pages.c 55.1 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
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES.
 *
 * The iopt_pages is the center of the storage and motion of PFNs. Each
 * iopt_pages represents a logical linear array of full PFNs. The array is 0
 * based and has npages in it. Accessors use 'index' to refer to the entry in
 * this logical array, regardless of its storage location.
 *
 * PFNs are stored in a tiered scheme:
 *  1) iopt_pages::pinned_pfns xarray
 *  2) An iommu_domain
 *  3) The origin of the PFNs, i.e. the userspace pointer
 *
 * PFN have to be copied between all combinations of tiers, depending on the
 * configuration.
 *
 * When a PFN is taken out of the userspace pointer it is pinned exactly once.
 * The storage locations of the PFN's index are tracked in the two interval
 * trees. If no interval includes the index then it is not pinned.
 *
 * If access_itree includes the PFN's index then an in-kernel access has
 * requested the page. The PFN is stored in the xarray so other requestors can
 * continue to find it.
 *
 * If the domains_itree includes the PFN's index then an iommu_domain is storing
 * the PFN and it can be read back using iommu_iova_to_phys(). To avoid
 * duplicating storage the xarray is not used if only iommu_domains are using
 * the PFN's index.
 *
 * As a general principle this is designed so that destroy never fails. This
 * means removing an iommu_domain or releasing a in-kernel access will not fail
 * due to insufficient memory. In practice this means some cases have to hold
 * PFNs in the xarray even though they are also being stored in an iommu_domain.
 *
 * While the iopt_pages can use an iommu_domain as storage, it does not have an
 * IOVA itself. Instead the iopt_area represents a range of IOVA and uses the
 * iopt_pages as the PFN provider. Multiple iopt_areas can share the iopt_pages
 * and reference their own slice of the PFN array, with sub page granularity.
 *
 * In this file the term 'last' indicates an inclusive and closed interval, eg
 * [0,0] refers to a single PFN. 'end' means an open range, eg [0,0) refers to
 * no PFNs.
 *
 * Be cautious of overflow. An IOVA can go all the way up to U64_MAX, so
 * last_iova + 1 can overflow. An iopt_pages index will always be much less than
 * ULONG_MAX so last_index + 1 cannot overflow.
 */
#include <linux/overflow.h>
#include <linux/slab.h>
#include <linux/iommu.h>
#include <linux/sched/mm.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
#include <linux/iommufd.h>

#include "io_pagetable.h"
#include "double_span.h"

59
#ifndef CONFIG_IOMMUFD_TEST
60
#define TEMP_MEMORY_LIMIT 65536
61 62 63
#else
#define TEMP_MEMORY_LIMIT iommufd_test_memory_limit
#endif
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
#define BATCH_BACKUP_SIZE 32

/*
 * More memory makes pin_user_pages() and the batching more efficient, but as
 * this is only a performance optimization don't try too hard to get it. A 64k
 * allocation can hold about 26M of 4k pages and 13G of 2M pages in an
 * pfn_batch. Various destroy paths cannot fail and provide a small amount of
 * stack memory as a backup contingency. If backup_len is given this cannot
 * fail.
 */
static void *temp_kmalloc(size_t *size, void *backup, size_t backup_len)
{
	void *res;

	if (WARN_ON(*size == 0))
		return NULL;

	if (*size < backup_len)
		return backup;
83 84 85 86

	if (!backup && iommufd_should_fail())
		return NULL;

87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
	*size = min_t(size_t, *size, TEMP_MEMORY_LIMIT);
	res = kmalloc(*size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
	if (res)
		return res;
	*size = PAGE_SIZE;
	if (backup_len) {
		res = kmalloc(*size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
		if (res)
			return res;
		*size = backup_len;
		return backup;
	}
	return kmalloc(*size, GFP_KERNEL);
}

void interval_tree_double_span_iter_update(
	struct interval_tree_double_span_iter *iter)
{
	unsigned long last_hole = ULONG_MAX;
	unsigned int i;

	for (i = 0; i != ARRAY_SIZE(iter->spans); i++) {
		if (interval_tree_span_iter_done(&iter->spans[i])) {
			iter->is_used = -1;
			return;
		}

		if (iter->spans[i].is_hole) {
			last_hole = min(last_hole, iter->spans[i].last_hole);
			continue;
		}

		iter->is_used = i + 1;
		iter->start_used = iter->spans[i].start_used;
		iter->last_used = min(iter->spans[i].last_used, last_hole);
		return;
	}

	iter->is_used = 0;
	iter->start_hole = iter->spans[0].start_hole;
	iter->last_hole =
		min(iter->spans[0].last_hole, iter->spans[1].last_hole);
}

void interval_tree_double_span_iter_first(
	struct interval_tree_double_span_iter *iter,
	struct rb_root_cached *itree1, struct rb_root_cached *itree2,
	unsigned long first_index, unsigned long last_index)
{
	unsigned int i;

	iter->itrees[0] = itree1;
	iter->itrees[1] = itree2;
	for (i = 0; i != ARRAY_SIZE(iter->spans); i++)
		interval_tree_span_iter_first(&iter->spans[i], iter->itrees[i],
					      first_index, last_index);
	interval_tree_double_span_iter_update(iter);
}

void interval_tree_double_span_iter_next(
	struct interval_tree_double_span_iter *iter)
{
	unsigned int i;

	if (iter->is_used == -1 ||
	    iter->last_hole == iter->spans[0].last_index) {
		iter->is_used = -1;
		return;
	}

	for (i = 0; i != ARRAY_SIZE(iter->spans); i++)
		interval_tree_span_iter_advance(
			&iter->spans[i], iter->itrees[i], iter->last_hole + 1);
	interval_tree_double_span_iter_update(iter);
}

static void iopt_pages_add_npinned(struct iopt_pages *pages, size_t npages)
{
165 166 167 168 169
	int rc;

	rc = check_add_overflow(pages->npinned, npages, &pages->npinned);
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(rc || pages->npinned > pages->npages);
170 171 172 173
}

static void iopt_pages_sub_npinned(struct iopt_pages *pages, size_t npages)
{
174 175 176 177 178
	int rc;

	rc = check_sub_overflow(pages->npinned, npages, &pages->npinned);
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(rc || pages->npinned > pages->npages);
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
}

static void iopt_pages_err_unpin(struct iopt_pages *pages,
				 unsigned long start_index,
				 unsigned long last_index,
				 struct page **page_list)
{
	unsigned long npages = last_index - start_index + 1;

	unpin_user_pages(page_list, npages);
	iopt_pages_sub_npinned(pages, npages);
}

/*
 * index is the number of PAGE_SIZE units from the start of the area's
 * iopt_pages. If the iova is sub page-size then the area has an iova that
 * covers a portion of the first and last pages in the range.
 */
static unsigned long iopt_area_index_to_iova(struct iopt_area *area,
					     unsigned long index)
{
200 201 202
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(index < iopt_area_index(area) ||
			index > iopt_area_last_index(area));
203 204 205 206 207 208 209 210 211
	index -= iopt_area_index(area);
	if (index == 0)
		return iopt_area_iova(area);
	return iopt_area_iova(area) - area->page_offset + index * PAGE_SIZE;
}

static unsigned long iopt_area_index_to_iova_last(struct iopt_area *area,
						  unsigned long index)
{
212 213 214
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(index < iopt_area_index(area) ||
			index > iopt_area_last_index(area));
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236
	if (index == iopt_area_last_index(area))
		return iopt_area_last_iova(area);
	return iopt_area_iova(area) - area->page_offset +
	       (index - iopt_area_index(area) + 1) * PAGE_SIZE - 1;
}

static void iommu_unmap_nofail(struct iommu_domain *domain, unsigned long iova,
			       size_t size)
{
	size_t ret;

	ret = iommu_unmap(domain, iova, size);
	/*
	 * It is a logic error in this code or a driver bug if the IOMMU unmaps
	 * something other than exactly as requested. This implies that the
	 * iommu driver may not fail unmap for reasons beyond bad agruments.
	 * Particularly, the iommu driver may not do a memory allocation on the
	 * unmap path.
	 */
	WARN_ON(ret != size);
}

