WSL2-Linux-Kernel/include/linux/vfio.h

256 строки
8.2 KiB
C
Исходник Обычный вид История

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* VFIO API definition
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*/
#ifndef VFIO_H
#define VFIO_H
#include <linux/iommu.h>
#include <linux/mm.h>
#include <linux/workqueue.h>
#include <linux/poll.h>
#include <uapi/linux/vfio.h>
vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas <yishaih@nvidia.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-08-06 04:19:00 +03:00
/*
* VFIO devices can be placed in a set, this allows all devices to share this
* structure and the VFIO core will provide a lock that is held around
* open_device()/close_device() for all devices in the set.
*/
struct vfio_device_set {
void *set_id;
struct mutex lock;
struct list_head device_list;
unsigned int device_count;
};
vfio: Split creation of a vfio_device into init and register ops This makes the struct vfio_device part of the public interface so it can be used with container_of and so forth, as is typical for a Linux subystem. This is the first step to bring some type-safety to the vfio interface by allowing the replacement of 'void *' and 'struct device *' inputs with a simple and clear 'struct vfio_device *' For now the self-allocating vfio_add_group_dev() interface is kept so each user can be updated as a separate patch. The expected usage pattern is driver core probe() function: my_device = kzalloc(sizeof(*mydevice)); vfio_init_group_dev(&my_device->vdev, dev, ops, mydevice); /* other driver specific prep */ vfio_register_group_dev(&my_device->vdev); dev_set_drvdata(dev, my_device); driver core remove() function: my_device = dev_get_drvdata(dev); vfio_unregister_group_dev(&my_device->vdev); /* other driver specific tear down */ kfree(my_device); Allowing the driver to be able to use the drvdata and vfio_device to go to/from its own data. The pattern also makes it clear that vfio_register_group_dev() must be last in the sequence, as once it is called the core code can immediately start calling ops. The init/register gap is provided to allow for the driver to do setup before ops can be called and thus avoid races. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Liu Yi L <yi.l.liu@intel.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Message-Id: <3-v3-225de1400dfc+4e074-vfio1_jgg@nvidia.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-03-30 18:53:05 +03:00
struct vfio_device {
struct device *dev;
const struct vfio_device_ops *ops;
struct vfio_group *group;
vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas <yishaih@nvidia.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-08-06 04:19:00 +03:00
struct vfio_device_set *dev_set;
struct list_head dev_set_list;
vfio: Split creation of a vfio_device into init and register ops This makes the struct vfio_device part of the public interface so it can be used with container_of and so forth, as is typical for a Linux subystem. This is the first step to bring some type-safety to the vfio interface by allowing the replacement of 'void *' and 'struct device *' inputs with a simple and clear 'struct vfio_device *' For now the self-allocating vfio_add_group_dev() interface is kept so each user can be updated as a separate patch. The expected usage pattern is driver core probe() function: my_device = kzalloc(sizeof(*mydevice)); vfio_init_group_dev(&my_device->vdev, dev, ops, mydevice); /* other driver specific prep */ vfio_register_group_dev(&my_device->vdev); dev_set_drvdata(dev, my_device); driver core remove() function: my_device = dev_get_drvdata(dev); vfio_unregister_group_dev(&my_device->vdev); /* other driver specific tear down */ kfree(my_device); Allowing the driver to be able to use the drvdata and vfio_device to go to/from its own data. The pattern also makes it clear that vfio_register_group_dev() must be last in the sequence, as once it is called the core code can immediately start calling ops. The init/register gap is provided to allow for the driver to do setup before ops can be called and thus avoid races. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Liu Yi L <yi.l.liu@intel.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Message-Id: <3-v3-225de1400dfc+4e074-vfio1_jgg@nvidia.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-03-30 18:53:05 +03:00
/* Members below here are private, not for driver use */
refcount_t refcount;
vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas <yishaih@nvidia.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-08-06 04:19:00 +03:00
unsigned int open_count;
vfio: Split creation of a vfio_device into init and register ops This makes the struct vfio_device part of the public interface so it can be used with container_of and so forth, as is typical for a Linux subystem. This is the first step to bring some type-safety to the vfio interface by allowing the replacement of 'void *' and 'struct device *' inputs with a simple and clear 'struct vfio_device *' For now the self-allocating vfio_add_group_dev() interface is kept so each user can be updated as a separate patch. The expected usage pattern is driver core probe() function: my_device = kzalloc(sizeof(*mydevice)); vfio_init_group_dev(&my_device->vdev, dev, ops, mydevice); /* other driver specific prep */ vfio_register_group_dev(&my_device->vdev); dev_set_drvdata(dev, my_device); driver core remove() function: my_device = dev_get_drvdata(dev); vfio_unregister_group_dev(&my_device->vdev); /* other driver specific tear down */ kfree(my_device); Allowing the driver to be able to use the drvdata and vfio_device to go to/from its own data. The pattern also makes it clear that vfio_register_group_dev() must be last in the sequence, as once it is called the core code can immediately start calling ops. The init/register gap is provided to allow for the driver to do setup before ops can be called and thus avoid races. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Liu Yi L <yi.l.liu@intel.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Message-Id: <3-v3-225de1400dfc+4e074-vfio1_jgg@nvidia.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-03-30 18:53:05 +03:00
struct completion comp;
struct list_head group_next;
};
/**
* struct vfio_device_ops - VFIO bus driver device callbacks
*
vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas <yishaih@nvidia.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-08-06 04:19:00 +03:00
* @open_device: Called when the first file descriptor is opened for this device
* @close_device: Opposite of open_device
* @read: Perform read(2) on device file descriptor
* @write: Perform write(2) on device file descriptor
* @ioctl: Perform ioctl(2) on device file descriptor, supporting VFIO_DEVICE_*
* operations documented below
* @mmap: Perform mmap(2) on a region of the device file descriptor
* @request: Request for the bus driver to release the device
* @match: Optional device name match callback (return: 0 for no-match, >0 for
* match, -errno for abort (ex. match with insufficient or incorrect
* additional args)
*/
struct vfio_device_ops {
char *name;
vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas <yishaih@nvidia.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-08-06 04:19:00 +03:00
int (*open_device)(struct vfio_device *vdev);
void (*close_device)(struct vfio_device *vdev);
ssize_t (*read)(struct vfio_device *vdev, char __user *buf,
size_t count, loff_t *ppos);
ssize_t (*write)(struct vfio_device *vdev, const char __user *buf,
size_t count, loff_t *size);
long (*ioctl)(struct vfio_device *vdev, unsigned int cmd,
unsigned long arg);
int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma);
void (*request)(struct vfio_device *vdev, unsigned int count);
int (*match)(struct vfio_device *vdev, char *buf);
};
extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev);
vfio: Split creation of a vfio_device into init and register ops This makes the struct vfio_device part of the public interface so it can be used with container_of and so forth, as is typical for a Linux subystem. This is the first step to bring some type-safety to the vfio interface by allowing the replacement of 'void *' and 'struct device *' inputs with a simple and clear 'struct vfio_device *' For now the self-allocating vfio_add_group_dev() interface is kept so each user can be updated as a separate patch. The expected usage pattern is driver core probe() function: my_device = kzalloc(sizeof(*mydevice)); vfio_init_group_dev(&my_device->vdev, dev, ops, mydevice); /* other driver specific prep */ vfio_register_group_dev(&my_device->vdev); dev_set_drvdata(dev, my_device); driver core remove() function: my_device = dev_get_drvdata(dev); vfio_unregister_group_dev(&my_device->vdev); /* other driver specific tear down */ kfree(my_device); Allowing the driver to be able to use the drvdata and vfio_device to go to/from its own data. The pattern also makes it clear that vfio_register_group_dev() must be last in the sequence, as once it is called the core code can immediately start calling ops. The init/register gap is provided to allow for the driver to do setup before ops can be called and thus avoid races. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Liu Yi L <yi.l.liu@intel.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Message-Id: <3-v3-225de1400dfc+4e074-vfio1_jgg@nvidia.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-03-30 18:53:05 +03:00
