hmm.c 31.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
/*
 * Copyright 2013 Red Hat Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that 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.
 *
 * Authors: Jérôme Glisse <jglisse@redhat.com>
 */
/*
 * Refer to include/linux/hmm.h for information about heterogeneous memory
 * management or HMM for short.
 */
#include <linux/mm.h>
#include <linux/hmm.h>
22
#include <linux/init.h>
23 24
#include <linux/rmap.h>
#include <linux/swap.h>
25 26
#include <linux/slab.h>
#include <linux/sched.h>
27 28
#include <linux/mmzone.h>
#include <linux/pagemap.h>
29 30
#include <linux/swapops.h>
#include <linux/hugetlb.h>
31
#include <linux/memremap.h>
32
#include <linux/jump_label.h>
33
#include <linux/mmu_notifier.h>
34 35 36
#include <linux/memory_hotplug.h>

#define PA_SECTION_SIZE (1UL << PA_SECTION_SHIFT)
37 38


39 40 41 42 43 44 45
/*
 * Device private memory see HMM (Documentation/vm/hmm.txt) or hmm.h
 */
DEFINE_STATIC_KEY_FALSE(device_private_key);
EXPORT_SYMBOL(device_private_key);


46
#ifdef CONFIG_HMM
47 48
static const struct mmu_notifier_ops hmm_mmu_notifier_ops;

49 50 51 52
/*
 * struct hmm - HMM per mm struct
 *
 * @mm: mm struct this HMM struct is bound to
53
 * @lock: lock protecting ranges list
54
 * @sequence: we track updates to the CPU page table with a sequence number
55
 * @ranges: list of range being snapshotted
56 57 58
 * @mirrors: list of mirrors for this mm
 * @mmu_notifier: mmu notifier to track updates to CPU page table
 * @mirrors_sem: read/write semaphore protecting the mirrors list
59 60 61
 */
struct hmm {
	struct mm_struct	*mm;
62
	spinlock_t		lock;
63
	atomic_t		sequence;
64
	struct list_head	ranges;
65 66 67
	struct list_head	mirrors;
	struct mmu_notifier	mmu_notifier;
	struct rw_semaphore	mirrors_sem;
68 69 70 71 72 73 74 75 76 77 78 79
};

/*
 * hmm_register - register HMM against an mm (HMM internal)
 *
 * @mm: mm struct to attach to
 *
 * This is not intended to be used directly by device drivers. It allocates an
 * HMM struct if mm does not have one, and initializes it.
 */
static struct hmm *hmm_register(struct mm_struct *mm)
{
80 81
	struct hmm *hmm = READ_ONCE(mm->hmm);
	bool cleanup = false;
82 83 84 85 86 87

	/*
	 * The hmm struct can only be freed once the mm_struct goes away,
	 * hence we should always have pre-allocated an new hmm struct
	 * above.
	 */
88 89 90 91 92 93 94 95 96 97
	if (hmm)
		return hmm;

	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
	if (!hmm)
		return NULL;
	INIT_LIST_HEAD(&hmm->mirrors);
	init_rwsem(&hmm->mirrors_sem);
	atomic_set(&hmm->sequence, 0);
	hmm->mmu_notifier.ops = NULL;
98 99
	INIT_LIST_HEAD(&hmm->ranges);
	spin_lock_init(&hmm->lock);
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123
	hmm->mm = mm;

	/*
	 * We should only get here if hold the mmap_sem in write mode ie on
	 * registration of first mirror through hmm_mirror_register()
	 */
	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
	if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
		kfree(hmm);
		return NULL;
	}

	spin_lock(&mm->page_table_lock);
	if (!mm->hmm)
		mm->hmm = hmm;
	else
		cleanup = true;
	spin_unlock(&mm->page_table_lock);

	if (cleanup) {
		mmu_notifier_unregister(&hmm->mmu_notifier, mm);
		kfree(hmm);
	}

124 125 126 127 128 129 130 131
	return mm->hmm;
}

void hmm_mm_destroy(struct mm_struct *mm)
{
	kfree(mm->hmm);
}
#endif /* CONFIG_HMM */
132 133 134 135 136 137 138 139

