vfio: fix deadlock between group lock and kvm lock

After 51cdc8bc12, we have another deadlock scenario between the
kvm->lock and the vfio group_lock with two different codepaths acquiring
the locks in different order.  Specifically in vfio_open_device, vfio
holds the vfio group_lock when issuing device->ops->open_device but some
drivers (like vfio-ap) need to acquire kvm->lock during their open_device
routine;  Meanwhile, kvm_vfio_release will acquire the kvm->lock first
before calling vfio_file_set_kvm which will acquire the vfio group_lock.

To resolve this, let's remove the need for the vfio group_lock from the
kvm_vfio_release codepath.  This is done by introducing a new spinlock to
protect modifications to the vfio group kvm pointer, and acquiring a kvm
ref from within vfio while holding this spinlock, with the reference held
until the last close for the device in question.

Fixes: 51cdc8bc12 ("kvm/vfio: Fix potential deadlock on vfio group_lock")
Reported-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Tested-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20230203215027.151988-2-mjrosato@linux.ibm.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/group.c

@@ -154,6 +154,18 @@ out_unlock:
 	return ret;
 }
 
+static void vfio_device_group_get_kvm_safe(struct vfio_device *device)
+{
+	spin_lock(&device->group->kvm_ref_lock);
+	if (!device->group->kvm)
+		goto unlock;
+
+	_vfio_device_get_kvm_safe(device, device->group->kvm);
+
+unlock:
+	spin_unlock(&device->group->kvm_ref_lock);
+}
+
 static int vfio_device_group_open(struct vfio_device *device)
 {
 	int ret;
@@ -164,13 +176,23 @@ static int vfio_device_group_open(struct vfio_device *device)
 		goto out_unlock;
 	}
 
+	mutex_lock(&device->dev_set->lock);
+
 	/*
-	 * Here we pass the KVM pointer with the group under the lock.  If the
+	 * Before the first device open, get the KVM pointer currently
-	 * device driver will use it, it must obtain a reference and release it
+	 * associated with the group (if there is one) and obtain a reference
-	 * during close_device.
+	 * now that will be held until the open_count reaches 0 again.  Save
+	 * the pointer in the device for use by drivers.
 	 */
-	ret = vfio_device_open(device, device->group->iommufd,
+	if (device->open_count == 0)
-			       device->group->kvm);
+		vfio_device_group_get_kvm_safe(device);
+
+	ret = vfio_device_open(device, device->group->iommufd, device->kvm);
+
+	if (device->open_count == 0)
+		vfio_device_put_kvm(device);
+
+	mutex_unlock(&device->dev_set->lock);
 
 out_unlock:
 	mutex_unlock(&device->group->group_lock);
@@ -180,7 +202,14 @@ out_unlock:
 void vfio_device_group_close(struct vfio_device *device)
 {
 	mutex_lock(&device->group->group_lock);
+	mutex_lock(&device->dev_set->lock);
+
 	vfio_device_close(device, device->group->iommufd);
+
+	if (device->open_count == 0)
+		vfio_device_put_kvm(device);
+
+	mutex_unlock(&device->dev_set->lock);
 	mutex_unlock(&device->group->group_lock);
 }
 
@@ -450,6 +479,7 @@ static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
 
 	refcount_set(&group->drivers, 1);
 	mutex_init(&group->group_lock);
+	spin_lock_init(&group->kvm_ref_lock);
 	INIT_LIST_HEAD(&group->device_list);
 	mutex_init(&group->device_lock);
 	group->iommu_group = iommu_group;
@@ -803,9 +833,9 @@ void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
 	if (!vfio_file_is_group(file))
 		return;
 
-	mutex_lock(&group->group_lock);
+	spin_lock(&group->kvm_ref_lock);
 	group->kvm = kvm;
-	mutex_unlock(&group->group_lock);
+	spin_unlock(&group->kvm_ref_lock);
 }
 EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
 

drivers/vfio/vfio.h

@@ -74,6 +74,7 @@ struct vfio_group {
 	struct file			*opened_file;
 	struct blocking_notifier_head	notifier;
 	struct iommufd_ctx		*iommufd;
+	spinlock_t			kvm_ref_lock;
 };
 
 int vfio_device_set_group(struct vfio_device *device,
@@ -244,4 +245,18 @@ extern bool vfio_noiommu __read_mostly;
 enum { vfio_noiommu = false };
 #endif
 
