virtio_pci.c 19.1 KB
Newer Older
A
Anthony Liguori 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
/*
 * Virtio PCI driver
 *
 * This module allows virtio devices to be used over a virtual PCI device.
 * This can be used with QEMU based VMMs like KVM or Xen.
 *
 * Copyright IBM Corp. 2007
 *
 * Authors:
 *  Anthony Liguori  <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include <linux/module.h>
#include <linux/list.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_pci.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>

MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
MODULE_DESCRIPTION("virtio-pci");
MODULE_LICENSE("GPL");
MODULE_VERSION("1");

/* Our device structure */
struct virtio_pci_device
{
	struct virtio_device vdev;
	struct pci_dev *pci_dev;

	/* the IO mapping for the PCI config space */
A
Al Viro 已提交
40
	void __iomem *ioaddr;
A
Anthony Liguori 已提交
41 42 43 44

	/* a list of queues so we can dispatch IRQs */
	spinlock_t lock;
	struct list_head virtqueues;
45 46 47 48 49 50 51 52 53 54

	/* MSI-X support */
	int msix_enabled;
	int intx_enabled;
	struct msix_entry *msix_entries;
	/* Name strings for interrupts. This size should be enough,
	 * and I'm too lazy to allocate each name separately. */
	char (*msix_names)[256];
	/* Number of available vectors */
	unsigned msix_vectors;
M
Michael S. Tsirkin 已提交
55
	/* Vectors allocated, excluding per-vq vectors if any */
56
	unsigned msix_used_vectors;
M
Michael S. Tsirkin 已提交
57 58
	/* Whether we have vector per vq */
	bool per_vq_vectors;
59 60 61 62 63 64 65 66
};

/* Constants for MSI-X */
/* Use first vector for configuration changes, second and the rest for
 * virtqueues Thus, we need at least 2 vectors for MSI. */
enum {
	VP_MSIX_CONFIG_VECTOR = 0,
	VP_MSIX_VQ_VECTOR = 1,
A
Anthony Liguori 已提交
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
};

struct virtio_pci_vq_info
{
	/* the actual virtqueue */
	struct virtqueue *vq;

	/* the number of entries in the queue */
	int num;

	/* the index of the queue */
	int queue_index;

	/* the virtual address of the ring queue */
	void *queue;

	/* the list node for the virtqueues list */
	struct list_head node;
85 86 87

	/* MSI-X vector (or none) */
	unsigned vector;
A
Anthony Liguori 已提交
88 89 90 91 92 93 94 95 96 97 98 99 100
};

/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
static struct pci_device_id virtio_pci_id_table[] = {
	{ 0x1af4, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
	{ 0 },
};

MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);

/* A PCI device has it's own struct device and so does a virtio device so
 * we create a place for the virtio devices to show up in sysfs.  I think it
 * would make more sense for virtio to not insist on having it's own device. */
101
static struct device *virtio_pci_root;
A
Anthony Liguori 已提交
102 103 104 105 106 107 108

/* Convert a generic virtio device to our structure */
static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
{
	return container_of(vdev, struct virtio_pci_device, vdev);
}

109 110 111 112 113 114 115 116 117 118
/* virtio config->get_features() implementation */
static u32 vp_get_features(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	/* When someone needs more than 32 feature bits, we'll need to
	 * steal a bit to indicate that the rest are somewhere else. */
	return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
}

119 120
/* virtio config->finalize_features() implementation */
static void vp_finalize_features(struct virtio_device *vdev)
A
Anthony Liguori 已提交
121 122 123
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

124 125 126
	/* Give virtio_ring a chance to accept features. */
	vring_transport_features(vdev);

127 128 129
	/* We only support 32 feature bits. */
	BUILD_BUG_ON(ARRAY_SIZE(vdev->features) != 1);
	iowrite32(vdev->features[0], vp_dev->ioaddr+VIRTIO_PCI_GUEST_FEATURES);
A
Anthony Liguori 已提交
130 131 132 133 134 135 136
}