#if IS_ENABLED(CONFIG_HMM_MIRROR)
static void hmm_invalidate_range(struct hmm *hmm,
				 enum hmm_update_type action,
				 unsigned long start,
				 unsigned long end)
{
	struct hmm_mirror *mirror;
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
	struct hmm_range *range;

	spin_lock(&hmm->lock);
	list_for_each_entry(range, &hmm->ranges, list) {
		unsigned long addr, idx, npages;

		if (end < range->start || start >= range->end)
			continue;

		range->valid = false;
		addr = max(start, range->start);
		idx = (addr - range->start) >> PAGE_SHIFT;
		npages = (min(range->end, end) - addr) >> PAGE_SHIFT;
		memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages);
	}
	spin_unlock(&hmm->lock);
156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237

	down_read(&hmm->mirrors_sem);
	list_for_each_entry(mirror, &hmm->mirrors, list)
		mirror->ops->sync_cpu_device_pagetables(mirror, action,
							start, end);
	up_read(&hmm->mirrors_sem);
}

static void hmm_invalidate_range_start(struct mmu_notifier *mn,
				       struct mm_struct *mm,
				       unsigned long start,
				       unsigned long end)
{
	struct hmm *hmm = mm->hmm;

	VM_BUG_ON(!hmm);

	atomic_inc(&hmm->sequence);
}

static void hmm_invalidate_range_end(struct mmu_notifier *mn,
				     struct mm_struct *mm,
				     unsigned long start,
				     unsigned long end)
{
	struct hmm *hmm = mm->hmm;

	VM_BUG_ON(!hmm);

	hmm_invalidate_range(mm->hmm, HMM_UPDATE_INVALIDATE, start, end);
}

static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
	.invalidate_range_start	= hmm_invalidate_range_start,
	.invalidate_range_end	= hmm_invalidate_range_end,
};

/*
 * hmm_mirror_register() - register a mirror against an mm
 *
 * @mirror: new mirror struct to register
 * @mm: mm to register against
 *
 * To start mirroring a process address space, the device driver must register
 * an HMM mirror struct.
 *
 * THE mm->mmap_sem MUST BE HELD IN WRITE MODE !
 */
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
{
	/* Sanity check */
	if (!mm || !mirror || !mirror->ops)
		return -EINVAL;

	mirror->hmm = hmm_register(mm);
	if (!mirror->hmm)
		return -ENOMEM;

	down_write(&mirror->hmm->mirrors_sem);
	list_add(&mirror->list, &mirror->hmm->mirrors);
	up_write(&mirror->hmm->mirrors_sem);

	return 0;
}
EXPORT_SYMBOL(hmm_mirror_register);

/*
 * hmm_mirror_unregister() - unregister a mirror
 *
 * @mirror: new mirror struct to register
 *
 * Stop mirroring a process address space, and cleanup.
 */
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
	struct hmm *hmm = mirror->hmm;

	down_write(&hmm->mirrors_sem);
	list_del(&mirror->list);
	up_write(&hmm->mirrors_sem);
}
EXPORT_SYMBOL(hmm_mirror_unregister);
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
struct hmm_vma_walk {
	struct hmm_range	*range;
	unsigned long		last;
	bool			fault;
	bool			block;
	bool			write;
};

static int hmm_vma_do_fault(struct mm_walk *walk,
			    unsigned long addr,
			    hmm_pfn_t *pfn)
{
	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct vm_area_struct *vma = walk->vma;
	int r;

	flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY;
	flags |= hmm_vma_walk->write ? FAULT_FLAG_WRITE : 0;
	r = handle_mm_fault(vma, addr, flags);
	if (r & VM_FAULT_RETRY)
		return -EBUSY;
	if (r & VM_FAULT_ERROR) {
		*pfn = HMM_PFN_ERROR;
		return -EFAULT;
	}

	return -EAGAIN;
}

269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
static void hmm_pfns_special(hmm_pfn_t *pfns,
			     unsigned long addr,
			     unsigned long end)
{
	for (; addr < end; addr += PAGE_SIZE, pfns++)
		*pfns = HMM_PFN_SPECIAL;
}

static int hmm_pfns_bad(unsigned long addr,
			unsigned long end,
			struct mm_walk *walk)
{
	struct hmm_range *range = walk->private;
	hmm_pfn_t *pfns = range->pfns;
	unsigned long i;

	i = (addr - range->start) >> PAGE_SHIFT;
	for (; addr < end; addr += PAGE_SIZE, i++)
		pfns[i] = HMM_PFN_ERROR;

	return 0;
}

292 293 294 295 296 297 298 299
static void hmm_pfns_clear(hmm_pfn_t *pfns,
			   unsigned long addr,
			   unsigned long end)
{
	for (; addr < end; addr += PAGE_SIZE, pfns++)
		*pfns = 0;
}

300 301 302 303
static int hmm_vma_walk_hole(unsigned long addr,
			     unsigned long end,
			     struct mm_walk *walk)
{
304 305
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
306 307 308
	hmm_pfn_t *pfns = range->pfns;
	unsigned long i;

309
	hmm_vma_walk->last = addr;
310
	i = (addr - range->start) >> PAGE_SHIFT;
311
	for (; addr < end; addr += PAGE_SIZE, i++) {
312
		pfns[i] = HMM_PFN_EMPTY;
313 314
		if (hmm_vma_walk->fault) {
			int ret;
315

