From: Shay Drory <shayd@nvidia.com>
Date: Tue, 26 Oct 2021 08:25:19 +0300
Subject: net/mlx5: Use first online CPU instead of hard coded CPU
Patch-mainline: v5.16-rc8
Git-commit: 26a7993c93a74a3fee83a37b46e00e69e49e57c2
References: jsc#SLE-19253
Hard coded CPU (0 in our case) might be offline. Hence, use the first
online CPU instead.
Fixes: f891b7cdbdcd ("net/mlx5: Enable single IRQ for PCI Function")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -398,7 +398,7 @@ irq_pool_request_vector(struct mlx5_irq_
cpumask_copy(irq->mask, affinity);
if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max &&
cpumask_empty(irq->mask))
- cpumask_set_cpu(0, irq->mask);
+ cpumask_set_cpu(cpumask_first(cpu_online_mask), irq->mask);
irq_set_affinity_hint(irq->irqn, irq->mask);
unlock:
mutex_unlock(&pool->lock);