pasid.c 21.8 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2
/*
3 4 5 6 7 8 9 10 11
 * intel-pasid.c - PASID idr, table and entry manipulation
 *
 * Copyright (C) 2018 Intel Corporation
 *
 * Author: Lu Baolu <baolu.lu@linux.intel.com>
 */

#define pr_fmt(fmt)	"DMAR: " fmt

12
#include <linux/bitops.h>
13
#include <linux/cpufeature.h>
14 15 16 17
#include <linux/dmar.h>
#include <linux/intel-iommu.h>
#include <linux/iommu.h>
#include <linux/memory.h>
18 19
#include <linux/pci.h>
#include <linux/pci-ats.h>
20 21
#include <linux/spinlock.h>

22
#include "pasid.h"
23 24 25 26 27

/*
 * Intel IOMMU system wide PASID name space:
 */
u32 intel_pasid_max_id = PASID_MAX;
28

29
int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
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
{
	unsigned long flags;
	u8 status_code;
	int ret = 0;
	u64 res;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);
	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
		      !(res & VCMD_VRSP_IP), res);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);

	status_code = VCMD_VRSP_SC(res);
	switch (status_code) {
	case VCMD_VRSP_SC_SUCCESS:
		*pasid = VCMD_VRSP_RESULT_PASID(res);
		break;
	case VCMD_VRSP_SC_NO_PASID_AVAIL:
		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
		ret = -ENOSPC;
		break;
	default:
		ret = -ENODEV;
		pr_warn("IOMMU: %s: Unexpected error code %d\n",
			iommu->name, status_code);
	}

	return ret;
}

60
void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
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
{
	unsigned long flags;
	u8 status_code;
	u64 res;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);
	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
		      !(res & VCMD_VRSP_IP), res);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);

	status_code = VCMD_VRSP_SC(res);
	switch (status_code) {
	case VCMD_VRSP_SC_SUCCESS:
		break;
	case VCMD_VRSP_SC_INVALID_PASID:
		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
		break;
	default:
		pr_warn("IOMMU: %s: Unexpected error code %d\n",
			iommu->name, status_code);
	}
}

86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
/*
 * Per device pasid table management:
 */
static inline void
device_attach_pasid_table(struct device_domain_info *info,
			  struct pasid_table *pasid_table)
{
	info->pasid_table = pasid_table;
	list_add(&info->table, &pasid_table->dev);
}

static inline void
device_detach_pasid_table(struct device_domain_info *info,
			  struct pasid_table *pasid_table)
{
	info->pasid_table = NULL;
	list_del(&info->table);
}

struct pasid_table_opaque {
	struct pasid_table	**pasid_table;
	int			segment;
	int			bus;
	int			devfn;
};

static int search_pasid_table(struct device_domain_info *info, void *opaque)
{
	struct pasid_table_opaque *data = opaque;

	if (info->iommu->segment == data->segment &&
	    info->bus == data->bus &&
	    info->devfn == data->devfn &&
	    info->pasid_table) {
		*data->pasid_table = info->pasid_table;
		return 1;
	}

	return 0;
}

static int get_alias_pasid_table(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct pasid_table_opaque *data = opaque;

	data->segment = pci_domain_nr(pdev->bus);
	data->bus = PCI_BUS_NUM(alias);
	data->devfn = alias & 0xff;

	return for_each_device_domain(&search_pasid_table, data);
}

/*
 * Allocate a pasid table for @dev. It should be called in a
 * single-thread context.
 */
int intel_pasid_alloc_table(struct device *dev)
{
	struct device_domain_info *info;
	struct pasid_table *pasid_table;
	struct pasid_table_opaque data;
	struct page *pages;
148
	u32 max_pasid = 0;
149
	int ret, order;
150
	int size;
151

152
	might_sleep();
153
	info = get_domain_info(dev);
154
	if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table))
155 156 157 158 159 160 161 162 163
		return -EINVAL;

	/* DMA alias device already has a pasid table, use it: */
	data.pasid_table = &pasid_table;
	ret = pci_for_each_dma_alias(to_pci_dev(dev),
				     &get_alias_pasid_table, &data);
	if (ret)
		goto attach_out;

164
	pasid_table = kzalloc(sizeof(*pasid_table), GFP_KERNEL);
165 166 167 168
	if (!pasid_table)
		return -ENOMEM;
	INIT_LIST_HEAD(&pasid_table->dev);