316 317 318 319 320 321 322
			ret = hmm_vma_do_fault(walk, addr, &pfns[i]);
			if (ret != -EAGAIN)
				return ret;
		}
	}

	return hmm_vma_walk->fault ? -EAGAIN : 0;
323 324 325 326 327 328
}

static int hmm_vma_walk_clear(unsigned long addr,
			      unsigned long end,
			      struct mm_walk *walk)
{
329 330
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
331 332 333
	hmm_pfn_t *pfns = range->pfns;
	unsigned long i;

334
	hmm_vma_walk->last = addr;
335
	i = (addr - range->start) >> PAGE_SHIFT;
336
	for (; addr < end; addr += PAGE_SIZE, i++) {
337
		pfns[i] = 0;
338 339
		if (hmm_vma_walk->fault) {
			int ret;
340

341 342 343 344 345 346 347
			ret = hmm_vma_do_fault(walk, addr, &pfns[i]);
			if (ret != -EAGAIN)
				return ret;
		}
	}

	return hmm_vma_walk->fault ? -EAGAIN : 0;
348 349 350 351 352 353 354
}

static int hmm_vma_walk_pmd(pmd_t *pmdp,
			    unsigned long start,
			    unsigned long end,
			    struct mm_walk *walk)
{
355 356
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
357 358 359
	struct vm_area_struct *vma = walk->vma;
	hmm_pfn_t *pfns = range->pfns;
	unsigned long addr = start, i;
360
	bool write_fault;
361 362 363 364 365
	hmm_pfn_t flag;
	pte_t *ptep;

	i = (addr - range->start) >> PAGE_SHIFT;
	flag = vma->vm_flags & VM_READ ? HMM_PFN_READ : 0;
366
	write_fault = hmm_vma_walk->fault & hmm_vma_walk->write;
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

again:
	if (pmd_none(*pmdp))
		return hmm_vma_walk_hole(start, end, walk);

	if (pmd_huge(*pmdp) && vma->vm_flags & VM_HUGETLB)
		return hmm_pfns_bad(start, end, walk);

	if (pmd_devmap(*pmdp) || pmd_trans_huge(*pmdp)) {
		unsigned long pfn;
		pmd_t pmd;

		/*
		 * No need to take pmd_lock here, even if some other threads
		 * is splitting the huge pmd we will get that event through
		 * mmu_notifier callback.
		 *
		 * So just read pmd value and check again its a transparent
		 * huge or device mapping one and compute corresponding pfn
		 * values.
		 */
		pmd = pmd_read_atomic(pmdp);
		barrier();
		if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
			goto again;
		if (pmd_protnone(pmd))
			return hmm_vma_walk_clear(start, end, walk);

395 396 397
		if (write_fault && !pmd_write(pmd))
			return hmm_vma_walk_clear(start, end, walk);

398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
		pfn = pmd_pfn(pmd) + pte_index(addr);
		flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
		for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
			pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag;
		return 0;
	}

	if (pmd_bad(*pmdp))
		return hmm_pfns_bad(start, end, walk);

	ptep = pte_offset_map(pmdp, addr);
	for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
		pte_t pte = *ptep;

		pfns[i] = 0;

414
		if (pte_none(pte)) {
415
			pfns[i] = HMM_PFN_EMPTY;
416 417
			if (hmm_vma_walk->fault)
				goto fault;
418 419 420
			continue;
		}

421 422 423 424 425 426 427 428 429 430 431 432 433 434 435
		if (!pte_present(pte)) {
			swp_entry_t entry;

			if (!non_swap_entry(entry)) {
				if (hmm_vma_walk->fault)
					goto fault;
				continue;
			}

			entry = pte_to_swp_entry(pte);

			/*
			 * This is a special swap entry, ignore migration, use
			 * device and report anything else as error.
			 */
436 437 438 439 440 441 442 443 444
			if (is_device_private_entry(entry)) {
				pfns[i] = hmm_pfn_t_from_pfn(swp_offset(entry));
				if (is_write_device_private_entry(entry)) {
					pfns[i] |= HMM_PFN_WRITE;
				} else if (write_fault)
					goto fault;
				pfns[i] |= HMM_PFN_DEVICE_UNADDRESSABLE;
				pfns[i] |= flag;
			} else if (is_migration_entry(entry)) {
445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462
				if (hmm_vma_walk->fault) {
					pte_unmap(ptep);
					hmm_vma_walk->last = addr;
					migration_entry_wait(vma->vm_mm,
							     pmdp, addr);
					return -EAGAIN;
				}
				continue;
			} else {
				/* Report error for everything else */
				pfns[i] = HMM_PFN_ERROR;
			}
			continue;
		}

		if (write_fault && !pte_write(pte))
			goto fault;