void vfio_init_group_dev(struct vfio_device *device, struct device *dev,
const struct vfio_device_ops *ops);
void vfio_uninit_group_dev(struct vfio_device *device);
vfio: Split creation of a vfio_device into init and register ops This makes the struct vfio_device part of the public interface so it can be used with container_of and so forth, as is typical for a Linux subystem. This is the first step to bring some type-safety to the vfio interface by allowing the replacement of 'void *' and 'struct device *' inputs with a simple and clear 'struct vfio_device *' For now the self-allocating vfio_add_group_dev() interface is kept so each user can be updated as a separate patch. The expected usage pattern is driver core probe() function: my_device = kzalloc(sizeof(*mydevice)); vfio_init_group_dev(&my_device->vdev, dev, ops, mydevice); /* other driver specific prep */ vfio_register_group_dev(&my_device->vdev); dev_set_drvdata(dev, my_device); driver core remove() function: my_device = dev_get_drvdata(dev); vfio_unregister_group_dev(&my_device->vdev); /* other driver specific tear down */ kfree(my_device); Allowing the driver to be able to use the drvdata and vfio_device to go to/from its own data. The pattern also makes it clear that vfio_register_group_dev() must be last in the sequence, as once it is called the core code can immediately start calling ops. The init/register gap is provided to allow for the driver to do setup before ops can be called and thus avoid races. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Liu Yi L <yi.l.liu@intel.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Message-Id: <3-v3-225de1400dfc+4e074-vfio1_jgg@nvidia.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-03-30 18:53:05 +03:00
int vfio_register_group_dev(struct vfio_device *device);
void vfio_unregister_group_dev(struct vfio_device *device);
extern struct vfio_device *vfio_device_get_from_dev(struct device *dev);
extern void vfio_device_put(struct vfio_device *device);
vfio: Provide better generic support for open/release vfio_device_ops Currently the driver ops have an open/release pair that is called once each time a device FD is opened or closed. Add an additional set of open/close_device() ops which are called when the device FD is opened for the first time and closed for the last time. An analysis shows that all of the drivers require this semantic. Some are open coding it as part of their reflck implementation, and some are just buggy and miss it completely. To retain the current semantics PCI and FSL depend on, introduce the idea of a "device set" which is a grouping of vfio_device's that share the same lock around opening. The device set is established by providing a 'set_id' pointer. All vfio_device's that provide the same pointer will be joined to the same singleton memory and lock across the whole set. This effectively replaces the oddly named reflck. After conversion the set_id will be sourced from: - A struct device from a fsl_mc_device (fsl) - A struct pci_slot (pci) - A struct pci_bus (pci) - The struct vfio_device (everything) The design ensures that the above pointers are live as long as the vfio_device is registered, so they form reliable unique keys to group vfio_devices into sets. This implementation uses xarray instead of searching through the driver core structures, which simplifies the somewhat tricky locking in this area. Following patches convert all the drivers. Signed-off-by: Yishai Hadas <yishaih@nvidia.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/4-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-08-06 04:19:00 +03:00
int vfio_assign_device_set(struct vfio_device *device, void *set_id);
/* events for the backend driver notify callback */
enum vfio_iommu_notify_type {
VFIO_IOMMU_CONTAINER_CLOSE = 0,
};
/**
* struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks
*/
struct vfio_iommu_driver_ops {
char *name;
struct module *owner;
void *(*open)(unsigned long arg);
void (*release)(void *iommu_data);
ssize_t (*read)(void *iommu_data, char __user *buf,
size_t count, loff_t *ppos);
ssize_t (*write)(void *iommu_data, const char __user *buf,
size_t count, loff_t *size);
long (*ioctl)(void *iommu_data, unsigned int cmd,
unsigned long arg);
int (*mmap)(void *iommu_data, struct vm_area_struct *vma);
int (*attach_group)(void *iommu_data,
struct iommu_group *group);
void (*detach_group)(void *iommu_data,
struct iommu_group *group);
int (*pin_pages)(void *iommu_data,
struct iommu_group *group,
unsigned long *user_pfn,
int npage, int prot,
unsigned long *phys_pfn);
int (*unpin_pages)(void *iommu_data,
unsigned long *user_pfn, int npage);
int (*register_notifier)(void *iommu_data,
unsigned long *events,
struct notifier_block *nb);
int (*unregister_notifier)(void *iommu_data,
struct notifier_block *nb);
int (*dma_rw)(void *iommu_data, dma_addr_t user_iova,
void *data, size_t count, bool write);
struct iommu_domain *(*group_iommu_domain)(void *iommu_data,
struct iommu_group *group);
void (*notify)(void *iommu_data,
enum vfio_iommu_notify_type event);
};
extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
extern void vfio_unregister_iommu_driver(
const struct vfio_iommu_driver_ops *ops);
vfio: add external user support VFIO is designed to be used via ioctls on file descriptors returned by VFIO. However in some situations support for an external user is required. The first user is KVM on PPC64 (SPAPR TCE protocol) which is going to use the existing VFIO groups for exclusive access in real/virtual mode on a host to avoid passing map/unmap requests to the user space which would made things pretty slow. The protocol includes: 1. do normal VFIO init operation: - opening a new container; - attaching group(s) to it; - setting an IOMMU driver for a container. When IOMMU is set for a container, all groups in it are considered ready to use by an external user. 2. User space passes a group fd to an external user. The external user calls vfio_group_get_external_user() to verify that: - the group is initialized; - IOMMU is set for it. If both checks passed, vfio_group_get_external_user() increments the container user counter to prevent the VFIO group from disposal before KVM exits. 3. The external user calls vfio_external_user_iommu_id() to know an IOMMU ID. PPC64 KVM uses it to link logical bus number (LIOBN) with IOMMU ID. 4. When the external KVM finishes, it calls vfio_group_put_external_user() to release the VFIO group. This call decrements the container user counter. Everything gets released. The "vfio: Limit group opens" patch is also required for the consistency. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2013-08-05 20:52:36 +04:00
/*
* External user API
*/
extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
extern void vfio_group_put_external_user(struct vfio_group *group);
extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device
*dev);
extern bool vfio_external_group_match_file(struct vfio_group *group,
struct file *filep);
vfio: add external user support VFIO is designed to be used via ioctls on file descriptors returned by VFIO. However in some situations support for an external user is required. The first user is KVM on PPC64 (SPAPR TCE protocol) which is going to use the existing VFIO groups for exclusive access in real/virtual mode on a host to avoid passing map/unmap requests to the user space which would made things pretty slow. The protocol includes: 1. do normal VFIO init operation: - opening a new container; - attaching group(s) to it; - setting an IOMMU driver for a container. When IOMMU is set for a container, all groups in it are considered ready to use by an external user. 2. User space passes a group fd to an external user. The external user calls vfio_group_get_external_user() to verify that: - the group is initialized; - IOMMU is set for it. If both checks passed, vfio_group_get_external_user() increments the container user counter to prevent the VFIO group from disposal before KVM exits. 3. The external user calls vfio_external_user_iommu_id() to know an IOMMU ID. PPC64 KVM uses it to link logical bus number (LIOBN) with IOMMU ID. 4. When the external KVM finishes, it calls vfio_group_put_external_user() to release the VFIO group. This call decrements the container user counter. Everything gets released. The "vfio: Limit group opens" patch is also required for the consistency. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2013-08-05 20:52:36 +04:00
extern int vfio_external_user_iommu_id(struct vfio_group *group);
