khugepaged.c 47.7 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2 3 4 5
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/sched.h>
6
#include <linux/sched/mm.h>
7
#include <linux/sched/coredump.h>
8 9 10 11 12 13 14 15 16 17 18 19
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/swapops.h>
20
#include <linux/shmem_fs.h>
21 22 23 24 25 26 27 28 29 30 31 32

#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"

enum scan_result {
	SCAN_FAIL,
	SCAN_SUCCEED,
	SCAN_PMD_NULL,
	SCAN_EXCEED_NONE_PTE,
	SCAN_PTE_NON_PRESENT,
	SCAN_PAGE_RO,
33
	SCAN_LACK_REFERENCED_PAGE,
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48
	SCAN_PAGE_NULL,
	SCAN_SCAN_ABORT,
	SCAN_PAGE_COUNT,
	SCAN_PAGE_LRU,
	SCAN_PAGE_LOCK,
	SCAN_PAGE_ANON,
	SCAN_PAGE_COMPOUND,
	SCAN_ANY_PROCESS,
	SCAN_VMA_NULL,
	SCAN_VMA_CHECK,
	SCAN_ADDRESS_RANGE,
	SCAN_SWAP_CACHE_PAGE,
	SCAN_DEL_PAGE_LRU,
	SCAN_ALLOC_HUGE_PAGE_FAIL,
	SCAN_CGROUP_CHARGE_FAIL,
49 50
	SCAN_EXCEED_SWAP_PTE,
	SCAN_TRUNCATED,
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108
};

#define CREATE_TRACE_POINTS
#include <trace/events/huge_memory.h>

/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
/* during fragmentation poll the hugepage allocator once every minute */
static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
static unsigned long khugepaged_sleep_expire;
static DEFINE_SPINLOCK(khugepaged_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
/*
 * default collapse hugepages if there is at least one pte mapped like
 * it would have happened if the vma was large enough during page
 * fault.
 */
static unsigned int khugepaged_max_ptes_none __read_mostly;
static unsigned int khugepaged_max_ptes_swap __read_mostly;

#define MM_SLOTS_HASH_BITS 10
static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);

static struct kmem_cache *mm_slot_cache __read_mostly;

/**
 * struct mm_slot - hash lookup from mm to mm_slot
 * @hash: hash collision list
 * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head
 * @mm: the mm that this information is valid for
 */
struct mm_slot {
	struct hlist_node hash;
	struct list_head mm_node;
	struct mm_struct *mm;
};

/**
 * struct khugepaged_scan - cursor for scanning
 * @mm_head: the head of the mm list to scan
 * @mm_slot: the current mm_slot we are scanning
 * @address: the next address inside that to be scanned
 *
 * There is only the one khugepaged_scan instance of this cursor structure.
 */
struct khugepaged_scan {
	struct list_head mm_head;
	struct mm_slot *mm_slot;
	unsigned long address;
};

static struct khugepaged_scan khugepaged_scan = {
	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
};

109
#ifdef CONFIG_SYSFS
110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
					 struct kobj_attribute *attr,
					 char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs);
}

static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
					  struct kobj_attribute *attr,
					  const char *buf, size_t count)
{
	unsigned long msecs;
	int err;

	err = kstrtoul(buf, 10, &msecs);
	if (err || msecs > UINT_MAX)
		return -EINVAL;

	khugepaged_scan_sleep_millisecs = msecs;
	khugepaged_sleep_expire = 0;
	wake_up_interruptible(&khugepaged_wait);

	return count;
}
static struct kobj_attribute scan_sleep_millisecs_attr =
	__ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show,
	       scan_sleep_millisecs_store);

static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
					  struct kobj_attribute *attr,
					  char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs);
}

static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
					   struct kobj_attribute *attr,
					   const char *buf, size_t count)
{
	unsigned long msecs;
	int err;

	err = kstrtoul(buf, 10, &msecs);
	if (err || msecs > UINT_MAX)
		return -EINVAL;

	khugepaged_alloc_sleep_millisecs = msecs;
	khugepaged_sleep_expire = 0;
	wake_up_interruptible(&khugepaged_wait);

	return count;
}
static struct kobj_attribute alloc_sleep_millisecs_attr =
	__ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show,
	       alloc_sleep_millisecs_store);

static ssize_t pages_to_scan_show(struct kobject *kobj,
				  struct kobj_attribute *attr,
				  char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_pages_to_scan);
}
static ssize_t pages_to_scan_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int err;
	unsigned long pages;

	err = kstrtoul(buf, 10, &pages);
	if (err || !pages || pages > UINT_MAX)
		return -EINVAL;

	khugepaged_pages_to_scan = pages;

	return count;
}
static struct kobj_attribute pages_to_scan_attr =
	__ATTR(pages_to_scan, 0644, pages_to_scan_show,
	       pages_to_scan_store);

static ssize_t pages_collapsed_show(struct kobject *kobj,
				    struct kobj_attribute *attr,
				    char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_pages_collapsed);
}
static struct kobj_attribute pages_collapsed_attr =
	__ATTR_RO(pages_collapsed);

static ssize_t full_scans_show(struct kobject *kobj,
			       struct kobj_attribute *attr,
			       char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_full_scans);
}
static struct kobj_attribute full_scans_attr =
	__ATTR_RO(full_scans);

static ssize_t khugepaged_defrag_show(struct kobject *kobj,
				      struct kobj_attribute *attr, char *buf)
{
	return single_hugepage_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static ssize_t khugepaged_defrag_store(struct kobject *kobj,
				       struct kobj_attribute *attr,
				       const char *buf, size_t count)
{
	return single_hugepage_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static struct kobj_attribute khugepaged_defrag_attr =
	__ATTR(defrag, 0644, khugepaged_defrag_show,
	       khugepaged_defrag_store);

/*
 * max_ptes_none controls if khugepaged should collapse hugepages over
 * any unmapped ptes in turn potentially increasing the memory
 * footprint of the vmas. When max_ptes_none is 0 khugepaged will not
 * reduce the available free memory in the system as it
 * runs. Increasing max_ptes_none will instead potentially reduce the
 * free memory in the system during the khugepaged scan.
 */
static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj,
					     struct kobj_attribute *attr,
					     char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_max_ptes_none);
}
static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj,
					      struct kobj_attribute *attr,
					      const char *buf, size_t count)
{
	int err;
	unsigned long max_ptes_none;

	err = kstrtoul(buf, 10, &max_ptes_none);
	if (err || max_ptes_none > HPAGE_PMD_NR-1)
		return -EINVAL;

	khugepaged_max_ptes_none = max_ptes_none;

	return count;
}
static struct kobj_attribute khugepaged_max_ptes_none_attr =
	__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
	       khugepaged_max_ptes_none_store);

static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj,
					     struct kobj_attribute *attr,
					     char *buf)
{
	return sprintf(buf, "%u\n", khugepaged_max_ptes_swap);
}

static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj,
					      struct kobj_attribute *attr,
					      const char *buf, size_t count)
{
	int err;
	unsigned long max_ptes_swap;

	err  = kstrtoul(buf, 10, &max_ptes_swap);
	if (err || max_ptes_swap > HPAGE_PMD_NR-1)
		return -EINVAL;

	khugepaged_max_ptes_swap = max_ptes_swap;

	return count;
}

static struct kobj_attribute khugepaged_max_ptes_swap_attr =
	__ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show,
	       khugepaged_max_ptes_swap_store);

static struct attribute *khugepaged_attr[] = {
	&khugepaged_defrag_attr.attr,
	&khugepaged_max_ptes_none_attr.attr,
	&pages_to_scan_attr.attr,
	&pages_collapsed_attr.attr,
	&full_scans_attr.attr,
	&scan_sleep_millisecs_attr.attr,
	&alloc_sleep_millisecs_attr.attr,
	&khugepaged_max_ptes_swap_attr.attr,
	NULL,
};

struct attribute_group khugepaged_attr_group = {
	.attrs = khugepaged_attr,
	.name = "khugepaged",
};
302
#endif /* CONFIG_SYSFS */
303

