iommu/vt-d: Add bind guest PASID support

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@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200516062101.29541-5-baolu.lu@linux.intel.comSigned-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/intel-iommu.c

@@ -5780,6 +5780,10 @@ const struct iommu_ops intel_iommu_ops = {
 	.is_attach_deferred	= intel_iommu_is_attach_deferred,
 	.def_domain_type	= device_def_domain_type,
 	.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)

drivers/iommu/intel-svm.c

@@ -226,6 +226,206 @@ 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 *dmar_domain;
+	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))
+		return -ENOTSUPP;
+
+	/* VT-d supports devices with full 20 bit PASIDs only */
+	if (pci_max_pasids(to_pci_dev(dev)) != PASID_MAX)
+		return -EINVAL;
+
+	/*
+	 * We only check host PASID range, we have no knowledge to check
+	 * guest PASID range.
+	 */
+	if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
+		return -EINVAL;
+
+	dmar_domain = to_dmar_domain(domain);
+
+	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))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		for_each_svm_dev(sdev, svm, dev) {
+			/*
+			 * For devices with aux domains, we should allow
+			 * multiple bind calls with the same PASID and pdev.
+			 */
+			if (iommu_dev_feature_enabled(dev,
+						      IOMMU_DEV_FEAT_AUX)) {
+				sdev->users++;
+			} else {
+				dev_warn_ratelimited(dev,
+						     "Already bound with PASID %u\n",
+						     svm->pasid);
+				ret = -EBUSY;
+			}
+			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. We can drop the following line
+		 * once VFIO and IOASID set check is in place.
+		 */
+		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);
+		mmput(svm->mm);
+	}
+	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+	if (!sdev) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	sdev->dev = dev;
+
+	/* Only count users if device has aux domains */
+	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
+		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_ratelimited(dev, "Failed to enable PASID capability\n");
+		kfree(sdev);
+		goto out;
+	}
+
+	/*
+	 * PASID table is per device for better security. Therefore, for
+	 * each bind of a new device even with an existing PASID, we need to
+	 * call the nested mode setup function here.
+	 */
+	spin_lock(&iommu->lock);
+	ret = intel_pasid_setup_nested(iommu, dev, (pgd_t *)data->gpgd,
+				       data->hpasid, &data->vtd, dmar_domain,
+				       data->addr_width);
+	spin_unlock(&iommu->lock);
+	if (ret) {
+		dev_err_ratelimited(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.
+		 */
+		kfree(sdev);
+		goto out;
+	}
+
+	svm->flags |= SVM_FLAG_GUEST_MODE;
+
+	init_rcu_head(&sdev->rcu);
+	list_add_rcu(&sdev->list, &svm->devs);
+ out:
+	if (!IS_ERR_OR_NULL(svm) && list_empty(&svm->devs)) {
+		ioasid_set_data(data->hpasid, NULL);
+		kfree(svm);
+	}
+
+	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;
+		if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
+			sdev->users--;
+		if (!sdev->users) {
+			list_del_rcu(&sdev->list);
+			intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
+			intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
+			/* 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)) {
+				/*
+				 * We do not free the IOASID here in that
+				 * IOMMU driver did not allocate it.
+				 * Unlike native SVM, IOASID for guest use was
+				 * allocated prior to the bind call.
+				 * In any case, if the free call comes before
+				 * the unbind, IOMMU driver will get notified
+				 * and perform cleanup.
+				 */
+				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);

include/linux/intel-iommu.h

@@ -698,7 +698,9 @@ 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);
-
+int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			  struct iommu_gpasid_bind_data *data);
+int intel_svm_unbind_gpasid(struct device *dev, int pasid);
 struct svm_dev_ops;
 
 struct intel_svm_dev {
@@ -715,9 +717,11 @@ 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; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
 	struct list_head list;
 };

include/linux/intel-svm.h

@@ -44,6 +44,18 @@ 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 PASID bind is for guest
+ * processes. Compared to the host bind, the primary differences are:
+ * 1. mm life cycle management
+ * 2. fault reporting
+ */
+#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.
+ */
+#define SVM_FLAG_GUEST_PASID		(1<<3)
 
 #ifdef CONFIG_INTEL_IOMMU_SVM