Re: [PATCH RFC 3/3] net: stmmac: Migrate IRQ balancing to cpumask_local_spread()

On Wed, Aug 19, 2026 at 04:30:32PM +0200, Florian Bezdeka wrote:
> The previous balancing mechanism was based on num_online_cpus(), which
> is a problem for systems cpu-isolating workloads. IRQs were targeting
> CPUs that were isolated for those sensitive workloads.
> 
> With a migration to cpumask_local_spread() we
>     - get NUMA locality
>     - honor the default SMP affinity mask, which avoids targeting
>       isolated CPUs.
> 
> This also aligns with the pattern used by most network drivers dealing
> with IRQ affinities / affinity hints.
> 
> Signed-off-by: Florian Bezdeka <[email protected]>
> ---
>  drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 21 +++++++++++++++++----
>  1 file changed, 17 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index a71f0df263785dd8badc45292ca3067ab33bda05..949ced7e46d2814b57c6bd86b4886ac3bf33996c 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -3826,11 +3826,16 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
>  	struct stmmac_priv *priv = netdev_priv(dev);
>  	struct stmmac_msi *msi = priv->msi;
>  	enum request_irq_err irq_err;
> +	cpumask_var_t affinity;
>  	int irq_idx = 0;
>  	char *int_name;
> +	int node;
>  	int ret;
>  	int i;
>  
> +	if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
> +		return -ENOMEM;
> +
>  	/* For common interrupt */
>  	int_name = msi->int_name_mac;
>  	sprintf(int_name, "%s:%s", dev->name, "mac");
> @@ -3916,6 +3921,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
>  	}
>  
>  	/* Request Rx MSI irq */
> +	node = dev_to_node(&priv->dev->dev);
>  	for (i = 0; i < priv->plat->rx_queues_to_use; i++) {
>  		if (i >= MTL_MAX_RX_QUEUES)
>  			break;
> @@ -3935,8 +3941,10 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
>  			irq_idx = i;
>  			goto irq_error;
>  		}
> -		irq_set_affinity_hint(msi->rx_irq[i],
> -				      cpumask_of(i % num_online_cpus()));
> +
> +		cpumask_clear(affinity);
> +		cpumask_set_cpu(cpumask_local_spread(i, node), affinity);
> +		irq_set_affinity_and_hint(msi->rx_irq[i], affinity);

If you want to spread more than one IRQ, you'd better convert your
loop into for_each_numa_hop_mask(). That way you don't need to
introduce new function. See the comment on top of
cpumask_local_spread():

 * For those who wants to enumerate all CPUs based on their NUMA distances,
 * i.e. call this function in a loop, like:
 *
 * for (i = 0; i < num_online_cpus(); i++) {
 *      cpu = cpumask_local_spread(i, node);
 *      do_something(cpu);
 * }
 *
 * There's a better alternative based on for_each()-like iterators:
 *
 *      for_each_numa_hop_mask(mask, node) {
 *              for_each_cpu_andnot(cpu, mask, prev)
 *                      do_something(cpu);
 *              prev = mask;
 *      }

Thanks,
Yury

>  	}
>  
>  	/* Request Tx MSI irq */
> @@ -3959,13 +3967,18 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
>  			irq_idx = i;
>  			goto irq_error;
>  		}
> -		irq_set_affinity_hint(msi->tx_irq[i],
> -				      cpumask_of(i % num_online_cpus()));
> +
> +		cpumask_clear(affinity);
> +		cpumask_set_cpu(cpumask_local_spread(i, node), affinity);
> +		irq_set_affinity_and_hint(msi->tx_irq[i], affinity);
>  	}
>  
> +	free_cpumask_var(affinity);
> +
>  	return 0;
>  
>  irq_error:
> +	free_cpumask_var(affinity);
>  	stmmac_free_irq(dev, irq_err, irq_idx);
>  	return ret;
>  }
> 
> -- 
> 2.55.0