304
#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399

int hugepage_madvise(struct vm_area_struct *vma,
		     unsigned long *vm_flags, int advice)
{
	switch (advice) {
	case MADV_HUGEPAGE:
#ifdef CONFIG_S390
		/*
		 * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390
		 * can't handle this properly after s390_enable_sie, so we simply
		 * ignore the madvise to prevent qemu from causing a SIGSEGV.
		 */
		if (mm_has_pgste(vma->vm_mm))
			return 0;
#endif
		*vm_flags &= ~VM_NOHUGEPAGE;
		*vm_flags |= VM_HUGEPAGE;
		/*
		 * If the vma become good for khugepaged to scan,
		 * register it here without waiting a page fault that
		 * may not happen any time soon.
		 */
		if (!(*vm_flags & VM_NO_KHUGEPAGED) &&
				khugepaged_enter_vma_merge(vma, *vm_flags))
			return -ENOMEM;
		break;
	case MADV_NOHUGEPAGE:
		*vm_flags &= ~VM_HUGEPAGE;
		*vm_flags |= VM_NOHUGEPAGE;
		/*
		 * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning
		 * this vma even if we leave the mm registered in khugepaged if
		 * it got registered before VM_NOHUGEPAGE was set.
		 */
		break;
	}

	return 0;
}

int __init khugepaged_init(void)
{
	mm_slot_cache = kmem_cache_create("khugepaged_mm_slot",
					  sizeof(struct mm_slot),
					  __alignof__(struct mm_slot), 0, NULL);
	if (!mm_slot_cache)
		return -ENOMEM;

	khugepaged_pages_to_scan = HPAGE_PMD_NR * 8;
	khugepaged_max_ptes_none = HPAGE_PMD_NR - 1;
	khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8;

	return 0;
}

void __init khugepaged_destroy(void)
{
	kmem_cache_destroy(mm_slot_cache);
}

static inline struct mm_slot *alloc_mm_slot(void)
{
	if (!mm_slot_cache)	/* initialization failed */
		return NULL;
	return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL);
}

static inline void free_mm_slot(struct mm_slot *mm_slot)
{
	kmem_cache_free(mm_slot_cache, mm_slot);
}

static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;

	hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm)
		if (mm == mm_slot->mm)
			return mm_slot;

	return NULL;
}

static void insert_to_mm_slots_hash(struct mm_struct *mm,
				    struct mm_slot *mm_slot)
{
	mm_slot->mm = mm;
	hash_add(mm_slots_hash, &mm_slot->hash, (long)mm);
}

static inline int khugepaged_test_exit(struct mm_struct *mm)
{
	return atomic_read(&mm->mm_users) == 0;
}

400 401
static bool hugepage_vma_check(struct vm_area_struct *vma,
			       unsigned long vm_flags)
402
{
403 404
	if ((!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
	    (vm_flags & VM_NOHUGEPAGE) ||
405 406 407 408 409 410 411 412 413 414 415 416
	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
		return false;
	if (shmem_file(vma->vm_file)) {
		if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
			return false;
		return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
				HPAGE_PMD_NR);
	}
	if (!vma->anon_vma || vma->vm_ops)
		return false;
	if (is_vma_temporary_stack(vma))
		return false;
417
	return !(vm_flags & VM_NO_KHUGEPAGED);
418 419
}

420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445
int __khugepaged_enter(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	int wakeup;

	mm_slot = alloc_mm_slot();
	if (!mm_slot)
		return -ENOMEM;

	/* __khugepaged_exit() must not run from under us */
	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
		free_mm_slot(mm_slot);
		return 0;
	}

	spin_lock(&khugepaged_mm_lock);
	insert_to_mm_slots_hash(mm, mm_slot);
	/*
	 * Insert just behind the scanning cursor, to let the area settle
	 * down a little.
	 */
	wakeup = list_empty(&khugepaged_scan.mm_head);
	list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head);
	spin_unlock(&khugepaged_mm_lock);

V
Vegard Nossum 已提交
446
	mmgrab(mm);
447 448 449 450 451 452 453 454 455 456
	if (wakeup)
		wake_up_interruptible(&khugepaged_wait);

	return 0;
}

int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
			       unsigned long vm_flags)
{
	unsigned long hstart, hend;
457 458 459 460 461

	/*
	 * khugepaged does not yet work on non-shmem files or special
	 * mappings. And file-private shmem THP is not supported.
	 */
462
	if (!hugepage_vma_check(vma, vm_flags))
463
		return 0;
464

465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505
	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
	hend = vma->vm_end & HPAGE_PMD_MASK;
	if (hstart < hend)
		return khugepaged_enter(vma, vm_flags);
	return 0;
}

void __khugepaged_exit(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	int free = 0;

	spin_lock(&khugepaged_mm_lock);
	mm_slot = get_mm_slot(mm);
	if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
		hash_del(&mm_slot->hash);
		list_del(&mm_slot->mm_node);
		free = 1;
	}
	spin_unlock(&khugepaged_mm_lock);

	if (free) {
		clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
		free_mm_slot(mm_slot);
		mmdrop(mm);
	} else if (mm_slot) {
		/*
		 * This is required to serialize against
		 * khugepaged_test_exit() (which is guaranteed to run
		 * under mmap sem read mode). Stop here (after we
		 * return all pagetables will be destroyed) until
		 * khugepaged has finished working on the pagetables
		 * under the mmap_sem.
		 */
		down_write(&mm->mmap_sem);
		up_write(&mm->mmap_sem);
	}
}

static void release_pte_page(struct page *page)
{
506
	dec_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page));
507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525
	unlock_page(page);
	putback_lru_page(page);
}

static void release_pte_pages(pte_t *pte, pte_t *_pte)
{
	while (--_pte >= pte) {
		pte_t pteval = *_pte;
		if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval)))
			release_pte_page(pte_page(pteval));
	}
}

static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
					unsigned long address,
					pte_t *pte)
{
	struct page *page = NULL;
	pte_t *_pte;
526 527
	int none_or_zero = 0, result = 0, referenced = 0;
	bool writable = false;
528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551

