vfio.c 6.1 KB
Newer Older
A
Alex Williamson 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
/*
 * VFIO-KVM bridge pseudo device
 *
 * Copyright (C) 2013 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/errno.h>
#include <linux/file.h>
#include <linux/kvm_host.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
P
Paolo Bonzini 已提交
21
#include "vfio.h"
A
Alex Williamson 已提交
22 23 24 25 26 27 28 29 30

struct kvm_vfio_group {
	struct list_head node;
	struct vfio_group *vfio_group;
};

struct kvm_vfio {
	struct list_head group_list;
	struct mutex lock;
31
	bool noncoherent;
A
Alex Williamson 已提交
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
};

static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
{
	struct vfio_group *vfio_group;
	struct vfio_group *(*fn)(struct file *);

	fn = symbol_get(vfio_group_get_external_user);
	if (!fn)
		return ERR_PTR(-EINVAL);

	vfio_group = fn(filep);

	symbol_put(vfio_group_get_external_user);

	return vfio_group;
}

static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
{
	void (*fn)(struct vfio_group *);

	fn = symbol_get(vfio_group_put_external_user);
	if (!fn)
		return;

	fn(vfio_group);

	symbol_put(vfio_group_put_external_user);
}

63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78
static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
{
	long (*fn)(struct vfio_group *, unsigned long);
	long ret;

	fn = symbol_get(vfio_external_check_extension);
	if (!fn)
		return false;

	ret = fn(vfio_group, VFIO_DMA_CC_IOMMU);

	symbol_put(vfio_external_check_extension);

	return ret > 0;
}

79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94
/*
 * Groups can use the same or different IOMMU domains.  If the same then
 * adding a new group may change the coherency of groups we've previously
 * been told about.  We don't want to care about any of that so we retest
 * each group and bail as soon as we find one that's noncoherent.  This
 * means we only ever [un]register_noncoherent_dma once for the whole device.
 */
static void kvm_vfio_update_coherency(struct kvm_device *dev)
{
	struct kvm_vfio *kv = dev->private;
	bool noncoherent = false;
	struct kvm_vfio_group *kvg;

	mutex_lock(&kv->lock);

	list_for_each_entry(kvg, &kv->group_list, node) {
95 96 97 98
		if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) {
			noncoherent = true;
			break;
		}
99 100 101 102 103 104 105 106 107 108 109 110 111 112
	}

	if (noncoherent != kv->noncoherent) {
		kv->noncoherent = noncoherent;

		if (kv->noncoherent)
			kvm_arch_register_noncoherent_dma(dev->kvm);
		else
			kvm_arch_unregister_noncoherent_dma(dev->kvm);
	}

	mutex_unlock(&kv->lock);
}

A
Alex Williamson 已提交
113 114 115 116 117
static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
{
	struct kvm_vfio *kv = dev->private;
	struct vfio_group *vfio_group;
	struct kvm_vfio_group *kvg;
P
Paul Bolle 已提交
118
	int32_t __user *argp = (int32_t __user *)(unsigned long)arg;
A
Alex Williamson 已提交
119 120 121 122 123 124
	struct fd f;
	int32_t fd;
	int ret;

	switch (attr) {
	case KVM_DEV_VFIO_GROUP_ADD:
P
Paul Bolle 已提交
125
		if (get_user(fd, argp))
A
Alex Williamson 已提交
126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
			return -EFAULT;

		f = fdget(fd);
		if (!f.file)
			return -EBADF;

		vfio_group = kvm_vfio_group_get_external_user(f.file);
		fdput(f);

		if (IS_ERR(vfio_group))
			return PTR_ERR(vfio_group);

		mutex_lock(&kv->lock);

		list_for_each_entry(kvg, &kv->group_list, node) {
			if (kvg->vfio_group == vfio_group) {
				mutex_unlock(&kv->lock);
				kvm_vfio_group_put_external_user(vfio_group);
				return -EEXIST;
			}
		}

		kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
		if (!kvg) {
			mutex_unlock(&kv->lock);
			kvm_vfio_group_put_external_user(vfio_group);
			return -ENOMEM;
		}

		list_add_tail(&kvg->node, &kv->group_list);
		kvg->vfio_group = vfio_group;