237 238 239 240 241 242 243 244 245 246 247 248
static void iopt_area_unmap_domain_range(struct iopt_area *area,
					 struct iommu_domain *domain,
					 unsigned long start_index,
					 unsigned long last_index)
{
	unsigned long start_iova = iopt_area_index_to_iova(area, start_index);

	iommu_unmap_nofail(domain, start_iova,
			   iopt_area_index_to_iova_last(area, last_index) -
				   start_iova + 1);
}

249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
static struct iopt_area *iopt_pages_find_domain_area(struct iopt_pages *pages,
						     unsigned long index)
{
	struct interval_tree_node *node;

	node = interval_tree_iter_first(&pages->domains_itree, index, index);
	if (!node)
		return NULL;
	return container_of(node, struct iopt_area, pages_node);
}

/*
 * A simple datastructure to hold a vector of PFNs, optimized for contiguous
 * PFNs. This is used as a temporary holding memory for shuttling pfns from one
 * place to another. Generally everything is made more efficient if operations
 * work on the largest possible grouping of pfns. eg fewer lock/unlock cycles,
 * better cache locality, etc
 */
struct pfn_batch {
	unsigned long *pfns;
	u32 *npfns;
	unsigned int array_size;
	unsigned int end;
	unsigned int total_pfns;
};

static void batch_clear(struct pfn_batch *batch)
{
	batch->total_pfns = 0;
	batch->end = 0;
	batch->pfns[0] = 0;
	batch->npfns[0] = 0;
}

/*
 * Carry means we carry a portion of the final hugepage over to the front of the
 * batch
 */
static void batch_clear_carry(struct pfn_batch *batch, unsigned int keep_pfns)
{
	if (!keep_pfns)
		return batch_clear(batch);

292 293 294 295
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(!batch->end ||
			batch->npfns[batch->end - 1] < keep_pfns);

296 297 298
	batch->total_pfns = keep_pfns;
	batch->pfns[0] = batch->pfns[batch->end - 1] +
			 (batch->npfns[batch->end - 1] - keep_pfns);
299
	batch->npfns[0] = keep_pfns;
300
	batch->end = 1;
301 302 303 304 305 306
}

static void batch_skip_carry(struct pfn_batch *batch, unsigned int skip_pfns)
{
	if (!batch->total_pfns)
		return;
307 308
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(batch->total_pfns != batch->npfns[0]);
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
	skip_pfns = min(batch->total_pfns, skip_pfns);
	batch->pfns[0] += skip_pfns;
	batch->npfns[0] -= skip_pfns;
	batch->total_pfns -= skip_pfns;
}

static int __batch_init(struct pfn_batch *batch, size_t max_pages, void *backup,
			size_t backup_len)
{
	const size_t elmsz = sizeof(*batch->pfns) + sizeof(*batch->npfns);
	size_t size = max_pages * elmsz;

	batch->pfns = temp_kmalloc(&size, backup, backup_len);
	if (!batch->pfns)
		return -ENOMEM;
324 325
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && WARN_ON(size < elmsz))
		return -EINVAL;
326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348
	batch->array_size = size / elmsz;
	batch->npfns = (u32 *)(batch->pfns + batch->array_size);
	batch_clear(batch);
	return 0;
}

static int batch_init(struct pfn_batch *batch, size_t max_pages)
{
	return __batch_init(batch, max_pages, NULL, 0);
}

static void batch_init_backup(struct pfn_batch *batch, size_t max_pages,
			      void *backup, size_t backup_len)
{
	__batch_init(batch, max_pages, backup, backup_len);
}

static void batch_destroy(struct pfn_batch *batch, void *backup)
{
	if (batch->pfns != backup)
		kfree(batch->pfns);
}

349
/* true if the pfn was added, false otherwise */
350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424
static bool batch_add_pfn(struct pfn_batch *batch, unsigned long pfn)
{
	const unsigned int MAX_NPFNS = type_max(typeof(*batch->npfns));

	if (batch->end &&
	    pfn == batch->pfns[batch->end - 1] + batch->npfns[batch->end - 1] &&
	    batch->npfns[batch->end - 1] != MAX_NPFNS) {
		batch->npfns[batch->end - 1]++;
		batch->total_pfns++;
		return true;
	}
	if (batch->end == batch->array_size)
		return false;
	batch->total_pfns++;
	batch->pfns[batch->end] = pfn;
	batch->npfns[batch->end] = 1;
	batch->end++;
	return true;
}

/*
 * Fill the batch with pfns from the domain. When the batch is full, or it
 * reaches last_index, the function will return. The caller should use
 * batch->total_pfns to determine the starting point for the next iteration.
 */
static void batch_from_domain(struct pfn_batch *batch,
			      struct iommu_domain *domain,
			      struct iopt_area *area, unsigned long start_index,
			      unsigned long last_index)
{
	unsigned int page_offset = 0;
	unsigned long iova;
	phys_addr_t phys;

	iova = iopt_area_index_to_iova(area, start_index);
	if (start_index == iopt_area_index(area))
		page_offset = area->page_offset;
	while (start_index <= last_index) {
		/*
		 * This is pretty slow, it would be nice to get the page size
		 * back from the driver, or have the driver directly fill the
		 * batch.
		 */
		phys = iommu_iova_to_phys(domain, iova) - page_offset;
		if (!batch_add_pfn(batch, PHYS_PFN(phys)))
			return;
		iova += PAGE_SIZE - page_offset;
		page_offset = 0;
		start_index++;
	}
}

static struct page **raw_pages_from_domain(struct iommu_domain *domain,
					   struct iopt_area *area,
					   unsigned long start_index,
					   unsigned long last_index,
					   struct page **out_pages)
{
	unsigned int page_offset = 0;
	unsigned long iova;
	phys_addr_t phys;

	iova = iopt_area_index_to_iova(area, start_index);
	if (start_index == iopt_area_index(area))
		page_offset = area->page_offset;
	while (start_index <= last_index) {
		phys = iommu_iova_to_phys(domain, iova) - page_offset;
		*(out_pages++) = pfn_to_page(PHYS_PFN(phys));
		iova += PAGE_SIZE - page_offset;
		page_offset = 0;
		start_index++;
	}
	return out_pages;
}

425
/* Continues reading a domain until we reach a discontinuity in the pfns. */
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
static void batch_from_domain_continue(struct pfn_batch *batch,
				       struct iommu_domain *domain,
				       struct iopt_area *area,
				       unsigned long start_index,
				       unsigned long last_index)
{
	unsigned int array_size = batch->array_size;

	batch->array_size = batch->end;
	batch_from_domain(batch, domain, area, start_index, last_index);
	batch->array_size = array_size;
}

/*
 * This is part of the VFIO compatibility support for VFIO_TYPE1_IOMMU. That
 * mode permits splitting a mapped area up, and then one of the splits is
 * unmapped. Doing this normally would cause us to violate our invariant of
 * pairing map/unmap. Thus, to support old VFIO compatibility disable support
 * for batching consecutive PFNs. All PFNs mapped into the iommu are done in
 * PAGE_SIZE units, not larger or smaller.
 */
static int batch_iommu_map_small(struct iommu_domain *domain,
				 unsigned long iova, phys_addr_t paddr,
				 size_t size, int prot)
{
	unsigned long start_iova = iova;
	int rc;

454 455 456 457
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(paddr % PAGE_SIZE || iova % PAGE_SIZE ||
			size % PAGE_SIZE);

458
	while (size) {
459
		rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot,
460
			       GFP_KERNEL_ACCOUNT);
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
		if (rc)
			goto err_unmap;
		iova += PAGE_SIZE;
		paddr += PAGE_SIZE;
		size -= PAGE_SIZE;
	}
	return 0;

err_unmap:
	if (start_iova != iova)
		iommu_unmap_nofail(domain, start_iova, iova - start_iova);
	return rc;
}

static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain,
			   struct iopt_area *area, unsigned long start_index)
{
	bool disable_large_pages = area->iopt->disable_large_pages;
	unsigned long last_iova = iopt_area_last_iova(area);
	unsigned int page_offset = 0;
	unsigned long start_iova;
	unsigned long next_iova;
	unsigned int cur = 0;
	unsigned long iova;
	int rc;