	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
	     _pte++, address += PAGE_SIZE) {
		pte_t pteval = *_pte;
		if (pte_none(pteval) || (pte_present(pteval) &&
				is_zero_pfn(pte_pfn(pteval)))) {
			if (!userfaultfd_armed(vma) &&
			    ++none_or_zero <= khugepaged_max_ptes_none) {
				continue;
			} else {
				result = SCAN_EXCEED_NONE_PTE;
				goto out;
			}
		}
		if (!pte_present(pteval)) {
			result = SCAN_PTE_NON_PRESENT;
			goto out;
		}
		page = vm_normal_page(vma, address, pteval);
		if (unlikely(!page)) {
			result = SCAN_PAGE_NULL;
			goto out;
		}

552 553 554 555 556 557
		/* TODO: teach khugepaged to collapse THP mapped with pte */
		if (PageCompound(page)) {
			result = SCAN_PAGE_COMPOUND;
			goto out;
		}

558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575
		VM_BUG_ON_PAGE(!PageAnon(page), page);

		/*
		 * We can do it before isolate_lru_page because the
		 * page can't be freed from under us. NOTE: PG_lock
		 * is needed to serialize against split_huge_page
		 * when invoked from the VM.
		 */
		if (!trylock_page(page)) {
			result = SCAN_PAGE_LOCK;
			goto out;
		}

		/*
		 * cannot use mapcount: can't collapse if there's a gup pin.
		 * The page must only be referenced by the scanned process
		 * and page swap cache.
		 */
576
		if (page_count(page) != 1 + PageSwapCache(page)) {
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604
			unlock_page(page);
			result = SCAN_PAGE_COUNT;
			goto out;
		}
		if (pte_write(pteval)) {
			writable = true;
		} else {
			if (PageSwapCache(page) &&
			    !reuse_swap_page(page, NULL)) {
				unlock_page(page);
				result = SCAN_SWAP_CACHE_PAGE;
				goto out;
			}
			/*
			 * Page is not in the swap cache. It can be collapsed
			 * into a THP.
			 */
		}

		/*
		 * Isolate the page to avoid collapsing an hugepage
		 * currently in use by the VM.
		 */
		if (isolate_lru_page(page)) {
			unlock_page(page);
			result = SCAN_DEL_PAGE_LRU;
			goto out;
		}
605 606
		inc_node_page_state(page,
				NR_ISOLATED_ANON + page_is_file_cache(page));
607 608 609
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		VM_BUG_ON_PAGE(PageLRU(page), page);

610
		/* There should be enough young pte to collapse the page */
611 612 613
		if (pte_young(pteval) ||
		    page_is_young(page) || PageReferenced(page) ||
		    mmu_notifier_test_young(vma->vm_mm, address))
614
			referenced++;
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
	}
	if (likely(writable)) {
		if (likely(referenced)) {
			result = SCAN_SUCCEED;
			trace_mm_collapse_huge_page_isolate(page, none_or_zero,
							    referenced, writable, result);
			return 1;
		}
	} else {
		result = SCAN_PAGE_RO;
	}

out:
	release_pte_pages(pte, _pte);
	trace_mm_collapse_huge_page_isolate(page, none_or_zero,
					    referenced, writable, result);
	return 0;
}

static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
				      struct vm_area_struct *vma,
				      unsigned long address,
				      spinlock_t *ptl)
{
	pte_t *_pte;
640 641
	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
				_pte++, page++, address += PAGE_SIZE) {
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
		pte_t pteval = *_pte;
		struct page *src_page;

		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
			clear_user_highpage(page, address);
			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
			if (is_zero_pfn(pte_pfn(pteval))) {
				/*
				 * ptl mostly unnecessary.
				 */
				spin_lock(ptl);
				/*
				 * paravirt calls inside pte_clear here are
				 * superfluous.
				 */
				pte_clear(vma->vm_mm, address, _pte);
				spin_unlock(ptl);
			}
		} else {
			src_page = pte_page(pteval);
			copy_user_highpage(page, src_page, address, vma);
			VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page);
			release_pte_page(src_page);
			/*
			 * ptl mostly unnecessary, but preempt has to
			 * be disabled to update the per-cpu stats
			 * inside page_remove_rmap().
			 */
			spin_lock(ptl);
			/*
			 * paravirt calls inside pte_clear here are
			 * superfluous.
			 */
			pte_clear(vma->vm_mm, address, _pte);
			page_remove_rmap(src_page, false);
			spin_unlock(ptl);
			free_page_and_swap_cache(src_page);
		}
	}
}

static void khugepaged_alloc_sleep(void)
{
	DEFINE_WAIT(wait);

	add_wait_queue(&khugepaged_wait, &wait);
	freezable_schedule_timeout_interruptible(
		msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
	remove_wait_queue(&khugepaged_wait, &wait);
}

static int khugepaged_node_load[MAX_NUMNODES];

static bool khugepaged_scan_abort(int nid)
{
	int i;

	/*
700
	 * If node_reclaim_mode is disabled, then no extra effort is made to
701 702
	 * allocate memory locally.
	 */
703
	if (!node_reclaim_mode)
704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721
		return false;

	/* If there is a count for this node already, it must be acceptable */
	if (khugepaged_node_load[nid])
		return false;

	for (i = 0; i < MAX_NUMNODES; i++) {
		if (!khugepaged_node_load[i])
			continue;
		if (node_distance(nid, i) > RECLAIM_DISTANCE)
			return true;
	}
	return false;
}

/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */
static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)
{
722
	return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT;
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768
}

#ifdef CONFIG_NUMA
static int khugepaged_find_target_node(void)
{
	static int last_khugepaged_target_node = NUMA_NO_NODE;
	int nid, target_node = 0, max_value = 0;

	/* find first node with max normal pages hit */
	for (nid = 0; nid < MAX_NUMNODES; nid++)
		if (khugepaged_node_load[nid] > max_value) {
			max_value = khugepaged_node_load[nid];
			target_node = nid;
		}

	/* do some balance if several nodes have the same hit record */
	if (target_node <= last_khugepaged_target_node)
		for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES;
				nid++)
			if (max_value == khugepaged_node_load[nid]) {
				target_node = nid;
				break;
			}

	last_khugepaged_target_node = target_node;
	return target_node;
}

static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
{
	if (IS_ERR(*hpage)) {
		if (!*wait)
			return false;

		*wait = false;
		*hpage = NULL;
		khugepaged_alloc_sleep();
	} else if (*hpage) {
		put_page(*hpage);
		*hpage = NULL;
	}

	return true;
}

static struct page *
769
khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
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
{
	VM_BUG_ON_PAGE(*hpage, *hpage);

