Message-ID: <20191118054339-mutt-send-email-mst@kernel.org>
Date:   Mon, 18 Nov 2019 05:44:25 -0500
From:   "Michael S. Tsirkin" <mst@...hat.com>
To:     Jason Wang <jasowang@...hat.com>
Cc:     kvm@...r.kernel.org, linux-s390@...r.kernel.org,
        linux-kernel@...r.kernel.org, dri-devel@...ts.freedesktop.org,
        intel-gfx@...ts.freedesktop.org,
        intel-gvt-dev@...ts.freedesktop.org, kwankhede@...dia.com,
        alex.williamson@...hat.com, tiwei.bie@...el.com,
        virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
        cohuck@...hat.com, maxime.coquelin@...hat.com,
        cunming.liang@...el.com, zhihong.wang@...el.com,
        rob.miller@...adcom.com, xiao.w.wang@...el.com,
        haotian.wang@...ive.com, zhenyuw@...ux.intel.com,
        zhi.a.wang@...el.com, jani.nikula@...ux.intel.com,
        joonas.lahtinen@...ux.intel.com, rodrigo.vivi@...el.com,
        airlied@...ux.ie, daniel@...ll.ch, farman@...ux.ibm.com,
        pasic@...ux.ibm.com, sebott@...ux.ibm.com, oberpar@...ux.ibm.com,
        heiko.carstens@...ibm.com, gor@...ux.ibm.com,
        borntraeger@...ibm.com, akrowiak@...ux.ibm.com,
        freude@...ux.ibm.com, lingshan.zhu@...el.com, eperezma@...hat.com,
        lulu@...hat.com, parav@...lanox.com,
        christophe.de.dinechin@...il.com, kevin.tian@...el.com,
        stefanha@...hat.com, rdunlap@...radead.org, hch@...radead.org,
        gregkh@...uxfoundation.org, jgg@...lanox.com
Subject: Re: [PATCH V12 5/6] virtio: introduce a mdev based transport

On Mon, Nov 18, 2019 at 02:17:02PM +0800, Jason Wang wrote:
> This patch introduces a new mdev transport for virtio. This is used to
> use kernel virtio driver to drive the mediated device that is capable
> of populating virtqueue directly.
> 
> A new virtio-mdev driver will be registered to the mdev bus, when a
> new virtio-mdev device is probed, it will register the device with
> mdev based config ops. This means it is a software transport between
> mdev driver and mdev device. The transport was implemented through
> bus_ops of mdev parent.
> 
> Signed-off-by: Jason Wang <jasowang@...hat.com>
> ---
>  drivers/virtio/Kconfig       |  13 ++
>  drivers/virtio/Makefile      |   1 +
>  drivers/virtio/virtio_mdev.c | 409 +++++++++++++++++++++++++++++++++++
>  include/linux/mdev_virtio.h  |   5 +
>  4 files changed, 428 insertions(+)
>  create mode 100644 drivers/virtio/virtio_mdev.c
> 
> diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
> index 078615cf2afc..6a89b3de97d3 100644
> --- a/drivers/virtio/Kconfig
> +++ b/drivers/virtio/Kconfig
> @@ -43,6 +43,19 @@ config VIRTIO_PCI_LEGACY
>  
>  	  If unsure, say Y.
>  
> +config VIRTIO_MDEV
> +	tristate "MDEV driver for virtio devices"
> +	depends on MDEV_VIRTIO
> +	default n
> +	help
> +	  This driver provides support for virtio based paravirtual
> +	  device driver over MDEV bus. For this to be useful, you need
> +	  an appropriate virtio mdev device implementation that
> +	  operates on a physical device to allow the datapath of virtio
> +	  to be offloaded to hardware.
> +
> +	  If unsure, say M.
> +
>  config VIRTIO_PMEM
>  	tristate "Support for virtio pmem driver"
>  	depends on VIRTIO
> diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
> index 3a2b5c5dcf46..f2997b6c812f 100644
> --- a/drivers/virtio/Makefile
> +++ b/drivers/virtio/Makefile
> @@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
>  virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
>  obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
>  obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
> +obj-$(CONFIG_VIRTIO_MDEV) += virtio_mdev.o
> diff --git a/drivers/virtio/virtio_mdev.c b/drivers/virtio/virtio_mdev.c
> new file mode 100644
> index 000000000000..7fdb42f055df
> --- /dev/null
> +++ b/drivers/virtio/virtio_mdev.c
> @@ -0,0 +1,409 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * VIRTIO based driver for Mediated device
> + *
> + * Copyright (c) 2019, Red Hat. All rights reserved.