	/* The first index might be a partial page */
	if (start_index == iopt_area_index(area))
		page_offset = area->page_offset;
	next_iova = iova = start_iova =
		iopt_area_index_to_iova(area, start_index);
	while (cur < batch->end) {
		next_iova = min(last_iova + 1,
				next_iova + batch->npfns[cur] * PAGE_SIZE -
					page_offset);
		if (disable_large_pages)
			rc = batch_iommu_map_small(
				domain, iova,
				PFN_PHYS(batch->pfns[cur]) + page_offset,
				next_iova - iova, area->iommu_prot);
		else
			rc = iommu_map(domain, iova,
				       PFN_PHYS(batch->pfns[cur]) + page_offset,
504
				       next_iova - iova, area->iommu_prot,
505
				       GFP_KERNEL_ACCOUNT);
506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
		if (rc)
			goto err_unmap;
		iova = next_iova;
		page_offset = 0;
		cur++;
	}
	return 0;
err_unmap:
	if (start_iova != iova)
		iommu_unmap_nofail(domain, start_iova, iova - start_iova);
	return rc;
}

static void batch_from_xarray(struct pfn_batch *batch, struct xarray *xa,
			      unsigned long start_index,
			      unsigned long last_index)
{
	XA_STATE(xas, xa, start_index);
	void *entry;

	rcu_read_lock();
	while (true) {
		entry = xas_next(&xas);
		if (xas_retry(&xas, entry))
			continue;
		WARN_ON(!xa_is_value(entry));
		if (!batch_add_pfn(batch, xa_to_value(entry)) ||
		    start_index == last_index)
			break;
		start_index++;
	}
	rcu_read_unlock();
}

static void batch_from_xarray_clear(struct pfn_batch *batch, struct xarray *xa,
				    unsigned long start_index,
				    unsigned long last_index)
{
	XA_STATE(xas, xa, start_index);
	void *entry;

	xas_lock(&xas);
	while (true) {
		entry = xas_next(&xas);
		if (xas_retry(&xas, entry))
			continue;
		WARN_ON(!xa_is_value(entry));
		if (!batch_add_pfn(batch, xa_to_value(entry)))
			break;
		xas_store(&xas, NULL);
		if (start_index == last_index)
			break;
		start_index++;
	}
	xas_unlock(&xas);
}

static void clear_xarray(struct xarray *xa, unsigned long start_index,
			 unsigned long last_index)
{
	XA_STATE(xas, xa, start_index);
	void *entry;

	xas_lock(&xas);
	xas_for_each(&xas, entry, last_index)
		xas_store(&xas, NULL);
	xas_unlock(&xas);
}

static int pages_to_xarray(struct xarray *xa, unsigned long start_index,
			   unsigned long last_index, struct page **pages)
{
	struct page **end_pages = pages + (last_index - start_index) + 1;
579
	struct page **half_pages = pages + (end_pages - pages) / 2;
580 581 582 583 584 585 586
	XA_STATE(xas, xa, start_index);

	do {
		void *old;

		xas_lock(&xas);
		while (pages != end_pages) {
587 588 589 590 591 592 593 594 595
			/* xarray does not participate in fault injection */
			if (pages == half_pages && iommufd_should_fail()) {
				xas_set_err(&xas, -EINVAL);
				xas_unlock(&xas);
				/* aka xas_destroy() */
				xas_nomem(&xas, GFP_KERNEL);
				goto err_clear;
			}

596 597 598 599 600 601 602 603 604 605
			old = xas_store(&xas, xa_mk_value(page_to_pfn(*pages)));
			if (xas_error(&xas))
				break;
			WARN_ON(old);
			pages++;
			xas_next(&xas);
		}
		xas_unlock(&xas);
	} while (xas_nomem(&xas, GFP_KERNEL));

606
err_clear:
607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
	if (xas_error(&xas)) {
		if (xas.xa_index != start_index)
			clear_xarray(xa, start_index, xas.xa_index - 1);
		return xas_error(&xas);
	}
	return 0;
}

static void batch_from_pages(struct pfn_batch *batch, struct page **pages,
			     size_t npages)
{
	struct page **end = pages + npages;

	for (; pages != end; pages++)
		if (!batch_add_pfn(batch, page_to_pfn(*pages)))
			break;
}

static void batch_unpin(struct pfn_batch *batch, struct iopt_pages *pages,
			unsigned int first_page_off, size_t npages)
{
	unsigned int cur = 0;

	while (first_page_off) {
		if (batch->npfns[cur] > first_page_off)
			break;
		first_page_off -= batch->npfns[cur];
		cur++;
	}

	while (npages) {
		size_t to_unpin = min_t(size_t, npages,
					batch->npfns[cur] - first_page_off);

		unpin_user_page_range_dirty_lock(
			pfn_to_page(batch->pfns[cur] + first_page_off),
			to_unpin, pages->writable);
		iopt_pages_sub_npinned(pages, to_unpin);
		cur++;
		first_page_off = 0;
		npages -= to_unpin;
	}
}

static void copy_data_page(struct page *page, void *data, unsigned long offset,
			   size_t length, unsigned int flags)
{
	void *mem;

	mem = kmap_local_page(page);
	if (flags & IOMMUFD_ACCESS_RW_WRITE) {
		memcpy(mem + offset, data, length);
		set_page_dirty_lock(page);
	} else {
		memcpy(data, mem + offset, length);
	}
	kunmap_local(mem);
}

static unsigned long batch_rw(struct pfn_batch *batch, void *data,
			      unsigned long offset, unsigned long length,
			      unsigned int flags)
{
	unsigned long copied = 0;
	unsigned int npage = 0;
	unsigned int cur = 0;

	while (cur < batch->end) {
		unsigned long bytes = min(length, PAGE_SIZE - offset);

		copy_data_page(pfn_to_page(batch->pfns[cur] + npage), data,
			       offset, bytes, flags);
		offset = 0;
		length -= bytes;
		data += bytes;
		copied += bytes;
		npage++;
		if (npage == batch->npfns[cur]) {
			npage = 0;
			cur++;
		}
		if (!length)
			break;
	}
	return copied;
}

/* pfn_reader_user is just the pin_user_pages() path */
struct pfn_reader_user {
	struct page **upages;
	size_t upages_len;
	unsigned long upages_start;
	unsigned long upages_end;
	unsigned int gup_flags;
	/*
	 * 1 means mmget() and mmap_read_lock(), 0 means only mmget(), -1 is
	 * neither
	 */
	int locked;
};

static void pfn_reader_user_init(struct pfn_reader_user *user,
				 struct iopt_pages *pages)
{
	user->upages = NULL;
	user->upages_start = 0;
	user->upages_end = 0;
	user->locked = -1;

716 717 718
	user->gup_flags = FOLL_LONGTERM;
	if (pages->writable)
		user->gup_flags |= FOLL_WRITE;
719 720 721 722 723 724 725 726 727 728
}

static void pfn_reader_user_destroy(struct pfn_reader_user *user,
				    struct iopt_pages *pages)
{
	if (user->locked != -1) {
		if (user->locked)
			mmap_read_unlock(pages->source_mm);
		if (pages->source_mm != current->mm)
			mmput(pages->source_mm);
729
		user->locked = -1;
730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
	}

	kfree(user->upages);
	user->upages = NULL;
}

static int pfn_reader_user_pin(struct pfn_reader_user *user,
			       struct iopt_pages *pages,
			       unsigned long start_index,
			       unsigned long last_index)
{
	bool remote_mm = pages->source_mm != current->mm;
	unsigned long npages;
	uintptr_t uptr;
	long rc;

746 747 748 749
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
	    WARN_ON(last_index < start_index))
		return -EINVAL;