169
	if (info->pasid_supported)
170
		max_pasid = min_t(u32, pci_max_pasids(to_pci_dev(dev)),
171 172 173 174
				  intel_pasid_max_id);

	size = max_pasid >> (PASID_PDE_SHIFT - 3);
	order = size ? get_order(size) : 0;
175
	pages = alloc_pages_node(info->iommu->node,
176
				 GFP_KERNEL | __GFP_ZERO, order);
177 178
	if (!pages) {
		kfree(pasid_table);
179
		return -ENOMEM;
180
	}
181 182 183

	pasid_table->table = page_address(pages);
	pasid_table->order = order;
184
	pasid_table->max_pasid = 1 << (order + PAGE_SHIFT + 3);
185 186 187 188 189 190 191 192 193 194 195

attach_out:
	device_attach_pasid_table(info, pasid_table);

	return 0;
}

void intel_pasid_free_table(struct device *dev)
{
	struct device_domain_info *info;
	struct pasid_table *pasid_table;
196 197 198
	struct pasid_dir_entry *dir;
	struct pasid_entry *table;
	int i, max_pde;
199

200
	info = get_domain_info(dev);
201
	if (!info || !dev_is_pci(dev) || !info->pasid_table)
202 203 204 205 206 207 208 209
		return;

	pasid_table = info->pasid_table;
	device_detach_pasid_table(info, pasid_table);

	if (!list_empty(&pasid_table->dev))
		return;

210 211 212 213 214 215 216 217
	/* Free scalable mode PASID directory tables: */
	dir = pasid_table->table;
	max_pde = pasid_table->max_pasid >> PASID_PDE_SHIFT;
	for (i = 0; i < max_pde; i++) {
		table = get_pasid_table_from_pde(&dir[i]);
		free_pgtable_page(table);
	}

218 219 220 221 222 223 224 225
	free_pages((unsigned long)pasid_table->table, pasid_table->order);
	kfree(pasid_table);
}

struct pasid_table *intel_pasid_get_table(struct device *dev)
{
	struct device_domain_info *info;

226
	info = get_domain_info(dev);
227 228 229 230 231 232
	if (!info)
		return NULL;

	return info->pasid_table;
}

233
static int intel_pasid_get_dev_max_id(struct device *dev)
234 235 236
{
	struct device_domain_info *info;

237
	info = get_domain_info(dev);
238 239 240 241 242 243
	if (!info || !info->pasid_table)
		return 0;

	return info->pasid_table->max_pasid;
}

244
static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
245
{
246
	struct device_domain_info *info;
247
	struct pasid_table *pasid_table;
248
	struct pasid_dir_entry *dir;
249
	struct pasid_entry *entries;
250
	int dir_index, index;
251 252

	pasid_table = intel_pasid_get_table(dev);
253
	if (WARN_ON(!pasid_table || pasid >= intel_pasid_get_dev_max_id(dev)))
254 255
		return NULL;

256
	dir = pasid_table->table;
257
	info = get_domain_info(dev);
258 259 260
	dir_index = pasid >> PASID_PDE_SHIFT;
	index = pasid & PASID_PTE_MASK;

261
retry:
262 263 264
	entries = get_pasid_table_from_pde(&dir[dir_index]);
	if (!entries) {
		entries = alloc_pgtable_page(info->iommu->node);
265
		if (!entries)
266 267
			return NULL;

268 269 270 271 272 273 274 275 276 277 278
		/*
		 * The pasid directory table entry won't be freed after
		 * allocation. No worry about the race with free and
		 * clear. However, this entry might be populated by others
		 * while we are preparing it. Use theirs with a retry.
		 */
		if (cmpxchg64(&dir[dir_index].val, 0ULL,
			      (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) {
			free_pgtable_page(entries);
			goto retry;
		}
279
	}
280

281
	return &entries[index];
282 283 284 285 286 287 288
}

/*
 * Interfaces for PASID table entry manipulation:
 */
static inline void pasid_clear_entry(struct pasid_entry *pe)
{
289 290 291 292 293 294 295 296
	WRITE_ONCE(pe->val[0], 0);
	WRITE_ONCE(pe->val[1], 0);
	WRITE_ONCE(pe->val[2], 0);
	WRITE_ONCE(pe->val[3], 0);
	WRITE_ONCE(pe->val[4], 0);
	WRITE_ONCE(pe->val[5], 0);
	WRITE_ONCE(pe->val[6], 0);
	WRITE_ONCE(pe->val[7], 0);
297 298
}