/* virtio config->get() implementation */
static void vp_get(struct virtio_device *vdev, unsigned offset,
		   void *buf, unsigned len)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
137 138
	void __iomem *ioaddr = vp_dev->ioaddr +
				VIRTIO_PCI_CONFIG(vp_dev) + offset;
A
Anthony Liguori 已提交
139 140 141 142 143 144 145 146 147 148 149 150 151
	u8 *ptr = buf;
	int i;

	for (i = 0; i < len; i++)
		ptr[i] = ioread8(ioaddr + i);
}

/* the config->set() implementation.  it's symmetric to the config->get()
 * implementation */
static void vp_set(struct virtio_device *vdev, unsigned offset,
		   const void *buf, unsigned len)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
152 153
	void __iomem *ioaddr = vp_dev->ioaddr +
				VIRTIO_PCI_CONFIG(vp_dev) + offset;
A
Anthony Liguori 已提交
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
	const u8 *ptr = buf;
	int i;

	for (i = 0; i < len; i++)
		iowrite8(ptr[i], ioaddr + i);
}

/* config->{get,set}_status() implementations */
static u8 vp_get_status(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
}

static void vp_set_status(struct virtio_device *vdev, u8 status)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	/* We should never be setting status to 0. */
	BUG_ON(status == 0);
173
	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
A
Anthony Liguori 已提交
174 175 176 177 178 179
}

static void vp_reset(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	/* 0 status means a reset. */
180
	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
A
Anthony Liguori 已提交
181 182 183 184 185 186 187 188 189 190 191 192 193
}

/* the notify function used when creating a virt queue */
static void vp_notify(struct virtqueue *vq)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_vq_info *info = vq->priv;

	/* we write the queue's selector into the notification register to
	 * signal the other end */
	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
}

194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224
/* Handle a configuration change: Tell driver if it wants to know. */
static irqreturn_t vp_config_changed(int irq, void *opaque)
{
	struct virtio_pci_device *vp_dev = opaque;
	struct virtio_driver *drv;
	drv = container_of(vp_dev->vdev.dev.driver,
			   struct virtio_driver, driver);

	if (drv && drv->config_changed)
		drv->config_changed(&vp_dev->vdev);
	return IRQ_HANDLED;
}

/* Notify all virtqueues on an interrupt. */
static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
{
	struct virtio_pci_device *vp_dev = opaque;
	struct virtio_pci_vq_info *info;
	irqreturn_t ret = IRQ_NONE;
	unsigned long flags;

	spin_lock_irqsave(&vp_dev->lock, flags);
	list_for_each_entry(info, &vp_dev->virtqueues, node) {
		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
			ret = IRQ_HANDLED;
	}
	spin_unlock_irqrestore(&vp_dev->lock, flags);

	return ret;
}

A
Anthony Liguori 已提交
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
/* A small wrapper to also acknowledge the interrupt when it's handled.
 * I really need an EIO hook for the vring so I can ack the interrupt once we
 * know that we'll be handling the IRQ but before we invoke the callback since
 * the callback may notify the host which results in the host attempting to
 * raise an interrupt that we would then mask once we acknowledged the
 * interrupt. */
static irqreturn_t vp_interrupt(int irq, void *opaque)
{
	struct virtio_pci_device *vp_dev = opaque;
	u8 isr;

	/* reading the ISR has the effect of also clearing it so it's very
	 * important to save off the value. */
	isr = ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);

	/* It's definitely not us if the ISR was not high */
	if (!isr)
		return IRQ_NONE;

	/* Configuration change?  Tell driver if it wants to know. */
245 246
	if (isr & VIRTIO_PCI_ISR_CONFIG)
		vp_config_changed(irq, opaque);
A
Anthony Liguori 已提交
247

248
	return vp_vring_interrupt(irq, opaque);
A
Anthony Liguori 已提交
249 250
}

251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271
static void vp_free_vectors(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	int i;

	if (vp_dev->intx_enabled) {
		free_irq(vp_dev->pci_dev->irq, vp_dev);
		vp_dev->intx_enabled = 0;
	}

