Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+49
View File
@@ -0,0 +1,49 @@
config VFIO_IOMMU_TYPE1
tristate
depends on VFIO
default n
config VFIO_IOMMU_SPAPR_TCE
tristate
depends on VFIO && SPAPR_TCE_IOMMU
default VFIO
config VFIO_SPAPR_EEH
tristate
depends on EEH && VFIO_IOMMU_SPAPR_TCE
default VFIO
config VFIO_VIRQFD
tristate
depends on VFIO && EVENTFD
default n
menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
depends on IOMMU_API
select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU || ARM_SMMU_V3)
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/vfio.txt for more details.
If you don't know what to do here, say N.
menuconfig VFIO_NOIOMMU
bool "VFIO No-IOMMU support"
depends on VFIO
help
VFIO is built on the ability to isolate devices using the IOMMU.
Only with an IOMMU can userspace access to DMA capable devices be
considered secure. VFIO No-IOMMU mode enables IOMMU groups for
devices without IOMMU backing for the purpose of re-using the VFIO
infrastructure in a non-secure mode. Use of this mode will result
in an unsupportable kernel and will therefore taint the kernel.
Device assignment to virtual machines is also not possible with
this mode since there is no IOMMU to provide DMA translation.
If you don't know what to do here, say N.
source "drivers/vfio/pci/Kconfig"
source "drivers/vfio/platform/Kconfig"
source "drivers/vfio/mdev/Kconfig"
source "virt/lib/Kconfig"
+11
View File
@@ -0,0 +1,11 @@
# SPDX-License-Identifier: GPL-2.0
vfio_virqfd-y := virqfd.o
obj-$(CONFIG_VFIO) += vfio.o
obj-$(CONFIG_VFIO_VIRQFD) += vfio_virqfd.o
obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
obj-$(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/
+17
View File
@@ -0,0 +1,17 @@
config VFIO_MDEV
tristate "Mediated device driver framework"
depends on VFIO
default n
help
Provides a framework to virtualize devices.
See Documentation/vfio-mediated-device.txt for more details.
If you don't know what do here, say N.
config VFIO_MDEV_DEVICE
tristate "VFIO driver for Mediated devices"
depends on VFIO && VFIO_MDEV
default n
help
VFIO based driver for Mediated devices.
+5
View File
@@ -0,0 +1,5 @@
mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o
obj-$(CONFIG_VFIO_MDEV) += mdev.o
obj-$(CONFIG_VFIO_MDEV_DEVICE) += vfio_mdev.o
+412
View File
@@ -0,0 +1,412 @@
/*
* Mediated device Core Driver
*
* Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
* Author: Neo Jia <cjia@nvidia.com>
* Kirti Wankhede <kwankhede@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/slab.h>
#include <linux/uuid.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"
static LIST_HEAD(parent_list);
static DEFINE_MUTEX(parent_list_lock);
static struct class_compat *mdev_bus_compat_class;
static LIST_HEAD(mdev_list);
static DEFINE_MUTEX(mdev_list_lock);
struct device *mdev_parent_dev(struct mdev_device *mdev)
{
return mdev->parent->dev;
}
EXPORT_SYMBOL(mdev_parent_dev);
void *mdev_get_drvdata(struct mdev_device *mdev)
{
return mdev->driver_data;
}
EXPORT_SYMBOL(mdev_get_drvdata);
void mdev_set_drvdata(struct mdev_device *mdev, void *data)
{
mdev->driver_data = data;
}
EXPORT_SYMBOL(mdev_set_drvdata);
struct device *mdev_dev(struct mdev_device *mdev)
{
return &mdev->dev;
}
EXPORT_SYMBOL(mdev_dev);
struct mdev_device *mdev_from_dev(struct device *dev)
{
return dev_is_mdev(dev) ? to_mdev_device(dev) : NULL;
}
EXPORT_SYMBOL(mdev_from_dev);
uuid_le mdev_uuid(struct mdev_device *mdev)
{
return mdev->uuid;
}
EXPORT_SYMBOL(mdev_uuid);
/* Should be called holding parent_list_lock */
static struct mdev_parent *__find_parent_device(struct device *dev)
{
struct mdev_parent *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 mdev_parent *parent = container_of(kref, struct mdev_parent,
ref);
struct device *dev = parent->dev;
kfree(parent);
put_device(dev);
}
static
inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
{
if (parent)
kref_get(&parent->ref);
return parent;
}
static inline void mdev_put_parent(struct mdev_parent *parent)
{
if (parent)
kref_put(&parent->ref, mdev_release_parent);
}
static int mdev_device_create_ops(struct kobject *kobj,
struct mdev_device *mdev)
{
struct mdev_parent *parent = mdev->parent;
int ret;
ret = parent->ops->create(kobj, mdev);
if (ret)
return ret;
ret = sysfs_create_groups(&mdev->dev.kobj,
parent->ops->mdev_attr_groups);
if (ret)
parent->ops->remove(mdev);
return ret;
}
/*
* mdev_device_remove_ops gets called from sysfs's 'remove' and when parent
* device is being unregistered from mdev device framework.
* - 'force_remove' is set to 'false' when called from sysfs's 'remove' which
* indicates that if the mdev device is active, used by VMM or userspace
* application, vendor driver could return error then don't remove the device.
* - 'force_remove' is set to 'true' when called from mdev_unregister_device()
* which indicate that parent device is being removed from mdev device
* framework so remove mdev device forcefully.
*/
static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
{
struct mdev_parent *parent = mdev->parent;
int ret;
/*
* Vendor driver can return error if VMM or userspace application is
* using this mdev device.
*/
ret = parent->ops->remove(mdev);
if (ret && !force_remove)
return -EBUSY;
sysfs_remove_groups(&mdev->dev.kobj, parent->ops->mdev_attr_groups);
return 0;
}
static int mdev_device_remove_cb(struct device *dev, void *data)
{
if (dev_is_mdev(dev))
mdev_device_remove(dev, true);
return 0;
}
/*
* 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 mdev_parent_ops *ops)
{
int ret;
struct mdev_parent *parent;
/* check for mandatory ops */
if (!ops || !ops->create || !ops->remove || !ops->supported_type_groups)
return -EINVAL;
dev = get_device(dev);
if (!dev)
return -EINVAL;
mutex_lock(&parent_list_lock);
/* Check for duplicate */
parent = __find_parent_device(dev);
if (parent) {
parent = NULL;
ret = -EEXIST;
goto add_dev_err;
}
parent = kzalloc(sizeof(*parent), GFP_KERNEL);
if (!parent) {
ret = -ENOMEM;
goto add_dev_err;
}
kref_init(&parent->ref);
parent->dev = dev;
parent->ops = ops;
if (!mdev_bus_compat_class) {
mdev_bus_compat_class = class_compat_register("mdev_bus");
if (!mdev_bus_compat_class) {
ret = -ENOMEM;
goto add_dev_err;
}
}
ret = parent_create_sysfs_files(parent);
if (ret)
goto add_dev_err;
ret = class_compat_create_link(mdev_bus_compat_class, dev, NULL);
if (ret)
dev_warn(dev, "Failed to create compatibility class link\n");
list_add(&parent->next, &parent_list);
mutex_unlock(&parent_list_lock);
dev_info(dev, "MDEV: Registered\n");
return 0;
add_dev_err:
mutex_unlock(&parent_list_lock);
if (parent)
mdev_put_parent(parent);
else
put_device(dev);
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 mdev_parent *parent;
mutex_lock(&parent_list_lock);
parent = __find_parent_device(dev);
if (!parent) {
mutex_unlock(&parent_list_lock);
return;
}
dev_info(dev, "MDEV: Unregistering\n");
list_del(&parent->next);
class_compat_remove_link(mdev_bus_compat_class, dev, NULL);
device_for_each_child(dev, NULL, mdev_device_remove_cb);
parent_remove_sysfs_files(parent);
mutex_unlock(&parent_list_lock);
mdev_put_parent(parent);
}
EXPORT_SYMBOL(mdev_unregister_device);
static void mdev_device_release(struct device *dev)
{
struct mdev_device *mdev = to_mdev_device(dev);
mutex_lock(&mdev_list_lock);
list_del(&mdev->next);
mutex_unlock(&mdev_list_lock);
dev_dbg(&mdev->dev, "MDEV: destroying\n");
kfree(mdev);
}
int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
{
int ret;
struct mdev_device *mdev, *tmp;
struct mdev_parent *parent;
struct mdev_type *type = to_mdev_type(kobj);
parent = mdev_get_parent(type->parent);
if (!parent)
return -EINVAL;
mutex_lock(&mdev_list_lock);
/* Check for duplicate */
list_for_each_entry(tmp, &mdev_list, next) {
if (!uuid_le_cmp(tmp->uuid, uuid)) {
mutex_unlock(&mdev_list_lock);
ret = -EEXIST;
goto mdev_fail;
}
}
mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
if (!mdev) {
mutex_unlock(&mdev_list_lock);
ret = -ENOMEM;
goto mdev_fail;
}
memcpy(&mdev->uuid, &uuid, sizeof(uuid_le));
list_add(&mdev->next, &mdev_list);
mutex_unlock(&mdev_list_lock);
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", uuid.b);
ret = device_register(&mdev->dev);
if (ret) {
put_device(&mdev->dev);
goto mdev_fail;
}
ret = mdev_device_create_ops(kobj, mdev);
if (ret)
goto create_fail;
ret = mdev_create_sysfs_files(&mdev->dev, type);
if (ret) {
mdev_device_remove_ops(mdev, true);
goto create_fail;
}
mdev->type_kobj = kobj;
mdev->active = true;
dev_dbg(&mdev->dev, "MDEV: created\n");
return 0;
create_fail:
device_unregister(&mdev->dev);
mdev_fail:
mdev_put_parent(parent);
return ret;
}
int mdev_device_remove(struct device *dev, bool force_remove)
{
struct mdev_device *mdev, *tmp;
struct mdev_parent *parent;
struct mdev_type *type;
int ret;
mdev = to_mdev_device(dev);
mutex_lock(&mdev_list_lock);
list_for_each_entry(tmp, &mdev_list, next) {
if (tmp == mdev)
break;
}
if (tmp != mdev) {
mutex_unlock(&mdev_list_lock);
return -ENODEV;
}
if (!mdev->active) {
mutex_unlock(&mdev_list_lock);
return -EAGAIN;
}
mdev->active = false;
mutex_unlock(&mdev_list_lock);
type = to_mdev_type(mdev->type_kobj);
parent = mdev->parent;
ret = mdev_device_remove_ops(mdev, force_remove);
if (ret) {
mdev->active = true;
return ret;
}
mdev_remove_sysfs_files(dev, type);
device_unregister(dev);
mdev_put_parent(parent);
return 0;
}
static int __init mdev_init(void)
{
return mdev_bus_register();
}
static void __exit mdev_exit(void)
{
if (mdev_bus_compat_class)
class_compat_unregister(mdev_bus_compat_class);
mdev_bus_unregister();
}
module_init(mdev_init)
module_exit(mdev_exit)
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_SOFTDEP("post: vfio_mdev");
+119
View File
@@ -0,0 +1,119 @@
/*
* MDEV driver
*
* Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
* Author: Neo Jia <cjia@nvidia.com>
* Kirti Wankhede <kwankhede@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))
return PTR_ERR(group);
ret = iommu_group_add_device(group, &mdev->dev);
if (!ret)
dev_info(&mdev->dev, "MDEV: group_id = %d\n",
iommu_group_id(group));
iommu_group_put(group);
return ret;
}
static void mdev_detach_iommu(struct mdev_device *mdev)
{
iommu_group_remove_device(&mdev->dev);
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)
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;
}
struct bus_type mdev_bus_type = {
.name = "mdev",
.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);
}
+64
View File
@@ -0,0 +1,64 @@
/*
* Mediated device interal definitions
*
* Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
* Author: Neo Jia <cjia@nvidia.com>
* Kirti Wankhede <kwankhede@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);
struct mdev_parent {
struct device *dev;
const struct mdev_parent_ops *ops;
struct kref ref;
struct list_head next;
struct kset *mdev_types_kset;
struct list_head type_list;
};
struct mdev_device {
struct device dev;
struct mdev_parent *parent;
uuid_le uuid;
void *driver_data;
struct kref ref;
struct list_head next;
struct kobject *type_kobj;
bool active;
};
#define to_mdev_device(dev) container_of(dev, struct mdev_device, dev)
#define dev_is_mdev(d) ((d)->bus == &mdev_bus_type)
struct mdev_type {
struct kobject kobj;
struct kobject *devices_kobj;
struct mdev_parent *parent;
struct list_head next;
struct attribute_group *group;
};
#define to_mdev_type_attr(_attr) \
container_of(_attr, struct mdev_type_attribute, attr)
#define to_mdev_type(_kobj) \
container_of(_kobj, struct mdev_type, kobj)
int parent_create_sysfs_files(struct mdev_parent *parent);
void parent_remove_sysfs_files(struct mdev_parent *parent);
int mdev_create_sysfs_files(struct device *dev, struct mdev_type *type);
void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type);
int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid);
int mdev_device_remove(struct device *dev, bool force_remove);
#endif /* MDEV_PRIVATE_H */
+286
View File
@@ -0,0 +1,286 @@
/*
* File attributes for Mediated devices
*
* Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
* Author: Neo Jia <cjia@nvidia.com>
* Kirti Wankhede <kwankhede@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"
/* Static functions */
static ssize_t mdev_type_attr_show(struct kobject *kobj,
struct attribute *__attr, char *buf)
{
struct mdev_type_attribute *attr = to_mdev_type_attr(__attr);
struct mdev_type *type = to_mdev_type(kobj);
ssize_t ret = -EIO;
if (attr->show)
ret = attr->show(kobj, type->parent->dev, buf);
return ret;
}
static ssize_t mdev_type_attr_store(struct kobject *kobj,
struct attribute *__attr,
const char *buf, size_t count)
{
struct mdev_type_attribute *attr = to_mdev_type_attr(__attr);
struct mdev_type *type = to_mdev_type(kobj);
ssize_t ret = -EIO;
if (attr->store)
ret = attr->store(&type->kobj, type->parent->dev, buf, count);
return ret;
}
static const struct sysfs_ops mdev_type_sysfs_ops = {
.show = mdev_type_attr_show,
.store = mdev_type_attr_store,
};
static ssize_t create_store(struct kobject *kobj, struct device *dev,
const char *buf, size_t count)
{
char *str;
uuid_le uuid;
int ret;
if ((count < UUID_STRING_LEN) || (count > UUID_STRING_LEN + 1))
return -EINVAL;
str = kstrndup(buf, count, GFP_KERNEL);
if (!str)
return -ENOMEM;
ret = uuid_le_to_bin(str, &uuid);
kfree(str);
if (ret)
return ret;
ret = mdev_device_create(kobj, dev, uuid);
if (ret)
return ret;
return count;
}
MDEV_TYPE_ATTR_WO(create);
static void mdev_type_release(struct kobject *kobj)
{
struct mdev_type *type = to_mdev_type(kobj);
pr_debug("Releasing group %s\n", kobj->name);
kfree(type);
}
static struct kobj_type mdev_type_ktype = {
.sysfs_ops = &mdev_type_sysfs_ops,
.release = mdev_type_release,
};
struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
struct attribute_group *group)
{
struct mdev_type *type;
int ret;
if (!group->name) {
pr_err("%s: Type name empty!\n", __func__);
return ERR_PTR(-EINVAL);
}
type = kzalloc(sizeof(*type), GFP_KERNEL);
if (!type)
return ERR_PTR(-ENOMEM);
type->kobj.kset = parent->mdev_types_kset;
