lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Thu, 29 Sep 2022 10:55:19 -0600
From:   Alex Williamson <alex.williamson@...hat.com>
To:     Kevin Tian <kevin.tian@...el.com>
Cc:     Zhenyu Wang <zhenyuw@...ux.intel.com>,
        Zhi Wang <zhi.a.wang@...el.com>,
        Jani Nikula <jani.nikula@...ux.intel.com>,
        Joonas Lahtinen <joonas.lahtinen@...ux.intel.com>,
        Rodrigo Vivi <rodrigo.vivi@...el.com>,
        Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>,
        David Airlie <airlied@...ux.ie>,
        Daniel Vetter <daniel@...ll.ch>,
        Eric Farman <farman@...ux.ibm.com>,
        Matthew Rosato <mjrosato@...ux.ibm.com>,
        Halil Pasic <pasic@...ux.ibm.com>,
        Vineeth Vijayan <vneethv@...ux.ibm.com>,
        Peter Oberparleiter <oberpar@...ux.ibm.com>,
        Heiko Carstens <hca@...ux.ibm.com>,
        Vasily Gorbik <gor@...ux.ibm.com>,
        Alexander Gordeev <agordeev@...ux.ibm.com>,
        Christian Borntraeger <borntraeger@...ux.ibm.com>,
        Sven Schnelle <svens@...ux.ibm.com>,
        Tony Krowiak <akrowiak@...ux.ibm.com>,
        Jason Herne <jjherne@...ux.ibm.com>,
        Harald Freudenberger <freude@...ux.ibm.com>,
        Diana Craciun <diana.craciun@....nxp.com>,
        Cornelia Huck <cohuck@...hat.com>,
        Longfang Liu <liulongfang@...wei.com>,
        Shameer Kolothum <shameerali.kolothum.thodi@...wei.com>,
        Jason Gunthorpe <jgg@...pe.ca>,
        Yishai Hadas <yishaih@...dia.com>,
        Eric Auger <eric.auger@...hat.com>,
        Kirti Wankhede <kwankhede@...dia.com>,
        Leon Romanovsky <leon@...nel.org>,
        Abhishek Sahu <abhsahu@...dia.com>,
        Christoph Hellwig <hch@...radead.org>,
        intel-gvt-dev@...ts.freedesktop.org,
        intel-gfx@...ts.freedesktop.org, dri-devel@...ts.freedesktop.org,
        linux-kernel@...r.kernel.org, linux-s390@...r.kernel.org,
        kvm@...r.kernel.org, Yi Liu <yi.l.liu@...el.com>
Subject: Re: [PATCH v4 15/15] vfio: Add struct device to vfio_device

Hi Kevin,

This introduced the regression discovered here:

https://lore.kernel.org/all/20220928125650.0a2ea297.alex.williamson@redhat.com/

Seems we're not releasing the resources when removing an mdev.  This is
a regression, so it needs to be fixed or reverted before the merge
window.  Thanks,

Alex

On Wed, 21 Sep 2022 18:44:01 +0800
Kevin Tian <kevin.tian@...el.com> wrote:

> From: Yi Liu <yi.l.liu@...el.com>
> 
> and replace kref. With it a 'vfio-dev/vfioX' node is created under the
> sysfs path of the parent, indicating the device is bound to a vfio
> driver, e.g.:
> 
> /sys/devices/pci0000\:6f/0000\:6f\:01.0/vfio-dev/vfio0
> 
> It is also a preparatory step toward adding cdev for supporting future
> device-oriented uAPI.
> 
> Add Documentation/ABI/testing/sysfs-devices-vfio-dev.
> 
> Suggested-by: Jason Gunthorpe <jgg@...dia.com>
> Signed-off-by: Yi Liu <yi.l.liu@...el.com>
> Signed-off-by: Kevin Tian <kevin.tian@...el.com>
> Reviewed-by: Jason Gunthorpe <jgg@...dia.com>
> ---
>  .../ABI/testing/sysfs-devices-vfio-dev        |  8 +++
>  MAINTAINERS                                   |  1 +
>  drivers/vfio/vfio_main.c                      | 64 +++++++++++++++----
>  include/linux/vfio.h                          |  6 +-
>  4 files changed, 65 insertions(+), 14 deletions(-)
>  create mode 100644 Documentation/ABI/testing/sysfs-devices-vfio-dev
> 
> diff --git a/Documentation/ABI/testing/sysfs-devices-vfio-dev b/Documentation/ABI/testing/sysfs-devices-vfio-dev
> new file mode 100644
> index 000000000000..e21424fd9666
> --- /dev/null
> +++ b/Documentation/ABI/testing/sysfs-devices-vfio-dev
> @@ -0,0 +1,8 @@
> +What:		 /sys/.../<device>/vfio-dev/vfioX/
> +Date:		 September 2022
> +Contact:	 Yi Liu <yi.l.liu@...el.com>
> +Description:
> +		 This directory is created when the device is bound to a
> +		 vfio driver. The layout under this directory matches what
> +		 exists for a standard 'struct device'. 'X' is a unique
> +		 index marking this device in vfio.
> diff --git a/MAINTAINERS b/MAINTAINERS
> index d30f26e07cd3..02c8f11b1c17 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -21312,6 +21312,7 @@ R:	Cornelia Huck <cohuck@...hat.com>
>  L:	kvm@...r.kernel.org
>  S:	Maintained
>  T:	git git://github.com/awilliam/linux-vfio.git
> +F:	Documentation/ABI/testing/sysfs-devices-vfio-dev
>  F:	Documentation/driver-api/vfio.rst
>  F:	drivers/vfio/
>  F:	include/linux/vfio.h
> diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
> index c27449613a1d..f9d10dbcf3e6 100644
> --- a/drivers/vfio/vfio_main.c
> +++ b/drivers/vfio/vfio_main.c
> @@ -49,6 +49,8 @@ static struct vfio {
>  	struct mutex			group_lock; /* locks group_list */
>  	struct ida			group_ida;
>  	dev_t				group_devt;
> +	struct class			*device_class;
> +	struct ida			device_ida;
>  } vfio;
>  
>  struct vfio_iommu_driver {
> @@ -485,12 +487,13 @@ static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
>   * VFIO driver API
>   */
>  /* Release helper called by vfio_put_device() */
> -void vfio_device_release(struct kref *kref)
> +static void vfio_device_release(struct device *dev)
>  {
>  	struct vfio_device *device =
> -			container_of(kref, struct vfio_device, kref);
> +			container_of(dev, struct vfio_device, device);
>  
>  	vfio_release_device_set(device);
> +	ida_free(&vfio.device_ida, device->index);
>  
>  	/*
>  	 * kvfree() cannot be done here due to a life cycle mess in
> @@ -500,7 +503,6 @@ void vfio_device_release(struct kref *kref)
>  	 */
>  	device->ops->release(device);
>  }
> -EXPORT_SYMBOL_GPL(vfio_device_release);
>  
>  /*
>   * Allocate and initialize vfio_device so it can be registered to vfio
> @@ -548,6 +550,13 @@ int vfio_init_device(struct vfio_device *device, struct device *dev,
>  {
>  	int ret;
>  
> +	ret = ida_alloc_max(&vfio.device_ida, MINORMASK, GFP_KERNEL);
> +	if (ret < 0) {
> +		dev_dbg(dev, "Error to alloc index\n");
> +		return ret;
> +	}
> +
> +	device->index = ret;
>  	init_completion(&device->comp);
>  	device->dev = dev;
>  	device->ops = ops;
> @@ -558,11 +567,15 @@ int vfio_init_device(struct vfio_device *device, struct device *dev,
>  			goto out_uninit;
>  	}
>  
> -	kref_init(&device->kref);
> +	device_initialize(&device->device);
> +	device->device.release = vfio_device_release;
> +	device->device.class = vfio.device_class;
> +	device->device.parent = device->dev;
>  	return 0;
>  
>  out_uninit:
>  	vfio_release_device_set(device);
> +	ida_free(&vfio.device_ida, device->index);
>  	return ret;
>  }
>  EXPORT_SYMBOL_GPL(vfio_init_device);
> @@ -659,6 +672,7 @@ static int __vfio_register_dev(struct vfio_device *device,
>  		struct vfio_group *group)
>  {
>  	struct vfio_device *existing_device;
> +	int ret;
>  
>  	if (IS_ERR(group))
