On Thu, 4 Aug 2016 00:33:51 +0530
Kirti Wankhede <kwankh...@nvidia.com> wrote:
> Design for Mediated Device Driver:
> Main purpose of this driver is to provide a common interface for mediated
> device management that can be used by different drivers of different
> devices.
>
> This module provides a generic interface to create the device, add it to
> mediated bus, add device to IOMMU group and then add it to vfio group.
>
> Below is the high Level block diagram, with Nvidia, Intel and IBM devices
> as example, since these are the devices which are going to actively use
> this module as of now.
>
> +---------------+
> | |
> | +-----------+ | mdev_register_driver() +--------------+
> | | | +<------------------------+ __init() |
> | | | | | |
> | | mdev | +------------------------>+ |<-> VFIO user
> | | bus | | probe()/remove() | vfio_mpci.ko | APIs
> | | driver | | | |
> | | | | +--------------+
> | | | | mdev_register_driver() +--------------+
> | | | +<------------------------+ __init() |
> | | | | | |
> | | | +------------------------>+ |<-> VFIO user
> | +-----------+ | probe()/remove() | vfio_mccw.ko | APIs
> | | | |
> | MDEV CORE | +--------------+
> | MODULE |
> | mdev.ko |
> | +-----------+ | mdev_register_device() +--------------+
> | | | +<------------------------+ |
> | | | | | nvidia.ko |<-> physical
> | | | +------------------------>+ | device
> | | | | callback +--------------+
> | | Physical | |
> | | device | | mdev_register_device() +--------------+
> | | interface | |<------------------------+ |
> | | | | | i915.ko |<-> physical
> | | | +------------------------>+ | device
> | | | | callback +--------------+
> | | | |
> | | | | mdev_register_device() +--------------+
> | | | +<------------------------+ |
> | | | | | ccw_device.ko|<-> physical
> | | | +------------------------>+ | device
> | | | | callback +--------------+
> | +-----------+ |
> +---------------+
>
> Core driver provides two types of registration interfaces:
> 1. Registration interface for mediated bus driver:
>
> /**
> * struct mdev_driver - Mediated device's driver
> * @name: driver name
> * @probe: called when new device created
> * @remove:called when device removed
> * @match: called when new device or driver is added for this bus.
> Return 1 if given device can be handled by given driver and
> zero otherwise.
> * @driver:device driver structure
> *
> **/
> struct mdev_driver {
> const char *name;
> int (*probe) (struct device *dev);
> void (*remove) (struct device *dev);
> int (*match)(struct device *dev);
> struct device_driver driver;
> };
>
> int mdev_register_driver(struct mdev_driver *drv, struct module *owner);
> void mdev_unregister_driver(struct mdev_driver *drv);
>
> Mediated device's driver for mdev should use this interface to register
> with Core driver. With this, mediated devices driver for such devices is
> responsible to add mediated device to VFIO group.
>
> 2. Physical device driver interface
> This interface provides vendor driver the set APIs to manage physical
> device related work in their own driver. APIs are :
> - supported_config: provide supported configuration list by the vendor
> driver
> - create: to allocate basic resources in vendor driver for a mediated
> device.
> - destroy: to free resources in vendor driver when mediated device is
> destroyed.
> - reset: to free and reallocate resources in vendor driver during reboot
> - start: to initiate mediated device initialization process from vendor
> driver
> - shutdown: to teardown mediated device resources during teardown.
> - read : read emulation callback.
> - write: write emulation callback.
> - set_irqs: send interrupt configuration information that VMM sets.
> - get_region_info: to provide region size and its flags for the mediated
> device.
> - validate_map_request: to validate remap pfn request.
>
> This registration interface should be used by vendor drivers to register
> each physical device to mdev core driver.
> Locks to serialize above callbacks are removed. If required, vendor driver
> can have locks to serialize above APIs in their driver.
>
> Added support to keep track of physical mappings for each mdev device.
> APIs to be used by mediated device bus driver to add and delete mappings to
> tracking logic:
> int mdev_add_phys_mapping(struct mdev_device *mdev,
> struct address_space *mapping,
> unsigned long addr, unsigned long size)
> void mdev_del_phys_mapping(struct mdev_device *mdev, unsigned long addr)
>
> API to be used by vendor driver to invalidate mapping:
> int mdev_device_invalidate_mapping(struct mdev_device *mdev,
> unsigned long addr, unsigned long size)
>
> Signed-off-by: Kirti Wankhede <kwankh...@nvidia.com>
> Signed-off-by: Neo Jia <c...@nvidia.com>
> Change-Id: I73a5084574270b14541c529461ea2f03c292d510
> ---
> drivers/vfio/Kconfig | 1 +
> drivers/vfio/Makefile | 1 +
> drivers/vfio/mdev/Kconfig | 12 +
> drivers/vfio/mdev/Makefile | 5 +
> drivers/vfio/mdev/mdev_core.c | 676
> +++++++++++++++++++++++++++++++++++++++
> drivers/vfio/mdev/mdev_driver.c | 142 ++++++++
> drivers/vfio/mdev/mdev_private.h | 33 ++
> drivers/vfio/mdev/mdev_sysfs.c | 269 ++++++++++++++++
> include/linux/mdev.h | 236 ++++++++++++++
> 9 files changed, 1375 insertions(+)
> create mode 100644 drivers/vfio/mdev/Kconfig
> create mode 100644 drivers/vfio/mdev/Makefile
> create mode 100644 drivers/vfio/mdev/mdev_core.c
> create mode 100644 drivers/vfio/mdev/mdev_driver.c
> create mode 100644 drivers/vfio/mdev/mdev_private.h
> create mode 100644 drivers/vfio/mdev/mdev_sysfs.c
> create mode 100644 include/linux/mdev.h
>
> diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> index da6e2ce77495..23eced02aaf6 100644
> --- a/drivers/vfio/Kconfig
> +++ b/drivers/vfio/Kconfig
> @@ -48,4 +48,5 @@ menuconfig VFIO_NOIOMMU
>
> source "drivers/vfio/pci/Kconfig"
> source "drivers/vfio/platform/Kconfig"
> +source "drivers/vfio/mdev/Kconfig"
> source "virt/lib/Kconfig"
> diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
> index 7b8a31f63fea..4a23c13b6be4 100644
> --- a/drivers/vfio/Makefile
> +++ b/drivers/vfio/Makefile
> @@ -7,3 +7,4 @@ obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
> obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o
> obj-$(CONFIG_VFIO_PCI) += pci/
> obj-$(CONFIG_VFIO_PLATFORM) += platform/
> +obj-$(CONFIG_VFIO_MDEV) += mdev/
> diff --git a/drivers/vfio/mdev/Kconfig b/drivers/vfio/mdev/Kconfig
> new file mode 100644
> index 000000000000..a34fbc66f92f
> --- /dev/null
> +++ b/drivers/vfio/mdev/Kconfig
> @@ -0,0 +1,12 @@
> +
> +config VFIO_MDEV
> + tristate "Mediated device driver framework"
> + depends on VFIO
> + default n
> + help
> + Provides a framework to virtualize device.
