|
|
|
|
@ -0,0 +1,367 @@
|
|
|
|
|
/*
|
|
|
|
|
* VFIO API definition
|
|
|
|
|
*
|
|
|
|
|
* 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.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef VFIO_H
|
|
|
|
|
#define VFIO_H
|
|
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
|
#include <linux/ioctl.h>
|
|
|
|
|
|
|
|
|
|
#define VFIO_API_VERSION 0
|
|
|
|
|
|
|
|
|
|
#ifdef __KERNEL__ /* Internal VFIO-core/bus driver API */
|
|
|
|
|
|
|
|
|
|
#include <linux/iommu.h>
|
|
|
|
|
#include <linux/mm.h>
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* struct vfio_device_ops - VFIO bus driver device callbacks
|
|
|
|
|
*
|
|
|
|
|
* @open: Called when userspace creates new file descriptor for device
|
|
|
|
|
* @release: Called when userspace releases file descriptor for 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
|
|
|
|
|
*/
|
|
|
|
|
struct vfio_device_ops {
|
|
|
|
|
char *name;
|
|
|
|
|
int (*open)(void *device_data);
|
|
|
|
|
void (*release)(void *device_data);
|
|
|
|
|
ssize_t (*read)(void *device_data, char __user *buf,
|
|
|
|
|
size_t count, loff_t *ppos);
|
|
|
|
|
ssize_t (*write)(void *device_data, const char __user *buf,
|
|
|
|
|
size_t count, loff_t *size);
|
|
|
|
|
long (*ioctl)(void *device_data, unsigned int cmd,
|
|
|
|
|
unsigned long arg);
|
|
|
|
|
int (*mmap)(void *device_data, struct vm_area_struct *vma);
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
extern int vfio_add_group_dev(struct device *dev,
|
|
|
|
|
const struct vfio_device_ops *ops,
|
|
|
|
|
void *device_data);
|
|
|
|
|
|
|
|
|
|
extern void *vfio_del_group_dev(struct device *dev);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* 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);
|
|
|
|
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
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);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* offsetofend(TYPE, MEMBER)
|
|
|
|
|
*
|
|
|
|
|
* @TYPE: The type of the structure
|
|
|
|
|
* @MEMBER: The member within the structure to get the end offset of
|
|
|
|
|
*
|
|
|
|
|
* Simple helper macro for dealing with variable sized structures passed
|
|
|
|
|
* from user space. This allows us to easily determine if the provided
|
|
|
|
|
* structure is sized to include various fields.
|
|
|
|
|
*/
|
|
|
|
|
#define offsetofend(TYPE, MEMBER) ({ \
|
|
|
|
|
TYPE tmp; \
|
|
|
|
|
offsetof(TYPE, MEMBER) + sizeof(tmp.MEMBER); }) \
|
|
|
|
|
|
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
|
|
|
|
|
/* Kernel & User level defines for VFIO IOCTLs. */
|
|
|
|
|
|
|
|
|
|
/* Extensions */
|
|
|
|
|
|
|
|
|
|
/* None yet */
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The IOCTL interface is designed for extensibility by embedding the
|
|
|
|
|
* structure length (argsz) and flags into structures passed between
|
|
|
|
|
* kernel and userspace. We therefore use the _IO() macro for these
|
|
|
|
|
* defines to avoid implicitly embedding a size into the ioctl request.
|
|
|
|
|
* As structure fields are added, argsz will increase to match and flag
|
|
|
|
|
* bits will be defined to indicate additional fields with valid data.
|
|
|
|
|
* It's *always* the caller's responsibility to indicate the size of
|
|
|
|
|
* the structure passed by setting argsz appropriately.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define VFIO_TYPE (';')
|
|
|
|
|
#define VFIO_BASE 100
|
|
|
|
|
|
|
|
|
|
/* -------- IOCTLs for VFIO file descriptor (/dev/vfio/vfio) -------- */
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_GET_API_VERSION - _IO(VFIO_TYPE, VFIO_BASE + 0)
|
|
|
|
|
*
|
|
|
|
|
* Report the version of the VFIO API. This allows us to bump the entire
|
|
|
|
|
* API version should we later need to add or change features in incompatible
|
|
|
|
|
* ways.
