IOMMU Archive on lore.kernel.org
 help / color / Atom feed
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
To: Lu Baolu <baolu.lu@linux.intel.com>
Cc: Yi L <yi.l.liu@linux.intel.com>,
	"Tian, Kevin" <kevin.tian@intel.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Raj Ashok <ashok.raj@intel.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.com>,
	LKML <linux-kernel@vger.kernel.org>,
	iommu@lists.linux-foundation.org,
	David Woodhouse <dwmw2@infradead.org>,
	Jonathan Cameron <jic23@kernel.org>
Subject: Re: [PATCH V9 04/10] iommu/vt-d: Add bind guest PASID support
Date: Fri, 31 Jan 2020 13:48:52 -0800
Message-ID: <20200131134852.626cc18f@jacob-builder> (raw)
In-Reply-To: <4961a1af-adc3-3ef5-fb93-7f25955c9af3@linux.intel.com>

Hi Baolu,
Thanks for the review, my comments inline.

On Thu, 30 Jan 2020 15:22:09 +0800
Lu Baolu <baolu.lu@linux.intel.com> wrote:

> Hi Jacob,
> 
> On 2020/1/29 14:01, Jacob Pan wrote:
> > When supporting guest SVA with emulated IOMMU, the guest PASID
> > table is shadowed in VMM. Updates to guest vIOMMU PASID table
> > will result in PASID cache flush which will be passed down to
> > the host as bind guest PASID calls.
> > 
> > For the SL page tables, it will be harvested from device's
> > default domain (request w/o PASID), or aux domain in case of
> > mediated device.
> > 
> >      .-------------.  .---------------------------.
> >      |   vIOMMU    |  | Guest process CR3, FL only|
> >      |             |  '---------------------------'
> >      .----------------/
> >      | PASID Entry |--- PASID cache flush -
> >      '-------------'                       |
> >      |             |                       V
> >      |             |                CR3 in GPA
> >      '-------------'
> > Guest
> > ------| Shadow |--------------------------|--------
> >        v        v                          v
> > Host
> >      .-------------.  .----------------------.
> >      |   pIOMMU    |  | Bind FL for GVA-GPA  |
> >      |             |  '----------------------'
> >      .----------------/  |
> >      | PASID Entry |     V (Nested xlate)
> >      '----------------\.------------------------------.
> >      |             |   |SL for GPA-HPA, default domain|
> >      |             |   '------------------------------'
> >      '-------------'
> > Where:
> >   - FL = First level/stage one page tables
> >   - SL = Second level/stage two page tables
> > 
> > Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> > Signed-off-by: Liu, Yi L <yi.l.liu@linux.intel.com>
> > ---
> >   drivers/iommu/intel-iommu.c |   4 +
> >   drivers/iommu/intel-svm.c   | 223
> > ++++++++++++++++++++++++++++++++++++++++++++
> > include/linux/intel-iommu.h |   8 +- include/linux/intel-svm.h   |
> > 17 ++++ 4 files changed, 251 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/iommu/intel-iommu.c
> > b/drivers/iommu/intel-iommu.c index 15fdd0915018..8a4136e805ac
> > 100644 --- a/drivers/iommu/intel-iommu.c
> > +++ b/drivers/iommu/intel-iommu.c
> > @@ -6182,6 +6182,10 @@ const struct iommu_ops intel_iommu_ops = {
> >   	.dev_disable_feat	= intel_iommu_dev_disable_feat,
> >   	.is_attach_deferred	=
> > intel_iommu_is_attach_deferred, .pgsize_bitmap		=
> > INTEL_IOMMU_PGSIZES, +#ifdef CONFIG_INTEL_IOMMU_SVM
> > +	.sva_bind_gpasid	= intel_svm_bind_gpasid,
> > +	.sva_unbind_gpasid	= intel_svm_unbind_gpasid,
> > +#endif
> >   };
> >   
> >   static void quirk_iommu_igfx(struct pci_dev *dev)
> > diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
> > index d7f2a5358900..7a87d2e2e0ad 100644
> > --- a/drivers/iommu/intel-svm.c
> > +++ b/drivers/iommu/intel-svm.c
> > @@ -226,6 +226,229 @@ static LIST_HEAD(global_svm_list);
> >   	list_for_each_entry((sdev), &(svm)->devs, list)	\
> >   		if ((d) != (sdev)->dev) {} else
> >   
> > +int intel_svm_bind_gpasid(struct iommu_domain *domain,
> > +			struct device *dev,
> > +			struct iommu_gpasid_bind_data *data)
> > +{
> > +	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
> > +	struct dmar_domain *ddomain;
> > +	struct intel_svm_dev *sdev;
> > +	struct intel_svm *svm;
> > +	int ret = 0;
> > +
> > +	if (WARN_ON(!iommu) || !data)
> > +		return -EINVAL;
> > +