> + See Documentation/vfio-mediated-device.txt for more details.
> +
> + If you don't know what do here, say N.
> +
> +
> diff --git a/drivers/vfio/mdev/Makefile b/drivers/vfio/mdev/Makefile
> new file mode 100644
> index 000000000000..56a75e689582
> --- /dev/null
> +++ b/drivers/vfio/mdev/Makefile
> @@ -0,0 +1,5 @@
> +
> +mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o
> +
> +obj-$(CONFIG_VFIO_MDEV) += mdev.o
> +
> diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
> new file mode 100644
> index 000000000000..90ff073abfce
> --- /dev/null
> +++ b/drivers/vfio/mdev/mdev_core.c
> @@ -0,0 +1,676 @@
> +/*
> + * Mediated device Core Driver
> + *
> + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
> + * Author: Neo Jia <c...@nvidia.com>
> + * Kirti Wankhede <kwankh...@nvidia.com>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#include <linux/module.h>
> +#include <linux/device.h>
> +#include <linux/fs.h>
> +#include <linux/slab.h>
> +#include <linux/sched.h>
> +#include <linux/uuid.h>
> +#include <linux/vfio.h>
> +#include <linux/iommu.h>
> +#include <linux/sysfs.h>
> +#include <linux/mdev.h>
> +
> +#include "mdev_private.h"
> +
> +#define DRIVER_VERSION "0.1"
> +#define DRIVER_AUTHOR "NVIDIA Corporation"
> +#define DRIVER_DESC "Mediated device Core Driver"
> +
> +#define MDEV_CLASS_NAME "mdev"
> +
> +static LIST_HEAD(parent_list);
> +static DEFINE_MUTEX(parent_list_lock);
> +
> +static int mdev_add_attribute_group(struct device *dev,
> + const struct attribute_group **groups)
> +{
> + return sysfs_create_groups(&dev->kobj, groups);
> +}
> +
> +static void mdev_remove_attribute_group(struct device *dev,
> + const struct attribute_group **groups)
> +{
> + sysfs_remove_groups(&dev->kobj, groups);
> +}
> +
> +/* Should be called holding parent->mdev_list_lock */
I often like to prepend "__" onto the name of functions like this to
signal a special calling convention.
> +static struct mdev_device *find_mdev_device(struct parent_device *parent,
> + uuid_le uuid, int instance)
> +{
> + struct mdev_device *mdev;
> +
> + list_for_each_entry(mdev, &parent->mdev_list, next) {
> + if ((uuid_le_cmp(mdev->uuid, uuid) == 0) &&
> + (mdev->instance == instance))
> + return mdev;
> + }
> + return NULL;
> +}
> +
> +/* Should be called holding parent_list_lock */
> +static struct parent_device *find_parent_device(struct device *dev)
> +{
> + struct parent_device *parent;
> +
> + list_for_each_entry(parent, &parent_list, next) {
> + if (parent->dev == dev)
> + return parent;
> + }
> + return NULL;
> +}
> +
> +static void mdev_release_parent(struct kref *kref)
> +{
> + struct parent_device *parent = container_of(kref, struct parent_device,
> + ref);
> + kfree(parent);
> +}
> +
> +static
> +inline struct parent_device *mdev_get_parent(struct parent_device *parent)
> +{
> + if (parent)
> + kref_get(&parent->ref);
> +
> + return parent;
> +}
> +
> +static inline void mdev_put_parent(struct parent_device *parent)
> +{
> + if (parent)
> + kref_put(&parent->ref, mdev_release_parent);
> +}
> +
> +static struct parent_device *mdev_get_parent_by_dev(struct device *dev)
> +{
> + struct parent_device *parent = NULL, *p;
> +
> + mutex_lock(&parent_list_lock);
> + list_for_each_entry(p, &parent_list, next) {
> + if (p->dev == dev) {
> + parent = mdev_get_parent(p);
> + break;
> + }
> + }
> + mutex_unlock(&parent_list_lock);
> + return parent;
Use what you've created:
{
struct parent_device *parent;
mutex_lock(&parent_list_lock);
parent = mdev_get_parent(find_parent_device(dev));
mutex_unlock(&parent_list_lock);
return parent;
}
> +}
> +
> +static int mdev_device_create_ops(struct mdev_device *mdev, char
> *mdev_params)
> +{
> + struct parent_device *parent = mdev->parent;
> + int ret;
> +
> + ret = parent->ops->create(mdev, mdev_params);
> + if (ret)
> + return ret;
> +
> + ret = mdev_add_attribute_group(&mdev->dev,
> + parent->ops->mdev_attr_groups);
> + if (ret)
> + parent->ops->destroy(mdev);
> +
> + return ret;
> +}
> +
> +static int mdev_device_destroy_ops(struct mdev_device *mdev, bool force)
> +{
> + struct parent_device *parent = mdev->parent;
> + int ret = 0;
> +
> + /*
> + * If vendor driver doesn't return success that means vendor
> + * driver doesn't support hot-unplug
> + */
> + ret = parent->ops->destroy(mdev);
> + if (ret && !force)
> + return -EBUSY;
This still seems troublesome, I'm not sure why we don't just require
hot-unplug support. Without it, we seem to have a limbo state where a
device exists, but not fully.
> +
> + mdev_remove_attribute_group(&mdev->dev,
> + parent->ops->mdev_attr_groups);
> +
> + return ret;
> +}
> +
> +static void mdev_release_device(struct kref *kref)
> +{
> + struct mdev_device *mdev = container_of(kref, struct mdev_device, ref);
> + struct parent_device *parent = mdev->parent;
> +
> + list_del(&mdev->next);
> + mutex_unlock(&parent->mdev_list_lock);
Maybe worthy of a short comment to more obviously match this unlock to
the kref_put_mutex() below.
> +
> + device_unregister(&mdev->dev);
> + wake_up(&parent->release_done);
> + mdev_put_parent(parent);
> +}
> +
> +struct mdev_device *mdev_get_device(struct mdev_device *mdev)
> +{
> + kref_get(&mdev->ref);
> + return mdev;
> +}
> +EXPORT_SYMBOL(mdev_get_device);
Is the intention here that the caller already has a reference to mdev
and wants to get another? Or I see the cases where use locking
to get this reference. There's potential to misuse this, if not
outright abuse it, which worries me. A reference cannot be
spontaneously generated, it needs to be sourced from somewhere.