	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
		free_irq(vp_dev->msix_entries[i].vector, vp_dev);

	if (vp_dev->msix_enabled) {
		/* Disable the vector used for configuration */
		iowrite16(VIRTIO_MSI_NO_VECTOR,
			  vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
		/* Flush the write out to device */
		ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);

		pci_disable_msix(vp_dev->pci_dev);
272 273
		vp_dev->msix_enabled = 0;
		vp_dev->msix_vectors = 0;
274
	}
275 276 277 278 279 280

	vp_dev->msix_used_vectors = 0;
	kfree(vp_dev->msix_names);
	vp_dev->msix_names = NULL;
	kfree(vp_dev->msix_entries);
	vp_dev->msix_entries = NULL;
281 282
}

M
Michael S. Tsirkin 已提交
283 284
static int vp_request_vectors(struct virtio_device *vdev, int nvectors,
			      bool per_vq_vectors)
285 286 287 288 289
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	const char *name = dev_name(&vp_dev->vdev.dev);
	unsigned i, v;
	int err = -ENOMEM;
M
Michael S. Tsirkin 已提交
290 291 292 293 294 295 296 297 298 299 300

	if (!nvectors) {
		/* Can't allocate MSI-X vectors, use regular interrupt */
		vp_dev->msix_vectors = 0;
		err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
				  IRQF_SHARED, name, vp_dev);
		if (err)
			return err;
		vp_dev->intx_enabled = 1;
		return 0;
	}
301 302 303 304

	vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
				       GFP_KERNEL);
	if (!vp_dev->msix_entries)
305
		goto error;
306 307 308
	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
				     GFP_KERNEL);
	if (!vp_dev->msix_names)
309
		goto error;
310 311 312 313

	for (i = 0; i < nvectors; ++i)
		vp_dev->msix_entries[i].entry = i;

M
Michael S. Tsirkin 已提交
314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
	err = pci_enable_msix(vp_dev->pci_dev, vp_dev->msix_entries, nvectors);
	if (err > 0)
		err = -ENOSPC;
	if (err)
		goto error;
	vp_dev->msix_vectors = nvectors;
	vp_dev->msix_enabled = 1;

	/* Set the vector used for configuration */
	v = vp_dev->msix_used_vectors;
	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
		 "%s-config", name);
	err = request_irq(vp_dev->msix_entries[v].vector,
			  vp_config_changed, 0, vp_dev->msix_names[v],
			  vp_dev);
	if (err)
		goto error;
	++vp_dev->msix_used_vectors;
332

M
Michael S. Tsirkin 已提交
333 334 335 336 337 338
	iowrite16(v, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
	/* Verify we had enough resources to assign the vector */
	v = ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
	if (v == VIRTIO_MSI_NO_VECTOR) {
		err = -EBUSY;
		goto error;
339 340
	}

M
Michael S. Tsirkin 已提交
341
	if (!per_vq_vectors) {
342 343 344 345 346 347 348 349
		/* Shared vector for all VQs */
		v = vp_dev->msix_used_vectors;
		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
			 "%s-virtqueues", name);
		err = request_irq(vp_dev->msix_entries[v].vector,
				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
				  vp_dev);
		if (err)
350
			goto error;
351 352 353
		++vp_dev->msix_used_vectors;
	}
	return 0;
354
error:
355 356 357 358
	vp_free_vectors(vdev);
	return err;
}

A
Anthony Liguori 已提交
359
static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
360
				    void (*callback)(struct virtqueue *vq),
M
Michael S. Tsirkin 已提交
361 362
				    const char *name,
				    u16 vector)
A
Anthony Liguori 已提交
363 364 365 366
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_vq_info *info;
	struct virtqueue *vq;
367
	unsigned long flags, size;
M
Michael S. Tsirkin 已提交
368
	u16 num;
A
Anthony Liguori 已提交
369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386
	int err;