|
|
|
|
|
* Return: VFIO_API_VERSION
|
|
|
|
|
* Availability: Always
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_GET_API_VERSION _IO(VFIO_TYPE, VFIO_BASE + 0)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_CHECK_EXTENSION - _IOW(VFIO_TYPE, VFIO_BASE + 1, __u32)
|
|
|
|
|
*
|
|
|
|
|
* Check whether an extension is supported.
|
|
|
|
|
* Return: 0 if not supported, 1 (or some other positive integer) if supported.
|
|
|
|
|
* Availability: Always
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_CHECK_EXTENSION _IO(VFIO_TYPE, VFIO_BASE + 1)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_SET_IOMMU - _IOW(VFIO_TYPE, VFIO_BASE + 2, __s32)
|
|
|
|
|
*
|
|
|
|
|
* Set the iommu to the given type. The type must be supported by an
|
|
|
|
|
* iommu driver as verified by calling CHECK_EXTENSION using the same
|
|
|
|
|
* type. A group must be set to this file descriptor before this
|
|
|
|
|
* ioctl is available. The IOMMU interfaces enabled by this call are
|
|
|
|
|
* specific to the value set.
|
|
|
|
|
* Return: 0 on success, -errno on failure
|
|
|
|
|
* Availability: When VFIO group attached
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_SET_IOMMU _IO(VFIO_TYPE, VFIO_BASE + 2)
|
|
|
|
|
|
|
|
|
|
/* -------- IOCTLs for GROUP file descriptors (/dev/vfio/$GROUP) -------- */
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_GROUP_GET_STATUS - _IOR(VFIO_TYPE, VFIO_BASE + 3,
|
|
|
|
|
* struct vfio_group_status)
|
|
|
|
|
*
|
|
|
|
|
* Retrieve information about the group. Fills in provided
|
|
|
|
|
* struct vfio_group_info. Caller sets argsz.
|
|
|
|
|
* Return: 0 on succes, -errno on failure.
|
|
|
|
|
* Availability: Always
|
|
|
|
|
*/
|
|
|
|
|
struct vfio_group_status {
|
|
|
|
|
__u32 argsz;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
#define VFIO_GROUP_FLAGS_VIABLE (1 << 0)
|
|
|
|
|
#define VFIO_GROUP_FLAGS_CONTAINER_SET (1 << 1)
|
|
|
|
|
};
|
|
|
|
|
#define VFIO_GROUP_GET_STATUS _IO(VFIO_TYPE, VFIO_BASE + 3)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_GROUP_SET_CONTAINER - _IOW(VFIO_TYPE, VFIO_BASE + 4, __s32)
|
|
|
|
|
*
|
|
|
|
|
* Set the container for the VFIO group to the open VFIO file
|
|
|
|
|
* descriptor provided. Groups may only belong to a single
|
|
|
|
|
* container. Containers may, at their discretion, support multiple
|
|
|
|
|
* groups. Only when a container is set are all of the interfaces
|
|
|
|
|
* of the VFIO file descriptor and the VFIO group file descriptor
|
|
|
|
|
* available to the user.
|
|
|
|
|
* Return: 0 on success, -errno on failure.
|
|
|
|
|
* Availability: Always
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_GROUP_SET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 4)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_GROUP_UNSET_CONTAINER - _IO(VFIO_TYPE, VFIO_BASE + 5)
|
|
|
|
|
*
|
|
|
|
|
* Remove the group from the attached container. This is the
|
|
|
|
|
* opposite of the SET_CONTAINER call and returns the group to
|
|
|
|
|
* an initial state. All device file descriptors must be released
|
|
|
|
|
* prior to calling this interface. When removing the last group
|
|
|
|
|
* from a container, the IOMMU will be disabled and all state lost,
|
|
|
|
|
* effectively also returning the VFIO file descriptor to an initial
|
|
|
|
|
* state.
