vmd.c 19.8 KB
Newer Older
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 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
/*
 * Volume Management Device driver
 * Copyright (c) 2015, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/msi.h>
#include <linux/pci.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>

#include <asm/irqdomain.h>
#include <asm/device.h>
#include <asm/msi.h>
#include <asm/msidef.h>

#define VMD_CFGBAR	0
#define VMD_MEMBAR1	2
#define VMD_MEMBAR2	4

/*
 * Lock for manipulating VMD IRQ lists.
 */
static DEFINE_RAW_SPINLOCK(list_lock);

/**
 * struct vmd_irq - private data to map driver IRQ to the VMD shared vector
 * @node:	list item for parent traversal.
 * @rcu:	RCU callback item for freeing.
 * @irq:	back pointer to parent.
 * @virq:	the virtual IRQ value provided to the requesting driver.
 *
 * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
 * a VMD IRQ using this structure.
 */
struct vmd_irq {
	struct list_head	node;
	struct rcu_head		rcu;
	struct vmd_irq_list	*irq;
	unsigned int		virq;
};

/**
 * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector
 * @irq_list:	the list of irq's the VMD one demuxes to.
 * @vmd_vector:	the h/w IRQ assigned to the VMD.
 * @index:	index into the VMD MSI-X table; used for message routing.
 * @count:	number of child IRQs assigned to this vector; used to track
 *		sharing.
 */
struct vmd_irq_list {
	struct list_head	irq_list;
	struct vmd_dev		*vmd;
	unsigned int		vmd_vector;
	unsigned int		index;
	unsigned int		count;
};

struct vmd_dev {
	struct pci_dev		*dev;

	spinlock_t		cfg_lock;
	char __iomem		*cfgbar;

	int msix_count;
	struct msix_entry	*msix_entries;
	struct vmd_irq_list	*irqs;

	struct pci_sysdata	sysdata;
	struct resource		resources[3];
	struct irq_domain	*irq_domain;
	struct pci_bus		*bus;

#ifdef CONFIG_X86_DEV_DMA_OPS
	struct dma_map_ops	dma_ops;
	struct dma_domain	dma_domain;
#endif
};

static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
{
	return container_of(bus->sysdata, struct vmd_dev, sysdata);
}

/*
 * Drivers managing a device in a VMD domain allocate their own IRQs as before,
 * but the MSI entry for the hardware it's driving will be programmed with a
 * destination ID for the VMD MSI-X table.  The VMD muxes interrupts in its
 * domain into one of its own, and the VMD driver de-muxes these for the
 * handlers sharing that VMD IRQ.  The vmd irq_domain provides the operations
 * and irq_chip to set this up.
 */
static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
	struct vmd_irq *vmdirq = data->chip_data;
	struct vmd_irq_list *irq = vmdirq->irq;

	msg->address_hi = MSI_ADDR_BASE_HI;
	msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(irq->index);
	msg->data = 0;
}

/*
 * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops.
 */
static void vmd_irq_enable(struct irq_data *data)
{
	struct vmd_irq *vmdirq = data->chip_data;
122
	unsigned long flags;
123

124
	raw_spin_lock_irqsave(&list_lock, flags);
125
	list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
126
	raw_spin_unlock_irqrestore(&list_lock, flags);
127 128 129 130 131 132 133

	data->chip->irq_unmask(data);
}

static void vmd_irq_disable(struct irq_data *data)
{
	struct vmd_irq *vmdirq = data->chip_data;
134
	unsigned long flags;
135 136 137

	data->chip->irq_mask(data);

138
	raw_spin_lock_irqsave(&list_lock, flags);
139
	list_del_rcu(&vmdirq->node);
140
	INIT_LIST_HEAD_RCU(&vmdirq->node);
141
	raw_spin_unlock_irqrestore(&list_lock, flags);
142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171
}

/*
 * XXX: Stubbed until we develop acceptable way to not create conflicts with
 * other devices sharing the same vector.
 */
static int vmd_irq_set_affinity(struct irq_data *data,
				const struct cpumask *dest, bool force)
{
	return -EINVAL;
}

static struct irq_chip vmd_msi_controller = {
	.name			= "VMD-MSI",
	.irq_enable		= vmd_irq_enable,
	.irq_disable		= vmd_irq_disable,
	.irq_compose_msi_msg	= vmd_compose_msi_msg,
	.irq_set_affinity	= vmd_irq_set_affinity,
};

static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info,
				     msi_alloc_info_t *arg)
{
	return 0;
}

