1 files changed, 482 insertions, 40 deletions

diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 5177bb061b17..f7df90c423b4 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -16,13 +16,19 @@
 #include <linux/fs.h>
 #include <linux/idr.h>
 #include <linux/iommu.h>
+#if IS_ENABLED(CONFIG_KVM)
+#include <linux/kvm_host.h>
+#endif
 #include <linux/list.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
+#include <linux/mount.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/pseudo_fs.h>
 #include <linux/rwsem.h>
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/string.h>
@@ -40,11 +46,22 @@
 #define DRIVER_AUTHOR	"Alex Williamson <alex.williamson@redhat.com>"
 #define DRIVER_DESC	"VFIO - User Level meta-driver"
 
+#define VFIO_MAGIC 0x5646494f /* "VFIO" */
+
 static struct vfio {
 	struct class			*device_class;
 	struct ida			device_ida;
+	struct vfsmount			*vfs_mount;
+	int				fs_count;
 } vfio;
 
+#ifdef CONFIG_VFIO_NOIOMMU
+bool vfio_noiommu __read_mostly;
+module_param_named(enable_unsafe_noiommu_mode,
+		   vfio_noiommu, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode.  This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel.  If you do not know what this is for, step away. (default: false)");
+#endif
+
 static DEFINE_XARRAY(vfio_device_set_xa);
 
 int vfio_assign_device_set(struct vfio_device *device, void *set_id)
@@ -131,6 +148,21 @@ unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set)
 }
 EXPORT_SYMBOL_GPL(vfio_device_set_open_count);
 
+struct vfio_device *
+vfio_find_device_in_devset(struct vfio_device_set *dev_set,
+			   struct device *dev)
+{
+	struct vfio_device *cur;
+
+	lockdep_assert_held(&dev_set->lock);
+
+	list_for_each_entry(cur, &dev_set->device_list, dev_set_list)
+		if (cur->dev == dev)
+			return cur;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(vfio_find_device_in_devset);
+
 /*
  * Device objects - create, release, get, put, search
  */
@@ -140,11 +172,13 @@ void vfio_device_put_registration(struct vfio_device *device)
 	if (refcount_dec_and_test(&device->refcount))
 		complete(&device->comp);
 }
+EXPORT_SYMBOL_GPL(vfio_device_put_registration);
 
 bool vfio_device_try_get_registration(struct vfio_device *device)
 {
 	return refcount_inc_not_zero(&device->refcount);
 }
+EXPORT_SYMBOL_GPL(vfio_device_try_get_registration);
 
 /*
  * VFIO driver API
@@ -161,6 +195,8 @@ static void vfio_device_release(struct device *dev)
 	if (device->ops->release)
 		device->ops->release(device);
 
+	iput(device->inode);
+	simple_release_fs(&vfio.vfs_mount, &vfio.fs_count);
 	kvfree(device);
 }
 
@@ -203,6 +239,34 @@ out_free:
 }
 EXPORT_SYMBOL_GPL(_vfio_alloc_device);
 
+static int vfio_fs_init_fs_context(struct fs_context *fc)
+{
+	return init_pseudo(fc, VFIO_MAGIC) ? 0 : -ENOMEM;
+}
+
+static struct file_system_type vfio_fs_type = {
+	.name = "vfio",
+	.owner = THIS_MODULE,
+	.init_fs_context = vfio_fs_init_fs_context,
+	.kill_sb = kill_anon_super,
+};
+
+static struct inode *vfio_fs_inode_new(void)
+{
+	struct inode *inode;
+	int ret;
+
+	ret = simple_pin_fs(&vfio_fs_type, &vfio.vfs_mount, &vfio.fs_count);
+	if (ret)
+		return ERR_PTR(ret);
+
+	inode = alloc_anon_inode(vfio.vfs_mount->mnt_sb);
+	if (IS_ERR(inode))
+		simple_release_fs(&vfio.vfs_mount, &vfio.fs_count);
+
+	return inode;
+}
+
 /*
  * Initialize a vfio_device so it can be registered to vfio core.
  */
@@ -221,6 +285,11 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev,
 	init_completion(&device->comp);
 	device->dev = dev;
 	device->ops = ops;
+	device->inode = vfio_fs_inode_new();
+	if (IS_ERR(device->inode)) {
+		ret = PTR_ERR(device->inode);
+		goto out_inode;
+	}
 
 	if (ops->init) {
 		ret = ops->init(device);
@@ -235,6 +304,9 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev,
 	return 0;
 
 out_uninit:
+	iput(device->inode);
+	simple_release_fs(&vfio.vfs_mount, &vfio.fs_count);
+out_inode:
 	vfio_release_device_set(device);
 	ida_free(&vfio.device_ida, device->index);
 	return ret;
@@ -245,9 +317,11 @@ static int __vfio_register_dev(struct vfio_device *device,
 {
 	int ret;
 