	*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
	if (unlikely(!*hpage)) {
		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
		*hpage = ERR_PTR(-ENOMEM);
		return NULL;
	}

	prep_transhuge_page(*hpage);
	count_vm_event(THP_COLLAPSE_ALLOC);
	return *hpage;
}
#else
static int khugepaged_find_target_node(void)
{
	return 0;
}

static inline struct page *alloc_khugepaged_hugepage(void)
{
	struct page *page;

	page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(),
			   HPAGE_PMD_ORDER);
	if (page)
		prep_transhuge_page(page);
	return page;
}

static struct page *khugepaged_alloc_hugepage(bool *wait)
{
	struct page *hpage;

	do {
		hpage = alloc_khugepaged_hugepage();
		if (!hpage) {
			count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
			if (!*wait)
				return NULL;

			*wait = false;
			khugepaged_alloc_sleep();
		} else
			count_vm_event(THP_COLLAPSE_ALLOC);
	} while (unlikely(!hpage) && likely(khugepaged_enabled()));

	return hpage;
}

static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
{
	if (!*hpage)
		*hpage = khugepaged_alloc_hugepage(wait);

	if (unlikely(!*hpage))
		return false;

	return true;
}

static struct page *
833
khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
834 835 836 837 838 839 840 841 842 843 844 845 846 847
{
	VM_BUG_ON(!*hpage);

	return  *hpage;
}
#endif

/*
 * If mmap_sem temporarily dropped, revalidate vma
 * before taking mmap_sem.
 * Return 0 if succeeds, otherwise return none-zero
 * value (scan code).
 */

848 849
static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
		struct vm_area_struct **vmap)
850 851 852 853 854 855 856
{
	struct vm_area_struct *vma;
	unsigned long hstart, hend;

	if (unlikely(khugepaged_test_exit(mm)))
		return SCAN_ANY_PROCESS;

857
	*vmap = vma = find_vma(mm, address);
858 859 860 861 862 863 864
	if (!vma)
		return SCAN_VMA_NULL;

	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
	hend = vma->vm_end & HPAGE_PMD_MASK;
	if (address < hstart || address + HPAGE_PMD_SIZE > hend)
		return SCAN_ADDRESS_RANGE;
865
	if (!hugepage_vma_check(vma, vma->vm_flags))
866 867 868 869 870 871 872 873 874 875 876 877 878 879
		return SCAN_VMA_CHECK;
	return 0;
}

/*
 * Bring missing pages in from swap, to complete THP collapse.
 * Only done if khugepaged_scan_pmd believes it is worthwhile.
 *
 * Called and returns without pte mapped or spinlocks held,
 * but with mmap_sem held to protect against vma changes.
 */

static bool __collapse_huge_page_swapin(struct mm_struct *mm,
					struct vm_area_struct *vma,
880 881
					unsigned long address, pmd_t *pmd,
					int referenced)
882
{
883 884
	int swapped_in = 0;
	vm_fault_t ret = 0;
J
Jan Kara 已提交
885
	struct vm_fault vmf = {
886 887 888 889
		.vma = vma,
		.address = address,
		.flags = FAULT_FLAG_ALLOW_RETRY,
		.pmd = pmd,
890
		.pgoff = linear_page_index(vma, address),
891 892
	};

893 894 895 896 897
	/* we only decide to swapin, if there is enough young ptes */
	if (referenced < HPAGE_PMD_NR/2) {
		trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
		return false;
	}
J
Jan Kara 已提交
898 899 900
	vmf.pte = pte_offset_map(pmd, address);
	for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE;
			vmf.pte++, vmf.address += PAGE_SIZE) {
J
Jan Kara 已提交
901 902
		vmf.orig_pte = *vmf.pte;
		if (!is_swap_pte(vmf.orig_pte))
903 904
			continue;
		swapped_in++;
J
Jan Kara 已提交
905
		ret = do_swap_page(&vmf);
906

907 908 909
		/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
		if (ret & VM_FAULT_RETRY) {
			down_read(&mm->mmap_sem);
J
Jan Kara 已提交
910
			if (hugepage_vma_revalidate(mm, address, &vmf.vma)) {
911
				/* vma is no longer available, don't continue to swapin */
912
				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
913
				return false;
914
			}
915
			/* check if the pmd is still valid */
916 917
			if (mm_find_pmd(mm, address) != pmd) {
				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
918
				return false;
919
			}
920 921
		}
		if (ret & VM_FAULT_ERROR) {
922
			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
923 924 925
			return false;
		}
		/* pte is unmapped now, we need to map it */
J
Jan Kara 已提交
926
		vmf.pte = pte_offset_map(pmd, vmf.address);
927
	}
J
Jan Kara 已提交
928 929
	vmf.pte--;
	pte_unmap(vmf.pte);
930
	trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1);
931 932 933 934 935 936
	return true;
}

static void collapse_huge_page(struct mm_struct *mm,
				   unsigned long address,
				   struct page **hpage,
937
				   int node, int referenced)
938 939 940 941 942 943 944 945
{
	pmd_t *pmd, _pmd;
	pte_t *pte;
	pgtable_t pgtable;
	struct page *new_page;
	spinlock_t *pmd_ptl, *pte_ptl;
	int isolated = 0, result = 0;
	struct mem_cgroup *memcg;
946
	struct vm_area_struct *vma;
947 948 949 950 951 952 953
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */
	gfp_t gfp;

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);

	/* Only allocate from the target node */
M
Michal Hocko 已提交
954
	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
955

956 957 958 959 960 961 962 963
	/*
	 * Before allocating the hugepage, release the mmap_sem read lock.
	 * The allocation can take potentially a long time if it involves
	 * sync compaction, and we do not need to hold the mmap_sem during
	 * that. We will recheck the vma after taking it again in write mode.
	 */
	up_read(&mm->mmap_sem);
	new_page = khugepaged_alloc_page(hpage, gfp, node);
964 965 966 967 968
	if (!new_page) {
		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
		goto out_nolock;
	}

969
	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
970 971 972 973 974
		result = SCAN_CGROUP_CHARGE_FAIL;
		goto out_nolock;
	}

	down_read(&mm->mmap_sem);
975
	result = hugepage_vma_revalidate(mm, address, &vma);
976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
	if (result) {
		mem_cgroup_cancel_charge(new_page, memcg, true);
		up_read(&mm->mmap_sem);
		goto out_nolock;
	}

	pmd = mm_find_pmd(mm, address);
	if (!pmd) {
		result = SCAN_PMD_NULL;
		mem_cgroup_cancel_charge(new_page, memcg, true);
		up_read(&mm->mmap_sem);
		goto out_nolock;
	}