> + *     Author: Jason Wang <jasowang@...hat.com>
> + *
> + */
> +
> +#include <linux/init.h>
> +#include <linux/module.h>
> +#include <linux/device.h>
> +#include <linux/kernel.h>
> +#include <linux/slab.h>
> +#include <linux/uuid.h>
> +#include <linux/virtio.h>
> +#include <linux/mdev_virtio.h>
> +#include <linux/virtio_config.h>
> +#include <linux/virtio_ring.h>
> +
> +#define DRIVER_VERSION  "0.1"
> +#define DRIVER_AUTHOR   "Red Hat Corporation"
> +#define DRIVER_DESC     "VIRTIO based driver for Mediated device"
> +
> +#define to_virtio_mdev_device(dev) \
> +	container_of(dev, struct virtio_mdev_device, vdev)
> +
> +struct virtio_mdev_device {
> +	struct virtio_device vdev;
> +	struct mdev_device *mdev;
> +	u64 features;
> +
> +	/* The lock to protect virtqueue list */
> +	spinlock_t lock;
> +	/* List of virtio_mdev_vq_info */
> +	struct list_head virtqueues;
> +};
> +
> +struct virtio_mdev_vq_info {
> +	/* the actual virtqueue */
> +	struct virtqueue *vq;
> +
> +	/* the list node for the virtqueues list */
> +	struct list_head node;
> +};
> +
> +static struct mdev_device *vm_get_mdev(struct virtio_device *vdev)
> +{
> +	struct virtio_mdev_device *vm_dev = to_virtio_mdev_device(vdev);
> +	struct mdev_device *mdev = vm_dev->mdev;
> +
> +	return mdev;
> +}
> +
> +static void virtio_mdev_get(struct virtio_device *vdev, unsigned offset,
> +			    void *buf, unsigned len)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	ops->get_config(mdev, offset, buf, len);
> +}
> +
> +static void virtio_mdev_set(struct virtio_device *vdev, unsigned offset,
> +			    const void *buf, unsigned len)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	ops->set_config(mdev, offset, buf, len);
> +}
> +
> +static u32 virtio_mdev_generation(struct virtio_device *vdev)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +
> +	if (ops->get_generation)
> +		return ops->get_generation(mdev);
> +
> +	return 0;
> +}
> +
> +static u8 virtio_mdev_get_status(struct virtio_device *vdev)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	return ops->get_status(mdev);
> +}
> +
> +static void virtio_mdev_set_status(struct virtio_device *vdev, u8 status)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	return ops->set_status(mdev, status);
> +}
> +
> +static void virtio_mdev_reset(struct virtio_device *vdev)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	return ops->set_status(mdev, 0);
> +}
> +
> +static bool virtio_mdev_notify(struct virtqueue *vq)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vq->vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	ops->kick_vq(mdev, vq->index);
> +
> +	return true;
> +}
> +
> +static irqreturn_t virtio_mdev_config_cb(void *private)
> +{
> +	struct virtio_mdev_device *vm_dev = private;
> +
> +	virtio_config_changed(&vm_dev->vdev);
> +
> +	return IRQ_HANDLED;
> +}
> +
> +static irqreturn_t virtio_mdev_virtqueue_cb(void *private)
> +{
> +	struct virtio_mdev_vq_info *info = private;
> +
> +	return vring_interrupt(0, info->vq);
> +}
> +
> +static struct virtqueue *
> +virtio_mdev_setup_vq(struct virtio_device *vdev, unsigned int index,
> +		     void (*callback)(struct virtqueue *vq),
> +		     const char *name, bool ctx)
> +{
> +	struct virtio_mdev_device *vm_dev = to_virtio_mdev_device(vdev);
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +	struct virtio_mdev_vq_info *info;
> +	struct virtio_mdev_callback cb;
> +	struct virtqueue *vq;
> +	u64 desc_addr, driver_addr, device_addr;
> +	unsigned long flags;
> +	u32 align, num;
> +	int err;
> +
> +	if (!name)
> +		return NULL;
> +
> +	/* Queue shouldn't already be set up. */
> +	if (ops->get_vq_ready(mdev, index))
> +		return ERR_PTR(-ENOENT);
> +
> +	/* Allocate and fill out our active queue description */
> +	info = kmalloc(sizeof(*info), GFP_KERNEL);
> +	if (!info)
> +		return ERR_PTR(-ENOMEM);
> +
> +	num = ops->get_vq_num_max(mdev);
> +	if (num == 0) {
> +		err = -ENOENT;
> +		goto error_new_virtqueue;
> +	}
> +
> +	/* Create the vring */
> +	align = ops->get_vq_align(mdev);
> +	vq = vring_create_virtqueue(index, num, align, vdev,
> +				    true, true, ctx,
> +				    virtio_mdev_notify, callback, name);
> +	if (!vq) {
> +		err = -ENOMEM;
> +		goto error_new_virtqueue;
> +	}
> +
> +	/* Setup virtqueue callback */
> +	cb.callback = virtio_mdev_virtqueue_cb;
> +	cb.private = info;
> +	ops->set_vq_cb(mdev, index, &cb);
> +	ops->set_vq_num(mdev, index, virtqueue_get_vring_size(vq));
> +
> +	desc_addr = virtqueue_get_desc_addr(vq);
> +	driver_addr = virtqueue_get_avail_addr(vq);
> +	device_addr = virtqueue_get_used_addr(vq);
> +
> +	if (ops->set_vq_address(mdev, index,
> +				desc_addr, driver_addr,
> +				device_addr)) {
> +		err = -EINVAL;
> +		goto err_vq;
> +	}
> +
> +	ops->set_vq_ready(mdev, index, 1);
> +
> +	vq->priv = info;
> +	info->vq = vq;
> +
> +	spin_lock_irqsave(&vm_dev->lock, flags);
> +	list_add(&info->node, &vm_dev->virtqueues);
> +	spin_unlock_irqrestore(&vm_dev->lock, flags);
> +
> +	return vq;
> +
> +err_vq:
> +	vring_del_virtqueue(vq);
> +error_new_virtqueue:
> +	ops->set_vq_ready(mdev, index, 0);
> +	WARN_ON(ops->get_vq_ready(mdev, index));
> +	kfree(info);
> +	return ERR_PTR(err);
> +}
> +
> +static void virtio_mdev_del_vq(struct virtqueue *vq)
> +{
> +	struct virtio_mdev_device *vm_dev = to_virtio_mdev_device(vq->vdev);
> +	struct mdev_device *mdev = vm_dev->mdev;
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +	struct virtio_mdev_vq_info *info = vq->priv;
> +	unsigned int index = vq->index;
> +	unsigned long flags;
> +
> +	spin_lock_irqsave(&vm_dev->lock, flags);
> +	list_del(&info->node);
> +	spin_unlock_irqrestore(&vm_dev->lock, flags);
> +
> +	/* Select and deactivate the queue */
> +	ops->set_vq_ready(mdev, index, 0);
> +	WARN_ON(ops->get_vq_ready(mdev, index));
> +
> +	vring_del_virtqueue(vq);
> +
> +	kfree(info);
> +}
> +
> +static void virtio_mdev_del_vqs(struct virtio_device *vdev)
> +{
> +	struct virtqueue *vq, *n;
> +
> +	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
> +		virtio_mdev_del_vq(vq);
> +}
> +
> +static int virtio_mdev_find_vqs(struct virtio_device *vdev, unsigned nvqs,
> +				struct virtqueue *vqs[],
> +				vq_callback_t *callbacks[],
> +				const char * const names[],
> +				const bool *ctx,
> +				struct irq_affinity *desc)
> +{
> +	struct virtio_mdev_device *vm_dev = to_virtio_mdev_device(vdev);
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +	struct virtio_mdev_callback cb;
> +	int i, err, queue_idx = 0;
> +
> +	for (i = 0; i < nvqs; ++i) {
> +		if (!names[i]) {
> +			vqs[i] = NULL;
> +			continue;
> +		}
> +
> +		vqs[i] = virtio_mdev_setup_vq(vdev, queue_idx++,
> +					      callbacks[i], names[i], ctx ?
> +					      ctx[i] : false);
> +		if (IS_ERR(vqs[i])) {
> +			err = PTR_ERR(vqs[i]);
> +			goto err_setup_vq;
> +		}
> +	}
> +
> +	cb.callback = virtio_mdev_config_cb;
> +	cb.private = vm_dev;
> +	ops->set_config_cb(mdev, &cb);
> +
> +	return 0;
> +
> +err_setup_vq:
> +	virtio_mdev_del_vqs(vdev);
> +	return err;
> +}
> +
> +static u64 virtio_mdev_get_features(struct virtio_device *vdev)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	return ops->get_features(mdev);
> +}
> +
> +static int virtio_mdev_finalize_features(struct virtio_device *vdev)
> +{
> +	struct mdev_device *mdev = vm_get_mdev(vdev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +
> +	/* Give virtio_ring a chance to accept features. */
> +	vring_transport_features(vdev);
> +
> +	return ops->set_features(mdev, vdev->features);
