iommu.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Alex Williamson <alex.williamson@redhat.com>
To: Liu Yi L <yi.l.liu@intel.com>
Cc: jean-philippe@linaro.org, kevin.tian@intel.com,
	ashok.raj@intel.com, kvm@vger.kernel.org,
	iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
	yi.y.sun@intel.com, hao.wu@intel.com, jun.j.tian@intel.com
Subject: Re: [PATCH v3 06/14] vfio/type1: Add VFIO_IOMMU_PASID_REQUEST (alloc/free)
Date: Thu, 2 Jul 2020 15:18:32 -0600	[thread overview]
Message-ID: <20200702151832.048b44d1@x1.home> (raw)
In-Reply-To: <1592988927-48009-7-git-send-email-yi.l.liu@intel.com>

On Wed, 24 Jun 2020 01:55:19 -0700
Liu Yi L <yi.l.liu@intel.com> 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>
> ---
> 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 | 96 ++++++++++++++++++++++++++++++++++++++++-
>  drivers/vfio/vfio_pasid.c       | 10 +++++
>  include/linux/vfio.h            |  6 +++
>  include/uapi/linux/vfio.h       | 36 ++++++++++++++++
>  5 files changed, 147 insertions(+), 2 deletions(-)
> 
> 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 8c143d5..d0891c5 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -73,6 +73,7 @@ struct vfio_iommu {
>  	bool			v2;
>  	bool			nesting;
>  	struct iommu_nesting_info *nesting_info;
> +	struct vfio_mm		*vmm;

Structure alignment again.

>  	bool			dirty_page_tracking;
>  	bool			pinned_page_dirty_scope;
>  };
> @@ -1933,6 +1934,17 @@ 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)
> +{
> +	if (iommu->vmm) {
> +		vfio_mm_put(iommu->vmm);
> +		iommu->vmm = NULL;
> +	}
> +
> +	kfree(iommu->nesting_info);

iommu->nesting_info = NULL;

> +}
> +
>  static int vfio_iommu_type1_attach_group(void *iommu_data,
>  					 struct iommu_group *iommu_group)
>  {
> @@ -2067,6 +2079,25 @@ 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);

This looks pretty dicey in the case of !CONFIG_VFIO_PASID, can we get
here in that case?  If so it looks like we're doing bad things with
setting the domain->ioasid_sid.

> +			if (ret)
> +				goto out_detach;
> +		}
>  	}
>  
>  	/* Get aperture info */
> @@ -2178,7 +2209,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
>  	return 0;
>  
>  out_detach:
> -	kfree(iommu->nesting_info);
> +	if (iommu->nesting_info)
> +		vfio_iommu_release_nesting_info(iommu);

Make vfio_iommu_release_nesting_info() check iommu->nesting_info, then
call it unconditionally?

>  	vfio_iommu_detach_group(domain, group);
>  out_domain:
>  	iommu_domain_free(domain->domain);
> @@ -2380,7 +2412,8 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
>  				else
>  					vfio_iommu_unmap_unpin_reaccount(iommu);
>  
> -				kfree(iommu->nesting_info);
> +				if (iommu->nesting_info)
> +					vfio_iommu_release_nesting_info(iommu);
>  			}
>  			iommu_domain_free(domain->domain);
>  			list_del(&domain->next);
> @@ -2852,6 +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 = -ENOTSUPP;
> +
> +	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 = -ENOTSUPP;
> +
> +	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)

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?

> +		return -EINVAL;
> +
> +	switch (req.flags & VFIO_PASID_REQUEST_MASK) {
> +	case VFIO_IOMMU_ALLOC_PASID:
> +		return vfio_iommu_type1_pasid_alloc(iommu,
> +					req.range.min, req.range.max);
> +	case VFIO_IOMMU_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)
>  {
> @@ -2868,6 +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 dd5b6d1..2ea9f1a 100644
> --- a/drivers/vfio/vfio_pasid.c
> +++ b/drivers/vfio/vfio_pasid.c
> @@ -54,6 +54,7 @@ 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);
>  
>  static void vfio_mm_get(struct vfio_mm *vmm)
>  {
> @@ -103,6 +104,13 @@ struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task)
>  	mmput(mm);
>  	return vmm;
>  }
> +EXPORT_SYMBOL_GPL(vfio_mm_get_from_task);
> +
> +int vfio_mm_ioasid_sid(struct vfio_mm *vmm)
> +{
> +	return vmm->ioasid_sid;
> +}
> +EXPORT_SYMBOL_GPL(vfio_mm_ioasid_sid);
>  
>  int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
>  {
> @@ -112,6 +120,7 @@ int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max)
>  
>  	return (pasid == INVALID_IOASID) ? -ENOSPC : pasid;
>  }
> +EXPORT_SYMBOL_GPL(vfio_pasid_alloc);
>  
>  void vfio_pasid_free_range(struct vfio_mm *vmm,
>  			    ioasid_t min, ioasid_t max)
> @@ -129,6 +138,7 @@ void vfio_pasid_free_range(struct vfio_mm *vmm,
>  	for (; pasid <= max; pasid++)
>  		ioasid_free(pasid);
>  }
> +EXPORT_SYMBOL_GPL(vfio_pasid_free_range);
>  
>  static int __init vfio_pasid_init(void)
>  {
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 74e077d..8e60a32 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 f1f39e1..657b2db 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -1162,6 +1162,42 @@ 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.
> + *
> + * @flags=VFIO_IOMMU_ALLOC_PASID, allocate a single PASID within @range.
> + * @flags=VFIO_IOMMU_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_ALLOC_PASID	(1 << 0)
> +#define VFIO_IOMMU_FREE_PASID	(1 << 1)