750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774
	if (!user->upages) {
		/* All undone in pfn_reader_destroy() */
		user->upages_len =
			(last_index - start_index + 1) * sizeof(*user->upages);
		user->upages = temp_kmalloc(&user->upages_len, NULL, 0);
		if (!user->upages)
			return -ENOMEM;
	}

	if (user->locked == -1) {
		/*
		 * The majority of usages will run the map task within the mm
		 * providing the pages, so we can optimize into
		 * get_user_pages_fast()
		 */
		if (remote_mm) {
			if (!mmget_not_zero(pages->source_mm))
				return -EFAULT;
		}
		user->locked = 0;
	}

	npages = min_t(unsigned long, last_index - start_index + 1,
		       user->upages_len / sizeof(*user->upages));

775 776 777 778

	if (iommufd_should_fail())
		return -EFAULT;

779 780 781 782 783 784 785 786 787 788
	uptr = (uintptr_t)(pages->uptr + start_index * PAGE_SIZE);
	if (!remote_mm)
		rc = pin_user_pages_fast(uptr, npages, user->gup_flags,
					 user->upages);
	else {
		if (!user->locked) {
			mmap_read_lock(pages->source_mm);
			user->locked = 1;
		}
		rc = pin_user_pages_remote(pages->source_mm, uptr, npages,
789
					   user->gup_flags, user->upages,
790
					   &user->locked);
791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917
	}
	if (rc <= 0) {
		if (WARN_ON(!rc))
			return -EFAULT;
		return rc;
	}
	iopt_pages_add_npinned(pages, rc);
	user->upages_start = start_index;
	user->upages_end = start_index + rc;
	return 0;
}

/* This is the "modern" and faster accounting method used by io_uring */
static int incr_user_locked_vm(struct iopt_pages *pages, unsigned long npages)
{
	unsigned long lock_limit;
	unsigned long cur_pages;
	unsigned long new_pages;

	lock_limit = task_rlimit(pages->source_task, RLIMIT_MEMLOCK) >>
		     PAGE_SHIFT;
	do {
		cur_pages = atomic_long_read(&pages->source_user->locked_vm);
		new_pages = cur_pages + npages;
		if (new_pages > lock_limit)
			return -ENOMEM;
	} while (atomic_long_cmpxchg(&pages->source_user->locked_vm, cur_pages,
				     new_pages) != cur_pages);
	return 0;
}

static void decr_user_locked_vm(struct iopt_pages *pages, unsigned long npages)
{
	if (WARN_ON(atomic_long_read(&pages->source_user->locked_vm) < npages))
		return;
	atomic_long_sub(npages, &pages->source_user->locked_vm);
}

/* This is the accounting method used for compatibility with VFIO */
static int update_mm_locked_vm(struct iopt_pages *pages, unsigned long npages,
			       bool inc, struct pfn_reader_user *user)
{
	bool do_put = false;
	int rc;

	if (user && user->locked) {
		mmap_read_unlock(pages->source_mm);
		user->locked = 0;
		/* If we had the lock then we also have a get */
	} else if ((!user || !user->upages) &&
		   pages->source_mm != current->mm) {
		if (!mmget_not_zero(pages->source_mm))
			return -EINVAL;
		do_put = true;
	}

	mmap_write_lock(pages->source_mm);
	rc = __account_locked_vm(pages->source_mm, npages, inc,
				 pages->source_task, false);
	mmap_write_unlock(pages->source_mm);

	if (do_put)
		mmput(pages->source_mm);
	return rc;
}

static int do_update_pinned(struct iopt_pages *pages, unsigned long npages,
			    bool inc, struct pfn_reader_user *user)
{
	int rc = 0;

	switch (pages->account_mode) {
	case IOPT_PAGES_ACCOUNT_NONE:
		break;
	case IOPT_PAGES_ACCOUNT_USER:
		if (inc)
			rc = incr_user_locked_vm(pages, npages);
		else
			decr_user_locked_vm(pages, npages);
		break;
	case IOPT_PAGES_ACCOUNT_MM:
		rc = update_mm_locked_vm(pages, npages, inc, user);
		break;
	}
	if (rc)
		return rc;

	pages->last_npinned = pages->npinned;
	if (inc)
		atomic64_add(npages, &pages->source_mm->pinned_vm);
	else
		atomic64_sub(npages, &pages->source_mm->pinned_vm);
	return 0;
}

static void update_unpinned(struct iopt_pages *pages)
{
	if (WARN_ON(pages->npinned > pages->last_npinned))
		return;
	if (pages->npinned == pages->last_npinned)
		return;
	do_update_pinned(pages, pages->last_npinned - pages->npinned, false,
			 NULL);
}

/*
 * Changes in the number of pages pinned is done after the pages have been read
 * and processed. If the user lacked the limit then the error unwind will unpin
 * everything that was just pinned. This is because it is expensive to calculate
 * how many pages we have already pinned within a range to generate an accurate
 * prediction in advance of doing the work to actually pin them.
 */
static int pfn_reader_user_update_pinned(struct pfn_reader_user *user,
					 struct iopt_pages *pages)
{
	unsigned long npages;
	bool inc;

	lockdep_assert_held(&pages->mutex);

	if (pages->npinned == pages->last_npinned)
		return 0;

	if (pages->npinned < pages->last_npinned) {
		npages = pages->last_npinned - pages->npinned;
		inc = false;
	} else {
918 919
		if (iommufd_should_fail())
			return -ENOMEM;
920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982
		npages = pages->npinned - pages->last_npinned;
		inc = true;
	}
	return do_update_pinned(pages, npages, inc, user);
}

/*
 * PFNs are stored in three places, in order of preference:
 * - The iopt_pages xarray. This is only populated if there is a
 *   iopt_pages_access
 * - The iommu_domain under an area
 * - The original PFN source, ie pages->source_mm
 *
 * This iterator reads the pfns optimizing to load according to the
 * above order.
 */
struct pfn_reader {
	struct iopt_pages *pages;
	struct interval_tree_double_span_iter span;
	struct pfn_batch batch;
	unsigned long batch_start_index;
	unsigned long batch_end_index;
	unsigned long last_index;

	struct pfn_reader_user user;
};

static int pfn_reader_update_pinned(struct pfn_reader *pfns)
{
	return pfn_reader_user_update_pinned(&pfns->user, pfns->pages);
}

/*
 * The batch can contain a mixture of pages that are still in use and pages that
 * need to be unpinned. Unpin only pages that are not held anywhere else.
 */
static void pfn_reader_unpin(struct pfn_reader *pfns)
{
	unsigned long last = pfns->batch_end_index - 1;
	unsigned long start = pfns->batch_start_index;
	struct interval_tree_double_span_iter span;
	struct iopt_pages *pages = pfns->pages;

	lockdep_assert_held(&pages->mutex);

	interval_tree_for_each_double_span(&span, &pages->access_itree,
					   &pages->domains_itree, start, last) {
		if (span.is_used)
			continue;

		batch_unpin(&pfns->batch, pages, span.start_hole - start,
			    span.last_hole - span.start_hole + 1);
	}
}

/* Process a single span to load it from the proper storage */
static int pfn_reader_fill_span(struct pfn_reader *pfns)
{
	struct interval_tree_double_span_iter *span = &pfns->span;
	unsigned long start_index = pfns->batch_end_index;
	struct iopt_area *area;
	int rc;

983 984 985 986
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
	    WARN_ON(span->last_used < start_index))
		return -EINVAL;

987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
	if (span->is_used == 1) {
		batch_from_xarray(&pfns->batch, &pfns->pages->pinned_pfns,
				  start_index, span->last_used);
		return 0;
	}

	if (span->is_used == 2) {
		/*
		 * Pull as many pages from the first domain we find in the
		 * target span. If it is too small then we will be called again
		 * and we'll find another area.
		 */
		area = iopt_pages_find_domain_area(pfns->pages, start_index);
		if (WARN_ON(!area))
			return -EINVAL;