	/* Select the queue we're interested in */
	iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);

	/* Check if queue is either not available or already active. */
	num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
		return ERR_PTR(-ENOENT);

	/* allocate and fill out our structure the represents an active
	 * queue */
	info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
	if (!info)
		return ERR_PTR(-ENOMEM);

	info->queue_index = index;
	info->num = num;
M
Michael S. Tsirkin 已提交
387
	info->vector = vector;
A
Anthony Liguori 已提交
388

389
	size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
390
	info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
A
Anthony Liguori 已提交
391 392 393 394 395 396
	if (info->queue == NULL) {
		err = -ENOMEM;
		goto out_info;
	}

	/* activate the queue */
397
	iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
A
Anthony Liguori 已提交
398 399 400
		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);

	/* create the vring */
401
	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN,
402
				 vdev, info->queue, vp_notify, callback, name);
A
Anthony Liguori 已提交
403 404 405 406 407 408 409 410
	if (!vq) {
		err = -ENOMEM;
		goto out_activate_queue;
	}

	vq->priv = info;
	info->vq = vq;

M
Michael S. Tsirkin 已提交
411
	 if (vector != VIRTIO_MSI_NO_VECTOR) {
412 413 414 415 416 417 418 419
		iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
		vector = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
		if (vector == VIRTIO_MSI_NO_VECTOR) {
			err = -EBUSY;
			goto out_assign;
		}
	}

420
	spin_lock_irqsave(&vp_dev->lock, flags);
A
Anthony Liguori 已提交
421
	list_add(&info->node, &vp_dev->virtqueues);
422
	spin_unlock_irqrestore(&vp_dev->lock, flags);
A
Anthony Liguori 已提交
423 424 425

	return vq;

426 427
out_assign:
	vring_del_virtqueue(vq);
A
Anthony Liguori 已提交
428 429
out_activate_queue:
	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
430
	free_pages_exact(info->queue, size);
A
Anthony Liguori 已提交
431 432 433 434 435 436 437 438 439
out_info:
	kfree(info);
	return ERR_PTR(err);
}

static void vp_del_vq(struct virtqueue *vq)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_vq_info *info = vq->priv;
M
Michael S. Tsirkin 已提交
440 441 442 443 444
	unsigned long flags, size;

	spin_lock_irqsave(&vp_dev->lock, flags);
	list_del(&info->node);
	spin_unlock_irqrestore(&vp_dev->lock, flags);
A
Anthony Liguori 已提交
445

446 447 448 449 450 451 452 453 454
	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);

	if (vp_dev->msix_enabled) {
		iowrite16(VIRTIO_MSI_NO_VECTOR,
			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
		/* Flush the write out to device */
		ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
	}

A
Anthony Liguori 已提交
455 456 457 458 459
	vring_del_virtqueue(vq);

	/* Select and deactivate the queue */
	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);

460
	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
461
	free_pages_exact(info->queue, size);
A
Anthony Liguori 已提交
462 463 464
	kfree(info);
}

465
/* the config->del_vqs() implementation */
466 467
static void vp_del_vqs(struct virtio_device *vdev)
{
M
Michael S. Tsirkin 已提交
468
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
469
	struct virtqueue *vq, *n;
M
Michael S. Tsirkin 已提交
470
	struct virtio_pci_vq_info *info;
471

M
Michael S. Tsirkin 已提交
472 473 474 475
	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
		info = vq->priv;
		if (vp_dev->per_vq_vectors)
			free_irq(vp_dev->msix_entries[info->vector].vector, vq);
476
		vp_del_vq(vq);
M
Michael S. Tsirkin 已提交
477 478
	}
	vp_dev->per_vq_vectors = false;
479 480

	vp_free_vectors(vdev);
481 482
}

M
Michael S. Tsirkin 已提交
483 484 485 486 487 488
static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
			      struct virtqueue *vqs[],
			      vq_callback_t *callbacks[],
			      const char *names[],
			      int nvectors,
			      bool per_vq_vectors)
489
{
M
Michael S. Tsirkin 已提交
490 491 492
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u16 vector;
	int i, err, allocated_vectors;
493