463 464
		pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
		pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
465 466 467 468 469 470
		continue;

fault:
		pte_unmap(ptep);
		/* Fault all pages in range */
		return hmm_vma_walk_clear(start, end, walk);
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
	}
	pte_unmap(ptep - 1);

	return 0;
}

/*
 * hmm_vma_get_pfns() - snapshot CPU page table for a range of virtual addresses
 * @vma: virtual memory area containing the virtual address range
 * @range: used to track snapshot validity
 * @start: range virtual start address (inclusive)
 * @end: range virtual end address (exclusive)
 * @entries: array of hmm_pfn_t: provided by the caller, filled in by function
 * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, 0 success
 *
 * This snapshots the CPU page table for a range of virtual addresses. Snapshot
 * validity is tracked by range struct. See hmm_vma_range_done() for further
 * information.
 *
 * The range struct is initialized here. It tracks the CPU page table, but only
 * if the function returns success (0), in which case the caller must then call
 * hmm_vma_range_done() to stop CPU page table update tracking on this range.
 *
 * NOT CALLING hmm_vma_range_done() IF FUNCTION RETURNS 0 WILL LEAD TO SERIOUS
 * MEMORY CORRUPTION ! YOU HAVE BEEN WARNED !
 */
int hmm_vma_get_pfns(struct vm_area_struct *vma,
		     struct hmm_range *range,
		     unsigned long start,
		     unsigned long end,
		     hmm_pfn_t *pfns)
{
503
	struct hmm_vma_walk hmm_vma_walk;
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
	struct mm_walk mm_walk;
	struct hmm *hmm;

	/* FIXME support hugetlb fs */
	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
		hmm_pfns_special(pfns, start, end);
		return -EINVAL;
	}

	/* Sanity check, this really should not happen ! */
	if (start < vma->vm_start || start >= vma->vm_end)
		return -EINVAL;
	if (end < vma->vm_start || end > vma->vm_end)
		return -EINVAL;

	hmm = hmm_register(vma->vm_mm);
	if (!hmm)
		return -ENOMEM;
	/* Caller must have registered a mirror, via hmm_mirror_register() ! */
	if (!hmm->mmu_notifier.ops)
		return -EINVAL;

	/* Initialize range to track CPU page table update */
	range->start = start;
	range->pfns = pfns;
	range->end = end;
	spin_lock(&hmm->lock);
	range->valid = true;
	list_add_rcu(&range->list, &hmm->ranges);
	spin_unlock(&hmm->lock);

535 536 537 538
	hmm_vma_walk.fault = false;
	hmm_vma_walk.range = range;
	mm_walk.private = &hmm_vma_walk;

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
	mm_walk.vma = vma;
	mm_walk.mm = vma->vm_mm;
	mm_walk.pte_entry = NULL;
	mm_walk.test_walk = NULL;
	mm_walk.hugetlb_entry = NULL;
	mm_walk.pmd_entry = hmm_vma_walk_pmd;
	mm_walk.pte_hole = hmm_vma_walk_hole;

	walk_page_range(start, end, &mm_walk);
	return 0;
}
EXPORT_SYMBOL(hmm_vma_get_pfns);

/*
 * hmm_vma_range_done() - stop tracking change to CPU page table over a range
 * @vma: virtual memory area containing the virtual address range
 * @range: range being tracked
 * Returns: false if range data has been invalidated, true otherwise
 *
 * Range struct is used to track updates to the CPU page table after a call to
 * either hmm_vma_get_pfns() or hmm_vma_fault(). Once the device driver is done
 * using the data,  or wants to lock updates to the data it got from those
 * functions, it must call the hmm_vma_range_done() function, which will then
 * stop tracking CPU page table updates.
 *
 * Note that device driver must still implement general CPU page table update
 * tracking either by using hmm_mirror (see hmm_mirror_register()) or by using
 * the mmu_notifier API directly.
 *
 * CPU page table update tracking done through hmm_range is only temporary and
 * to be used while trying to duplicate CPU page table contents for a range of
 * virtual addresses.
 *
 * There are two ways to use this :
 * again:
574
 *   hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
575 576 577 578 579 580 581 582 583 584
 *   trans = device_build_page_table_update_transaction(pfns);
 *   device_page_table_lock();
 *   if (!hmm_vma_range_done(vma, range)) {
 *     device_page_table_unlock();
 *     goto again;
 *   }
 *   device_commit_transaction(trans);
 *   device_page_table_unlock();
 *
 * Or:
585
 *   hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613
 *   device_page_table_lock();
 *   hmm_vma_range_done(vma, range);
 *   device_update_page_table(pfns);
 *   device_page_table_unlock();
 */
bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range)
{
	unsigned long npages = (range->end - range->start) >> PAGE_SHIFT;
	struct hmm *hmm;

	if (range->end <= range->start) {
		BUG();
		return false;
	}

	hmm = hmm_register(vma->vm_mm);
	if (!hmm) {
		memset(range->pfns, 0, sizeof(*range->pfns) * npages);
		return false;
	}

	spin_lock(&hmm->lock);
	list_del_rcu(&range->list);
	spin_unlock(&hmm->lock);

	return range->valid;
}
EXPORT_SYMBOL(hmm_vma_range_done);
614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736