	/*
	 * __collapse_huge_page_swapin always returns with mmap_sem locked.
992
	 * If it fails, we release mmap_sem and jump out_nolock.
993 994
	 * Continuing to collapse causes inconsistency.
	 */
995
	if (!__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) {
996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007
		mem_cgroup_cancel_charge(new_page, memcg, true);
		up_read(&mm->mmap_sem);
		goto out_nolock;
	}

	up_read(&mm->mmap_sem);
	/*
	 * Prevent all access to pagetables with the exception of
	 * gup_fast later handled by the ptep_clear_flush and the VM
	 * handled by the anon_vma lock + PG_lock.
	 */
	down_write(&mm->mmap_sem);
1008
	result = hugepage_vma_revalidate(mm, address, &vma);
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
	if (result)
		goto out;
	/* check if the pmd is still valid */
	if (mm_find_pmd(mm, address) != pmd)
		goto out;

	anon_vma_lock_write(vma->anon_vma);

	pte = pte_offset_map(pmd, address);
	pte_ptl = pte_lockptr(mm, pmd);

	mmun_start = address;
	mmun_end   = address + HPAGE_PMD_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
	/*
	 * After this gup_fast can't run anymore. This also removes
	 * any huge TLB entry from the CPU so we won't allow
	 * huge and small TLB entries for the same virtual address
	 * to avoid the risk of CPU bugs in that area.
	 */
	_pmd = pmdp_collapse_flush(vma, address, pmd);
	spin_unlock(pmd_ptl);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

	spin_lock(pte_ptl);
	isolated = __collapse_huge_page_isolate(vma, address, pte);
	spin_unlock(pte_ptl);

	if (unlikely(!isolated)) {
		pte_unmap(pte);
		spin_lock(pmd_ptl);
		BUG_ON(!pmd_none(*pmd));
		/*
		 * We can only use set_pmd_at when establishing
		 * hugepmds and never for establishing regular pmds that
		 * points to regular pagetables. Use pmd_populate for that
		 */
		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
		spin_unlock(pmd_ptl);
		anon_vma_unlock_write(vma->anon_vma);
		result = SCAN_FAIL;
		goto out;
	}

	/*
	 * All pages are isolated and locked so anon_vma rmap
	 * can't run anymore.
	 */
	anon_vma_unlock_write(vma->anon_vma);

	__collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl);
	pte_unmap(pte);
	__SetPageUptodate(new_page);
	pgtable = pmd_pgtable(_pmd);

	_pmd = mk_huge_pmd(new_page, vma->vm_page_prot);
1066
	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
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

	/*
	 * spin_lock() below is not the equivalent of smp_wmb(), so
	 * this is needed to avoid the copy_huge_page writes to become
	 * visible after the set_pmd_at() write.
	 */
	smp_wmb();

	spin_lock(pmd_ptl);
	BUG_ON(!pmd_none(*pmd));
	page_add_new_anon_rmap(new_page, vma, address, true);
	mem_cgroup_commit_charge(new_page, memcg, false, true);
	lru_cache_add_active_or_unevictable(new_page, vma);
	pgtable_trans_huge_deposit(mm, pmd, pgtable);
	set_pmd_at(mm, address, pmd, _pmd);
	update_mmu_cache_pmd(vma, address, pmd);
	spin_unlock(pmd_ptl);

	*hpage = NULL;

	khugepaged_pages_collapsed++;
	result = SCAN_SUCCEED;
out_up_write:
	up_write(&mm->mmap_sem);
out_nolock:
	trace_mm_collapse_huge_page(mm, isolated, result);
	return;
out:
	mem_cgroup_cancel_charge(new_page, memcg, true);
	goto out_up_write;
}

static int khugepaged_scan_pmd(struct mm_struct *mm,
			       struct vm_area_struct *vma,
			       unsigned long address,
			       struct page **hpage)
{
	pmd_t *pmd;
	pte_t *pte, *_pte;
1106
	int ret = 0, none_or_zero = 0, result = 0, referenced = 0;
1107 1108 1109 1110
	struct page *page = NULL;
	unsigned long _address;
	spinlock_t *ptl;
	int node = NUMA_NO_NODE, unmapped = 0;
1111
	bool writable = false;
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 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);

	pmd = mm_find_pmd(mm, address);
	if (!pmd) {
		result = SCAN_PMD_NULL;
		goto out;
	}

	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
	     _pte++, _address += PAGE_SIZE) {
		pte_t pteval = *_pte;
		if (is_swap_pte(pteval)) {
			if (++unmapped <= khugepaged_max_ptes_swap) {
				continue;
			} else {
				result = SCAN_EXCEED_SWAP_PTE;
				goto out_unmap;
			}
		}
		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
			if (!userfaultfd_armed(vma) &&
			    ++none_or_zero <= khugepaged_max_ptes_none) {
				continue;
			} else {
				result = SCAN_EXCEED_NONE_PTE;
				goto out_unmap;
			}
		}
		if (!pte_present(pteval)) {
			result = SCAN_PTE_NON_PRESENT;
			goto out_unmap;
		}
		if (pte_write(pteval))
			writable = true;

		page = vm_normal_page(vma, _address, pteval);
		if (unlikely(!page)) {
			result = SCAN_PAGE_NULL;
			goto out_unmap;
		}

		/* TODO: teach khugepaged to collapse THP mapped with pte */
		if (PageCompound(page)) {
			result = SCAN_PAGE_COMPOUND;
			goto out_unmap;
		}

		/*
		 * Record which node the original page is from and save this
		 * information to khugepaged_node_load[].
		 * Khupaged will allocate hugepage from the node has the max
		 * hit record.
		 */
		node = page_to_nid(page);
		if (khugepaged_scan_abort(node)) {
			result = SCAN_SCAN_ABORT;
			goto out_unmap;
		}
		khugepaged_node_load[node]++;
		if (!PageLRU(page)) {
			result = SCAN_PAGE_LRU;
			goto out_unmap;
		}
		if (PageLocked(page)) {
			result = SCAN_PAGE_LOCK;
			goto out_unmap;
		}
		if (!PageAnon(page)) {
			result = SCAN_PAGE_ANON;
			goto out_unmap;
		}

		/*
		 * cannot use mapcount: can't collapse if there's a gup pin.
		 * The page must only be referenced by the scanned process
		 * and page swap cache.
		 */
1192
		if (page_count(page) != 1 + PageSwapCache(page)) {
1193 1194 1195 1196 1197 1198
			result = SCAN_PAGE_COUNT;
			goto out_unmap;
		}
		if (pte_young(pteval) ||
		    page_is_young(page) || PageReferenced(page) ||
		    mmu_notifier_test_young(vma->vm_mm, address))
1199
			referenced++;
1200 1201 1202 1203 1204 1205
	}
	if (writable) {
		if (referenced) {
			result = SCAN_SUCCEED;
			ret = 1;
		} else {
1206
			result = SCAN_LACK_REFERENCED_PAGE;
1207 1208 1209 1210 1211 1212 1213 1214 1215
		}
	} else {
		result = SCAN_PAGE_RO;
	}
out_unmap:
	pte_unmap_unlock(pte, ptl);
	if (ret) {
		node = khugepaged_find_target_node();
		/* collapse_huge_page will return with the mmap_sem released */
1216
		collapse_huge_page(mm, address, hpage, node, referenced);
1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246
	}
out:
	trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
				     none_or_zero, result, unmapped);
	return ret;
}

static void collect_mm_slot(struct mm_slot *mm_slot)
{
	struct mm_struct *mm = mm_slot->mm;

	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));

	if (khugepaged_test_exit(mm)) {
		/* free mm_slot */
		hash_del(&mm_slot->hash);
		list_del(&mm_slot->mm_node);

		/*
		 * Not strictly needed because the mm exited already.
		 *
		 * clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
		 */

