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:   Mon, 6 Jul 2020 16:06:58 +0200
From:   Auger Eric <eric.auger@...hat.com>
To:     Liu Yi L <yi.l.liu@...el.com>, alex.williamson@...hat.com,
        baolu.lu@...ux.intel.com, joro@...tes.org
Cc:     kevin.tian@...el.com, jacob.jun.pan@...ux.intel.com,
        ashok.raj@...el.com, jun.j.tian@...el.com, yi.y.sun@...el.com,
        jean-philippe@...aro.org, peterx@...hat.com, hao.wu@...el.com,
        stefanha@...il.com, iommu@...ts.linux-foundation.org,
        kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v4 04/15] vfio/type1: Report iommu nesting info to
 userspace

Hi Yi,
On 7/4/20 1:26 PM, Liu Yi L wrote:
> This patch exports iommu nesting capability info to user space through
> VFIO. User space is expected to check this info for supported uAPIs (e.g.
> PASID alloc/free, bind page table, and cache invalidation) and the vendor
> specific format information for first level/stage page table that will be
> bound to.
> 
> The nesting info is available only after the nesting iommu type is set
> for a container. Current implementation imposes one limitation - one
> nesting container should include at most one group. The philosophy of
> vfio container is having all groups/devices within the container share
> the same IOMMU context. When vSVA is enabled, one IOMMU context could
> include one 2nd-level address space and multiple 1st-level address spaces.
> While the 2nd-leve address space is reasonably sharable by multiple groups
> , blindly sharing 1st-level address spaces across all groups within the
> container might instead break the guest expectation. In the future sub/
> super container concept might be introduced to allow partial address space
> sharing within an IOMMU context. But for now let's go with this restriction
> by requiring singleton container for using nesting iommu features. Below
> link has the related discussion about this decision.
> 
> https://lkml.org/lkml/2020/5/15/1028
> 
> Cc: Kevin Tian <kevin.tian@...el.com>
> CC: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> Cc: Alex Williamson <alex.williamson@...hat.com>
> Cc: Eric Auger <eric.auger@...hat.com>
> Cc: Jean-Philippe Brucker <jean-philippe@...aro.org>
> Cc: Joerg Roedel <joro@...tes.org>
> Cc: Lu Baolu <baolu.lu@...ux.intel.com>
> Signed-off-by: Liu Yi L <yi.l.liu@...el.com>
> ---
> v3 -> v4:
> *) address comments against v3.
> 
> v1 -> v2:
> *) added in v2
> ---
> 
>  drivers/vfio/vfio_iommu_type1.c | 105 +++++++++++++++++++++++++++++++++++-----
>  include/uapi/linux/vfio.h       |  16 ++++++
>  2 files changed, 109 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 7accb59..80623b8 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -62,18 +62,20 @@ MODULE_PARM_DESC(dma_entry_limit,
>  		 "Maximum number of user DMA mappings per container (65535).");
>  
>  struct vfio_iommu {
> -	struct list_head	domain_list;
> -	struct list_head	iova_list;
> -	struct vfio_domain	*external_domain; /* domain for external user */
> -	struct mutex		lock;
> -	struct rb_root		dma_list;
> -	struct blocking_notifier_head notifier;
> -	unsigned int		dma_avail;
> -	uint64_t		pgsize_bitmap;
> -	bool			v2;
> -	bool			nesting;
> -	bool			dirty_page_tracking;
> -	bool			pinned_page_dirty_scope;
> +	struct list_head		domain_list;
> +	struct list_head		iova_list;
> +	struct vfio_domain		*external_domain; /* domain for
> +							     external user */
> +	struct mutex			lock;
> +	struct rb_root			dma_list;
> +	struct blocking_notifier_head	notifier;
> +	unsigned int			dma_avail;
> +	uint64_t			pgsize_bitmap;
> +	bool				v2;
> +	bool				nesting;
> +	bool				dirty_page_tracking;
> +	bool				pinned_page_dirty_scope;
> +	struct iommu_nesting_info	*nesting_info;
>  };
>  
>  struct vfio_domain {
> @@ -130,6 +132,9 @@ struct vfio_regions {
>  #define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)	\
>  					(!list_empty(&iommu->domain_list))
>  
> +#define IS_DOMAIN_IN_CONTAINER(iommu)	((iommu->external_domain) || \
> +					 (!list_empty(&iommu->domain_list)))
> +
>  #define DIRTY_BITMAP_BYTES(n)	(ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE)
>  
>  /*
> @@ -1929,6 +1934,13 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
>  
