net/mlx5e: Stop NAPI when irq balancer changes affinity

NAPI context keeps rescheduling on same CPU as long as it's busy.
This doesn't give the oppurtunity for changes in irq affinities
to take effect.
Fix that by calling napi_complete_done() upon a change in affinity.
This would stop the NAPI and reschedule it on the new CPU.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -582,6 +582,9 @@ struct mlx5e_channel {
 	__be32                     mkey_be;
 	u8                         num_tc;
 
+	/* data path - accessed per napi poll */
+	struct irq_desc *irq_desc;
+
 	/* control */
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -1761,7 +1761,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	struct net_device *netdev = priv->netdev;
 	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
+	unsigned int irq;
 	int err;
+	int eqn;
 
 	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
@@ -1778,6 +1780,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->num_tc   = params->num_tc;
 	c->xdp      = !!params->xdp_prog;
 
+	mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+	c->irq_desc = irq_to_desc(irq);
+
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
 	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);

drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c

@@ -30,8 +30,20 @@
  * SOFTWARE.
  */
 
+#include <linux/irq.h>
 #include "en.h"
 
+static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
+{
+	int current_cpu = smp_processor_id();
+	const struct cpumask *aff;
+	struct irq_data *idata;
+
+	idata = irq_desc_get_irq_data(c->irq_desc);
+	aff = irq_data_get_affinity_mask(idata);
+	return cpumask_test_cpu(current_cpu, aff);
+}
+
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
@@ -51,8 +63,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 
 	busy |= c->rq.post_wqes(&c->rq);
 
-	if (busy)
-		return budget;
+	if (busy) {
+		if (likely(mlx5e_channel_no_affinity_change(c)))
+			return budget;
+		if (work_done == budget)
+			work_done--;
+	}
 
 	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;