M
Michael S. Tsirkin 已提交
494
	err = vp_request_vectors(vdev, nvectors, per_vq_vectors);
495 496
	if (err)
		goto error_request;
497

M
Michael S. Tsirkin 已提交
498 499
	vp_dev->per_vq_vectors = per_vq_vectors;
	allocated_vectors = vp_dev->msix_used_vectors;
500
	for (i = 0; i < nvqs; ++i) {
M
Michael S. Tsirkin 已提交
501 502 503 504 505 506 507 508 509
		if (!callbacks[i] || !vp_dev->msix_enabled)
			vector = VIRTIO_MSI_NO_VECTOR;
		else if (vp_dev->per_vq_vectors)
			vector = allocated_vectors++;
		else
			vector = VP_MSIX_VQ_VECTOR;
		vqs[i] = vp_find_vq(vdev, i, callbacks[i], names[i], vector);
		if (IS_ERR(vqs[i])) {
			err = PTR_ERR(vqs[i]);
510
			goto error_find;
M
Michael S. Tsirkin 已提交
511 512 513 514 515 516 517 518 519 520 521 522 523
		}
		/* allocate per-vq irq if available and necessary */
		if (vp_dev->per_vq_vectors && vector != VIRTIO_MSI_NO_VECTOR) {
			snprintf(vp_dev->msix_names[vector], sizeof *vp_dev->msix_names,
				 "%s-%s", dev_name(&vp_dev->vdev.dev), names[i]);
			err = request_irq(vp_dev->msix_entries[vector].vector,
					  vring_interrupt, 0,
					  vp_dev->msix_names[vector], vqs[i]);
			if (err) {
				vp_del_vq(vqs[i]);
				goto error_find;
			}
		}
524 525 526
	}
	return 0;

527
error_find:
528
	vp_del_vqs(vdev);
529 530

error_request:
M
Michael S. Tsirkin 已提交
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
	return err;
}

/* the config->find_vqs() implementation */
static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
		       struct virtqueue *vqs[],
		       vq_callback_t *callbacks[],
		       const char *names[])
{
	int vectors = 0;
	int i, uninitialized_var(err);

	/* How many vectors would we like? */
	for (i = 0; i < nvqs; ++i)
		if (callbacks[i])
			++vectors;

	/* We want at most one vector per queue and one for config changes. */
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				 vectors + 1, true);
	if (!err)
		return 0;
	/* Fallback to separate vectors for config and a shared for queues. */
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				 2, false);
	if (!err)
		return 0;
	/* Finally fall back to regular interrupts. */
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				 0, false);
	return err;
562 563
}

A
Anthony Liguori 已提交
564 565 566 567 568 569
static struct virtio_config_ops virtio_pci_config_ops = {
	.get		= vp_get,
	.set		= vp_set,
	.get_status	= vp_get_status,
	.set_status	= vp_set_status,
	.reset		= vp_reset,
570 571
	.find_vqs	= vp_find_vqs,
	.del_vqs	= vp_del_vqs,
572
	.get_features	= vp_get_features,
573
	.finalize_features = vp_finalize_features,
A
Anthony Liguori 已提交
574 575
};

576 577 578 579 580 581
static void virtio_pci_release_dev(struct device *_d)
{
	struct virtio_device *dev = container_of(_d, struct virtio_device, dev);
	struct virtio_pci_device *vp_dev = to_vp_device(dev);
	struct pci_dev *pci_dev = vp_dev->pci_dev;

582
	vp_del_vqs(dev);
583 584 585 586 587 588 589
	pci_set_drvdata(pci_dev, NULL);
	pci_iounmap(pci_dev, vp_dev->ioaddr);
	pci_release_regions(pci_dev);
	pci_disable_device(pci_dev);
	kfree(vp_dev);
}

