[PATCH v9 1/3] vfio/mdev: Add iommu related member in mdev_device

[PATCH v9 1/3] vfio/mdev: Add iommu related member in mdev_device

[Lu Baolu]

A parent device might create different types of mediated
devices. For example, a mediated device could be created
by the parent device with full isolation and protection
provided by the IOMMU. One usage case could be found on
Intel platforms where a mediated device is an assignable
subset of a PCI, the DMA requests on behalf of it are all
tagged with a PASID. Since IOMMU supports PASID-granular
translations (scalable mode in VT-d 3.0), this mediated
device could be individually protected and isolated by an
IOMMU.

This patch adds a new member in the struct mdev_device to
indicate that the mediated device represented by mdev could
be isolated and protected by attaching a domain to a device
represented by mdev->iommu_device. It also adds a helper to
add or set the iommu device.

* mdev_device->iommu_device
  - This, if set, indicates that the mediated device could
    be fully isolated and protected by IOMMU via attaching
    an iommu domain to this device. If empty, it indicates
    using vendor defined isolation, hence bypass IOMMU.

* mdev_set/get_iommu_device(dev, iommu_device)
  - Set or get the iommu device which represents this mdev
    in IOMMU's device scope. Drivers don't need to set the
    iommu device if it uses vendor defined isolation.

Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Liu Yi L <yi.l.liu@intel.com>
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/mdev/mdev_core.c    | 18 ++++++++++++++++++
 drivers/vfio/mdev/mdev_private.h |  1 +
 include/linux/mdev.h             | 14 ++++++++++++++
 3 files changed, 33 insertions(+)

diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index 9d29c71bcf99..318959a994e4 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -396,6 +396,24 @@ int mdev_device_remove(struct device *dev, bool force_remove)
 	return 0;
 }
 
+int mdev_set_iommu_device(struct device *dev, struct device *iommu_device)
+{
+	struct mdev_device *mdev = to_mdev_device(dev);
+
+	mdev->iommu_device = iommu_device;
+
+	return 0;
+}
+EXPORT_SYMBOL(mdev_set_iommu_device);
+
+struct device *mdev_get_iommu_device(struct device *dev)
+{
+	struct mdev_device *mdev = to_mdev_device(dev);
+
+	return mdev->iommu_device;
+}
+EXPORT_SYMBOL(mdev_get_iommu_device);
+
 static int __init mdev_init(void)
 {
 	return mdev_bus_register();
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index 379758c52b1b..f4eba723fea5 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -33,6 +33,7 @@ struct mdev_device {
 	struct kref ref;
 	struct list_head next;
 	struct kobject *type_kobj;
+	struct device *iommu_device;
 	bool active;
 };
 
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 12354ab4164a..f4a88a6dd054 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -15,6 +15,20 @@
 
 struct mdev_device;
 
+/*
+ * Called by the parent device driver to set the device which represents
+ * this mdev in iommu protection scope. By default, the iommu device is
+ * NULL, that indicates using vendor defined isolation.
+ *
+ * @dev: the mediated device that iommu will isolate.
+ * @iommu_device: a pci device which represents the iommu for @dev.
+ *
+ * Return 0 for success, otherwise negative error value.
+ */
+int mdev_set_iommu_device(struct device *dev, struct device *iommu_device);
+
+struct device *mdev_get_iommu_device(struct device *dev);
+
 /**
  * struct mdev_parent_ops - Structure to be registered for each parent device to
  * register the device to mdev module.
-- 
2.17.1

[PATCH v9 2/3] vfio/type1: Add domain at(de)taching group helpers

[Lu Baolu]

This adds helpers to attach or detach a domain to a
group. This will replace iommu_attach_group() which
only works for non-mdev devices.

If a domain is attaching to a group which includes the
mediated devices, it should attach to the iommu device
(a pci device which represents the mdev in iommu scope)
instead. The added helper supports attaching domain to
groups for both pci and mdev devices.

Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 84 ++++++++++++++++++++++++++++++---
 1 file changed, 77 insertions(+), 7 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index d0f731c9920a..c956b85264ae 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -97,6 +97,7 @@ struct vfio_dma {
 struct vfio_group {
 	struct iommu_group	*iommu_group;
 	struct list_head	next;
+	bool			mdev_group;	/* An mdev group */
 };
 
 /*
@@ -1311,6 +1312,75 @@ static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base)
 	return ret;
 }
 
+static struct device *vfio_mdev_get_iommu_device(struct device *dev)
+{
+	struct device *(*fn)(struct device *dev);
+	struct device *iommu_device;
+
+	fn = symbol_get(mdev_get_iommu_device);
+	if (fn) {
+		iommu_device = fn(dev);
+		symbol_put(mdev_get_iommu_device);
+
+		return iommu_device;
+	}
+
+	return NULL;
+}
+
+static int vfio_mdev_attach_domain(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+	struct device *iommu_device;
+
+	iommu_device = vfio_mdev_get_iommu_device(dev);
+	if (iommu_device) {
+		if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
+			return iommu_aux_attach_device(domain, iommu_device);
+		else
+			return iommu_attach_device(domain, iommu_device);
+	}
+
+	return -EINVAL;
+}
+
+static int vfio_mdev_detach_domain(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+	struct device *iommu_device;
+
+	iommu_device = vfio_mdev_get_iommu_device(dev);
+	if (iommu_device) {
+		if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
+			iommu_aux_detach_device(domain, iommu_device);
+		else
+			iommu_detach_device(domain, iommu_device);
+	}
+
+	return 0;
+}
+
+static int vfio_iommu_attach_group(struct vfio_domain *domain,
+				   struct vfio_group *group)
+{
+	if (group->mdev_group)
+		return iommu_group_for_each_dev(group->iommu_group,
+						domain->domain,
+						vfio_mdev_attach_domain);
+	else
+		return iommu_attach_group(domain->domain, group->iommu_group);
+}
+
+static void vfio_iommu_detach_group(struct vfio_domain *domain,
+				    struct vfio_group *group)
+{
+	if (group->mdev_group)
+		iommu_group_for_each_dev(group->iommu_group, domain->domain,
+					 vfio_mdev_detach_domain);
+	else
+		iommu_detach_group(domain->domain, group->iommu_group);
+}
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
@@ -1386,7 +1456,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 			goto out_domain;
 	}
 
-	ret = iommu_attach_group(domain->domain, iommu_group);
+	ret = vfio_iommu_attach_group(domain, group);
 	if (ret)
 		goto out_domain;
 
@@ -1418,8 +1488,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		if (d->domain->ops == domain->domain->ops &&
 		    d->prot == domain->prot) {
-			iommu_detach_group(domain->domain, iommu_group);
-			if (!iommu_attach_group(d->domain, iommu_group)) {
+			vfio_iommu_detach_group(domain, group);
+			if (!vfio_iommu_attach_group(d, group)) {
 				list_add(&group->next, &d->group_list);
 				iommu_domain_free(domain->domain);
 				kfree(domain);
@@ -1427,7 +1497,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 				return 0;
 			}
 
-			ret = iommu_attach_group(domain->domain, iommu_group);
+			ret = vfio_iommu_attach_group(domain, group);
 			if (ret)
 				goto out_domain;
 		}
@@ -1453,7 +1523,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	return 0;
 
 out_detach:
-	iommu_detach_group(domain->domain, iommu_group);
+	vfio_iommu_detach_group(domain, group);
 out_domain:
 	iommu_domain_free(domain->domain);
 out_free:
@@ -1544,7 +1614,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		if (!group)
 			continue;
 
-		iommu_detach_group(domain->domain, iommu_group);
+		vfio_iommu_detach_group(domain, group);
 		list_del(&group->next);
 		kfree(group);
 		/*
@@ -1610,7 +1680,7 @@ static void vfio_release_domain(struct vfio_domain *domain, bool external)
 	list_for_each_entry_safe(group, group_tmp,
 				 &domain->group_list, next) {
 		if (!external)
-			iommu_detach_group(domain->domain, group->iommu_group);
+			vfio_iommu_detach_group(domain, group);
 		list_del(&group->next);
 		kfree(group);
 	}
-- 
2.17.1

[PATCH v9 3/3] vfio/type1: Handle different mdev isolation type

[Lu Baolu]

This adds the support to determine the isolation type
of a mediated device group by checking whether it has
an iommu device. If an iommu device exists, an iommu
domain will be allocated and then attached to the iommu
device. Otherwise, keep the same behavior as it is.

Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 55 +++++++++++++++++++++++++--------
 1 file changed, 42 insertions(+), 13 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c956b85264ae..3be1db3501cc 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -565,7 +565,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 	mutex_lock(&iommu->lock);
 
 	/* Fail if notifier list is empty */
-	if ((!iommu->external_domain) || (!iommu->notifier.head)) {
+	if (!iommu->notifier.head) {
 		ret = -EINVAL;
 		goto pin_done;
 	}
@@ -647,11 +647,6 @@ static int vfio_iommu_type1_unpin_pages(void *iommu_data,
 
 	mutex_lock(&iommu->lock);
 
-	if (!iommu->external_domain) {
-		mutex_unlock(&iommu->lock);
-		return -EINVAL;
-	}
-
 	do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu);
 	for (i = 0; i < npage; i++) {
 		struct vfio_dma *dma;
@@ -1381,13 +1376,40 @@ static void vfio_iommu_detach_group(struct vfio_domain *domain,
 		iommu_detach_group(domain->domain, group->iommu_group);
 }
 
+static bool vfio_bus_is_mdev(struct bus_type *bus)
+{
+	struct bus_type *mdev_bus;
+	bool ret = false;
+
+	mdev_bus = symbol_get(mdev_bus_type);
+	if (mdev_bus) {
+		ret = (bus == mdev_bus);
+		symbol_put(mdev_bus_type);
+	}
+
+	return ret;
+}
+
+static int vfio_mdev_iommu_device(struct device *dev, void *data)
+{
+	struct device **old = data, *new;
+
+	new = vfio_mdev_get_iommu_device(dev);
+	if (!new || (*old && *old != new))
+		return -EINVAL;
+
+	*old = new;
+
+	return 0;
+}
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_group *group;
 	struct vfio_domain *domain, *d;
-	struct bus_type *bus = NULL, *mdev_bus;
+	struct bus_type *bus = NULL;
 	int ret;
 	bool resv_msi, msi_remap;
 	phys_addr_t resv_msi_base;
@@ -1422,23 +1444,30 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_free;
 
-	mdev_bus = symbol_get(mdev_bus_type);
+	if (vfio_bus_is_mdev(bus)) {
+		struct device *iommu_device = NULL;
 
-	if (mdev_bus) {
-		if ((bus == mdev_bus) && !iommu_present(bus)) {
-			symbol_put(mdev_bus_type);
+		group->mdev_group = true;
+
+		/* Determine the isolation type */
+		ret = iommu_group_for_each_dev(iommu_group, &iommu_device,
+					       vfio_mdev_iommu_device);
+		if (ret || !iommu_device) {
 			if (!iommu->external_domain) {
 				INIT_LIST_HEAD(&domain->group_list);
 				iommu->external_domain = domain;
-			} else
+			} else {
 				kfree(domain);
+			}
 
 			list_add(&group->next,
 				 &iommu->external_domain->group_list);
 			mutex_unlock(&iommu->lock);
+
 			return 0;
 		}
-		symbol_put(mdev_bus_type);
+
+		bus = iommu_device->bus;
 	}
 
 	domain->domain = iommu_domain_alloc(bus);
-- 
2.17.1

Re: [PATCH v9 0/3] vfio/mdev: IOMMU aware mediated device

[Joerg Roedel]

On Fri, Apr 12, 2019 at 12:13:23PM +0800, Lu Baolu wrote:
> Lu Baolu (3):
>   vfio/mdev: Add iommu related member in mdev_device
>   vfio/type1: Add domain at(de)taching group helpers
>   vfio/type1: Handle different mdev isolation type

Applied, thanks.