Re: [PATCH net-next v6 1/5] net: move ARFS rmap management to core

[Joe Damato <jdamato@fastly.com>]

On Fri, Jan 17, 2025 at 05:33:31PM -0700, Ahmed Zaki wrote:
> Add a new netdev flag "rx_cpu_rmap_auto". Drivers supporting ARFS should
> set the flag via netif_enable_cpu_rmap() and core will allocate and manage
> the ARFS rmap. Freeing the rmap is also done by core when the netdev is
> freed.
> 
> For better IRQ affinity management, move the IRQ rmap notifier inside the
> napi_struct. Consequently, add new notify.notify and notify.release
> functions: netif_irq_cpu_rmap_notify() and netif_napi_affinity_release().
> 
> Acked-by: David Arinzon <darinzon@amazon.com>
> Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>

[...]

> diff --git a/net/core/dev.c b/net/core/dev.c
> index fe5f5855593d..dbb63005bc2b 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -6862,6 +6862,141 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
>  }
>  EXPORT_SYMBOL(netif_queue_set_napi);
>  
> +#ifdef CONFIG_RFS_ACCEL
> +static void
> +netif_irq_cpu_rmap_notify(struct irq_affinity_notify *notify,
> +			  const cpumask_t *mask)
> +{
> +	struct napi_struct *napi =
> +		container_of(notify, struct napi_struct, notify);
> +	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
> +	int err;

I wonder if this generates a warning with some compilers? err is
defined not used if !napi->dev->rx_cpu_rmap_auto ? Not sure.

> +	if (napi->dev->rx_cpu_rmap_auto) {
> +		err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask);
> +		if (err)
> +			pr_warn("%s: RMAP update failed (%d)\n",
> +				__func__, err);
> +	}
> +}
> +
> +static void netif_napi_affinity_release(struct kref *ref)
> +{
> +	struct napi_struct *napi =
> +		container_of(ref, struct napi_struct, notify.kref);
> +	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
> +
> +	if (!napi->dev->rx_cpu_rmap_auto)
> +		return;
> +	rmap->obj[napi->napi_rmap_idx] = NULL;
> +	napi->napi_rmap_idx = -1;
> +	cpu_rmap_put(rmap);
> +}
> +
> +static int napi_irq_cpu_rmap_add(struct napi_struct *napi, int irq)
> +{
> +	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
> +	int rc;
> +
> +	if (!rmap)
> +		return -EINVAL;
> +
> +	napi->notify.notify = netif_irq_cpu_rmap_notify;
> +	napi->notify.release = netif_napi_affinity_release;

Maybe the callbacks should only be set at the end after everything
else is successful, just before the return 0 ?

> +	cpu_rmap_get(rmap);
> +	rc = cpu_rmap_add(rmap, napi);
> +	if (rc < 0)
> +		goto err_add;
> +
> +	napi->napi_rmap_idx = rc;
> +	rc = irq_set_affinity_notifier(irq, &napi->notify);
> +	if (rc)
> +		goto err_set;
> +
> +	return 0;
> +
> +err_set:
> +	rmap->obj[napi->napi_rmap_idx] = NULL;
> +	napi->napi_rmap_idx = -1;
> +err_add:
> +	cpu_rmap_put(rmap);
> +	return rc;
> +}

[...]

> +void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
> +{
> +	int rc;
> +
> +	if (!napi->dev->rx_cpu_rmap_auto)
> +		goto out;

Maybe the above if statement could be extended to be something like:

if (!napi->dev->rx_cpu_rmap_auto || napi->irq < 0)
  goto out;

then you can omit the irq > 0 checks in the code below, potentially?

> +	/* Remove existing rmap entries */
> +	if (napi->irq != irq && napi->irq > 0)
> +		irq_set_affinity_notifier(napi->irq, NULL);
> +
> +	if (irq > 0) {
> +		rc = napi_irq_cpu_rmap_add(napi, irq);
> +		if (rc) {
> +			netdev_warn(napi->dev, "Unable to update ARFS map (%d)\n",
> +				    rc);
> +			netif_disable_cpu_rmap(napi->dev);
> +		}
> +	}
> +
> +out:
> +	napi->irq = irq;
> +}
> +EXPORT_SYMBOL(netif_napi_set_irq_locked);
> +