		/* The storage_domain cannot change without the pages mutex */
		batch_from_domain(
			&pfns->batch, area->storage_domain, area, start_index,
			min(iopt_area_last_index(area), span->last_used));
		return 0;
	}

	if (start_index >= pfns->user.upages_end) {
		rc = pfn_reader_user_pin(&pfns->user, pfns->pages, start_index,
					 span->last_hole);
		if (rc)
			return rc;
	}

	batch_from_pages(&pfns->batch,
			 pfns->user.upages +
				 (start_index - pfns->user.upages_start),
			 pfns->user.upages_end - start_index);
	return 0;
}

static bool pfn_reader_done(struct pfn_reader *pfns)
{
	return pfns->batch_start_index == pfns->last_index + 1;
}

static int pfn_reader_next(struct pfn_reader *pfns)
{
	int rc;

	batch_clear(&pfns->batch);
	pfns->batch_start_index = pfns->batch_end_index;

	while (pfns->batch_end_index != pfns->last_index + 1) {
		unsigned int npfns = pfns->batch.total_pfns;

1039 1040 1041 1042
		if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
		    WARN_ON(interval_tree_double_span_iter_done(&pfns->span)))
			return -EINVAL;

1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125
		rc = pfn_reader_fill_span(pfns);
		if (rc)
			return rc;

		if (WARN_ON(!pfns->batch.total_pfns))
			return -EINVAL;

		pfns->batch_end_index =
			pfns->batch_start_index + pfns->batch.total_pfns;
		if (pfns->batch_end_index == pfns->span.last_used + 1)
			interval_tree_double_span_iter_next(&pfns->span);

		/* Batch is full */
		if (npfns == pfns->batch.total_pfns)
			return 0;
	}
	return 0;
}

static int pfn_reader_init(struct pfn_reader *pfns, struct iopt_pages *pages,
			   unsigned long start_index, unsigned long last_index)
{
	int rc;

	lockdep_assert_held(&pages->mutex);

	pfns->pages = pages;
	pfns->batch_start_index = start_index;
	pfns->batch_end_index = start_index;
	pfns->last_index = last_index;
	pfn_reader_user_init(&pfns->user, pages);
	rc = batch_init(&pfns->batch, last_index - start_index + 1);
	if (rc)
		return rc;
	interval_tree_double_span_iter_first(&pfns->span, &pages->access_itree,
					     &pages->domains_itree, start_index,
					     last_index);
	return 0;
}

/*
 * There are many assertions regarding the state of pages->npinned vs
 * pages->last_pinned, for instance something like unmapping a domain must only
 * decrement the npinned, and pfn_reader_destroy() must be called only after all
 * the pins are updated. This is fine for success flows, but error flows
 * sometimes need to release the pins held inside the pfn_reader before going on
 * to complete unmapping and releasing pins held in domains.
 */
static void pfn_reader_release_pins(struct pfn_reader *pfns)
{
	struct iopt_pages *pages = pfns->pages;

	if (pfns->user.upages_end > pfns->batch_end_index) {
		size_t npages = pfns->user.upages_end - pfns->batch_end_index;

		/* Any pages not transferred to the batch are just unpinned */
		unpin_user_pages(pfns->user.upages + (pfns->batch_end_index -
						      pfns->user.upages_start),
				 npages);
		iopt_pages_sub_npinned(pages, npages);
		pfns->user.upages_end = pfns->batch_end_index;
	}
	if (pfns->batch_start_index != pfns->batch_end_index) {
		pfn_reader_unpin(pfns);
		pfns->batch_start_index = pfns->batch_end_index;
	}
}

static void pfn_reader_destroy(struct pfn_reader *pfns)
{
	struct iopt_pages *pages = pfns->pages;

	pfn_reader_release_pins(pfns);
	pfn_reader_user_destroy(&pfns->user, pfns->pages);
	batch_destroy(&pfns->batch, NULL);
	WARN_ON(pages->last_npinned != pages->npinned);
}

static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages,
			    unsigned long start_index, unsigned long last_index)
{
	int rc;

1126 1127 1128 1129
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
	    WARN_ON(last_index < start_index))
		return -EINVAL;

1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
	rc = pfn_reader_init(pfns, pages, start_index, last_index);
	if (rc)
		return rc;
	rc = pfn_reader_next(pfns);
	if (rc) {
		pfn_reader_destroy(pfns);
		return rc;
	}
	return 0;
}
1140 1141 1142 1143 1144

struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length,
				    bool writable)
{
	struct iopt_pages *pages;
1145
	unsigned long end;
1146 1147 1148 1149 1150 1151 1152 1153

	/*
	 * The iommu API uses size_t as the length, and protect the DIV_ROUND_UP
	 * below from overflow
	 */
	if (length > SIZE_MAX - PAGE_SIZE || length == 0)
		return ERR_PTR(-EINVAL);

1154 1155 1156
	if (check_add_overflow((unsigned long)uptr, length, &end))
		return ERR_PTR(-EOVERFLOW);

1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209
	pages = kzalloc(sizeof(*pages), GFP_KERNEL_ACCOUNT);
	if (!pages)
		return ERR_PTR(-ENOMEM);

	kref_init(&pages->kref);
	xa_init_flags(&pages->pinned_pfns, XA_FLAGS_ACCOUNT);
	mutex_init(&pages->mutex);
	pages->source_mm = current->mm;
	mmgrab(pages->source_mm);
	pages->uptr = (void __user *)ALIGN_DOWN((uintptr_t)uptr, PAGE_SIZE);
	pages->npages = DIV_ROUND_UP(length + (uptr - pages->uptr), PAGE_SIZE);
	pages->access_itree = RB_ROOT_CACHED;
	pages->domains_itree = RB_ROOT_CACHED;
	pages->writable = writable;
	if (capable(CAP_IPC_LOCK))
		pages->account_mode = IOPT_PAGES_ACCOUNT_NONE;
	else
		pages->account_mode = IOPT_PAGES_ACCOUNT_USER;
	pages->source_task = current->group_leader;
	get_task_struct(current->group_leader);
	pages->source_user = get_uid(current_user());
	return pages;
}

void iopt_release_pages(struct kref *kref)
{
	struct iopt_pages *pages = container_of(kref, struct iopt_pages, kref);

	WARN_ON(!RB_EMPTY_ROOT(&pages->access_itree.rb_root));
	WARN_ON(!RB_EMPTY_ROOT(&pages->domains_itree.rb_root));
	WARN_ON(pages->npinned);
	WARN_ON(!xa_empty(&pages->pinned_pfns));
	mmdrop(pages->source_mm);
	mutex_destroy(&pages->mutex);
	put_task_struct(pages->source_task);
	free_uid(pages->source_user);
	kfree(pages);
}

static void
iopt_area_unpin_domain(struct pfn_batch *batch, struct iopt_area *area,
		       struct iopt_pages *pages, struct iommu_domain *domain,
		       unsigned long start_index, unsigned long last_index,
		       unsigned long *unmapped_end_index,
		       unsigned long real_last_index)
{
	while (start_index <= last_index) {
		unsigned long batch_last_index;

		if (*unmapped_end_index <= last_index) {
			unsigned long start =
				max(start_index, *unmapped_end_index);

1210 1211 1212 1213 1214
			if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
			    batch->total_pfns)
				WARN_ON(*unmapped_end_index -
						batch->total_pfns !=
					start_index);
1215 1216
			batch_from_domain(batch, domain, area, start,
					  last_index);
1217
			batch_last_index = start_index + batch->total_pfns - 1;
1218 1219 1220 1221
		} else {
			batch_last_index = last_index;
		}

1222 1223 1224
		if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
			WARN_ON(batch_last_index > real_last_index);

1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509
		/*
		 * unmaps must always 'cut' at a place where the pfns are not
		 * contiguous to pair with the maps that always install
		 * contiguous pages. Thus, if we have to stop unpinning in the
		 * middle of the domains we need to keep reading pfns until we
		 * find a cut point to do the unmap. The pfns we read are
		 * carried over and either skipped or integrated into the next
		 * batch.
		 */
		if (batch_last_index == last_index &&
		    last_index != real_last_index)
			batch_from_domain_continue(batch, domain, area,
						   last_index + 1,
						   real_last_index);

		if (*unmapped_end_index <= batch_last_index) {
			iopt_area_unmap_domain_range(
				area, domain, *unmapped_end_index,
				start_index + batch->total_pfns - 1);
			*unmapped_end_index = start_index + batch->total_pfns;
		}

