exit_parking(dim);
-		break;
-
-	case DIM_PARKING_TIRED:
-		dim->tired--;
-		if (!dim->tired)
-			net_dim_exit_parking(dim);
-		break;
-
-	case DIM_GOING_RIGHT:
-	case DIM_GOING_LEFT:
-		stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats);
-		if (stats_res != DIM_STATS_BETTER)
-			dim_turn(dim);
-
-		if (dim_on_top(dim)) {
-			dim_park_on_top(dim);
-			break;
-		}
-
-		step_res = net_dim_step(dim);
-		switch (step_res) {
-		case DIM_ON_EDGE:
-			dim_park_on_top(dim);
-			break;
-		case DIM_TOO_TIRED:
-			dim_park_tired(dim);
-			break;
-		}
-
-		break;
-	}
+/**
+ *	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);
 
-	if (prev_state != DIM_PARKING_ON_TOP ||
-	    dim->tune_state != DIM_PARKING_ON_TOP)
-		dim->prev_stats = *curr_stats;
+/**
+ *	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);
 
-	return dim->profile_ix != prev_ix;
-}
+/**
+ *	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);
 
-static inline void net_dim(struct dim *dim,
-			   struct dim_sample end_sample)
-{
-	struct dim_stats curr_stats;
-	u16 nevents;
+/**
+ *	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);
 
-	switch (dim->state) {
-	case DIM_MEASURE_IN_PROGRESS:
-		nevents = BIT_GAP(BITS_PER_TYPE(u16),
-				  end_sample.event_ctr,
-				  dim->start_sample.event_ctr);
-		if (nevents < DIM_NEVENTS)
-			break;
-		dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats);
-		if (net_dim_decision(&curr_stats, dim)) {
-			dim->state = DIM_APPLY_NEW_PROFILE;
-			schedule_work(&dim->work);
-			break;
-		}
-		/* fall through */
-	case DIM_START_MEASURE:
-		dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr,
-				  end_sample.byte_ctr, &dim->start_sample);
-		dim->state = DIM_MEASURE_IN_PROGRESS;
-		break;
-	case DIM_APPLY_NEW_PROFILE:
-		break;
-	}
-}
+/**
+ *	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 /* NET_DIM_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index 90623a0e1942..78ddb9526b62 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -562,6 +562,14 @@ config SIGNATURE
 	  Digital signature verification. Currently only RSA is supported.
 	  Implementation is done using GnuPG MPI library
 
+config DIMLIB
+	bool "DIM library"
+	default y
+	help
+	  Dynamic Interrupt Moderation library.
+	  Implements an algorithm for dynamically change CQ modertion values
+	  according to run time performance.
+
 #
 # libfdt files, only selected if needed.
 #
diff --git a/lib/Makefile b/lib/Makefile
index fb7697031a79..dcb558c7554d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -202,6 +202,7 @@ obj-$(CONFIG_GLOB) += glob.o
 obj-$(CONFIG_GLOB_SELFTEST) += globtest.o
 
 obj-$(CONFIG_MPILIB) += mpi/
+obj-$(CONFIG_DIMLIB) += dim/
 obj-$(CONFIG_SIGNATURE) += digsig.o
 
