Subject: Re: [PATCH v2] vhost/vdpa: Add MSI translation tables to iommu for
 software-managed MSI
To:     "Michael S. Tsirkin" <mst@redhat.com>
CC:     <joro@8bytes.org>, <will@kernel.org>, <robin.murphy@arm.com>,
        <jasowang@redhat.com>, <iommu@lists.linux.dev>,
        <linux-kernel@vger.kernel.org>, <kvm@vger.kernel.org>,
        <virtualization@lists.linux-foundation.org>,
        <netdev@vger.kernel.org>, <wangrong68@huawei.com>
References: <20230207120843.1580403-1-sunnanyong@huawei.com>
 <20230215064759-mutt-send-email-mst@kernel.org>
From:   Nanyong Sun <sunnanyong@huawei.com>
Message-ID: <18aa2ad4-df34-de2d-4bda-8a49c191df18@huawei.com>
Date:   Thu, 16 Feb 2023 20:11:06 +0800
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101
 Thunderbird/78.8.1
MIME-Version: 1.0
In-Reply-To: <20230215064759-mutt-send-email-mst@kernel.org>
Content-Type: text/plain; charset="gbk"; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk


On 2023/2/15 19:48, Michael S. Tsirkin wrote:
> On Tue, Feb 07, 2023 at 08:08:43PM +0800, Nanyong Sun wrote:
>> From: Rong Wang <wangrong68@huawei.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.
> put changelog after --- pls

Ok, will do that in version3

>
>> Signed-off-by: Rong Wang <wangrong68@huawei.com>
>> Signed-off-by: Nanyong Sun <sunnanyong@huawei.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;
>>   	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;
>> +}
>> +
>>   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;
>> -- 
>> 2.25.1
> .