+#ifdef CONFIG_HAVE_KVM
+void _vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm);
+void vfio_device_put_kvm(struct vfio_device *device);
+#else
+static inline void _vfio_device_get_kvm_safe(struct vfio_device *device,
+					     struct kvm *kvm)
+{
+}
+
+static inline void vfio_device_put_kvm(struct vfio_device *device)
+{
+}
+#endif
+
 #endif

drivers/vfio/vfio_main.c

@@ -16,6 +16,9 @@
 #include <linux/fs.h>
 #include <linux/idr.h>
 #include <linux/iommu.h>
+#ifdef CONFIG_HAVE_KVM
+#include <linux/kvm_host.h>
+#endif
 #include <linux/list.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
@@ -338,6 +341,55 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 }
 EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
 
+#ifdef CONFIG_HAVE_KVM
+void _vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm)
+{
+	void (*pfn)(struct kvm *kvm);
+	bool (*fn)(struct kvm *kvm);
+	bool ret;
+
+	lockdep_assert_held(&device->dev_set->lock);
+
+	pfn = symbol_get(kvm_put_kvm);
+	if (WARN_ON(!pfn))
+		return;
+
+	fn = symbol_get(kvm_get_kvm_safe);
+	if (WARN_ON(!fn)) {
+		symbol_put(kvm_put_kvm);
+		return;
+	}
+
+	ret = fn(kvm);
+	symbol_put(kvm_get_kvm_safe);
+	if (!ret) {
+		symbol_put(kvm_put_kvm);
+		return;
+	}
+
+	device->put_kvm = pfn;
+	device->kvm = kvm;
+}
+
+void vfio_device_put_kvm(struct vfio_device *device)
+{
+	lockdep_assert_held(&device->dev_set->lock);
+
+	if (!device->kvm)
+		return;
+
+	if (WARN_ON(!device->put_kvm))
+		goto clear;
+
+	device->put_kvm(device->kvm);
+	device->put_kvm = NULL;
+	symbol_put(kvm_put_kvm);
+
+clear:
+	device->kvm = NULL;
+}
+#endif
+
 /* true if the vfio_device has open_device() called but not close_device() */
 static bool vfio_assert_device_open(struct vfio_device *device)
 {
@@ -361,7 +413,6 @@ static int vfio_device_first_open(struct vfio_device *device,
 	if (ret)
 		goto err_module_put;
 
-	device->kvm = kvm;
 	if (device->ops->open_device) {
 		ret = device->ops->open_device(device);
 		if (ret)
@@ -370,7 +421,6 @@ static int vfio_device_first_open(struct vfio_device *device,
 	return 0;
 
 err_unuse_iommu:
-	device->kvm = NULL;
 	if (iommufd)
 		vfio_iommufd_unbind(device);
 	else
@@ -387,7 +437,6 @@ static void vfio_device_last_close(struct vfio_device *device,
 
 	if (device->ops->close_device)
 		device->ops->close_device(device);
-	device->kvm = NULL;
 	if (iommufd)
 		vfio_iommufd_unbind(device);
 	else
@@ -400,14 +449,14 @@ int vfio_device_open(struct vfio_device *device,
 {
 	int ret = 0;
 
-	mutex_lock(&device->dev_set->lock);
+	lockdep_assert_held(&device->dev_set->lock);
+
 	device->open_count++;
 	if (device->open_count == 1) {
 		ret = vfio_device_first_open(device, iommufd, kvm);
 		if (ret)
 			device->open_count--;
 	}
-	mutex_unlock(&device->dev_set->lock);
 
 	return ret;
 }
@@ -415,12 +464,12 @@ int vfio_device_open(struct vfio_device *device,
 void vfio_device_close(struct vfio_device *device,
 		       struct iommufd_ctx *iommufd)
 {
-	mutex_lock(&device->dev_set->lock);
+	lockdep_assert_held(&device->dev_set->lock);
+
 	vfio_assert_device_open(device);
 	if (device->open_count == 1)
 		vfio_device_last_close(device, iommufd);
 	device->open_count--;
-	mutex_unlock(&device->dev_set->lock);
 }
 
 /*

include/linux/vfio.h

@@ -46,7 +46,6 @@ struct vfio_device {
 	struct vfio_device_set *dev_set;
 	struct list_head dev_set_list;
 	unsigned int migration_flags;
-	/* Driver must reference the kvm during open_device or never touch it */
 	struct kvm *kvm;
 
 	/* Members below here are private, not for driver use */
@@ -58,6 +57,7 @@ struct vfio_device {
 	struct list_head group_next;
 	struct list_head iommu_entry;
 	struct iommufd_access *iommufd_access;
+	void (*put_kvm)(struct kvm *kvm);
 #if IS_ENABLED(CONFIG_IOMMUFD)
 	struct iommufd_device *iommufd_device;
 	struct iommufd_ctx *iommufd_ictx;