		/* unpin must follow unmap */
		batch_unpin(batch, pages, 0,
			    batch_last_index - start_index + 1);
		start_index = batch_last_index + 1;

		batch_clear_carry(batch,
				  *unmapped_end_index - batch_last_index - 1);
	}
}

static void __iopt_area_unfill_domain(struct iopt_area *area,
				      struct iopt_pages *pages,
				      struct iommu_domain *domain,
				      unsigned long last_index)
{
	struct interval_tree_double_span_iter span;
	unsigned long start_index = iopt_area_index(area);
	unsigned long unmapped_end_index = start_index;
	u64 backup[BATCH_BACKUP_SIZE];
	struct pfn_batch batch;

	lockdep_assert_held(&pages->mutex);

	/*
	 * For security we must not unpin something that is still DMA mapped,
	 * so this must unmap any IOVA before we go ahead and unpin the pages.
	 * This creates a complexity where we need to skip over unpinning pages
	 * held in the xarray, but continue to unmap from the domain.
	 *
	 * The domain unmap cannot stop in the middle of a contiguous range of
	 * PFNs. To solve this problem the unpinning step will read ahead to the
	 * end of any contiguous span, unmap that whole span, and then only
	 * unpin the leading part that does not have any accesses. The residual
	 * PFNs that were unmapped but not unpinned are called a "carry" in the
	 * batch as they are moved to the front of the PFN list and continue on
	 * to the next iteration(s).
	 */
	batch_init_backup(&batch, last_index + 1, backup, sizeof(backup));
	interval_tree_for_each_double_span(&span, &pages->domains_itree,
					   &pages->access_itree, start_index,
					   last_index) {
		if (span.is_used) {
			batch_skip_carry(&batch,
					 span.last_used - span.start_used + 1);
			continue;
		}
		iopt_area_unpin_domain(&batch, area, pages, domain,
				       span.start_hole, span.last_hole,
				       &unmapped_end_index, last_index);
	}
	/*
	 * If the range ends in a access then we do the residual unmap without
	 * any unpins.
	 */
	if (unmapped_end_index != last_index + 1)
		iopt_area_unmap_domain_range(area, domain, unmapped_end_index,
					     last_index);
	WARN_ON(batch.total_pfns);
	batch_destroy(&batch, backup);
	update_unpinned(pages);
}

static void iopt_area_unfill_partial_domain(struct iopt_area *area,
					    struct iopt_pages *pages,
					    struct iommu_domain *domain,
					    unsigned long end_index)
{
	if (end_index != iopt_area_index(area))
		__iopt_area_unfill_domain(area, pages, domain, end_index - 1);
}

/**
 * iopt_area_unmap_domain() - Unmap without unpinning PFNs in a domain
 * @area: The IOVA range to unmap
 * @domain: The domain to unmap
 *
 * The caller must know that unpinning is not required, usually because there
 * are other domains in the iopt.
 */
void iopt_area_unmap_domain(struct iopt_area *area, struct iommu_domain *domain)
{
	iommu_unmap_nofail(domain, iopt_area_iova(area),
			   iopt_area_length(area));
}

/**
 * iopt_area_unfill_domain() - Unmap and unpin PFNs in a domain
 * @area: IOVA area to use
 * @pages: page supplier for the area (area->pages is NULL)
 * @domain: Domain to unmap from
 *
 * The domain should be removed from the domains_itree before calling. The
 * domain will always be unmapped, but the PFNs may not be unpinned if there are
 * still accesses.
 */
void iopt_area_unfill_domain(struct iopt_area *area, struct iopt_pages *pages,
			     struct iommu_domain *domain)
{
	__iopt_area_unfill_domain(area, pages, domain,
				  iopt_area_last_index(area));
}

/**
 * iopt_area_fill_domain() - Map PFNs from the area into a domain
 * @area: IOVA area to use
 * @domain: Domain to load PFNs into
 *
 * Read the pfns from the area's underlying iopt_pages and map them into the
 * given domain. Called when attaching a new domain to an io_pagetable.
 */
int iopt_area_fill_domain(struct iopt_area *area, struct iommu_domain *domain)
{
	unsigned long done_end_index;
	struct pfn_reader pfns;
	int rc;

	lockdep_assert_held(&area->pages->mutex);

	rc = pfn_reader_first(&pfns, area->pages, iopt_area_index(area),
			      iopt_area_last_index(area));
	if (rc)
		return rc;

	while (!pfn_reader_done(&pfns)) {
		done_end_index = pfns.batch_start_index;
		rc = batch_to_domain(&pfns.batch, domain, area,
				     pfns.batch_start_index);
		if (rc)
			goto out_unmap;
		done_end_index = pfns.batch_end_index;

		rc = pfn_reader_next(&pfns);
		if (rc)
			goto out_unmap;
	}

	rc = pfn_reader_update_pinned(&pfns);
	if (rc)
		goto out_unmap;
	goto out_destroy;

out_unmap:
	pfn_reader_release_pins(&pfns);
	iopt_area_unfill_partial_domain(area, area->pages, domain,
					done_end_index);
out_destroy:
	pfn_reader_destroy(&pfns);
	return rc;
}

/**
 * iopt_area_fill_domains() - Install PFNs into the area's domains
 * @area: The area to act on
 * @pages: The pages associated with the area (area->pages is NULL)
 *
 * Called during area creation. The area is freshly created and not inserted in
 * the domains_itree yet. PFNs are read and loaded into every domain held in the
 * area's io_pagetable and the area is installed in the domains_itree.
 *
 * On failure all domains are left unchanged.
 */
int iopt_area_fill_domains(struct iopt_area *area, struct iopt_pages *pages)
{
	unsigned long done_first_end_index;
	unsigned long done_all_end_index;
	struct iommu_domain *domain;
	unsigned long unmap_index;
	struct pfn_reader pfns;
	unsigned long index;
	int rc;

	lockdep_assert_held(&area->iopt->domains_rwsem);

	if (xa_empty(&area->iopt->domains))
		return 0;

	mutex_lock(&pages->mutex);
	rc = pfn_reader_first(&pfns, pages, iopt_area_index(area),
			      iopt_area_last_index(area));
	if (rc)
		goto out_unlock;

	while (!pfn_reader_done(&pfns)) {
		done_first_end_index = pfns.batch_end_index;
		done_all_end_index = pfns.batch_start_index;
		xa_for_each(&area->iopt->domains, index, domain) {
			rc = batch_to_domain(&pfns.batch, domain, area,
					     pfns.batch_start_index);
			if (rc)
				goto out_unmap;
		}
		done_all_end_index = done_first_end_index;

		rc = pfn_reader_next(&pfns);
		if (rc)
			goto out_unmap;
	}
	rc = pfn_reader_update_pinned(&pfns);
	if (rc)
		goto out_unmap;

	area->storage_domain = xa_load(&area->iopt->domains, 0);
	interval_tree_insert(&area->pages_node, &pages->domains_itree);
	goto out_destroy;

out_unmap:
	pfn_reader_release_pins(&pfns);
	xa_for_each(&area->iopt->domains, unmap_index, domain) {
		unsigned long end_index;

		if (unmap_index < index)
			end_index = done_first_end_index;
		else
			end_index = done_all_end_index;

		/*
		 * The area is not yet part of the domains_itree so we have to
		 * manage the unpinning specially. The last domain does the
		 * unpin, every other domain is just unmapped.
		 */
		if (unmap_index != area->iopt->next_domain_id - 1) {
			if (end_index != iopt_area_index(area))
				iopt_area_unmap_domain_range(
					area, domain, iopt_area_index(area),
					end_index - 1);
		} else {
			iopt_area_unfill_partial_domain(area, pages, domain,
							end_index);
		}
	}
out_destroy:
	pfn_reader_destroy(&pfns);
out_unlock:
	mutex_unlock(&pages->mutex);
	return rc;
}

