net/mlx5: Store flow counters in a list

In order to improve performance of flow counter stats query loop that
traverses all configured flow counters, replace rb_tree with double-linked
list. This change improves performance of traversing flow counters by
removing the tree traversal. (profiling data showed that call to rb_next
was most top CPU consumer)

However, lookup of flow flow counter in list becomes linear, instead of
logarithmic. This problem is fixed by next patch in series, which adds idr
for fast lookup. Idr is to be used because it is not an intrusive data
structure and doesn't require adding any new members to struct mlx5_fc,
which allows its control data part to stay <= 1 cache line in size.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Amir Vadai <amir@vadai.me>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

3 files changed, 42 insertions, 50 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 617d6239c5f3..a06f83c0c2b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -139,7 +139,7 @@ struct mlx5_fc_cache {
 };
 
 struct mlx5_fc {
-	struct rb_node node;
+	struct list_head list;
 	struct llist_node addlist;
 	struct llist_node dellist;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index f1266f215a31..90ebfee37508 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -73,36 +73,38 @@
  *   elapsed, the thread will actually query the hardware.
  */
 
-static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter)
+static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev,
+						      u32 id)
 {
-	struct rb_node **new = &root->rb_node;
-	struct rb_node *parent = NULL;
-
-	while (*new) {
-		struct mlx5_fc *this = rb_entry(*new, struct mlx5_fc, node);
-		int result = counter->id - this->id;
-
-		parent = *new;
-		if (result < 0)
-			new = &((*new)->rb_left);
-		else
-			new = &((*new)->rb_right);
-	}
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+	struct mlx5_fc *counter;
+
+	list_for_each_entry(counter, &fc_stats->counters, list)
+		if (counter->id > id)
+			return &counter->list;
+
+	return &fc_stats->counters;
+}
+
+static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev,
+				 struct mlx5_fc *counter)
+{
+	struct list_head *next = mlx5_fc_counters_lookup_next(dev, counter->id);
 
-	/* Add new node and rebalance tree. */
-	rb_link_node(&counter->node, parent, new);
-	rb_insert_color(&counter->node, root);
+	list_add_tail(&counter->list, next);
 }
 
-/* The function returns the last node that was queried so the caller
+/* The function returns the last counter that was queried so the caller
  * function can continue calling it till all counters are queried.
  */
-static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
+static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
 					   struct mlx5_fc *first,
 					   u32 last_id)
 {
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+	struct mlx5_fc *counter = NULL;
 	struct mlx5_cmd_fc_bulk *b;
-	struct rb_node *node = NULL;
+	bool more = false;
 	u32 afirst_id;
 	int num;
 	int err;
@@ -132,14 +134,16 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
 		goto out;
 	}
 
-	for (node = &first->node; node; node = rb_next(node)) {
-		struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node);
+	counter = first;
+	list_for_each_entry_from(counter, &fc_stats->counters, list) {
 		struct mlx5_fc_cache *c = &counter->cache;
 		u64 packets;
 		u64 bytes;
 
-		if (counter->id > last_id)
+		if (counter->id > last_id) {
+			more = true;
 			break;
+		}
 
 		mlx5_cmd_fc_bulk_get(dev, b,
 				     counter->id, &packets, &bytes);
@@ -155,7 +159,7 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
 out:
 	mlx5_cmd_fc_bulk_free(b);
 
-	return node;
+	return more ? counter : NULL;
 }
 
 static void mlx5_free_fc(struct mlx5_core_dev *dev,
@@ -173,33 +177,30 @@ static void mlx5_fc_stats_work(struct work_struct *work)
 	struct llist_node *tmplist = llist_del_all(&fc_stats->addlist);
 	struct mlx5_fc *counter = NULL, *last = NULL, *tmp;
 	unsigned long now = jiffies;
-	struct rb_node *node;
 
-	if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters))
+	if (tmplist || !list_empty(&fc_stats->counters))
 		queue_delayed_work(fc_stats->wq, &fc_stats->work,
 				   fc_stats->sampling_interval);
 
 	llist_for_each_entry(counter, tmplist, addlist)
-		mlx5_fc_stats_insert(&fc_stats->counters, counter);
+		mlx5_fc_stats_insert(dev, counter);
 
 	tmplist = llist_del_all(&fc_stats->dellist);
 	llist_for_each_entry_safe(counter, tmp, tmplist, dellist) {
-		rb_erase(&counter->node, &fc_stats->counters);
+		list_del(&counter->list);
 
 		mlx5_free_fc(dev, counter);
 	}
 
-	node = rb_last(&fc_stats->counters);
-	if (time_before(now, fc_stats->next_query) || !node)
+	if (time_before(now, fc_stats->next_query) ||
+	    list_empty(&fc_stats->counters))
 		return;
-	last = rb_entry(node, struct mlx5_fc, node);
-
-	node = rb_first(&fc_stats->counters);
-	while (node) {
-		counter = rb_entry(node, struct mlx5_fc, node);
+	last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list);
 
-		node = mlx5_fc_stats_query(dev, counter, last->id);
-	}
+	counter = list_first_entry(&fc_stats->counters, struct mlx5_fc,
+				   list);
+	while (counter)
+		counter = mlx5_fc_stats_query(dev, counter, last->id);
 
 	fc_stats->next_query = now + fc_stats->sampling_interval;
 }
@@ -257,7 +258,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
 
-	fc_stats->counters = RB_ROOT;
+	INIT_LIST_HEAD(&fc_stats->counters);
 	init_llist_head(&fc_stats->addlist);
 	init_llist_head(&fc_stats->dellist);
 
@@ -277,7 +278,6 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
 	struct llist_node *tmplist;
 	struct mlx5_fc *counter;
 	struct mlx5_fc *tmp;
-	struct rb_node *node;
 
 	cancel_delayed_work_sync(&dev->priv.fc_stats.work);
 	destroy_workqueue(dev->priv.fc_stats.wq);
@@ -287,16 +287,8 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
 	llist_for_each_entry_safe(counter, tmp, tmplist, addlist)
 		mlx5_free_fc(dev, counter);
 
-	node = rb_first(&fc_stats->counters);
-	while (node) {
-		counter = rb_entry(node, struct mlx5_fc, node);
-
-		node = rb_next(node);
-
-		rb_erase(&counter->node, &fc_stats->counters);
-
+	list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list)
 		mlx5_free_fc(dev, counter);
-	}
 }
 
 int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4b53ac64004b..61bed33e6675 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -583,7 +583,7 @@ struct mlx5_irq_info {
 };
 
 struct mlx5_fc_stats {
-	struct rb_root counters;
+	struct list_head counters;
 	struct llist_head addlist;
 	struct llist_head dellist;