huge_memory.c 61.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 *  Copyright (C) 2009  Red Hat, Inc.
 *
 *  This work is licensed under the terms of the GNU GPL, version 2. See
 *  the COPYING file in the top-level directory.
 */

#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
A
Andrea Arcangeli 已提交
15 16 17
#include <linux/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
18
#include <linux/freezer.h>
A
Andrea Arcangeli 已提交
19
#include <linux/mman.h>
20 21 22 23
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"

A
Andrea Arcangeli 已提交
24 25 26 27 28 29 30
/*
 * By default transparent hugepage support is enabled for all mappings
 * and khugepaged scans all mappings. Defrag is only invoked by
 * khugepaged hugepage allocations and by page faults inside
 * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived
 * allocations.
 */
31
unsigned long transparent_hugepage_flags __read_mostly =
32
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
A
Andrea Arcangeli 已提交
33
	(1<<TRANSPARENT_HUGEPAGE_FLAG)|
34 35 36 37
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
A
Andrea Arcangeli 已提交
38
	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)|
A
Andrea Arcangeli 已提交
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);

/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
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 struct task_struct *khugepaged_thread __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
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 = HPAGE_PMD_NR-1;

static int khugepaged(void *none);
static int mm_slots_hash_init(void);
static int khugepaged_slab_init(void);
static void khugepaged_slab_free(void);

#define MM_SLOTS_HASH_HEADS 1024
static struct hlist_head *mm_slots_hash __read_mostly;
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;
} khugepaged_scan = {
	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
};

96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136

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

	if (!test_bit(TRANSPARENT_HUGEPAGE_FLAG,
		      &transparent_hugepage_flags) &&
	    !test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
		      &transparent_hugepage_flags))
		return 0;

	for_each_populated_zone(zone)
		nr_zones++;

	/* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */
	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)
		min_free_kbytes = recommended_min;
	setup_per_zone_wmarks();
	return 0;
}
late_initcall(set_recommended_min_free_kbytes);

A
Andrea Arcangeli 已提交
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
static int start_khugepaged(void)
{
	int err = 0;
	if (khugepaged_enabled()) {
		int wakeup;
		if (unlikely(!mm_slot_cache || !mm_slots_hash)) {
			err = -ENOMEM;
			goto out;
		}
		mutex_lock(&khugepaged_mutex);
		if (!khugepaged_thread)
			khugepaged_thread = kthread_run(khugepaged, NULL,
							"khugepaged");
		if (unlikely(IS_ERR(khugepaged_thread))) {
			printk(KERN_ERR
			       "khugepaged: kthread_run(khugepaged) failed\n");
			err = PTR_ERR(khugepaged_thread);
			khugepaged_thread = NULL;
		}
		wakeup = !list_empty(&khugepaged_scan.mm_head);
		mutex_unlock(&khugepaged_mutex);
		if (wakeup)
			wake_up_interruptible(&khugepaged_wait);
160 161

		set_recommended_min_free_kbytes();
A
Andrea Arcangeli 已提交
162 163 164 165 166 167
	} else
		/* wakeup to exit */
		wake_up_interruptible(&khugepaged_wait);
out:
	return err;
}
168 169

#ifdef CONFIG_SYSFS
A
Andrea Arcangeli 已提交
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
static ssize_t double_flag_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf,
				enum transparent_hugepage_flag enabled,
				enum transparent_hugepage_flag req_madv)
{
	if (test_bit(enabled, &transparent_hugepage_flags)) {
		VM_BUG_ON(test_bit(req_madv, &transparent_hugepage_flags));
		return sprintf(buf, "[always] madvise never\n");
	} else if (test_bit(req_madv, &transparent_hugepage_flags))
		return sprintf(buf, "always [madvise] never\n");
	else
		return sprintf(buf, "always madvise [never]\n");
}
static ssize_t double_flag_store(struct kobject *kobj,
				 struct kobj_attribute *attr,
				 const char *buf, size_t count,
				 enum transparent_hugepage_flag enabled,
				 enum transparent_hugepage_flag req_madv)
{
	if (!memcmp("always", buf,
		    min(sizeof("always")-1, count))) {
		set_bit(enabled, &transparent_hugepage_flags);
		clear_bit(req_madv, &transparent_hugepage_flags);
	} else if (!memcmp("madvise", buf,
			   min(sizeof("madvise")-1, count))) {
		clear_bit(enabled, &transparent_hugepage_flags);
		set_bit(req_madv, &transparent_hugepage_flags);
	} else if (!memcmp("never", buf,
			   min(sizeof("never")-1, count))) {
		clear_bit(enabled, &transparent_hugepage_flags);
		clear_bit(req_madv, &transparent_hugepage_flags);
	} else
		return -EINVAL;