/**
 * iopt_area_unfill_domains() - unmap PFNs from the area's domains
 * @area: The area to act on
 * @pages: The pages associated with the area (area->pages is NULL)
 *
 * Called during area destruction. This unmaps the iova's covered by all the
 * area's domains and releases the PFNs.
 */
void iopt_area_unfill_domains(struct iopt_area *area, struct iopt_pages *pages)
{
	struct io_pagetable *iopt = area->iopt;
	struct iommu_domain *domain;
	unsigned long index;

	lockdep_assert_held(&iopt->domains_rwsem);

	mutex_lock(&pages->mutex);
	if (!area->storage_domain)
		goto out_unlock;

	xa_for_each(&iopt->domains, index, domain)
		if (domain != area->storage_domain)
			iopt_area_unmap_domain_range(
				area, domain, iopt_area_index(area),
				iopt_area_last_index(area));

1510 1511
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
		WARN_ON(RB_EMPTY_NODE(&area->pages_node.rb));
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794
	interval_tree_remove(&area->pages_node, &pages->domains_itree);
	iopt_area_unfill_domain(area, pages, area->storage_domain);
	area->storage_domain = NULL;
out_unlock:
	mutex_unlock(&pages->mutex);
}

static void iopt_pages_unpin_xarray(struct pfn_batch *batch,
				    struct iopt_pages *pages,
				    unsigned long start_index,
				    unsigned long end_index)
{
	while (start_index <= end_index) {
		batch_from_xarray_clear(batch, &pages->pinned_pfns, start_index,
					end_index);
		batch_unpin(batch, pages, 0, batch->total_pfns);
		start_index += batch->total_pfns;
		batch_clear(batch);
	}
}

/**
 * iopt_pages_unfill_xarray() - Update the xarry after removing an access
 * @pages: The pages to act on
 * @start_index: Starting PFN index
 * @last_index: Last PFN index
 *
 * Called when an iopt_pages_access is removed, removes pages from the itree.
 * The access should already be removed from the access_itree.
 */
void iopt_pages_unfill_xarray(struct iopt_pages *pages,
			      unsigned long start_index,
			      unsigned long last_index)
{
	struct interval_tree_double_span_iter span;
	u64 backup[BATCH_BACKUP_SIZE];
	struct pfn_batch batch;
	bool batch_inited = false;

	lockdep_assert_held(&pages->mutex);

	interval_tree_for_each_double_span(&span, &pages->access_itree,
					   &pages->domains_itree, start_index,
					   last_index) {
		if (!span.is_used) {
			if (!batch_inited) {
				batch_init_backup(&batch,
						  last_index - start_index + 1,
						  backup, sizeof(backup));
				batch_inited = true;
			}
			iopt_pages_unpin_xarray(&batch, pages, span.start_hole,
						span.last_hole);
		} else if (span.is_used == 2) {
			/* Covered by a domain */
			clear_xarray(&pages->pinned_pfns, span.start_used,
				     span.last_used);
		}
		/* Otherwise covered by an existing access */
	}
	if (batch_inited)
		batch_destroy(&batch, backup);
	update_unpinned(pages);
}

/**
 * iopt_pages_fill_from_xarray() - Fast path for reading PFNs
 * @pages: The pages to act on
 * @start_index: The first page index in the range
 * @last_index: The last page index in the range
 * @out_pages: The output array to return the pages
 *
 * This can be called if the caller is holding a refcount on an
 * iopt_pages_access that is known to have already been filled. It quickly reads
 * the pages directly from the xarray.
 *
 * This is part of the SW iommu interface to read pages for in-kernel use.
 */
void iopt_pages_fill_from_xarray(struct iopt_pages *pages,
				 unsigned long start_index,
				 unsigned long last_index,
				 struct page **out_pages)
{
	XA_STATE(xas, &pages->pinned_pfns, start_index);
	void *entry;

	rcu_read_lock();
	while (start_index <= last_index) {
		entry = xas_next(&xas);
		if (xas_retry(&xas, entry))
			continue;
		WARN_ON(!xa_is_value(entry));
		*(out_pages++) = pfn_to_page(xa_to_value(entry));
		start_index++;
	}
	rcu_read_unlock();
}

static int iopt_pages_fill_from_domain(struct iopt_pages *pages,
				       unsigned long start_index,
				       unsigned long last_index,
				       struct page **out_pages)
{
	while (start_index != last_index + 1) {
		unsigned long domain_last;
		struct iopt_area *area;

		area = iopt_pages_find_domain_area(pages, start_index);
		if (WARN_ON(!area))
			return -EINVAL;

		domain_last = min(iopt_area_last_index(area), last_index);
		out_pages = raw_pages_from_domain(area->storage_domain, area,
						  start_index, domain_last,
						  out_pages);
		start_index = domain_last + 1;
	}
	return 0;
}

static int iopt_pages_fill_from_mm(struct iopt_pages *pages,
				   struct pfn_reader_user *user,
				   unsigned long start_index,
				   unsigned long last_index,
				   struct page **out_pages)
{
	unsigned long cur_index = start_index;
	int rc;

	while (cur_index != last_index + 1) {
		user->upages = out_pages + (cur_index - start_index);
		rc = pfn_reader_user_pin(user, pages, cur_index, last_index);
		if (rc)
			goto out_unpin;
		cur_index = user->upages_end;
	}
	return 0;

out_unpin:
	if (start_index != cur_index)
		iopt_pages_err_unpin(pages, start_index, cur_index - 1,
				     out_pages);
	return rc;
}

/**
 * iopt_pages_fill_xarray() - Read PFNs
 * @pages: The pages to act on
 * @start_index: The first page index in the range
 * @last_index: The last page index in the range
 * @out_pages: The output array to return the pages, may be NULL
 *
 * This populates the xarray and returns the pages in out_pages. As the slow
 * path this is able to copy pages from other storage tiers into the xarray.
 *
 * On failure the xarray is left unchanged.
 *
 * This is part of the SW iommu interface to read pages for in-kernel use.
 */
int iopt_pages_fill_xarray(struct iopt_pages *pages, unsigned long start_index,
			   unsigned long last_index, struct page **out_pages)
{
	struct interval_tree_double_span_iter span;
	unsigned long xa_end = start_index;
	struct pfn_reader_user user;
	int rc;

	lockdep_assert_held(&pages->mutex);

	pfn_reader_user_init(&user, pages);
	user.upages_len = (last_index - start_index + 1) * sizeof(*out_pages);
	interval_tree_for_each_double_span(&span, &pages->access_itree,
					   &pages->domains_itree, start_index,
					   last_index) {
		struct page **cur_pages;

		if (span.is_used == 1) {
			cur_pages = out_pages + (span.start_used - start_index);
			iopt_pages_fill_from_xarray(pages, span.start_used,
						    span.last_used, cur_pages);
			continue;
		}

		if (span.is_used == 2) {
			cur_pages = out_pages + (span.start_used - start_index);
			iopt_pages_fill_from_domain(pages, span.start_used,
						    span.last_used, cur_pages);
			rc = pages_to_xarray(&pages->pinned_pfns,
					     span.start_used, span.last_used,
					     cur_pages);
			if (rc)
				goto out_clean_xa;
			xa_end = span.last_used + 1;
			continue;
		}

		/* hole */
		cur_pages = out_pages + (span.start_hole - start_index);
		rc = iopt_pages_fill_from_mm(pages, &user, span.start_hole,
					     span.last_hole, cur_pages);
		if (rc)
			goto out_clean_xa;
		rc = pages_to_xarray(&pages->pinned_pfns, span.start_hole,
				     span.last_hole, cur_pages);
		if (rc) {
			iopt_pages_err_unpin(pages, span.start_hole,
					     span.last_hole, cur_pages);
			goto out_clean_xa;
		}
		xa_end = span.last_hole + 1;
	}
	rc = pfn_reader_user_update_pinned(&user, pages);
	if (rc)
		goto out_clean_xa;
	user.upages = NULL;
	pfn_reader_user_destroy(&user, pages);
	return 0;

out_clean_xa:
	if (start_index != xa_end)
		iopt_pages_unfill_xarray(pages, start_index, xa_end - 1);
	user.upages = NULL;
	pfn_reader_user_destroy(&user, pages);
	return rc;
}