299 300 301 302 303 304 305 306 307 308 309 310 311
static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
{
	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
	WRITE_ONCE(pe->val[1], 0);
	WRITE_ONCE(pe->val[2], 0);
	WRITE_ONCE(pe->val[3], 0);
	WRITE_ONCE(pe->val[4], 0);
	WRITE_ONCE(pe->val[5], 0);
	WRITE_ONCE(pe->val[6], 0);
	WRITE_ONCE(pe->val[7], 0);
}

static void
312
intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
313 314 315 316 317 318 319
{
	struct pasid_entry *pe;

	pe = intel_pasid_get_entry(dev, pasid);
	if (WARN_ON(!pe))
		return;

320 321 322 323
	if (fault_ignore && pasid_pte_is_present(pe))
		pasid_clear_entry_with_fpd(pe);
	else
		pasid_clear_entry(pe);
324
}
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400

static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
{
	u64 old;

	old = READ_ONCE(*ptr);
	WRITE_ONCE(*ptr, (old & ~mask) | bits);
}

/*
 * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
 * PASID entry.
 */
static inline void
pasid_set_domain_id(struct pasid_entry *pe, u64 value)
{
	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
}

/*
 * Get domain ID value of a scalable mode PASID entry.
 */
static inline u16
pasid_get_domain_id(struct pasid_entry *pe)
{
	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
}

/*
 * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
 * of a scalable mode PASID entry.
 */
static inline void
pasid_set_slptr(struct pasid_entry *pe, u64 value)
{
	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
}

/*
 * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
 * entry.
 */
static inline void
pasid_set_address_width(struct pasid_entry *pe, u64 value)
{
	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
}

/*
 * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
 * of a scalable mode PASID entry.
 */
static inline void
pasid_set_translation_type(struct pasid_entry *pe, u64 value)
{
	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
}

/*
 * Enable fault processing by clearing the FPD(Fault Processing
 * Disable) field (Bit 1) of a scalable mode PASID entry.
 */
static inline void pasid_set_fault_enable(struct pasid_entry *pe)
{
	pasid_set_bits(&pe->val[0], 1 << 1, 0);
}

/*
 * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
 * scalable mode PASID entry.
 */
static inline void pasid_set_sre(struct pasid_entry *pe)
{
	pasid_set_bits(&pe->val[2], 1 << 0, 1);
}

401 402 403 404 405 406 407 408 409
/*
 * Setup the WPE(Write Protect Enable) field (Bit 132) of a
 * scalable mode PASID entry.
 */
static inline void pasid_set_wpe(struct pasid_entry *pe)
{
	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
}

410 411 412 413 414 415 416 417 418 419 420 421 422 423 424
/*
 * Setup the P(Present) field (Bit 0) of a scalable mode PASID
 * entry.
 */
static inline void pasid_set_present(struct pasid_entry *pe)
{
	pasid_set_bits(&pe->val[0], 1 << 0, 1);
}

/*
 * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
 * entry.
 */
static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
{
425
	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
426 427
}

428 429 430 431 432 433 434 435 436 437
/*
 * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
 * PASID entry.
 */
static inline void
pasid_set_pgsnp(struct pasid_entry *pe)
{
	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
}

438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457
/*
 * Setup the First Level Page table Pointer field (Bit 140~191)
 * of a scalable mode PASID entry.
 */
static inline void
pasid_set_flptr(struct pasid_entry *pe, u64 value)
{
	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
}

/*
 * Setup the First Level Paging Mode field (Bit 130~131) of a
 * scalable mode PASID entry.
 */
static inline void
pasid_set_flpm(struct pasid_entry *pe, u64 value)
{
	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
}

458 459 460 461 462 463 464 465 466 467
/*
 * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
 * of a scalable mode PASID entry.
 */
static inline void
pasid_set_eafe(struct pasid_entry *pe)
{
	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
}

468 469
static void
pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
470
				    u16 did, u32 pasid)
471 472 473
{
	struct qi_desc desc;

474 475
	desc.qw0 = QI_PC_DID(did) | QI_PC_GRAN(QI_PC_PASID_SEL) |
		QI_PC_PASID(pasid) | QI_PC_TYPE;
476 477 478 479
	desc.qw1 = 0;
	desc.qw2 = 0;
	desc.qw3 = 0;

480
	qi_submit_sync(iommu, &desc, 1, 0);
481 482 483 484
}

static void
devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
485
			       struct device *dev, u32 pasid)
486 487 488 489
{
	struct device_domain_info *info;
	u16 sid, qdep, pfsid;