type->parent = parent;
ret = kobject_init_and_add(&type->kobj, &mdev_type_ktype, NULL,
"%s-%s", dev_driver_string(parent->dev),
group->name);
if (ret) {
kobject_put(&type->kobj);
return ERR_PTR(ret);
}
ret = sysfs_create_file(&type->kobj, &mdev_type_attr_create.attr);
if (ret)
goto attr_create_failed;
type->devices_kobj = kobject_create_and_add("devices", &type->kobj);
if (!type->devices_kobj) {
ret = -ENOMEM;
goto attr_devices_failed;
}
ret = sysfs_create_files(&type->kobj,
(const struct attribute **)group->attrs);
if (ret) {
ret = -ENOMEM;
goto attrs_failed;
}
type->group = group;
return type;
attrs_failed:
kobject_put(type->devices_kobj);
attr_devices_failed:
sysfs_remove_file(&type->kobj, &mdev_type_attr_create.attr);
attr_create_failed:
kobject_del(&type->kobj);
kobject_put(&type->kobj);
return ERR_PTR(ret);
}
static void remove_mdev_supported_type(struct mdev_type *type)
{
sysfs_remove_files(&type->kobj,
(const struct attribute **)type->group->attrs);
kobject_put(type->devices_kobj);
sysfs_remove_file(&type->kobj, &mdev_type_attr_create.attr);
kobject_del(&type->kobj);
kobject_put(&type->kobj);
}
static int add_mdev_supported_type_groups(struct mdev_parent *parent)
{
int i;
for (i = 0; parent->ops->supported_type_groups[i]; i++) {
struct mdev_type *type;
type = add_mdev_supported_type(parent,
parent->ops->supported_type_groups[i]);
if (IS_ERR(type)) {
struct mdev_type *ltype, *tmp;
list_for_each_entry_safe(ltype, tmp, &parent->type_list,
next) {
list_del(&ltype->next);
remove_mdev_supported_type(ltype);
}
return PTR_ERR(type);
}
list_add(&type->next, &parent->type_list);
}
return 0;
}
/* mdev sysfs functions */
void parent_remove_sysfs_files(struct mdev_parent *parent)
{
struct mdev_type *type, *tmp;
list_for_each_entry_safe(type, tmp, &parent->type_list, next) {
list_del(&type->next);
remove_mdev_supported_type(type);
}
sysfs_remove_groups(&parent->dev->kobj, parent->ops->dev_attr_groups);
kset_unregister(parent->mdev_types_kset);
}
int parent_create_sysfs_files(struct mdev_parent *parent)
{
int ret;
parent->mdev_types_kset = kset_create_and_add("mdev_supported_types",
NULL, &parent->dev->kobj);
if (!parent->mdev_types_kset)
return -ENOMEM;
INIT_LIST_HEAD(&parent->type_list);
ret = sysfs_create_groups(&parent->dev->kobj,
parent->ops->dev_attr_groups);
if (ret)
goto create_err;
ret = add_mdev_supported_type_groups(parent);
if (ret)
sysfs_remove_groups(&parent->dev->kobj,
parent->ops->dev_attr_groups);
else
return ret;
create_err:
kset_unregister(parent->mdev_types_kset);
return ret;
}
static ssize_t remove_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
unsigned long val;
if (kstrtoul(buf, 0, &val) < 0)
return -EINVAL;
if (val && device_remove_file_self(dev, attr)) {
int ret;
ret = mdev_device_remove(dev, false);
if (ret) {
device_create_file(dev, attr);
return ret;
}
}
return count;
}
static DEVICE_ATTR_WO(remove);
static const struct attribute *mdev_device_attrs[] = {
&dev_attr_remove.attr,
NULL,
};
int mdev_create_sysfs_files(struct device *dev, struct mdev_type *type)
{
int ret;
ret = sysfs_create_link(type->devices_kobj, &dev->kobj, dev_name(dev));
if (ret)
return ret;
ret = sysfs_create_link(&dev->kobj, &type->kobj, "mdev_type");
if (ret)
goto type_link_failed;
ret = sysfs_create_files(&dev->kobj, mdev_device_attrs);
if (ret)
goto create_files_failed;
return ret;
create_files_failed:
sysfs_remove_link(&dev->kobj, "mdev_type");
type_link_failed:
sysfs_remove_link(type->devices_kobj, dev_name(dev));
return ret;
}
void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type)
{
sysfs_remove_files(&dev->kobj, mdev_device_attrs);
sysfs_remove_link(&dev->kobj, "mdev_type");
sysfs_remove_link(type->devices_kobj, dev_name(dev));
}
+148
View File
@@ -0,0 +1,148 @@
/*
* VFIO based driver for Mediated device
*
* Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
* Author: Neo Jia <cjia@nvidia.com>
* Kirti Wankhede <kwankhede@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/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/vfio.h>
#include <linux/mdev.h>
#include "mdev_private.h"
#define DRIVER_VERSION "0.1"
#define DRIVER_AUTHOR "NVIDIA Corporation"
#define DRIVER_DESC "VFIO based driver for Mediated device"
static int vfio_mdev_open(void *device_data)
{
struct mdev_device *mdev = device_data;
struct mdev_parent *parent = mdev->parent;
int ret;
if (unlikely(!parent->ops->open))
return -EINVAL;
if (!try_module_get(THIS_MODULE))
return -ENODEV;
ret = parent->ops->open(mdev);
if (ret)
module_put(THIS_MODULE);
return ret;
}
static void vfio_mdev_release(void *device_data)
{
struct mdev_device *mdev = device_data;
struct mdev_parent *parent = mdev->parent;
if (likely(parent->ops->release))
parent->ops->release(mdev);
module_put(THIS_MODULE);
}
static long vfio_mdev_unlocked_ioctl(void *device_data,
unsigned int cmd, unsigned long arg)
{
struct mdev_device *mdev = device_data;
struct mdev_parent *parent = mdev->parent;
if (unlikely(!parent->ops->ioctl))
return -EINVAL;
return parent->ops->ioctl(mdev, cmd, arg);
}
static ssize_t vfio_mdev_read(void *device_data, char __user *buf,
size_t count, loff_t *ppos)
{
struct mdev_device *mdev = device_data;
struct mdev_parent *parent = mdev->parent;
if (unlikely(!parent->ops->read))
return -EINVAL;
return parent->ops->read(mdev, buf, count, ppos);
}
static ssize_t vfio_mdev_write(void *device_data, const char __user *buf,
size_t count, loff_t *ppos)
{
struct mdev_device *mdev = device_data;
struct mdev_parent *parent = mdev->parent;
if (unlikely(!parent->ops->write))
return -EINVAL;
return parent->ops->write(mdev, buf, count, ppos);
}
static int vfio_mdev_mmap(void *device_data, struct vm_area_struct *vma)
{
struct mdev_device *mdev = device_data;
struct mdev_parent *parent = mdev->parent;
if (unlikely(!parent->ops->mmap))
return -EINVAL;
return parent->ops->mmap(mdev, vma);
}
static const struct vfio_device_ops vfio_mdev_dev_ops = {
.name = "vfio-mdev",
.open = vfio_mdev_open,
.release = vfio_mdev_release,
.ioctl = vfio_mdev_unlocked_ioctl,
.read = vfio_mdev_read,
.write = vfio_mdev_write,
.mmap = vfio_mdev_mmap,
};
static int vfio_mdev_probe(struct device *dev)
{
struct mdev_device *mdev = to_mdev_device(dev);
return vfio_add_group_dev(dev, &vfio_mdev_dev_ops, mdev);
}
static void vfio_mdev_remove(struct device *dev)
{
vfio_del_group_dev(dev);
}
static struct mdev_driver vfio_mdev_driver = {
.name = "vfio_mdev",
.probe = vfio_mdev_probe,
.remove = vfio_mdev_remove,
};
static int __init vfio_mdev_init(void)
{
return mdev_register_driver(&vfio_mdev_driver, THIS_MODULE);
}
static void __exit vfio_mdev_exit(void)
{
mdev_unregister_driver(&vfio_mdev_driver);
}
module_init(vfio_mdev_init)
module_exit(vfio_mdev_exit)
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
+40
View File
@@ -0,0 +1,40 @@
config VFIO_PCI
tristate "VFIO support for PCI devices"
depends on VFIO && PCI && EVENTFD
select VFIO_VIRQFD
select IRQ_BYPASS_MANAGER
help
Support for the PCI VFIO bus driver. This is required to make
use of PCI drivers using the VFIO framework.
If you don't know what to do here, say N.
config VFIO_PCI_VGA
bool "VFIO PCI support for VGA devices"
depends on VFIO_PCI && X86 && VGA_ARB
help
Support for VGA extension to VFIO PCI. This exposes an additional
region on VGA devices for accessing legacy VGA addresses used by
BIOS and generic video drivers.
If you don't know what to do here, say N.
config VFIO_PCI_MMAP
depends on VFIO_PCI
def_bool y if !S390
config VFIO_PCI_INTX
depends on VFIO_PCI
def_bool y if !S390
config VFIO_PCI_IGD
bool "VFIO PCI extensions for Intel graphics (GVT-d)"
depends on VFIO_PCI && X86
default y
help
Support for Intel IGD specific extensions to enable direct
assignment to virtual machines. This includes exposing an IGD
specific firmware table and read-only copies of the host bridge
and LPC bridge config space.
To enable Intel IGD assignment through vfio-pci, say Y.
+5
View File
@@ -0,0 +1,5 @@
vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o
obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
+280
View File
@@ -0,0 +1,280 @@
/*
* VFIO PCI Intel Graphics support
*
* Copyright (C) 2016 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.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.
*
* Register a device specific region through which to provide read-only
* access to the Intel IGD opregion. The register defining the opregion
* address is also virtualized to prevent user modification.
*/
#include <linux/io.h>
#include <linux/pci.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include "vfio_pci_private.h"
#define OPREGION_SIGNATURE "IntelGraphicsMem"
#define OPREGION_SIZE (8 * 1024)
#define OPREGION_PCI_ADDR 0xfc
static size_t vfio_pci_igd_rw(struct vfio_pci_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite)
{
unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS;
void *base = vdev->region[i].data;
loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
if (pos >= vdev->region[i].size || iswrite)
return -EINVAL;
count = min(count, (size_t)(vdev->region[i].size - pos));
if (copy_to_user(buf, base + pos, count))
return -EFAULT;
*ppos += count;
return count;
}
static void vfio_pci_igd_release(struct vfio_pci_device *vdev,
struct vfio_pci_region *region)
{
memunmap(region->data);
}
static const struct vfio_pci_regops vfio_pci_igd_regops = {
.rw = vfio_pci_igd_rw,
.release = vfio_pci_igd_release,
};
static int vfio_pci_igd_opregion_init(struct vfio_pci_device *vdev)
{
__le32 *dwordp = (__le32 *)(vdev->vconfig + OPREGION_PCI_ADDR);
u32 addr, size;
void *base;
int ret;
ret = pci_read_config_dword(vdev->pdev, OPREGION_PCI_ADDR, &addr);
if (ret)
return ret;
if (!addr || !(~addr))
return -ENODEV;
base = memremap(addr, OPREGION_SIZE, MEMREMAP_WB);
if (!base)
return -ENOMEM;
if (memcmp(base, OPREGION_SIGNATURE, 16)) {
memunmap(base);
return -EINVAL;
}
size = le32_to_cpu(*(__le32 *)(base + 16));
if (!size) {
memunmap(base);
return -EINVAL;
}
size *= 1024; /* In KB */
if (size != OPREGION_SIZE) {
memunmap(base);
base = memremap(addr, size, MEMREMAP_WB);
if (!base)
return -ENOMEM;
}
ret = vfio_pci_register_dev_region(vdev,
PCI_VENDOR_ID_INTEL | VFIO_REGION_TYPE_PCI_VENDOR_TYPE,
VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION,
&vfio_pci_igd_regops, size, VFIO_REGION_INFO_FLAG_READ, base);
if (ret) {
memunmap(base);
return ret;
}
/* Fill vconfig with the hw value and virtualize register */
*dwordp = cpu_to_le32(addr);
memset(vdev->pci_config_map + OPREGION_PCI_ADDR,
PCI_CAP_ID_INVALID_VIRT, 4);
return ret;
}
static size_t vfio_pci_igd_cfg_rw(struct vfio_pci_device *vdev,
char __user *buf, size_t count, loff_t *ppos,
bool iswrite)
{
unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS;
struct pci_dev *pdev = vdev->region[i].data;
loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
size_t size;
int ret;
if (pos >= vdev->region[i].size || iswrite)
return -EINVAL;
size = count = min(count, (size_t)(vdev->region[i].size - pos));
if ((pos & 1) && size) {
u8 val;
ret = pci_user_read_config_byte(pdev, pos, &val);
if (ret)
return pcibios_err_to_errno(ret);
if (copy_to_user(buf + count - size, &val, 1))
return -EFAULT;
pos++;
size--;
}
if ((pos & 3) && size > 2) {
u16 val;
ret = pci_user_read_config_word(pdev, pos, &val);
if (ret)
return pcibios_err_to_errno(ret);
val = cpu_to_le16(val);
if (copy_to_user(buf + count - size, &val, 2))
return -EFAULT;
pos += 2;
size -= 2;
}
while (size > 3) {
u32 val;
ret = pci_user_read_config_dword(pdev, pos, &val);
if (ret)
return pcibios_err_to_errno(ret);
val = cpu_to_le32(val);
if (copy_to_user(buf + count - size, &val, 4))
return -EFAULT;
pos += 4;
size -= 4;
}
while (size >= 2) {
u16 val;
ret = pci_user_read_config_word(pdev, pos, &val);
if (ret)
return pcibios_err_to_errno(ret);
val = cpu_to_le16(val);
if (copy_to_user(buf + count - size, &val, 2))
return -EFAULT;
pos += 2;
size -= 2;
}
while (size) {
u8 val;
ret = pci_user_read_config_byte(pdev, pos, &val);
if (ret)
return pcibios_err_to_errno(ret);
if (copy_to_user(buf + count - size, &val, 1))
return -EFAULT;
pos++;
size--;
}
*ppos += count;
return count;
}
static void vfio_pci_igd_cfg_release(struct vfio_pci_device *vdev,
struct vfio_pci_region *region)
{
struct pci_dev *pdev = region->data;
pci_dev_put(pdev);
}
static const struct vfio_pci_regops vfio_pci_igd_cfg_regops = {
.rw = vfio_pci_igd_cfg_rw,
.release = vfio_pci_igd_cfg_release,
};
static int vfio_pci_igd_cfg_init(struct vfio_pci_device *vdev)
{
struct pci_dev *host_bridge, *lpc_bridge;
int ret;
host_bridge = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
if (!host_bridge)
return -ENODEV;
if (host_bridge->vendor != PCI_VENDOR_ID_INTEL ||
host_bridge->class != (PCI_CLASS_BRIDGE_HOST << 8)) {
pci_dev_put(host_bridge);
return -EINVAL;
}
ret = vfio_pci_register_dev_region(vdev,
PCI_VENDOR_ID_INTEL | VFIO_REGION_TYPE_PCI_VENDOR_TYPE,
VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG,
&vfio_pci_igd_cfg_regops, host_bridge->cfg_size,
VFIO_REGION_INFO_FLAG_READ, host_bridge);
if (ret) {
pci_dev_put(host_bridge);
return ret;
}
lpc_bridge = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0x1f, 0));
if (!lpc_bridge)
return -ENODEV;
if (lpc_bridge->vendor != PCI_VENDOR_ID_INTEL ||
lpc_bridge->class != (PCI_CLASS_BRIDGE_ISA << 8)) {
pci_dev_put(lpc_bridge);
return -EINVAL;
}
ret = vfio_pci_register_dev_region(vdev,
PCI_VENDOR_ID_INTEL | VFIO_REGION_TYPE_PCI_VENDOR_TYPE,
VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG,
&vfio_pci_igd_cfg_regops, lpc_bridge->cfg_size,
VFIO_REGION_INFO_FLAG_READ, lpc_bridge);
if (ret) {
pci_dev_put(lpc_bridge);
return ret;
}
return 0;
}
int vfio_pci_igd_init(struct vfio_pci_device *vdev)
{
int ret;
ret = vfio_pci_igd_opregion_init(vdev);
if (ret)
return ret;
ret = vfio_pci_igd_cfg_init(vdev);
if (ret)
return ret;
return 0;
}
+696
View File
@@ -0,0 +1,696 @@
/*
* VFIO PCI interrupt handling
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.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.