/*
 * hmm_vma_fault() - try to fault some address in a virtual address range
 * @vma: virtual memory area containing the virtual address range
 * @range: use to track pfns array content validity
 * @start: fault range virtual start address (inclusive)
 * @end: fault range virtual end address (exclusive)
 * @pfns: array of hmm_pfn_t, only entry with fault flag set will be faulted
 * @write: is it a write fault
 * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
 * Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop)
 *
 * This is similar to a regular CPU page fault except that it will not trigger
 * any memory migration if the memory being faulted is not accessible by CPUs.
 *
 * On error, for one virtual address in the range, the function will set the
 * hmm_pfn_t error flag for the corresponding pfn entry.
 *
 * Expected use pattern:
 * retry:
 *   down_read(&mm->mmap_sem);
 *   // Find vma and address device wants to fault, initialize hmm_pfn_t
 *   // array accordingly
 *   ret = hmm_vma_fault(vma, start, end, pfns, allow_retry);
 *   switch (ret) {
 *   case -EAGAIN:
 *     hmm_vma_range_done(vma, range);
 *     // You might want to rate limit or yield to play nicely, you may
 *     // also commit any valid pfn in the array assuming that you are
 *     // getting true from hmm_vma_range_monitor_end()
 *     goto retry;
 *   case 0:
 *     break;
 *   default:
 *     // Handle error !
 *     up_read(&mm->mmap_sem)
 *     return;
 *   }
 *   // Take device driver lock that serialize device page table update
 *   driver_lock_device_page_table_update();
 *   hmm_vma_range_done(vma, range);
 *   // Commit pfns we got from hmm_vma_fault()
 *   driver_unlock_device_page_table_update();
 *   up_read(&mm->mmap_sem)
 *
 * YOU MUST CALL hmm_vma_range_done() AFTER THIS FUNCTION RETURN SUCCESS (0)
 * BEFORE FREEING THE range struct OR YOU WILL HAVE SERIOUS MEMORY CORRUPTION !
 *
 * YOU HAVE BEEN WARNED !
 */
int hmm_vma_fault(struct vm_area_struct *vma,
		  struct hmm_range *range,
		  unsigned long start,
		  unsigned long end,
		  hmm_pfn_t *pfns,
		  bool write,
		  bool block)
{
	struct hmm_vma_walk hmm_vma_walk;
	struct mm_walk mm_walk;
	struct hmm *hmm;
	int ret;

	/* Sanity check, this really should not happen ! */
	if (start < vma->vm_start || start >= vma->vm_end)
		return -EINVAL;
	if (end < vma->vm_start || end > vma->vm_end)
		return -EINVAL;

	hmm = hmm_register(vma->vm_mm);
	if (!hmm) {
		hmm_pfns_clear(pfns, start, end);
		return -ENOMEM;
	}
	/* Caller must have registered a mirror using hmm_mirror_register() */
	if (!hmm->mmu_notifier.ops)
		return -EINVAL;

	/* Initialize range to track CPU page table update */
	range->start = start;
	range->pfns = pfns;
	range->end = end;
	spin_lock(&hmm->lock);
	range->valid = true;
	list_add_rcu(&range->list, &hmm->ranges);
	spin_unlock(&hmm->lock);

	/* FIXME support hugetlb fs */
	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
		hmm_pfns_special(pfns, start, end);
		return 0;
	}

	hmm_vma_walk.fault = true;
	hmm_vma_walk.write = write;
	hmm_vma_walk.block = block;
	hmm_vma_walk.range = range;
	mm_walk.private = &hmm_vma_walk;
	hmm_vma_walk.last = range->start;

	mm_walk.vma = vma;
	mm_walk.mm = vma->vm_mm;
	mm_walk.pte_entry = NULL;
	mm_walk.test_walk = NULL;
	mm_walk.hugetlb_entry = NULL;
	mm_walk.pmd_entry = hmm_vma_walk_pmd;
	mm_walk.pte_hole = hmm_vma_walk_hole;

	do {
		ret = walk_page_range(start, end, &mm_walk);
		start = hmm_vma_walk.last;
	} while (ret == -EAGAIN);

	if (ret) {
		unsigned long i;

		i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
		hmm_pfns_clear(&pfns[i], hmm_vma_walk.last, end);
		hmm_vma_range_done(vma, range);
	}
	return ret;
}
EXPORT_SYMBOL(hmm_vma_fault);
737
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
738 739