> +}
> +
> +static const char *virtio_mdev_bus_name(struct virtio_device *vdev)
> +{
> +	struct virtio_mdev_device *vm_dev = to_virtio_mdev_device(vdev);
> +	struct mdev_device *mdev = vm_dev->mdev;
> +
> +	return dev_name(mdev_dev(mdev));
> +}
> +
> +static const struct virtio_config_ops virtio_mdev_config_ops = {
> +	.get		= virtio_mdev_get,
> +	.set		= virtio_mdev_set,
> +	.generation	= virtio_mdev_generation,
> +	.get_status	= virtio_mdev_get_status,
> +	.set_status	= virtio_mdev_set_status,
> +	.reset		= virtio_mdev_reset,
> +	.find_vqs	= virtio_mdev_find_vqs,
> +	.del_vqs	= virtio_mdev_del_vqs,
> +	.get_features	= virtio_mdev_get_features,
> +	.finalize_features = virtio_mdev_finalize_features,
> +	.bus_name	= virtio_mdev_bus_name,
> +};
> +
> +static void virtio_mdev_release_dev(struct device *_d)
> +{
> +	struct virtio_device *vdev =
> +	       container_of(_d, struct virtio_device, dev);
> +	struct virtio_mdev_device *vm_dev =
> +	       container_of(vdev, struct virtio_mdev_device, vdev);
> +	struct mdev_device *mdev = vm_dev->mdev;
> +
> +	devm_kfree(mdev_dev(mdev), vm_dev);
> +}
> +
> +static int virtio_mdev_probe(struct device *dev)
> +{
> +	struct mdev_device *mdev = mdev_virtio_from_dev(dev);
> +	const struct mdev_virtio_ops *ops = mdev_virtio_get_ops(mdev);
> +	struct virtio_mdev_device *vm_dev;
> +	int rc;
> +
> +	vm_dev = devm_kzalloc(dev, sizeof(*vm_dev), GFP_KERNEL);
> +	if (!vm_dev)
> +		return -ENOMEM;
> +
> +	vm_dev->vdev.dev.parent = dev;
> +	vm_dev->vdev.dev.release = virtio_mdev_release_dev;
> +	vm_dev->vdev.config = &virtio_mdev_config_ops;
> +	vm_dev->mdev = mdev;
> +	INIT_LIST_HEAD(&vm_dev->virtqueues);
> +	spin_lock_init(&vm_dev->lock);
> +
> +	vm_dev->vdev.id.device = ops->get_device_id(mdev);
> +	if (vm_dev->vdev.id.device == 0)
> +		return -ENODEV;
> +
> +	vm_dev->vdev.id.vendor = ops->get_vendor_id(mdev);
> +	rc = register_virtio_device(&vm_dev->vdev);
> +	if (rc)
> +		put_device(dev);
> +	else
> +		dev_set_drvdata(dev, vm_dev);
> +
> +	return rc;
> +}
> +
> +static void virtio_mdev_remove(struct device *dev)
> +{
> +	struct virtio_mdev_device *vm_dev = dev_get_drvdata(dev);
> +
> +	unregister_virtio_device(&vm_dev->vdev);
> +}
> +
> +static const struct mdev_virtio_class_id virtio_id_table[] = {
> +	{ MDEV_VIRTIO_CLASS_ID_VIRTIO },
> +	{ 0 },
> +};
> +

Do we still need the class ID? It's a virtio mdev bus,
do we need a virtio class as well?

> +MODULE_DEVICE_TABLE(mdev_virtio, virtio_id_table);
> +
> +static struct mdev_virtio_driver virtio_mdev_driver = {
> +	.drv = {
> +		.name	= "virtio_mdev",
> +		.probe	= virtio_mdev_probe,
> +		.remove = virtio_mdev_remove,
> +	},
> +	.id_table = virtio_id_table,
> +};
> +
> +static int __init virtio_mdev_init(void)
> +{
> +	return mdev_register_driver(&virtio_mdev_driver.drv, THIS_MODULE,
> +				    &mdev_virtio_bus_type);
> +}
> +
> +static void __exit virtio_mdev_exit(void)
> +{
> +	mdev_unregister_driver(&virtio_mdev_driver.drv);
> +}
> +
> +module_init(virtio_mdev_init)
> +module_exit(virtio_mdev_exit)
> +
> +MODULE_VERSION(DRIVER_VERSION);
> +MODULE_LICENSE("GPL v2");
> +MODULE_AUTHOR(DRIVER_AUTHOR);
> +MODULE_DESCRIPTION(DRIVER_DESC);
> diff --git a/include/linux/mdev_virtio.h b/include/linux/mdev_virtio.h
> index ef2dbb6c383a..5f75f3cf59e1 100644
> --- a/include/linux/mdev_virtio.h
> +++ b/include/linux/mdev_virtio.h
> @@ -25,6 +25,11 @@ struct virtio_mdev_callback {
>  	void *private;
>  };
>  
> +enum {
> +	MDEV_VIRTIO_CLASS_ID_VIRTIO = 1,
> +	/* New entries must be added here */
> +};
> +
>  /**
>   * struct mdev_virtio_device_ops - Structure to be registered for each
>   * mdev device to register the device for virtio/vhost drivers.
> -- 
> 2.19.1

Powered by blists - more mailing lists