vfio: Add VFIO_DEVICE_BIND_IOMMUFD

This adds ioctl for userspace to bind device cdev fd to iommufd.

    VFIO_DEVICE_BIND_IOMMUFD: bind device to an iommufd, hence gain DMA
			      control provided by the iommufd. open_device
			      op is called after bind_iommufd op.

Tested-by: Nicolin Chen <[email protected]>
Tested-by: Matthew Rosato <[email protected]>
Tested-by: Yanting Jiang <[email protected]>
Tested-by: Shameer Kolothum <[email protected]>
Tested-by: Terrence Xu <[email protected]>
Tested-by: Zhenzhong Duan <[email protected]>
Signed-off-by: Yi Liu <[email protected]>
Reviewed-by: Jason Gunthorpe <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alex Williamson <[email protected]>

Author: yiliu1765

drivers/vfio/device_cdev.c

@@ -3,6 +3,7 @@
  * Copyright (c) 2023 Intel Corporation.
  */
 #include <linux/vfio.h>
+#include <linux/iommufd.h>
 
 #include "vfio.h"
 
@@ -45,6 +46,112 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep)
 	return ret;
 }
 
+static void vfio_df_get_kvm_safe(struct vfio_device_file *df)
+{
+	spin_lock(&df->kvm_ref_lock);
+	vfio_device_get_kvm_safe(df->device, df->kvm);
+	spin_unlock(&df->kvm_ref_lock);
+}
+
+long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
+				struct vfio_device_bind_iommufd __user *arg)
+{
+	struct vfio_device *device = df->device;
+	struct vfio_device_bind_iommufd bind;
+	unsigned long minsz;
+	int ret;
+
+	static_assert(__same_type(arg->out_devid, df->devid));
+
+	minsz = offsetofend(struct vfio_device_bind_iommufd, out_devid);
+
+	if (copy_from_user(&bind, arg, minsz))
+		return -EFAULT;
+
+	if (bind.argsz < minsz || bind.flags || bind.iommufd < 0)
+		return -EINVAL;
+
+	/* BIND_IOMMUFD only allowed for cdev fds */
+	if (df->group)
+		return -EINVAL;
+
+	ret = vfio_device_block_group(device);
+	if (ret)
+		return ret;
+
+	mutex_lock(&device->dev_set->lock);
+	/* one device cannot be bound twice */
+	if (df->access_granted) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	df->iommufd = iommufd_ctx_from_fd(bind.iommufd);
+	if (IS_ERR(df->iommufd)) {
+		ret = PTR_ERR(df->iommufd);
+		df->iommufd = NULL;
+		goto out_unlock;
+	}
+
+	/*
+	 * Before the device open, get the KVM pointer currently
+	 * associated with the device file (if there is) and obtain
+	 * a reference.  This reference is held until device closed.
+	 * Save the pointer in the device for use by drivers.
+	 */
+	vfio_df_get_kvm_safe(df);
+
+	ret = vfio_df_open(df);
+	if (ret)
+		goto out_put_kvm;
+
+	ret = copy_to_user(&arg->out_devid, &df->devid,
+			   sizeof(df->devid)) ? -EFAULT : 0;
+	if (ret)
+		goto out_close_device;
+
+	device->cdev_opened = true;
+	/*
+	 * Paired with smp_load_acquire() in vfio_device_fops::ioctl/
+	 * read/write/mmap
+	 */
+	smp_store_release(&df->access_granted, true);
+	mutex_unlock(&device->dev_set->lock);
+	return 0;
+
+out_close_device:
+	vfio_df_close(df);
+out_put_kvm:
+	vfio_device_put_kvm(device);
+	iommufd_ctx_put(df->iommufd);
+	df->iommufd = NULL;
+out_unlock:
+	mutex_unlock(&device->dev_set->lock);
+	vfio_device_unblock_group(device);
+	return ret;
+}
+
+void vfio_df_unbind_iommufd(struct vfio_device_file *df)
+{
+	struct vfio_device *device = df->device;
+
+	/*
+	 * In the time of close, there is no contention with another one
+	 * changing this flag.  So read df->access_granted without lock
+	 * and no smp_load_acquire() is ok.
+	 */
+	if (!df->access_granted)
+		return;
+
+	mutex_lock(&device->dev_set->lock);
+	vfio_df_close(df);
+	vfio_device_put_kvm(device);
+	iommufd_ctx_put(df->iommufd);
+	device->cdev_opened = false;
+	mutex_unlock(&device->dev_set->lock);
+	vfio_device_unblock_group(device);
+}
+
 static char *vfio_device_devnode(const struct device *dev, umode_t *mode)
 {
 	return kasprintf(GFP_KERNEL, "vfio/devices/%s", dev_name(dev));