		/* khugepaged_mm_lock actually not necessary for the below */
		free_mm_slot(mm_slot);
		mmdrop(mm);
	}
}

1247
#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)
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
static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
{
	struct vm_area_struct *vma;
	unsigned long addr;
	pmd_t *pmd, _pmd;

	i_mmap_lock_write(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
		/* probably overkill */
		if (vma->anon_vma)
			continue;
		addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
		if (addr & ~HPAGE_PMD_MASK)
			continue;
		if (vma->vm_end < addr + HPAGE_PMD_SIZE)
			continue;
		pmd = mm_find_pmd(vma->vm_mm, addr);
		if (!pmd)
			continue;
		/*
		 * We need exclusive mmap_sem to retract page table.
		 * If trylock fails we would end up with pte-mapped THP after
		 * re-fault. Not ideal, but it's more important to not disturb
		 * the system too much.
		 */
		if (down_write_trylock(&vma->vm_mm->mmap_sem)) {
			spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
			/* assume page table is clear */
			_pmd = pmdp_collapse_flush(vma, addr, pmd);
			spin_unlock(ptl);
			up_write(&vma->vm_mm->mmap_sem);
1279
			mm_dec_nr_ptes(vma->vm_mm);
1280
			pte_free(vma->vm_mm, pmd_pgtable(_pmd));
1281 1282 1283 1284 1285 1286 1287 1288 1289 1290
		}
	}
	i_mmap_unlock_write(mapping);
}

/**
 * collapse_shmem - collapse small tmpfs/shmem pages into huge one.
 *
 * Basic scheme is simple, details are more complex:
 *  - allocate and freeze a new huge page;
1291
 *  - scan page cache replacing old pages with the new one
1292 1293
 *    + swap in pages if necessary;
 *    + fill in gaps;
1294 1295
 *    + keep old pages around in case rollback is required;
 *  - if replacing succeeds:
1296 1297 1298 1299 1300
 *    + copy data over;
 *    + free old pages;
 *    + unfreeze huge page;
 *  - if replacing failed;
 *    + put all pages back and unfreeze them;
1301
 *    + restore gaps in the page cache;
1302 1303 1304 1305 1306 1307 1308
 *    + free huge page;
 */
static void collapse_shmem(struct mm_struct *mm,
		struct address_space *mapping, pgoff_t start,
		struct page **hpage, int node)
{
	gfp_t gfp;
1309
	struct page *new_page;
1310 1311 1312
	struct mem_cgroup *memcg;
	pgoff_t index, end = start + HPAGE_PMD_NR;
	LIST_HEAD(pagelist);
1313
	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
1314 1315 1316 1317 1318
	int nr_none = 0, result = SCAN_SUCCEED;

	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));

	/* Only allocate from the target node */
M
Michal Hocko 已提交
1319
	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
1320 1321 1322 1323 1324 1325 1326

	new_page = khugepaged_alloc_page(hpage, gfp, node);
	if (!new_page) {
		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
		goto out;
	}

1327
	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
		result = SCAN_CGROUP_CHARGE_FAIL;
		goto out;
	}

	new_page->index = start;
	new_page->mapping = mapping;
	__SetPageSwapBacked(new_page);
	__SetPageLocked(new_page);
	BUG_ON(!page_ref_freeze(new_page, 1));

	/*
1339 1340 1341 1342
	 * At this point the new_page is 'frozen' (page_count() is zero),
	 * locked and not up-to-date. It's safe to insert it into the page
	 * cache, because nobody would be able to map it or use it in other
	 * way until we unfreeze it.
1343 1344
	 */

1345 1346 1347 1348 1349
	/* This will be less messy when we use multi-index entries */
	do {
		xas_lock_irq(&xas);
		xas_create_range(&xas);
		if (!xas_error(&xas))
1350
			break;
1351 1352 1353 1354
		xas_unlock_irq(&xas);
		if (!xas_nomem(&xas, GFP_KERNEL))
			goto out;
	} while (1);
1355

1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
	xas_set(&xas, start);
	for (index = start; index < end; index++) {
		struct page *page = xas_next(&xas);

		VM_BUG_ON(index != xas.xa_index);
		if (!page) {
			if (!shmem_charge(mapping->host, 1)) {
				result = SCAN_FAIL;
				break;
			}
			xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
			nr_none++;
			continue;
		}
1370

1371
		if (xa_is_value(page) || !PageUptodate(page)) {
1372
			xas_unlock_irq(&xas);
1373 1374 1375 1376
			/* swap in or instantiate fallocated page */
			if (shmem_getpage(mapping->host, index, &page,
						SGP_NOHUGE)) {
				result = SCAN_FAIL;
1377
				goto xa_unlocked;
1378
			}
1379 1380
			xas_lock_irq(&xas);
			xas_set(&xas, index);
1381 1382 1383 1384 1385 1386 1387 1388
		} else if (trylock_page(page)) {
			get_page(page);
		} else {
			result = SCAN_PAGE_LOCK;
			break;
		}

		/*
M
Matthew Wilcox 已提交
1389
		 * The page must be locked, so we can drop the i_pages lock
1390 1391 1392 1393 1394 1395 1396 1397 1398 1399
		 * without racing with truncate.
		 */
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		VM_BUG_ON_PAGE(!PageUptodate(page), page);
		VM_BUG_ON_PAGE(PageTransCompound(page), page);

		if (page_mapping(page) != mapping) {
			result = SCAN_TRUNCATED;
			goto out_unlock;
		}
1400
		xas_unlock_irq(&xas);
1401 1402 1403 1404 1405 1406 1407

		if (isolate_lru_page(page)) {
			result = SCAN_DEL_PAGE_LRU;
			goto out_isolate_failed;
		}

		if (page_mapped(page))
M
Matthew Wilcox 已提交
1408
			unmap_mapping_pages(mapping, index, 1, false);
1409

1410 1411
		xas_lock_irq(&xas);
		xas_set(&xas, index);
1412

1413
		VM_BUG_ON_PAGE(page != xas_load(&xas), page);
1414 1415 1416 1417 1418
		VM_BUG_ON_PAGE(page_mapped(page), page);

		/*
		 * The page is expected to have page_count() == 3:
		 *  - we hold a pin on it;
1419
		 *  - one reference from page cache;
1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433
		 *  - one from isolate_lru_page;
		 */
		if (!page_ref_freeze(page, 3)) {
			result = SCAN_PAGE_COUNT;
			goto out_lru;
		}

		/*
		 * Add the page to the list to be able to undo the collapse if
		 * something go wrong.
		 */
		list_add_tail(&page->lru, &pagelist);

		/* Finally, replace with the new page. */
1434
		xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
1435 1436
		continue;
out_lru:
1437
		xas_unlock_irq(&xas);
1438 1439 1440 1441
		putback_lru_page(page);
out_isolate_failed:
		unlock_page(page);
		put_page(page);
1442
		goto xa_unlocked;
1443 1444 1445 1446 1447
out_unlock:
		unlock_page(page);
		put_page(page);
		break;
	}
1448
	xas_unlock_irq(&xas);
1449

