net/mlx4: Add EQ pool

Previously, mlx4_en allocated EQs and used them exclusively.
This affected RoCE performance, as applications which are
events sensitive were limited to use only the legacy EQs.

Change that by introducing an EQ pool. This pool is managed
by mlx4_core. EQs are assigned to ports (when there are limited
number of EQs, multiple ports could be assigned to the same EQs).

An exception to this rule is the ASYNC EQ which handles various events.

Legacy EQs are completely removed as all EQs could be shared.

When a consumer (mlx4_ib/mlx4_en) requests an EQ, it asks for
EQ serving on a specific port. The core driver calculates which
EQ should be assigned to that request.

Because IRQs are shared between IB and Ethernet modules, their
names only include the PCI device BDF address.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 23 insertions, 49 deletions

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8c96c71e7bab..024b0f745035 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2041,77 +2041,52 @@ static void init_pkeys(struct mlx4_ib_dev *ibdev)
 
 static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 {
-	char name[80];
-	int eq_per_port = 0;
-	int added_eqs = 0;
-	int total_eqs = 0;
-	int i, j, eq;
-
-	/* Legacy mode or comp_pool is not large enough */
-	if (dev->caps.comp_pool == 0 ||
-	    dev->caps.num_ports > dev->caps.comp_pool)
-		return;
-
-	eq_per_port = dev->caps.comp_pool / dev->caps.num_ports;
-
-	/* Init eq table */
-	added_eqs = 0;
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
-		added_eqs += eq_per_port;
-
-	total_eqs = dev->caps.num_comp_vectors + added_eqs;
+	int i, j, eq = 0, total_eqs = 0;
 
-	ibdev->eq_table = kzalloc(total_eqs * sizeof(int), GFP_KERNEL);
+	ibdev->eq_table = kcalloc(dev->caps.num_comp_vectors,
+				  sizeof(ibdev->eq_table[0]), GFP_KERNEL);
 	if (!ibdev->eq_table)
 		return;
 
-	ibdev->eq_added = added_eqs;
-
-	eq = 0;
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) {
-		for (j = 0; j < eq_per_port; j++) {
-			snprintf(name, sizeof(name), "mlx4-ib-%d-%d@%s",
-				 i, j, dev->persist->pdev->bus->name);
-			/* Set IRQ for specific name (per ring) */
-			if (mlx4_assign_eq(dev, name, NULL,
-					   &ibdev->eq_table[eq])) {
-				/* Use legacy (same as mlx4_en driver) */
-				pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq);
-				ibdev->eq_table[eq] =
-					(eq % dev->caps.num_comp_vectors);
-			}
-			eq++;
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		for (j = 0; j < mlx4_get_eqs_per_port(dev, i);
+		     j++, total_eqs++) {
+			if (i > 1 &&  mlx4_is_eq_shared(dev, total_eqs))
+				continue;
+			ibdev->eq_table[eq] = total_eqs;
+			if (!mlx4_assign_eq(dev, i,
+					    &ibdev->eq_table[eq]))
+				eq++;
+			else
+				ibdev->eq_table[eq] = -1;
 		}
 	}
 
-	/* Fill the reset of the vector with legacy EQ */
-	for (i = 0, eq = added_eqs; i < dev->caps.num_comp_vectors; i++)
-		ibdev->eq_table[eq++] = i;
+	for (i = eq; i < dev->caps.num_comp_vectors;
+	     ibdev->eq_table[i++] = -1)
+		;
 
 	/* Advertise the new number of EQs to clients */
-	ibdev->ib_dev.num_comp_vectors = total_eqs;
+	ibdev->ib_dev.num_comp_vectors = eq;
 }
 
 static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 {
 	int i;
+	int total_eqs = ibdev->ib_dev.num_comp_vectors;
 
-	/* no additional eqs were added */
+	/* no eqs were allocated */
 	if (!ibdev->eq_table)
 		return;
 
 	/* Reset the advertised EQ number */
-	ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
+	ibdev->ib_dev.num_comp_vectors = 0;
 
-	/* Free only the added eqs */
-	for (i = 0; i < ibdev->eq_added; i++) {
-		/* Don't free legacy eqs if used */
-		if (ibdev->eq_table[i] <= dev->caps.num_comp_vectors)
-			continue;
+	for (i = 0; i < total_eqs; i++)
 		mlx4_release_eq(dev, ibdev->eq_table[i]);
-	}
 
 	kfree(ibdev->eq_table);
+	ibdev->eq_table = NULL;
 }
 
 static void *mlx4_ib_add(struct mlx4_dev *dev)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index fce3934372a1..ef80e6c99a68 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -523,7 +523,6 @@ struct mlx4_ib_dev {
 	struct mlx4_ib_iboe	iboe;
 	int			counters[MLX4_MAX_PORTS];
 	int		       *eq_table;
-	int			eq_added;
 	struct kobject	       *iov_parent;
 	struct kobject	       *ports_parent;
 	struct kobject	       *dev_ports_parent[MLX4_MFUNC_MAX];