> +
> +void mdev_put_device(struct mdev_device *mdev)
> +{
> + struct parent_device *parent = mdev->parent;
> +
> + kref_put_mutex(&mdev->ref, mdev_release_device,
> + &parent->mdev_list_lock);
> +}
> +EXPORT_SYMBOL(mdev_put_device);
> +
> +/*
> + * Find first mediated device from given uuid and increment refcount of
> + * mediated device. Caller should call mdev_put_device() when the use of
> + * mdev_device is done.
> + */
> +static struct mdev_device *mdev_get_first_device_by_uuid(uuid_le uuid)
> +{
> + struct mdev_device *mdev = NULL, *p;
> + struct parent_device *parent;
> +
> + mutex_lock(&parent_list_lock);
> + list_for_each_entry(parent, &parent_list, next) {
> + mutex_lock(&parent->mdev_list_lock);
> + list_for_each_entry(p, &parent->mdev_list, next) {
> + if (uuid_le_cmp(p->uuid, uuid) == 0) {
> + mdev = mdev_get_device(p);
> + break;
> + }
> + }
> + mutex_unlock(&parent->mdev_list_lock);
> +
> + if (mdev)
> + break;
> + }
> + mutex_unlock(&parent_list_lock);
> + return mdev;
> +}
This is used later by mdev_device_start() and mdev_device_stop() to get
the parent_device so it can call the start and stop ops callbacks
respectively. That seems to imply that all of instances for a given
uuid come from the same parent_device. Where is that enforced? I'm
still having a hard time buying into the uuid+instance plan when it
seems like each mdev_device should have an actual unique uuid.
Userspace tools can figure out which uuids to start for a given user, I
don't see much value in collecting them to instances within a uuid.
> +
> +/*
> + * Find mediated device from given iommu_group and increment refcount of
> + * mediated device. Caller should call mdev_put_device() when the use of
> + * mdev_device is done.
> + */
> +struct mdev_device *mdev_get_device_by_group(struct iommu_group *group)
> +{
> + struct mdev_device *mdev = NULL, *p;
> + struct parent_device *parent;
> +
> + mutex_lock(&parent_list_lock);
> + list_for_each_entry(parent, &parent_list, next) {
> + mutex_lock(&parent->mdev_list_lock);
> + list_for_each_entry(p, &parent->mdev_list, next) {
> + if (!p->group)
> + continue;
> +
> + if (iommu_group_id(p->group) == iommu_group_id(group)) {
> + mdev = mdev_get_device(p);
> + break;
> + }
> + }
> + mutex_unlock(&parent->mdev_list_lock);
> +
> + if (mdev)
> + break;
> + }
> + mutex_unlock(&parent_list_lock);
> + return mdev;
> +}
> +EXPORT_SYMBOL(mdev_get_device_by_group);
> +
> +/*
> + * mdev_register_device : Register a device
> + * @dev: device structure representing parent device.
> + * @ops: Parent device operation structure to be registered.
> + *
> + * Add device to list of registered parent devices.
> + * Returns a negative value on error, otherwise 0.
> + */
> +int mdev_register_device(struct device *dev, const struct parent_ops *ops)
> +{
> + int ret = 0;
> + struct parent_device *parent;
> +
> + if (!dev || !ops)
> + return -EINVAL;
> +
> + /* check for mandatory ops */
> + if (!ops->create || !ops->destroy)
> + return -EINVAL;
> +
> + mutex_lock(&parent_list_lock);
> +
> + /* Check for duplicate */
> + parent = find_parent_device(dev);
> + if (parent) {
> + ret = -EEXIST;
> + goto add_dev_err;
> + }
> +
> + parent = kzalloc(sizeof(*parent), GFP_KERNEL);
> + if (!parent) {
> + ret = -ENOMEM;
> + goto add_dev_err;
> + }
> +
> + kref_init(&parent->ref);
> + list_add(&parent->next, &parent_list);
> +
> + parent->dev = dev;
> + parent->ops = ops;
> + mutex_init(&parent->mdev_list_lock);
> + INIT_LIST_HEAD(&parent->mdev_list);
> + init_waitqueue_head(&parent->release_done);
> + mutex_unlock(&parent_list_lock);
> +
> + ret = mdev_create_sysfs_files(dev);
> + if (ret)
> + goto add_sysfs_error;
> +
> + ret = mdev_add_attribute_group(dev, ops->dev_attr_groups);
> + if (ret)
> + goto add_group_error;
> +
> + dev_info(dev, "MDEV: Registered\n");
> + return 0;
> +
> +add_group_error:
> + mdev_remove_sysfs_files(dev);
> +add_sysfs_error:
> + mutex_lock(&parent_list_lock);
> + list_del(&parent->next);
> + mutex_unlock(&parent_list_lock);
> + mdev_put_parent(parent);
> + return ret;
> +
> +add_dev_err:
> + mutex_unlock(&parent_list_lock);
> + return ret;
> +}
> +EXPORT_SYMBOL(mdev_register_device);
> +
> +/*
> + * mdev_unregister_device : Unregister a parent device
> + * @dev: device structure representing parent device.
> + *
> + * Remove device from list of registered parent devices. Give a chance to
> free
> + * existing mediated devices for given device.
> + */
> +
> +void mdev_unregister_device(struct device *dev)
> +{
> + struct parent_device *parent;
> + struct mdev_device *mdev, *n;
Above *p was used for a temp pointer.
> + int ret;
> +
> + mutex_lock(&parent_list_lock);
> + parent = find_parent_device(dev);
> +
> + if (!parent) {
> + mutex_unlock(&parent_list_lock);
> + return;
> + }
> + dev_info(dev, "MDEV: Unregistering\n");
> +
> + /*
> + * Remove parent from the list and remove create and destroy sysfs
Quoting "create" and "destroy" would make this a bit more readable:
Remove parent from the list and remove "create" and "destroy"
sysfs...
Took me a couple reads to figure out "remove create" wasn't a typo.
> + * files so that no new mediated device could be created for this parent
> + */
> + list_del(&parent->next);
> + mdev_remove_sysfs_files(dev);
> + mutex_unlock(&parent_list_lock);
> +
> + mdev_remove_attribute_group(dev,
> + parent->ops->dev_attr_groups);
> +
Why do we need to remove sysfs files under the parent_list_lock?
> + mutex_lock(&parent->mdev_list_lock);
> + list_for_each_entry_safe(mdev, n, &parent->mdev_list, next) {
> + mdev_device_destroy_ops(mdev, true);
> + mutex_unlock(&parent->mdev_list_lock);
> + mdev_put_device(mdev);
> + mutex_lock(&parent->mdev_list_lock);
*cringe* Any time we need to release the list lock inside the
traversal makes me nervous. What about using list_first_entry() since
I don't think using list_for_each_entry_safe() really makes it safe
from concurrent operations on the list once we drop that lock.