*
* Derived from original vfio:
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
* Author: Tom Lyon, pugs@cisco.com
*/
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/eventfd.h>
#include <linux/msi.h>
#include <linux/pci.h>
#include <linux/file.h>
#include <linux/vfio.h>
#include <linux/wait.h>
#include <linux/slab.h>
#include "vfio_pci_private.h"
/*
* INTx
*/
static void vfio_send_intx_eventfd(void *opaque, void *unused)
{
struct vfio_pci_device *vdev = opaque;
if (likely(is_intx(vdev) && !vdev->virq_disabled))
eventfd_signal(vdev->ctx[0].trigger, 1);
}
void vfio_pci_intx_mask(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
unsigned long flags;
spin_lock_irqsave(&vdev->irqlock, flags);
/*
* Masking can come from interrupt, ioctl, or config space
* via INTx disable. The latter means this can get called
* even when not using intx delivery. In this case, just
* try to have the physical bit follow the virtual bit.
*/
if (unlikely(!is_intx(vdev))) {
if (vdev->pci_2_3)
pci_intx(pdev, 0);
} else if (!vdev->ctx[0].masked) {
/*
* Can't use check_and_mask here because we always want to
* mask, not just when something is pending.
*/
if (vdev->pci_2_3)
pci_intx(pdev, 0);
else
disable_irq_nosync(pdev->irq);
vdev->ctx[0].masked = true;
}
spin_unlock_irqrestore(&vdev->irqlock, flags);
}
/*
* If this is triggered by an eventfd, we can't call eventfd_signal
* or else we'll deadlock on the eventfd wait queue. Return >0 when
* a signal is necessary, which can then be handled via a work queue
* or directly depending on the caller.
*/
static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
{
struct vfio_pci_device *vdev = opaque;
struct pci_dev *pdev = vdev->pdev;
unsigned long flags;
int ret = 0;
spin_lock_irqsave(&vdev->irqlock, flags);
/*
* Unmasking comes from ioctl or config, so again, have the
* physical bit follow the virtual even when not using INTx.
*/
if (unlikely(!is_intx(vdev))) {
if (vdev->pci_2_3)
pci_intx(pdev, 1);
} else if (vdev->ctx[0].masked && !vdev->virq_disabled) {
/*
* A pending interrupt here would immediately trigger,
* but we can avoid that overhead by just re-sending
* the interrupt to the user.
*/
if (vdev->pci_2_3) {
if (!pci_check_and_unmask_intx(pdev))
ret = 1;
} else
enable_irq(pdev->irq);
vdev->ctx[0].masked = (ret > 0);
}
spin_unlock_irqrestore(&vdev->irqlock, flags);
return ret;
}
void vfio_pci_intx_unmask(struct vfio_pci_device *vdev)
{
if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0)
vfio_send_intx_eventfd(vdev, NULL);
}
static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
{
struct vfio_pci_device *vdev = dev_id;
unsigned long flags;
int ret = IRQ_NONE;
spin_lock_irqsave(&vdev->irqlock, flags);
if (!vdev->pci_2_3) {
disable_irq_nosync(vdev->pdev->irq);
vdev->ctx[0].masked = true;
ret = IRQ_HANDLED;
} else if (!vdev->ctx[0].masked && /* may be shared */
pci_check_and_mask_intx(vdev->pdev)) {
vdev->ctx[0].masked = true;
ret = IRQ_HANDLED;
}
spin_unlock_irqrestore(&vdev->irqlock, flags);
if (ret == IRQ_HANDLED)
vfio_send_intx_eventfd(vdev, NULL);
return ret;
}
static int vfio_intx_enable(struct vfio_pci_device *vdev)
{
if (!is_irq_none(vdev))
return -EINVAL;
if (!vdev->pdev->irq)
return -ENODEV;
vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
if (!vdev->ctx)
return -ENOMEM;
vdev->num_ctx = 1;
/*
* If the virtual interrupt is masked, restore it. Devices
* supporting DisINTx can be masked at the hardware level
* here, non-PCI-2.3 devices will have to wait until the
* interrupt is enabled.
*/
vdev->ctx[0].masked = vdev->virq_disabled;
if (vdev->pci_2_3)
pci_intx(vdev->pdev, !vdev->ctx[0].masked);
vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX;
return 0;
}
static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd)
{
struct pci_dev *pdev = vdev->pdev;
unsigned long irqflags = IRQF_SHARED;
struct eventfd_ctx *trigger;
unsigned long flags;
int ret;
if (vdev->ctx[0].trigger) {
free_irq(pdev->irq, vdev);
kfree(vdev->ctx[0].name);
eventfd_ctx_put(vdev->ctx[0].trigger);
vdev->ctx[0].trigger = NULL;
}
if (fd < 0) /* Disable only */
return 0;
vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)",
pci_name(pdev));
if (!vdev->ctx[0].name)
return -ENOMEM;
trigger = eventfd_ctx_fdget(fd);
if (IS_ERR(trigger)) {
kfree(vdev->ctx[0].name);
return PTR_ERR(trigger);
}
vdev->ctx[0].trigger = trigger;
if (!vdev->pci_2_3)
irqflags = 0;
ret = request_irq(pdev->irq, vfio_intx_handler,
irqflags, vdev->ctx[0].name, vdev);
if (ret) {
vdev->ctx[0].trigger = NULL;
kfree(vdev->ctx[0].name);
eventfd_ctx_put(trigger);
return ret;
}
/*
* INTx disable will stick across the new irq setup,
* disable_irq won't.
*/
spin_lock_irqsave(&vdev->irqlock, flags);
if (!vdev->pci_2_3 && vdev->ctx[0].masked)
disable_irq_nosync(pdev->irq);
spin_unlock_irqrestore(&vdev->irqlock, flags);
return 0;
}
static void vfio_intx_disable(struct vfio_pci_device *vdev)
{
vfio_virqfd_disable(&vdev->ctx[0].unmask);
vfio_virqfd_disable(&vdev->ctx[0].mask);
vfio_intx_set_signal(vdev, -1);
vdev->irq_type = VFIO_PCI_NUM_IRQS;
vdev->num_ctx = 0;
kfree(vdev->ctx);
}
/*
* MSI/MSI-X
*/
static irqreturn_t vfio_msihandler(int irq, void *arg)
{
struct eventfd_ctx *trigger = arg;
eventfd_signal(trigger, 1);
return IRQ_HANDLED;
}
static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
{
struct pci_dev *pdev = vdev->pdev;
unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
int ret;
u16 cmd;
if (!is_irq_none(vdev))
return -EINVAL;
vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
if (!vdev->ctx)
return -ENOMEM;
/* return the number of supported vectors if we can't get all: */
cmd = vfio_pci_memory_lock_and_enable(vdev);
ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag);
if (ret < nvec) {
if (ret > 0)
pci_free_irq_vectors(pdev);
vfio_pci_memory_unlock_and_restore(vdev, cmd);
kfree(vdev->ctx);
return ret;
}
vfio_pci_memory_unlock_and_restore(vdev, cmd);
vdev->num_ctx = nvec;
vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
VFIO_PCI_MSI_IRQ_INDEX;
if (!msix) {
/*
* Compute the virtual hardware field for max msi vectors -
* it is the log base 2 of the number of vectors.
*/
vdev->msi_qmax = fls(nvec * 2 - 1) - 1;
}
return 0;
}
static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
int vector, int fd, bool msix)
{
struct pci_dev *pdev = vdev->pdev;
struct eventfd_ctx *trigger;
int irq, ret;
u16 cmd;
if (vector < 0 || vector >= vdev->num_ctx)
return -EINVAL;
irq = pci_irq_vector(pdev, vector);
if (vdev->ctx[vector].trigger) {
irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
cmd = vfio_pci_memory_lock_and_enable(vdev);
free_irq(irq, vdev->ctx[vector].trigger);
vfio_pci_memory_unlock_and_restore(vdev, cmd);
kfree(vdev->ctx[vector].name);
eventfd_ctx_put(vdev->ctx[vector].trigger);
vdev->ctx[vector].trigger = NULL;
}
if (fd < 0)
return 0;
vdev->ctx[vector].name = kasprintf(GFP_KERNEL, "vfio-msi%s[%d](%s)",
msix ? "x" : "", vector,
pci_name(pdev));
if (!vdev->ctx[vector].name)
return -ENOMEM;
trigger = eventfd_ctx_fdget(fd);
if (IS_ERR(trigger)) {
kfree(vdev->ctx[vector].name);
return PTR_ERR(trigger);
}
/*
* The MSIx vector table resides in device memory which may be cleared
* via backdoor resets. We don't allow direct access to the vector
* table so even if a userspace driver attempts to save/restore around
* such a reset it would be unsuccessful. To avoid this, restore the
* cached value of the message prior to enabling.
*/
cmd = vfio_pci_memory_lock_and_enable(vdev);
if (msix) {
struct msi_msg msg;
get_cached_msi_msg(irq, &msg);
pci_write_msi_msg(irq, &msg);
}
ret = request_irq(irq, vfio_msihandler, 0,
vdev->ctx[vector].name, trigger);
vfio_pci_memory_unlock_and_restore(vdev, cmd);
if (ret) {
kfree(vdev->ctx[vector].name);
eventfd_ctx_put(trigger);
return ret;
}
vdev->ctx[vector].producer.token = trigger;
vdev->ctx[vector].producer.irq = irq;
ret = irq_bypass_register_producer(&vdev->ctx[vector].producer);
if (unlikely(ret)) {
dev_info(&pdev->dev,
"irq bypass producer (token %p) registration fails: %d\n",
vdev->ctx[vector].producer.token, ret);
vdev->ctx[vector].producer.token = NULL;
}
vdev->ctx[vector].trigger = trigger;
return 0;
}
static int vfio_msi_set_block(struct vfio_pci_device *vdev, unsigned start,
unsigned count, int32_t *fds, bool msix)
{
int i, j, ret = 0;
if (start >= vdev->num_ctx || start + count > vdev->num_ctx)
return -EINVAL;
for (i = 0, j = start; i < count && !ret; i++, j++) {
int fd = fds ? fds[i] : -1;
ret = vfio_msi_set_vector_signal(vdev, j, fd, msix);
}
if (ret) {
for (--j; j >= (int)start; j--)
vfio_msi_set_vector_signal(vdev, j, -1, msix);
}
return ret;
}
static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
{
struct pci_dev *pdev = vdev->pdev;
int i;
u16 cmd;
for (i = 0; i < vdev->num_ctx; i++) {
vfio_virqfd_disable(&vdev->ctx[i].unmask);
vfio_virqfd_disable(&vdev->ctx[i].mask);
}
vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
cmd = vfio_pci_memory_lock_and_enable(vdev);
pci_free_irq_vectors(pdev);
vfio_pci_memory_unlock_and_restore(vdev, cmd);
/*
* Both disable paths above use pci_intx_for_msi() to clear DisINTx
* via their shutdown paths. Restore for NoINTx devices.
