[bug report] powerpc: per device MSI irq domain

[Nilay Shroff]

On 12/6/25 8:08 PM, Nam Cao wrote:
> Nilay Shroff <nilay at linux.ibm.com> writes:
>> Yes you can find the architecture document here: 
>> https://github.com/linuxppc/public-docs/blob/main/LoPAPR/LoPAR-20200812.pdf
>>
>> You may refer section 7 in the above document, which describes RTAS API.
> 
> Thank you, that helped a lot.
> 
> Can you please confirm that the below diff fixes the problem? It brings
> back the "fallback" thing that you mentioned.
> 
> Best regards,
> Nam
> 
> diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
> index a82aaa786e9e..8898a968a59b 100644
> --- a/arch/powerpc/platforms/pseries/msi.c
> +++ b/arch/powerpc/platforms/pseries/msi.c
> @@ -19,6 +19,11 @@
>  
>  #include "pseries.h"
>  
> +struct pseries_msi_device {
> +	unsigned int msi_quota;
> +	unsigned int msi_used;
> +};
> +
>  static int query_token, change_token;
>  
>  #define RTAS_QUERY_FN		0
> @@ -433,8 +438,26 @@ static int pseries_msi_ops_prepare(struct irq_domain *domain, struct device *dev
>  	struct msi_domain_info *info = domain->host_data;
>  	struct pci_dev *pdev = to_pci_dev(dev);
>  	int type = (info->flags & MSI_FLAG_PCI_MSIX) ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
> +	int ret;
> +
> +	struct pseries_msi_device *pseries_dev __free(kfree)
> +		= kmalloc(sizeof(*pseries_dev), GFP_KERNEL);
> +	if (!pseries_dev)
> +		return -ENOMEM;
> +
> +	ret = rtas_prepare_msi_irqs(pdev, nvec, type, arg);
> +	if (ret > 0) {
> +		nvec = ret;
> +		ret = rtas_prepare_msi_irqs(pdev, nvec, type, arg);
> +	}
> +	if (ret < 0)
> +		return ret;
>  
> -	return rtas_prepare_msi_irqs(pdev, nvec, type, arg);
> +	pseries_dev->msi_quota = nvec;
> +	pseries_dev->msi_used = 0;
> +
> +	arg->scratchpad[0].ptr = no_free_ptr(pseries_dev);
> +	return 0;
>  }
>  
>  /*
> @@ -443,9 +466,13 @@ static int pseries_msi_ops_prepare(struct irq_domain *domain, struct device *dev
>   */
>  static void pseries_msi_ops_teardown(struct irq_domain *domain, msi_alloc_info_t *arg)
>  {
> +	struct pseries_msi_device *pseries_dev = arg->scratchpad[0].ptr;
>  	struct pci_dev *pdev = to_pci_dev(domain->dev);
>  
>  	rtas_disable_msi(pdev);
> +
> +	WARN_ON(pseries_dev->msi_used);
> +	kfree(pseries_dev);
>  }
>  
>  static void pseries_msi_shutdown(struct irq_data *d)
> @@ -546,12 +573,18 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
>  				    unsigned int nr_irqs, void *arg)
>  {
>  	struct pci_controller *phb = domain->host_data;
> +	struct pseries_msi_device *pseries_dev;
>  	msi_alloc_info_t *info = arg;
>  	struct msi_desc *desc = info->desc;
>  	struct pci_dev *pdev = msi_desc_to_pci_dev(desc);
>  	int hwirq;
>  	int i, ret;
>  
> +	pseries_dev = info->scratchpad[0].ptr;
> +
> +	if (pseries_dev->msi_used + nr_irqs > pseries_dev->msi_quota)
> +		return -ENOSPC;
> +
>  	hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_index);
>  	if (hwirq < 0) {
>  		dev_err(&pdev->dev, "Failed to query HW IRQ: %d\n", hwirq);
> @@ -567,9 +600,10 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
>  			goto out;
>  
>  		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
> -					      &pseries_msi_irq_chip, domain->host_data);
> +					      &pseries_msi_irq_chip, pseries_dev);
>  	}
>  
> +	pseries_dev->msi_used++;
>  	return 0;
>  
>  out:
> @@ -582,9 +616,11 @@ static void pseries_irq_domain_free(struct irq_domain *domain, unsigned int virq
>  				    unsigned int nr_irqs)
>  {
>  	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
> -	struct pci_controller *phb = irq_data_get_irq_chip_data(d);
> +	struct pseries_msi_device *pseries_dev = irq_data_get_irq_chip_data(d);
> +	struct pci_controller *phb = domain->host_data;
>  
>  	pr_debug("%s bridge %pOF %d #%d\n", __func__, phb->dn, virq, nr_irqs);
> +	pseries_dev->msi_used -= nr_irqs;
>  	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
>  }
>  

Thnaks for the patch! I tested it on my system and I confirmed that
this patch fixes the bug reported earlier. That said, if you're
planning to send a formal patch upstream with the above change then
please feel free to add,

Acked-by: Nilay Shroff <nilay at inux.ibm.com>