-	if (WARN_ON(device->ops->bind_iommufd &&
-		    (!device->ops->unbind_iommufd ||
-		     !device->ops->attach_ioas)))
+	if (WARN_ON(IS_ENABLED(CONFIG_IOMMUFD) &&
+		    (!device->ops->bind_iommufd ||
+		     !device->ops->unbind_iommufd ||
+		     !device->ops->attach_ioas ||
+		     !device->ops->detach_ioas)))
 		return -EINVAL;
 
 	/*
@@ -265,7 +339,18 @@ static int __vfio_register_dev(struct vfio_device *device,
 	if (ret)
 		return ret;
 
-	ret = device_add(&device->device);
+	/*
+	 * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
+	 * restore cache coherency. It has to be checked here because it is only
+	 * valid for cases where we are using iommu groups.
+	 */
+	if (type == VFIO_IOMMU && !vfio_device_is_noiommu(device) &&
+	    !device_iommu_capable(device->dev, IOMMU_CAP_CACHE_COHERENCY)) {
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	ret = vfio_device_add(device);
 	if (ret)
 		goto err_out;
 
@@ -273,6 +358,7 @@ static int __vfio_register_dev(struct vfio_device *device,
 	refcount_set(&device->refcount, 1);
 
 	vfio_device_group_register(device);
+	vfio_device_debugfs_init(device);
 
 	return 0;
 err_out:
@@ -305,6 +391,18 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 	bool interrupted = false;
 	long rc;
 
+	/*
+	 * Prevent new device opened by userspace via the
+	 * VFIO_GROUP_GET_DEVICE_FD in the group path.
+	 */
+	vfio_device_group_unregister(device);
+
+	/*
+	 * Balances vfio_device_add() in register path, also prevents
+	 * new device opened by userspace in the cdev path.
+	 */
+	vfio_device_del(device);
+
 	vfio_device_put_registration(device);
 	rc = try_wait_for_completion(&device->comp);
 	while (rc <= 0) {
@@ -328,25 +426,89 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
-	vfio_device_group_unregister(device);
-
-	/* Balances device_add in register path */
-	device_del(&device->device);
-
+	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
 EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
 
+#if IS_ENABLED(CONFIG_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);
+
+	if (!kvm)
+		return;
+
+	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)
 {
 	return !WARN_ON_ONCE(!READ_ONCE(device->open_count));
 }
 
-static int vfio_device_first_open(struct vfio_device *device,
-				  struct iommufd_ctx *iommufd, struct kvm *kvm)
+struct vfio_device_file *
+vfio_allocate_device_file(struct vfio_device *device)
+{
+	struct vfio_device_file *df;
+
+	df = kzalloc(sizeof(*df), GFP_KERNEL_ACCOUNT);
+	if (!df)
+		return ERR_PTR(-ENOMEM);
+
+	df->device = device;
+	spin_lock_init(&df->kvm_ref_lock);
+
+	return df;
+}
+
+static int vfio_df_device_first_open(struct vfio_device_file *df)
 {
+	struct vfio_device *device = df->device;
+	struct iommufd_ctx *iommufd = df->iommufd;
 	int ret;
 
 	lockdep_assert_held(&device->dev_set->lock);
@@ -355,13 +517,12 @@ static int vfio_device_first_open(struct vfio_device *device,
 		return -ENODEV;
 
 	if (iommufd)
-		ret = vfio_iommufd_bind(device, iommufd);
+		ret = vfio_df_iommufd_bind(df);
 	else
 		ret = vfio_device_group_use_iommu(device);
 	if (ret)
 		goto err_module_put;
 
