[ofa-general][PATCH 2/3] mlx4: Default value for automatic completion vector selection

[Yevgeny Petrilin]

When the vector number passed to mlx4_cq_alloc is MLX4_LEAST_ATTACHED_VECTOR (0xffffffff),
the driver selects the completion vector that has the least CQ's attached
to it and attaches the CQ to the chosen vector.
IB_CQ_VECTOR_LEAST_ATTACHED is defined in rdma/ib_verbs.h, when mlx4_ib driver,
receives this cq vector number, it uses MLX4_LEAST_ATTACHED_VECTOR an CQ creation.

Signed-off-by: Yevgeny Petrilin <yevgenyp at mellanox.co.il>
---
 drivers/infiniband/hw/mlx4/cq.c |    4 +++-
 drivers/net/mlx4/cq.c           |   22 +++++++++++++++++++++-
 drivers/net/mlx4/en_cq.c        |    2 +-
 drivers/net/mlx4/mlx4.h         |    1 +
 include/linux/mlx4/device.h     |    2 ++
 include/rdma/ib_verbs.h         |   10 +++++++++-
 6 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 5de41bd..384e616 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -222,7 +222,9 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	}

 	err = mlx4_cq_alloc(dev->dev, entries, &cq->buf.mtt, uar,
-			    cq->db.dma, &cq->mcq, vector, 0);
+			    cq->db.dma, &cq->mcq,
+			    vector == IB_CQ_VECTOR_LEAST_ATTACHED ?
+			    MLX4_LEAST_ATTACHED_VECTOR : vector, 0);
 	if (err)
 		goto err_dbmap;

diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index a675e85..31a5190 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -187,6 +187,22 @@ int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
 }
 EXPORT_SYMBOL_GPL(mlx4_cq_resize);

+static int mlx4_find_least_loaded_vector(struct mlx4_priv *priv)
+{
+	int i;
+	int index = 0;
+	int min = priv->eq_table.eq[MLX4_EQ_COMP_CPU0].load;
+
+	for (i = 1; i < priv->dev.caps.num_comp_vectors; i++) {
+		if (priv->eq_table.eq[MLX4_EQ_COMP_CPU0 + i].load < min) {
+			index = i;
+			min = priv->eq_table.eq[MLX4_EQ_COMP_CPU0 + i].load;
+		}
+	}
+
+	return index;
+}
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
 		  unsigned vector, int collapsed)
@@ -228,7 +244,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 	cq_context->flags	    = cpu_to_be32(!!collapsed << 18);
 	cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index);

-	if (vector >= dev->caps.num_comp_vectors) {
+	if (vector == MLX4_LEAST_ATTACHED_VECTOR)
+		vector = mlx4_find_least_loaded_vector(priv);
+	else if (vector >= dev->caps.num_comp_vectors) {
 		err = -EINVAL;
 		goto err_radix;
 	}
@@ -248,6 +266,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 	if (err)
 		goto err_radix;

+	priv->eq_table.eq[cq->comp_eq_idx].load++;
 	cq->cons_index = 0;
 	cq->arm_sn     = 1;
 	cq->uar        = uar;
@@ -285,6 +304,7 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
 		mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);

 	synchronize_irq(priv->eq_table.eq[cq->comp_eq_idx].irq);
+	priv->eq_table.eq[cq->comp_eq_idx].load--;

 	spin_lock_irq(&cq_table->lock);
 	radix_tree_delete(&cq_table->tree, cq->cqn);
diff --git a/drivers/net/mlx4/en_cq.c b/drivers/net/mlx4/en_cq.c
index 8f388e8..9fd9eab 100644
--- a/drivers/net/mlx4/en_cq.c
+++ b/drivers/net/mlx4/en_cq.c
@@ -56,7 +56,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 		cq->vector = ring % mdev->dev->caps.num_comp_vectors;
 	} else {
 		cq->buf_size = sizeof(struct mlx4_cqe);
-		cq->vector = 0;
+		cq->vector = MLX4_LEAST_ATTACHED_VECTOR;
 	}

 	cq->ring = ring;
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 612abe6..1b953ab 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -145,6 +145,7 @@ struct mlx4_eq {
 	u16			irq;
 	u16			have_irq;
 	int			nent;
+	int			load;
 	struct mlx4_buf_list   *page_list;
 	struct mlx4_mtt		mtt;
 };
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6228b97..f9638e5 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -169,6 +169,8 @@ enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };

+#define MLX4_LEAST_ATTACHED_VECTOR	0xffffffff
+
 static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 {
 	return (major << 32) | (minor << 16) | subminor;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 936e333..e76e028 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1448,6 +1448,13 @@ static inline int ib_post_recv(struct ib_qp *qp,
 	return qp->device->post_recv(qp, recv_wr, bad_recv_wr);
 }

+/*
+ * IB_CQ_VECTOR_LEAST_ATTACHED: The constant specifies that
+ *	the CQ will be attached to the completion vector that has
+ *	the least number of CQs already attached to it.
+ */
+#define IB_CQ_VECTOR_LEAST_ATTACHED	0xffffffff
+
 /**
  * ib_create_cq - Creates a CQ on the specified device.
  * @device: The device on which to create the CQ.
@@ -1459,7 +1466,8 @@ static inline int ib_post_recv(struct ib_qp *qp,
  *   the associated completion and event handlers.
  * @cqe: The minimum size of the CQ.
  * @comp_vector - Completion vector used to signal completion events.
- *     Must be >= 0 and < context->num_comp_vectors.
+ *     Must be >= 0 and < context->num_comp_vectors
+ *     or IB_CQ_VECTOR_LEAST_ATTACHED.
  *
  * Users can examine the cq structure to determine the actual CQ size.
  */
-- 
1.5.4