Date:   Tue, 7 Feb 2023 11:41:13 +0800
From:   Yan Zhao <yan.y.zhao@intel.com>
To:     Yi Liu <yi.l.liu@intel.com>
CC:     <alex.williamson@redhat.com>, <jgg@nvidia.com>,
        <kevin.tian@intel.com>, <linux-s390@vger.kernel.org>,
        <yi.y.sun@linux.intel.com>, <kvm@vger.kernel.org>,
        <mjrosato@linux.ibm.com>, <jasowang@redhat.com>,
        <cohuck@redhat.com>, <linux-kernel@vger.kernel.org>,
        <peterx@redhat.com>, <eric.auger@redhat.com>,
        <nicolinc@nvidia.com>, <shameerali.kolothum.thodi@huawei.com>,
        <suravee.suthikulpanit@amd.com>, <chao.p.peng@linux.intel.com>,
        <lulu@redhat.com>, <intel-gvt-dev@lists.freedesktop.org>,
        <intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH v2 13/14] vfio: Add ioctls for device cdev using iommufd
Message-ID: <Y+HIWRM/TjWcuT6I@yzhao56-desk.sh.intel.com>
Reply-To: Yan Zhao <yan.y.zhao@intel.com>
References: <20230206090532.95598-1-yi.l.liu@intel.com>
 <20230206090532.95598-14-yi.l.liu@intel.com>
Content-Type: text/plain; charset="us-ascii"
Content-Disposition: inline
In-Reply-To: <20230206090532.95598-14-yi.l.liu@intel.com>
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?EKCmzgwGmE3ZSC+zzqKx5fRGGQ9vb/QJ1yNyXcFrz89sjyO+SKmcp2rOKtWP?=
 =?us-ascii?Q?9EZV7PRFokRw9n3cU+Xi4DHFAYKk3Oat/NKgX5NDv5BtIlQP6lSyCp06Q1Mg?=
 =?us-ascii?Q?2m+IyBNCjRXD9JGpoQBbM8pWsFQZ6DaEA/rGgaazsDxtjLwvt+vZOYY9arTE?=
 =?us-ascii?Q?EV4TLySPmRWtbeaq/EdF0hM0Phg+Qu2Eqf1/uk5vTd+Xae1fTcRc3i3bIDI4?=
 =?us-ascii?Q?9yy1lE8ldZ1Enb3+J2toWeJsPrbFIuFl2X2wvz7RbdhJ2a1H4dJBoAOXcM5v?=
 =?us-ascii?Q?RnYDKhm/H2iy+IgQzNGlwIkVzdgiPj0dnHsM0X4T+xjsP+A7AXShK/LpRA28?=
 =?us-ascii?Q?ViAuoO8Ce9/XeN50BBr04adn8chG3Bcv04KVDmbLXsjYThuoCbhmZVLt38+R?=
 =?us-ascii?Q?PNbcRNlTfuI1ZD5IBVs8YHcFY/1LdfQtKUywx6RPEuNeVtqYDG8Zk8aSzbHU?=
 =?us-ascii?Q?QaMfcRkEtLmxsH+0/1ZRbch4NncU1FdVmBgKqSlaUpBGQFv6MIbYOXHINXBW?=
 =?us-ascii?Q?VrpL6P8ItTdjDFR0yRhqhh4xXt7Gc1iIyIZ2Abnptfk5d1ZhbfHCoBV3vI2l?=
 =?us-ascii?Q?sQy6INDdrjYH2/GlkNle47iPvmaUt9TCBdJrrdmdCxKo26pqe7wKzf0E55Ws?=
 =?us-ascii?Q?MK/0k9GW60zpZt2xVYmyVAx0J/vsRVwi6gx8g+nKOIlQo97M+RCFE6T+u5x0?=
 =?us-ascii?Q?0Djvx7MrrxEOBOkszLiBZS3r7OuCalcd4WSPpSpz0jZ2kRG98iXUXKEsdqxN?=
 =?us-ascii?Q?IJsNkslKXS6k2RdabbkRJnQ7Z12Fdz5ve/bhU3JXxBf3IbLr4rMjlKS/g+dy?=
 =?us-ascii?Q?oFaUG8CRin8MJxu02D4OKAKPUe3y3N4Hm2Fch+UYj1GAIDTC5PIOgTtInZYt?=
 =?us-ascii?Q?uDPqbRrjlZMy1oUUME8XWC7TVTcHbPcPQcbWnmYnBW8A7otfkRNLXKJtFJvr?=
 =?us-ascii?Q?5zZOdSd1hH+cYsoML5qldWZSqgPkQObxQ+BhNfvXGIDkRSimVoE4U500GFiS?=
 =?us-ascii?Q?4FYvoVgZSwgzYJL/4BJnJn9tz8Kj/gjz0a/LtsA01tAb/jjDwDLGKS35kc8H?=
 =?us-ascii?Q?BFZ8MzikqwG5Jll/jmwVS54+1qRpfK8DfqiN13kcFkIYJdo6DiKte4qdlWHy?=
 =?us-ascii?Q?osjVAba3ZP9iK80q/O4sps5qiRKScrygearQsJdW3hIQ5q1kjZfxX5/CnG6z?=
 =?us-ascii?Q?aE4/oq4l4v+53M4YBNAVqkLspbDSSyB/qn5DFq9xNZc+MtlVhMHiWZQvpgF6?=
 =?us-ascii?Q?fbFUCQ/k/mVVpC5MtWQZfs3vMs0+qEDiP10vr8UiWSRzZhsa9PjxAZ1hi1fw?=
 =?us-ascii?Q?2w9Ey5or6P/QUesujWXqOWic1cnE73NH+y41h1B/WAf6BdjIJ6QRTG9l0f0u?=
 =?us-ascii?Q?buRY/4q4RxsNuTiXfEoOOfvSZ//s8JVqQA9W6bqFRnfJ6rdLH7nzoRaSchxj?=
 =?us-ascii?Q?5o6k4Tto84EMlU7JiCjL1YPBU2z1kK0uNJI1AdP95Ky/2FYhbQIbC0WT44oa?=
 =?us-ascii?Q?XDVz8eZtJvS3K2+7zEK0IoM7hDC2rwNXC1IVAzxdtIFh3Qt236Y3/eykpAkp?=
 =?us-ascii?Q?V1FihYpzwWikRbhrW32YvnAe2PDu9MJ1T0enq2g1OwOzWKWyOaNxGY2qISdF?=
 =?us-ascii?Q?pg=3D=3D?=
X-MS-Exchange-CrossTenant-Network-Message-Id: 3bb99a40-11fb-4e0b-996f-08db08c077dd
X-MS-Exchange-CrossTenant-AuthSource: DS7PR11MB5966.namprd11.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 07 Feb 2023 04:04:54.2842
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 46c98d88-e344-4ed4-8496-4ed7712e255d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: NhKkEqzY9FE1XnLxeQDByz4ZXdLccCq7x/nSxJ+TULG6apAQn8HCzddOiEtN7UkGU7iWvQ3p+DFif32MhgXVyg==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SA3PR11MB7582
X-OriginatorOrg: intel.com
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Feb 06, 2023 at 01:05:31AM -0800, Yi Liu wrote:
...