drivers/vfio/vfio.h

@@ -287,6 +287,9 @@ static inline void vfio_device_del(struct vfio_device *device)
 }
 
 int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep);
+long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
+				struct vfio_device_bind_iommufd __user *arg);
+void vfio_df_unbind_iommufd(struct vfio_device_file *df);
 int vfio_cdev_init(struct class *device_class);
 void vfio_cdev_cleanup(void);
 #else
@@ -310,6 +313,16 @@ static inline int vfio_device_fops_cdev_open(struct inode *inode,
 	return 0;
 }
 
+static inline long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
+					      struct vfio_device_bind_iommufd __user *arg)
+{
+	return -ENOTTY;
+}
+
+static inline void vfio_df_unbind_iommufd(struct vfio_device_file *df)
+{
+}
+
 static inline int vfio_cdev_init(struct class *device_class)
 {
 	return 0;

drivers/vfio/vfio_main.c

@@ -575,6 +575,8 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)
 
 	if (df->group)
 		vfio_df_group_close(df);
+	else
+		vfio_df_unbind_iommufd(df);
 
 	vfio_device_put_registration(device);
 
@@ -1149,6 +1151,9 @@ static long vfio_device_fops_unl_ioctl(struct file *filep,
 	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;

include/linux/vfio.h

@@ -64,8 +64,9 @@ struct vfio_device {
 	void (*put_kvm)(struct kvm *kvm);
 #if IS_ENABLED(CONFIG_IOMMUFD)
 	struct iommufd_device *iommufd_device;
-	bool iommufd_attached;
+	u8 iommufd_attached:1;
 #endif
+	u8 cdev_opened:1;
 };
 
 /**
@@ -168,7 +169,7 @@ vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx)
 
 static inline bool vfio_device_cdev_opened(struct vfio_device *device)
 {
-	return false;
+	return device->cdev_opened;
 }
 
 /**

include/uapi/linux/vfio.h

@@ -897,6 +897,33 @@ struct vfio_device_feature {
 
 #define VFIO_DEVICE_FEATURE		_IO(VFIO_TYPE, VFIO_BASE + 17)
 
+/*
+ * VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18,
+ *				   struct vfio_device_bind_iommufd)
+ * @argsz:	 User filled size of this data.
+ * @flags:	 Must be 0.
+ * @iommufd:	 iommufd to bind.
+ * @out_devid:	 The device id generated by this bind. devid is a handle for
+ *		 this device/iommufd bond and can be used in IOMMUFD commands.
+ *
+ * Bind a vfio_device to the specified iommufd.
+ *
+ * User is restricted from accessing the device before the binding operation
+ * is completed.  Only allowed on cdev fds.
+ *
+ * Unbind is automatically conducted when device fd is closed.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_bind_iommufd {
+	__u32		argsz;
+	__u32		flags;
+	__s32		iommufd;
+	__u32		out_devid;
+};
+
+#define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 18)
+
 /*
  * Provide support for setting a PCI VF Token, which is used as a shared
  * secret between PF and VF drivers.  This feature may only be set on a