490
	info = get_domain_info(dev);
491 492 493 494 495 496 497
	if (!info || !info->ats_enabled)
		return;

	sid = info->bus << 8 | info->devfn;
	qdep = info->ats_qdep;
	pfsid = info->pfsid;

498 499 500 501 502 503 504 505 506 507
	/*
	 * When PASID 0 is used, it indicates RID2PASID(DMA request w/o PASID),
	 * devTLB flush w/o PASID should be used. For non-zero PASID under
	 * SVA usage, device could do DMA with multiple PASIDs. It is more
	 * efficient to flush devTLB specific to the PASID.
	 */
	if (pasid == PASID_RID2PASID)
		qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT);
	else
		qi_flush_dev_iotlb_pasid(iommu, sid, pfsid, pasid, qdep, 0, 64 - VTD_PAGE_SHIFT);
508 509
}

510
void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
511
				 u32 pasid, bool fault_ignore)
512 513 514 515 516 517 518 519
{
	struct pasid_entry *pte;
	u16 did;

	pte = intel_pasid_get_entry(dev, pasid);
	if (WARN_ON(!pte))
		return;

520 521 522
	if (!(pte->val[0] & PASID_PTE_PRESENT))
		return;

523
	did = pasid_get_domain_id(pte);
524
	intel_pasid_clear_entry(dev, pasid, fault_ignore);
525 526 527 528 529

	if (!ecap_coherent(iommu->ecap))
		clflush_cache_range(pte, sizeof(*pte));

	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
530
	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
531 532 533 534 535 536

	/* Device IOTLB doesn't need to be flushed in caching mode. */
	if (!cap_caching_mode(iommu->cap))
		devtlb_invalidation_with_pasid(iommu, dev, pasid);
}

537 538
static void pasid_flush_caches(struct intel_iommu *iommu,
				struct pasid_entry *pte,
539
			       u32 pasid, u16 did)
540 541 542 543 544 545
{
	if (!ecap_coherent(iommu->ecap))
		clflush_cache_range(pte, sizeof(*pte));

	if (cap_caching_mode(iommu->cap)) {
		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
546
		qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
547 548 549 550 551
	} else {
		iommu_flush_write_buffer(iommu);
	}
}

552 553
static inline int pasid_enable_wpe(struct pasid_entry *pte)
{
554
#ifdef CONFIG_X86
555 556 557 558 559 560 561
	unsigned long cr0 = read_cr0();

	/* CR0.WP is normally set but just to be sure */
	if (unlikely(!(cr0 & X86_CR0_WP))) {
		pr_err_ratelimited("No CPU write protect!\n");
		return -EINVAL;
	}
562
#endif
563 564 565 566 567
	pasid_set_wpe(pte);

	return 0;
};

568 569 570 571 572 573
/*
 * Set up the scalable mode pasid table entry for first only
 * translation type.
 */
int intel_pasid_setup_first_level(struct intel_iommu *iommu,
				  struct device *dev, pgd_t *pgd,
574
				  u32 pasid, u16 did, int flags)
575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
{
	struct pasid_entry *pte;

	if (!ecap_flts(iommu->ecap)) {
		pr_err("No first level translation support on %s\n",
		       iommu->name);
		return -EINVAL;
	}

	pte = intel_pasid_get_entry(dev, pasid);
	if (WARN_ON(!pte))
		return -EINVAL;

	pasid_clear_entry(pte);

	/* Setup the first level page table pointer: */
	pasid_set_flptr(pte, (u64)__pa(pgd));
	if (flags & PASID_FLAG_SUPERVISOR_MODE) {
		if (!ecap_srs(iommu->ecap)) {
			pr_err("No supervisor request support on %s\n",
			       iommu->name);
			return -EINVAL;
		}
		pasid_set_sre(pte);
599 600 601
		if (pasid_enable_wpe(pte))
			return -EINVAL;

602 603
	}

604
	if (flags & PASID_FLAG_FL5LP) {
605 606 607
		if (cap_5lp_support(iommu->cap)) {
			pasid_set_flpm(pte, 1);
		} else {
608
			pr_err("No 5-level paging support for first-level\n");
609 610 611 612
			pasid_clear_entry(pte);
			return -EINVAL;
		}
	}
613

614 615 616
	if (flags & PASID_FLAG_PAGE_SNOOP)
		pasid_set_pgsnp(pte);

617 618 619 620 621
	pasid_set_domain_id(pte, did);
	pasid_set_address_width(pte, iommu->agaw);
	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));

