Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 447 insertions, 0 deletions

diff --git a/lib/dim/Makefile b/lib/dim/Makefile
new file mode 100644
index 000000000..1d6858a10
--- /dev/null
+++ b/lib/dim/Makefile
@@ -0,0 +1,7 @@
+#
+# DIM Dynamic Interrupt Moderation library
+#
+
+obj-$(CONFIG_DIMLIB) += dim.o
+
+dim-y := dim.o net_dim.o rdma_dim.o
diff --git a/lib/dim/dim.c b/lib/dim/dim.c
new file mode 100644
index 000000000..e89aaf07b
--- /dev/null
+++ b/lib/dim/dim.c
@@ -0,0 +1,84 @@
+// 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);
+
+bool 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);
+	u32 ncomps = BIT_GAP(BITS_PER_TYPE(u32), end->comp_ctr,
+			     start->comp_ctr);
+
+	if (!delta_us)
+		return false;
+
+	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);
+	curr_stats->cpms = DIV_ROUND_UP(ncomps * USEC_PER_MSEC, delta_us);
+	if (curr_stats->epms != 0)
+		curr_stats->cpe_ratio = DIV_ROUND_DOWN_ULL(
+			curr_stats->cpms * 100, curr_stats->epms);
+	else
+		curr_stats->cpe_ratio = 0;
+
+	return true;
+}
+EXPORT_SYMBOL(dim_calc_stats);
diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c
new file mode 100644
index 000000000..4e32f7aaa
--- /dev/null
+++ b/lib/dim/net_dim.c
@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2018, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#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
+#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256
+#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128
+#define NET_DIM_DEF_PROFILE_CQE 1
+#define NET_DIM_DEF_PROFILE_EQE 1
+
+#define NET_DIM_RX_EQE_PROFILES { \
+	{.usec = 1,   .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \
+	{.usec = 8,   .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \
+	{.usec = 64,  .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \
+	{.usec = 128, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \
+	{.usec = 256, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}  \
+}
+
+#define NET_DIM_RX_CQE_PROFILES { \
+	{.usec = 2,  .pkts = 256,},             \
+	{.usec = 8,  .pkts = 128,},             \
+	{.usec = 16, .pkts = 64,},              \
+	{.usec = 32, .pkts = 64,},              \
+	{.usec = 64, .pkts = 64,}               \
+}
+
+#define NET_DIM_TX_EQE_PROFILES { \
+	{.usec = 1,   .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,},  \
+	{.usec = 8,   .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,},  \
+	{.usec = 32,  .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,},  \
+	{.usec = 64,  .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,},  \
+	{.usec = 128, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}   \
+}
+
+#define NET_DIM_TX_CQE_PROFILES { \
+	{.usec = 5,  .pkts = 128,},  \
+	{.usec = 8,  .pkts = 64,},  \
+	{.usec = 16, .pkts = 32,},  \
+	{.usec = 32, .pkts = 32,},  \
+	{.usec = 64, .pkts = 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,
+};
+
+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;
+		if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats))
+			break;
+		if (net_dim_decision(&curr_stats, dim)) {
+			dim->state = DIM_APPLY_NEW_PROFILE;
+			schedule_work(&dim->work);
+			break;
+		}
+		fallthrough;
+	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);
diff --git a/lib/dim/rdma_dim.c b/lib/dim/rdma_dim.c
new file mode 100644
index 000000000..88f779486
--- /dev/null
+++ b/lib/dim/rdma_dim.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2019, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <linux/dim.h>
+
+static int rdma_dim_step(struct dim *dim)
+{
+	if (dim->tune_state == DIM_GOING_RIGHT) {
+		if (dim->profile_ix == (RDMA_DIM_PARAMS_NUM_PROFILES - 1))
+			return DIM_ON_EDGE;
+		dim->profile_ix++;
+		dim->steps_right++;
+	}
+	if (dim->tune_state == DIM_GOING_LEFT) {
+		if (dim->profile_ix == 0)
+			return DIM_ON_EDGE;
+		dim->profile_ix--;
+		dim->steps_left++;
+	}
+
+	return DIM_STEPPED;
+}
+
+static int rdma_dim_stats_compare(struct dim_stats *curr,
+				  struct dim_stats *prev)
+{
+	/* first stat */
+	if (!prev->cpms)
+		return DIM_STATS_SAME;
+
+	if (IS_SIGNIFICANT_DIFF(curr->cpms, prev->cpms))
+		return (curr->cpms > prev->cpms) ? DIM_STATS_BETTER :
+						DIM_STATS_WORSE;
+
+	if (IS_SIGNIFICANT_DIFF(curr->cpe_ratio, prev->cpe_ratio))
+		return (curr->cpe_ratio > prev->cpe_ratio) ? DIM_STATS_BETTER :
+						DIM_STATS_WORSE;
+
+	return DIM_STATS_SAME;
+}
+
+static bool rdma_dim_decision(struct dim_stats *curr_stats, struct dim *dim)
+{
+	int prev_ix = dim->profile_ix;
+	u8 state = dim->tune_state;
+	int stats_res;
+	int step_res;
+
+	if (state != DIM_PARKING_ON_TOP && state != DIM_PARKING_TIRED) {
+		stats_res = rdma_dim_stats_compare(curr_stats,
+						   &dim->prev_stats);
+
+		switch (stats_res) {
+		case DIM_STATS_SAME:
+			if (curr_stats->cpe_ratio <= 50 * prev_ix)
+				dim->profile_ix = 0;
+			break;
+		case DIM_STATS_WORSE:
+			dim_turn(dim);
+			fallthrough;
+		case DIM_STATS_BETTER:
+			step_res = rdma_dim_step(dim);
+			if (step_res == DIM_ON_EDGE)
+				dim_turn(dim);
+			break;
+		}
+	}
+
+	dim->prev_stats = *curr_stats;
+
+	return dim->profile_ix != prev_ix;
+}
+
+void rdma_dim(struct dim *dim, u64 completions)
+{
+	struct dim_sample *curr_sample = &dim->measuring_sample;
+	struct dim_stats curr_stats;
+	u32 nevents;
+
+	dim_update_sample_with_comps(curr_sample->event_ctr + 1, 0, 0,
+				     curr_sample->comp_ctr + completions,
+				     &dim->measuring_sample);
+
+	switch (dim->state) {
+	case DIM_MEASURE_IN_PROGRESS:
+		nevents = curr_sample->event_ctr - dim->start_sample.event_ctr;
+		if (nevents < DIM_NEVENTS)
+			break;
+		if (!dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats))
+			break;
+		if (rdma_dim_decision(&curr_stats, dim)) {
+			dim->state = DIM_APPLY_NEW_PROFILE;
+			schedule_work(&dim->work);
+			break;
+		}
+		fallthrough;
+	case DIM_START_MEASURE:
+		dim->state = DIM_MEASURE_IN_PROGRESS;
+		dim_update_sample_with_comps(curr_sample->event_ctr, 0, 0,
+					     curr_sample->comp_ctr,
+					     &dim->start_sample);
+		break;
+	case DIM_APPLY_NEW_PROFILE:
+		break;
+	}
+}
+EXPORT_SYMBOL(rdma_dim);