> + }
> + mutex_unlock(&parent->mdev_list_lock);
> +
> + do {
> + ret = wait_event_interruptible_timeout(parent->release_done,
> + list_empty(&parent->mdev_list), HZ * 10);
> + if (ret == -ERESTARTSYS) {
> + dev_warn(dev, "Mediated devices are in use, task"
> + " \"%s\" (%d) "
> + "blocked until all are released",
> + current->comm, task_pid_nr(current));
> + }
> + } while (ret <= 0);
> +
> + mdev_put_parent(parent);
> +}
> +EXPORT_SYMBOL(mdev_unregister_device);
> +
> +/*
> + * Functions required for mdev_sysfs
> + */
> +static void mdev_device_release(struct device *dev)
> +{
> + struct mdev_device *mdev = to_mdev_device(dev);
> +
> + dev_dbg(&mdev->dev, "MDEV: destroying\n");
> + kfree(mdev);
> +}
> +
> +int mdev_device_create(struct device *dev, uuid_le uuid, uint32_t instance,
> + char *mdev_params)
> +{
> + int ret;
> + struct mdev_device *mdev;
> + struct parent_device *parent;
> +
> + parent = mdev_get_parent_by_dev(dev);
> + if (!parent)
> + return -EINVAL;
> +
> + mutex_lock(&parent->mdev_list_lock);
> + /* Check for duplicate */
> + mdev = find_mdev_device(parent, uuid, instance);
> + if (mdev) {
> + ret = -EEXIST;
> + goto create_err;
> + }
> +
> + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
> + if (!mdev) {
> + ret = -ENOMEM;
> + goto create_err;
> + }
> +
> + memcpy(&mdev->uuid, &uuid, sizeof(uuid_le));
> + mdev->instance = instance;
> + mdev->parent = parent;
> + kref_init(&mdev->ref);
> +
> + mdev->dev.parent = dev;
> + mdev->dev.bus = &mdev_bus_type;
> + mdev->dev.release = mdev_device_release;
> + dev_set_name(&mdev->dev, "%pUl-%d", uuid.b, instance);
> +
> + ret = device_register(&mdev->dev);
> + if (ret) {
> + put_device(&mdev->dev);
> + goto create_err;
> + }
> +
> + ret = mdev_device_create_ops(mdev, mdev_params);
> + if (ret)
> + goto create_failed;
> +
> + list_add(&mdev->next, &parent->mdev_list);
> + mutex_unlock(&parent->mdev_list_lock);
> +
> + dev_dbg(&mdev->dev, "MDEV: created\n");
> +
> + return ret;
> +
> +create_failed:
> + device_unregister(&mdev->dev);
> +
> +create_err:
> + mutex_unlock(&parent->mdev_list_lock);
> + mdev_put_parent(parent);
> + return ret;
> +}
> +
> +int mdev_device_destroy(struct device *dev, uuid_le uuid, uint32_t instance)
> +{
> + struct mdev_device *mdev;
> + struct parent_device *parent;
> + int ret;
> +
> + parent = mdev_get_parent_by_dev(dev);
> + if (!parent)
> + return -EINVAL;
> +
> + mutex_lock(&parent->mdev_list_lock);
> + mdev = find_mdev_device(parent, uuid, instance);
> + if (!mdev) {
> + ret = -EINVAL;
-ENODEV?
> + goto destroy_err;
> + }
> +
> + ret = mdev_device_destroy_ops(mdev, false);
> + if (ret)
> + goto destroy_err;
> +
> + mutex_unlock(&parent->mdev_list_lock);
> + mdev_put_device(mdev);
> +
> + mdev_put_parent(parent);
> + return ret;
> +
> +destroy_err:
> + mutex_unlock(&parent->mdev_list_lock);
> + mdev_put_parent(parent);
> + return ret;
> +}
> +
> +int mdev_device_invalidate_mapping(struct mdev_device *mdev,
> + unsigned long addr, unsigned long size)
> +{
> + int ret = -EINVAL;
> + struct mdev_phys_mapping *phys_mappings;
> + struct addr_desc *addr_desc;
> +
> + if (!mdev || !mdev->phys_mappings.mapping)
> + return ret;
> +
> + phys_mappings = &mdev->phys_mappings;
> +
> + mutex_lock(&phys_mappings->addr_desc_list_lock);
> +
> + list_for_each_entry(addr_desc, &phys_mappings->addr_desc_list, next) {
> +
> + if ((addr > addr_desc->start) &&
> + (addr + size < addr_desc->start + addr_desc->size)) {
This looks incomplete, minimally I think these should be >= and <=, but
that still only covers fully enclosed invalidation ranges. Do we need
to support partial invalidations?
> + unmap_mapping_range(phys_mappings->mapping,
> + addr, size, 0);
> + ret = 0;
> + goto unlock_exit;
If partial overlaps can occur, we'll need an exhaustive search.
> + }
> + }
> +
> +unlock_exit:
> + mutex_unlock(&phys_mappings->addr_desc_list_lock);
> + return ret;
> +}
> +EXPORT_SYMBOL(mdev_device_invalidate_mapping);
> +
> +/* Sanity check for the physical mapping list for mediated device */
> +
> +int mdev_add_phys_mapping(struct mdev_device *mdev,
> + struct address_space *mapping,
> + unsigned long addr, unsigned long size)
> +{
> + struct mdev_phys_mapping *phys_mappings;
> + struct addr_desc *addr_desc, *new_addr_desc;
> + int ret = 0;
> +
> + if (!mdev)
> + return -EINVAL;
> +
> + phys_mappings = &mdev->phys_mappings;
> + if (phys_mappings->mapping && (mapping != phys_mappings->mapping))
> + return -EINVAL;
> +
> + if (!phys_mappings->mapping) {
> + phys_mappings->mapping = mapping;
> + mutex_init(&phys_mappings->addr_desc_list_lock);
> + INIT_LIST_HEAD(&phys_mappings->addr_desc_list);
> + }
This looks racy, should we be acquiring the mutex earlier?