1450
xa_unlocked:
1451
	if (result == SCAN_SUCCEED) {
1452
		struct page *page, *tmp;
1453 1454 1455
		struct zone *zone = page_zone(new_page);

		/*
1456 1457
		 * Replacing old pages with new one has succeeded, now we
		 * need to copy the content and free the old pages.
1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470
		 */
		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
					page);
			list_del(&page->lru);
			unlock_page(page);
			page_ref_unfreeze(page, 1);
			page->mapping = NULL;
			ClearPageActive(page);
			ClearPageUnevictable(page);
			put_page(page);
		}

1471
		local_irq_disable();
1472
		__inc_node_page_state(new_page, NR_SHMEM_THPS);
1473
		if (nr_none) {
1474 1475
			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
1476
		}
1477
		local_irq_enable();
1478 1479

		/*
1480
		 * Remove pte page tables, so we can re-fault
1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493
		 * the page as huge.
		 */
		retract_page_tables(mapping, start);

		/* Everything is ready, let's unfreeze the new_page */
		set_page_dirty(new_page);
		SetPageUptodate(new_page);
		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
		mem_cgroup_commit_charge(new_page, memcg, false, true);
		lru_cache_add_anon(new_page);
		unlock_page(new_page);

		*hpage = NULL;
1494 1495

		khugepaged_pages_collapsed++;
1496
	} else {
1497 1498
		struct page *page;
		/* Something went wrong: roll back page cache changes */
1499
		shmem_uncharge(mapping->host, nr_none);
1500 1501 1502
		xas_lock_irq(&xas);
		xas_set(&xas, start);
		xas_for_each(&xas, page, end - 1) {
1503 1504
			page = list_first_entry_or_null(&pagelist,
					struct page, lru);
1505
			if (!page || xas.xa_index < page->index) {
1506 1507 1508
				if (!nr_none)
					break;
				nr_none--;
1509
				/* Put holes back where they were */
1510
				xas_store(&xas, NULL);
1511 1512 1513
				continue;
			}

1514
			VM_BUG_ON_PAGE(page->index != xas.xa_index, page);
1515 1516 1517 1518

			/* Unfreeze the page. */
			list_del(&page->lru);
			page_ref_unfreeze(page, 2);
1519 1520 1521
			xas_store(&xas, page);
			xas_pause(&xas);
			xas_unlock_irq(&xas);
1522 1523
			putback_lru_page(page);
			unlock_page(page);
1524
			xas_lock_irq(&xas);
1525 1526
		}
		VM_BUG_ON(nr_none);
1527
		xas_unlock_irq(&xas);
1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544

		/* Unfreeze new_page, caller would take care about freeing it */
		page_ref_unfreeze(new_page, 1);
		mem_cgroup_cancel_charge(new_page, memcg, true);
		unlock_page(new_page);
		new_page->mapping = NULL;
	}
out:
	VM_BUG_ON(!list_empty(&pagelist));
	/* TODO: tracepoints */
}

static void khugepaged_scan_shmem(struct mm_struct *mm,
		struct address_space *mapping,
		pgoff_t start, struct page **hpage)
{
	struct page *page = NULL;
1545
	XA_STATE(xas, &mapping->i_pages, start);
1546 1547 1548 1549 1550 1551 1552 1553
	int present, swap;
	int node = NUMA_NO_NODE;
	int result = SCAN_SUCCEED;

	present = 0;
	swap = 0;
	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
	rcu_read_lock();
1554 1555
	xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) {
		if (xas_retry(&xas, page))
1556 1557
			continue;

1558
		if (xa_is_value(page)) {
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
			if (++swap > khugepaged_max_ptes_swap) {
				result = SCAN_EXCEED_SWAP_PTE;
				break;
			}
			continue;
		}

		if (PageTransCompound(page)) {
			result = SCAN_PAGE_COMPOUND;
			break;
		}

		node = page_to_nid(page);
		if (khugepaged_scan_abort(node)) {
			result = SCAN_SCAN_ABORT;
			break;
		}
		khugepaged_node_load[node]++;

		if (!PageLRU(page)) {
			result = SCAN_PAGE_LRU;
			break;
		}

		if (page_count(page) != 1 + page_mapcount(page)) {
			result = SCAN_PAGE_COUNT;
			break;
		}

		/*
		 * We probably should check if the page is referenced here, but
		 * nobody would transfer pte_young() to PageReferenced() for us.
		 * And rmap walk here is just too costly...
		 */

		present++;

		if (need_resched()) {
1597
			xas_pause(&xas);
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
			cond_resched_rcu();
		}
	}
	rcu_read_unlock();

	if (result == SCAN_SUCCEED) {
		if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {
			result = SCAN_EXCEED_NONE_PTE;
		} else {
			node = khugepaged_find_target_node();
			collapse_shmem(mm, mapping, start, hpage, node);
		}
	}

	/* TODO: tracepoints */
}
#else
static void khugepaged_scan_shmem(struct mm_struct *mm,
		struct address_space *mapping,
		pgoff_t start, struct page **hpage)
{
	BUILD_BUG();
}
#endif

1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646
static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
					    struct page **hpage)
	__releases(&khugepaged_mm_lock)
	__acquires(&khugepaged_mm_lock)
{
	struct mm_slot *mm_slot;
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	int progress = 0;

	VM_BUG_ON(!pages);
	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));

	if (khugepaged_scan.mm_slot)
		mm_slot = khugepaged_scan.mm_slot;
	else {
		mm_slot = list_entry(khugepaged_scan.mm_head.next,
				     struct mm_slot, mm_node);
		khugepaged_scan.address = 0;
		khugepaged_scan.mm_slot = mm_slot;
	}
	spin_unlock(&khugepaged_mm_lock);

	mm = mm_slot->mm;
1647 1648 1649 1650 1651 1652 1653 1654
	/*
	 * Don't wait for semaphore (to avoid long wait times).  Just move to
	 * the next mm on the list.
	 */
	vma = NULL;
	if (unlikely(!down_read_trylock(&mm->mmap_sem)))
		goto breakouterloop_mmap_sem;
	if (likely(!khugepaged_test_exit(mm)))
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665
		vma = find_vma(mm, khugepaged_scan.address);

	progress++;
	for (; vma; vma = vma->vm_next) {
		unsigned long hstart, hend;

		cond_resched();
		if (unlikely(khugepaged_test_exit(mm))) {
			progress++;
			break;
		}
1666
		if (!hugepage_vma_check(vma, vma->vm_flags)) {
1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689
skip:
			progress++;
			continue;
		}
		hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
		hend = vma->vm_end & HPAGE_PMD_MASK;
		if (hstart >= hend)
			goto skip;
		if (khugepaged_scan.address > hend)
			goto skip;
		if (khugepaged_scan.address < hstart)
			khugepaged_scan.address = hstart;
		VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);

		while (khugepaged_scan.address < hend) {
			int ret;
			cond_resched();
			if (unlikely(khugepaged_test_exit(mm)))
				goto breakouterloop;