/*
 * This uses the pfn_reader instead of taking a shortcut by using the mm. It can
 * do every scenario and is fully consistent with what an iommu_domain would
 * see.
 */
static int iopt_pages_rw_slow(struct iopt_pages *pages,
			      unsigned long start_index,
			      unsigned long last_index, unsigned long offset,
			      void *data, unsigned long length,
			      unsigned int flags)
{
	struct pfn_reader pfns;
	int rc;

	mutex_lock(&pages->mutex);

	rc = pfn_reader_first(&pfns, pages, start_index, last_index);
	if (rc)
		goto out_unlock;

	while (!pfn_reader_done(&pfns)) {
		unsigned long done;

		done = batch_rw(&pfns.batch, data, offset, length, flags);
		data += done;
		length -= done;
		offset = 0;
		pfn_reader_unpin(&pfns);

		rc = pfn_reader_next(&pfns);
		if (rc)
			goto out_destroy;
	}
	if (WARN_ON(length != 0))
		rc = -EINVAL;
out_destroy:
	pfn_reader_destroy(&pfns);
out_unlock:
	mutex_unlock(&pages->mutex);
	return rc;
}

/*
 * A medium speed path that still allows DMA inconsistencies, but doesn't do any
 * memory allocations or interval tree searches.
 */
static int iopt_pages_rw_page(struct iopt_pages *pages, unsigned long index,
			      unsigned long offset, void *data,
			      unsigned long length, unsigned int flags)
{
	struct page *page = NULL;
	int rc;

	if (!mmget_not_zero(pages->source_mm))
		return iopt_pages_rw_slow(pages, index, index, offset, data,
					  length, flags);

1795 1796 1797 1798 1799
	if (iommufd_should_fail()) {
		rc = -EINVAL;
		goto out_mmput;
	}

1800 1801 1802 1803
	mmap_read_lock(pages->source_mm);
	rc = pin_user_pages_remote(
		pages->source_mm, (uintptr_t)(pages->uptr + index * PAGE_SIZE),
		1, (flags & IOMMUFD_ACCESS_RW_WRITE) ? FOLL_WRITE : 0, &page,
1804
		NULL);
1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838
	mmap_read_unlock(pages->source_mm);
	if (rc != 1) {
		if (WARN_ON(rc >= 0))
			rc = -EINVAL;
		goto out_mmput;
	}
	copy_data_page(page, data, offset, length, flags);
	unpin_user_page(page);
	rc = 0;

out_mmput:
	mmput(pages->source_mm);
	return rc;
}

/**
 * iopt_pages_rw_access - Copy to/from a linear slice of the pages
 * @pages: pages to act on
 * @start_byte: First byte of pages to copy to/from
 * @data: Kernel buffer to get/put the data
 * @length: Number of bytes to copy
 * @flags: IOMMUFD_ACCESS_RW_* flags
 *
 * This will find each page in the range, kmap it and then memcpy to/from
 * the given kernel buffer.
 */
int iopt_pages_rw_access(struct iopt_pages *pages, unsigned long start_byte,
			 void *data, unsigned long length, unsigned int flags)
{
	unsigned long start_index = start_byte / PAGE_SIZE;
	unsigned long last_index = (start_byte + length - 1) / PAGE_SIZE;
	bool change_mm = current->mm != pages->source_mm;
	int rc = 0;

1839 1840 1841 1842
	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
	    (flags & __IOMMUFD_ACCESS_RW_SLOW_PATH))
		change_mm = true;

1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993
	if ((flags & IOMMUFD_ACCESS_RW_WRITE) && !pages->writable)
		return -EPERM;

	if (!(flags & IOMMUFD_ACCESS_RW_KTHREAD) && change_mm) {
		if (start_index == last_index)
			return iopt_pages_rw_page(pages, start_index,
						  start_byte % PAGE_SIZE, data,
						  length, flags);
		return iopt_pages_rw_slow(pages, start_index, last_index,
					  start_byte % PAGE_SIZE, data, length,
					  flags);
	}

	/*
	 * Try to copy using copy_to_user(). We do this as a fast path and
	 * ignore any pinning inconsistencies, unlike a real DMA path.
	 */
	if (change_mm) {
		if (!mmget_not_zero(pages->source_mm))
			return iopt_pages_rw_slow(pages, start_index,
						  last_index,
						  start_byte % PAGE_SIZE, data,
						  length, flags);
		kthread_use_mm(pages->source_mm);
	}

	if (flags & IOMMUFD_ACCESS_RW_WRITE) {
		if (copy_to_user(pages->uptr + start_byte, data, length))
			rc = -EFAULT;
	} else {
		if (copy_from_user(data, pages->uptr + start_byte, length))
			rc = -EFAULT;
	}

	if (change_mm) {
		kthread_unuse_mm(pages->source_mm);
		mmput(pages->source_mm);
	}

	return rc;
}

static struct iopt_pages_access *
iopt_pages_get_exact_access(struct iopt_pages *pages, unsigned long index,
			    unsigned long last)
{
	struct interval_tree_node *node;

	lockdep_assert_held(&pages->mutex);

	/* There can be overlapping ranges in this interval tree */
	for (node = interval_tree_iter_first(&pages->access_itree, index, last);
	     node; node = interval_tree_iter_next(node, index, last))
		if (node->start == index && node->last == last)
			return container_of(node, struct iopt_pages_access,
					    node);
	return NULL;
}

/**
 * iopt_area_add_access() - Record an in-knerel access for PFNs
 * @area: The source of PFNs
 * @start_index: First page index
 * @last_index: Inclusive last page index
 * @out_pages: Output list of struct page's representing the PFNs
 * @flags: IOMMUFD_ACCESS_RW_* flags
 *
 * Record that an in-kernel access will be accessing the pages, ensure they are
 * pinned, and return the PFNs as a simple list of 'struct page *'.
 *
 * This should be undone through a matching call to iopt_area_remove_access()
 */
int iopt_area_add_access(struct iopt_area *area, unsigned long start_index,
			  unsigned long last_index, struct page **out_pages,
			  unsigned int flags)
{
	struct iopt_pages *pages = area->pages;
	struct iopt_pages_access *access;
	int rc;

	if ((flags & IOMMUFD_ACCESS_RW_WRITE) && !pages->writable)
		return -EPERM;

	mutex_lock(&pages->mutex);
	access = iopt_pages_get_exact_access(pages, start_index, last_index);
	if (access) {
		area->num_accesses++;
		access->users++;
		iopt_pages_fill_from_xarray(pages, start_index, last_index,
					    out_pages);
		mutex_unlock(&pages->mutex);
		return 0;
	}

	access = kzalloc(sizeof(*access), GFP_KERNEL_ACCOUNT);
	if (!access) {
		rc = -ENOMEM;
		goto err_unlock;
	}

	rc = iopt_pages_fill_xarray(pages, start_index, last_index, out_pages);
	if (rc)
		goto err_free;

	access->node.start = start_index;
	access->node.last = last_index;
	access->users = 1;
	area->num_accesses++;
	interval_tree_insert(&access->node, &pages->access_itree);
	mutex_unlock(&pages->mutex);
	return 0;

err_free:
	kfree(access);
err_unlock:
	mutex_unlock(&pages->mutex);
	return rc;
}

/**
 * iopt_area_remove_access() - Release an in-kernel access for PFNs
 * @area: The source of PFNs
 * @start_index: First page index
 * @last_index: Inclusive last page index
 *
 * Undo iopt_area_add_access() and unpin the pages if necessary. The caller
 * must stop using the PFNs before calling this.
 */
void iopt_area_remove_access(struct iopt_area *area, unsigned long start_index,
			     unsigned long last_index)
{
	struct iopt_pages *pages = area->pages;
	struct iopt_pages_access *access;

	mutex_lock(&pages->mutex);
	access = iopt_pages_get_exact_access(pages, start_index, last_index);
	if (WARN_ON(!access))
		goto out_unlock;

	WARN_ON(area->num_accesses == 0 || access->users == 0);
	area->num_accesses--;
	access->users--;
	if (access->users)
		goto out_unlock;

	interval_tree_remove(&access->node, &pages->access_itree);
	iopt_pages_unfill_xarray(pages, start_index, last_index);
	kfree(access);
out_unlock:
	mutex_unlock(&pages->mutex);
}