virtio_pci.c 19.2 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
/*
 * 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>
20
#include <linux/slab.h>
A
Anthony Liguori 已提交
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
#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
41
	void __iomem *ioaddr;
A
Anthony Liguori 已提交
42 43 44 45

	/* a list of queues so we can dispatch IRQs */
	spinlock_t lock;
	struct list_head virtqueues;
46 47 48 49 50 51 52 53 54 55

	/* 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
56
	/* Vectors allocated, excluding per-vq vectors if any */
57
	unsigned msix_used_vectors;
M
Michael S. Tsirkin 已提交
58 59
	/* Whether we have vector per vq */
	bool per_vq_vectors;
60 61 62 63 64 65 66 67
};

/* 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
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
};

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;
86 87

	/* MSI-X vector (or none) */
R
Rusty Russell 已提交
88
	unsigned msix_vector;
A
Anthony Liguori 已提交
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104
};

/* 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);

/* 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);
}

105 106 107 108 109 110 111 112 113 114
/* 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);
}

115 116
/* virtio config->finalize_features() implementation */
static void vp_finalize_features(struct virtio_device *vdev)
A
Anthony Liguori 已提交
117 118 119
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

120 121 122
	/* Give virtio_ring a chance to accept features. */
	vring_transport_features(vdev);

123 124 125
	/* 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
126 127 128 129 130 131 132
}

/* 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);
133 134
	void __iomem *ioaddr = vp_dev->ioaddr +
				VIRTIO_PCI_CONFIG(vp_dev) + offset;
A
Anthony Liguori 已提交
135 136 137 138 139 140 141 142 143 144 145 146 147
	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);
148 149
	void __iomem *ioaddr = vp_dev->ioaddr +
				VIRTIO_PCI_CONFIG(vp_dev) + offset;
A
Anthony Liguori 已提交
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
	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);
169
	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
A
Anthony Liguori 已提交
170 171 172 173 174 175
}

static void vp_reset(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	/* 0 status means a reset. */
176
	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
A
Anthony Liguori 已提交
177 178 179 180 181 182 183 184 185 186 187 188 189
}

/* 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);
}

190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
/* 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
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
/* 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. */
241 242
	if (isr & VIRTIO_PCI_ISR_CONFIG)
		vp_config_changed(irq, opaque);
A
Anthony Liguori 已提交
243

244
	return vp_vring_interrupt(irq, opaque);
A
Anthony Liguori 已提交
245 246
}

247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267
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);
268 269
		vp_dev->msix_enabled = 0;
		vp_dev->msix_vectors = 0;
270
	}
271 272 273 274 275 276

	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;
277 278
}

R
Rusty Russell 已提交
279 280
static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
				   bool per_vq_vectors)
281 282 283 284 285
{
	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
286

287 288 289
	vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
				       GFP_KERNEL);
	if (!vp_dev->msix_entries)
290
		goto error;
291 292 293
	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
				     GFP_KERNEL);
	if (!vp_dev->msix_names)
294
		goto error;
295 296 297 298

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

R
Rusty Russell 已提交
299
	/* pci_enable_msix returns positive if we can't get this many. */
M
Michael S. Tsirkin 已提交
300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317
	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;
318

M
Michael S. Tsirkin 已提交
319 320 321 322 323 324
	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;
325 326
	}

M
Michael S. Tsirkin 已提交
327
	if (!per_vq_vectors) {
328 329 330 331 332 333 334 335
		/* 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)
336
			goto error;
337 338 339
		++vp_dev->msix_used_vectors;
	}
	return 0;
340
error:
341 342 343 344
	vp_free_vectors(vdev);
	return err;
}

R
Rusty Russell 已提交
345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360
static int vp_request_intx(struct virtio_device *vdev)
{
	int err;
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
			  IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
	if (!err)
		vp_dev->intx_enabled = 1;
	return err;
}

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

387
	size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
388
	info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
A
Anthony Liguori 已提交
389 390 391 392 393 394
	if (info->queue == NULL) {
		err = -ENOMEM;
		goto out_info;
	}

	/* activate the queue */
395
	iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
A
Anthony Liguori 已提交
396 397 398
		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);

	/* create the vring */
399
	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN,
400
				 vdev, info->queue, vp_notify, callback, name);
A
Anthony Liguori 已提交
401 402 403 404 405 406 407 408
	if (!vq) {
		err = -ENOMEM;
		goto out_activate_queue;
	}

