Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

4 files changed, 583 insertions, 0 deletions

diff --git a/lib/dim/Makefile b/lib/dim/Makefile
new file mode 100644
index 000000000..5b9bfaac7
--- /dev/null
+++ b/lib/dim/Makefile
@@ -0,0 +1,7 @@
+#
+# DIM Dynamic Interrupt Moderation library
+#
+
+obj-$(CONFIG_DIMLIB) += dimlib.o
+
+dimlib-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..97c3d084e
--- /dev/null
+++ b/lib/dim/dim.c
@@ -0,0 +1,88 @@
+// 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(const struct dim_sample *start,
+		    const 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);
+
+MODULE_DESCRIPTION("Dynamic Interrupt Moderation (DIM) library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c
new file mode 100644
index 000000000..d8d4f6553
--- /dev/null
+++ b/lib/dim/net_dim.c
@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2018, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <linux/dim.h>
+#include <linux/rtnetlink.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_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);
+
+int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags,
+			   u8 coal_flags, u8 rx_mode, u8 tx_mode,
+			   void (*rx_dim_work)(struct work_struct *work),
+			   void (*tx_dim_work)(struct work_struct *work))
+{
+	struct dim_cq_moder *rxp = NULL, *txp;
+	struct dim_irq_moder *moder;
+	int len;
+
+	dev->irq_moder = kzalloc_obj(*dev->irq_moder);
+	if (!dev->irq_moder)
+		return -ENOMEM;
+
+	moder = dev->irq_moder;
+	len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile);
+
+	moder->coal_flags = coal_flags;
+	moder->profile_flags = profile_flags;
+
+	if (profile_flags & DIM_PROFILE_RX) {
+		moder->rx_dim_work = rx_dim_work;
+		moder->dim_rx_mode = rx_mode;
+		rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL);
+		if (!rxp)
+			goto free_moder;
+
+		rcu_assign_pointer(moder->rx_profile, rxp);
+	}
+
+	if (profile_flags & DIM_PROFILE_TX) {
+		moder->tx_dim_work = tx_dim_work;
+		moder->dim_tx_mode = tx_mode;
+		txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL);
+		if (!txp)
+			goto free_rxp;
+
+		rcu_assign_pointer(moder->tx_profile, txp);
+	}
+
+	return 0;
+
+free_rxp:
+	kfree(rxp);
+free_moder:
+	kfree(moder);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(net_dim_init_irq_moder);
+
+/* RTNL lock is held. */
+void net_dim_free_irq_moder(struct net_device *dev)
+{
+	struct dim_cq_moder *rxp, *txp;
+
+	if (!dev->irq_moder)
+		return;
+
+	rxp = rtnl_dereference(dev->irq_moder->rx_profile);
+	txp = rtnl_dereference(dev->irq_moder->tx_profile);
+
+	rcu_assign_pointer(dev->irq_moder->rx_profile, NULL);
+	rcu_assign_pointer(dev->irq_moder->tx_profile, NULL);
+
+	kfree_rcu(rxp, rcu);
+	kfree_rcu(txp, rcu);
+	kfree(dev->irq_moder);
+}
+EXPORT_SYMBOL(net_dim_free_irq_moder);
+
+void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx)
+{
+	struct dim_irq_moder *irq_moder = dev->irq_moder;
+
+	if (!irq_moder)
+		return;
+
+	if (is_tx) {
+		INIT_WORK(&dim->work, irq_moder->tx_dim_work);
+		dim->mode = READ_ONCE(irq_moder->dim_tx_mode);
+		return;
+	}
+
+	INIT_WORK(&dim->work, irq_moder->rx_dim_work);
+	dim->mode = READ_ONCE(irq_moder->dim_rx_mode);
+}
+EXPORT_SYMBOL(net_dim_setting);
+
+void net_dim_work_cancel(struct dim *dim)
+{
+	cancel_work_sync(&dim->work);
+}
+EXPORT_SYMBOL(net_dim_work_cancel);
+
+struct dim_cq_moder net_dim_get_rx_irq_moder(struct net_device *dev,
+					     struct dim *dim)
+{
+	struct dim_cq_moder res, *profile;
+
+	rcu_read_lock();
+	profile = rcu_dereference(dev->irq_moder->rx_profile);
+	res = profile[dim->profile_ix];
+	rcu_read_unlock();
+
+	res.cq_period_mode = dim->mode;
+
+	return res;
+}
+EXPORT_SYMBOL(net_dim_get_rx_irq_moder);
+
+struct dim_cq_moder net_dim_get_tx_irq_moder(struct net_device *dev,
+					     struct dim *dim)
+{
+	struct dim_cq_moder res, *profile;
+
+	rcu_read_lock();
+	profile = rcu_dereference(dev->irq_moder->tx_profile);
+	res = profile[dim->profile_ix];
+	rcu_read_unlock();
+
+	res.cq_period_mode = dim->mode;
+
+	return res;
+}
+EXPORT_SYMBOL(net_dim_get_tx_irq_moder);
+
+void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode)
+{
+	WRITE_ONCE(dev->irq_moder->dim_rx_mode, rx_mode);
+}
+EXPORT_SYMBOL(net_dim_set_rx_mode);
+
+void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode)
+{
+	WRITE_ONCE(dev->irq_moder->dim_tx_mode, tx_mode);
+}
+EXPORT_SYMBOL(net_dim_set_tx_mode);
+
+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, const 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);