740
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1039 1040 1041 1042 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
struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
				       unsigned long addr)
{
	struct page *page;

	page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
	if (!page)
		return NULL;
	lock_page(page);
	return page;
}
EXPORT_SYMBOL(hmm_vma_alloc_locked_page);


static void hmm_devmem_ref_release(struct percpu_ref *ref)
{
	struct hmm_devmem *devmem;

	devmem = container_of(ref, struct hmm_devmem, ref);
	complete(&devmem->completion);
}

static void hmm_devmem_ref_exit(void *data)
{
	struct percpu_ref *ref = data;
	struct hmm_devmem *devmem;

	devmem = container_of(ref, struct hmm_devmem, ref);
	percpu_ref_exit(ref);
	devm_remove_action(devmem->device, &hmm_devmem_ref_exit, data);
}

static void hmm_devmem_ref_kill(void *data)
{
	struct percpu_ref *ref = data;
	struct hmm_devmem *devmem;

	devmem = container_of(ref, struct hmm_devmem, ref);
	percpu_ref_kill(ref);
	wait_for_completion(&devmem->completion);
	devm_remove_action(devmem->device, &hmm_devmem_ref_kill, data);
}

static int hmm_devmem_fault(struct vm_area_struct *vma,
			    unsigned long addr,
			    const struct page *page,
			    unsigned int flags,
			    pmd_t *pmdp)
{
	struct hmm_devmem *devmem = page->pgmap->data;

	return devmem->ops->fault(devmem, vma, addr, page, flags, pmdp);
}

static void hmm_devmem_free(struct page *page, void *data)
{
	struct hmm_devmem *devmem = data;

	devmem->ops->free(devmem, page);
}

static DEFINE_MUTEX(hmm_devmem_lock);
static RADIX_TREE(hmm_devmem_radix, GFP_KERNEL);

static void hmm_devmem_radix_release(struct resource *resource)
{
	resource_size_t key, align_start, align_size, align_end;

	align_start = resource->start & ~(PA_SECTION_SIZE - 1);
	align_size = ALIGN(resource_size(resource), PA_SECTION_SIZE);
	align_end = align_start + align_size - 1;

	mutex_lock(&hmm_devmem_lock);
	for (key = resource->start;
	     key <= resource->end;
	     key += PA_SECTION_SIZE)
		radix_tree_delete(&hmm_devmem_radix, key >> PA_SECTION_SHIFT);
	mutex_unlock(&hmm_devmem_lock);
}

static void hmm_devmem_release(struct device *dev, void *data)
{
	struct hmm_devmem *devmem = data;
	struct resource *resource = devmem->resource;
	unsigned long start_pfn, npages;
	struct zone *zone;
	struct page *page;

	if (percpu_ref_tryget_live(&devmem->ref)) {
		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
		percpu_ref_put(&devmem->ref);
	}

	/* pages are dead and unused, undo the arch mapping */
	start_pfn = (resource->start & ~(PA_SECTION_SIZE - 1)) >> PAGE_SHIFT;
	npages = ALIGN(resource_size(resource), PA_SECTION_SIZE) >> PAGE_SHIFT;

	page = pfn_to_page(start_pfn);
	zone = page_zone(page);

	mem_hotplug_begin();
	__remove_pages(zone, start_pfn, npages);
	mem_hotplug_done();

	hmm_devmem_radix_release(resource);
}

static struct hmm_devmem *hmm_devmem_find(resource_size_t phys)
{
	WARN_ON_ONCE(!rcu_read_lock_held());

	return radix_tree_lookup(&hmm_devmem_radix, phys >> PA_SECTION_SHIFT);
}

static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
{
	resource_size_t key, align_start, align_size, align_end;
	struct device *device = devmem->device;
	int ret, nid, is_ram;
	unsigned long pfn;

	align_start = devmem->resource->start & ~(PA_SECTION_SIZE - 1);
	align_size = ALIGN(devmem->resource->start +
			   resource_size(devmem->resource),
			   PA_SECTION_SIZE) - align_start;

	is_ram = region_intersects(align_start, align_size,
				   IORESOURCE_SYSTEM_RAM,
				   IORES_DESC_NONE);
	if (is_ram == REGION_MIXED) {
		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
				__func__, devmem->resource);
		return -ENXIO;
	}
	if (is_ram == REGION_INTERSECTS)
		return -ENXIO;

