[PATCH net-next V5 2/2] net/mlx4_en: Use affinity hint

[Amir Vadai]

From: Yuval Atias <yuvala@xxxxxxxxxxxx>

The âaffinity hintâ mechanism is used by the user space
daemon, irqbalancer, to indicate a preferred CPU mask for irqs.
Irqbalancer can use this hint to balance the irqs between the
cpus indicated by the mask.

We wish the HCA to preferentially map the IRQs it uses to numa cores
close to it.  To accomplish this, we use
netif_set_rx_queue_affinity_hint(), that sets the affinity hint
according the following policy:
First it maps IRQs to âcloseâ numa cores.  If these are exhausted, the
remaining IRQs are mapped to âfarâ numa cores.

Signed-off-by: Yuval Atias <yuvala@xxxxxxxxxxxx>
Signed-off-by: Amir Vadai <amirv@xxxxxxxxxxxx>
---
 drivers/infiniband/hw/mlx4/main.c              |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_cq.c     |  6 +++++-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 30 ++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/eq.c        | 14 +++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 +
 include/linux/mlx4/device.h                    |  2 +-
 6 files changed, 51 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index f9c12e9..7b4725d 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1837,7 +1837,7 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 				i, j, dev->pdev->bus->name);
 			/* Set IRQ for specific name (per ring) */
 			if (mlx4_assign_eq(dev, name, NULL,
-					   &ibdev->eq_table[eq])) {
+					   &ibdev->eq_table[eq], NULL)) {
 				/* Use legacy (same as mlx4_en driver) */
 				pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq);
 				ibdev->eq_table[eq] =
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 70e9532..b09418b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -119,11 +119,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	if (cq->is_tx == RX) {
 		if (mdev->dev->caps.comp_pool) {
 			if (!cq->vector) {
+				struct mlx4_en_rx_ring *ring =
+					priv->rx_ring[cq->ring];
+
 				sprintf(name, "%s-%d", priv->dev->name,
 					cq->ring);
 				/* Set IRQ for specific name (per ring) */
 				if (mlx4_assign_eq(mdev->dev, name, rmap,
-						   &cq->vector)) {
+						   &cq->vector,
+						   ring->affinity_mask)) {
 					cq->vector = (cq->ring + 1 + priv->port)
 					    % mdev->dev->caps.num_comp_vectors;
 					mlx4_warn(mdev, "Failed Assigning an EQ to "
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 3db5946..a6fc7a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1521,6 +1521,32 @@ static void mlx4_en_linkstate(struct work_struct *work)
 	mutex_unlock(&mdev->state_lock);
 }
 
+static void mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+	struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
+	int numa_node = priv->mdev->dev->numa_node;
+
+	if (numa_node == -1)
+		return;
+
+	if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL)) {
+		en_err(priv, "Failed to allocate core mask\n");
+		return;
+	}
+
+	if (irq_set_mq_dev_affinit_hint(ring_idx, numa_node,
+					ring->affinity_mask)) {
+		en_err(priv, "Failed setting affinity hint\n");
+		free_cpumask_var(ring->affinity_mask);
+		ring->affinity_mask = NULL;
+	}
+}
+
+static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+	free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
+	priv->rx_ring[ring_idx]->affinity_mask = NULL;
+}
 
 int mlx4_en_start_port(struct net_device *dev)
 {
@@ -1562,6 +1588,8 @@ int mlx4_en_start_port(struct net_device *dev)
 
 		mlx4_en_cq_init_lock(cq);
 
+		mlx4_en_init_affinity_hint(priv, i);
+
 		err = mlx4_en_activate_cq(priv, cq, i);
 		if (err) {
 			en_err(priv, "Failed activating Rx CQ\n");
@@ -1836,6 +1864,8 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 			msleep(1);
 		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 		mlx4_en_deactivate_cq(priv, cq);
+
+		mlx4_en_free_affinity_hint(priv, i);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 8992b38..a3d8502 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1311,7 +1311,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 EXPORT_SYMBOL(mlx4_test_interrupts);
 
 int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector)
+		   int *vector, cpumask_var_t cpu_hint_mask)
 {
 
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1344,6 +1344,16 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 				continue;
 				/*we dont want to break here*/
 			}
+			if (cpu_hint_mask) {
+				err = irq_set_affinity_hint(
+						priv->eq_table.eq[vec].irq,
+						cpu_hint_mask);
+				if (err) {
+					mlx4_warn(dev, "Failed setting affinity hint\n");
+					/*we dont want to break here*/
+				}
+			}
+
 			eq_set_ci(&priv->eq_table.eq[vec], 1);
 		}
 	}
@@ -1370,6 +1380,8 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 		  Belonging to a legacy EQ*/
 		mutex_lock(&priv->msix_ctl.pool_lock);
 		if (priv->msix_ctl.pool_bm & 1ULL << i) {
+			irq_set_affinity_hint(priv->eq_table.eq[vec].irq,
+					      NULL);
 			free_irq(priv->eq_table.eq[vec].irq,
 				 &priv->eq_table.eq[vec]);
 			priv->msix_ctl.pool_bm &= ~(1ULL << i);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 69e1f36..0de8b0d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -313,6 +313,7 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	int hwtstamp_rx_filter;
+	cpumask_var_t affinity_mask;
 };
 
 struct mlx4_en_cq {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 5edd2c6..f8c253f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1148,7 +1148,7 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupts(struct mlx4_dev *dev);
 int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector);
+		   int *vector, cpumask_t *cpu_hint_mask);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
 int mlx4_get_phys_port_id(struct mlx4_dev *dev);
-- 
1.8.3.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/