*/
if (vdev->nointx)
pci_intx(pdev, 0);
vdev->irq_type = VFIO_PCI_NUM_IRQS;
vdev->num_ctx = 0;
kfree(vdev->ctx);
}
/*
* IOCTL support
*/
static int vfio_pci_set_intx_unmask(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
if (!is_intx(vdev) || start != 0 || count != 1)
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_NONE) {
vfio_pci_intx_unmask(vdev);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t unmask = *(uint8_t *)data;
if (unmask)
vfio_pci_intx_unmask(vdev);
} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t fd = *(int32_t *)data;
if (fd >= 0)
return vfio_virqfd_enable((void *) vdev,
vfio_pci_intx_unmask_handler,
vfio_send_intx_eventfd, NULL,
&vdev->ctx[0].unmask, fd);
vfio_virqfd_disable(&vdev->ctx[0].unmask);
}
return 0;
}
static int vfio_pci_set_intx_mask(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
if (!is_intx(vdev) || start != 0 || count != 1)
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_NONE) {
vfio_pci_intx_mask(vdev);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t mask = *(uint8_t *)data;
if (mask)
vfio_pci_intx_mask(vdev);
} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
return -ENOTTY; /* XXX implement me */
}
return 0;
}
static int vfio_pci_set_intx_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
if (is_intx(vdev) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
vfio_intx_disable(vdev);
return 0;
}
if (!(is_intx(vdev) || is_irq_none(vdev)) || start != 0 || count != 1)
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t fd = *(int32_t *)data;
int ret;
if (is_intx(vdev))
return vfio_intx_set_signal(vdev, fd);
ret = vfio_intx_enable(vdev);
if (ret)
return ret;
ret = vfio_intx_set_signal(vdev, fd);
if (ret)
vfio_intx_disable(vdev);
return ret;
}
if (!is_intx(vdev))
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_NONE) {
vfio_send_intx_eventfd(vdev, NULL);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t trigger = *(uint8_t *)data;
if (trigger)
vfio_send_intx_eventfd(vdev, NULL);
}
return 0;
}
static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
int i;
bool msix = (index == VFIO_PCI_MSIX_IRQ_INDEX) ? true : false;
if (irq_is(vdev, index) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
vfio_msi_disable(vdev, msix);
return 0;
}
if (!(irq_is(vdev, index) || is_irq_none(vdev)))
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t *fds = data;
int ret;
if (vdev->irq_type == index)
return vfio_msi_set_block(vdev, start, count,
fds, msix);
ret = vfio_msi_enable(vdev, start + count, msix);
if (ret)
return ret;
ret = vfio_msi_set_block(vdev, start, count, fds, msix);
if (ret)
vfio_msi_disable(vdev, msix);
return ret;
}
if (!irq_is(vdev, index) || start + count > vdev->num_ctx)
return -EINVAL;
for (i = start; i < start + count; i++) {
if (!vdev->ctx[i].trigger)
continue;
if (flags & VFIO_IRQ_SET_DATA_NONE) {
eventfd_signal(vdev->ctx[i].trigger, 1);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t *bools = data;
if (bools[i - start])
eventfd_signal(vdev->ctx[i].trigger, 1);
}
}
return 0;
}
static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
unsigned int count, uint32_t flags,
void *data)
{
/* DATA_NONE/DATA_BOOL enables loopback testing */
if (flags & VFIO_IRQ_SET_DATA_NONE) {
if (*ctx) {
if (count) {
eventfd_signal(*ctx, 1);
} else {
eventfd_ctx_put(*ctx);
*ctx = NULL;
}
return 0;
}
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t trigger;
if (!count)
return -EINVAL;
trigger = *(uint8_t *)data;
if (trigger && *ctx)
eventfd_signal(*ctx, 1);
return 0;
} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t fd;
if (!count)
return -EINVAL;
fd = *(int32_t *)data;
if (fd == -1) {
if (*ctx)
eventfd_ctx_put(*ctx);
*ctx = NULL;
} else if (fd >= 0) {
struct eventfd_ctx *efdctx;
efdctx = eventfd_ctx_fdget(fd);
if (IS_ERR(efdctx))
return PTR_ERR(efdctx);
if (*ctx)
eventfd_ctx_put(*ctx);
*ctx = efdctx;
}
return 0;
}
return -EINVAL;
}
static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1)
return -EINVAL;
return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger,
count, flags, data);
}
static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1)
return -EINVAL;
return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger,
count, flags, data);
}
int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
unsigned index, unsigned start, unsigned count,
void *data)
{
int (*func)(struct vfio_pci_device *vdev, unsigned index,
unsigned start, unsigned count, uint32_t flags,
void *data) = NULL;
switch (index) {
case VFIO_PCI_INTX_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_MASK:
func = vfio_pci_set_intx_mask;
break;
case VFIO_IRQ_SET_ACTION_UNMASK:
func = vfio_pci_set_intx_unmask;
break;
case VFIO_IRQ_SET_ACTION_TRIGGER:
func = vfio_pci_set_intx_trigger;
break;
}
break;
case VFIO_PCI_MSI_IRQ_INDEX:
case VFIO_PCI_MSIX_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_MASK:
case VFIO_IRQ_SET_ACTION_UNMASK:
/* XXX Need masking support exported */
break;
case VFIO_IRQ_SET_ACTION_TRIGGER:
func = vfio_pci_set_msi_trigger;
break;
}
break;
case VFIO_PCI_ERR_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_TRIGGER:
if (pci_is_pcie(vdev->pdev))
func = vfio_pci_set_err_trigger;
break;
}
break;
case VFIO_PCI_REQ_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_TRIGGER:
func = vfio_pci_set_req_trigger;
break;
}
break;
}
if (!func)
return -ENOTTY;
return func(vdev, index, start, count, flags, data);
}
+176
View File
@@ -0,0 +1,176 @@
/*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.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.
*
* Derived from original vfio:
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
* Author: Tom Lyon, pugs@cisco.com
*/
#include <linux/mutex.h>
#include <linux/pci.h>
#include <linux/irqbypass.h>
#include <linux/types.h>
#ifndef VFIO_PCI_PRIVATE_H
#define VFIO_PCI_PRIVATE_H
#define VFIO_PCI_OFFSET_SHIFT 40
#define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT)
#define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT)
#define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1)
/* Special capability IDs predefined access */
#define PCI_CAP_ID_INVALID 0xFF /* default raw access */
#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */
/* Cap maximum number of ioeventfds per device (arbitrary) */
#define VFIO_PCI_IOEVENTFD_MAX 1000
struct vfio_pci_ioeventfd {
struct list_head next;
struct virqfd *virqfd;
void __iomem *addr;
uint64_t data;
loff_t pos;
int bar;
int count;
};
struct vfio_pci_irq_ctx {
struct eventfd_ctx *trigger;
struct virqfd *unmask;
struct virqfd *mask;
char *name;
bool masked;
struct irq_bypass_producer producer;
};
struct vfio_pci_device;
struct vfio_pci_region;
struct vfio_pci_regops {
size_t (*rw)(struct vfio_pci_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite);
void (*release)(struct vfio_pci_device *vdev,
struct vfio_pci_region *region);
};
struct vfio_pci_region {
u32 type;
u32 subtype;
const struct vfio_pci_regops *ops;
void *data;
size_t size;
u32 flags;
};
struct vfio_pci_dummy_resource {
struct resource resource;
int index;
struct list_head res_next;
};
struct vfio_pci_mmap_vma {
struct vm_area_struct *vma;
struct list_head vma_next;
};
struct vfio_pci_device {
struct pci_dev *pdev;
void __iomem *barmap[PCI_STD_RESOURCE_END + 1];
bool bar_mmap_supported[PCI_STD_RESOURCE_END + 1];
u8 *pci_config_map;
u8 *vconfig;
struct perm_bits *msi_perm;
spinlock_t irqlock;
struct mutex igate;
struct vfio_pci_irq_ctx *ctx;
int num_ctx;
int irq_type;
int num_regions;
struct vfio_pci_region *region;
u8 msi_qmax;
u8 msix_bar;
u16 msix_size;
u32 msix_offset;
u32 rbar[7];
bool pci_2_3;
bool virq_disabled;
bool reset_works;
bool extended_caps;
bool bardirty;
bool has_vga;
bool needs_reset;
bool nointx;
struct pci_saved_state *pci_saved_state;
int refcnt;
int ioeventfds_nr;
struct eventfd_ctx *err_trigger;
struct eventfd_ctx *req_trigger;
struct list_head dummy_resources_list;
struct mutex ioeventfds_lock;
struct list_head ioeventfds_list;
struct mutex vma_lock;
struct list_head vma_list;
struct rw_semaphore memory_lock;
};
#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX)
#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX)
#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev)))
#define irq_is(vdev, type) (vdev->irq_type == type)
extern void vfio_pci_intx_mask(struct vfio_pci_device *vdev);
extern void vfio_pci_intx_unmask(struct vfio_pci_device *vdev);
extern int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev,
uint32_t flags, unsigned index,
unsigned start, unsigned count, void *data);
extern ssize_t vfio_pci_config_rw(struct vfio_pci_device *vdev,
char __user *buf, size_t count,
loff_t *ppos, bool iswrite);
extern ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite);
extern ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite);
extern long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
uint64_t data, int count, int fd);
extern int vfio_pci_init_perm_bits(void);
extern void vfio_pci_uninit_perm_bits(void);
extern int vfio_config_init(struct vfio_pci_device *vdev);
extern void vfio_config_free(struct vfio_pci_device *vdev);
extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
unsigned int type, unsigned int subtype,
const struct vfio_pci_regops *ops,
size_t size, u32 flags, void *data);
extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev);
extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device
*vdev);
extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev);
extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev,
u16 cmd);
#ifdef CONFIG_VFIO_PCI_IGD
extern int vfio_pci_igd_init(struct vfio_pci_device *vdev);
#else
static inline int vfio_pci_igd_init(struct vfio_pci_device *vdev)
{
return -ENODEV;
}
#endif
#endif /* VFIO_PCI_PRIVATE_H */
+404
View File
@@ -0,0 +1,404 @@
/*
* VFIO PCI I/O Port & MMIO access
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.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.
*
* Derived from original vfio:
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
* Author: Tom Lyon, pugs@cisco.com
*/
#include <linux/fs.h>
#include <linux/pci.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/vfio.h>
#include <linux/vgaarb.h>
#include "vfio_pci_private.h"
#ifdef __LITTLE_ENDIAN
#define vfio_ioread64 ioread64
#define vfio_iowrite64 iowrite64
#define vfio_ioread32 ioread32
#define vfio_iowrite32 iowrite32
#define vfio_ioread16 ioread16
#define vfio_iowrite16 iowrite16
#else
#define vfio_ioread64 ioread64be
#define vfio_iowrite64 iowrite64be
#define vfio_ioread32 ioread32be
#define vfio_iowrite32 iowrite32be
#define vfio_ioread16 ioread16be
#define vfio_iowrite16 iowrite16be
#endif
#define vfio_ioread8 ioread8
#define vfio_iowrite8 iowrite8
/*
* Read or write from an __iomem region (MMIO or I/O port) with an excluded
* range which is inaccessible. The excluded range drops writes and fills
* reads with -1. This is intended for handling MSI-X vector tables and
* leftover space for ROM BARs.
*/
static ssize_t do_io_rw(void __iomem *io, char __user *buf,
loff_t off, size_t count, size_t x_start,
size_t x_end, bool iswrite)
{
ssize_t done = 0;
while (count) {
size_t fillable, filled;
if (off < x_start)
fillable = min(count, (size_t)(x_start - off));
else if (off >= x_end)
fillable = count;
else
fillable = 0;
if (fillable >= 4 && !(off % 4)) {
u32 val;
if (iswrite) {
if (copy_from_user(&val, buf, 4))
return -EFAULT;
vfio_iowrite32(val, io + off);
} else {
val = vfio_ioread32(io + off);
if (copy_to_user(buf, &val, 4))
return -EFAULT;
}
filled = 4;
} else if (fillable >= 2 && !(off % 2)) {
u16 val;
if (iswrite) {
if (copy_from_user(&val, buf, 2))
return -EFAULT;
vfio_iowrite16(val, io + off);
} else {
val = vfio_ioread16(io + off);
if (copy_to_user(buf, &val, 2))
return -EFAULT;
}
filled = 2;
} else if (fillable) {
u8 val;
if (iswrite) {
if (copy_from_user(&val, buf, 1))
return -EFAULT;
vfio_iowrite8(val, io + off);
} else {
val = vfio_ioread8(io + off);
if (copy_to_user(buf, &val, 1))
return -EFAULT;
}
filled = 1;
} else {
/* Fill reads with -1, drop writes */
filled = min(count, (size_t)(x_end - off));
if (!iswrite) {
u8 val = 0xFF;
size_t i;
for (i = 0; i < filled; i++)
if (copy_to_user(buf + i, &val, 1))
return -EFAULT;
}
}
count -= filled;
done += filled;
off += filled;
buf += filled;
}
return done;
}
static int vfio_pci_setup_barmap(struct vfio_pci_device *vdev, int bar)
{
struct pci_dev *pdev = vdev->pdev;
int ret;
void __iomem *io;
if (vdev->barmap[bar])
return 0;
ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
if (ret)
return ret;
io = pci_iomap(pdev, bar, 0);
if (!io) {
pci_release_selected_regions(pdev, 1 << bar);
return -ENOMEM;
}
vdev->barmap[bar] = io;
return 0;
}
ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite)
{
struct pci_dev *pdev = vdev->pdev;
loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
int bar = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
size_t x_start = 0, x_end = 0;
resource_size_t end;
void __iomem *io;
struct resource *res = &vdev->pdev->resource[bar];
ssize_t done;
if (pci_resource_start(pdev, bar))
end = pci_resource_len(pdev, bar);
else if (bar == PCI_ROM_RESOURCE &&
pdev->resource[bar].flags & IORESOURCE_ROM_SHADOW)
end = 0x20000;
else
return -EINVAL;
if (pos >= end)
return -EINVAL;
count = min(count, (size_t)(end - pos));
if (res->flags & IORESOURCE_MEM) {
down_read(&vdev->memory_lock);
if (!__vfio_pci_memory_enabled(vdev)) {
up_read(&vdev->memory_lock);
return -EIO;
}
}
if (bar == PCI_ROM_RESOURCE) {
/*
* The ROM can fill less space than the BAR, so we start the
* excluded range at the end of the actual ROM. This makes
* filling large ROM BARs much faster.