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

R
Rusty Russell 已提交
409 410 411 412
	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
		iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
		msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
413 414 415 416 417
			err = -EBUSY;
			goto out_assign;
		}
	}

418 419 420 421 422 423 424
	if (callback) {
		spin_lock_irqsave(&vp_dev->lock, flags);
		list_add(&info->node, &vp_dev->virtqueues);
		spin_unlock_irqrestore(&vp_dev->lock, flags);
	} else {
		INIT_LIST_HEAD(&info->node);
	}
A
Anthony Liguori 已提交
425 426 427

	return vq;

428 429
out_assign:
	vring_del_virtqueue(vq);
A
Anthony Liguori 已提交
430 431
out_activate_queue:
	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
432
	free_pages_exact(info->queue, size);
A
Anthony Liguori 已提交
433 434 435 436 437 438 439 440 441
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
442 443 444 445 446
	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
447

448 449 450 451 452 453 454 455 456
	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
457 458 459 460 461
	vring_del_virtqueue(vq);

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

462
	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
463
	free_pages_exact(info->queue, size);
A
Anthony Liguori 已提交
464 465 466
	kfree(info);
}

467
/* the config->del_vqs() implementation */
468 469
static void vp_del_vqs(struct virtio_device *vdev)
{
M
Michael S. Tsirkin 已提交
470
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
471
	struct virtqueue *vq, *n;
M
Michael S. Tsirkin 已提交
472
	struct virtio_pci_vq_info *info;
473

M
Michael S. Tsirkin 已提交
474 475
	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
		info = vq->priv;
476 477
		if (vp_dev->per_vq_vectors &&
			info->msix_vector != VIRTIO_MSI_NO_VECTOR)
R
Rusty Russell 已提交
478 479
			free_irq(vp_dev->msix_entries[info->msix_vector].vector,
				 vq);
480
		vp_del_vq(vq);
M
Michael S. Tsirkin 已提交
481 482
	}
	vp_dev->per_vq_vectors = false;
483 484

	vp_free_vectors(vdev);
485 486
}

M
Michael S. Tsirkin 已提交
487 488 489 490
static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
			      struct virtqueue *vqs[],
			      vq_callback_t *callbacks[],
			      const char *names[],
R
Rusty Russell 已提交
491
			      bool use_msix,
M
Michael S. Tsirkin 已提交
492
			      bool per_vq_vectors)
493
{
M
Michael S. Tsirkin 已提交
494
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
R
Rusty Russell 已提交
495 496
	u16 msix_vec;
	int i, err, nvectors, allocated_vectors;
497

R
Rusty Russell 已提交
498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518
	if (!use_msix) {
		/* Old style: one normal interrupt for change and all vqs. */
		err = vp_request_intx(vdev);
		if (err)
			goto error_request;
	} else {
		if (per_vq_vectors) {
			/* Best option: one for change interrupt, one per vq. */
			nvectors = 1;
			for (i = 0; i < nvqs; ++i)
				if (callbacks[i])
					++nvectors;
		} else {
			/* Second best: one for change, shared for all vqs. */
			nvectors = 2;
		}

		err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
		if (err)
			goto error_request;
	}
519

M
Michael S. Tsirkin 已提交
520 521
	vp_dev->per_vq_vectors = per_vq_vectors;
	allocated_vectors = vp_dev->msix_used_vectors;
522
	for (i = 0; i < nvqs; ++i) {
M
Michael S. Tsirkin 已提交
523
		if (!callbacks[i] || !vp_dev->msix_enabled)
R
Rusty Russell 已提交
524
			msix_vec = VIRTIO_MSI_NO_VECTOR;
M
Michael S. Tsirkin 已提交
525
		else if (vp_dev->per_vq_vectors)
R
Rusty Russell 已提交
526
			msix_vec = allocated_vectors++;
M
Michael S. Tsirkin 已提交
527
		else
R
Rusty Russell 已提交
528 529
			msix_vec = VP_MSIX_VQ_VECTOR;
		vqs[i] = setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
M
Michael S. Tsirkin 已提交
530 531
		if (IS_ERR(vqs[i])) {
			err = PTR_ERR(vqs[i]);
532
			goto error_find;
M
Michael S. Tsirkin 已提交
533
		}
534 535 536 537

		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
			continue;

M
Michael S. Tsirkin 已提交
538
		/* allocate per-vq irq if available and necessary */
539 540 541 542 543 544 545 546 547 548 549
		snprintf(vp_dev->msix_names[msix_vec],
			 sizeof *vp_dev->msix_names,
			 "%s-%s",
			 dev_name(&vp_dev->vdev.dev), names[i]);
		err = request_irq(vp_dev->msix_entries[msix_vec].vector,
				  vring_interrupt, 0,
				  vp_dev->msix_names[msix_vec],
				  vqs[i]);
		if (err) {
			vp_del_vq(vqs[i]);
			goto error_find;
M
Michael S. Tsirkin 已提交
550
		}
551 552 553
	}
	return 0;

554
error_find:
555
	vp_del_vqs(vdev);
556 557

error_request:
M
Michael S. Tsirkin 已提交
558 559 560 561 562 563 564 565 566
	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[])
{
R
Rusty Russell 已提交
567
	int err;
M
Michael S. Tsirkin 已提交
568

R
Rusty Russell 已提交
569 570
	/* Try MSI-X with one vector per queue. */
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
M
Michael S. Tsirkin 已提交
571 572
	if (!err)
		return 0;
R
Rusty Russell 已提交
573
	/* Fallback: MSI-X with one vector for config, one shared for queues. */
M
Michael S. Tsirkin 已提交
574
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
R
Rusty Russell 已提交
575
				 true, false);
M
Michael S. Tsirkin 已提交
576 577 578
	if (!err)
		return 0;
	/* Finally fall back to regular interrupts. */
R
Rusty Russell 已提交
579 580
	return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				  false, false);
581 582
}

A
Anthony Liguori 已提交
583 584 585 586 587 588
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,
589 590
	.find_vqs	= vp_find_vqs,
	.del_vqs	= vp_del_vqs,
591
	.get_features	= vp_get_features,
592
	.finalize_features = vp_finalize_features,
A
Anthony Liguori 已提交
593 594
};

595 596
static void virtio_pci_release_dev(struct device *_d)
{
597 598
	struct virtio_device *dev = container_of(_d, struct virtio_device,
						 dev);
599 600 601 602 603
	struct virtio_pci_device *vp_dev = to_vp_device(dev);

	kfree(vp_dev);
}

A
Anthony Liguori 已提交
604 605 606 607 608 609 610 611 612 613 614
/* 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;

615 616 617 618 619 620
	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
621 622 623 624 625
	/* allocate our structure and fill it out */
	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
	if (vp_dev == NULL)
		return -ENOMEM;

626
	vp_dev->vdev.dev.parent = &pci_dev->dev;
627
	vp_dev->vdev.dev.release = virtio_pci_release_dev;
A
Anthony Liguori 已提交
628 629 630 631 632
	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);

633 634 635
	/* Disable MSI/MSIX to bring device to a known good state. */
	pci_msi_off(pci_dev);

A
Anthony Liguori 已提交
636 637 638 639 640 641 642 643 644 645 646 647 648 649
	/* 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);
650
	pci_set_master(pci_dev);
A
Anthony Liguori 已提交
651 652 653 654

	/* 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
T
Thomas Weber 已提交
655
	 * the subsystem ids */
A
Anthony Liguori 已提交
656 657 658 659 660 661
	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)
662
		goto out_set_drvdata;
A
Anthony Liguori 已提交
663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681

	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);

682
	unregister_virtio_device(&vp_dev->vdev);
683 684 685 686 687 688

	vp_del_vqs(&vp_dev->vdev);
	pci_set_drvdata(pci_dev, NULL);
	pci_iounmap(pci_dev, vp_dev->ioaddr);
	pci_release_regions(pci_dev);
	pci_disable_device(pci_dev);
A
Anthony Liguori 已提交
689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
}

#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,
711
	.remove		= __devexit_p(virtio_pci_remove),
A
Anthony Liguori 已提交
712 713 714 715 716 717 718 719
#ifdef CONFIG_PM
	.suspend	= virtio_pci_suspend,
	.resume		= virtio_pci_resume,
#endif
};

static int __init virtio_pci_init(void)
{
720
	return pci_register_driver(&virtio_pci_driver);
A
Anthony Liguori 已提交
721 722 723 724 725 726 727 728 729 730
}

module_init(virtio_pci_init);

static void __exit virtio_pci_exit(void)
{
	pci_unregister_driver(&virtio_pci_driver);
}

module_exit(virtio_pci_exit);