Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
IronPort-SDR: lKWFHWNZYnlqaBmkSxOp+ICIPdzooc5adi49GeZB83dBcTb4g7dqgLCwdj5WMn3WuQ7JlH7Yq8
 f6ISoez1kUMw==
IronPort-SDR: 3n7ZaBt1QAtL8ckMyOn0+HIcWqDND4WEFimtAJUDCEPAMqYddkyHPVEF5IQ4bJL28vudceK//d
 7+ieRaMumCaA==
From:   "Tian, Kevin" <kevin.tian@intel.com>
To:     "Liu, Yi L" <yi.l.liu@intel.com>,
        "alex.williamson@redhat.com" <alex.williamson@redhat.com>,
        "eric.auger@redhat.com" <eric.auger@redhat.com>
CC:     "jacob.jun.pan@linux.intel.com" <jacob.jun.pan@linux.intel.com>,
        "joro@8bytes.org" <joro@8bytes.org>,
        "Raj, Ashok" <ashok.raj@intel.com>,
        "Tian, Jun J" <jun.j.tian@intel.com>,
        "Sun, Yi Y" <yi.y.sun@intel.com>,
        "jean-philippe@linaro.org" <jean-philippe@linaro.org>,
        "peterx@redhat.com" <peterx@redhat.com>,
        "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>,
        "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "Wu, Hao" <hao.wu@intel.com>
Subject: RE: [PATCH v1 5/8] vfio/type1: Report 1st-level/stage-1 format to
 userspace
Thread-Topic: [PATCH v1 5/8] vfio/type1: Report 1st-level/stage-1 format to
 userspace
Thread-Index: AQHWAEUcrRt83jyTNECgMYM7VBywiqhg9Y6g
Date:   Mon, 30 Mar 2020 11:48:45 +0000
Message-ID: <AADFC41AFE54684AB9EE6CBC0274A5D19D7FF8BC@SHSMSX104.ccr.corp.intel.com>
References: <1584880325-10561-1-git-send-email-yi.l.liu@intel.com>
 <1584880325-10561-6-git-send-email-yi.l.liu@intel.com>
In-Reply-To: <1584880325-10561-6-git-send-email-yi.l.liu@intel.com>
Accept-Language: en-US
Content-Language: en-US
dlp-product: dlpe-windows
dlp-version: 11.2.0.6
dlp-reaction: no-action
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 8BIT
MIME-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