*/
io = pci_map_rom(pdev, &x_start);
if (!io) {
done = -ENOMEM;
goto out;
}
x_end = end;
} else {
int ret = vfio_pci_setup_barmap(vdev, bar);
if (ret) {
done = ret;
goto out;
}
io = vdev->barmap[bar];
}
if (bar == vdev->msix_bar) {
x_start = vdev->msix_offset;
x_end = vdev->msix_offset + vdev->msix_size;
}
done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite);
if (done >= 0)
*ppos += done;
if (bar == PCI_ROM_RESOURCE)
pci_unmap_rom(pdev, io);
out:
if (res->flags & IORESOURCE_MEM)
up_read(&vdev->memory_lock);
return done;
}
ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite)
{
int ret;
loff_t off, pos = *ppos & VFIO_PCI_OFFSET_MASK;
void __iomem *iomem = NULL;
unsigned int rsrc;
bool is_ioport;
ssize_t done;
if (!vdev->has_vga)
return -EINVAL;
if (pos > 0xbfffful)
return -EINVAL;
switch ((u32)pos) {
case 0xa0000 ... 0xbffff:
count = min(count, (size_t)(0xc0000 - pos));
iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1);
off = pos - 0xa0000;
rsrc = VGA_RSRC_LEGACY_MEM;
is_ioport = false;
break;
case 0x3b0 ... 0x3bb:
count = min(count, (size_t)(0x3bc - pos));
iomem = ioport_map(0x3b0, 0x3bb - 0x3b0 + 1);
off = pos - 0x3b0;
rsrc = VGA_RSRC_LEGACY_IO;
is_ioport = true;
break;
case 0x3c0 ... 0x3df:
count = min(count, (size_t)(0x3e0 - pos));
iomem = ioport_map(0x3c0, 0x3df - 0x3c0 + 1);
off = pos - 0x3c0;
rsrc = VGA_RSRC_LEGACY_IO;
is_ioport = true;
break;
default:
return -EINVAL;
}
if (!iomem)
return -ENOMEM;
ret = vga_get_interruptible(vdev->pdev, rsrc);
if (ret) {
is_ioport ? ioport_unmap(iomem) : iounmap(iomem);
return ret;
}
done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite);
vga_put(vdev->pdev, rsrc);
is_ioport ? ioport_unmap(iomem) : iounmap(iomem);
if (done >= 0)
*ppos += done;
return done;
}
static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
{
struct vfio_pci_ioeventfd *ioeventfd = opaque;
switch (ioeventfd->count) {
case 1:
vfio_iowrite8(ioeventfd->data, ioeventfd->addr);
break;
case 2:
vfio_iowrite16(ioeventfd->data, ioeventfd->addr);
break;
case 4:
vfio_iowrite32(ioeventfd->data, ioeventfd->addr);
break;
#ifdef iowrite64
case 8:
vfio_iowrite64(ioeventfd->data, ioeventfd->addr);
break;
#endif
}
return 0;
}
long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
uint64_t data, int count, int fd)
{
struct pci_dev *pdev = vdev->pdev;
loff_t pos = offset & VFIO_PCI_OFFSET_MASK;
int ret, bar = VFIO_PCI_OFFSET_TO_INDEX(offset);
struct vfio_pci_ioeventfd *ioeventfd;
/* Only support ioeventfds into BARs */
if (bar > VFIO_PCI_BAR5_REGION_INDEX)
return -EINVAL;
if (pos + count > pci_resource_len(pdev, bar))
return -EINVAL;
/* Disallow ioeventfds working around MSI-X table writes */
if (bar == vdev->msix_bar &&
!(pos + count <= vdev->msix_offset ||
pos >= vdev->msix_offset + vdev->msix_size))
return -EINVAL;
#ifndef iowrite64
if (count == 8)
return -EINVAL;
#endif
ret = vfio_pci_setup_barmap(vdev, bar);
if (ret)
return ret;
mutex_lock(&vdev->ioeventfds_lock);
list_for_each_entry(ioeventfd, &vdev->ioeventfds_list, next) {
if (ioeventfd->pos == pos && ioeventfd->bar == bar &&
ioeventfd->data == data && ioeventfd->count == count) {
if (fd == -1) {
vfio_virqfd_disable(&ioeventfd->virqfd);
list_del(&ioeventfd->next);
vdev->ioeventfds_nr--;
kfree(ioeventfd);
ret = 0;
} else
ret = -EEXIST;
goto out_unlock;
}
}
if (fd < 0) {
ret = -ENODEV;
goto out_unlock;
}
if (vdev->ioeventfds_nr >= VFIO_PCI_IOEVENTFD_MAX) {
ret = -ENOSPC;
goto out_unlock;
}
ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL);
if (!ioeventfd) {
ret = -ENOMEM;
goto out_unlock;
}
ioeventfd->addr = vdev->barmap[bar] + pos;
ioeventfd->data = data;
ioeventfd->pos = pos;
ioeventfd->bar = bar;
ioeventfd->count = count;
ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
NULL, NULL, &ioeventfd->virqfd, fd);
if (ret) {
kfree(ioeventfd);
goto out_unlock;
}
list_add(&ioeventfd->next, &vdev->ioeventfds_list);
vdev->ioeventfds_nr++;
out_unlock:
mutex_unlock(&vdev->ioeventfds_lock);
return ret;
}
+22
View File
@@ -0,0 +1,22 @@
config VFIO_PLATFORM
tristate "VFIO support for platform devices"
depends on VFIO && EVENTFD && (ARM || ARM64)
select VFIO_VIRQFD
help
Support for platform devices with VFIO. This is required to make
use of platform devices present on the system using the VFIO
framework.
If you don't know what to do here, say N.
config VFIO_AMBA
tristate "VFIO support for AMBA devices"
depends on VFIO_PLATFORM && ARM_AMBA
help
Support for ARM AMBA devices with VFIO. This is required to make
use of ARM AMBA devices present on the system using the VFIO
framework.
If you don't know what to do here, say N.
source "drivers/vfio/platform/reset/Kconfig"
+13
View File
@@ -0,0 +1,13 @@
# SPDX-License-Identifier: GPL-2.0
vfio-platform-base-y := vfio_platform_common.o vfio_platform_irq.o
vfio-platform-y := vfio_platform.o
obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform.o
obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform-base.o
obj-$(CONFIG_VFIO_PLATFORM) += reset/
vfio-amba-y := vfio_amba.o
obj-$(CONFIG_VFIO_AMBA) += vfio-amba.o
obj-$(CONFIG_VFIO_AMBA) += vfio-platform-base.o
obj-$(CONFIG_VFIO_AMBA) += reset/
+24
View File
@@ -0,0 +1,24 @@
config VFIO_PLATFORM_CALXEDAXGMAC_RESET
tristate "VFIO support for calxeda xgmac reset"
depends on VFIO_PLATFORM
help
Enables the VFIO platform driver to handle reset for Calxeda xgmac
If you don't know what to do here, say N.
config VFIO_PLATFORM_AMDXGBE_RESET
tristate "VFIO support for AMD XGBE reset"
depends on VFIO_PLATFORM
help
Enables the VFIO platform driver to handle reset for AMD XGBE
If you don't know what to do here, say N.
config VFIO_PLATFORM_BCMFLEXRM_RESET
tristate "VFIO support for Broadcom FlexRM reset"
depends on VFIO_PLATFORM && (ARCH_BCM_IPROC || COMPILE_TEST)
default ARCH_BCM_IPROC
help
Enables the VFIO platform driver to handle reset for Broadcom FlexRM
If you don't know what to do here, say N.
+9
View File
@@ -0,0 +1,9 @@
# SPDX-License-Identifier: GPL-2.0
vfio-platform-calxedaxgmac-y := vfio_platform_calxedaxgmac.o
vfio-platform-amdxgbe-y := vfio_platform_amdxgbe.o
ccflags-y += -Idrivers/vfio/platform
obj-$(CONFIG_VFIO_PLATFORM_CALXEDAXGMAC_RESET) += vfio-platform-calxedaxgmac.o
obj-$(CONFIG_VFIO_PLATFORM_AMDXGBE_RESET) += vfio-platform-amdxgbe.o
obj-$(CONFIG_VFIO_PLATFORM_BCMFLEXRM_RESET) += vfio_platform_bcmflexrm.o
@@ -0,0 +1,127 @@
/*
* VFIO platform driver specialized for AMD xgbe reset
* reset code is inherited from AMD xgbe native driver
*
* Copyright (c) 2015 Linaro Ltd.
* www.linaro.org
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/io.h>
#include <uapi/linux/mdio.h>
#include <linux/delay.h>
#include "vfio_platform_private.h"
#define DMA_MR 0x3000
#define MAC_VR 0x0110
#define DMA_ISR 0x3008
#define MAC_ISR 0x00b0
#define PCS_MMD_SELECT 0xff
#define MDIO_AN_INT 0x8002
#define MDIO_AN_INTMASK 0x8001
static unsigned int xmdio_read(void *ioaddr, unsigned int mmd,
unsigned int reg)
{
unsigned int mmd_address, value;
mmd_address = (mmd << 16) | ((reg) & 0xffff);
iowrite32(mmd_address >> 8, ioaddr + (PCS_MMD_SELECT << 2));
value = ioread32(ioaddr + ((mmd_address & 0xff) << 2));
return value;
}
static void xmdio_write(void *ioaddr, unsigned int mmd,
unsigned int reg, unsigned int value)
{
unsigned int mmd_address;
mmd_address = (mmd << 16) | ((reg) & 0xffff);
iowrite32(mmd_address >> 8, ioaddr + (PCS_MMD_SELECT << 2));
iowrite32(value, ioaddr + ((mmd_address & 0xff) << 2));
}
static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
{
struct vfio_platform_region *xgmac_regs = &vdev->regions[0];
struct vfio_platform_region *xpcs_regs = &vdev->regions[1];
u32 dma_mr_value, pcs_value, value;
unsigned int count;
if (!xgmac_regs->ioaddr) {
xgmac_regs->ioaddr =
ioremap_nocache(xgmac_regs->addr, xgmac_regs->size);
if (!xgmac_regs->ioaddr)
return -ENOMEM;
}
if (!xpcs_regs->ioaddr) {
xpcs_regs->ioaddr =
ioremap_nocache(xpcs_regs->addr, xpcs_regs->size);
if (!xpcs_regs->ioaddr)
return -ENOMEM;
}
/* reset the PHY through MDIO*/
pcs_value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_PCS, MDIO_CTRL1);
pcs_value |= MDIO_CTRL1_RESET;
xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_PCS, MDIO_CTRL1, pcs_value);
count = 50;
do {
msleep(20);
pcs_value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_PCS,
MDIO_CTRL1);
} while ((pcs_value & MDIO_CTRL1_RESET) && --count);
if (pcs_value & MDIO_CTRL1_RESET)
pr_warn("%s XGBE PHY reset timeout\n", __func__);
/* disable auto-negotiation */
value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1);
value &= ~MDIO_AN_CTRL1_ENABLE;
xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1, value);
/* disable AN IRQ */
xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
/* clear AN IRQ */
xmdio_write(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_AN_INT, 0);
/* MAC software reset */
dma_mr_value = ioread32(xgmac_regs->ioaddr + DMA_MR);
dma_mr_value |= 0x1;
iowrite32(dma_mr_value, xgmac_regs->ioaddr + DMA_MR);
usleep_range(10, 15);
count = 2000;
while (--count && (ioread32(xgmac_regs->ioaddr + DMA_MR) & 1))
usleep_range(500, 600);
if (!count)
pr_warn("%s MAC SW reset failed\n", __func__);
return 0;
}
module_vfio_reset_handler("amd,xgbe-seattle-v1a", vfio_platform_amdxgbe_reset);
MODULE_VERSION("0.1");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Eric Auger <eric.auger@linaro.org>");
MODULE_DESCRIPTION("Reset support for AMD xgbe vfio platform device");
@@ -0,0 +1,113 @@
/*
* Copyright (C) 2017 Broadcom
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation version 2.
*
* This program is distributed "as is" WITHOUT ANY WARRANTY of any
* kind, whether express or implied; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
/*
* This driver provides reset support for Broadcom FlexRM ring manager
* to VFIO platform.
*/
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include "vfio_platform_private.h"
/* FlexRM configuration */
#define RING_REGS_SIZE 0x10000
#define RING_VER_MAGIC 0x76303031
/* Per-Ring register offsets */
#define RING_VER 0x000
#define RING_CONTROL 0x034
#define RING_FLUSH_DONE 0x038
/* Register RING_CONTROL fields */
#define CONTROL_FLUSH_SHIFT 5
/* Register RING_FLUSH_DONE fields */
#define FLUSH_DONE_MASK 0x1
static int vfio_platform_bcmflexrm_shutdown(void __iomem *ring)
{
unsigned int timeout;
/* Disable/inactivate ring */
writel_relaxed(0x0, ring + RING_CONTROL);
/* Set ring flush state */
timeout = 1000; /* timeout of 1s */
writel_relaxed(BIT(CONTROL_FLUSH_SHIFT), ring + RING_CONTROL);
do {
if (readl_relaxed(ring + RING_FLUSH_DONE) &
FLUSH_DONE_MASK)
break;
mdelay(1);
} while (--timeout);
if (!timeout)
return -ETIMEDOUT;
/* Clear ring flush state */
timeout = 1000; /* timeout of 1s */
writel_relaxed(0x0, ring + RING_CONTROL);
do {
if (!(readl_relaxed(ring + RING_FLUSH_DONE) &
FLUSH_DONE_MASK))
break;
mdelay(1);
} while (--timeout);
if (!timeout)
return -ETIMEDOUT;
return 0;
}
static int vfio_platform_bcmflexrm_reset(struct vfio_platform_device *vdev)
{
void __iomem *ring;
int rc = 0, ret = 0, ring_num = 0;
struct vfio_platform_region *reg = &vdev->regions[0];
/* Map FlexRM ring registers if not mapped */
if (!reg->ioaddr) {
reg->ioaddr = ioremap_nocache(reg->addr, reg->size);
if (!reg->ioaddr)
return -ENOMEM;
}
/* Discover and shutdown each FlexRM ring */
for (ring = reg->ioaddr;
ring < (reg->ioaddr + reg->size); ring += RING_REGS_SIZE) {
if (readl_relaxed(ring + RING_VER) == RING_VER_MAGIC) {
rc = vfio_platform_bcmflexrm_shutdown(ring);
if (rc) {
dev_warn(vdev->device,
"FlexRM ring%d shutdown error %d\n",
ring_num, rc);
ret |= rc;
}
ring_num++;
}
}
return ret;
}
module_vfio_reset_handler("brcm,iproc-flexrm-mbox",
vfio_platform_bcmflexrm_reset);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Anup Patel <anup.patel@broadcom.com>");
MODULE_DESCRIPTION("Reset support for Broadcom FlexRM VFIO platform device");
@@ -0,0 +1,85 @@
/*
* VFIO platform driver specialized for Calxeda xgmac reset
* reset code is inherited from calxeda xgmac native driver
*
* Copyright 2010-2011 Calxeda, Inc.
* Copyright (c) 2015 Linaro Ltd.
* www.linaro.org
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/io.h>
#include "vfio_platform_private.h"
#define DRIVER_VERSION "0.1"
#define DRIVER_AUTHOR "Eric Auger <eric.auger@linaro.org>"
#define DRIVER_DESC "Reset support for Calxeda xgmac vfio platform device"
/* XGMAC Register definitions */
#define XGMAC_CONTROL 0x00000000 /* MAC Configuration */
/* DMA Control and Status Registers */
#define XGMAC_DMA_CONTROL 0x00000f18 /* Ctrl (Operational Mode) */
#define XGMAC_DMA_INTR_ENA 0x00000f1c /* Interrupt Enable */
/* DMA Control registe defines */
#define DMA_CONTROL_ST 0x00002000 /* Start/Stop Transmission */
#define DMA_CONTROL_SR 0x00000002 /* Start/Stop Receive */
/* Common MAC defines */
#define MAC_ENABLE_TX 0x00000008 /* Transmitter Enable */
#define MAC_ENABLE_RX 0x00000004 /* Receiver Enable */
static inline void xgmac_mac_disable(void __iomem *ioaddr)
{
u32 value = readl(ioaddr + XGMAC_DMA_CONTROL);
value &= ~(DMA_CONTROL_ST | DMA_CONTROL_SR);
writel(value, ioaddr + XGMAC_DMA_CONTROL);
value = readl(ioaddr + XGMAC_CONTROL);
value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
writel(value, ioaddr + XGMAC_CONTROL);
}
static int vfio_platform_calxedaxgmac_reset(struct vfio_platform_device *vdev)
{
struct vfio_platform_region *reg = &vdev->regions[0];
if (!reg->ioaddr) {
reg->ioaddr =
ioremap_nocache(reg->addr, reg->size);
if (!reg->ioaddr)
return -ENOMEM;
}
/* disable IRQ */
writel(0, reg->ioaddr + XGMAC_DMA_INTR_ENA);
/* Disable the MAC core */
xgmac_mac_disable(reg->ioaddr);
return 0;
}
module_vfio_reset_handler("calxeda,hb-xgmac", vfio_platform_calxedaxgmac_reset);
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
+117
View File
@@ -0,0 +1,117 @@
/*
* Copyright (C) 2013 - Virtual Open Systems
* Author: Antonios Motakis <a.motakis@virtualopensystems.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/vfio.h>
#include <linux/amba/bus.h>
#include "vfio_platform_private.h"
#define DRIVER_VERSION "0.10"
#define DRIVER_AUTHOR "Antonios Motakis <a.motakis@virtualopensystems.com>"
#define DRIVER_DESC "VFIO for AMBA devices - User Level meta-driver"
/* probing devices from the AMBA bus */
static struct resource *get_amba_resource(struct vfio_platform_device *vdev,
int i)
{
struct amba_device *adev = (struct amba_device *) vdev->opaque;
if (i == 0)
return &adev->res;
return NULL;
}
static int get_amba_irq(struct vfio_platform_device *vdev, int i)
{
struct amba_device *adev = (struct amba_device *) vdev->opaque;
int ret = 0;
if (i < AMBA_NR_IRQS)
ret = adev->irq[i];
/* zero is an unset IRQ for AMBA devices */
return ret ? ret : -ENXIO;
}
static int vfio_amba_probe(struct amba_device *adev, const struct amba_id *id)
{
struct vfio_platform_device *vdev;
int ret;
vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
if (!vdev)
return -ENOMEM;
vdev->name = kasprintf(GFP_KERNEL, "vfio-amba-%08x", adev->periphid);
if (!vdev->name) {
kfree(vdev);
return -ENOMEM;
}
vdev->opaque = (void *) adev;
vdev->flags = VFIO_DEVICE_FLAGS_AMBA;
vdev->get_resource = get_amba_resource;
vdev->get_irq = get_amba_irq;
vdev->parent_module = THIS_MODULE;
vdev->reset_required = false;
ret = vfio_platform_probe_common(vdev, &adev->dev);
if (ret) {
kfree(vdev->name);
kfree(vdev);
}
return ret;
}
static int vfio_amba_remove(struct amba_device *adev)
{
struct vfio_platform_device *vdev;
vdev = vfio_platform_remove_common(&adev->dev);
if (vdev) {
kfree(vdev->name);
kfree(vdev);
return 0;
}
return -EINVAL;
}
static const struct amba_id pl330_ids[] = {
{ 0, 0 },
};
MODULE_DEVICE_TABLE(amba, pl330_ids);
static struct amba_driver vfio_amba_driver = {
.probe = vfio_amba_probe,
.remove = vfio_amba_remove,
.id_table = pl330_ids,
.drv = {
.name = "vfio-amba",
.owner = THIS_MODULE,
},
};
module_amba_driver(vfio_amba_driver);
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
+108
View File
@@ -0,0 +1,108 @@
/*
* Copyright (C) 2013 - Virtual Open Systems
* Author: Antonios Motakis <a.motakis@virtualopensystems.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/vfio.h>
#include <linux/platform_device.h>
#include "vfio_platform_private.h"
#define DRIVER_VERSION "0.10"
#define DRIVER_AUTHOR "Antonios Motakis <a.motakis@virtualopensystems.com>"
#define DRIVER_DESC "VFIO for platform devices - User Level meta-driver"
static bool reset_required = true;
module_param(reset_required, bool, 0444);
MODULE_PARM_DESC(reset_required, "override reset requirement (default: 1)");
/* probing devices from the linux platform bus */
static struct resource *get_platform_resource(struct vfio_platform_device *vdev,
int num)
{
struct platform_device *dev = (struct platform_device *) vdev->opaque;
int i;
for (i = 0; i < dev->num_resources; i++) {
struct resource *r = &dev->resource[i];
if (resource_type(r) & (IORESOURCE_MEM|IORESOURCE_IO)) {
if (!num)
return r;
num--;
}
}
return NULL;
}
static int get_platform_irq(struct vfio_platform_device *vdev, int i)
{
struct platform_device *pdev = (struct platform_device *) vdev->opaque;
return platform_get_irq(pdev, i);
}
static int vfio_platform_probe(struct platform_device *pdev)
{
struct vfio_platform_device *vdev;
int ret;
vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
if (!vdev)
return -ENOMEM;
vdev->opaque = (void *) pdev;
vdev->name = pdev->name;
vdev->flags = VFIO_DEVICE_FLAGS_PLATFORM;
vdev->get_resource = get_platform_resource;
vdev->get_irq = get_platform_irq;
vdev->parent_module = THIS_MODULE;
vdev->reset_required = reset_required;
ret = vfio_platform_probe_common(vdev, &pdev->dev);
if (ret)
kfree(vdev);
return ret;
}
static int vfio_platform_remove(struct platform_device *pdev)
{
struct vfio_platform_device *vdev;
vdev = vfio_platform_remove_common(&pdev->dev);
if (vdev) {
kfree(vdev);
return 0;
}
return -EINVAL;
}
static struct platform_driver vfio_platform_driver = {
.probe = vfio_platform_probe,
.remove = vfio_platform_remove,
.driver = {
.name = "vfio-platform",
},
};
module_platform_driver(vfio_platform_driver);
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
@@ -0,0 +1,756 @@
/*
* Copyright (C) 2013 - Virtual Open Systems
* Author: Antonios Motakis <a.motakis@virtualopensystems.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/device.h>
#include <linux/acpi.h>
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include "vfio_platform_private.h"
#define DRIVER_VERSION "0.10"
#define DRIVER_AUTHOR "Antonios Motakis <a.motakis@virtualopensystems.com>"
#define DRIVER_DESC "VFIO platform base module"
#define VFIO_PLATFORM_IS_ACPI(vdev) ((vdev)->acpihid != NULL)
static LIST_HEAD(reset_list);
static DEFINE_MUTEX(driver_lock);
static vfio_platform_reset_fn_t vfio_platform_lookup_reset(const char *compat,
struct module **module)
{
struct vfio_platform_reset_node *iter;
vfio_platform_reset_fn_t reset_fn = NULL;
mutex_lock(&driver_lock);
list_for_each_entry(iter, &reset_list, link) {
if (!strcmp(iter->compat, compat) &&
try_module_get(iter->owner)) {
*module = iter->owner;
reset_fn = iter->of_reset;
break;
}
}
mutex_unlock(&driver_lock);
return reset_fn;
}
static int vfio_platform_acpi_probe(struct vfio_platform_device *vdev,
struct device *dev)
{
struct acpi_device *adev;
if (acpi_disabled)
return -ENOENT;
adev = ACPI_COMPANION(dev);
if (!adev) {
pr_err("VFIO: ACPI companion device not found for %s\n",
vdev->name);
return -ENODEV;
}
#ifdef CONFIG_ACPI
vdev->acpihid = acpi_device_hid(adev);
#endif
return WARN_ON(!vdev->acpihid) ? -EINVAL : 0;
}
static int vfio_platform_acpi_call_reset(struct vfio_platform_device *vdev,
const char **extra_dbg)
{
#ifdef CONFIG_ACPI
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
struct device *dev = vdev->device;
acpi_handle handle = ACPI_HANDLE(dev);
acpi_status acpi_ret;
acpi_ret = acpi_evaluate_object(handle, "_RST", NULL, &buffer);
if (ACPI_FAILURE(acpi_ret)) {
if (extra_dbg)
*extra_dbg = acpi_format_exception(acpi_ret);
return -EINVAL;
}
return 0;
#else
return -ENOENT;
#endif
}
static bool vfio_platform_acpi_has_reset(struct vfio_platform_device *vdev)
{
#ifdef CONFIG_ACPI
struct device *dev = vdev->device;
acpi_handle handle = ACPI_HANDLE(dev);
return acpi_has_method(handle, "_RST");
#else
return false;
#endif
}
static bool vfio_platform_has_reset(struct vfio_platform_device *vdev)
{
if (VFIO_PLATFORM_IS_ACPI(vdev))
return vfio_platform_acpi_has_reset(vdev);
return vdev->of_reset ? true : false;
}
static int vfio_platform_get_reset(struct vfio_platform_device *vdev)
{
if (VFIO_PLATFORM_IS_ACPI(vdev))
return vfio_platform_acpi_has_reset(vdev) ? 0 : -ENOENT;
vdev->of_reset = vfio_platform_lookup_reset(vdev->compat,
&vdev->reset_module);
if (!vdev->of_reset) {
request_module("vfio-reset:%s", vdev->compat);
vdev->of_reset = vfio_platform_lookup_reset(vdev->compat,
&vdev->reset_module);
}
return vdev->of_reset ? 0 : -ENOENT;
}
static void vfio_platform_put_reset(struct vfio_platform_device *vdev)
{
if (VFIO_PLATFORM_IS_ACPI(vdev))
return;
if (vdev->of_reset)
module_put(vdev->reset_module);
}
static int vfio_platform_regions_init(struct vfio_platform_device *vdev)
{
int cnt = 0, i;
while (vdev->get_resource(vdev, cnt))
cnt++;
vdev->regions = kcalloc(cnt, sizeof(struct vfio_platform_region),
GFP_KERNEL);
if (!vdev->regions)
return -ENOMEM;
for (i = 0; i < cnt; i++) {
struct resource *res =
vdev->get_resource(vdev, i);
if (!res)
goto err;
vdev->regions[i].addr = res->start;
vdev->regions[i].size = resource_size(res);
vdev->regions[i].flags = 0;
switch (resource_type(res)) {
case IORESOURCE_MEM:
vdev->regions[i].type = VFIO_PLATFORM_REGION_TYPE_MMIO;
vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_READ;
if (!(res->flags & IORESOURCE_READONLY))
vdev->regions[i].flags |=
VFIO_REGION_INFO_FLAG_WRITE;
/*
* Only regions addressed with PAGE granularity may be
* MMAPed securely.
*/
if (!(vdev->regions[i].addr & ~PAGE_MASK) &&
!(vdev->regions[i].size & ~PAGE_MASK))
vdev->regions[i].flags |=
VFIO_REGION_INFO_FLAG_MMAP;
break;
case IORESOURCE_IO:
vdev->regions[i].type = VFIO_PLATFORM_REGION_TYPE_PIO;
break;
default:
goto err;
}
}
vdev->num_regions = cnt;
return 0;
err:
kfree(vdev->regions);
return -EINVAL;
}
static void vfio_platform_regions_cleanup(struct vfio_platform_device *vdev)
{
int i;
for (i = 0; i < vdev->num_regions; i++)
iounmap(vdev->regions[i].ioaddr);
vdev->num_regions = 0;
kfree(vdev->regions);
}
static int vfio_platform_call_reset(struct vfio_platform_device *vdev,
const char **extra_dbg)
{
if (VFIO_PLATFORM_IS_ACPI(vdev)) {
dev_info(vdev->device, "reset\n");
return vfio_platform_acpi_call_reset(vdev, extra_dbg);
} else if (vdev->of_reset) {
dev_info(vdev->device, "reset\n");
return vdev->of_reset(vdev);
}
dev_warn(vdev->device, "no reset function found!\n");
return -EINVAL;
}
static void vfio_platform_release(void *device_data)
{
struct vfio_platform_device *vdev = device_data;
mutex_lock(&driver_lock);
if (!(--vdev->refcnt)) {
const char *extra_dbg = NULL;
int ret;
ret = vfio_platform_call_reset(vdev, &extra_dbg);
if (ret && vdev->reset_required) {
dev_warn(vdev->device, "reset driver is required and reset call failed in release (%d) %s\n",
ret, extra_dbg ? extra_dbg : "");
WARN_ON(1);
}
pm_runtime_put(vdev->device);
vfio_platform_regions_cleanup(vdev);
vfio_platform_irq_cleanup(vdev);
}
mutex_unlock(&driver_lock);
module_put(vdev->parent_module);
}
static int vfio_platform_open(void *device_data)
{
struct vfio_platform_device *vdev = device_data;
int ret;
if (!try_module_get(vdev->parent_module))
return -ENODEV;
mutex_lock(&driver_lock);
if (!vdev->refcnt) {
const char *extra_dbg = NULL;
ret = vfio_platform_regions_init(vdev);
if (ret)
goto err_reg;
ret = vfio_platform_irq_init(vdev);
if (ret)
goto err_irq;
ret = pm_runtime_get_sync(vdev->device);
if (ret < 0)
goto err_rst;
ret = vfio_platform_call_reset(vdev, &extra_dbg);
if (ret && vdev->reset_required) {
dev_warn(vdev->device, "reset driver is required and reset call failed in open (%d) %s\n",
ret, extra_dbg ? extra_dbg : "");
goto err_rst;
}
}
vdev->refcnt++;
mutex_unlock(&driver_lock);
return 0;
err_rst:
pm_runtime_put(vdev->device);
vfio_platform_irq_cleanup(vdev);
err_irq:
vfio_platform_regions_cleanup(vdev);
err_reg:
mutex_unlock(&driver_lock);
module_put(THIS_MODULE);
return ret;
}
static long vfio_platform_ioctl(void *device_data,
unsigned int cmd, unsigned long arg)
{
struct vfio_platform_device *vdev = device_data;
unsigned long minsz;
if (cmd == VFIO_DEVICE_GET_INFO) {
struct vfio_device_info info;
minsz = offsetofend(struct vfio_device_info, num_irqs);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
if (vfio_platform_has_reset(vdev))
vdev->flags |= VFIO_DEVICE_FLAGS_RESET;
info.flags = vdev->flags;
info.num_regions = vdev->num_regions;
info.num_irqs = vdev->num_irqs;
return copy_to_user((void __user *)arg, &info, minsz) ?
-EFAULT : 0;
} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
struct vfio_region_info info;
minsz = offsetofend(struct vfio_region_info, offset);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
if (info.index >= vdev->num_regions)
return -EINVAL;
/* map offset to the physical address */
info.offset = VFIO_PLATFORM_INDEX_TO_OFFSET(info.index);
info.size = vdev->regions[info.index].size;
info.flags = vdev->regions[info.index].flags;
return copy_to_user((void __user *)arg, &info, minsz) ?
-EFAULT : 0;
} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
struct vfio_irq_info info;
minsz = offsetofend(struct vfio_irq_info, count);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
if (info.index >= vdev->num_irqs)
return -EINVAL;
info.flags = vdev->irqs[info.index].flags;
info.count = vdev->irqs[info.index].count;
return copy_to_user((void __user *)arg, &info, minsz) ?
-EFAULT : 0;
} else if (cmd == VFIO_DEVICE_SET_IRQS) {
struct vfio_irq_set hdr;
u8 *data = NULL;
int ret = 0;
size_t data_size = 0;
minsz = offsetofend(struct vfio_irq_set, count);
if (copy_from_user(&hdr, (void __user *)arg, minsz))
return -EFAULT;
ret = vfio_set_irqs_validate_and_prepare(&hdr, vdev->num_irqs,
vdev->num_irqs, &data_size);
if (ret)
return ret;
if (data_size) {
data = memdup_user((void __user *)(arg + minsz),
data_size);
if (IS_ERR(data))
return PTR_ERR(data);
}
mutex_lock(&vdev->igate);
ret = vfio_platform_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
hdr.start, hdr.count, data);
mutex_unlock(&vdev->igate);
kfree(data);
return ret;
} else if (cmd == VFIO_DEVICE_RESET) {
return vfio_platform_call_reset(vdev, NULL);
}
return -ENOTTY;
}
static ssize_t vfio_platform_read_mmio(struct vfio_platform_region *reg,
char __user *buf, size_t count,
loff_t off)
{
unsigned int done = 0;
if (!reg->ioaddr) {
reg->ioaddr =
ioremap_nocache(reg->addr, reg->size);
if (!reg->ioaddr)
return -ENOMEM;
}
while (count) {
size_t filled;
if (count >= 4 && !(off % 4)) {
u32 val;
val = ioread32(reg->ioaddr + off);
if (copy_to_user(buf, &val, 4))
goto err;
filled = 4;
} else if (count >= 2 && !(off % 2)) {
u16 val;
val = ioread16(reg->ioaddr + off);
if (copy_to_user(buf, &val, 2))
goto err;
filled = 2;
} else {
u8 val;
val = ioread8(reg->ioaddr + off);
if (copy_to_user(buf, &val, 1))
goto err;
filled = 1;
}
count -= filled;
done += filled;
off += filled;
buf += filled;
}
return done;
err:
return -EFAULT;
}
static ssize_t vfio_platform_read(void *device_data, char __user *buf,
size_t count, loff_t *ppos)
{
struct vfio_platform_device *vdev = device_data;
unsigned int index = VFIO_PLATFORM_OFFSET_TO_INDEX(*ppos);
loff_t off = *ppos & VFIO_PLATFORM_OFFSET_MASK;
if (index >= vdev->num_regions)
return -EINVAL;
if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ))
return -EINVAL;
if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
return vfio_platform_read_mmio(&vdev->regions[index],
buf, count, off);
else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
return -EINVAL; /* not implemented */
return -EINVAL;
}
static ssize_t vfio_platform_write_mmio(struct vfio_platform_region *reg,
const char __user *buf, size_t count,
loff_t off)
{
unsigned int done = 0;
if (!reg->ioaddr) {
reg->ioaddr =
ioremap_nocache(reg->addr, reg->size);
if (!reg->ioaddr)
return -ENOMEM;
}
while (count) {
size_t filled;
if (count >= 4 && !(off % 4)) {
u32 val;
if (copy_from_user(&val, buf, 4))
goto err;
iowrite32(val, reg->ioaddr + off);
filled = 4;
} else if (count >= 2 && !(off % 2)) {
u16 val;
if (copy_from_user(&val, buf, 2))
goto err;
iowrite16(val, reg->ioaddr + off);
filled = 2;
} else {
u8 val;
if (copy_from_user(&val, buf, 1))
goto err;
iowrite8(val, reg->ioaddr + off);
filled = 1;
}
count -= filled;
done += filled;
off += filled;
buf += filled;
}
return done;
err:
return -EFAULT;
}
static ssize_t vfio_platform_write(void *device_data, const char __user *buf,
size_t count, loff_t *ppos)
{
struct vfio_platform_device *vdev = device_data;
unsigned int index = VFIO_PLATFORM_OFFSET_TO_INDEX(*ppos);
loff_t off = *ppos & VFIO_PLATFORM_OFFSET_MASK;
if (index >= vdev->num_regions)
return -EINVAL;
if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE))
return -EINVAL;
if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
return vfio_platform_write_mmio(&vdev->regions[index],
buf, count, off);
else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
return -EINVAL; /* not implemented */
return -EINVAL;
}
static int vfio_platform_mmap_mmio(struct vfio_platform_region region,
struct vm_area_struct *vma)
{
u64 req_len, pgoff, req_start;
req_len = vma->vm_end - vma->vm_start;
pgoff = vma->vm_pgoff &
((1U << (VFIO_PLATFORM_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
req_start = pgoff << PAGE_SHIFT;
if (region.size < PAGE_SIZE || req_start + req_len > region.size)
return -EINVAL;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
vma->vm_pgoff = (region.addr >> PAGE_SHIFT) + pgoff;
return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
req_len, vma->vm_page_prot);
}
static int vfio_platform_mmap(void *device_data, struct vm_area_struct *vma)
{
struct vfio_platform_device *vdev = device_data;
unsigned int index;
index = vma->vm_pgoff >> (VFIO_PLATFORM_OFFSET_SHIFT - PAGE_SHIFT);
if (vma->vm_end < vma->vm_start)
return -EINVAL;
if (!(vma->vm_flags & VM_SHARED))
return -EINVAL;
if (index >= vdev->num_regions)
return -EINVAL;
if (vma->vm_start & ~PAGE_MASK)
return -EINVAL;
if (vma->vm_end & ~PAGE_MASK)
return -EINVAL;
if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_MMAP))
return -EINVAL;
if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ)
&& (vma->vm_flags & VM_READ))
return -EINVAL;
if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE)
&& (vma->vm_flags & VM_WRITE))
return -EINVAL;
vma->vm_private_data = vdev;
if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_MMIO)
return vfio_platform_mmap_mmio(vdev->regions[index], vma);
else if (vdev->regions[index].type & VFIO_PLATFORM_REGION_TYPE_PIO)
return -EINVAL; /* not implemented */
return -EINVAL;
}
static const struct vfio_device_ops vfio_platform_ops = {
.name = "vfio-platform",
.open = vfio_platform_open,
.release = vfio_platform_release,
.ioctl = vfio_platform_ioctl,
.read = vfio_platform_read,
.write = vfio_platform_write,
.mmap = vfio_platform_mmap,
};
static int vfio_platform_of_probe(struct vfio_platform_device *vdev,
struct device *dev)
{
int ret;
ret = device_property_read_string(dev, "compatible",
&vdev->compat);
if (ret)
pr_err("VFIO: Cannot retrieve compat for %s\n", vdev->name);
return ret;
}
/*
* There can be two kernel build combinations. One build where
* ACPI is not selected in Kconfig and another one with the ACPI Kconfig.
*
* In the first case, vfio_platform_acpi_probe will return since
* acpi_disabled is 1. DT user will not see any kind of messages from
* ACPI.
*
* In the second case, both DT and ACPI is compiled in but the system is
* booting with any of these combinations.
*
* If the firmware is DT type, then acpi_disabled is 1. The ACPI probe routine
* terminates immediately without any messages.
*
* If the firmware is ACPI type, then acpi_disabled is 0. All other checks are
* valid checks. We cannot claim that this system is DT.
*/
int vfio_platform_probe_common(struct vfio_platform_device *vdev,
struct device *dev)
{
struct iommu_group *group;
int ret;
if (!vdev)
return -EINVAL;
ret = vfio_platform_acpi_probe(vdev, dev);
if (ret)
ret = vfio_platform_of_probe(vdev, dev);
if (ret)
return ret;
vdev->device = dev;
ret = vfio_platform_get_reset(vdev);
if (ret && vdev->reset_required) {
pr_err("VFIO: No reset function found for device %s\n",
vdev->name);
return ret;
}
group = vfio_iommu_group_get(dev);
if (!group) {
pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
ret = -EINVAL;
goto put_reset;
}
ret = vfio_add_group_dev(dev, &vfio_platform_ops, vdev);
if (ret)
goto put_iommu;
mutex_init(&vdev->igate);
pm_runtime_enable(vdev->device);
return 0;
put_iommu:
vfio_iommu_group_put(group, dev);
put_reset:
vfio_platform_put_reset(vdev);
return ret;
}
EXPORT_SYMBOL_GPL(vfio_platform_probe_common);
struct vfio_platform_device *vfio_platform_remove_common(struct device *dev)
{
struct vfio_platform_device *vdev;
vdev = vfio_del_group_dev(dev);
if (vdev) {
pm_runtime_disable(vdev->device);
vfio_platform_put_reset(vdev);
vfio_iommu_group_put(dev->iommu_group, dev);
}
return vdev;
}
EXPORT_SYMBOL_GPL(vfio_platform_remove_common);
void __vfio_platform_register_reset(struct vfio_platform_reset_node *node)
{
mutex_lock(&driver_lock);
list_add(&node->link, &reset_list);
mutex_unlock(&driver_lock);
}
EXPORT_SYMBOL_GPL(__vfio_platform_register_reset);
void vfio_platform_unregister_reset(const char *compat,
vfio_platform_reset_fn_t fn)
{
struct vfio_platform_reset_node *iter, *temp;
mutex_lock(&driver_lock);
list_for_each_entry_safe(iter, temp, &reset_list, link) {
if (!strcmp(iter->compat, compat) && (iter->of_reset == fn)) {
list_del(&iter->link);
break;
}
}
mutex_unlock(&driver_lock);
}
EXPORT_SYMBOL_GPL(vfio_platform_unregister_reset);
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
+337
View File
@@ -0,0 +1,337 @@
/*
* VFIO platform devices interrupt handling
*
* Copyright (C) 2013 - Virtual Open Systems
* Author: Antonios Motakis <a.motakis@virtualopensystems.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/eventfd.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/vfio.h>
#include <linux/irq.h>
#include "vfio_platform_private.h"
static void vfio_platform_mask(struct vfio_platform_irq *irq_ctx)
{
unsigned long flags;
spin_lock_irqsave(&irq_ctx->lock, flags);
if (!irq_ctx->masked) {
disable_irq_nosync(irq_ctx->hwirq);
irq_ctx->masked = true;
}
spin_unlock_irqrestore(&irq_ctx->lock, flags);
}
static int vfio_platform_mask_handler(void *opaque, void *unused)
{
struct vfio_platform_irq *irq_ctx = opaque;
vfio_platform_mask(irq_ctx);
return 0;
}
static int vfio_platform_set_irq_mask(struct vfio_platform_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags,
void *data)
{
if (start != 0 || count != 1)
return -EINVAL;
if (!(vdev->irqs[index].flags & VFIO_IRQ_INFO_MASKABLE))
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t fd = *(int32_t *)data;
if (fd >= 0)
return vfio_virqfd_enable((void *) &vdev->irqs[index],
vfio_platform_mask_handler,
NULL, NULL,
&vdev->irqs[index].mask, fd);
vfio_virqfd_disable(&vdev->irqs[index].mask);
return 0;
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
vfio_platform_mask(&vdev->irqs[index]);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t mask = *(uint8_t *)data;
if (mask)
vfio_platform_mask(&vdev->irqs[index]);
}
return 0;
}
static void vfio_platform_unmask(struct vfio_platform_irq *irq_ctx)
{
unsigned long flags;
spin_lock_irqsave(&irq_ctx->lock, flags);
if (irq_ctx->masked) {
enable_irq(irq_ctx->hwirq);
irq_ctx->masked = false;
}
spin_unlock_irqrestore(&irq_ctx->lock, flags);
}
static int vfio_platform_unmask_handler(void *opaque, void *unused)
{
struct vfio_platform_irq *irq_ctx = opaque;
vfio_platform_unmask(irq_ctx);
return 0;
}
static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags,
void *data)
{
if (start != 0 || count != 1)
return -EINVAL;
if (!(vdev->irqs[index].flags & VFIO_IRQ_INFO_MASKABLE))
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t fd = *(int32_t *)data;
if (fd >= 0)
return vfio_virqfd_enable((void *) &vdev->irqs[index],
vfio_platform_unmask_handler,
NULL, NULL,
&vdev->irqs[index].unmask,
fd);
vfio_virqfd_disable(&vdev->irqs[index].unmask);
return 0;
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
vfio_platform_unmask(&vdev->irqs[index]);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t unmask = *(uint8_t *)data;
if (unmask)
vfio_platform_unmask(&vdev->irqs[index]);
}
return 0;
}
static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id)
{
struct vfio_platform_irq *irq_ctx = dev_id;
unsigned long flags;
int ret = IRQ_NONE;
spin_lock_irqsave(&irq_ctx->lock, flags);
if (!irq_ctx->masked) {
ret = IRQ_HANDLED;
/* automask maskable interrupts */
disable_irq_nosync(irq_ctx->hwirq);
irq_ctx->masked = true;
}
spin_unlock_irqrestore(&irq_ctx->lock, flags);
if (ret == IRQ_HANDLED)
eventfd_signal(irq_ctx->trigger, 1);
return ret;
}
static irqreturn_t vfio_irq_handler(int irq, void *dev_id)
{
struct vfio_platform_irq *irq_ctx = dev_id;
eventfd_signal(irq_ctx->trigger, 1);
return IRQ_HANDLED;
}
static int vfio_set_trigger(struct vfio_platform_device *vdev, int index,
int fd, irq_handler_t handler)
{
struct vfio_platform_irq *irq = &vdev->irqs[index];
struct eventfd_ctx *trigger;
int ret;
if (irq->trigger) {
irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN);
free_irq(irq->hwirq, irq);
kfree(irq->name);
eventfd_ctx_put(irq->trigger);
irq->trigger = NULL;
}
if (fd < 0) /* Disable only */
return 0;
irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)",
irq->hwirq, vdev->name);
if (!irq->name)
return -ENOMEM;
trigger = eventfd_ctx_fdget(fd);
if (IS_ERR(trigger)) {
kfree(irq->name);
return PTR_ERR(trigger);
}
irq->trigger = trigger;
irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN);
ret = request_irq(irq->hwirq, handler, 0, irq->name, irq);
if (ret) {
kfree(irq->name);
eventfd_ctx_put(trigger);
irq->trigger = NULL;
return ret;
}
if (!irq->masked)
enable_irq(irq->hwirq);
return 0;
}
static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags,