A
Anthony Liguori 已提交
590 591 592 593 594 595 596 597 598 599 600
/* the PCI probing function */
static int __devinit virtio_pci_probe(struct pci_dev *pci_dev,
				      const struct pci_device_id *id)
{
	struct virtio_pci_device *vp_dev;
	int err;

	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
		return -ENODEV;

601 602 603 604 605 606
	if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
		printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
		       VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
		return -ENODEV;
	}

A
Anthony Liguori 已提交
607 608 609 610 611
	/* allocate our structure and fill it out */
	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
	if (vp_dev == NULL)
		return -ENOMEM;

612
	vp_dev->vdev.dev.parent = virtio_pci_root;
613
	vp_dev->vdev.dev.release = virtio_pci_release_dev;
A
Anthony Liguori 已提交
614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643
	vp_dev->vdev.config = &virtio_pci_config_ops;
	vp_dev->pci_dev = pci_dev;
	INIT_LIST_HEAD(&vp_dev->virtqueues);
	spin_lock_init(&vp_dev->lock);

	/* enable the device */
	err = pci_enable_device(pci_dev);
	if (err)
		goto out;

	err = pci_request_regions(pci_dev, "virtio-pci");
	if (err)
		goto out_enable_device;

	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
	if (vp_dev->ioaddr == NULL)
		goto out_req_regions;

	pci_set_drvdata(pci_dev, vp_dev);

	/* we use the subsystem vendor/device id as the virtio vendor/device
	 * id.  this allows us to use the same PCI vendor/device id for all
	 * virtio devices and to identify the particular virtio driver by
	 * the subsytem ids */
	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
	vp_dev->vdev.id.device = pci_dev->subsystem_device;

	/* finally register the virtio device */
	err = register_virtio_device(&vp_dev->vdev);
	if (err)
644
		goto out_set_drvdata;
A
Anthony Liguori 已提交
645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663

	return 0;

out_set_drvdata:
	pci_set_drvdata(pci_dev, NULL);
	pci_iounmap(pci_dev, vp_dev->ioaddr);
out_req_regions:
	pci_release_regions(pci_dev);
out_enable_device:
	pci_disable_device(pci_dev);
out:
	kfree(vp_dev);
	return err;
}

static void __devexit virtio_pci_remove(struct pci_dev *pci_dev)
{
	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);

664
	unregister_virtio_device(&vp_dev->vdev);
A
Anthony Liguori 已提交
665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697
}

#ifdef CONFIG_PM
static int virtio_pci_suspend(struct pci_dev *pci_dev, pm_message_t state)
{
	pci_save_state(pci_dev);
	pci_set_power_state(pci_dev, PCI_D3hot);
	return 0;
}

static int virtio_pci_resume(struct pci_dev *pci_dev)
{
	pci_restore_state(pci_dev);
	pci_set_power_state(pci_dev, PCI_D0);
	return 0;
}
#endif

static struct pci_driver virtio_pci_driver = {
	.name		= "virtio-pci",
	.id_table	= virtio_pci_id_table,
	.probe		= virtio_pci_probe,
	.remove		= virtio_pci_remove,
#ifdef CONFIG_PM
	.suspend	= virtio_pci_suspend,
	.resume		= virtio_pci_resume,
#endif
};

static int __init virtio_pci_init(void)
{
	int err;

698 699 700
	virtio_pci_root = root_device_register("virtio-pci");
	if (IS_ERR(virtio_pci_root))
		return PTR_ERR(virtio_pci_root);
A
Anthony Liguori 已提交
701 702 703

	err = pci_register_driver(&virtio_pci_driver);
	if (err)
704
		root_device_unregister(virtio_pci_root);
A
Anthony Liguori 已提交
705 706 707 708 709 710 711 712 713

	return err;
}

module_init(virtio_pci_init);

static void __exit virtio_pci_exit(void)
{
	pci_unregister_driver(&virtio_pci_driver);
714
	root_device_unregister(virtio_pci_root);
A
Anthony Liguori 已提交
715 716 717
}

module_exit(virtio_pci_exit);