> +void vfio_device_cdev_close(struct vfio_device_file *df)
> +{
> +	mutex_lock(&df->device->dev_set->lock);
> +	vfio_device_close(df);
> +	vfio_device_put_kvm(df->device);
> +	mutex_unlock(&df->device->dev_set->lock);
> +}
> +

...

> +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;
> +	unsigned long minsz;
> +	struct fd f;
> +	int ret;
> +
> +	minsz = offsetofend(struct vfio_device_bind_iommufd, iommufd);
> +
> +	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;
> +
> +	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 first 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 + minsz,
> +			   &bind.out_devid,
> +			   sizeof(bind.out_devid)) ? -EFAULT : 0;
> +	if (ret)
> +		goto out_close_device;
> +
> +	if (iommufd)
> +		fdput(f);
> +	else if (df->noiommu)
> +		dev_warn(device->dev, "vfio-noiommu device used by user "
> +			 "(%s:%d)\n", current->comm, task_pid_nr(current));
> +	mutex_unlock(&device->dev_set->lock);
> +	return 0;
> +
> +out_close_device:
> +	vfio_device_close(df);
vfio_device_close() is called here if any error after vfio_device_open().
But it will also be called unconditionally in vfio_device_cdev_close() and
cause a wrong value of device->open_count.

df->access_granted in patch 07 can also be of wrong true value after
this vfio_device_close().


> +out_put_kvm:
> +	vfio_device_put_kvm(device);
> +out_put_file:
> +	if (iommufd)
> +		fdput(f);
> +out_unlock:
> +	df->iommufd = NULL;
> +	df->noiommu = false;
> +	mutex_unlock(&device->dev_set->lock);
> +	return ret;
> +}
> +