	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
	devmem->pagemap.res = devmem->resource;
	devmem->pagemap.page_fault = hmm_devmem_fault;
	devmem->pagemap.page_free = hmm_devmem_free;
	devmem->pagemap.dev = devmem->device;
	devmem->pagemap.ref = &devmem->ref;
	devmem->pagemap.data = devmem;

	mutex_lock(&hmm_devmem_lock);
	align_end = align_start + align_size - 1;
	for (key = align_start; key <= align_end; key += PA_SECTION_SIZE) {
		struct hmm_devmem *dup;

		rcu_read_lock();
		dup = hmm_devmem_find(key);
		rcu_read_unlock();
		if (dup) {
			dev_err(device, "%s: collides with mapping for %s\n",
				__func__, dev_name(dup->device));
			mutex_unlock(&hmm_devmem_lock);
			ret = -EBUSY;
			goto error;
		}
		ret = radix_tree_insert(&hmm_devmem_radix,
					key >> PA_SECTION_SHIFT,
					devmem);
		if (ret) {
			dev_err(device, "%s: failed: %d\n", __func__, ret);
			mutex_unlock(&hmm_devmem_lock);
			goto error_radix;
		}
	}
	mutex_unlock(&hmm_devmem_lock);

	nid = dev_to_node(device);
	if (nid < 0)
		nid = numa_mem_id();

	mem_hotplug_begin();
	/*
	 * For device private memory we call add_pages() as we only need to
	 * allocate and initialize struct page for the device memory. More-
	 * over the device memory is un-accessible thus we do not want to
	 * create a linear mapping for the memory like arch_add_memory()
	 * would do.
	 */
	ret = add_pages(nid, align_start >> PAGE_SHIFT,
			align_size >> PAGE_SHIFT, false);
	if (ret) {
		mem_hotplug_done();
		goto error_add_memory;
	}
	move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
				align_start >> PAGE_SHIFT,
				align_size >> PAGE_SHIFT);
	mem_hotplug_done();

	for (pfn = devmem->pfn_first; pfn < devmem->pfn_last; pfn++) {
		struct page *page = pfn_to_page(pfn);

		page->pgmap = &devmem->pagemap;
	}
	return 0;

error_add_memory:
	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
error_radix:
	hmm_devmem_radix_release(devmem->resource);
error:
	return ret;
}

static int hmm_devmem_match(struct device *dev, void *data, void *match_data)
{
	struct hmm_devmem *devmem = data;

	return devmem->resource == match_data;
}

static void hmm_devmem_pages_remove(struct hmm_devmem *devmem)
{
	devres_release(devmem->device, &hmm_devmem_release,
		       &hmm_devmem_match, devmem->resource);
}

/*
 * hmm_devmem_add() - hotplug ZONE_DEVICE memory for device memory
 *
 * @ops: memory event device driver callback (see struct hmm_devmem_ops)
 * @device: device struct to bind the resource too
 * @size: size in bytes of the device memory to add
 * Returns: pointer to new hmm_devmem struct ERR_PTR otherwise
 *
 * This function first finds an empty range of physical address big enough to
 * contain the new resource, and then hotplugs it as ZONE_DEVICE memory, which
 * in turn allocates struct pages. It does not do anything beyond that; all
 * events affecting the memory will go through the various callbacks provided
 * by hmm_devmem_ops struct.
 *
 * Device driver should call this function during device initialization and
 * is then responsible of memory management. HMM only provides helpers.
 */
struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
				  struct device *device,
				  unsigned long size)
{
	struct hmm_devmem *devmem;
	resource_size_t addr;
	int ret;

	static_branch_enable(&device_private_key);

	devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
				   GFP_KERNEL, dev_to_node(device));
	if (!devmem)
		return ERR_PTR(-ENOMEM);

	init_completion(&devmem->completion);
	devmem->pfn_first = -1UL;
	devmem->pfn_last = -1UL;
	devmem->resource = NULL;
	devmem->device = device;
	devmem->ops = ops;

	ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
			      0, GFP_KERNEL);
	if (ret)
		goto error_percpu_ref;

	ret = devm_add_action(device, hmm_devmem_ref_exit, &devmem->ref);
	if (ret)
		goto error_devm_add_action;

	size = ALIGN(size, PA_SECTION_SIZE);
	addr = min((unsigned long)iomem_resource.end,
		   (1UL << MAX_PHYSMEM_BITS) - 1);
	addr = addr - size + 1UL;