|
|
|
|
|
* Return: 0 on success, -errno on failure.
|
|
|
|
|
* Availability: When attached to container
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_GROUP_UNSET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 5)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_GROUP_GET_DEVICE_FD - _IOW(VFIO_TYPE, VFIO_BASE + 6, char)
|
|
|
|
|
*
|
|
|
|
|
* Return a new file descriptor for the device object described by
|
|
|
|
|
* the provided string. The string should match a device listed in
|
|
|
|
|
* the devices subdirectory of the IOMMU group sysfs entry. The
|
|
|
|
|
* group containing the device must already be added to this context.
|
|
|
|
|
* Return: new file descriptor on success, -errno on failure.
|
|
|
|
|
* Availability: When attached to container
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_GROUP_GET_DEVICE_FD _IO(VFIO_TYPE, VFIO_BASE + 6)
|
|
|
|
|
|
|
|
|
|
/* --------------- IOCTLs for DEVICE file descriptors --------------- */
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_DEVICE_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 7,
|
|
|
|
|
* struct vfio_device_info)
|
|
|
|
|
*
|
|
|
|
|
* Retrieve information about the device. Fills in provided
|
|
|
|
|
* struct vfio_device_info. Caller sets argsz.
|
|
|
|
|
* Return: 0 on success, -errno on failure.
|
|
|
|
|
*/
|
|
|
|
|
struct vfio_device_info {
|
|
|
|
|
__u32 argsz;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
#define VFIO_DEVICE_FLAGS_RESET (1 << 0) /* Device supports reset */
|
|
|
|
|
__u32 num_regions; /* Max region index + 1 */
|
|
|
|
|
__u32 num_irqs; /* Max IRQ index + 1 */
|
|
|
|
|
};
|
|
|
|
|
#define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
|
|
|
|
|
* struct vfio_region_info)
|
|
|
|
|
*
|
|
|
|
|
* Retrieve information about a device region. Caller provides
|
|
|
|
|
* struct vfio_region_info with index value set. Caller sets argsz.
|
|
|
|
|
* Implementation of region mapping is bus driver specific. This is
|
|
|
|
|
* intended to describe MMIO, I/O port, as well as bus specific
|
|
|
|
|
* regions (ex. PCI config space). Zero sized regions may be used
|
|
|
|
|
* to describe unimplemented regions (ex. unimplemented PCI BARs).
|
|
|
|
|
* Return: 0 on success, -errno on failure.
|
|
|
|
|
*/
|
|
|
|
|
struct vfio_region_info {
|
|
|
|
|
__u32 argsz;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
#define VFIO_REGION_INFO_FLAG_READ (1 << 0) /* Region supports read */
|
|
|
|
|
#define VFIO_REGION_INFO_FLAG_WRITE (1 << 1) /* Region supports write */
|
|
|
|
|
#define VFIO_REGION_INFO_FLAG_MMAP (1 << 2) /* Region supports mmap */
|
|
|
|
|
__u32 index; /* Region index */
|
|
|
|
|
__u32 resv; /* Reserved for alignment */
|
|
|
|
|
__u64 size; /* Region size (bytes) */
|
|
|
|
|
__u64 offset; /* Region offset from start of device fd */
|
|
|
|
|
};
|
|
|
|
|
#define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
|
|
|
|
|
* struct vfio_irq_info)
|
|
|
|
|
*
|
|
|
|
|
* Retrieve information about a device IRQ. Caller provides
|
|
|
|
|
* struct vfio_irq_info with index value set. Caller sets argsz.
|
|
|
|
|
* Implementation of IRQ mapping is bus driver specific. Indexes
|
|
|
|
|
* using multiple IRQs are primarily intended to support MSI-like
|
|
|
|
|
* interrupt blocks. Zero count irq blocks may be used to describe
|
|
|
|
|
* unimplemented interrupt types.