> +
> + mutex_lock(&phys_mappings->addr_desc_list_lock);
> +
> + list_for_each_entry(addr_desc, &phys_mappings->addr_desc_list, next) {
> + if ((addr + size < addr_desc->start) ||
> + (addr_desc->start + addr_desc->size) < addr)
<= on both, I think
> + continue;
> + else {
> + /* should be no overlap */
> + ret = -EINVAL;
> + goto mapping_exit;
> + }
> + }
> +
> + /* add the new entry to the list */
> + new_addr_desc = kzalloc(sizeof(*new_addr_desc), GFP_KERNEL);
> +
> + if (!new_addr_desc) {
> + ret = -ENOMEM;
> + goto mapping_exit;
> + }
> +
> + new_addr_desc->start = addr;
> + new_addr_desc->size = size;
> + list_add(&new_addr_desc->next, &phys_mappings->addr_desc_list);
> +
> +mapping_exit:
> + mutex_unlock(&phys_mappings->addr_desc_list_lock);
> + return ret;
> +}
> +EXPORT_SYMBOL(mdev_add_phys_mapping);
> +
> +void mdev_del_phys_mapping(struct mdev_device *mdev, unsigned long addr)
> +{
> + struct mdev_phys_mapping *phys_mappings;
> + struct addr_desc *addr_desc;
> +
> + if (!mdev)
> + return;
> +
> + phys_mappings = &mdev->phys_mappings;
> +
> + mutex_lock(&phys_mappings->addr_desc_list_lock);
> + list_for_each_entry(addr_desc, &phys_mappings->addr_desc_list, next) {
> + if (addr_desc->start == addr) {
> + list_del(&addr_desc->next);
> + kfree(addr_desc);
> + break;
> + }
> + }
> + mutex_unlock(&phys_mappings->addr_desc_list_lock);
> +}
> +EXPORT_SYMBOL(mdev_del_phys_mapping);
> +
> +void mdev_device_supported_config(struct device *dev, char *str)
> +{
> + struct parent_device *parent;
> +
> + parent = mdev_get_parent_by_dev(dev);
> +
> + if (parent) {
> + if (parent->ops->supported_config)
> + parent->ops->supported_config(parent->dev, str);
> + mdev_put_parent(parent);
> + }
> +}
> +
> +int mdev_device_start(uuid_le uuid)
> +{
> + int ret = 0;
> + struct mdev_device *mdev;
> + struct parent_device *parent;
> +
> + mdev = mdev_get_first_device_by_uuid(uuid);
> + if (!mdev)
> + return -EINVAL;
> +
> + parent = mdev->parent;
> +
> + if (parent->ops->start)
> + ret = parent->ops->start(mdev->uuid);
Assumes uuids do not span parent_devices?
> +
> + if (ret)
> + pr_err("mdev_start failed %d\n", ret);
> + else
> + kobject_uevent(&mdev->dev.kobj, KOBJ_ONLINE);
> +
> + mdev_put_device(mdev);
> +
> + return ret;
> +}
> +
> +int mdev_device_stop(uuid_le uuid)
> +{
> + int ret = 0;
> + struct mdev_device *mdev;
> + struct parent_device *parent;
> +
> + mdev = mdev_get_first_device_by_uuid(uuid);
> + if (!mdev)
> + return -EINVAL;
> +
> + parent = mdev->parent;
> +
> + if (parent->ops->stop)
> + ret = parent->ops->stop(mdev->uuid);
> +
> + if (ret)
> + pr_err("mdev stop failed %d\n", ret);
> + else
> + kobject_uevent(&mdev->dev.kobj, KOBJ_OFFLINE);
> +
> + mdev_put_device(mdev);
> + return ret;
> +}
> +
> +static struct class mdev_class = {
> + .name = MDEV_CLASS_NAME,
> + .owner = THIS_MODULE,
> + .class_attrs = mdev_class_attrs,
> +};
> +
> +static int __init mdev_init(void)
> +{
> + int ret;
> +
> + ret = class_register(&mdev_class);
> + if (ret) {
> + pr_err("Failed to register mdev class\n");
> + return ret;
> + }
> +
> + ret = mdev_bus_register();
> + if (ret) {
> + pr_err("Failed to register mdev bus\n");
> + class_unregister(&mdev_class);
> + return ret;
> + }
> +
> + return ret;
> +}
> +
> +static void __exit mdev_exit(void)
> +{
> + mdev_bus_unregister();
> + class_unregister(&mdev_class);
> +}
> +
> +module_init(mdev_init)
> +module_exit(mdev_exit)
> +
> +MODULE_VERSION(DRIVER_VERSION);
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR(DRIVER_AUTHOR);
> +MODULE_DESCRIPTION(DRIVER_DESC);
> diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c
> new file mode 100644
> index 000000000000..00680bd06224
> --- /dev/null
> +++ b/drivers/vfio/mdev/mdev_driver.c
> @@ -0,0 +1,142 @@
> +/*
> + * MDEV driver
> + *
> + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
> + * Author: Neo Jia <c...@nvidia.com>
> + * Kirti Wankhede <kwankh...@nvidia.com>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#include <linux/device.h>
> +#include <linux/iommu.h>
> +#include <linux/mdev.h>
> +
> +#include "mdev_private.h"
> +
> +static int mdev_attach_iommu(struct mdev_device *mdev)
> +{
> + int ret;
> + struct iommu_group *group;
> +
> + group = iommu_group_alloc();
> + if (IS_ERR(group)) {
> + dev_err(&mdev->dev, "MDEV: failed to allocate group!\n");
> + return PTR_ERR(group);
> + }
> +
> + ret = iommu_group_add_device(group, &mdev->dev);
> + if (ret) {
> + dev_err(&mdev->dev, "MDEV: failed to add dev to group!\n");
> + goto attach_fail;
> + }
> +
> + mdev->group = group;
> +
> + dev_info(&mdev->dev, "MDEV: group_id = %d\n",
> + iommu_group_id(group));
> +attach_fail:
> + iommu_group_put(group);
> + return ret;
> +}
> +
> +static void mdev_detach_iommu(struct mdev_device *mdev)
> +{
> + iommu_group_remove_device(&mdev->dev);
> + mdev->group = NULL;
> + dev_info(&mdev->dev, "MDEV: detaching iommu\n");
> +}
> +
> +static int mdev_probe(struct device *dev)
> +{
> + struct mdev_driver *drv = to_mdev_driver(dev->driver);
> + struct mdev_device *mdev = to_mdev_device(dev);
> + int ret;
> +
> + ret = mdev_attach_iommu(mdev);
> + if (ret) {
> + dev_err(dev, "Failed to attach IOMMU\n");
> + return ret;
> + }
> +
> + if (drv && drv->probe)
> + ret = drv->probe(dev);
> +
> + if (ret)
> + mdev_detach_iommu(mdev);
> +
> + return ret;
> +}
> +
> +static int mdev_remove(struct device *dev)
> +{
> + struct mdev_driver *drv = to_mdev_driver(dev->driver);
> + struct mdev_device *mdev = to_mdev_device(dev);
> +
> + if (drv && drv->remove)
> + drv->remove(dev);
> +
> + mdev_detach_iommu(mdev);
> +
> + return 0;
> +}
> +
> +static int mdev_match(struct device *dev, struct device_driver *driver)
> +{
> + struct mdev_driver *drv = to_mdev_driver(driver);
> +
> + if (drv && drv->match)
> + return drv->match(dev);
> +
> + return 0;
> +}
> +
> +struct bus_type mdev_bus_type = {
> + .name = "mdev",
> + .match = mdev_match,
> + .probe = mdev_probe,
> + .remove = mdev_remove,
> +};
> +EXPORT_SYMBOL_GPL(mdev_bus_type);
> +
> +/*
> + * mdev_register_driver - register a new MDEV driver
> + * @drv: the driver to register
> + * @owner: module owner of driver to be registered
> + *
> + * Returns a negative value on error, otherwise 0.