	return count;
}

static ssize_t enabled_show(struct kobject *kobj,
			    struct kobj_attribute *attr, char *buf)
{
	return double_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_FLAG,
				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
}
static ssize_t enabled_store(struct kobject *kobj,
			     struct kobj_attribute *attr,
			     const char *buf, size_t count)
{
A
Andrea Arcangeli 已提交
219 220 221 222 223 224 225 226 227 228 229 230
	ssize_t ret;

	ret = double_flag_store(kobj, attr, buf, count,
				TRANSPARENT_HUGEPAGE_FLAG,
				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);

	if (ret > 0) {
		int err = start_khugepaged();
		if (err)
			ret = err;
	}

231 232 233 234 235 236 237
	if (ret > 0 &&
	    (test_bit(TRANSPARENT_HUGEPAGE_FLAG,
		      &transparent_hugepage_flags) ||
	     test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
		      &transparent_hugepage_flags)))
		set_recommended_min_free_kbytes();

A
Andrea Arcangeli 已提交
238
	return ret;
239 240 241 242 243 244 245 246
}
static struct kobj_attribute enabled_attr =
	__ATTR(enabled, 0644, enabled_show, enabled_store);

static ssize_t single_flag_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf,
				enum transparent_hugepage_flag flag)
{
247 248
	return sprintf(buf, "%d\n",
		       !!test_bit(flag, &transparent_hugepage_flags));
249
}
250

251 252 253 254 255
static ssize_t single_flag_store(struct kobject *kobj,
				 struct kobj_attribute *attr,
				 const char *buf, size_t count,
				 enum transparent_hugepage_flag flag)
{
256 257 258 259 260 261 262 263 264 265
	unsigned long value;
	int ret;

	ret = kstrtoul(buf, 10, &value);
	if (ret < 0)
		return ret;
	if (value > 1)
		return -EINVAL;

	if (value)
266
		set_bit(flag, &transparent_hugepage_flags);
267
	else
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324
		clear_bit(flag, &transparent_hugepage_flags);

	return count;
}

/*
 * Currently defrag only disables __GFP_NOWAIT for allocation. A blind
 * __GFP_REPEAT is too aggressive, it's never worth swapping tons of
 * memory just to allocate one more hugepage.
 */
static ssize_t defrag_show(struct kobject *kobj,
			   struct kobj_attribute *attr, char *buf)
{
	return double_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
				TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
static ssize_t defrag_store(struct kobject *kobj,
			    struct kobj_attribute *attr,
			    const char *buf, size_t count)
{
	return double_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
				 TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
static struct kobj_attribute defrag_attr =
	__ATTR(defrag, 0644, defrag_show, defrag_store);

#ifdef CONFIG_DEBUG_VM
static ssize_t debug_cow_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf)
{
	return single_flag_show(kobj, attr, buf,
				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
}
static ssize_t debug_cow_store(struct kobject *kobj,
			       struct kobj_attribute *attr,
			       const char *buf, size_t count)
{
	return single_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
}
static struct kobj_attribute debug_cow_attr =
	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
#endif /* CONFIG_DEBUG_VM */

static struct attribute *hugepage_attr[] = {
	&enabled_attr.attr,
	&defrag_attr.attr,
#ifdef CONFIG_DEBUG_VM
	&debug_cow_attr.attr,
#endif
	NULL,
};

static struct attribute_group hugepage_attr_group = {
	.attrs = hugepage_attr,
A
Andrea Arcangeli 已提交
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487
};

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

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

	khugepaged_alloc_sleep_millisecs = msecs;
	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 = strict_strtoul(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_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_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 = strict_strtoul(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 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,
	NULL,
};

static struct attribute_group khugepaged_attr_group = {
	.attrs = khugepaged_attr,
	.name = "khugepaged",
488 489 490 491 492 493
};
#endif /* CONFIG_SYSFS */

static int __init hugepage_init(void)
{
	int err;
A
Andrea Arcangeli 已提交
494 495
#ifdef CONFIG_SYSFS
	static struct kobject *hugepage_kobj;
496
#endif
497