>  		return PTR_ERR(group);
> @@ -675,16 +689,21 @@ static int __vfio_register_dev(struct vfio_device *device,
>  		dev_WARN(device->dev, "Device already exists on group %d\n",
>  			 iommu_group_id(group->iommu_group));
>  		vfio_device_put_registration(existing_device);
> -		if (group->type == VFIO_NO_IOMMU ||
> -		    group->type == VFIO_EMULATED_IOMMU)
> -			iommu_group_remove_device(device->dev);
> -		vfio_group_put(group);
> -		return -EBUSY;
> +		ret = -EBUSY;
> +		goto err_out;
>  	}
>  
>  	/* Our reference on group is moved to the device */
>  	device->group = group;
>  
> +	ret = dev_set_name(&device->device, "vfio%d", device->index);
> +	if (ret)
> +		goto err_out;
> +
> +	ret = device_add(&device->device);
> +	if (ret)
> +		goto err_out;
> +
>  	/* Refcounting can't start until the driver calls register */
>  	refcount_set(&device->refcount, 1);
>  
> @@ -693,6 +712,12 @@ static int __vfio_register_dev(struct vfio_device *device,
>  	mutex_unlock(&group->device_lock);
>  
>  	return 0;
> +err_out:
> +	if (group->type == VFIO_NO_IOMMU ||
> +	    group->type == VFIO_EMULATED_IOMMU)
> +		iommu_group_remove_device(device->dev);
> +	vfio_group_put(group);
> +	return ret;
>  }
>  
>  int vfio_register_group_dev(struct vfio_device *device)
> @@ -779,6 +804,9 @@ void vfio_unregister_group_dev(struct vfio_device *device)
>  	list_del(&device->group_next);
>  	mutex_unlock(&group->device_lock);
>  
> +	/* Balances device_add in register path */
> +	device_del(&device->device);
> +
>  	if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
>  		iommu_group_remove_device(device->dev);
>  
> @@ -2362,6 +2390,7 @@ static int __init vfio_init(void)
>  	int ret;
>  
>  	ida_init(&vfio.group_ida);
> +	ida_init(&vfio.device_ida);
>  	mutex_init(&vfio.group_lock);
>  	mutex_init(&vfio.iommu_drivers_lock);
>  	INIT_LIST_HEAD(&vfio.group_list);
> @@ -2377,11 +2406,18 @@ static int __init vfio_init(void)
>  	vfio.class = class_create(THIS_MODULE, "vfio");
>  	if (IS_ERR(vfio.class)) {
>  		ret = PTR_ERR(vfio.class);
> -		goto err_class;
> +		goto err_group_class;
>  	}
>  
>  	vfio.class->devnode = vfio_devnode;
>  
> +	/* /sys/class/vfio-dev/vfioX */
> +	vfio.device_class = class_create(THIS_MODULE, "vfio-dev");
> +	if (IS_ERR(vfio.device_class)) {
> +		ret = PTR_ERR(vfio.device_class);
> +		goto err_dev_class;
> +	}
> +
>  	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
>  	if (ret)
>  		goto err_alloc_chrdev;
> @@ -2398,9 +2434,12 @@ static int __init vfio_init(void)
>  err_driver_register:
>  	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
>  err_alloc_chrdev:
> +	class_destroy(vfio.device_class);
> +	vfio.device_class = NULL;
> +err_dev_class:
>  	class_destroy(vfio.class);
>  	vfio.class = NULL;
> -err_class:
> +err_group_class:
>  	misc_deregister(&vfio_dev);
>  	return ret;
>  }
> @@ -2412,8 +2451,11 @@ static void __exit vfio_cleanup(void)
>  #ifdef CONFIG_VFIO_NOIOMMU
>  	vfio_unregister_iommu_driver(&vfio_noiommu_ops);
>  #endif
> +	ida_destroy(&vfio.device_ida);
>  	ida_destroy(&vfio.group_ida);
>  	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
> +	class_destroy(vfio.device_class);
> +	vfio.device_class = NULL;
>  	class_destroy(vfio.class);
>  	vfio.class = NULL;
>  	misc_deregister(&vfio_dev);
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 3cf857b1eec7..ee399a768070 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -47,7 +47,8 @@ struct vfio_device {
>  	struct kvm *kvm;
>  
>  	/* Members below here are private, not for driver use */
> -	struct kref kref;	/* object life cycle */
> +	unsigned int index;
> +	struct device device;	/* device.kref covers object life circle */
>  	refcount_t refcount;	/* user count on registered device*/
>  	unsigned int open_count;
>  	struct completion comp;
> @@ -178,10 +179,9 @@ struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev,
>  int vfio_init_device(struct vfio_device *device, struct device *dev,
>  		     const struct vfio_device_ops *ops);
>  void vfio_free_device(struct vfio_device *device);
> -void vfio_device_release(struct kref *kref);
>  static inline void vfio_put_device(struct vfio_device *device)
>  {
> -	kref_put(&device->kref, vfio_device_release);
> +	put_device(&device->device);
>  }
>  
>  int vfio_register_group_dev(struct vfio_device *device);

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