diff mbox series

[net,7/9] net/mlx5: Don't request more than supported EQs

Message ID 20210331201424.331095-8-saeed@kernel.org (mailing list archive)
State Accepted
Commit a7b76002ae78cd230ee652ccdfedf21aa94fcecc
Delegated to: Netdev Maintainers
Headers show
Series [net,1/9] net/mlx5e: Fix mapping of ct_label zero | expand

Checks

Context Check Description
netdev/apply success Patch already applied to net
netdev/tree_selection success Clearly marked for net

Commit Message

Saeed Mahameed March 31, 2021, 8:14 p.m. UTC 
From: Daniel Jurgens <danielj@mellanox.com>

Calculating the number of compeltion EQs based on the number of
available IRQ vectors doesn't work now that all async EQs share one IRQ.
Thus the max number of EQs can be exceeded on systems with more than
approximately 256 CPUs. Take this into account when calculating the
number of available completion EQs.

Fixes: 81bfa206032a ("net/mlx5: Use a single IRQ for all async EQs")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 174dfbc996c6..1fa9c18563da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -931,13 +931,24 @@  void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 	mutex_unlock(&table->lock);
 }
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#define MLX5_MAX_ASYNC_EQS 4
+#else
+#define MLX5_MAX_ASYNC_EQS 3
+#endif
+
 int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int err;
 
 	eq_table->num_comp_eqs =
-		mlx5_irq_get_num_comp(eq_table->irq_table);
+		min_t(int,
+		      mlx5_irq_get_num_comp(eq_table->irq_table),
+		      num_eqs - MLX5_MAX_ASYNC_EQS);
 
 	err = create_async_eqs(dev);
 	if (err) {