/*
 * XXX: We can be even smarter selecting the best IRQ once we solve the
 * affinity problem.
 */
172
static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc)
173
{
174
	int i, best = 1;
175
	unsigned long flags;
176

177 178 179
	if (!desc->msi_attrib.is_msix || vmd->msix_count == 1)
		return &vmd->irqs[0];

180
	raw_spin_lock_irqsave(&list_lock, flags);
181 182 183 184
	for (i = 1; i < vmd->msix_count; i++)
		if (vmd->irqs[i].count < vmd->irqs[best].count)
			best = i;
	vmd->irqs[best].count++;
185
	raw_spin_unlock_irqrestore(&list_lock, flags);
186 187 188 189 190 191 192 193

	return &vmd->irqs[best];
}

static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info,
			unsigned int virq, irq_hw_number_t hwirq,
			msi_alloc_info_t *arg)
{
194 195
	struct msi_desc *desc = arg->desc;
	struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus);
196 197 198 199 200 201
	struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL);

	if (!vmdirq)
		return -ENOMEM;

	INIT_LIST_HEAD(&vmdirq->node);
202
	vmdirq->irq = vmd_next_irq(vmd, desc);
203 204 205
	vmdirq->virq = virq;

	irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip,
206
			    vmdirq, handle_untracked_irq, vmd, NULL);
207 208 209 210 211 212 213
	return 0;
}

static void vmd_msi_free(struct irq_domain *domain,
			struct msi_domain_info *info, unsigned int virq)
{
	struct vmd_irq *vmdirq = irq_get_chip_data(virq);
214
	unsigned long flags;
215 216

	/* XXX: Potential optimization to rebalance */
217
	raw_spin_lock_irqsave(&list_lock, flags);
218
	vmdirq->irq->count--;
219
	raw_spin_unlock_irqrestore(&list_lock, flags);
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272

	kfree_rcu(vmdirq, rcu);
}

static int vmd_msi_prepare(struct irq_domain *domain, struct device *dev,
			   int nvec, msi_alloc_info_t *arg)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct vmd_dev *vmd = vmd_from_bus(pdev->bus);

	if (nvec > vmd->msix_count)
		return vmd->msix_count;

	memset(arg, 0, sizeof(*arg));
	return 0;
}

static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
{
	arg->desc = desc;
}

static struct msi_domain_ops vmd_msi_domain_ops = {
	.get_hwirq	= vmd_get_hwirq,
	.msi_init	= vmd_msi_init,
	.msi_free	= vmd_msi_free,
	.msi_prepare	= vmd_msi_prepare,
	.set_desc	= vmd_set_desc,
};

static struct msi_domain_info vmd_msi_domain_info = {
	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
			  MSI_FLAG_PCI_MSIX,
	.ops		= &vmd_msi_domain_ops,
	.chip		= &vmd_msi_controller,
};

#ifdef CONFIG_X86_DEV_DMA_OPS
/*
 * VMD replaces the requester ID with its own.  DMA mappings for devices in a
 * VMD domain need to be mapped for the VMD, not the device requiring
 * the mapping.
 */
static struct device *to_vmd_dev(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct vmd_dev *vmd = vmd_from_bus(pdev->bus);

	return &vmd->dev->dev;
}

static struct dma_map_ops *vmd_dma_ops(struct device *dev)
{
273
	return get_dma_ops(to_vmd_dev(dev));
274 275 276
}

static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
277
		       gfp_t flag, unsigned long attrs)
278 279 280 281 282 283
{
	return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag,
				       attrs);
}

static void vmd_free(struct device *dev, size_t size, void *vaddr,
284
		     dma_addr_t addr, unsigned long attrs)
285 286 287 288 289 290 291
{
	return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr,
				      attrs);
}

static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
		    void *cpu_addr, dma_addr_t addr, size_t size,
292
		    unsigned long attrs)
293 294 295 296 297 298 299
{
	return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr,
				      size, attrs);
}

static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
			   void *cpu_addr, dma_addr_t addr, size_t size,
300
			   unsigned long attrs)
301 302 303 304 305 306 307 308
{
	return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr,
					     addr, size, attrs);
}