|
|
|
|
|
*
|
|
|
|
|
* The EVENTFD flag indicates the interrupt index supports eventfd based
|
|
|
|
|
* signaling.
|
|
|
|
|
*
|
|
|
|
|
* The MASKABLE flags indicates the index supports MASK and UNMASK
|
|
|
|
|
* actions described below.
|
|
|
|
|
*
|
|
|
|
|
* AUTOMASKED indicates that after signaling, the interrupt line is
|
|
|
|
|
* automatically masked by VFIO and the user needs to unmask the line
|
|
|
|
|
* to receive new interrupts. This is primarily intended to distinguish
|
|
|
|
|
* level triggered interrupts.
|
|
|
|
|
*
|
|
|
|
|
* The NORESIZE flag indicates that the interrupt lines within the index
|
|
|
|
|
* are setup as a set and new subindexes cannot be enabled without first
|
|
|
|
|
* disabling the entire index. This is used for interrupts like PCI MSI
|
|
|
|
|
* and MSI-X where the driver may only use a subset of the available
|
|
|
|
|
* indexes, but VFIO needs to enable a specific number of vectors
|
|
|
|
|
* upfront. In the case of MSI-X, where the user can enable MSI-X and
|
|
|
|
|
* then add and unmask vectors, it's up to userspace to make the decision
|
|
|
|
|
* whether to allocate the maximum supported number of vectors or tear
|
|
|
|
|
* down setup and incrementally increase the vectors as each is enabled.
|
|
|
|
|
*/
|
|
|
|
|
struct vfio_irq_info {
|
|
|
|
|
__u32 argsz;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
#define VFIO_IRQ_INFO_EVENTFD (1 << 0)
|
|
|
|
|
#define VFIO_IRQ_INFO_MASKABLE (1 << 1)
|
|
|
|
|
#define VFIO_IRQ_INFO_AUTOMASKED (1 << 2)
|
|
|
|
|
#define VFIO_IRQ_INFO_NORESIZE (1 << 3)
|
|
|
|
|
__u32 index; /* IRQ index */
|
|
|
|
|
__u32 count; /* Number of IRQs within this index */
|
|
|
|
|
};
|
|
|
|
|
#define VFIO_DEVICE_GET_IRQ_INFO _IO(VFIO_TYPE, VFIO_BASE + 9)
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_DEVICE_SET_IRQS - _IOW(VFIO_TYPE, VFIO_BASE + 10, struct vfio_irq_set)
|
|
|
|
|
*
|
|
|
|
|
* Set signaling, masking, and unmasking of interrupts. Caller provides
|
|
|
|
|
* struct vfio_irq_set with all fields set. 'start' and 'count' indicate
|
|
|
|
|
* the range of subindexes being specified.
|
|
|
|
|
*
|
|
|
|
|
* The DATA flags specify the type of data provided. If DATA_NONE, the
|
|
|
|
|
* operation performs the specified action immediately on the specified
|
|
|
|
|
* interrupt(s). For example, to unmask AUTOMASKED interrupt [0,0]:
|
|
|
|
|
* flags = (DATA_NONE|ACTION_UNMASK), index = 0, start = 0, count = 1.
|
|
|
|
|
*
|
|
|
|
|
* DATA_BOOL allows sparse support for the same on arrays of interrupts.
|
|
|
|
|
* For example, to mask interrupts [0,1] and [0,3] (but not [0,2]):
|
|
|
|
|
* flags = (DATA_BOOL|ACTION_MASK), index = 0, start = 1, count = 3,
|
|
|
|
|
* data = {1,0,1}
|
|
|
|
|
*
|
|
|
|
|
* DATA_EVENTFD binds the specified ACTION to the provided __s32 eventfd.