> > +	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
> > +	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
> > +		return -EINVAL;
> > +
> > +	if (dev_is_pci(dev)) {
> > +		/* VT-d supports devices with full 20 bit PASIDs
> > only */
> > +		if (pci_max_pasids(to_pci_dev(dev)) != PASID_MAX)
> > +			return -EINVAL;
> > +	} else {
> > +		return -ENOTSUPP;
> > +	}
> > +
> > +	/*
> > +	 * We only check host PASID range, we have no knowledge to
> > check
> > +	 * guest PASID range nor do we use the guest PASID.
> > +	 */
> > +	if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
> > +		return -EINVAL;
> > +
> > +	ddomain = to_dmar_domain(domain);
> > +
> > +	/* Sanity check paging mode support match between host and
> > guest */
> > +	if (data->addr_width == ADDR_WIDTH_5LEVEL &&
> > +	    !cap_5lp_support(iommu->cap)) {
> > +		pr_err("Cannot support 5 level paging requested by
> > guest!\n");
> > +		return -EINVAL;
> > +	}
> > +
> > +	mutex_lock(&pasid_mutex);
> > +	svm = ioasid_find(NULL, data->hpasid, NULL);
> > +	if (IS_ERR(svm)) {
> > +		ret = PTR_ERR(svm);
> > +		goto out;
> > +	}
> > +
> > +	if (svm) {
> > +		/*
> > +		 * If we found svm for the PASID, there must be at
> > +		 * least one device bond, otherwise svm should be
> > freed.
> > +		 */
> > +		if (WARN_ON(list_empty(&svm->devs)))
> > +			return -EINVAL;  
> 
> goto out; otherwise, lock will still be hold.
yes, will fix
> 
> > +
> > +		if (svm->mm == get_task_mm(current) &&
> > +		    data->hpasid == svm->pasid &&
> > +		    data->gpasid == svm->gpasid) {
> > +			pr_warn("Cannot bind the same guest-host
> > PASID for the same process\n");
> > +			mmput(svm->mm);
> > +			return -EINVAL;  
> 
> The same here.
> 
ditto. thanks
> > +		}
> > + 
> > +		for_each_svm_dev(sdev, svm, dev) {
> > +			/* In case of multiple sub-devices of the
> > same pdev
> > +			 * assigned, we should allow multiple bind
> > calls with
> > +			 * the same PASID and pdev.
> > +			 */
> > +			sdev->users++;  
> 
> Need mmput() before goto out?
> 
Yes, I will add mmput(current->mm); before for_each_svm_dev()
> > +			goto out;
> > +		}
> > +	} else {
> > +		/* We come here when PASID has never been bond to
> > a device. */
> > +		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
> > +		if (!svm) {
> > +			ret = -ENOMEM;
> > +			goto out;
> > +		}
> > +		/* REVISIT: upper layer/VFIO can track host
> > process that bind the PASID.
> > +		 * ioasid_set = mm might be sufficient for vfio to
> > check pasid VMM
> > +		 * ownership.
> > +		 */
> > +		svm->mm = get_task_mm(current);
> > +		svm->pasid = data->hpasid;
> > +		if (data->flags & IOMMU_SVA_GPASID_VAL) {
> > +			svm->gpasid = data->gpasid;
> > +			svm->flags |= SVM_FLAG_GUEST_PASID;
> > +		}
> > +		ioasid_set_data(data->hpasid, svm);
> > +		INIT_LIST_HEAD_RCU(&svm->devs);
> > +		INIT_LIST_HEAD(&svm->list);
> > +
> > +		mmput(svm->mm);
> > +	}
> > +	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
> > +	if (!sdev) {
> > +		if (list_empty(&svm->devs)) {
> > +			ioasid_set_data(data->hpasid, NULL);
> > +			kfree(svm);
> > +		}
> > +		ret = -ENOMEM;
> > +		goto out;
> > +	}
> > +	sdev->dev = dev;
> > +	sdev->users = 1;
> > +
> > +	/* Set up device context entry for PASID if not enabled
> > already */
> > +	ret = intel_iommu_enable_pasid(iommu, sdev->dev);
> > +	if (ret) {
> > +		dev_err(dev, "Failed to enable PASID
> > capability\n");
> > +		kfree(sdev);
> > +		/*
> > +		 * If this this a new PASID that never bond to a
> > device, then
> > +		 * the device list must be empty which indicates
> > struct svm
> > +		 * was allocated in this function.
> > +		 */
> > +		if (list_empty(&svm->devs)) {
> > +			ioasid_set_data(data->hpasid, NULL);
> > +			kfree(svm);
> > +		}
> > +		goto out;
> > +	}
> > +
> > +	/*
> > +	 * For guest bind, we need to set up PASID table entry as
> > follows:
> > +	 * - FLPM matches guest paging mode
> > +	 * - turn on nested mode
> > +	 * - SL guest address width matching
> > +	 */
> > +	ret = intel_pasid_setup_nested(iommu,
> > +				       dev,
> > +				       (pgd_t *)data->gpgd,
> > +				data->hpasid,
> > +				&data->vtd,
> > +				ddomain,
> > +				data->addr_width);  
> 
> Parameter alignment.
> 
will fix.