> + */
> +int mdev_register_driver(struct mdev_driver *drv, struct module *owner)
> +{
> + /* initialize common driver fields */
> + drv->driver.name = drv->name;
> + drv->driver.bus = &mdev_bus_type;
> + drv->driver.owner = owner;
> +
> + /* register with core */
> + return driver_register(&drv->driver);
> +}
> +EXPORT_SYMBOL(mdev_register_driver);
> +
> +/*
> + * mdev_unregister_driver - unregister MDEV driver
> + * @drv: the driver to unregister
> + *
> + */
> +void mdev_unregister_driver(struct mdev_driver *drv)
> +{
> + driver_unregister(&drv->driver);
> +}
> +EXPORT_SYMBOL(mdev_unregister_driver);
> +
> +int mdev_bus_register(void)
> +{
> + return bus_register(&mdev_bus_type);
> +}
> +
> +void mdev_bus_unregister(void)
> +{
> + bus_unregister(&mdev_bus_type);
> +}
> diff --git a/drivers/vfio/mdev/mdev_private.h
> b/drivers/vfio/mdev/mdev_private.h
> new file mode 100644
> index 000000000000..ee2db61a8091
> --- /dev/null
> +++ b/drivers/vfio/mdev/mdev_private.h
> @@ -0,0 +1,33 @@
> +/*
> + * Mediated device interal definitions
> + *
> + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
> + * Author: Neo Jia <c...@nvidia.com>
> + * Kirti Wankhede <kwankh...@nvidia.com>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#ifndef MDEV_PRIVATE_H
> +#define MDEV_PRIVATE_H
> +
> +int mdev_bus_register(void);
> +void mdev_bus_unregister(void);
> +
> +/* Function prototypes for mdev_sysfs */
> +
> +extern struct class_attribute mdev_class_attrs[];
> +
> +int mdev_create_sysfs_files(struct device *dev);
> +void mdev_remove_sysfs_files(struct device *dev);
> +
> +int mdev_device_create(struct device *dev, uuid_le uuid, uint32_t instance,
> + char *mdev_params);
> +int mdev_device_destroy(struct device *dev, uuid_le uuid, uint32_t
> instance);
> +void mdev_device_supported_config(struct device *dev, char *str);
> +int mdev_device_start(uuid_le uuid);
> +int mdev_device_stop(uuid_le uuid);
> +
> +#endif /* MDEV_PRIVATE_H */
> diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
> new file mode 100644
> index 000000000000..e0457e68cf78
> --- /dev/null
> +++ b/drivers/vfio/mdev/mdev_sysfs.c
> @@ -0,0 +1,269 @@
> +/*
> + * File attributes for Mediated devices
> + *
> + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
> + * Author: Neo Jia <c...@nvidia.com>
> + * Kirti Wankhede <kwankh...@nvidia.com>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#include <linux/sysfs.h>
> +#include <linux/ctype.h>
> +#include <linux/device.h>
> +#include <linux/slab.h>
> +#include <linux/uuid.h>
> +#include <linux/mdev.h>
> +
> +#include "mdev_private.h"
> +
> +/* Prototypes */
> +static ssize_t mdev_supported_types_show(struct device *dev,
> + struct device_attribute *attr,
> + char *buf);
> +static DEVICE_ATTR_RO(mdev_supported_types);
> +
> +static ssize_t mdev_create_store(struct device *dev,
> + struct device_attribute *attr,
> + const char *buf, size_t count);
> +static DEVICE_ATTR_WO(mdev_create);
> +
> +static ssize_t mdev_destroy_store(struct device *dev,
> + struct device_attribute *attr,
> + const char *buf, size_t count);
> +static DEVICE_ATTR_WO(mdev_destroy);
> +
> +/* Static functions */
> +
> +
> +#define SUPPORTED_TYPE_BUFFER_LENGTH 4096
> +
> +/* mdev sysfs Functions */
> +static ssize_t mdev_supported_types_show(struct device *dev,
> + struct device_attribute *attr,
> + char *buf)
> +{
> + char *str, *ptr;
> + ssize_t n;
> +
> + str = kzalloc(sizeof(*str) * SUPPORTED_TYPE_BUFFER_LENGTH, GFP_KERNEL);
> + if (!str)
> + return -ENOMEM;
> +
> + ptr = str;
> + mdev_device_supported_config(dev, str);
> +
> + n = sprintf(buf, "%s\n", str);
> + kfree(ptr);
> +
> + return n;
> +}
> +
> +static ssize_t mdev_create_store(struct device *dev,
> + struct device_attribute *attr,
> + const char *buf, size_t count)
> +{
> + char *str, *pstr;
> + char *uuid_str, *instance_str, *mdev_params = NULL, *params = NULL;
> + uuid_le uuid;
> + uint32_t instance;
> + int ret;
> +
> + pstr = str = kstrndup(buf, count, GFP_KERNEL);
> +
> + if (!str)
> + return -ENOMEM;
> +
> + uuid_str = strsep(&str, ":");
> + if (!uuid_str) {
> + pr_err("mdev_create: Empty UUID string %s\n", buf);
> + ret = -EINVAL;
> + goto create_error;
> + }
> +
> + if (!str) {
> + pr_err("mdev_create: mdev instance not present %s\n", buf);
> + ret = -EINVAL;
> + goto create_error;
> + }
> +
> + instance_str = strsep(&str, ":");
> + if (!instance_str) {
> + pr_err("mdev_create: Empty instance string %s\n", buf);
> + ret = -EINVAL;
> + goto create_error;
> + }
> +
> + ret = kstrtouint(instance_str, 0, &instance);
> + if (ret) {
> + pr_err("mdev_create: mdev instance parsing error %s\n", buf);
> + goto create_error;
> + }
> +
> + if (str)
> + params = mdev_params = kstrdup(str, GFP_KERNEL);
> +
> + ret = uuid_le_to_bin(uuid_str, &uuid);
> + if (ret) {
> + pr_err("mdev_create: UUID parse error %s\n", buf);
> + goto create_error;
> + }
> +
> + ret = mdev_device_create(dev, uuid, instance, mdev_params);
> + if (ret)
> + pr_err("mdev_create: Failed to create mdev device\n");
> + else
> + ret = count;
> +
> +create_error:
> + kfree(params);
> + kfree(pstr);
> + return ret;
> +}
> +
> +static ssize_t mdev_destroy_store(struct device *dev,
> + struct device_attribute *attr,
> + const char *buf, size_t count)
> +{
I wonder if we should just have a "remove" file in sysfs under the
device.