static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
			       unsigned long offset, size_t size,
			       enum dma_data_direction dir,
309
			       unsigned long attrs)
310 311 312 313 314 315
{
	return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size,
					  dir, attrs);
}

static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
316
			   enum dma_data_direction dir, unsigned long attrs)
317 318 319 320 321
{
	vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs);
}

static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
322
		      enum dma_data_direction dir, unsigned long attrs)
323 324 325 326 327
{
	return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
}

static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
328
			 enum dma_data_direction dir, unsigned long attrs)
329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
{
	vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
}

static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
				    size_t size, enum dma_data_direction dir)
{
	vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
}

static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
				       size_t size, enum dma_data_direction dir)
{
	vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size,
						 dir);
}

static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
				int nents, enum dma_data_direction dir)
{
	vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
}

static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
				   int nents, enum dma_data_direction dir)
{
	vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
}

static int vmd_mapping_error(struct device *dev, dma_addr_t addr)
{
	return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr);
}

static int vmd_dma_supported(struct device *dev, u64 mask)
{
	return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask);
}

#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
static u64 vmd_get_required_mask(struct device *dev)
{
	return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev));
}
#endif

static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
{
	struct dma_domain *domain = &vmd->dma_domain;

379
	if (get_dma_ops(&vmd->dev->dev))
380 381 382 383 384 385 386 387 388 389 390
		del_dma_domain(domain);
}

#define ASSIGN_VMD_DMA_OPS(source, dest, fn)	\
	do {					\
		if (source->fn)			\
			dest->fn = vmd_##fn;	\
	} while (0)

static void vmd_setup_dma_ops(struct vmd_dev *vmd)
{
391
	const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev);
392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514
	struct dma_map_ops *dest = &vmd->dma_ops;
	struct dma_domain *domain = &vmd->dma_domain;

	domain->domain_nr = vmd->sysdata.domain;
	domain->dma_ops = dest;

	if (!source)
		return;
	ASSIGN_VMD_DMA_OPS(source, dest, alloc);
	ASSIGN_VMD_DMA_OPS(source, dest, free);
	ASSIGN_VMD_DMA_OPS(source, dest, mmap);
	ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable);
	ASSIGN_VMD_DMA_OPS(source, dest, map_page);
	ASSIGN_VMD_DMA_OPS(source, dest, unmap_page);
	ASSIGN_VMD_DMA_OPS(source, dest, map_sg);
	ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg);
	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu);
	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device);
	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu);
	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device);
	ASSIGN_VMD_DMA_OPS(source, dest, mapping_error);
	ASSIGN_VMD_DMA_OPS(source, dest, dma_supported);
#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
	ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask);
#endif
	add_dma_domain(domain);
}
#undef ASSIGN_VMD_DMA_OPS
#else
static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {}
static void vmd_setup_dma_ops(struct vmd_dev *vmd) {}
#endif

static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
				  unsigned int devfn, int reg, int len)
{
	char __iomem *addr = vmd->cfgbar +
			     (bus->number << 20) + (devfn << 12) + reg;

	if ((addr - vmd->cfgbar) + len >=
	    resource_size(&vmd->dev->resource[VMD_CFGBAR]))
		return NULL;

	return addr;
}

/*
 * CPU may deadlock if config space is not serialized on some versions of this
 * hardware, so all config space access is done under a spinlock.
 */
static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg,
			int len, u32 *value)
{
	struct vmd_dev *vmd = vmd_from_bus(bus);
	char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len);
	unsigned long flags;
	int ret = 0;

	if (!addr)
		return -EFAULT;

	spin_lock_irqsave(&vmd->cfg_lock, flags);
	switch (len) {
	case 1:
		*value = readb(addr);
		break;
	case 2:
		*value = readw(addr);
		break;
	case 4:
		*value = readl(addr);
		break;
	default:
		ret = -EINVAL;
		break;
	}
	spin_unlock_irqrestore(&vmd->cfg_lock, flags);
	return ret;
}

/*
 * VMD h/w converts non-posted config writes to posted memory writes. The
 * read-back in this function forces the completion so it returns only after
 * the config space was written, as expected.
 */
static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg,
			 int len, u32 value)
{
	struct vmd_dev *vmd = vmd_from_bus(bus);
	char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len);
	unsigned long flags;
	int ret = 0;

	if (!addr)
		return -EFAULT;

	spin_lock_irqsave(&vmd->cfg_lock, flags);
	switch (len) {
	case 1:
		writeb(value, addr);
		readb(addr);
		break;
	case 2:
		writew(value, addr);
		readw(addr);
		break;
	case 4:
		writel(value, addr);
		readl(addr);
		break;
	default:
		ret = -EINVAL;
		break;
	}
	spin_unlock_irqrestore(&vmd->cfg_lock, flags);
	return ret;
}

static struct pci_ops vmd_ops = {
	.read		= vmd_pci_read,
	.write		= vmd_pci_write,
};

515 516 517 518 519 520 521 522 523 524 525 526
static void vmd_attach_resources(struct vmd_dev *vmd)
{
	vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1];
	vmd->dev->resource[VMD_MEMBAR2].child = &vmd->resources[2];
}

static void vmd_detach_resources(struct vmd_dev *vmd)
{
	vmd->dev->resource[VMD_MEMBAR1].child = NULL;
	vmd->dev->resource[VMD_MEMBAR2].child = NULL;
}

527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550
/*
 * VMD domains start at 0x1000 to not clash with ACPI _SEG domains.
 */
static int vmd_find_free_domain(void)
{
	int domain = 0xffff;
	struct pci_bus *bus = NULL;

	while ((bus = pci_find_next_bus(bus)) != NULL)
		domain = max_t(int, domain, pci_domain_nr(bus));
	return domain + 1;
}

static int vmd_enable_domain(struct vmd_dev *vmd)
{
	struct pci_sysdata *sd = &vmd->sysdata;
	struct resource *res;
	u32 upper_bits;
	unsigned long flags;
	LIST_HEAD(resources);

	res = &vmd->dev->resource[VMD_CFGBAR];
	vmd->resources[0] = (struct resource) {
		.name  = "VMD CFGBAR",
551
		.start = 0,
552 553 554 555
		.end   = (resource_size(res) >> 20) - 1,
		.flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED,
	};

556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
	/*
	 * If the window is below 4GB, clear IORESOURCE_MEM_64 so we can
	 * put 32-bit resources in the window.
	 *
	 * There's no hardware reason why a 64-bit window *couldn't*
	 * contain a 32-bit resource, but pbus_size_mem() computes the
	 * bridge window size assuming a 64-bit window will contain no
	 * 32-bit resources.  __pci_assign_resource() enforces that
	 * artificial restriction to make sure everything will fit.
	 *
	 * The only way we could use a 64-bit non-prefechable MEMBAR is
	 * if its address is <4GB so that we can convert it to a 32-bit
	 * resource.  To be visible to the host OS, all VMD endpoints must
	 * be initially configured by platform BIOS, which includes setting
	 * up these resources.  We can assume the device is configured
	 * according to the platform needs.
	 */
573 574 575 576 577 578 579 580 581 582
	res = &vmd->dev->resource[VMD_MEMBAR1];
	upper_bits = upper_32_bits(res->end);
	flags = res->flags & ~IORESOURCE_SIZEALIGN;
	if (!upper_bits)
		flags &= ~IORESOURCE_MEM_64;
	vmd->resources[1] = (struct resource) {
		.name  = "VMD MEMBAR1",
		.start = res->start,
		.end   = res->end,
		.flags = flags,
583
		.parent = res,
584 585 586 587 588 589 590 591 592 593 594 595
	};

	res = &vmd->dev->resource[VMD_MEMBAR2];
	upper_bits = upper_32_bits(res->end);
	flags = res->flags & ~IORESOURCE_SIZEALIGN;
	if (!upper_bits)
		flags &= ~IORESOURCE_MEM_64;
	vmd->resources[2] = (struct resource) {
		.name  = "VMD MEMBAR2",
		.start = res->start + 0x2000,
		.end   = res->end,
		.flags = flags,
596
		.parent = res,
597 598 599 600 601 602 603 604 605
	};

	sd->domain = vmd_find_free_domain();
	if (sd->domain < 0)
		return sd->domain;

	sd->node = pcibus_to_node(vmd->dev->bus);

	vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info,
606
						    x86_vector_domain);
607 608 609 610 611 612 613 614 615 616 617 618 619 620
	if (!vmd->irq_domain)
		return -ENODEV;

	pci_add_resource(&resources, &vmd->resources[0]);
	pci_add_resource(&resources, &vmd->resources[1]);
	pci_add_resource(&resources, &vmd->resources[2]);
	vmd->bus = pci_create_root_bus(&vmd->dev->dev, 0, &vmd_ops, sd,
				       &resources);
	if (!vmd->bus) {
		pci_free_resource_list(&resources);
		irq_domain_remove(vmd->irq_domain);
		return -ENODEV;
	}

