vfio: VFIO core

VFIO is a secure user level driver for use with both virtual machines
and user level drivers.  VFIO makes use of IOMMU groups to ensure the
isolation of devices in use, allowing unprivileged user access.  It's
intended that VFIO will replace KVM device assignment and UIO drivers
(in cases where the target platform includes a sufficiently capable
IOMMU).

New in this version of VFIO is support for IOMMU groups managed
through the IOMMU core as well as a rework of the API, removing the
group merge interface.  We now go back to a model more similar to
original VFIO with UIOMMU support where the file descriptor obtained
from /dev/vfio/vfio allows access to the IOMMU, but only after a
group is added, avoiding the previous privilege issues with this type
of model.  IOMMU support is also now fully modular as IOMMUs have
vastly different interface requirements on different platforms.  VFIO
users are able to query and initialize the IOMMU model of their
choice.

Please see the follow-on Documentation commit for further description
and usage example.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 367 insertions, 0 deletions

diff --git a/include/linux/vfio.h b/include/linux/vfio.h
new file mode 100644
index 000000000000..03e56a5154b6
--- /dev/null
+++ b/include/linux/vfio.h
@@ -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 */