-	device->kvm = kvm;
 	if (device->ops->open_device) {
 		ret = device->ops->open_device(device);
 		if (ret)
@@ -370,9 +531,8 @@ static int vfio_device_first_open(struct vfio_device *device,
 	return 0;
 
 err_unuse_iommu:
-	device->kvm = NULL;
 	if (iommufd)
-		vfio_iommufd_unbind(device);
+		vfio_df_iommufd_unbind(df);
 	else
 		vfio_device_group_unuse_iommu(device);
 err_module_put:
@@ -380,47 +540,57 @@ err_module_put:
 	return ret;
 }
 
-static void vfio_device_last_close(struct vfio_device *device,
-				   struct iommufd_ctx *iommufd)
+static void vfio_df_device_last_close(struct vfio_device_file *df)
 {
+	struct vfio_device *device = df->device;
+	struct iommufd_ctx *iommufd = df->iommufd;
+
 	lockdep_assert_held(&device->dev_set->lock);
 
 	if (device->ops->close_device)
 		device->ops->close_device(device);
-	device->kvm = NULL;
 	if (iommufd)
-		vfio_iommufd_unbind(device);
+		vfio_df_iommufd_unbind(df);
 	else
 		vfio_device_group_unuse_iommu(device);
 	module_put(device->dev->driver->owner);
 }
 
-int vfio_device_open(struct vfio_device *device,
-		     struct iommufd_ctx *iommufd, struct kvm *kvm)
+int vfio_df_open(struct vfio_device_file *df)
 {
+	struct vfio_device *device = df->device;
 	int ret = 0;
 
-	mutex_lock(&device->dev_set->lock);
+	lockdep_assert_held(&device->dev_set->lock);
+
+	/*
+	 * Only the group path allows the device to be opened multiple
+	 * times.  The device cdev path doesn't have a secure way for it.
+	 */
+	if (device->open_count != 0 && !df->group)
+		return -EINVAL;
+
 	device->open_count++;
 	if (device->open_count == 1) {
-		ret = vfio_device_first_open(device, iommufd, kvm);
+		ret = vfio_df_device_first_open(df);
 		if (ret)
 			device->open_count--;
 	}
-	mutex_unlock(&device->dev_set->lock);
 
 	return ret;
 }
 
-void vfio_device_close(struct vfio_device *device,
-		       struct iommufd_ctx *iommufd)
+void vfio_df_close(struct vfio_device_file *df)
 {
-	mutex_lock(&device->dev_set->lock);
-	vfio_assert_device_open(device);
+	struct vfio_device *device = df->device;
+
+	lockdep_assert_held(&device->dev_set->lock);
+
+	if (!vfio_assert_device_open(device))
+		return;
 	if (device->open_count == 1)
-		vfio_device_last_close(device, iommufd);
+		vfio_df_device_last_close(df);
 	device->open_count--;
-	mutex_unlock(&device->dev_set->lock);
 }
 
 /*
@@ -461,12 +631,18 @@ static inline void vfio_device_pm_runtime_put(struct vfio_device *device)
  */
 static int vfio_device_fops_release(struct inode *inode, struct file *filep)
 {
-	struct vfio_device *device = filep->private_data;
+	struct vfio_device_file *df = filep->private_data;
+	struct vfio_device *device = df->device;
 
-	vfio_device_group_close(device);
+	if (df->group)
+		vfio_df_group_close(df);
+	else
+		vfio_df_unbind_iommufd(df);
 
 	vfio_device_put_registration(device);
 
+	kfree(df);
+
 	return 0;
 }
 
@@ -809,6 +985,63 @@ static int vfio_ioctl_device_feature_migration(struct vfio_device *device,
 	return 0;
 }
 