> > +	if (ret) {
> > +		dev_err(dev, "Failed to set up PASID %llu in
> > nested mode, Err %d\n",
> > +			data->hpasid, ret);
> > +		/*
> > +		 * PASID entry should be in cleared state if
> > nested mode
> > +		 * set up failed. So we only need to clear IOASID
> > tracking
> > +		 * data such that free call will succeed.
> > +		 */
> > +		ioasid_set_data(data->hpasid, NULL);  
> 
> Will this impact other devices sharing the same data->hpasid?
> 
Good point, it would impact other devices. IOASID data should be
cleared only after the svm->devs list is empty. Will move this line
below.
> > +		kfree(sdev);
> > +		if (list_empty(&svm->devs))
ioasid_set_data(data->hpasid, NULL);

> > +			kfree(svm);
> > +
> > +		goto out;
> > +	}
> > +	svm->flags |= SVM_FLAG_GUEST_MODE;
> > +
> > +	init_rcu_head(&sdev->rcu);
> > +	list_add_rcu(&sdev->list, &svm->devs);
> > + out:
> > +	mutex_unlock(&pasid_mutex);
> > +	return ret;
> > +}
> > +
> > +int intel_svm_unbind_gpasid(struct device *dev, int pasid)
> > +{
> > +	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
> > +	struct intel_svm_dev *sdev;
> > +	struct intel_svm *svm;
> > +	int ret = -EINVAL;
> > +
> > +	if (WARN_ON(!iommu))
> > +		return -EINVAL;
> > +
> > +	mutex_lock(&pasid_mutex);
> > +	svm = ioasid_find(NULL, pasid, NULL);
> > +	if (!svm) {
> > +		ret = -EINVAL;
> > +		goto out;
> > +	}
> > +
> > +	if (IS_ERR(svm)) {
> > +		ret = PTR_ERR(svm);
> > +		goto out;
> > +	}
> > +
> > +	for_each_svm_dev(sdev, svm, dev) {
> > +		ret = 0;
> > +		sdev->users--;
> > +		if (!sdev->users) {
> > +			list_del_rcu(&sdev->list);
> > +			intel_pasid_tear_down_entry(iommu, dev,
> > svm->pasid);
> > +			/* TODO: Drain in flight PRQ for the PASID
> > since it
> > +			 * may get reused soon, we don't want to
> > +			 * confuse with its previous life.
> > +			 * intel_svm_drain_prq(dev, pasid);
> > +			 */
> > +			kfree_rcu(sdev, rcu);
> > +
> > +			if (list_empty(&svm->devs)) {
> > +				list_del(&svm->list);  
> 
> It seems that you forgot adding above new allocated svm into
> global_svm_list list?
> 
IOASID xarray keeps track of all PASIDs, we don't need intel specific
svm list.