498 499 500 501 502 503 504
	err = -EINVAL;
	if (!has_transparent_hugepage()) {
		transparent_hugepage_flags = 0;
		goto out;
	}

#ifdef CONFIG_SYSFS
A
Andrea Arcangeli 已提交
505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
	err = -ENOMEM;
	hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
	if (unlikely(!hugepage_kobj)) {
		printk(KERN_ERR "hugepage: failed kobject create\n");
		goto out;
	}

	err = sysfs_create_group(hugepage_kobj, &hugepage_attr_group);
	if (err) {
		printk(KERN_ERR "hugepage: failed register hugeage group\n");
		goto out;
	}

	err = sysfs_create_group(hugepage_kobj, &khugepaged_attr_group);
	if (err) {
		printk(KERN_ERR "hugepage: failed register hugeage group\n");
		goto out;
	}
523
#endif
A
Andrea Arcangeli 已提交
524 525 526 527 528 529 530 531 532 533 534

	err = khugepaged_slab_init();
	if (err)
		goto out;

	err = mm_slots_hash_init();
	if (err) {
		khugepaged_slab_free();
		goto out;
	}

535 536 537 538 539 540 541 542
	/*
	 * By default disable transparent hugepages on smaller systems,
	 * where the extra memory used could hurt more than TLB overhead
	 * is likely to save.  The admin can still enable it through /sys.
	 */
	if (totalram_pages < (512 << (20 - PAGE_SHIFT)))
		transparent_hugepage_flags = 0;

A
Andrea Arcangeli 已提交
543 544
	start_khugepaged();

545 546
	set_recommended_min_free_kbytes();

A
Andrea Arcangeli 已提交
547 548
out:
	return err;
549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614
}
module_init(hugepage_init)

static int __init setup_transparent_hugepage(char *str)
{
	int ret = 0;
	if (!str)
		goto out;
	if (!strcmp(str, "always")) {
		set_bit(TRANSPARENT_HUGEPAGE_FLAG,
			&transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			  &transparent_hugepage_flags);
		ret = 1;
	} else if (!strcmp(str, "madvise")) {
		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
			  &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			&transparent_hugepage_flags);
		ret = 1;
	} else if (!strcmp(str, "never")) {
		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
			  &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			  &transparent_hugepage_flags);
		ret = 1;
	}
out:
	if (!ret)
		printk(KERN_WARNING
		       "transparent_hugepage= cannot parse, ignored\n");
	return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);

static void prepare_pmd_huge_pte(pgtable_t pgtable,
				 struct mm_struct *mm)
{
	assert_spin_locked(&mm->page_table_lock);

	/* FIFO */
	if (!mm->pmd_huge_pte)
		INIT_LIST_HEAD(&pgtable->lru);
	else
		list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
	mm->pmd_huge_pte = pgtable;
}

static inline pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pmd = pmd_mkwrite(pmd);
	return pmd;
}

static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long haddr, pmd_t *pmd,
					struct page *page)
{
	int ret = 0;
	pgtable_t pgtable;

	VM_BUG_ON(!PageCompound(page));
	pgtable = pte_alloc_one(mm, haddr);
	if (unlikely(!pgtable)) {
A
Andrea Arcangeli 已提交
615
		mem_cgroup_uncharge_page(page);
616 617 618 619 620 621 622 623 624 625
		put_page(page);
		return VM_FAULT_OOM;
	}

	clear_huge_page(page, haddr, HPAGE_PMD_NR);
	__SetPageUptodate(page);

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_none(*pmd))) {
		spin_unlock(&mm->page_table_lock);
A
Andrea Arcangeli 已提交
626
		mem_cgroup_uncharge_page(page);
627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649
		put_page(page);
		pte_free(mm, pgtable);
	} else {
		pmd_t entry;
		entry = mk_pmd(page, vma->vm_page_prot);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		entry = pmd_mkhuge(entry);
		/*
		 * The spinlocking to take the lru_lock inside
		 * page_add_new_anon_rmap() acts as a full memory
		 * barrier to be sure clear_huge_page writes become
		 * visible after the set_pmd_at() write.
		 */
		page_add_new_anon_rmap(page, vma, haddr);
		set_pmd_at(mm, haddr, pmd, entry);
		prepare_pmd_huge_pte(pgtable, mm);
		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
		spin_unlock(&mm->page_table_lock);
	}

	return ret;
}

650
static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
651
{
652
	return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp;
653 654 655 656
}

static inline struct page *alloc_hugepage_vma(int defrag,
					      struct vm_area_struct *vma,
657 658
					      unsigned long haddr, int nd,
					      gfp_t extra_gfp)
659
{
660
	return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp),
661
			       HPAGE_PMD_ORDER, vma, haddr, nd);
662 663 664
}