|
|
|
|
|
* A value of -1 can be used to either de-assign interrupts if already
|
|
|
|
|
* assigned or skip un-assigned interrupts. For example, to set an eventfd
|
|
|
|
|
* to be trigger for interrupts [0,0] and [0,2]:
|
|
|
|
|
* flags = (DATA_EVENTFD|ACTION_TRIGGER), index = 0, start = 0, count = 3,
|
|
|
|
|
* data = {fd1, -1, fd2}
|
|
|
|
|
* If index [0,1] is previously set, two count = 1 ioctls calls would be
|
|
|
|
|
* required to set [0,0] and [0,2] without changing [0,1].
|
|
|
|
|
*
|
|
|
|
|
* Once a signaling mechanism is set, DATA_BOOL or DATA_NONE can be used
|
|
|
|
|
* with ACTION_TRIGGER to perform kernel level interrupt loopback testing
|
|
|
|
|
* from userspace (ie. simulate hardware triggering).
|
|
|
|
|
*
|
|
|
|
|
* Setting of an event triggering mechanism to userspace for ACTION_TRIGGER
|
|
|
|
|
* enables the interrupt index for the device. Individual subindex interrupts
|
|
|
|
|
* can be disabled using the -1 value for DATA_EVENTFD or the index can be
|
|
|
|
|
* disabled as a whole with: flags = (DATA_NONE|ACTION_TRIGGER), count = 0.
|
|
|
|
|
*
|
|
|
|
|
* Note that ACTION_[UN]MASK specify user->kernel signaling (irqfds) while
|
|
|
|
|
* ACTION_TRIGGER specifies kernel->user signaling.
|
|
|
|
|
*/
|
|
|
|
|
struct vfio_irq_set {
|
|
|
|
|
__u32 argsz;
|
|
|
|
|
__u32 flags;
|
|
|
|
|
#define VFIO_IRQ_SET_DATA_NONE (1 << 0) /* Data not present */
|
|
|
|
|
#define VFIO_IRQ_SET_DATA_BOOL (1 << 1) /* Data is bool (u8) */
|
|
|
|
|
#define VFIO_IRQ_SET_DATA_EVENTFD (1 << 2) /* Data is eventfd (s32) */
|
|
|
|
|
#define VFIO_IRQ_SET_ACTION_MASK (1 << 3) /* Mask interrupt */
|
|
|
|
|
#define VFIO_IRQ_SET_ACTION_UNMASK (1 << 4) /* Unmask interrupt */
|
|
|
|
|
#define VFIO_IRQ_SET_ACTION_TRIGGER (1 << 5) /* Trigger interrupt */
|
|
|
|
|
__u32 index;
|
|
|
|
|
__u32 start;
|
|
|
|
|
__u32 count;
|
|
|
|
|
__u8 data[];
|
|
|
|
|
};
|
|
|
|
|
#define VFIO_DEVICE_SET_IRQS _IO(VFIO_TYPE, VFIO_BASE + 10)
|
|
|
|
|
|
|
|
|
|
#define VFIO_IRQ_SET_DATA_TYPE_MASK (VFIO_IRQ_SET_DATA_NONE | \
|
|
|
|
|
VFIO_IRQ_SET_DATA_BOOL | \
|
|
|
|
|
VFIO_IRQ_SET_DATA_EVENTFD)
|
|
|
|
|
#define VFIO_IRQ_SET_ACTION_TYPE_MASK (VFIO_IRQ_SET_ACTION_MASK | \
|
|
|
|
|
VFIO_IRQ_SET_ACTION_UNMASK | \
|
|
|
|
|
VFIO_IRQ_SET_ACTION_TRIGGER)
|
|
|
|
|
/**
|
|
|
|
|
* VFIO_DEVICE_RESET - _IO(VFIO_TYPE, VFIO_BASE + 11)
|
|
|
|
|
*
|
|
|
|
|
* Reset a device.
|
|
|
|
|
*/
|
|
|
|
|
#define VFIO_DEVICE_RESET _IO(VFIO_TYPE, VFIO_BASE + 11)
|
|
|
|
|
|
|
|
|
|
#endif /* VFIO_H */
|
Alex Williamson