VFIO_IOMMU_PASID_FLAG_{ALLOC,FREE} would be more similar to other VFIO
UAPI conventions.  Thanks,

Alex

> +	__u32	flags;
> +	struct {
> +		__u32	min;
> +		__u32	max;
> +	} range;
> +};
> +
> +#define VFIO_PASID_REQUEST_MASK	(VFIO_IOMMU_ALLOC_PASID | \
> +					 VFIO_IOMMU_FREE_PASID)
> +
> +#define VFIO_IOMMU_PASID_REQUEST	_IO(VFIO_TYPE, VFIO_BASE + 18)
> +
>  /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>  
>  /*

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  reply	other threads:[~2020-07-02 21:18 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-24  8:55 [PATCH v3 00/14] vfio: expose virtual Shared Virtual Addressing to VMs Liu Yi L
2020-06-24  8:55 ` [PATCH v3 01/14] vfio/type1: Refactor vfio_iommu_type1_ioctl() Liu Yi L
2020-07-02 21:21   ` Alex Williamson
2020-07-03  3:46     ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 02/14] iommu: Report domain nesting info Liu Yi L
2020-06-26  7:47   ` Jean-Philippe Brucker
2020-06-26 16:04     ` Robin Murphy
2020-06-27  6:53       ` Liu, Yi L
2020-06-30  1:20         ` Tian, Kevin
2020-06-27  6:14     ` Liu, Yi L
2020-06-29  9:24   ` Stefan Hajnoczi
2020-06-29 12:23     ` Liu, Yi L
2020-06-30  2:00       ` Tian, Kevin
2020-06-30  3:45         ` Liu, Yi L
2020-07-03  9:59         ` Stefan Hajnoczi
2020-07-02 17:54   ` Alex Williamson
2020-07-03  3:53     ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 03/14] vfio/type1: Report iommu nesting info to userspace Liu Yi L
2020-07-02 18:38   ` Alex Williamson
2020-07-03  6:05     ` Liu, Yi L
2020-07-03 13:03       ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 04/14] vfio: Add PASID allocation/free support Liu Yi L
2020-07-02 21:17   ` Alex Williamson
2020-07-03  6:08     ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 05/14] iommu/vt-d: Support setting ioasid set to domain Liu Yi L
2020-06-24  8:55 ` [PATCH v3 06/14] vfio/type1: Add VFIO_IOMMU_PASID_REQUEST (alloc/free) Liu Yi L
2020-07-02 21:18   ` Alex Williamson [this message]
2020-07-03  6:28     ` Liu, Yi L
2020-07-08  8:16       ` Liu, Yi L
2020-07-08 19:54         ` Alex Williamson
2020-07-09  0:32           ` Liu, Yi L
2020-07-09  1:56             ` Tian, Kevin
2020-07-09  2:08               ` Liu, Yi L
2020-07-09  2:18                 ` Tian, Kevin
2020-07-09  2:26                   ` Liu, Yi L
2020-07-09  7:16                     ` Liu, Yi L
2020-07-09 14:27                       ` Alex Williamson
2020-07-09 18:05                         ` Jacob Pan
2020-07-10  5:39                         ` Liu, Yi L
2020-07-10 12:55                           ` Alex Williamson
2020-07-10 13:03                             ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 07/14] iommu: Pass domain to sva_unbind_gpasid() Liu Yi L
2020-06-24  8:55 ` [PATCH v3 08/14] iommu/vt-d: Check ownership for PASIDs from user-space Liu Yi L
2020-06-24  8:55 ` [PATCH v3 09/14] vfio/type1: Support binding guest page tables to PASID Liu Yi L
2020-07-02 21:19   ` Alex Williamson
2020-07-03  6:46     ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 10/14] vfio/type1: Allow invalidating first-level/stage IOMMU cache Liu Yi L
2020-07-02 21:19   ` Alex Williamson
2020-07-03  3:47     ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 11/14] vfio/type1: Add vSVA support for IOMMU-backed mdevs Liu Yi L
2020-06-24  8:55 ` [PATCH v3 12/14] vfio/pci: Expose PCIe PASID capability to guest Liu Yi L
2020-06-24  8:55 ` [PATCH v3 13/14] vfio: Document dual stage control Liu Yi L
2020-06-29  9:21   ` Stefan Hajnoczi
2020-06-29  9:24     ` Liu, Yi L
2020-06-24  8:55 ` [PATCH v3 14/14] 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=20200702151832.048b44d1@x1.home \
    --to=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=hao.wu@intel.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jean-philippe@linaro.org \
    --cc=jun.j.tian@intel.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yi.l.liu@intel.com \
    --cc=yi.y.sun@intel.com \
    --subject='Re: [PATCH v3 06/14] vfio/type1: Add VFIO_IOMMU_PASID_REQUEST (alloc/free)' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).