I should delete this line and list init code. It was there before we
have the IOASID common code.

Great point, as a clean up, I think we should have removed the global
svm list and convert global_svm_list search with ioasid_find. Of
course, intel_svm->list is not needed after that.

> > +				/*
> > +				 * We do not free PASID here until
> > explicit call
> > +				 * from VFIO to free. The PASID
> > life cycle
> > +				 * management is largely tied to
> > VFIO management
> > +				 * of assigned device life cycles.
> > In case of
> > +				 * guest exit without a explicit
> > free PASID call,
> > +				 * the responsibility lies in VFIO
> > layer to free
> > +				 * the PASIDs allocated for the
> > guest.
> > +				 * For security reasons, VFIO has
> > to track the
> > +				 * PASID ownership per guest
> > anyway to ensure
> > +				 * that PASID allocated by one
> > guest cannot be
> > +				 * used by another.
> > +				 */
> > +				ioasid_set_data(pasid, NULL);
> > +				kfree(svm);
> > +			}
> > +		}
> > +		break;
> > +	}
> > +out:
> > +	mutex_unlock(&pasid_mutex);
> > +
> > +	return ret;
> > +}
> > +
> >   int intel_svm_bind_mm(struct device *dev, int *pasid, int flags,
> > struct svm_dev_ops *ops) {
> >   	struct intel_iommu *iommu =
> > intel_svm_device_to_iommu(dev); diff --git
> > a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index
> > c8abf051b2d5..b0ffecbc0dfc 100644 --- a/include/linux/intel-iommu.h
> > +++ b/include/linux/intel-iommu.h
> > @@ -679,7 +679,9 @@ struct dmar_domain *find_domain(struct device
> > *dev); extern void intel_svm_check(struct intel_iommu *iommu);
> >   extern int intel_svm_enable_prq(struct intel_iommu *iommu);
> >   extern int intel_svm_finish_prq(struct intel_iommu *iommu);
> > -
> > +extern int intel_svm_bind_gpasid(struct iommu_domain *domain,
> > +		struct device *dev, struct iommu_gpasid_bind_data
> > *data); +extern int intel_svm_unbind_gpasid(struct device *dev, int
> > pasid); struct svm_dev_ops;
> >   
> >   struct intel_svm_dev {
> > @@ -696,9 +698,13 @@ struct intel_svm_dev {
> >   struct intel_svm {
> >   	struct mmu_notifier notifier;
> >   	struct mm_struct *mm;
> > +
> >   	struct intel_iommu *iommu;
> >   	int flags;
> >   	int pasid;
> > +	int gpasid; /* Guest PASID in case of vSVA bind with
> > non-identity host
> > +		     * to guest PASID mapping.
> > +		     */
> >   	struct list_head devs;
> >   	struct list_head list;
> >   };
> > diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
> > index 94f047a8a845..a2c189ad0b01 100644
> > --- a/include/linux/intel-svm.h
> > +++ b/include/linux/intel-svm.h
> > @@ -44,6 +44,23 @@ struct svm_dev_ops {
> >    * do such IOTLB flushes automatically.
> >    */
> >   #define SVM_FLAG_SUPERVISOR_MODE	(1<<1)
> > +/*
> > + * The SVM_FLAG_GUEST_MODE flag is used when a guest process bind
> > to a device.
> > + * In this case the mm_struct is in the guest kernel or userspace,
> > its life
> > + * cycle is managed by VMM and VFIO layer. For IOMMU driver, this
> > API provides
> > + * means to bind/unbind guest CR3 with PASIDs allocated for a
> > device.
> > + */
> > +#define SVM_FLAG_GUEST_MODE	(1<<2)
> > +/*
> > + * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own
> > PASID space,
> > + * which requires guest and host PASID translation at both
> > directions. We keep
> > + * track of guest PASID in order to provide lookup service to
> > device drivers.
> > + * One such example is a physical function (PF) driver that
> > supports mediated
> > + * device (mdev) assignment. Guest programming of mdev
> > configuration space can
> > + * only be done with guest PASID, therefore PF driver needs to
> > find the matching
> > + * host PASID to program the real hardware.
> > + */
> > +#define SVM_FLAG_GUEST_PASID	(1<<3)
> >   
> >   #ifdef CONFIG_INTEL_IOMMU_SVM
> >   
> >   
> 
> Best regards,
> baolu