621
	vmd_attach_resources(vmd);
622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717
	vmd_setup_dma_ops(vmd);
	dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain);
	pci_rescan_bus(vmd->bus);

	WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj,
			       "domain"), "Can't create symlink to domain\n");
	return 0;
}

static irqreturn_t vmd_irq(int irq, void *data)
{
	struct vmd_irq_list *irqs = data;
	struct vmd_irq *vmdirq;

	rcu_read_lock();
	list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node)
		generic_handle_irq(vmdirq->virq);
	rcu_read_unlock();

	return IRQ_HANDLED;
}

static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
	struct vmd_dev *vmd;
	int i, err;

	if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20))
		return -ENOMEM;

	vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL);
	if (!vmd)
		return -ENOMEM;

	vmd->dev = dev;
	err = pcim_enable_device(dev);
	if (err < 0)
		return err;

	vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0);
	if (!vmd->cfgbar)
		return -ENOMEM;

	pci_set_master(dev);
	if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) &&
	    dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)))
		return -ENODEV;

	vmd->msix_count = pci_msix_vec_count(dev);
	if (vmd->msix_count < 0)
		return -ENODEV;

	vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs),
				 GFP_KERNEL);
	if (!vmd->irqs)
		return -ENOMEM;

	vmd->msix_entries = devm_kcalloc(&dev->dev, vmd->msix_count,
					 sizeof(*vmd->msix_entries),
					 GFP_KERNEL);
	if (!vmd->msix_entries)
		return -ENOMEM;
	for (i = 0; i < vmd->msix_count; i++)
		vmd->msix_entries[i].entry = i;

	vmd->msix_count = pci_enable_msix_range(vmd->dev, vmd->msix_entries, 1,
						vmd->msix_count);
	if (vmd->msix_count < 0)
		return vmd->msix_count;

	for (i = 0; i < vmd->msix_count; i++) {
		INIT_LIST_HEAD(&vmd->irqs[i].irq_list);
		vmd->irqs[i].vmd_vector = vmd->msix_entries[i].vector;
		vmd->irqs[i].index = i;

		err = devm_request_irq(&dev->dev, vmd->irqs[i].vmd_vector,
				       vmd_irq, 0, "vmd", &vmd->irqs[i]);
		if (err)
			return err;
	}

	spin_lock_init(&vmd->cfg_lock);
	pci_set_drvdata(dev, vmd);
	err = vmd_enable_domain(vmd);
	if (err)
		return err;

	dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n",
		 vmd->sysdata.domain);
	return 0;
}

static void vmd_remove(struct pci_dev *dev)
{
	struct vmd_dev *vmd = pci_get_drvdata(dev);

718
	vmd_detach_resources(vmd);
719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765
	pci_set_drvdata(dev, NULL);
	sysfs_remove_link(&vmd->dev->dev.kobj, "domain");
	pci_stop_root_bus(vmd->bus);
	pci_remove_root_bus(vmd->bus);
	vmd_teardown_dma_ops(vmd);
	irq_domain_remove(vmd->irq_domain);
}

#ifdef CONFIG_PM
static int vmd_suspend(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);

	pci_save_state(pdev);
	return 0;
}

static int vmd_resume(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);

	pci_restore_state(pdev);
	return 0;
}
#endif
static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume);

static const struct pci_device_id vmd_ids[] = {
	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x201d),},
	{0,}
};
MODULE_DEVICE_TABLE(pci, vmd_ids);

static struct pci_driver vmd_drv = {
	.name		= "vmd",
	.id_table	= vmd_ids,
	.probe		= vmd_probe,
	.remove		= vmd_remove,
	.driver		= {
		.pm	= &vmd_dev_pm_ops,
	},
};
module_pci_driver(vmd_drv);

MODULE_AUTHOR("Intel Corporation");
MODULE_LICENSE("GPL v2");
MODULE_VERSION("0.6");