> From: Liu, Yi L <yi.l.liu@intel.com>
> Sent: Sunday, March 22, 2020 8:32 PM
> 
> From: Liu Yi L <yi.l.liu@intel.com>
> 
> VFIO exposes IOMMU nesting translation (a.k.a dual stage translation)
> capability to userspace. Thus applications like QEMU could support
> vIOMMU with hardware's nesting translation capability for pass-through
> devices. Before setting up nesting translation for pass-through devices,
> QEMU and other applications need to learn the supported 1st-lvl/stage-1
> translation structure format like page table format.
> 
> Take vSVA (virtual Shared Virtual Addressing) as an example, to support
> vSVA for pass-through devices, QEMU setup nesting translation for pass-
> through devices. The guest page table are configured to host as 1st-lvl/
> stage-1 page table. Therefore, guest format should be compatible with
> host side.
> 
> This patch reports the supported 1st-lvl/stage-1 page table format on the
> current platform to userspace. QEMU and other alike applications should
> use this format info when trying to setup IOMMU nesting translation on
> host IOMMU.
> 
> Cc: Kevin Tian <kevin.tian@intel.com>
> CC: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Cc: Alex Williamson <alex.williamson@redhat.com>
> Cc: Eric Auger <eric.auger@redhat.com>
> Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
> Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
> ---
>  drivers/vfio/vfio_iommu_type1.c | 56
> +++++++++++++++++++++++++++++++++++++++++
>  include/uapi/linux/vfio.h       |  1 +
>  2 files changed, 57 insertions(+)
> 
> diff --git a/drivers/vfio/vfio_iommu_type1.c
> b/drivers/vfio/vfio_iommu_type1.c
> index 9aa2a67..82a9e0b 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -2234,11 +2234,66 @@ static int vfio_iommu_type1_pasid_free(struct
> vfio_iommu *iommu,
>  	return ret;
>  }
> 
> +static int vfio_iommu_get_stage1_format(struct vfio_iommu *iommu,
> +					 u32 *stage1_format)
> +{
> +	struct vfio_domain *domain;
> +	u32 format = 0, tmp_format = 0;
> +	int ret;
> +
> +	mutex_lock(&iommu->lock);
> +	if (list_empty(&iommu->domain_list)) {
> +		mutex_unlock(&iommu->lock);
> +		return -EINVAL;
> +	}
> +
> +	list_for_each_entry(domain, &iommu->domain_list, next) {
> +		if (iommu_domain_get_attr(domain->domain,
> +			DOMAIN_ATTR_PASID_FORMAT, &format)) {
> +			ret = -EINVAL;
> +			format = 0;
> +			goto out_unlock;
> +		}
> +		/*
> +		 * format is always non-zero (the first format is
> +		 * IOMMU_PASID_FORMAT_INTEL_VTD which is 1). For
> +		 * the reason of potential different backed IOMMU
> +		 * formats, here we expect to have identical formats
> +		 * in the domain list, no mixed formats support.
> +		 * return -EINVAL to fail the attempt of setup
> +		 * VFIO_TYPE1_NESTING_IOMMU if non-identical formats
> +		 * are detected.
> +		 */
> +		if (tmp_format && tmp_format != format) {
> +			ret = -EINVAL;
> +			format = 0;
> +			goto out_unlock;
> +		}
> +
> +		tmp_format = format;
> +	}

this path is invoked only in VFIO_IOMMU_GET_INFO path. If we don't
want to assume the status quo that one container holds only one
device w/ vIOMMU (the prerequisite for vSVA), looks we also need
check the format compatibility when attaching a new group to this
container?

> +	ret = 0;
> +
> +out_unlock:
> +	if (format)
> +		*stage1_format = format;
> +	mutex_unlock(&iommu->lock);
> +	return ret;
> +}
> +
>  static int vfio_iommu_info_add_nesting_cap(struct vfio_iommu *iommu,
>  					 struct vfio_info_cap *caps)
>  {
>  	struct vfio_info_cap_header *header;
>  	struct vfio_iommu_type1_info_cap_nesting *nesting_cap;
> +	u32 formats = 0;
> +	int ret;
> +
> +	ret = vfio_iommu_get_stage1_format(iommu, &formats);
> +	if (ret) {
> +		pr_warn("Failed to get stage-1 format\n");
> +		return ret;
> +	}
> 
>  	header = vfio_info_cap_add(caps, sizeof(*nesting_cap),
>  				   VFIO_IOMMU_TYPE1_INFO_CAP_NESTING,
> 1);
> @@ -2254,6 +2309,7 @@ static int vfio_iommu_info_add_nesting_cap(struct
> vfio_iommu *iommu,
>  		/* nesting iommu type supports PASID requests (alloc/free)
> */
>  		nesting_cap->nesting_capabilities |=
> VFIO_IOMMU_PASID_REQS;
>  	}
> +	nesting_cap->stage1_formats = formats;
> 
>  	return 0;
>  }
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index ed9881d..ebeaf3e 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -763,6 +763,7 @@ struct vfio_iommu_type1_info_cap_nesting {
>  	struct	vfio_info_cap_header header;
>  #define VFIO_IOMMU_PASID_REQS	(1 << 0)
>  	__u32	nesting_capabilities;
> +	__u32	stage1_formats;

do you plan to support multiple formats? If not, use singular name.

>  };
> 
>  #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
> --
> 2.7.4