+void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
+			      u32 req_nodes)
+{
+	struct interval_tree_node *prev, *curr, *comb_start, *comb_end;
+	unsigned long min_gap, curr_gap;
+
+	/* Special shortcut when a single range is required */
+	if (req_nodes == 1) {
+		unsigned long last;
+
+		comb_start = interval_tree_iter_first(root, 0, ULONG_MAX);
+
+		/* Empty list */
+		if (WARN_ON_ONCE(!comb_start))
+			return;
+
+		curr = comb_start;
+		while (curr) {
+			last = curr->last;
+			prev = curr;
+			curr = interval_tree_iter_next(curr, 0, ULONG_MAX);
+			if (prev != comb_start)
+				interval_tree_remove(prev, root);
+		}
+		comb_start->last = last;
+		return;
+	}
+
+	/* Combine ranges which have the smallest gap */
+	while (cur_nodes > req_nodes) {
+		prev = NULL;
+		min_gap = ULONG_MAX;
+		curr = interval_tree_iter_first(root, 0, ULONG_MAX);
+		while (curr) {
+			if (prev) {
+				curr_gap = curr->start - prev->last;
+				if (curr_gap < min_gap) {
+					min_gap = curr_gap;
+					comb_start = prev;
+					comb_end = curr;
+				}
+			}
+			prev = curr;
+			curr = interval_tree_iter_next(curr, 0, ULONG_MAX);
+		}
+
+		/* Empty list or no nodes to combine */
+		if (WARN_ON_ONCE(min_gap == ULONG_MAX))
+			break;
+
+		comb_start->last = comb_end->last;
+		interval_tree_remove(comb_end, root);
+		cur_nodes--;
+	}
+}
+EXPORT_SYMBOL_GPL(vfio_combine_iova_ranges);
+
 /* Ranges should fit into a single kernel page */
 #define LOG_MAX_RANGES \
 	(PAGE_SIZE / sizeof(struct vfio_device_feature_dma_logging_range))
@@ -1021,26 +1254,97 @@ static int vfio_ioctl_device_feature(struct vfio_device *device,
 			feature.argsz - minsz);
 	default:
 		if (unlikely(!device->ops->device_feature))
-			return -EINVAL;
+			return -ENOTTY;
 		return device->ops->device_feature(device, feature.flags,
 						   arg->data,
 						   feature.argsz - minsz);
 	}
 }
 
+static long vfio_get_region_info(struct vfio_device *device,
+				 struct vfio_region_info __user *arg)
+{
+	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
+	struct vfio_region_info info = {};
+	struct vfio_info_cap caps = {};
+	int ret;
+
+	if (unlikely(!device->ops->get_region_info_caps))
+		return -EINVAL;
+
+	if (copy_from_user(&info, arg, minsz))
+		return -EFAULT;
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	ret = device->ops->get_region_info_caps(device, &info, &caps);
+	if (ret)
+		goto out_free;
+
+	if (caps.size) {
+		info.flags |= VFIO_REGION_INFO_FLAG_CAPS;
+		if (info.argsz < sizeof(info) + caps.size) {
+			info.argsz = sizeof(info) + caps.size;
+			info.cap_offset = 0;
+		} else {
+			vfio_info_cap_shift(&caps, sizeof(info));
+			if (copy_to_user(arg + 1, caps.buf, caps.size)) {
+				ret = -EFAULT;
+				goto out_free;
+			}
+			info.cap_offset = sizeof(info);
+		}
+	}
+
+	if (copy_to_user(arg, &info, minsz)){
+		ret = -EFAULT;
+		goto out_free;
+	}
+
+out_free:
+	kfree(caps.buf);
+	return ret;
+}
+
 static long vfio_device_fops_unl_ioctl(struct file *filep,
 				       unsigned int cmd, unsigned long arg)
 {
-	struct vfio_device *device = filep->private_data;
+	struct vfio_device_file *df = filep->private_data;
+	struct vfio_device *device = df->device;
+	void __user *uptr = (void __user *)arg;
 	int ret;
 
+	if (cmd == VFIO_DEVICE_BIND_IOMMUFD)
+		return vfio_df_ioctl_bind_iommufd(df, uptr);
+
+	/* Paired with smp_store_release() following vfio_df_open() */
+	if (!smp_load_acquire(&df->access_granted))
+		return -EINVAL;
+
 	ret = vfio_device_pm_runtime_get(device);
 	if (ret)
 		return ret;
 
+	/* cdev only ioctls */
+	if (IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) && !df->group) {
+		switch (cmd) {
+		case VFIO_DEVICE_ATTACH_IOMMUFD_PT:
+			ret = vfio_df_ioctl_attach_pt(df, uptr);
+			goto out;
+
+		case VFIO_DEVICE_DETACH_IOMMUFD_PT:
+			ret = vfio_df_ioctl_detach_pt(df, uptr);
+			goto out;
+		}
+	}
+
 	switch (cmd) {
 	case VFIO_DEVICE_FEATURE:
-		ret = vfio_ioctl_device_feature(device, (void __user *)arg);
+		ret = vfio_ioctl_device_feature(device, uptr);
+		break;
+
+	case VFIO_DEVICE_GET_REGION_INFO:
+		ret = vfio_get_region_info(device, uptr);
 		break;
 
