LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
To: iommu@lists.linux-foundation.org,
	LKML <linux-kernel@vger.kernel.org>,
	Joerg Roedel <joro@8bytes.org>,
	David Woodhouse <dwmw2@infradead.org>,
	Eric Auger <eric.auger@redhat.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Cc: "Yi Liu" <yi.l.liu@intel.com>,
	"Tian, Kevin" <kevin.tian@intel.com>,
	Raj Ashok <ashok.raj@intel.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Lu Baolu" <baolu.lu@linux.intel.com>,
	Andriy Shevchenko <andriy.shevchenko@linux.intel.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Liu@vger.kernel.org, Yi L <yi.l.liu@linux.intel.com>
Subject: [PATCH v3 14/16] iommu/vt-d: Add bind guest PASID support
Date: Fri,  3 May 2019 15:32:15 -0700
Message-ID: <1556922737-76313-15-git-send-email-jacob.jun.pan@linux.intel.com> (raw)
In-Reply-To: <1556922737-76313-1-git-send-email-jacob.jun.pan@linux.intel.com>

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   | 175 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/intel-iommu.h |  10 ++-
 include/linux/intel-svm.h   |   7 ++
 4 files changed, 194 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1316c96..a10cb70 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5770,6 +5770,10 @@ const struct iommu_ops intel_iommu_ops = {
 	.dev_enable_feat	= intel_iommu_dev_enable_feat,
 	.dev_disable_feat	= intel_iommu_dev_disable_feat,
 	.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_g4x_gfx(struct pci_dev *dev)
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 068dd9e..0815615 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -231,6 +231,181 @@ static LIST_HEAD(global_svm_list);
 	list_for_each_entry(sdev, &svm->devs, list)	\
 	if (dev == sdev->dev)				\
 
+int intel_svm_bind_gpasid(struct iommu_domain *domain,
+			struct device *dev,
+			struct gpasid_bind_data *data)
+{
+	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_svm_dev *sdev;
+	struct intel_svm *svm = NULL;
+	struct dmar_domain *ddomain;
+	int ret = 0;
+
+	if (WARN_ON(!iommu) || !data)
+		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;
+	}
+
+	if (data->pasid <= 0 || data->pasid >= PASID_MAX)
+		return -EINVAL;
+
+	ddomain = to_dmar_domain(domain);
+	/* REVISIT:
+	 * Sanity check adddress width and paging mode support
+	 * width matching in two dimensions:
+	 * 1. paging mode CPU <= IOMMU
+	 * 2. address width Guest <= Host.
+	 */
+	mutex_lock(&pasid_mutex);
+	svm = ioasid_find(NULL, data->pasid, 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.
+		 */
+		BUG_ON(list_empty(&svm->devs));
+
+		for_each_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++;
+			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->pasid;
+		refcount_set(&svm->refs, 0);
+		ioasid_set_data(data->pasid, svm);
+		INIT_LIST_HEAD_RCU(&svm->devs);
+		INIT_LIST_HEAD(&svm->list);
+
+		mmput(svm->mm);
+	}
+	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+	if (!sdev) {
+		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);
+		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->gcr3,
+				data->pasid,
+				data->flags,
+				ddomain,
+				data->addr_width);
+	if (ret) {
+		dev_err(dev, "Failed to set up PASID %d in nested mode, Err %d\n",
+			data->pasid, ret);
+		kfree(sdev);
+		goto out;
+	}
+	svm->flags |= SVM_FLAG_GUEST_MODE;
+
+	init_rcu_head(&sdev->rcu);
+	refcount_inc(&svm->refs);
+	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_svm_dev *sdev;
+	struct intel_iommu *iommu;
+	struct intel_svm *svm;
+	int ret = -EINVAL;
+
+	mutex_lock(&pasid_mutex);
+	iommu = intel_svm_device_to_iommu(dev);
+	if (!iommu)
+		goto out;
+
+	svm = ioasid_find(NULL, pasid, NULL);
+	if (IS_ERR(svm)) {
+		ret = PTR_ERR(svm);
+		goto out;
+	}
+
+	if (!svm)
+		goto out;
+
+	for_each_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 live.
+			 * intel_svm_drain_prq(dev, pasid);
+			 */
+			kfree_rcu(sdev, rcu);
+
+			if (list_empty(&svm->devs)) {
+				list_del(&svm->list);
+				kfree(svm);
+				/*
+				 * 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);
+			}
+		}
+		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 48fa164..774f368 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -677,7 +677,9 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
 int intel_svm_init(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 gpasid_bind_data *data);
+extern int intel_svm_unbind_gpasid(struct device *dev, int pasid);
 struct svm_dev_ops;
 
 struct intel_svm_dev {
@@ -693,12 +695,16 @@ struct intel_svm_dev {
 
 struct intel_svm {
 	struct mmu_notifier notifier;
-	struct mm_struct *mm;
+	union {
+		struct mm_struct *mm;
+		u64 gcr3;
+	};
 	struct intel_iommu *iommu;
 	int flags;
 	int pasid;
 	struct list_head devs;
 	struct list_head list;
+	refcount_t refs; /* Number of devices sharing this PASID */
 };
 
 extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev);
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index e3f7631..34b0a3b 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -52,6 +52,13 @@ 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)
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 
-- 
2.7.4


  parent reply index

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-03 22:32 [PATCH v3 00/16] Shared virtual address IOMMU and VT-d support Jacob Pan
2019-05-03 22:32 ` [PATCH v3 01/16] iommu: Introduce attach/detach_pasid_table API Jacob Pan
2019-05-03 22:32 ` [PATCH v3 02/16] iommu: Introduce cache_invalidate API Jacob Pan
2019-05-13  9:14   ` Auger Eric
2019-05-13 11:20     ` Jean-Philippe Brucker
2019-05-13 16:50       ` Auger Eric
2019-05-13 17:09         ` Jean-Philippe Brucker
2019-05-13 22:16           ` Jacob Pan
2019-05-14  7:36             ` Auger Eric
2019-05-14 10:41               ` Jean-Philippe Brucker
2019-05-14 17:44                 ` Jacob Pan
2019-05-14 17:57                   ` Jacob Pan
2019-05-15 11:03                   ` Jean-Philippe Brucker
2019-05-15 14:47                     ` Tian, Kevin
2019-05-15 15:25                       ` Jean-Philippe Brucker
2019-05-14  7:46           ` Auger Eric
2019-05-14 10:42             ` Jean-Philippe Brucker
2019-05-14 11:02               ` Auger Eric
2019-05-14 17:55                 ` Jacob Pan
2019-05-15 15:52                   ` Jean-Philippe Brucker
2019-05-15 16:25                     ` Jacob Pan
2019-05-03 22:32 ` [PATCH v3 03/16] iommu: Add I/O ASID allocator Jacob Pan
2019-05-21  8:21   ` Auger Eric
2019-05-21 17:03     ` Jacob Pan
2019-05-22 12:19       ` Jean-Philippe Brucker
2019-05-21  9:41   ` Auger Eric
2019-05-21 17:05     ` Jacob Pan
2019-05-03 22:32 ` [PATCH v3 04/16] ioasid: Add custom IOASID allocator Jacob Pan
2019-05-21  9:55   ` Auger Eric
2019-05-22 19:42     ` Jacob Pan
2019-05-23  7:14       ` Auger Eric
2019-05-23 15:40         ` Jacob Pan
2019-05-03 22:32 ` [PATCH v3 05/16] iommu/vt-d: Enlightened PASID allocation Jacob Pan
2019-05-03 22:32 ` [PATCH v3 06/16] iommu/vt-d: Add custom allocator for IOASID Jacob Pan
2019-05-03 22:32 ` [PATCH v3 07/16] iommu/vtd: Optimize tlb invalidation for vIOMMU Jacob Pan
2019-05-03 22:32 ` [PATCH v3 08/16] iommu/vt-d: Replace Intel specific PASID allocator with IOASID Jacob Pan
2019-05-03 22:32 ` [PATCH v3 09/16] iommu: Introduce guest PASID bind function Jacob Pan
2019-05-16 14:14   ` Jean-Philippe Brucker
2019-05-16 16:14     ` Jacob Pan
2019-05-20 19:22       ` Jacob Pan
2019-05-21 16:09         ` Jean-Philippe Brucker
2019-05-21 22:50           ` Jacob Pan
2019-05-22 15:05             ` Jean-Philippe Brucker
2019-05-22 17:15               ` Jacob Pan
2019-05-03 22:32 ` [PATCH v3 10/16] iommu/vt-d: Move domain helper to header Jacob Pan
2019-05-03 22:32 ` [PATCH v3 11/16] iommu/vt-d: Avoid duplicated code for PASID setup Jacob Pan
2019-05-03 22:32 ` [PATCH v3 12/16] iommu/vt-d: Add nested translation helper function Jacob Pan
2019-05-03 22:32 ` [PATCH v3 13/16] iommu/vt-d: Clean up for SVM device list Jacob Pan
2019-05-03 22:32 ` Jacob Pan [this message]
2019-05-03 22:32 ` [PATCH v3 15/16] iommu/vt-d: Support flushing more translation cache types Jacob Pan
2019-05-03 22:32 ` [PATCH v3 16/16] iommu/vt-d: Add svm/sva invalidate function Jacob Pan
2019-05-15 16:31 ` [PATCH v3 00/16] Shared virtual address IOMMU and VT-d support Jacob Pan

Reply instructions:

You may reply publically 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=1556922737-76313-15-git-send-email-jacob.jun.pan@linux.intel.com \
    --to=jacob.jun.pan@linux.intel.com \
    --cc=Liu@vger.kernel.org \
    --cc=alex.williamson@redhat.com \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=ashok.raj@intel.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=dwmw2@infradead.org \
    --cc=eric.auger@redhat.com \
    --cc=hch@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jean-philippe.brucker@arm.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yi.l.liu@intel.com \
    --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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lkml.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lkml.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lkml.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lkml.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lkml.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lkml.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lkml.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lkml.kernel.org/lkml/7 lkml/git/7.git

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

Example config snippet for mirrors

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


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