[Intel-gfx] [PATCH v4 16/19] vfio: Add VFIO_DEVICE_BIND_IOMMUFD

[Liu, Yi L]

> From: Zhao, Yan Y <yan.y.zhao at intel.com>
> Sent: Wednesday, February 22, 2023 3:53 PM
> 
> On Mon, Feb 20, 2023 at 07:48:09PM -0800, Yi Liu wrote:
> > 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.
> > 			      VFIO no iommu mode is indicated by passing
> > 			      a negative iommufd value.
> >
> > Signed-off-by: Yi Liu <yi.l.liu at intel.com>
> > ---
> >  drivers/vfio/device_cdev.c | 137
> +++++++++++++++++++++++++++++++++++++
> >  drivers/vfio/vfio.h        |  17 ++++-
> >  drivers/vfio/vfio_main.c   |  30 ++++++--
> >  include/linux/iommufd.h    |   6 ++
> >  include/uapi/linux/vfio.h  |  34 +++++++++
> >  5 files changed, 219 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
> > index 9e2c1ecaaf4f..be62f0a5687e 100644
> > --- a/drivers/vfio/device_cdev.c
> > +++ b/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 +46,142 @@ int vfio_device_fops_cdev_open(struct inode
> *inode, struct file *filep)
> >  	return ret;
> >  }
> >
> > +static void vfio_device_get_kvm_safe(struct vfio_device_file *df)
> > +{
> > +	spin_lock(&df->kvm_ref_lock);
> > +	if (!df->kvm)
> > +		goto unlock;
> > +
> > +	_vfio_device_get_kvm_safe(df->device, df->kvm);
> > +
> > +unlock:
> > +	spin_unlock(&df->kvm_ref_lock);
> > +}
> > +
> > +void vfio_device_cdev_close(struct vfio_device_file *df)
> > +{
> > +	struct vfio_device *device = df->device;
> > +
> > +	mutex_lock(&device->dev_set->lock);
> > +	if (!smp_load_acquire(&df->access_granted)) {
> > +		mutex_unlock(&device->dev_set->lock);
> > +		return;
> > +	}
> > +	vfio_device_close(df);
> > +	vfio_device_put_kvm(device);
> > +	if (df->iommufd)
> > +		iommufd_ctx_put(df->iommufd);
> > +	mutex_unlock(&device->dev_set->lock);
> > +	vfio_device_unblock_group(device);
> > +}
> > +
> > +long vfio_device_ioctl_bind_iommufd(struct vfio_device_file *df,
> > +				    unsigned long arg)
> > +{
> > +	struct vfio_device *device = df->device;
> > +	struct vfio_device_bind_iommufd bind;
> > +	struct iommufd_ctx *iommufd = NULL;
> > +	struct fd f;
> > +	unsigned long minsz;
> > +	int ret;
> > +
> > +	minsz = offsetofend(struct vfio_device_bind_iommufd, out_devid);
> > +
> > +	if (copy_from_user(&bind, (void __user *)arg, minsz))
> > +		return -EFAULT;
> > +
> > +	if (bind.argsz < minsz || bind.flags)
> > +		return -EINVAL;
> > +
> > +	if (!device->ops->bind_iommufd)
> > +		return -ENODEV;
> > +
> > +	ret = vfio_device_block_group(device);
> > +	if (ret)
> > +		return ret;
> > +
> > +	mutex_lock(&device->dev_set->lock);
> > +	/*
> > +	 * If already been bound to an iommufd, or already set noiommu
> > +	 * then fail it.
> > +	 */
> > +	if (df->iommufd || df->noiommu) {
> > +		ret = -EINVAL;
> > +		goto out_unlock;
> > +	}
> > +
> > +	/* iommufd < 0 means noiommu mode */
> > +	if (bind.iommufd < 0) {
> > +		if (!capable(CAP_SYS_RAWIO)) {
> > +			ret = -EPERM;
> > +			goto out_unlock;
> > +		}
> > +		df->noiommu = true;
> > +	} else {
> > +		f = fdget(bind.iommufd);
> > +		if (!f.file) {
> > +			ret = -EBADF;
> > +			goto out_unlock;
> > +		}
> > +		iommufd = iommufd_ctx_from_file(f.file);
> > +		if (IS_ERR(iommufd)) {
> > +			ret = PTR_ERR(iommufd);
> > +			goto out_put_file;
> > +		}
> > +	}
> > +
> > +	/*
> > +	 * 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_device_get_kvm_safe(df);
> > +
> > +	df->iommufd = iommufd;
> > +	ret = vfio_device_open(df, &bind.out_devid, NULL);
> > +	if (ret)
> > +		goto out_put_kvm;
> > +
> > +	ret = copy_to_user((void __user *)arg +
> > +			   offsetofend(struct vfio_device_bind_iommufd,
> iommufd),
> > +			   &bind.out_devid,
> > +			   sizeof(bind.out_devid)) ? -EFAULT : 0;
> > +	if (ret)
> > +		goto out_close_device;
> > +
> > +	if (iommufd)
> > +		fdput(f);

Here check f.file

> > +	else if (df->noiommu)
> > +		dev_warn(device->dev, "vfio-noiommu device used by user
> "
> > +			 "(%s:%d)\n", current->comm,
> task_pid_nr(current));
> > +
> > +	/*
> > +	 * 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_device_close(df);
> > +out_put_kvm:
> > +	df->iommufd = NULL;
> > +	df->noiommu = false;
> > +	vfio_device_put_kvm(device);
> > +out_put_file:
> > +	if (iommufd) {
> > +		iommufd_ctx_put(iommufd);
> > +		fdput(f);
> even if iommufd is NULL, still need to fdput(f) if f.file is true, right?

Yes. it is. And also another line in above. 😊 may need to wrap the
fdget() and iommufd_ctx_from_file() into a helper. So fdput is called
in the helper.

> > +	}
> > +out_unlock:
> > +	mutex_unlock(&device->dev_set->lock);
> > +	vfio_device_unblock_group(device);
> > +	return ret;
> > +}
> > +