> + char *uuid_str, *str, *pstr;
> + uuid_le uuid;
> + unsigned int instance;
> + int ret;
> +
> + str = pstr = kstrndup(buf, count, GFP_KERNEL);
> +
> + if (!str)
> + return -ENOMEM;
> +
> + uuid_str = strsep(&str, ":");
> + if (!uuid_str) {
> + pr_err("mdev_destroy: Empty UUID string %s\n", buf);
> + ret = -EINVAL;
> + goto destroy_error;
> + }
> +
> + if (str == NULL) {
> + pr_err("mdev_destroy: instance not specified %s\n", buf);
> + ret = -EINVAL;
> + goto destroy_error;
> + }
> +
> + ret = kstrtouint(str, 0, &instance);
> + if (ret) {
> + pr_err("mdev_destroy: instance parsing error %s\n", buf);
> + goto destroy_error;
> + }
> +
> + ret = uuid_le_to_bin(uuid_str, &uuid);
> + if (ret) {
> + pr_err("mdev_destroy: UUID parse error %s\n", buf);
> + goto destroy_error;
> + }
> +
> + ret = mdev_device_destroy(dev, uuid, instance);
> + if (ret == 0)
> + ret = count;
> +
> +destroy_error:
> + kfree(pstr);
> + return ret;
> +}
> +
> +ssize_t mdev_start_store(struct class *class, struct class_attribute *attr,
> + const char *buf, size_t count)
> +{
> + char *uuid_str, *ptr;
> + uuid_le uuid;
> + int ret;
> +
> + ptr = uuid_str = kstrndup(buf, count, GFP_KERNEL);
> +
> + if (!uuid_str)
> + return -ENOMEM;
> +
> + ret = uuid_le_to_bin(uuid_str, &uuid);
> + if (ret) {
> + pr_err("mdev_start: UUID parse error %s\n", buf);
> + goto start_error;
> + }
> +
> + ret = mdev_device_start(uuid);
> + if (ret == 0)
> + ret = count;
> +
> +start_error:
> + kfree(ptr);
> + return ret;
> +}
> +
> +ssize_t mdev_stop_store(struct class *class, struct class_attribute *attr,
> + const char *buf, size_t count)
> +{
> + char *uuid_str, *ptr;
> + uuid_le uuid;
> + int ret;
> +
> + ptr = uuid_str = kstrndup(buf, count, GFP_KERNEL);
> +
> + if (!uuid_str)
> + return -ENOMEM;
> +
> + ret = uuid_le_to_bin(uuid_str, &uuid);
> + if (ret) {
> + pr_err("mdev_stop: UUID parse error %s\n", buf);
> + goto stop_error;
> + }
> +
> + ret = mdev_device_stop(uuid);
> + if (ret == 0)
> + ret = count;
> +
> +stop_error:
> + kfree(ptr);
> + return ret;
> +
> +}
> +
> +struct class_attribute mdev_class_attrs[] = {
> + __ATTR_WO(mdev_start),
> + __ATTR_WO(mdev_stop),
> + __ATTR_NULL
> +};
> +
> +int mdev_create_sysfs_files(struct device *dev)
> +{
> + int ret;
> +
> + ret = sysfs_create_file(&dev->kobj,
> + &dev_attr_mdev_supported_types.attr);
> + if (ret) {
> + pr_err("Failed to create mdev_supported_types sysfs entry\n");
> + return ret;
> + }
> +
> + ret = sysfs_create_file(&dev->kobj, &dev_attr_mdev_create.attr);
> + if (ret) {
> + pr_err("Failed to create mdev_create sysfs entry\n");
> + goto create_sysfs_failed;
> + }
> +
> + ret = sysfs_create_file(&dev->kobj, &dev_attr_mdev_destroy.attr);
> + if (ret) {
> + pr_err("Failed to create mdev_destroy sysfs entry\n");
> + sysfs_remove_file(&dev->kobj, &dev_attr_mdev_create.attr);
> + } else
> + return ret;
> +
> +create_sysfs_failed:
> + sysfs_remove_file(&dev->kobj, &dev_attr_mdev_supported_types.attr);
> + return ret;
> +}
> +
> +void mdev_remove_sysfs_files(struct device *dev)
> +{
> + sysfs_remove_file(&dev->kobj, &dev_attr_mdev_supported_types.attr);
> + sysfs_remove_file(&dev->kobj, &dev_attr_mdev_create.attr);
> + sysfs_remove_file(&dev->kobj, &dev_attr_mdev_destroy.attr);
> +}
> diff --git a/include/linux/mdev.h b/include/linux/mdev.h
> new file mode 100644
> index 000000000000..0b41f301a9b7
> --- /dev/null
> +++ b/include/linux/mdev.h
> @@ -0,0 +1,236 @@
> +/*
> + * Mediated device definition
> + *
> + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
> + * Author: Neo Jia <c...@nvidia.com>
> + * Kirti Wankhede <kwankh...@nvidia.com>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#ifndef MDEV_H
> +#define MDEV_H
> +
> +#include <uapi/linux/vfio.h>
> +
> +struct parent_device;
> +
> +/*
> + * Mediated device
> + */
> +
> +struct addr_desc {
> + unsigned long start;
> + unsigned long size;
> + struct list_head next;
> +};
> +
> +struct mdev_phys_mapping {
> + struct address_space *mapping;
> + struct list_head addr_desc_list;
> + struct mutex addr_desc_list_lock;
> +};
> +
> +struct mdev_device {
> + struct device dev;
> + struct parent_device *parent;
> + struct iommu_group *group;
> + uuid_le uuid;
> + uint32_t instance;
> + void *driver_data;
> +
> + /* internal only */
> + struct kref ref;
> + struct list_head next;
> +
> + struct mdev_phys_mapping phys_mappings;
> +};
> +
> +
> +/**
> + * struct parent_ops - Structure to be registered for each parent device to
> + * register the device to mdev module.
> + *
> + * @owner: The module owner.
> + * @dev_attr_groups: Default attributes of the parent device.
> + * @mdev_attr_groups: Default attributes of the mediated device.
> + * @supported_config: Called to get information about supported types.
> + * @dev : device structure of parent device.