 	default:
@@ -1050,7 +1354,7 @@ static long vfio_device_fops_unl_ioctl(struct file *filep,
 			ret = device->ops->ioctl(device, cmd, arg);
 		break;
 	}
-
+out:
 	vfio_device_pm_runtime_put(device);
 	return ret;
 }
@@ -1058,7 +1362,12 @@ static long vfio_device_fops_unl_ioctl(struct file *filep,
 static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf,
 				     size_t count, loff_t *ppos)
 {
-	struct vfio_device *device = filep->private_data;
+	struct vfio_device_file *df = filep->private_data;
+	struct vfio_device *device = df->device;
+
+	/* Paired with smp_store_release() following vfio_df_open() */
+	if (!smp_load_acquire(&df->access_granted))
+		return -EINVAL;
 
 	if (unlikely(!device->ops->read))
 		return -EINVAL;
@@ -1070,7 +1379,12 @@ static ssize_t vfio_device_fops_write(struct file *filep,
 				      const char __user *buf,
 				      size_t count, loff_t *ppos)
 {
-	struct vfio_device *device = filep->private_data;
+	struct vfio_device_file *df = filep->private_data;
+	struct vfio_device *device = df->device;
+
+	/* Paired with smp_store_release() following vfio_df_open() */
+	if (!smp_load_acquire(&df->access_granted))
+		return -EINVAL;
 
 	if (unlikely(!device->ops->write))
 		return -EINVAL;
@@ -1080,7 +1394,12 @@ static ssize_t vfio_device_fops_write(struct file *filep,
 
 static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma)
 {
-	struct vfio_device *device = filep->private_data;
+	struct vfio_device_file *df = filep->private_data;
+	struct vfio_device *device = df->device;
+
+	/* Paired with smp_store_release() following vfio_df_open() */
+	if (!smp_load_acquire(&df->access_granted))
+		return -EINVAL;
 
 	if (unlikely(!device->ops->mmap))
 		return -EINVAL;
@@ -1088,16 +1407,118 @@ static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma)
 	return device->ops->mmap(device, vma);
 }
 
+#ifdef CONFIG_PROC_FS
+static void vfio_device_show_fdinfo(struct seq_file *m, struct file *filep)
+{
+	char *path;
+	struct vfio_device_file *df = filep->private_data;
+	struct vfio_device *device = df->device;
+
+	path = kobject_get_path(&device->dev->kobj, GFP_KERNEL);
+	if (!path)
+		return;
+
+	seq_printf(m, "vfio-device-syspath: /sys%s\n", path);
+	kfree(path);
+}
+#endif
+
 const struct file_operations vfio_device_fops = {
 	.owner		= THIS_MODULE,
+	.open		= vfio_device_fops_cdev_open,
 	.release	= vfio_device_fops_release,
 	.read		= vfio_device_fops_read,
 	.write		= vfio_device_fops_write,
 	.unlocked_ioctl	= vfio_device_fops_unl_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
 	.mmap		= vfio_device_fops_mmap,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= vfio_device_show_fdinfo,
+#endif
 };
 