158 159
		kvm_arch_start_assignment(dev->kvm);

A
Alex Williamson 已提交
160 161
		mutex_unlock(&kv->lock);

162 163
		kvm_vfio_update_coherency(dev);

A
Alex Williamson 已提交
164 165 166
		return 0;

	case KVM_DEV_VFIO_GROUP_DEL:
P
Paul Bolle 已提交
167
		if (get_user(fd, argp))
A
Alex Williamson 已提交
168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
			return -EFAULT;

		f = fdget(fd);
		if (!f.file)
			return -EBADF;

		vfio_group = kvm_vfio_group_get_external_user(f.file);
		fdput(f);

		if (IS_ERR(vfio_group))
			return PTR_ERR(vfio_group);

		ret = -ENOENT;

		mutex_lock(&kv->lock);

		list_for_each_entry(kvg, &kv->group_list, node) {
			if (kvg->vfio_group != vfio_group)
				continue;

			list_del(&kvg->node);
			kvm_vfio_group_put_external_user(kvg->vfio_group);
			kfree(kvg);
			ret = 0;
			break;
		}

195 196
		kvm_arch_end_assignment(dev->kvm);

A
Alex Williamson 已提交
197 198 199 200
		mutex_unlock(&kv->lock);

		kvm_vfio_group_put_external_user(vfio_group);

201 202
		kvm_vfio_update_coherency(dev);

A
Alex Williamson 已提交
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245
		return ret;
	}

	return -ENXIO;
}

static int kvm_vfio_set_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_VFIO_GROUP:
		return kvm_vfio_set_group(dev, attr->attr, attr->addr);
	}

	return -ENXIO;
}

static int kvm_vfio_has_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_VFIO_GROUP:
		switch (attr->attr) {
		case KVM_DEV_VFIO_GROUP_ADD:
		case KVM_DEV_VFIO_GROUP_DEL:
			return 0;
		}

		break;
	}

	return -ENXIO;
}

static void kvm_vfio_destroy(struct kvm_device *dev)
{
	struct kvm_vfio *kv = dev->private;
	struct kvm_vfio_group *kvg, *tmp;

	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
		kvm_vfio_group_put_external_user(kvg->vfio_group);
		list_del(&kvg->node);
		kfree(kvg);
246
		kvm_arch_end_assignment(dev->kvm);
A
Alex Williamson 已提交
247 248
	}

249 250
	kvm_vfio_update_coherency(dev);

A
Alex Williamson 已提交
251 252 253 254
	kfree(kv);
	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
}

255 256 257 258 259 260 261 262 263 264
static int kvm_vfio_create(struct kvm_device *dev, u32 type);

static struct kvm_device_ops kvm_vfio_ops = {
	.name = "kvm-vfio",
	.create = kvm_vfio_create,
	.destroy = kvm_vfio_destroy,
	.set_attr = kvm_vfio_set_attr,
	.has_attr = kvm_vfio_has_attr,
};

A
Alex Williamson 已提交
265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286
static int kvm_vfio_create(struct kvm_device *dev, u32 type)
{
	struct kvm_device *tmp;
	struct kvm_vfio *kv;

	/* Only one VFIO "device" per VM */
	list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
		if (tmp->ops == &kvm_vfio_ops)
			return -EBUSY;

	kv = kzalloc(sizeof(*kv), GFP_KERNEL);
	if (!kv)
		return -ENOMEM;

	INIT_LIST_HEAD(&kv->group_list);
	mutex_init(&kv->lock);

	dev->private = kv;

	return 0;
}

P
Paolo Bonzini 已提交
287
int kvm_vfio_ops_init(void)
288 289 290
{
	return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
}
291 292 293 294 295

void kvm_vfio_ops_exit(void)
{
	kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO);
}