#ifndef CONFIG_NUMA
665 666
static inline struct page *alloc_hugepage(int defrag)
{
667
	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
668 669
			   HPAGE_PMD_ORDER);
}
670
#endif
671 672 673 674 675 676 677 678 679 680 681 682

int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
			       unsigned long address, pmd_t *pmd,
			       unsigned int flags)
{
	struct page *page;
	unsigned long haddr = address & HPAGE_PMD_MASK;
	pte_t *pte;

	if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
		if (unlikely(anon_vma_prepare(vma)))
			return VM_FAULT_OOM;
A
Andrea Arcangeli 已提交
683 684
		if (unlikely(khugepaged_enter(vma)))
			return VM_FAULT_OOM;
685
		page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
686
					  vma, haddr, numa_node_id(), 0);
687 688
		if (unlikely(!page)) {
			count_vm_event(THP_FAULT_FALLBACK);
689
			goto out;
690 691
		}
		count_vm_event(THP_FAULT_ALLOC);
A
Andrea Arcangeli 已提交
692 693 694 695
		if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
			put_page(page);
			goto out;
		}
696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809

		return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
	}
out:
	/*
	 * Use __pte_alloc instead of pte_alloc_map, because we can't
	 * run pte_offset_map on the pmd, if an huge pmd could
	 * materialize from under us from a different thread.
	 */
	if (unlikely(__pte_alloc(mm, vma, pmd, address)))
		return VM_FAULT_OOM;
	/* if an huge pmd materialized from under us just retry later */
	if (unlikely(pmd_trans_huge(*pmd)))
		return 0;
	/*
	 * A regular pmd is established and it can't morph into a huge pmd
	 * from under us anymore at this point because we hold the mmap_sem
	 * read mode and khugepaged takes it in write mode. So now it's
	 * safe to run pte_offset_map().
	 */
	pte = pte_offset_map(pmd, address);
	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}

int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
		  struct vm_area_struct *vma)
{
	struct page *src_page;
	pmd_t pmd;
	pgtable_t pgtable;
	int ret;

	ret = -ENOMEM;
	pgtable = pte_alloc_one(dst_mm, addr);
	if (unlikely(!pgtable))
		goto out;

	spin_lock(&dst_mm->page_table_lock);
	spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING);

	ret = -EAGAIN;
	pmd = *src_pmd;
	if (unlikely(!pmd_trans_huge(pmd))) {
		pte_free(dst_mm, pgtable);
		goto out_unlock;
	}
	if (unlikely(pmd_trans_splitting(pmd))) {
		/* split huge page running from under us */
		spin_unlock(&src_mm->page_table_lock);
		spin_unlock(&dst_mm->page_table_lock);
		pte_free(dst_mm, pgtable);

		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
		goto out;
	}
	src_page = pmd_page(pmd);
	VM_BUG_ON(!PageHead(src_page));
	get_page(src_page);
	page_dup_rmap(src_page);
	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);

	pmdp_set_wrprotect(src_mm, addr, src_pmd);
	pmd = pmd_mkold(pmd_wrprotect(pmd));
	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
	prepare_pmd_huge_pte(pgtable, dst_mm);

	ret = 0;
out_unlock:
	spin_unlock(&src_mm->page_table_lock);
	spin_unlock(&dst_mm->page_table_lock);
out:
	return ret;
}

/* no "address" argument so destroys page coloring of some arch */
pgtable_t get_pmd_huge_pte(struct mm_struct *mm)
{
	pgtable_t pgtable;

	assert_spin_locked(&mm->page_table_lock);