+static struct vfio_device *vfio_device_from_file(struct file *file)
+{
+	struct vfio_device_file *df = file->private_data;
+
+	if (file->f_op != &vfio_device_fops)
+		return NULL;
+	return df->device;
+}
+
+/**
+ * vfio_file_is_valid - True if the file is valid vfio file
+ * @file: VFIO group file or VFIO device file
+ */
+bool vfio_file_is_valid(struct file *file)
+{
+	return vfio_group_from_file(file) ||
+	       vfio_device_from_file(file);
+}
+EXPORT_SYMBOL_GPL(vfio_file_is_valid);
+
+/**
+ * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
+ *        is always CPU cache coherent
+ * @file: VFIO group file or VFIO device file
+ *
+ * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
+ * bit in DMA transactions. A return of false indicates that the user has
+ * rights to access additional instructions such as wbinvd on x86.
+ */
+bool vfio_file_enforced_coherent(struct file *file)
+{
+	struct vfio_device *device;
+	struct vfio_group *group;
+
+	group = vfio_group_from_file(file);
+	if (group)
+		return vfio_group_enforced_coherent(group);
+
+	device = vfio_device_from_file(file);
+	if (device)
+		return device_iommu_capable(device->dev,
+					    IOMMU_CAP_ENFORCE_CACHE_COHERENCY);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
+
+static void vfio_device_file_set_kvm(struct file *file, struct kvm *kvm)
+{
+	struct vfio_device_file *df = file->private_data;
+
+	/*
+	 * The kvm is first recorded in the vfio_device_file, and will
+	 * be propagated to vfio_device::kvm when the file is bound to
+	 * iommufd successfully in the vfio device cdev path.
+	 */
+	spin_lock(&df->kvm_ref_lock);
+	df->kvm = kvm;
+	spin_unlock(&df->kvm_ref_lock);
+}
+
+/**
+ * vfio_file_set_kvm - Link a kvm with VFIO drivers
+ * @file: VFIO group file or VFIO device file
+ * @kvm: KVM to link
+ *
+ * When a VFIO device is first opened the KVM will be available in
+ * device->kvm if one was associated with the file.
+ */
+void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
+{
+	struct vfio_group *group;
+
+	group = vfio_group_from_file(file);
+	if (group)
+		vfio_group_set_kvm(group, kvm);
+
+	if (vfio_device_from_file(file))
+		vfio_device_file_set_kvm(file, kvm);
+}
+EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
+
 /*
  * Sub-module support
  */
@@ -1116,6 +1537,9 @@ struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps,
 	void *buf;
 	struct vfio_info_cap_header *header, *tmp;
 
+	/* Ensure that the next capability struct will be aligned */
+	size = ALIGN(size, sizeof(u64));
+
 	buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL);
 	if (!buf) {
 		kfree(caps->buf);
@@ -1149,6 +1573,9 @@ void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset)
 	struct vfio_info_cap_header *tmp;
 	void *buf = (void *)caps->buf;
 
+	/* Capability structs should start with proper alignment */
+	WARN_ON(!IS_ALIGNED(offset, sizeof(u64)));
+
 	for (tmp = buf; tmp->next; tmp = buf + tmp->next - offset)
 		tmp->next += offset;
 }
@@ -1237,6 +1664,8 @@ int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
 	/* group->container cannot change while a vfio device is open */
 	if (!pages || !npage || WARN_ON(!vfio_assert_device_open(device)))
 		return -EINVAL;
+	if (!device->ops->dma_unmap)
+		return -EINVAL;
 	if (vfio_device_has_container(device))
 		return vfio_device_container_pin_pages(device, iova,
 						       npage, prot, pages);
@@ -1274,6 +1703,8 @@ void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage)
 {
 	if (WARN_ON(!vfio_assert_device_open(device)))
 		return;
+	if (WARN_ON(!device->ops->dma_unmap))
+		return;
 
 	if (vfio_device_has_container(device)) {
 		vfio_device_container_unpin_pages(device, iova, npage);
@@ -1353,15 +1784,23 @@ static int __init vfio_init(void)
 		goto err_virqfd;
 
 	/* /sys/class/vfio-dev/vfioX */
-	vfio.device_class = class_create(THIS_MODULE, "vfio-dev");
+	vfio.device_class = class_create("vfio-dev");
 	if (IS_ERR(vfio.device_class)) {
 		ret = PTR_ERR(vfio.device_class);
 		goto err_dev_class;
 	}
 
+	ret = vfio_cdev_init(vfio.device_class);
+	if (ret)
+		goto err_alloc_dev_chrdev;
+
+	vfio_debugfs_create_root();
 	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return 0;
 
+err_alloc_dev_chrdev:
+	class_destroy(vfio.device_class);
+	vfio.device_class = NULL;
 err_dev_class:
 	vfio_virqfd_exit();
 err_virqfd:
@@ -1371,7 +1810,9 @@ err_virqfd:
 
 static void __exit vfio_cleanup(void)
 {
+	vfio_debugfs_remove_root();
 	ida_destroy(&vfio.device_ida);
+	vfio_cdev_cleanup();
 	class_destroy(vfio.device_class);
 	vfio.device_class = NULL;
 	vfio_virqfd_exit();
@@ -1382,6 +1823,7 @@ static void __exit vfio_cleanup(void)
 module_init(vfio_init);
 module_exit(vfio_cleanup);
 
+MODULE_IMPORT_NS("IOMMUFD");
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR(DRIVER_AUTHOR);