	/* Setup Present and PASID Granular Transfer Type: */
622
	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
623
	pasid_set_present(pte);
624
	pasid_flush_caches(iommu, pte, pasid, did);
625 626 627 628

	return 0;
}

629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647
/*
 * Skip top levels of page tables for iommu which has less agaw
 * than default. Unnecessary for PT mode.
 */
static inline int iommu_skip_agaw(struct dmar_domain *domain,
				  struct intel_iommu *iommu,
				  struct dma_pte **pgd)
{
	int agaw;

	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
		*pgd = phys_to_virt(dma_pte_addr(*pgd));
		if (!dma_pte_present(*pgd))
			return -EINVAL;
	}

	return agaw;
}

648 649 650 651 652
/*
 * Set up the scalable mode pasid entry for second only translation type.
 */
int intel_pasid_setup_second_level(struct intel_iommu *iommu,
				   struct dmar_domain *domain,
653
				   struct device *dev, u32 pasid)
654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
{
	struct pasid_entry *pte;
	struct dma_pte *pgd;
	u64 pgd_val;
	int agaw;
	u16 did;

	/*
	 * If hardware advertises no support for second level
	 * translation, return directly.
	 */
	if (!ecap_slts(iommu->ecap)) {
		pr_err("No second level translation support on %s\n",
		       iommu->name);
		return -EINVAL;
	}

	pgd = domain->pgd;
672 673 674 675
	agaw = iommu_skip_agaw(domain, iommu, &pgd);
	if (agaw < 0) {
		dev_err(dev, "Invalid domain page table\n");
		return -EINVAL;
676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
	}

	pgd_val = virt_to_phys(pgd);
	did = domain->iommu_did[iommu->seq_id];

	pte = intel_pasid_get_entry(dev, pasid);
	if (!pte) {
		dev_err(dev, "Failed to get pasid entry of PASID %d\n", pasid);
		return -ENODEV;
	}

	pasid_clear_entry(pte);
	pasid_set_domain_id(pte, did);
	pasid_set_slptr(pte, pgd_val);
	pasid_set_address_width(pte, agaw);
691
	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
692 693 694
	pasid_set_fault_enable(pte);
	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));

695 696 697
	if (domain->domain.type == IOMMU_DOMAIN_UNMANAGED)
		pasid_set_pgsnp(pte);

698 699 700 701
	/*
	 * Since it is a second level only translation setup, we should
	 * set SRE bit as well (addresses are expected to be GPAs).
	 */
702 703
	if (pasid != PASID_RID2PASID)
		pasid_set_sre(pte);
704
	pasid_set_present(pte);
705
	pasid_flush_caches(iommu, pte, pasid, did);
706 707 708 709 710 711 712 713 714

	return 0;
}

/*
 * Set up the scalable mode pasid entry for passthrough translation type.
 */
int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
				   struct dmar_domain *domain,
715
				   struct device *dev, u32 pasid)
716 717 718 719 720 721 722 723 724 725 726 727 728
{
	u16 did = FLPT_DEFAULT_DID;
	struct pasid_entry *pte;

	pte = intel_pasid_get_entry(dev, pasid);
	if (!pte) {
		dev_err(dev, "Failed to get pasid entry of PASID %d\n", pasid);
		return -ENODEV;
	}

	pasid_clear_entry(pte);
	pasid_set_domain_id(pte, did);
	pasid_set_address_width(pte, iommu->agaw);
729
	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT);
730 731 732 733 734 735 736 737 738
	pasid_set_fault_enable(pte);
	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));

	/*
	 * We should set SRE bit as well since the addresses are expected
	 * to be GPAs.
	 */
	pasid_set_sre(pte);
	pasid_set_present(pte);
739
	pasid_flush_caches(iommu, pte, pasid, did);
740 741 742

	return 0;
}
743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761

static int
intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
			    struct iommu_gpasid_bind_data_vtd *pasid_data)
{
	/*
	 * Not all guest PASID table entry fields are passed down during bind,
	 * here we only set up the ones that are dependent on guest settings.
	 * Execution related bits such as NXE, SMEP are not supported.
	 * Other fields, such as snoop related, are set based on host needs
	 * regardless of guest settings.
	 */
	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) {
		if (!ecap_srs(iommu->ecap)) {
			pr_err_ratelimited("No supervisor request support on %s\n",
					   iommu->name);
			return -EINVAL;
		}
		pasid_set_sre(pte);
762 763 764
		/* Enable write protect WP if guest requested */
		if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_WPE)
			pasid_set_wpe(pte);
765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
	}