void *data)
{
struct vfio_platform_irq *irq = &vdev->irqs[index];
irq_handler_t handler;
if (vdev->irqs[index].flags & VFIO_IRQ_INFO_AUTOMASKED)
handler = vfio_automasked_irq_handler;
else
handler = vfio_irq_handler;
if (!count && (flags & VFIO_IRQ_SET_DATA_NONE))
return vfio_set_trigger(vdev, index, -1, handler);
if (start != 0 || count != 1)
return -EINVAL;
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int32_t fd = *(int32_t *)data;
return vfio_set_trigger(vdev, index, fd, handler);
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
handler(irq->hwirq, irq);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t trigger = *(uint8_t *)data;
if (trigger)
handler(irq->hwirq, irq);
}
return 0;
}
int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
uint32_t flags, unsigned index, unsigned start,
unsigned count, void *data)
{
int (*func)(struct vfio_platform_device *vdev, unsigned index,
unsigned start, unsigned count, uint32_t flags,
void *data) = NULL;
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_MASK:
func = vfio_platform_set_irq_mask;
break;
case VFIO_IRQ_SET_ACTION_UNMASK:
func = vfio_platform_set_irq_unmask;
break;
case VFIO_IRQ_SET_ACTION_TRIGGER:
func = vfio_platform_set_irq_trigger;
break;
}
if (!func)
return -ENOTTY;
return func(vdev, index, start, count, flags, data);
}
int vfio_platform_irq_init(struct vfio_platform_device *vdev)
{
int cnt = 0, i;
while (vdev->get_irq(vdev, cnt) >= 0)
cnt++;
vdev->irqs = kcalloc(cnt, sizeof(struct vfio_platform_irq), GFP_KERNEL);
if (!vdev->irqs)
return -ENOMEM;
for (i = 0; i < cnt; i++) {
int hwirq = vdev->get_irq(vdev, i);
if (hwirq < 0)
goto err;
spin_lock_init(&vdev->irqs[i].lock);
vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD;
if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK)
vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE
| VFIO_IRQ_INFO_AUTOMASKED;
vdev->irqs[i].count = 1;
vdev->irqs[i].hwirq = hwirq;
vdev->irqs[i].masked = false;
}
vdev->num_irqs = cnt;
return 0;
err:
kfree(vdev->irqs);
return -EINVAL;
}
void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev)
{
int i;
for (i = 0; i < vdev->num_irqs; i++)
vfio_set_trigger(vdev, i, -1, NULL);
vdev->num_irqs = 0;
kfree(vdev->irqs);
}
@@ -0,0 +1,127 @@
/*
* Copyright (C) 2013 - Virtual Open Systems
* Author: Antonios Motakis <a.motakis@virtualopensystems.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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#ifndef VFIO_PLATFORM_PRIVATE_H
#define VFIO_PLATFORM_PRIVATE_H
#include <linux/types.h>
#include <linux/interrupt.h>
#define VFIO_PLATFORM_OFFSET_SHIFT 40
#define VFIO_PLATFORM_OFFSET_MASK (((u64)(1) << VFIO_PLATFORM_OFFSET_SHIFT) - 1)
#define VFIO_PLATFORM_OFFSET_TO_INDEX(off) \
(off >> VFIO_PLATFORM_OFFSET_SHIFT)
#define VFIO_PLATFORM_INDEX_TO_OFFSET(index) \
((u64)(index) << VFIO_PLATFORM_OFFSET_SHIFT)
struct vfio_platform_irq {
u32 flags;
u32 count;
int hwirq;
char *name;
struct eventfd_ctx *trigger;
bool masked;
spinlock_t lock;
struct virqfd *unmask;
struct virqfd *mask;
};
struct vfio_platform_region {
u64 addr;
resource_size_t size;
u32 flags;
u32 type;
#define VFIO_PLATFORM_REGION_TYPE_MMIO 1
#define VFIO_PLATFORM_REGION_TYPE_PIO 2
void __iomem *ioaddr;
};
struct vfio_platform_device {
struct vfio_platform_region *regions;
u32 num_regions;
struct vfio_platform_irq *irqs;
u32 num_irqs;
int refcnt;
struct mutex igate;
struct module *parent_module;
const char *compat;
const char *acpihid;
struct module *reset_module;
struct device *device;
/*
* These fields should be filled by the bus specific binder
*/
void *opaque;
const char *name;
uint32_t flags;
/* callbacks to discover device resources */
struct resource*
(*get_resource)(struct vfio_platform_device *vdev, int i);
int (*get_irq)(struct vfio_platform_device *vdev, int i);
int (*of_reset)(struct vfio_platform_device *vdev);
bool reset_required;
};
typedef int (*vfio_platform_reset_fn_t)(struct vfio_platform_device *vdev);
struct vfio_platform_reset_node {
struct list_head link;
char *compat;
struct module *owner;
vfio_platform_reset_fn_t of_reset;
};
extern int vfio_platform_probe_common(struct vfio_platform_device *vdev,
struct device *dev);
extern struct vfio_platform_device *vfio_platform_remove_common
(struct device *dev);
extern int vfio_platform_irq_init(struct vfio_platform_device *vdev);
extern void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev);
extern int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev,
uint32_t flags, unsigned index,
unsigned start, unsigned count,
void *data);
extern void __vfio_platform_register_reset(struct vfio_platform_reset_node *n);
extern void vfio_platform_unregister_reset(const char *compat,
vfio_platform_reset_fn_t fn);
#define vfio_platform_register_reset(__compat, __reset) \
static struct vfio_platform_reset_node __reset ## _node = { \
.owner = THIS_MODULE, \
.compat = __compat, \
.of_reset = __reset, \
}; \
__vfio_platform_register_reset(&__reset ## _node)
#define module_vfio_reset_handler(compat, reset) \
MODULE_ALIAS("vfio-reset:" compat); \
static int __init reset ## _module_init(void) \
{ \
vfio_platform_register_reset(compat, reset); \
return 0; \
}; \
static void __exit reset ## _module_exit(void) \
{ \
vfio_platform_unregister_reset(compat, reset); \
}; \
module_init(reset ## _module_init); \
module_exit(reset ## _module_exit)
#endif /* VFIO_PLATFORM_PRIVATE_H */
+2262
View File
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
+110
View File
@@ -0,0 +1,110 @@
/*
* EEH functionality support for VFIO devices. The feature is only
* available on sPAPR compatible platforms.
*
* Copyright Gavin Shan, IBM Corporation 2014.
*
* 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/uaccess.h>
#include <linux/vfio.h>
#include <asm/eeh.h>
#define DRIVER_VERSION "0.1"
#define DRIVER_AUTHOR "Gavin Shan, IBM Corporation"
#define DRIVER_DESC "VFIO IOMMU SPAPR EEH"
/* We might build address mapping here for "fast" path later */
void vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
{
eeh_dev_open(pdev);
}
EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_open);
void vfio_spapr_pci_eeh_release(struct pci_dev *pdev)
{
eeh_dev_release(pdev);
}
EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_release);
long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
unsigned int cmd, unsigned long arg)
{
struct eeh_pe *pe;
struct vfio_eeh_pe_op op;
unsigned long minsz;
long ret = -EINVAL;
switch (cmd) {
case VFIO_CHECK_EXTENSION:
if (arg == VFIO_EEH)
ret = eeh_enabled() ? 1 : 0;
else
ret = 0;
break;
case VFIO_EEH_PE_OP:
pe = eeh_iommu_group_to_pe(group);
if (!pe)
return -ENODEV;
minsz = offsetofend(struct vfio_eeh_pe_op, op);
if (copy_from_user(&op, (void __user *)arg, minsz))
return -EFAULT;
if (op.argsz < minsz || op.flags)
return -EINVAL;
switch (op.op) {
case VFIO_EEH_PE_DISABLE:
ret = eeh_pe_set_option(pe, EEH_OPT_DISABLE);
break;
case VFIO_EEH_PE_ENABLE:
ret = eeh_pe_set_option(pe, EEH_OPT_ENABLE);
break;
case VFIO_EEH_PE_UNFREEZE_IO:
ret = eeh_pe_set_option(pe, EEH_OPT_THAW_MMIO);
break;
case VFIO_EEH_PE_UNFREEZE_DMA:
ret = eeh_pe_set_option(pe, EEH_OPT_THAW_DMA);
break;
case VFIO_EEH_PE_GET_STATE:
ret = eeh_pe_get_state(pe);
break;
case VFIO_EEH_PE_RESET_DEACTIVATE:
ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE);
break;
case VFIO_EEH_PE_RESET_HOT:
ret = eeh_pe_reset(pe, EEH_RESET_HOT);
break;
case VFIO_EEH_PE_RESET_FUNDAMENTAL:
ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL);
break;
case VFIO_EEH_PE_CONFIGURE:
ret = eeh_pe_configure(pe);
break;
case VFIO_EEH_PE_INJECT_ERR:
minsz = offsetofend(struct vfio_eeh_pe_op, err.mask);
if (op.argsz < minsz)
return -EINVAL;
if (copy_from_user(&op, (void __user *)arg, minsz))
return -EFAULT;
ret = eeh_pe_inject_err(pe, op.err.type, op.err.func,
op.err.addr, op.err.mask);
break;
default:
ret = -EINVAL;
}
}
return ret;
}
EXPORT_SYMBOL_GPL(vfio_spapr_iommu_eeh_ioctl);
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
+226
View File
@@ -0,0 +1,226 @@
/*
* VFIO generic eventfd code for IRQFD support.
* Derived from drivers/vfio/pci/vfio_pci_intrs.c
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.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/vfio.h>
#include <linux/eventfd.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/slab.h>
#define DRIVER_VERSION "0.1"
#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
#define DRIVER_DESC "IRQFD support for VFIO bus drivers"
static struct workqueue_struct *vfio_irqfd_cleanup_wq;
static DEFINE_SPINLOCK(virqfd_lock);
static int __init vfio_virqfd_init(void)
{
vfio_irqfd_cleanup_wq =
create_singlethread_workqueue("vfio-irqfd-cleanup");
if (!vfio_irqfd_cleanup_wq)
return -ENOMEM;
return 0;
}
static void __exit vfio_virqfd_exit(void)
{
destroy_workqueue(vfio_irqfd_cleanup_wq);
}
static void virqfd_deactivate(struct virqfd *virqfd)
{
queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
}
static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
__poll_t flags = key_to_poll(key);
if (flags & EPOLLIN) {
/* An event has been signaled, call function */
if ((!virqfd->handler ||
virqfd->handler(virqfd->opaque, virqfd->data)) &&
virqfd->thread)
schedule_work(&virqfd->inject);
}
if (flags & EPOLLHUP) {
unsigned long flags;
spin_lock_irqsave(&virqfd_lock, flags);
/*
* The eventfd is closing, if the virqfd has not yet been
* queued for release, as determined by testing whether the
* virqfd pointer to it is still valid, queue it now. As
* with kvm irqfds, we know we won't race against the virqfd
* going away because we hold the lock to get here.
*/
if (*(virqfd->pvirqfd) == virqfd) {
*(virqfd->pvirqfd) = NULL;
virqfd_deactivate(virqfd);
}
spin_unlock_irqrestore(&virqfd_lock, flags);
}
return 0;
}
static void virqfd_ptable_queue_proc(struct file *file,
wait_queue_head_t *wqh, poll_table *pt)
{
struct virqfd *virqfd = container_of(pt, struct virqfd, pt);
add_wait_queue(wqh, &virqfd->wait);
}
static void virqfd_shutdown(struct work_struct *work)
{
struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
u64 cnt;
eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
flush_work(&virqfd->inject);
eventfd_ctx_put(virqfd->eventfd);
kfree(virqfd);
}
static void virqfd_inject(struct work_struct *work)
{
struct virqfd *virqfd = container_of(work, struct virqfd, inject);
if (virqfd->thread)
virqfd->thread(virqfd->opaque, virqfd->data);
}
int vfio_virqfd_enable(void *opaque,
int (*handler)(void *, void *),
void (*thread)(void *, void *),
void *data, struct virqfd **pvirqfd, int fd)
{
struct fd irqfd;
struct eventfd_ctx *ctx;
struct virqfd *virqfd;
int ret = 0;
__poll_t events;
virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
if (!virqfd)
return -ENOMEM;
virqfd->pvirqfd = pvirqfd;
virqfd->opaque = opaque;
virqfd->handler = handler;
virqfd->thread = thread;
virqfd->data = data;
INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
INIT_WORK(&virqfd->inject, virqfd_inject);
irqfd = fdget(fd);
if (!irqfd.file) {
ret = -EBADF;
goto err_fd;
}
ctx = eventfd_ctx_fileget(irqfd.file);
if (IS_ERR(ctx)) {
ret = PTR_ERR(ctx);
goto err_ctx;
}
virqfd->eventfd = ctx;
/*
* virqfds can be released by closing the eventfd or directly
* through ioctl. These are both done through a workqueue, so
* we update the pointer to the virqfd under lock to avoid
* pushing multiple jobs to release the same virqfd.
*/
spin_lock_irq(&virqfd_lock);
if (*pvirqfd) {
spin_unlock_irq(&virqfd_lock);
ret = -EBUSY;
goto err_busy;
}
*pvirqfd = virqfd;
spin_unlock_irq(&virqfd_lock);
/*
* Install our own custom wake-up handling so we are notified via
* a callback whenever someone signals the underlying eventfd.
*/
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
events = vfs_poll(irqfd.file, &virqfd->pt);
/*
* Check if there was an event already pending on the eventfd
* before we registered and trigger it as if we didn't miss it.
*/
if (events & EPOLLIN) {
if ((!handler || handler(opaque, data)) && thread)
schedule_work(&virqfd->inject);
}
/*
* Do not drop the file until the irqfd is fully initialized,
* otherwise we might race against the EPOLLHUP.
*/
fdput(irqfd);
return 0;
err_busy:
eventfd_ctx_put(ctx);
err_ctx:
fdput(irqfd);
err_fd:
kfree(virqfd);
return ret;
}
EXPORT_SYMBOL_GPL(vfio_virqfd_enable);
void vfio_virqfd_disable(struct virqfd **pvirqfd)
{
unsigned long flags;
spin_lock_irqsave(&virqfd_lock, flags);
if (*pvirqfd) {
virqfd_deactivate(*pvirqfd);
*pvirqfd = NULL;
}
spin_unlock_irqrestore(&virqfd_lock, flags);
/*
* Block until we know all outstanding shutdown jobs have completed.
* Even if we don't queue the job, flush the wq to be sure it's
* been released.
*/
flush_workqueue(vfio_irqfd_cleanup_wq);
}
EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
module_init(vfio_virqfd_init);
module_exit(vfio_virqfd_exit);
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);