	/*
	 * FIXME add a new helper to quickly walk resource tree and find free
	 * range
	 *
	 * FIXME what about ioport_resource resource ?
	 */
	for (; addr > size && addr >= iomem_resource.start; addr -= size) {
		ret = region_intersects(addr, size, 0, IORES_DESC_NONE);
		if (ret != REGION_DISJOINT)
			continue;

		devmem->resource = devm_request_mem_region(device, addr, size,
							   dev_name(device));
		if (!devmem->resource) {
			ret = -ENOMEM;
			goto error_no_resource;
		}
		break;
	}
	if (!devmem->resource) {
		ret = -ERANGE;
		goto error_no_resource;
	}

	devmem->resource->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
	devmem->pfn_last = devmem->pfn_first +
			   (resource_size(devmem->resource) >> PAGE_SHIFT);

	ret = hmm_devmem_pages_create(devmem);
	if (ret)
		goto error_pages;

	devres_add(device, devmem);

	ret = devm_add_action(device, hmm_devmem_ref_kill, &devmem->ref);
	if (ret) {
		hmm_devmem_remove(devmem);
		return ERR_PTR(ret);
	}

	return devmem;

error_pages:
	devm_release_mem_region(device, devmem->resource->start,
				resource_size(devmem->resource));
error_no_resource:
error_devm_add_action:
	hmm_devmem_ref_kill(&devmem->ref);
	hmm_devmem_ref_exit(&devmem->ref);
error_percpu_ref:
	devres_free(devmem);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL(hmm_devmem_add);

/*
 * hmm_devmem_remove() - remove device memory (kill and free ZONE_DEVICE)
 *
 * @devmem: hmm_devmem struct use to track and manage the ZONE_DEVICE memory
 *
 * This will hot-unplug memory that was hotplugged by hmm_devmem_add on behalf
 * of the device driver. It will free struct page and remove the resource that
 * reserved the physical address range for this device memory.
 */
void hmm_devmem_remove(struct hmm_devmem *devmem)
{
	resource_size_t start, size;
	struct device *device;

	if (!devmem)
		return;

	device = devmem->device;
	start = devmem->resource->start;
	size = resource_size(devmem->resource);

	hmm_devmem_ref_kill(&devmem->ref);
	hmm_devmem_ref_exit(&devmem->ref);
	hmm_devmem_pages_remove(devmem);

	devm_release_mem_region(device, start, size);
}
EXPORT_SYMBOL(hmm_devmem_remove);
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 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179

/*
 * A device driver that wants to handle multiple devices memory through a
 * single fake device can use hmm_device to do so. This is purely a helper
 * and it is not needed to make use of any HMM functionality.
 */
#define HMM_DEVICE_MAX 256

static DECLARE_BITMAP(hmm_device_mask, HMM_DEVICE_MAX);
static DEFINE_SPINLOCK(hmm_device_lock);
static struct class *hmm_device_class;
static dev_t hmm_device_devt;

static void hmm_device_release(struct device *device)
{
	struct hmm_device *hmm_device;

	hmm_device = container_of(device, struct hmm_device, device);
	spin_lock(&hmm_device_lock);
	clear_bit(hmm_device->minor, hmm_device_mask);
	spin_unlock(&hmm_device_lock);

	kfree(hmm_device);
}

struct hmm_device *hmm_device_new(void *drvdata)
{
	struct hmm_device *hmm_device;

	hmm_device = kzalloc(sizeof(*hmm_device), GFP_KERNEL);
	if (!hmm_device)
		return ERR_PTR(-ENOMEM);

	spin_lock(&hmm_device_lock);
	hmm_device->minor = find_first_zero_bit(hmm_device_mask, HMM_DEVICE_MAX);
	if (hmm_device->minor >= HMM_DEVICE_MAX) {
		spin_unlock(&hmm_device_lock);
		kfree(hmm_device);
		return ERR_PTR(-EBUSY);
	}
	set_bit(hmm_device->minor, hmm_device_mask);
	spin_unlock(&hmm_device_lock);

	dev_set_name(&hmm_device->device, "hmm_device%d", hmm_device->minor);
	hmm_device->device.devt = MKDEV(MAJOR(hmm_device_devt),
					hmm_device->minor);
	hmm_device->device.release = hmm_device_release;
	dev_set_drvdata(&hmm_device->device, drvdata);
	hmm_device->device.class = hmm_device_class;
	device_initialize(&hmm_device->device);

	return hmm_device;
}
EXPORT_SYMBOL(hmm_device_new);

void hmm_device_put(struct hmm_device *hmm_device)
{
	put_device(&hmm_device->device);
}
EXPORT_SYMBOL(hmm_device_put);

static int __init hmm_init(void)
{
	int ret;

	ret = alloc_chrdev_region(&hmm_device_devt, 0,
				  HMM_DEVICE_MAX,
				  "hmm_device");
	if (ret)
		return ret;

	hmm_device_class = class_create(THIS_MODULE, "hmm_device");
	if (IS_ERR(hmm_device_class)) {
		unregister_chrdev_region(hmm_device_devt, HMM_DEVICE_MAX);
		return PTR_ERR(hmm_device_class);
	}
	return 0;
}

device_initcall(hmm_init);
1180
#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */