KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Auger Eric <eric.auger@redhat.com>
To: Liu Yi L <yi.l.liu@intel.com>,
	alex.williamson@redhat.com, baolu.lu@linux.intel.com,
	joro@8bytes.org
Cc: kevin.tian@intel.com, jacob.jun.pan@linux.intel.com,
	ashok.raj@intel.com, jun.j.tian@intel.com, yi.y.sun@intel.com,
	jean-philippe@linaro.org, peterx@redhat.com, hao.wu@intel.com,
	stefanha@gmail.com, iommu@lists.linux-foundation.org,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v4 07/15] vfio/type1: Add VFIO_IOMMU_PASID_REQUEST (alloc/free)
Date: Mon, 6 Jul 2020 17:17:34 +0200
Message-ID: <f78eac88-eb8e-a6f5-d701-146587660f5f@redhat.com> (raw)
In-Reply-To: <1593861989-35920-8-git-send-email-yi.l.liu@intel.com>

Hi Yi,

On 7/4/20 1:26 PM, Liu Yi L wrote:
> This patch allows user space to request PASID allocation/free, e.g. when
> serving the request from the guest.
> 
> PASIDs that are not freed by userspace are automatically freed when the
> IOASID set is destroyed when process exits.
> 
> 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>
> Cc: Joerg Roedel <joro@8bytes.org>
> Cc: Lu Baolu <baolu.lu@linux.intel.com>
> Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
> Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
> Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> ---
> v3 -> v4:
> *) address comments from v3, except the below comment against the range
>    of PASID_FREE request. needs more help on it.
>     "> +if (req.range.min > req.range.max)
> 
>     Is it exploitable that a user can spin the kernel for a long time in
>     the case of a free by calling this with [0, MAX_UINT] regardless of
>     their actual allocations?"
> 
> v1 -> v2:
> *) move the vfio_mm related code to be a seprate module
> *) use a single structure for alloc/free, could support a range of PASIDs
> *) fetch vfio_mm at group_attach time instead of at iommu driver open time
> ---
>  drivers/vfio/Kconfig            |  1 +
>  drivers/vfio/vfio_iommu_type1.c | 84 +++++++++++++++++++++++++++++++++++++++++
>  drivers/vfio/vfio_pasid.c       | 10 +++++
>  include/linux/vfio.h            |  6 +++
>  include/uapi/linux/vfio.h       | 36 ++++++++++++++++++
>  5 files changed, 137 insertions(+)
> 
> diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> index 3d8a108..95d90c6 100644
> --- a/drivers/vfio/Kconfig
> +++ b/drivers/vfio/Kconfig
> @@ -2,6 +2,7 @@
>  config VFIO_IOMMU_TYPE1
>  	tristate
>  	depends on VFIO
> +	select VFIO_PASID if (X86)
>  	default n
>  
>  config VFIO_IOMMU_SPAPR_TCE
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index 80623b8..29726ca 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -76,6 +76,7 @@ struct vfio_iommu {
>  	bool				dirty_page_tracking;
>  	bool				pinned_page_dirty_scope;
>  	struct iommu_nesting_info	*nesting_info;
> +	struct vfio_mm			*vmm;
>  };
>  
>  struct vfio_domain {
> @@ -1937,6 +1938,11 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
>  
>  static void vfio_iommu_release_nesting_info(struct vfio_iommu *iommu)
>  {
> +	if (iommu->vmm) {
> +		vfio_mm_put(iommu->vmm);
> +		iommu->vmm = NULL;
> +	}
> +
>  	kfree(iommu->nesting_info);
>  	iommu->nesting_info = NULL;
>  }
> @@ -2075,6 +2081,25 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
>  			goto out_detach;
>  		}
>  		iommu->nesting_info = info;
> +
> +		if (info->features & IOMMU_NESTING_FEAT_SYSWIDE_PASID) {
> +			struct vfio_mm *vmm;
> +			int sid;
> +
> +			vmm = vfio_mm_get_from_task(current);
> +			if (IS_ERR(vmm)) {
> +				ret = PTR_ERR(vmm);
> +				goto out_detach;
> +			}
> +			iommu->vmm = vmm;
> +
> +			sid = vfio_mm_ioasid_sid(vmm);
> +			ret = iommu_domain_set_attr(domain->domain,
> +						    DOMAIN_ATTR_IOASID_SID,
> +						    &sid);
> +			if (ret)
> +				goto out_detach;
> +		}
>  	}
>  
>  	/* Get aperture info */
> @@ -2860,6 +2885,63 @@ static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
>  	return -EINVAL;
>  }
>  
> +static int vfio_iommu_type1_pasid_alloc(struct vfio_iommu *iommu,
> +					unsigned int min,
> +					unsigned int max)
> +{
> +	int ret = -EOPNOTSUPP;
> +
> +	mutex_lock(&iommu->lock);
> +	if (iommu->vmm)
> +		ret = vfio_pasid_alloc(iommu->vmm, min, max);
> +	mutex_unlock(&iommu->lock);
> +	return ret;
> +}
> +
> +static int vfio_iommu_type1_pasid_free(struct vfio_iommu *iommu,
> +					unsigned int min,
> +					unsigned int max)
> +{
> +	int ret = -EOPNOTSUPP;
> +
> +	mutex_lock(&iommu->lock);
> +	if (iommu->vmm) {
> +		vfio_pasid_free_range(iommu->vmm, min, max);
> +		ret = 0;
> +	}
> +	mutex_unlock(&iommu->lock);
> +	return ret;
> +}
> +
> +static int vfio_iommu_type1_pasid_request(struct vfio_iommu *iommu,
> +					  unsigned long arg)
> +{
> +	struct vfio_iommu_type1_pasid_request req;
> +	unsigned long minsz;
> +
> +	minsz = offsetofend(struct vfio_iommu_type1_pasid_request, range);
> +
> +	if (copy_from_user(&req, (void __user *)arg, minsz))
> +		return -EFAULT;
> +
> +	if (req.argsz < minsz || (req.flags & ~VFIO_PASID_REQUEST_MASK))
> +		return -EINVAL;
> +
> +	if (req.range.min > req.range.max)
> +		return -EINVAL;
> +
> +	switch (req.flags & VFIO_PASID_REQUEST_MASK) {
> +	case VFIO_IOMMU_FLAG_ALLOC_PASID:
> +		return vfio_iommu_type1_pasid_alloc(iommu,
> +					req.range.min, req.range.max);
> +	case VFIO_IOMMU_FLAG_FREE_PASID:
> +		return vfio_iommu_type1_pasid_free(iommu,
> +					req.range.min, req.range.max);
> +	default:
> +		return -EINVAL;
> +	}
> +}
> +
>  static long vfio_iommu_type1_ioctl(void *iommu_data,
>  				   unsigned int cmd, unsigned long arg)
>  {
> @@ -2876,6 +2958,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
>  		return vfio_iommu_type1_unmap_dma(iommu, arg);
>  	case VFIO_IOMMU_DIRTY_PAGES:
>  		return vfio_iommu_type1_dirty_pages(iommu, arg);
> +	case VFIO_IOMMU_PASID_REQUEST:
> +		return vfio_iommu_type1_pasid_request(iommu, arg);
>  	}
>  
>  	return -ENOTTY;
> diff --git a/drivers/vfio/vfio_pasid.c b/drivers/vfio/vfio_pasid.c
> index c46b870..6f907db 100644
> --- a/drivers/vfio/vfio_pasid.c
> +++ b/drivers/vfio/vfio_pasid.c
> @@ -53,6 +53,7 @@ void vfio_mm_put(struct vfio_mm *vmm)
>  {
>  	kref_put_mutex(&vmm->kref, vfio_mm_release, &vfio_pasid.vfio_mm_lock);
>  }
> +EXPORT_SYMBOL_GPL(vfio_mm_put);
I think this should be belong to [5/15]
>  
>  static void vfio_mm_get(struct vfio_mm *vmm)
>  {
> @@ -104,6 +105,13 @@ struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task)
>  	mmput(mm);
>  	return vmm;
>  }
> +EXPORT_SYMBOL_GPL(vfio_mm_get_from_task);
same
> +
> +int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
extern?
same
> +{
> +	return vmm->ioasid_sid;
> +}
> +EXPORT_SYMBOL_GPL(vfio_mm_ioasid_sid);
>  
>  int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
>  {
> @@ -113,6 +121,7 @@ int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
>  
>  	return (pasid == INVALID_IOASID) ? -ENOSPC : pasid;
>  }
> +EXPORT_SYMBOL_GPL(vfio_pasid_alloc);
same
>  
>  void vfio_pasid_free_range(struct vfio_mm *vmm,
>  			    ioasid_t min, ioasid_t max)
> @@ -130,6 +139,7 @@ void vfio_pasid_free_range(struct vfio_mm *vmm,
>  	for (; pasid <= max; pasid++)
>  		ioasid_free(pasid);
>  }
> +EXPORT_SYMBOL_GPL(vfio_pasid_free_range);
same
>  
>  static int __init vfio_pasid_init(void)
>  {
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 9da6468..35c922a 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -101,6 +101,7 @@ struct vfio_mm;
>  #if IS_ENABLED(CONFIG_VFIO_PASID)
>  extern struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task);
>  extern void vfio_mm_put(struct vfio_mm *vmm);
> +int vfio_mm_ioasid_sid(struct vfio_mm *vmm);
>  extern int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max);
>  extern void vfio_pasid_free_range(struct vfio_mm *vmm,
>  					ioasid_t min, ioasid_t max);
> @@ -114,6 +115,11 @@ static inline void vfio_mm_put(struct vfio_mm *vmm)
>  {
>  }
>  
> +static inline int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
> +{
> +	return -ENOTTY;
> +}
> +
>  static inline int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
>  {
>  	return -ENOTTY;
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 3e3de9c..fe267b8e 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -1169,6 +1169,42 @@ struct vfio_iommu_type1_dirty_bitmap_get {
>  
>  #define VFIO_IOMMU_DIRTY_PAGES             _IO(VFIO_TYPE, VFIO_BASE + 17)
>  
> +/**
> + * VFIO_IOMMU_PASID_REQUEST - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
> + *				struct vfio_iommu_type1_pasid_request)
> + *
> + * PASID (Processor Address Space ID) is a PCIe concept for tagging
> + * address spaces in DMA requests. When system-wide PASID allocation
> + * is required by underlying iommu driver (e.g. Intel VT-d), this
> + * provides an interface for userspace to request pasid alloc/free
> + * for its assigned devices. Userspace should check the availability
> + * of this API through VFIO_IOMMU_GET_INFO.
name the capability?
> + *
> + * @flags=VFIO_IOMMU_FLAG_ALLOC_PASID, allocate a single PASID within @range.
> + * @flags=VFIO_IOMMU_FLAG_FREE_PASID, free the PASIDs within @range.
> + * @range is [min, max], which means both @min and @max are inclusive.
> + * ALLOC_PASID and FREE_PASID are mutually exclusive.
> + *
> + * returns: allocated PASID value on success, -errno on failure for
> + *	     ALLOC_PASID;
> + *	     0 for FREE_PASID operation;
> + */
> +struct vfio_iommu_type1_pasid_request {
> +	__u32	argsz;
> +#define VFIO_IOMMU_FLAG_ALLOC_PASID	(1 << 0)
> +#define VFIO_IOMMU_FLAG_FREE_PASID	(1 << 1)
> +	__u32	flags;> +	struct {
> +		__u32	min;
> +		__u32	max;
> +	} range;
> +};
> +
> +#define VFIO_PASID_REQUEST_MASK	(VFIO_IOMMU_FLAG_ALLOC_PASID | \
> +					 VFIO_IOMMU_FLAG_FREE_PASID)
> +
> +#define VFIO_IOMMU_PASID_REQUEST	_IO(VFIO_TYPE, VFIO_BASE + 18)
> +
>  /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>  
>  /*
> 

Thanks

Eric


  reply index

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-04 11:26 [PATCH v4 00/15] vfio: expose virtual Shared Virtual Addressing to VMs Liu Yi L
2020-07-04 11:26 ` [PATCH v4 01/15] vfio/type1: Refactor vfio_iommu_type1_ioctl() Liu Yi L
2020-07-06  9:34   ` Auger Eric
2020-07-06 12:27     ` Liu, Yi L
2020-07-06 12:55       ` Auger Eric
2020-07-06 13:00         ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 02/15] iommu: Report domain nesting info Liu Yi L
2020-07-06  9:34   ` Auger Eric
2020-07-06 12:20     ` Liu, Yi L
2020-07-06 13:00       ` Auger Eric
2020-07-06 13:17         ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 03/15] iommu/smmu: Report empty " Liu Yi L
2020-07-06 10:37   ` Auger Eric
2020-07-06 12:46     ` Liu, Yi L
2020-07-06 13:21       ` Auger Eric
2020-07-06 13:26         ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 04/15] vfio/type1: Report iommu nesting info to userspace Liu Yi L
2020-07-06 10:37   ` Auger Eric
2020-07-06 13:10     ` Liu, Yi L
2020-07-06 13:45       ` Auger Eric
2020-07-07  9:31         ` Liu, Yi L
2020-07-08  8:08           ` Liu, Yi L
2020-07-08 19:29             ` Alex Williamson
2020-07-09  0:25               ` Liu, Yi L
2020-07-06 14:06   ` Auger Eric
2020-07-07  9:34     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 05/15] vfio: Add PASID allocation/free support Liu Yi L
2020-07-06 14:52   ` Auger Eric
2020-07-07  9:45     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 06/15] iommu/vt-d: Support setting ioasid set to domain Liu Yi L
2020-07-06 14:52   ` Auger Eric
2020-07-07  9:37     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 07/15] vfio/type1: Add VFIO_IOMMU_PASID_REQUEST (alloc/free) Liu Yi L
2020-07-06 15:17   ` Auger Eric [this message]
2020-07-07  9:51     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 08/15] iommu: Pass domain to sva_unbind_gpasid() Liu Yi L
2020-07-04 11:26 ` [PATCH v4 09/15] iommu/vt-d: Check ownership for PASIDs from user-space Liu Yi L
2020-07-04 11:26 ` [PATCH v4 10/15] vfio/type1: Support binding guest page tables to PASID Liu Yi L
2020-07-04 11:26 ` [PATCH v4 11/15] vfio/type1: Allow invalidating first-level/stage IOMMU cache Liu Yi L
2020-07-04 11:26 ` [PATCH v4 12/15] vfio/type1: Add vSVA support for IOMMU-backed mdevs Liu Yi L
2020-07-04 11:26 ` [PATCH v4 13/15] vfio/pci: Expose PCIe PASID capability to guest Liu Yi L
2020-07-04 11:26 ` [PATCH v4 14/15] vfio: Document dual stage control Liu Yi L
2020-07-04 11:26 ` [PATCH v4 15/15] iommu/vt-d: Support reporting nesting capability info Liu Yi L

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=f78eac88-eb8e-a6f5-d701-146587660f5f@redhat.com \
    --to=eric.auger@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=hao.wu@intel.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jean-philippe@linaro.org \
    --cc=joro@8bytes.org \
    --cc=jun.j.tian@intel.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterx@redhat.com \
    --cc=stefanha@gmail.com \
    --cc=yi.l.liu@intel.com \
    --cc=yi.y.sun@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git