> + * @config: should return string listing supported config
> + * Returns integer: success (0) or error (< 0)
> + * @create: Called to allocate basic resources in parent device's
> + * driver for a particular mediated device. It is
> + * mandatory to provide create ops.
> + * @mdev: mdev_device structure on of mediated device
> + * that is being created
> + * @mdev_params: extra parameters required by parent
> + * device's driver.
> + * Returns integer: success (0) or error (< 0)
> + * @destroy: Called to free resources in parent device's driver for a
> + * a mediated device instance. It is mandatory to provide
> + * destroy ops.
> + * @mdev: mdev_device device structure which is being
> + * destroyed
> + * Returns integer: success (0) or error (< 0)
> + * If VMM is running and destroy() is called that means the
> + * mdev is being hotunpluged. Return error if VMM is
> + * running and driver doesn't support mediated device
> + * hotplug.
> + * @reset: Called to reset mediated device.
> + * @mdev: mdev_device device structure
> + * Returns integer: success (0) or error (< 0)
> + * @start: Called to initiate mediated device initialization
> + * process in parent device's driver before VMM starts.
> + * @uuid: UUID
> + * Returns integer: success (0) or error (< 0)
> + * @stop: Called to teardown mediated device related resources
> + * @uuid: UUID
> + * Returns integer: success (0) or error (< 0)
> + * @read: Read emulation callback
> + * @mdev: mediated device structure
> + * @buf: read buffer
> + * @count: number of bytes to read
> + * @pos: address.
> + * Retuns number on bytes read on success or error.
> + * @write: Write emulation callback
> + * @mdev: mediated device structure
> + * @buf: write buffer
> + * @count: number of bytes to be written
> + * @pos: address.
> + * Retuns number on bytes written on success or error.
> + * @set_irqs: Called to send about interrupts configuration
> + * information that VMM sets.
> + * @mdev: mediated device structure
> + * @flags, index, start, count and *data : same as that of
> + * struct vfio_irq_set of VFIO_DEVICE_SET_IRQS API.
> + * @get_region_info: Called to get VFIO region size and flags of mediated
> + * device.
> + * @mdev: mediated device structure
> + * @region_index: VFIO region index
> + * @region_info: output, returns size and flags of
> + * requested region.
> + * Returns integer: success (0) or error (< 0)
> + * @validate_map_request: Validate remap pfn request
> + * @mdev: mediated device structure
> + * @pos: address
> + * @virtaddr: target user address to start at. Vendor
> + * driver can change if required.
> + * @pfn: parent address of kernel memory, vendor driver
> + * can change if required.
> + * @size: size of map area, vendor driver can change the
> + * size of map area if desired.
> + * @prot: page protection flags for this mapping, vendor
> + * driver can change, if required.
> + * Returns integer: success (0) or error (< 0)
> + *
> + * Parent device that support mediated device should be registered with mdev
> + * module with parent_ops structure.
> + */
> +
> +struct parent_ops {
> + struct module *owner;
> + const struct attribute_group **dev_attr_groups;
> + const struct attribute_group **mdev_attr_groups;
> +
> + int (*supported_config)(struct device *dev, char *config);
> + int (*create)(struct mdev_device *mdev, char *mdev_params);
> + int (*destroy)(struct mdev_device *mdev);
> + int (*reset)(struct mdev_device *mdev);
> + int (*start)(uuid_le uuid);
> + int (*stop)(uuid_le uuid);
> + ssize_t (*read)(struct mdev_device *mdev, char *buf, size_t count,
> + loff_t pos);
> + ssize_t (*write)(struct mdev_device *mdev, char *buf, size_t count,
> + loff_t pos);
> + int (*set_irqs)(struct mdev_device *mdev, uint32_t flags,
> + unsigned int index, unsigned int start,
> + unsigned int count, void *data);
> + int (*get_region_info)(struct mdev_device *mdev, int region_index,
> + struct vfio_region_info *region_info);
> + int (*validate_map_request)(struct mdev_device *mdev, loff_t pos,
> + u64 *virtaddr, unsigned long *pfn,
> + unsigned long *size, pgprot_t *prot);
> +};
> +
> +/*
> + * Parent Device
> + */
> +
> +struct parent_device {
> + struct device *dev;
> + const struct parent_ops *ops;
> +
> + /* internal */
> + struct kref ref;
> + struct list_head next;
> + struct list_head mdev_list;
> + struct mutex mdev_list_lock;
> + wait_queue_head_t release_done;
> +};
> +
> +/**
> + * struct mdev_driver - Mediated device driver
> + * @name: driver name
> + * @probe: called when new device created
> + * @remove: called when device removed
> + * @match: called when new device or driver is added for this bus. Return 1
> if
> + * given device can be handled by given driver and zero otherwise.
> + * @driver: device driver structure
> + *
> + **/
> +struct mdev_driver {
> + const char *name;
> + int (*probe)(struct device *dev);
> + void (*remove)(struct device *dev);
> + int (*match)(struct device *dev);
> + struct device_driver driver;
> +};
> +
> +static inline struct mdev_driver *to_mdev_driver(struct device_driver *drv)
> +{
> + return drv ? container_of(drv, struct mdev_driver, driver) : NULL;
> +}
> +
> +static inline struct mdev_device *to_mdev_device(struct device *dev)
> +{
> + return dev ? container_of(dev, struct mdev_device, dev) : NULL;
> +}
> +
> +static inline void *mdev_get_drvdata(struct mdev_device *mdev)
> +{
> + return mdev->driver_data;
> +}
> +
> +static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data)
> +{
> + mdev->driver_data = data;
> +}
> +
> +extern struct bus_type mdev_bus_type;
> +
> +#define dev_is_mdev(d) ((d)->bus == &mdev_bus_type)
> +
> +extern int mdev_register_device(struct device *dev,
> + const struct parent_ops *ops);
> +extern void mdev_unregister_device(struct device *dev);
> +
> +extern int mdev_register_driver(struct mdev_driver *drv, struct module
> *owner);
> +extern void mdev_unregister_driver(struct mdev_driver *drv);
> +
> +extern struct mdev_device *mdev_get_device(struct mdev_device *mdev);
> +extern void mdev_put_device(struct mdev_device *mdev);
> +
> +extern struct mdev_device *mdev_get_device_by_group(struct iommu_group
> *group);
> +
> +extern int mdev_device_invalidate_mapping(struct mdev_device *mdev,
> + unsigned long addr, unsigned long size);
> +
> +extern int mdev_add_phys_mapping(struct mdev_device *mdev,
> + struct address_space *mapping,
> + unsigned long addr, unsigned long size);
> +
> +
> +extern void mdev_del_phys_mapping(struct mdev_device *mdev, unsigned long
> addr);
> +#endif /* MDEV_H */