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

  reply index

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-29  6:01 [PATCH V9 00/10] Nested Shared Virtual Address (SVA) VT-d support Jacob Pan
2020-01-29  6:01 ` [PATCH V9 01/10] iommu/vt-d: Move domain helper to header Jacob Pan
2020-01-29  6:01 ` [PATCH V9 02/10] iommu/uapi: Define a mask for bind data Jacob Pan
2020-02-12 12:43   ` Auger Eric
2020-03-20 21:35     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 03/10] iommu/vt-d: Add nested translation helper function Jacob Pan
2020-02-12 12:43   ` Auger Eric
2020-02-24 22:55     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 04/10] iommu/vt-d: Add bind guest PASID support Jacob Pan
2020-01-30  7:22   ` Lu Baolu
2020-01-31 21:48     ` Jacob Pan [this message]
2020-01-29  6:01 ` [PATCH V9 05/10] iommu/vt-d: Support flushing more translation cache types Jacob Pan
2020-02-12 12:55   ` Auger Eric
2020-02-14 23:27     ` Jacob Pan
2020-02-25  8:32       ` Auger Eric
2020-01-29  6:01 ` [PATCH V9 06/10] iommu/vt-d: Add svm/sva invalidate function Jacob Pan
2020-02-12 13:13   ` Auger Eric
2020-02-14 23:48     ` Jacob Pan
2020-02-21  6:34   ` Liu, Yi L
2020-02-21 19:08     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 07/10] iommu/vt-d: Cache virtual command capability register Jacob Pan
2020-02-12 13:00   ` Auger Eric
2020-02-21 20:20     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 08/10] iommu/vt-d: Enlightened PASID allocation Jacob Pan
2020-01-29  6:01 ` [PATCH V9 09/10] iommu/vt-d: Add custom allocator for IOASID Jacob Pan
2020-01-29  6:01 ` [PATCH V9 10/10] iommu/vt-d: Report PASID format as domain attribute Jacob Pan
2020-01-30  7:54   ` Lu Baolu
2020-02-04  5:43     ` Jacob Pan
2020-01-29 12:18 ` [PATCH V9 00/10] Nested Shared Virtual Address (SVA) VT-d support 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=20200131134852.626cc18f@jacob-builder \
    --to=jacob.jun.pan@linux.intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=dwmw2@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jean-philippe@linaro.com \
    --cc=jic23@kernel.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yi.l.liu@linux.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

IOMMU Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-iommu/0 linux-iommu/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 linux-iommu linux-iommu/ https://lore.kernel.org/linux-iommu \
		iommu@lists.linux-foundation.org
	public-inbox-index linux-iommu

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.linux-foundation.lists.iommu


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