>  	list_splice_tail(iova_copy, iova);
>  }
> +
> +static void vfio_iommu_release_nesting_info(struct vfio_iommu *iommu)
> +{
> +	kfree(iommu->nesting_info);
> +	iommu->nesting_info = NULL;
> +}
> +
>  static int vfio_iommu_type1_attach_group(void *iommu_data,
>  					 struct iommu_group *iommu_group)
>  {
> @@ -1959,6 +1971,12 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
>  		}
>  	}
>  
> +	/* Nesting type container can include only one group */
> +	if (iommu->nesting && IS_DOMAIN_IN_CONTAINER(iommu)) {
> +		mutex_unlock(&iommu->lock);
> +		return -EINVAL;
> +	}
> +
>  	group = kzalloc(sizeof(*group), GFP_KERNEL);
>  	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
>  	if (!group || !domain) {
> @@ -2029,6 +2047,36 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
>  	if (ret)
>  		goto out_domain;
>  
> +	/* Nesting cap info is available only after attaching */
> +	if (iommu->nesting) {
> +		struct iommu_nesting_info tmp;
> +		struct iommu_nesting_info *info;
> +
> +		/* First get the size of vendor specific nesting info */
> +		ret = iommu_domain_get_attr(domain->domain,
> +					    DOMAIN_ATTR_NESTING,
> +					    &tmp);
> +		if (ret)
> +			goto out_detach;
> +
> +		info = kzalloc(tmp.size, GFP_KERNEL);
> +		if (!info) {
> +			ret = -ENOMEM;
> +			goto out_detach;
> +		}
> +
> +		/* Now get the nesting info */
> +		info->size = tmp.size;
> +		ret = iommu_domain_get_attr(domain->domain,
> +					    DOMAIN_ATTR_NESTING,
> +					    info);
> +		if (ret) {
> +			kfree(info);
> +			goto out_detach;
> +		}
> +		iommu->nesting_info = info;
> +	}
> +
>  	/* Get aperture info */
>  	iommu_domain_get_attr(domain->domain, DOMAIN_ATTR_GEOMETRY, &geo);
>  
> @@ -2138,6 +2186,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
>  	return 0;
>  
>  out_detach:
> +	vfio_iommu_release_nesting_info(iommu);
>  	vfio_iommu_detach_group(domain, group);
>  out_domain:
>  	iommu_domain_free(domain->domain);
> @@ -2338,6 +2387,8 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
>  					vfio_iommu_unmap_unpin_all(iommu);
>  				else
>  					vfio_iommu_unmap_unpin_reaccount(iommu);
> +
> +				vfio_iommu_release_nesting_info(iommu);
>  			}
>  			iommu_domain_free(domain->domain);
>  			list_del(&domain->next);
> @@ -2546,6 +2597,30 @@ static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
>  	return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig));
>  }
>  
> +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;
> +	size_t size;
> +
> +	size = sizeof(*nesting_cap) + iommu->nesting_info->size;
> +
> +	header = vfio_info_cap_add(caps, size,
> +				   VFIO_IOMMU_TYPE1_INFO_CAP_NESTING, 1);
> +	if (IS_ERR(header))
> +		return PTR_ERR(header);
> +
> +	nesting_cap = container_of(header,
> +				   struct vfio_iommu_type1_info_cap_nesting,
> +				   header);
> +
> +	memcpy(&nesting_cap->info, iommu->nesting_info,
> +	       iommu->nesting_info->size);
> +
> +	return 0;
> +}
> +
>  static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
>  				     unsigned long arg)
>  {
> @@ -2586,6 +2661,12 @@ static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
>  	if (ret)
>  		return ret;
>  
> +	if (iommu->nesting_info) {
> +		ret = vfio_iommu_info_add_nesting_cap(iommu, &caps);
I think this should happen while holding the &iommu->lock because
nothing prevents the group from being detached in-between

Thanks

Eric
> +		if (ret)
> +			return ret;
> +	}
> +
>  	if (caps.size) {
>  		info.flags |= VFIO_IOMMU_INFO_CAPS;
>  
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 9204705..3e3de9c 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -1039,6 +1039,22 @@ struct vfio_iommu_type1_info_cap_migration {
>  	__u64	max_dirty_bitmap_size;		/* in bytes */
>  };
>  
> +#define VFIO_IOMMU_TYPE1_INFO_CAP_NESTING  3
> +
> +/*
> + * Reporting nesting info to user space.
> + *
> + * @info:	the nesting info provided by IOMMU driver. Today
> + *		it is expected to be a struct iommu_nesting_info
> + *		data.
> + */
> +struct vfio_iommu_type1_info_cap_nesting {
> +	struct	vfio_info_cap_header header;
> +	__u32	flags;
> +	__u32	padding;
> +	__u8	info[];
> +};
> +
>  #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
>  
>  /**
> 

Powered by blists - more mailing lists