netdev - Re: [PATCH v2] vhost/vdpa: Add MSI translation tables to iommu for software-managed MSI

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 16 Feb 2023 12:43:00 +0800
From:   Jason Wang <jasowang@...hat.com>
To:     Nanyong Sun <sunnanyong@...wei.com>, joro@...tes.org,
        will@...nel.org, robin.murphy@....com, mst@...hat.com
Cc:     iommu@...ts.linux.dev, linux-kernel@...r.kernel.org,
        kvm@...r.kernel.org, virtualization@...ts.linux-foundation.org,
        netdev@...r.kernel.org, wangrong68@...wei.com
Subject: Re: [PATCH v2] vhost/vdpa: Add MSI translation tables to iommu for
 software-managed MSI


在 2023/2/7 20:08, Nanyong Sun 写道:
> From: Rong Wang <wangrong68@...wei.com>
>
> 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.
>
> Signed-off-by: Rong Wang <wangrong68@...wei.com>
> Signed-off-by: Nanyong Sun <sunnanyong@...wei.com>
> ---
>   drivers/iommu/iommu.c |  1 +
>   drivers/vhost/vdpa.c  | 59 ++++++++++++++++++++++++++++++++++++++++---
>   2 files changed, 57 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 5f6a85aea501..af9c064ad8b2 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -2623,6 +2623,7 @@ void iommu_get_resv_regions(struct device *dev, struct list_head *list)
>   	if (ops->get_resv_regions)
>   		ops->get_resv_regions(dev, list);
>   }
> +EXPORT_SYMBOL(iommu_get_resv_regions);
>   
>   /**
>    * iommu_put_resv_regions - release resered regions
> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
> index ec32f785dfde..a58979da8acd 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;


Nit: it might be better to rename this as resv_regions.


>   	struct device dev;
>   	struct cdev cdev;
>   	atomic_t opened;
> @@ -216,6 +217,8 @@ static int vhost_vdpa_reset(struct vhost_vdpa *v)
>   
>   	v->in_batch = 0;
>   
> +	vhost_iotlb_reset(&v->resv_iotlb);
> +
>   	return vdpa_reset(vdpa);
>   }
>   
> @@ -1013,6 +1016,10 @@ 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;
> @@ -1103,6 +1110,45 @@ 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;
> +			with_sw_msi = true;
> +		}
> +	}
> +
> +	if (!ret && !with_hw_msi && with_sw_msi)
> +		ret = iommu_get_msi_cookie(domain, resv_msi_base);
> +
> +	iommu_put_resv_regions(dma_dev, &dev_resv_regions);
> +
> +	return ret;
> +}


As discussed in v1, I still prefer to factor out the common logic and 
move them to iommu.c. It helps to simplify the future bug fixing and 
enhancement.


> +
>   static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
>   {
>   	struct vdpa_device *vdpa = v->vdpa;
> @@ -1128,11 +1174,16 @@ 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;
> +err_attach_device:
> +	iommu_detach_device(v->domain, dma_dev);
> +err_alloc_domain:
>   	iommu_domain_free(v->domain);
>   	return ret;
>   }
> @@ -1385,6 +1436,8 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
>   		goto err;
>   	}
>   
> +	vhost_iotlb_init(&v->resv_iotlb, 0, 0);
> +
>   	r = dev_set_name(&v->dev, "vhost-vdpa-%u", minor);
>   	if (r)
>   		goto err;


We need clean resv_iotlb during release().

Other looks good.

Thanks