extern long vfio_external_check_extension(struct vfio_group *group,
unsigned long arg);
vfio: add external user support VFIO is designed to be used via ioctls on file descriptors returned by VFIO. However in some situations support for an external user is required. The first user is KVM on PPC64 (SPAPR TCE protocol) which is going to use the existing VFIO groups for exclusive access in real/virtual mode on a host to avoid passing map/unmap requests to the user space which would made things pretty slow. The protocol includes: 1. do normal VFIO init operation: - opening a new container; - attaching group(s) to it; - setting an IOMMU driver for a container. When IOMMU is set for a container, all groups in it are considered ready to use by an external user. 2. User space passes a group fd to an external user. The external user calls vfio_group_get_external_user() to verify that: - the group is initialized; - IOMMU is set for it. If both checks passed, vfio_group_get_external_user() increments the container user counter to prevent the VFIO group from disposal before KVM exits. 3. The external user calls vfio_external_user_iommu_id() to know an IOMMU ID. PPC64 KVM uses it to link logical bus number (LIOBN) with IOMMU ID. 4. When the external KVM finishes, it calls vfio_group_put_external_user() to release the VFIO group. This call decrements the container user counter. Everything gets released. The "vfio: Limit group opens" patch is also required for the consistency. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2013-08-05 20:52:36 +04:00
#define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long))
extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
int npage, int prot, unsigned long *phys_pfn);
extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
int npage);
extern int vfio_group_pin_pages(struct vfio_group *group,
unsigned long *user_iova_pfn, int npage,
int prot, unsigned long *phys_pfn);
extern int vfio_group_unpin_pages(struct vfio_group *group,
unsigned long *user_iova_pfn, int npage);
extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
void *data, size_t len, bool write);
extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group);
/* each type has independent events */
enum vfio_notify_type {
VFIO_IOMMU_NOTIFY = 0,
VFIO_GROUP_NOTIFY = 1,
};
/* events for VFIO_IOMMU_NOTIFY */
#define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0)
/* events for VFIO_GROUP_NOTIFY */
#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0)
extern int vfio_register_notifier(struct device *dev,
enum vfio_notify_type type,
unsigned long *required_events,
struct notifier_block *nb);
extern int vfio_unregister_notifier(struct device *dev,
enum vfio_notify_type type,
struct notifier_block *nb);
struct kvm;
extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm);
/*
* Sub-module helpers
*/
struct vfio_info_cap {
struct vfio_info_cap_header *buf;
size_t size;
};
extern struct vfio_info_cap_header *vfio_info_cap_add(
struct vfio_info_cap *caps, size_t size, u16 id, u16 version);
extern void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset);
extern int vfio_info_add_capability(struct vfio_info_cap *caps,
struct vfio_info_cap_header *cap,
size_t size);
extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr,
int num_irqs, int max_irq_type,
size_t *data_size);
struct pci_dev;
#if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH)
extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
extern void vfio_spapr_pci_eeh_release(struct pci_dev *pdev);
extern long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
unsigned int cmd,
unsigned long arg);
#else
static inline void vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
{
}
static inline void vfio_spapr_pci_eeh_release(struct pci_dev *pdev)
{
}
static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
unsigned int cmd,
unsigned long arg)
{
return -ENOTTY;
}
#endif /* CONFIG_VFIO_SPAPR_EEH */
/*
* IRQfd - generic
*/
struct virqfd {
void *opaque;
struct eventfd_ctx *eventfd;
int (*handler)(void *, void *);
void (*thread)(void *, void *);
void *data;
struct work_struct inject;
wait_queue_entry_t wait;
poll_table pt;
struct work_struct shutdown;
struct virqfd **pvirqfd;
};
extern int vfio_virqfd_enable(void *opaque,
int (*handler)(void *, void *),
void (*thread)(void *, void *),
void *data, struct virqfd **pvirqfd, int fd);
extern void vfio_virqfd_disable(struct virqfd **pvirqfd);
#endif /* VFIO_H */