			VM_BUG_ON(khugepaged_scan.address < hstart ||
				  khugepaged_scan.address + HPAGE_PMD_SIZE >
				  hend);
1690
			if (shmem_file(vma->vm_file)) {
1691
				struct file *file;
1692 1693
				pgoff_t pgoff = linear_page_index(vma,
						khugepaged_scan.address);
1694 1695 1696
				if (!shmem_huge_enabled(vma))
					goto skip;
				file = get_file(vma->vm_file);
1697 1698 1699 1700 1701 1702 1703 1704 1705 1706
				up_read(&mm->mmap_sem);
				ret = 1;
				khugepaged_scan_shmem(mm, file->f_mapping,
						pgoff, hpage);
				fput(file);
			} else {
				ret = khugepaged_scan_pmd(mm, vma,
						khugepaged_scan.address,
						hpage);
			}
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 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 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 1839 1840 1841 1842 1843 1844 1845 1846 1847
			/* move to next address */
			khugepaged_scan.address += HPAGE_PMD_SIZE;
			progress += HPAGE_PMD_NR;
			if (ret)
				/* we released mmap_sem so break loop */
				goto breakouterloop_mmap_sem;
			if (progress >= pages)
				goto breakouterloop;
		}
	}
breakouterloop:
	up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */
breakouterloop_mmap_sem:

	spin_lock(&khugepaged_mm_lock);
	VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
	/*
	 * Release the current mm_slot if this mm is about to die, or
	 * if we scanned all vmas of this mm.
	 */
	if (khugepaged_test_exit(mm) || !vma) {
		/*
		 * Make sure that if mm_users is reaching zero while
		 * khugepaged runs here, khugepaged_exit will find
		 * mm_slot not pointing to the exiting mm.
		 */
		if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) {
			khugepaged_scan.mm_slot = list_entry(
				mm_slot->mm_node.next,
				struct mm_slot, mm_node);
			khugepaged_scan.address = 0;
		} else {
			khugepaged_scan.mm_slot = NULL;
			khugepaged_full_scans++;
		}

		collect_mm_slot(mm_slot);
	}

	return progress;
}

static int khugepaged_has_work(void)
{
	return !list_empty(&khugepaged_scan.mm_head) &&
		khugepaged_enabled();
}

static int khugepaged_wait_event(void)
{
	return !list_empty(&khugepaged_scan.mm_head) ||
		kthread_should_stop();
}

static void khugepaged_do_scan(void)
{
	struct page *hpage = NULL;
	unsigned int progress = 0, pass_through_head = 0;
	unsigned int pages = khugepaged_pages_to_scan;
	bool wait = true;

	barrier(); /* write khugepaged_pages_to_scan to local stack */

	while (progress < pages) {
		if (!khugepaged_prealloc_page(&hpage, &wait))
			break;

		cond_resched();

		if (unlikely(kthread_should_stop() || try_to_freeze()))
			break;

		spin_lock(&khugepaged_mm_lock);
		if (!khugepaged_scan.mm_slot)
			pass_through_head++;
		if (khugepaged_has_work() &&
		    pass_through_head < 2)
			progress += khugepaged_scan_mm_slot(pages - progress,
							    &hpage);
		else
			progress = pages;
		spin_unlock(&khugepaged_mm_lock);
	}

	if (!IS_ERR_OR_NULL(hpage))
		put_page(hpage);
}

static bool khugepaged_should_wakeup(void)
{
	return kthread_should_stop() ||
	       time_after_eq(jiffies, khugepaged_sleep_expire);
}

static void khugepaged_wait_work(void)
{
	if (khugepaged_has_work()) {
		const unsigned long scan_sleep_jiffies =
			msecs_to_jiffies(khugepaged_scan_sleep_millisecs);

		if (!scan_sleep_jiffies)
			return;

		khugepaged_sleep_expire = jiffies + scan_sleep_jiffies;
		wait_event_freezable_timeout(khugepaged_wait,
					     khugepaged_should_wakeup(),
					     scan_sleep_jiffies);
		return;
	}

	if (khugepaged_enabled())
		wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
}

static int khugepaged(void *none)
{
	struct mm_slot *mm_slot;

	set_freezable();
	set_user_nice(current, MAX_NICE);

	while (!kthread_should_stop()) {
		khugepaged_do_scan();
		khugepaged_wait_work();
	}

	spin_lock(&khugepaged_mm_lock);
	mm_slot = khugepaged_scan.mm_slot;
	khugepaged_scan.mm_slot = NULL;
	if (mm_slot)
		collect_mm_slot(mm_slot);
	spin_unlock(&khugepaged_mm_lock);
	return 0;
}

static void set_recommended_min_free_kbytes(void)
{
	struct zone *zone;
	int nr_zones = 0;
	unsigned long recommended_min;

1848 1849 1850 1851 1852 1853 1854 1855
	for_each_populated_zone(zone) {
		/*
		 * We don't need to worry about fragmentation of
		 * ZONE_MOVABLE since it only has movable pages.
		 */
		if (zone_idx(zone) > gfp_zone(GFP_USER))
			continue;

1856
		nr_zones++;
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

	/* Ensure 2 pageblocks are free to assist fragmentation avoidance */
	recommended_min = pageblock_nr_pages * nr_zones * 2;

	/*
	 * Make sure that on average at least two pageblocks are almost free
	 * of another type, one for a migratetype to fall back to and a
	 * second to avoid subsequent fallbacks of other types There are 3
	 * MIGRATE_TYPES we care about.
	 */
	recommended_min += pageblock_nr_pages * nr_zones *
			   MIGRATE_PCPTYPES * MIGRATE_PCPTYPES;

	/* don't ever allow to reserve more than 5% of the lowmem */
	recommended_min = min(recommended_min,
			      (unsigned long) nr_free_buffer_pages() / 20);
	recommended_min <<= (PAGE_SHIFT-10);

	if (recommended_min > min_free_kbytes) {
		if (user_min_free_kbytes >= 0)
			pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n",
				min_free_kbytes, recommended_min);

		min_free_kbytes = recommended_min;
	}
	setup_per_zone_wmarks();
}

int start_stop_khugepaged(void)
{
	static struct task_struct *khugepaged_thread __read_mostly;
	static DEFINE_MUTEX(khugepaged_mutex);
	int err = 0;

	mutex_lock(&khugepaged_mutex);
	if (khugepaged_enabled()) {
		if (!khugepaged_thread)
			khugepaged_thread = kthread_run(khugepaged, NULL,
							"khugepaged");
		if (IS_ERR(khugepaged_thread)) {
			pr_err("khugepaged: kthread_run(khugepaged) failed\n");
			err = PTR_ERR(khugepaged_thread);
			khugepaged_thread = NULL;
			goto fail;
		}

		if (!list_empty(&khugepaged_scan.mm_head))
			wake_up_interruptible(&khugepaged_wait);

		set_recommended_min_free_kbytes();
	} else if (khugepaged_thread) {
		kthread_stop(khugepaged_thread);
		khugepaged_thread = NULL;
	}
fail:
	mutex_unlock(&khugepaged_mutex);
	return err;
}