virtio_pci.c 19.4 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

	/* MSI-X vector (or none) */
R
Rusty Russell 已提交
87
	unsigned msix_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
}

R
Rusty Russell 已提交
283 284
static int vp_request_msix_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
	vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
				       GFP_KERNEL);
	if (!vp_dev->msix_entries)
294
		goto error;
295 296 297
	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
				     GFP_KERNEL);
	if (!vp_dev->msix_names)
298
		goto error;
299 300 301 302

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

R
Rusty Russell 已提交
303
	/* pci_enable_msix returns positive if we can't get this many. */
M
Michael S. Tsirkin 已提交
304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
	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;
322

M
Michael S. Tsirkin 已提交
323 324 325 326 327 328
	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;
329 330
	}

M
Michael S. Tsirkin 已提交
331
	if (!per_vq_vectors) {
332 333 334 335 336 337 338 339
		/* 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)
340
			goto error;
341 342 343
		++vp_dev->msix_used_vectors;
	}
	return 0;
344
error:
345 346 347 348
	vp_free_vectors(vdev);
	return err;
}

R
Rusty Russell 已提交
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
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
365 366 367 368
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_vq_info *info;
	struct virtqueue *vq;
369
	unsigned long flags, size;
M
Michael S. Tsirkin 已提交
370
	u16 num;
A
Anthony Liguori 已提交
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
	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
389
	info->msix_vector = msix_vec;
A
Anthony Liguori 已提交
390

391
	size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
392
	info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
A
Anthony Liguori 已提交
393 394 395 396 397 398
	if (info->queue == NULL) {
		err = -ENOMEM;
		goto out_info;
	}

	/* activate the queue */
399
	iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
A
Anthony Liguori 已提交
400 401 402
		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);

	/* create the vring */
403
	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN,
404
				 vdev, info->queue, vp_notify, callback, name);
A
Anthony Liguori 已提交
405 406 407 408 409 410 411 412
	if (!vq) {
		err = -ENOMEM;
		goto out_activate_queue;
	}

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

R
Rusty Russell 已提交
413 414 415 416
	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) {
417 418 419 420 421
			err = -EBUSY;
			goto out_assign;
		}
	}

422
	spin_lock_irqsave(&vp_dev->lock, flags);
A
Anthony Liguori 已提交
423
	list_add(&info->node, &vp_dev->virtqueues);
424
	spin_unlock_irqrestore(&vp_dev->lock, flags);
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
474 475 476
	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
		info = vq->priv;
		if (vp_dev->per_vq_vectors)
R
Rusty Russell 已提交
477 478
			free_irq(vp_dev->msix_entries[info->msix_vector].vector,
				 vq);
479
		vp_del_vq(vq);
M
Michael S. Tsirkin 已提交
480 481
	}
	vp_dev->per_vq_vectors = false;
482 483

	vp_free_vectors(vdev);
484 485
}

M
Michael S. Tsirkin 已提交
486 487 488 489
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
490
			      bool use_msix,
M
Michael S. Tsirkin 已提交
491
			      bool per_vq_vectors)
492
{
M
Michael S. Tsirkin 已提交
493
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
R
Rusty Russell 已提交
494 495
	u16 msix_vec;
	int i, err, nvectors, allocated_vectors;
496

R
Rusty Russell 已提交
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517
	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;
	}
518

M
Michael S. Tsirkin 已提交
519 520
	vp_dev->per_vq_vectors = per_vq_vectors;
	allocated_vectors = vp_dev->msix_used_vectors;
521
	for (i = 0; i < nvqs; ++i) {
M
Michael S. Tsirkin 已提交
522
		if (!callbacks[i] || !vp_dev->msix_enabled)
R
Rusty Russell 已提交
523
			msix_vec = VIRTIO_MSI_NO_VECTOR;
M
Michael S. Tsirkin 已提交
524
		else if (vp_dev->per_vq_vectors)
R
Rusty Russell 已提交
525
			msix_vec = allocated_vectors++;
M
Michael S. Tsirkin 已提交
526
		else
R
Rusty Russell 已提交
527 528
			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
529 530
		if (IS_ERR(vqs[i])) {
			err = PTR_ERR(vqs[i]);
531
			goto error_find;
M
Michael S. Tsirkin 已提交
532
		}
533 534 535 536

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

M
Michael S. Tsirkin 已提交
537
		/* allocate per-vq irq if available and necessary */
538 539 540 541 542 543 544 545 546 547 548
		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
549
		}
550 551 552
	}
	return 0;

553
error_find:
554
	vp_del_vqs(vdev);
555 556

error_request:
M
Michael S. Tsirkin 已提交
557 558 559 560 561 562 563 564 565
	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
566
	int err;
M
Michael S. Tsirkin 已提交
567

R
Rusty Russell 已提交
568 569
	/* 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
570 571
	if (!err)
		return 0;
R
Rusty Russell 已提交
572
	/* Fallback: MSI-X with one vector for config, one shared for queues. */
M
Michael S. Tsirkin 已提交
573
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
R
Rusty Russell 已提交
574
				 true, false);
M
Michael S. Tsirkin 已提交
575 576 577
	if (!err)
		return 0;
	/* Finally fall back to regular interrupts. */
R
Rusty Russell 已提交
578 579
	return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				  false, false);
580 581
}

A
Anthony Liguori 已提交
582 583 584 585 586 587
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,
588 589
	.find_vqs	= vp_find_vqs,
	.del_vqs	= vp_del_vqs,
590
	.get_features	= vp_get_features,
591
	.finalize_features = vp_finalize_features,
A
Anthony Liguori 已提交
592 593
};

594 595 596 597 598 599
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;

600
	vp_del_vqs(dev);
601 602 603 604 605 606 607
	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
608 609 610 611 612 613 614 615 616 617 618
/* 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;

619 620 621 622 623 624
	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
625 626 627 628 629
	/* allocate our structure and fill it out */
	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
	if (vp_dev == NULL)
		return -ENOMEM;

630
	vp_dev->vdev.dev.parent = virtio_pci_root;
631
	vp_dev->vdev.dev.release = virtio_pci_release_dev;
A
Anthony Liguori 已提交
632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661
	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)
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);
A
Anthony Liguori 已提交
683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
}

#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;

716 717 718
	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
719 720 721

	err = pci_register_driver(&virtio_pci_driver);
	if (err)
722
		root_device_unregister(virtio_pci_root);
A
Anthony Liguori 已提交
723 724 725 726 727 728 729 730 731

	return err;
}

module_init(virtio_pci_init);

static void __exit virtio_pci_exit(void)
{
	pci_unregister_driver(&virtio_pci_driver);
732
	root_device_unregister(virtio_pci_root);
A
Anthony Liguori 已提交
733 734 735
}

module_exit(virtio_pci_exit);