netdev - Re: [PATCH] vhost: introduce vDPA based backend

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]

Message-ID: <20200218135359.GA9608@ziepe.ca>
Date:   Tue, 18 Feb 2020 09:53:59 -0400
From:   Jason Gunthorpe <jgg@...pe.ca>
To:     Tiwei Bie <tiwei.bie@...el.com>
Cc:     mst@...hat.com, jasowang@...hat.com, linux-kernel@...r.kernel.org,
        kvm@...r.kernel.org, virtualization@...ts.linux-foundation.org,
        netdev@...r.kernel.org, shahafs@...lanox.com,
        rob.miller@...adcom.com, haotian.wang@...ive.com,
        eperezma@...hat.com, lulu@...hat.com, parav@...lanox.com,
        rdunlap@...radead.org, hch@...radead.org, jiri@...lanox.com,
        hanand@...inx.com, mhabets@...arflare.com,
        maxime.coquelin@...hat.com, lingshan.zhu@...el.com,
        dan.daly@...el.com, cunming.liang@...el.com, zhihong.wang@...el.com
Subject: Re: [PATCH] vhost: introduce vDPA based backend

On Fri, Jan 31, 2020 at 11:36:51AM +0800, Tiwei Bie wrote:

> +static int vhost_vdpa_alloc_minor(struct vhost_vdpa *v)
> +{
> +	return idr_alloc(&vhost_vdpa.idr, v, 0, MINORMASK + 1,
> +			 GFP_KERNEL);
> +}

Please don't use idr in new code, use xarray directly

> +static int vhost_vdpa_probe(struct device *dev)
> +{
> +	struct vdpa_device *vdpa = dev_to_vdpa(dev);
> +	const struct vdpa_config_ops *ops = vdpa->config;
> +	struct vhost_vdpa *v;
> +	struct device *d;
> +	int minor, nvqs;
> +	int r;
> +
> +	/* Currently, we only accept the network devices. */
> +	if (ops->get_device_id(vdpa) != VIRTIO_ID_NET) {
> +		r = -ENOTSUPP;
> +		goto err;
> +	}
> +
> +	v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
> +	if (!v) {
> +		r = -ENOMEM;
> +		goto err;
> +	}
> +
> +	nvqs = VHOST_VDPA_VQ_MAX;
> +
> +	v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue),
> +			       GFP_KERNEL);
> +	if (!v->vqs) {
> +		r = -ENOMEM;
> +		goto err_alloc_vqs;
> +	}
> +
> +	mutex_init(&v->mutex);
> +	atomic_set(&v->opened, 0);
> +
> +	v->vdpa = vdpa;
> +	v->nvqs = nvqs;
> +	v->virtio_id = ops->get_device_id(vdpa);
> +
> +	mutex_lock(&vhost_vdpa.mutex);
> +
> +	minor = vhost_vdpa_alloc_minor(v);
> +	if (minor < 0) {
> +		r = minor;
> +		goto err_alloc_minor;
> +	}
> +
> +	d = device_create(vhost_vdpa.class, NULL,
> +			  MKDEV(MAJOR(vhost_vdpa.devt), minor),
> +			  v, "%d", vdpa->index);
> +	if (IS_ERR(d)) {
> +		r = PTR_ERR(d);
> +		goto err_device_create;
> +	}
> +

I can't understand what this messing around with major/minor numbers
does. Without allocating a cdev via cdev_add/etc there is only a
single char dev in existence here. This and the stuff in
vhost_vdpa_open() looks non-functional.

> +static void vhost_vdpa_remove(struct device *dev)
> +{
> +	DEFINE_WAIT_FUNC(wait, woken_wake_function);
> +	struct vhost_vdpa *v = dev_get_drvdata(dev);
> +	int opened;
> +
> +	add_wait_queue(&vhost_vdpa.release_q, &wait);
> +
> +	do {
> +		opened = atomic_cmpxchg(&v->opened, 0, 1);
> +		if (!opened)
> +			break;
> +		wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
> +	} while (1);
> +
> +	remove_wait_queue(&vhost_vdpa.release_q, &wait);

*barf* use the normal refcount pattern please

read side:

  refcount_inc_not_zero(uses)
  //stuff
  if (refcount_dec_and_test(uses))
     complete(completer)

destroy side:
  if (refcount_dec_and_test(uses))
     complete(completer)
  wait_for_completion(completer)
  // refcount now permanently == 0

Use a completion in driver code

> +	mutex_lock(&vhost_vdpa.mutex);
> +	device_destroy(vhost_vdpa.class,
> +		       MKDEV(MAJOR(vhost_vdpa.devt), v->minor));
> +	vhost_vdpa_free_minor(v->minor);
> +	mutex_unlock(&vhost_vdpa.mutex);
> +	kfree(v->vqs);
> +	kfree(v);

This use after-fress vs vhost_vdpa_open prior to it setting the open
bit. Maybe use xarray, rcu and kfree_rcu ..

> +static int __init vhost_vdpa_init(void)
> +{
> +	int r;
> +
> +	idr_init(&vhost_vdpa.idr);
> +	mutex_init(&vhost_vdpa.mutex);
> +	init_waitqueue_head(&vhost_vdpa.release_q);
> +
> +	/* /dev/vhost-vdpa/$vdpa_device_index */
> +	vhost_vdpa.class = class_create(THIS_MODULE, "vhost-vdpa");
> +	if (IS_ERR(vhost_vdpa.class)) {
> +		r = PTR_ERR(vhost_vdpa.class);
> +		goto err_class;
> +	}
> +
> +	vhost_vdpa.class->devnode = vhost_vdpa_devnode;
> +
> +	r = alloc_chrdev_region(&vhost_vdpa.devt, 0, MINORMASK + 1,
> +				"vhost-vdpa");
> +	if (r)
> +		goto err_alloc_chrdev;
> +
> +	cdev_init(&vhost_vdpa.cdev, &vhost_vdpa_fops);
> +	r = cdev_add(&vhost_vdpa.cdev, vhost_vdpa.devt, MINORMASK + 1);
> +	if (r)
> +		goto err_cdev_add;

It is very strange, is the intention to create a single global char
dev?

If so, why is there this:

+static int vhost_vdpa_open(struct inode *inode, struct file *filep)
+{
+	struct vhost_vdpa *v;
+	struct vhost_dev *dev;
+	struct vhost_virtqueue **vqs;
+	int nvqs, i, r, opened;
+
+	v = vhost_vdpa_get_from_minor(iminor(inode));

?

If the idea is to create a per-vdpa char dev then this stuff belongs
in vhost_vdpa_probe(), the cdev should be part of the vhost_vdpa, and
the above should be container_of not an idr lookup.

Jason