Re: [PATCH v3] vhost/vdpa: Add MSI translation tables to iommu for software-managed MSI

[Stefano Garzarella]

On Wed, Mar 20, 2024 at 06:19:12PM +0800, Wang Rong wrote:
> From: Rong Wang <w_angrong@xxxxxxx>
>
> Once enable iommu domain for one device, the MSI
> translation tables have to be there for software-managed MSI.
> Otherwise, platform with software-managed MSI without an
> irq bypass function, can not get a correct memory write event
> from pcie, will not get irqs.
> The solution is to obtain the MSI phy base address from
> iommu reserved region, and set it to iommu MSI cookie,
> then translation tables will be created while request irq.
>
> Change log
> ----------
>
> v1->v2:
> - add resv iotlb to avoid overlap mapping.
> v2->v3:
> - there is no need to export the iommu symbol anymore.
>
> Signed-off-by: Rong Wang <w_angrong@xxxxxxx>
> ---
> drivers/vhost/vdpa.c | 59 +++++++++++++++++++++++++++++++++++++++++---
> 1 file changed, 56 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
> index ba52d128aeb7..28b56b10372b 100644
> --- a/drivers/vhost/vdpa.c
> +++ b/drivers/vhost/vdpa.c
> @@ -49,6 +49,7 @@ struct vhost_vdpa {
> 	struct completion completion;
> 	struct vdpa_device *vdpa;
> 	struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS];
> +	struct vhost_iotlb resv_iotlb;
> 	struct device dev;
> 	struct cdev cdev;
> 	atomic_t opened;
> @@ -247,6 +248,7 @@ static int _compat_vdpa_reset(struct vhost_vdpa *v)
> static int vhost_vdpa_reset(struct vhost_vdpa *v)
> {
> 	v->in_batch = 0;
> +	vhost_iotlb_reset(&v->resv_iotlb);
> 	return _compat_vdpa_reset(v);
> }
>
> @@ -1219,10 +1221,15 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
> 	    msg->iova + msg->size - 1 > v->range.last)
> 		return -EINVAL;
>
> +	if (vhost_iotlb_itree_first(&v->resv_iotlb, msg->iova,
> +					msg->iova + msg->size - 1))
> +		return -EINVAL;
> +
> 	if (vhost_iotlb_itree_first(iotlb, msg->iova,
> 				    msg->iova + msg->size - 1))
> 		return -EEXIST;
>
> +

Unnecessary new line here.

> 	if (vdpa->use_va)
> 		return vhost_vdpa_va_map(v, iotlb, msg->iova, msg->size,
> 					 msg->uaddr, msg->perm);
> @@ -1307,6 +1314,45 @@ static ssize_t vhost_vdpa_chr_write_iter(struct kiocb *iocb,
> 	return vhost_chr_write_iter(dev, from);
> }
>
> +static int vhost_vdpa_resv_iommu_region(struct iommu_domain *domain, struct device *dma_dev,
> +	struct vhost_iotlb *resv_iotlb)
> +{
> +	struct list_head dev_resv_regions;
> +	phys_addr_t resv_msi_base = 0;
> +	struct iommu_resv_region *region;
> +	int ret = 0;
> +	bool with_sw_msi = false;
> +	bool with_hw_msi = false;
> +
> +	INIT_LIST_HEAD(&dev_resv_regions);
> +	iommu_get_resv_regions(dma_dev, &dev_resv_regions);
> +
> +	list_for_each_entry(region, &dev_resv_regions, list) {
> +		ret = vhost_iotlb_add_range_ctx(resv_iotlb, region->start,
> +				region->start + region->length - 1,
> +				0, 0, NULL);
> +		if (ret) {
> +			vhost_iotlb_reset(resv_iotlb);
> +			break;
> +		}
> +
> +		if (region->type == IOMMU_RESV_MSI)
> +			with_hw_msi = true;
> +
> +		if (region->type == IOMMU_RESV_SW_MSI) {
> +			resv_msi_base = region->start;

Can it happen that there are multiple regions of the IOMMU_RESV_SW_MSI 
type?

In this case, is it correct to overwrite `resv_msi_base`?

> +			with_sw_msi = true;
> +		}
> +	}
> +
> +	if (!ret && !with_hw_msi && with_sw_msi)
> +		ret = iommu_get_msi_cookie(domain, resv_msi_base);

If `iommu_get_msi_cookie()` fails:
 - Should we avoid calling iommu_put_resv_regions()?
 - Should we also call `vhost_iotlb_reset(resv_iotlb)` like for the
   vhost_iotlb_add_range_ctx() failure ?

If it is the case, maybe it's better to add an error label where do the 
cleanup.

> +
> +	iommu_put_resv_regions(dma_dev, &dev_resv_regions);
> +
> +	return ret;
> +}
> +
> static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
> {
> 	struct vdpa_device *vdpa = v->vdpa;
> @@ -1335,11 +1381,16 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
>
> 	ret = iommu_attach_device(v->domain, dma_dev);
> 	if (ret)
> -		goto err_attach;
> +		goto err_alloc_domain;
>
> -	return 0;
> +	ret = vhost_vdpa_resv_iommu_region(v->domain, dma_dev, &v->resv_iotlb);
> +	if (ret)
> +		goto err_attach_device;
>
> -err_attach:
> +	return 0;

I suggest to add a new line here to separate the error path for the 
success path.

> +err_attach_device:
> +	iommu_detach_device(v->domain, dma_dev);
> +err_alloc_domain:
> 	iommu_domain_free(v->domain);
> 	v->domain = NULL;
> 	return ret;
> @@ -1595,6 +1646,8 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
> 		goto err;
> 	}
>
> +	vhost_iotlb_init(&v->resv_iotlb, 0, 0);
> +

IIUC the lifetime of v->resv_iotlb, we initialize it here in the 
vdpa_driver.probe() and we fill it during the `open` of the vhost-vdpa 
character device.

So, should we reset it in the `release` of the vhost-vdpa character 
device?

Thanks,
Stefano

> 	r = dev_set_name(&v->dev, "vhost-vdpa-%u", minor);
> 	if (r)
> 		goto err;
> --
> 2.27.0