	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) {
		if (!ecap_eafs(iommu->ecap)) {
			pr_err_ratelimited("No extended access flag support on %s\n",
					   iommu->name);
			return -EINVAL;
		}
		pasid_set_eafe(pte);
	}

	/*
	 * Memory type is only applicable to devices inside processor coherent
	 * domain. Will add MTS support once coherent devices are available.
	 */
	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_MTS_MASK) {
		pr_warn_ratelimited("No memory type support %s\n",
				    iommu->name);
		return -EINVAL;
	}

	return 0;
}

/**
 * intel_pasid_setup_nested() - Set up PASID entry for nested translation.
 * This could be used for guest shared virtual address. In this case, the
 * first level page tables are used for GVA-GPA translation in the guest,
 * second level page tables are used for GPA-HPA translation.
 *
 * @iommu:      IOMMU which the device belong to
 * @dev:        Device to be set up for translation
 * @gpgd:       FLPTPTR: First Level Page translation pointer in GPA
 * @pasid:      PASID to be programmed in the device PASID table
 * @pasid_data: Additional PASID info from the guest bind request
 * @domain:     Domain info for setting up second level page tables
 * @addr_width: Address width of the first level (guest)
 */
int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
804
			     pgd_t *gpgd, u32 pasid,
805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
			     struct iommu_gpasid_bind_data_vtd *pasid_data,
			     struct dmar_domain *domain, int addr_width)
{
	struct pasid_entry *pte;
	struct dma_pte *pgd;
	int ret = 0;
	u64 pgd_val;
	int agaw;
	u16 did;

	if (!ecap_nest(iommu->ecap)) {
		pr_err_ratelimited("IOMMU: %s: No nested translation support\n",
				   iommu->name);
		return -EINVAL;
	}

	if (!(domain->flags & DOMAIN_FLAG_NESTING_MODE)) {
		pr_err_ratelimited("Domain is not in nesting mode, %x\n",
				   domain->flags);
		return -EINVAL;
	}

	pte = intel_pasid_get_entry(dev, pasid);
	if (WARN_ON(!pte))
		return -EINVAL;

	/*
	 * Caller must ensure PASID entry is not in use, i.e. not bind the
	 * same PASID to the same device twice.
	 */
	if (pasid_pte_is_present(pte))
		return -EBUSY;

	pasid_clear_entry(pte);

	/* Sanity checking performed by caller to make sure address
	 * width matching in two dimensions:
	 * 1. CPU vs. IOMMU
	 * 2. Guest vs. Host.
	 */
	switch (addr_width) {
#ifdef CONFIG_X86
	case ADDR_WIDTH_5LEVEL:
		if (!cpu_feature_enabled(X86_FEATURE_LA57) ||
		    !cap_5lp_support(iommu->cap)) {
			dev_err_ratelimited(dev,
					    "5-level paging not supported\n");
			return -EINVAL;
		}

		pasid_set_flpm(pte, 1);
		break;
#endif
	case ADDR_WIDTH_4LEVEL:
		pasid_set_flpm(pte, 0);
		break;
	default:
		dev_err_ratelimited(dev, "Invalid guest address width %d\n",
				    addr_width);
		return -EINVAL;
	}

	/* First level PGD is in GPA, must be supported by the second level */
868
	if ((uintptr_t)gpgd > domain->max_addr) {
869
		dev_err_ratelimited(dev,
870 871
				    "Guest PGD %lx not supported, max %llx\n",
				    (uintptr_t)gpgd, domain->max_addr);
872 873
		return -EINVAL;
	}
874
	pasid_set_flptr(pte, (uintptr_t)gpgd);
875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903

	ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data);
	if (ret)
		return ret;

	/* Setup the second level based on the given domain */
	pgd = domain->pgd;

	agaw = iommu_skip_agaw(domain, iommu, &pgd);
	if (agaw < 0) {
		dev_err_ratelimited(dev, "Invalid domain page table\n");
		return -EINVAL;
	}
	pgd_val = virt_to_phys(pgd);
	pasid_set_slptr(pte, pgd_val);
	pasid_set_fault_enable(pte);

	did = domain->iommu_did[iommu->seq_id];
	pasid_set_domain_id(pte, did);

	pasid_set_address_width(pte, agaw);
	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));

	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
	pasid_set_present(pte);
	pasid_flush_caches(iommu, pte, pasid, did);

	return ret;
}
反馈
建议
客服 返回
顶部