 lib-$(CONFIG_CLZ_TAB) += clz_tab.o
diff --git a/lib/dim/Makefile b/lib/dim/Makefile
new file mode 100644
index 000000000000..160afe288df0
--- /dev/null
+++ b/lib/dim/Makefile
@@ -0,0 +1,9 @@
+#
+# DIM Dynamic Interrupt Moderation library
+#
+
+obj-$(CONFIG_DIMLIB) = net_dim.o
+
+net_dim-y = \
+	dim.o		\
+	net_dim.o
diff --git a/lib/dim/dim.c b/lib/dim/dim.c
new file mode 100644
index 000000000000..17d5236759bd
--- /dev/null
+++ b/lib/dim/dim.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2019, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <linux/dim.h>
+
+bool dim_on_top(struct dim *dim)
+{
+	switch (dim->tune_state) {
+	case DIM_PARKING_ON_TOP:
+	case DIM_PARKING_TIRED:
+		return true;
+	case DIM_GOING_RIGHT:
+		return (dim->steps_left > 1) && (dim->steps_right == 1);
+	default: /* DIM_GOING_LEFT */
+		return (dim->steps_right > 1) && (dim->steps_left == 1);
+	}
+}
+EXPORT_SYMBOL(dim_on_top);
+
+void dim_turn(struct dim *dim)
+{
+	switch (dim->tune_state) {
+	case DIM_PARKING_ON_TOP:
+	case DIM_PARKING_TIRED:
+		break;
+	case DIM_GOING_RIGHT:
+		dim->tune_state = DIM_GOING_LEFT;
+		dim->steps_left = 0;
+		break;
+	case DIM_GOING_LEFT:
+		dim->tune_state = DIM_GOING_RIGHT;
+		dim->steps_right = 0;
+		break;
+	}
+}
+EXPORT_SYMBOL(dim_turn);
+
+void dim_park_on_top(struct dim *dim)
+{
+	dim->steps_right  = 0;
+	dim->steps_left   = 0;
+	dim->tired        = 0;
+	dim->tune_state   = DIM_PARKING_ON_TOP;
+}
+EXPORT_SYMBOL(dim_park_on_top);
+
+void dim_park_tired(struct dim *dim)
+{
+	dim->steps_right  = 0;
+	dim->steps_left   = 0;
+	dim->tune_state   = DIM_PARKING_TIRED;
+}
+EXPORT_SYMBOL(dim_park_tired);
+
+void dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+		    struct 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(DIM_NEVENTS * USEC_PER_MSEC,
+					delta_us);
+}
+EXPORT_SYMBOL(dim_calc_stats);
diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c
new file mode 100644
index 000000000000..a988de317773
--- /dev/null
+++ b/lib/dim/net_dim.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2018, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <linux/net_dim.h>
+#include <linux/dim.h>
+
+struct dim_cq_moder
+net_dim_get_rx_moderation(u8 cq_period_mode, int ix)
+{
+	struct dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix];
+
+	cq_moder.cq_period_mode = cq_period_mode;
+	return cq_moder;
+}
+EXPORT_SYMBOL(net_dim_get_rx_moderation);
+
+struct dim_cq_moder
+net_dim_get_def_rx_moderation(u8 cq_period_mode)
+{
+	u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+			NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
+
+	return net_dim_get_rx_moderation(cq_period_mode, profile_ix);
+}
+EXPORT_SYMBOL(net_dim_get_def_rx_moderation);
+
+struct dim_cq_moder
+net_dim_get_tx_moderation(u8 cq_period_mode, int ix)
+{
+	struct dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix];
+
+	cq_moder.cq_period_mode = cq_period_mode;
+	return cq_moder;
+}
+EXPORT_SYMBOL(net_dim_get_tx_moderation);
+
+struct dim_cq_moder
+net_dim_get_def_tx_moderation(u8 cq_period_mode)
+{
+	u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ?
+			NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE;
+
+	return net_dim_get_tx_moderation(cq_period_mode, profile_ix);
+}
+EXPORT_SYMBOL(net_dim_get_def_tx_moderation);
+
+static int net_dim_step(struct dim *dim)
+{
+	if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2))
+		return DIM_TOO_TIRED;
+
+	switch (dim->tune_state) {
+	case DIM_PARKING_ON_TOP:
+	case DIM_PARKING_TIRED:
+		break;
+	case DIM_GOING_RIGHT:
+		if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1))
+			return DIM_ON_EDGE;
+		dim->profile_ix++;
+		dim->steps_right++;
+		break;
+	case DIM_GOING_LEFT:
+		if (dim->profile_ix == 0)
+			return DIM_ON_EDGE;
+		dim->profile_ix--;
+		dim->steps_left++;
+		break;
+	}
+
+	dim->tired++;
+	return DIM_STEPPED;
+}
+
+static void net_dim_exit_parking(struct dim *dim)
+{
+	dim->tune_state = dim->profile_ix ? DIM_GOING_LEFT : DIM_GOING_RIGHT;
+	net_dim_step(dim);
+}
+
+static int net_dim_stats_compare(struct dim_stats *curr,
+				 struct dim_stats *prev)
+{
+	if (!prev->bpms)
+		return curr->bpms ? DIM_STATS_BETTER : DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms))
+		return (curr->bpms > prev->bpms) ? DIM_STATS_BETTER :
+						   DIM_STATS_WORSE;
+
+	if (!prev->ppms)
+		return curr->ppms ? DIM_STATS_BETTER :
+				    DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
+		return (curr->ppms > prev->ppms) ? DIM_STATS_BETTER :
+						   DIM_STATS_WORSE;
+
+	if (!prev->epms)
+		return DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
+		return (curr->epms < prev->epms) ? DIM_STATS_BETTER :
+						   DIM_STATS_WORSE;
+
+	return DIM_STATS_SAME;
+}
+
+static bool net_dim_decision(struct dim_stats *curr_stats, struct 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 DIM_PARKING_ON_TOP:
+		stats_res = net_dim_stats_compare(curr_stats,
+						  &dim->prev_stats);
+		if (stats_res != DIM_STATS_SAME)
+			net_dim_exit_parking(dim);
+		break;
+
+	case DIM_PARKING_TIRED:
+		dim->tired--;
+		if (!dim->tired)
+			net_dim_exit_parking(dim);
+		break;
+
+	case DIM_GOING_RIGHT:
+	case DIM_GOING_LEFT:
+		stats_res = net_dim_stats_compare(curr_stats,
+						  &dim->prev_stats);
+		if (stats_res != DIM_STATS_BETTER)
+			dim_turn(dim);
+
+		if (dim_on_top(dim)) {
+			dim_park_on_top(dim);
+			break;
+		}
+
+		step_res = net_dim_step(dim);
+		switch (step_res) {
+		case DIM_ON_EDGE:
+			dim_park_on_top(dim);
+			break;
+		case DIM_TOO_TIRED:
+			dim_park_tired(dim);
+			break;
+		}
+
+		break;
+	}
+
+	if (prev_state != DIM_PARKING_ON_TOP ||
+	    dim->tune_state != DIM_PARKING_ON_TOP)
+		dim->prev_stats = *curr_stats;
+
+	return dim->profile_ix != prev_ix;
+}
+
+void net_dim(struct dim *dim, struct dim_sample end_sample)
+{
+	struct dim_stats curr_stats;
+	u16 nevents;
+
+	switch (dim->state) {
+	case DIM_MEASURE_IN_PROGRESS:
+		nevents = BIT_GAP(BITS_PER_TYPE(u16),
+				  end_sample.event_ctr,
+				  dim->start_sample.event_ctr);
+		if (nevents < DIM_NEVENTS)
+			break;
+		dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats);
+		if (net_dim_decision(&curr_stats, dim)) {
+			dim->state = DIM_APPLY_NEW_PROFILE;
+			schedule_work(&dim->work);
+			break;
+		}
+		/* fall through */
+	case DIM_START_MEASURE:
+		dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr,
+				  end_sample.byte_ctr, &dim->start_sample);
+		dim->state = DIM_MEASURE_IN_PROGRESS;
+		break;
+	case DIM_APPLY_NEW_PROFILE:
+		break;
+	}
+}
+EXPORT_SYMBOL(net_dim);
-- 
2.21.0