[PATCH net v4 1/2] bonding: convert unbalanced_load to per-cpu state

[Hangbin Liu]

From: Hangbin Liu <liuhangbin@xxxxxxxxxx>

A later patch widens the bonding TLB tx counters from u32 to u64. The
unbalanced_load counter sits in the transmit hot path, and cross-CPU
synchronization of a u64 would introduce measurable overhead. Convert
unbalanced_load to a per-cpu counter first so that the subsequent
widening only touches per-cpu data local to each CPU.

Introduce struct unbalanced_load_stats to hold the per-cpu counter,
and move the aggregation into a helper, reset_unbalanced_load(), which
sums all per-cpu instances. Use the delta of current total load vs
variable prev_total_unbalanced to calculate the loading.

Signed-off-by: Hangbin Liu <liuhangbin@xxxxxxxxxx>
---
 drivers/net/bonding/bond_alb.c | 37 ++++++++++++++++++++++++++++++-------
 include/net/bond_alb.h         |  7 ++++++-
 2 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 839f7482dc18..0afed2c39231 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -133,6 +133,10 @@ static int tlb_initialize(struct bonding *bond)
 	if (!new_hashtbl)
 		return -ENOMEM;
 
+	bond_info->unbalanced_load = alloc_percpu(struct unbalanced_load_stats);
+	if (!bond_info->unbalanced_load)
+		goto out;
+
 	spin_lock_bh(&bond->mode_lock);
 
 	bond_info->tx_hashtbl = new_hashtbl;
@@ -143,6 +147,10 @@ static int tlb_initialize(struct bonding *bond)
 	spin_unlock_bh(&bond->mode_lock);
 
 	return 0;
+
+out:
+	kfree(new_hashtbl);
+	return -ENOMEM;
 }
 
 /* Must be called only after all slaves have been released */
@@ -154,6 +162,8 @@ static void tlb_deinitialize(struct bonding *bond)
 
 	kfree(bond_info->tx_hashtbl);
 	bond_info->tx_hashtbl = NULL;
+	free_percpu(bond_info->unbalanced_load);
+	bond_info->prev_total_unbalanced = 0;
 
 	spin_unlock_bh(&bond->mode_lock);
 }
@@ -1345,7 +1355,7 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
 		/* unbalanced or unassigned, send through primary */
 		tx_slave = rcu_dereference(bond->curr_active_slave);
 		if (bond->params.tlb_dynamic_lb)
-			bond_info->unbalanced_load += skb->len;
+			this_cpu_add(bond_info->unbalanced_load->tx_bytes, skb->len);
 	}
 
 	if (tx_slave && bond_slave_can_tx(tx_slave)) {
@@ -1529,6 +1539,23 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	return bond_do_alb_xmit(skb, bond, tx_slave);
 }
 
+static u32 reset_unbalanced_load(struct alb_bond_info *bond_info)
+{
+	struct unbalanced_load_stats *p;
+	u32 delta, total_bytes = 0;
+	int i;
+
+	for_each_possible_cpu(i) {
+		p = per_cpu_ptr(bond_info->unbalanced_load, i);
+		total_bytes += READ_ONCE(p->tx_bytes);
+	}
+
+	delta = total_bytes - bond_info->prev_total_unbalanced;
+	bond_info->prev_total_unbalanced = total_bytes;
+
+	return delta / BOND_TLB_REBALANCE_INTERVAL;
+}
+
 void bond_alb_monitor(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
@@ -1570,12 +1597,8 @@ void bond_alb_monitor(struct work_struct *work)
 	if (atomic_read(&bond_info->tx_rebalance_counter) >= BOND_TLB_REBALANCE_TICKS) {
 		bond_for_each_slave_rcu(bond, slave, iter) {
 			tlb_clear_slave(bond, slave, 1);
-			if (slave == rcu_access_pointer(bond->curr_active_slave)) {
-				SLAVE_TLB_INFO(slave).load =
-					bond_info->unbalanced_load /
-						BOND_TLB_REBALANCE_INTERVAL;
-				bond_info->unbalanced_load = 0;
-			}
+			if (slave == rcu_access_pointer(bond->curr_active_slave))
+				SLAVE_TLB_INFO(slave).load = reset_unbalanced_load(bond_info);
 		}
 		atomic_set(&bond_info->tx_rebalance_counter, 0);
 	}
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index e5945427f38d..6fb09b4fc7e2 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -123,9 +123,14 @@ struct tlb_slave_info {
 			 */
 };
 
+struct unbalanced_load_stats {
+	u32			tx_bytes;
+};
+
 struct alb_bond_info {
 	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
-	u32			unbalanced_load;
+	struct unbalanced_load_stats __percpu	*unbalanced_load;
+	u32			prev_total_unbalanced;
 	atomic_t		tx_rebalance_counter;
 	int			lp_counter;
 	/* -------- rlb parameters -------- */

-- 
2.55.0