	/* FIFO */
	pgtable = mm->pmd_huge_pte;
	if (list_empty(&pgtable->lru))
		mm->pmd_huge_pte = NULL;
	else {
		mm->pmd_huge_pte = list_entry(pgtable->lru.next,
					      struct page, lru);
		list_del(&pgtable->lru);
	}
	return pgtable;
}

static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long address,
					pmd_t *pmd, pmd_t orig_pmd,
					struct page *page,
					unsigned long haddr)
{
	pgtable_t pgtable;
	pmd_t _pmd;
	int ret = 0, i;
	struct page **pages;

	pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR,
			GFP_KERNEL);
	if (unlikely(!pages)) {
		ret |= VM_FAULT_OOM;
		goto out;
	}

	for (i = 0; i < HPAGE_PMD_NR; i++) {
810 811
		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
					       __GFP_OTHER_NODE,
812
					       vma, address, page_to_nid(page));
A
Andrea Arcangeli 已提交
813 814 815 816
		if (unlikely(!pages[i] ||
			     mem_cgroup_newpage_charge(pages[i], mm,
						       GFP_KERNEL))) {
			if (pages[i])
817
				put_page(pages[i]);
A
Andrea Arcangeli 已提交
818 819 820 821 822 823
			mem_cgroup_uncharge_start();
			while (--i >= 0) {
				mem_cgroup_uncharge_page(pages[i]);
				put_page(pages[i]);
			}
			mem_cgroup_uncharge_end();
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
			kfree(pages);
			ret |= VM_FAULT_OOM;
			goto out;
		}
	}

	for (i = 0; i < HPAGE_PMD_NR; i++) {
		copy_user_highpage(pages[i], page + i,
				   haddr + PAGE_SHIFT*i, vma);
		__SetPageUptodate(pages[i]);
		cond_resched();
	}

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto out_free_pages;
	VM_BUG_ON(!PageHead(page));

	pmdp_clear_flush_notify(vma, haddr, pmd);
	/* leave pmd empty until pte is filled */

	pgtable = get_pmd_huge_pte(mm);
	pmd_populate(mm, &_pmd, pgtable);

	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
		pte_t *pte, entry;
		entry = mk_pte(pages[i], vma->vm_page_prot);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		page_add_new_anon_rmap(pages[i], vma, haddr);
		pte = pte_offset_map(&_pmd, haddr);
		VM_BUG_ON(!pte_none(*pte));
		set_pte_at(mm, haddr, pte, entry);
		pte_unmap(pte);
	}
	kfree(pages);

	mm->nr_ptes++;
	smp_wmb(); /* make pte visible before pmd */
	pmd_populate(mm, pmd, pgtable);
	page_remove_rmap(page);
	spin_unlock(&mm->page_table_lock);

	ret |= VM_FAULT_WRITE;
	put_page(page);

out:
	return ret;

out_free_pages:
	spin_unlock(&mm->page_table_lock);
A
Andrea Arcangeli 已提交
874 875 876
	mem_cgroup_uncharge_start();
	for (i = 0; i < HPAGE_PMD_NR; i++) {
		mem_cgroup_uncharge_page(pages[i]);
877
		put_page(pages[i]);
A
Andrea Arcangeli 已提交
878 879
	}
	mem_cgroup_uncharge_end();
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
	kfree(pages);
	goto out;
}

int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
{
	int ret = 0;
	struct page *page, *new_page;
	unsigned long haddr;

	VM_BUG_ON(!vma->anon_vma);
	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_same(*pmd, orig_pmd)))
		goto out_unlock;

	page = pmd_page(orig_pmd);
	VM_BUG_ON(!PageCompound(page) || !PageHead(page));
	haddr = address & HPAGE_PMD_MASK;
	if (page_mapcount(page) == 1) {
		pmd_t entry;
		entry = pmd_mkyoung(orig_pmd);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		if (pmdp_set_access_flags(vma, haddr, pmd, entry,  1))
			update_mmu_cache(vma, address, entry);
		ret |= VM_FAULT_WRITE;
		goto out_unlock;
	}
	get_page(page);
	spin_unlock(&mm->page_table_lock);

	if (transparent_hugepage_enabled(vma) &&
	    !transparent_hugepage_debug_cow())
913
		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
914
					      vma, haddr, numa_node_id(), 0);
915 916 917 918
	else
		new_page = NULL;

	if (unlikely(!new_page)) {
919
		count_vm_event(THP_FAULT_FALLBACK);
920 921 922 923 924
		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
						   pmd, orig_pmd, page, haddr);
		put_page(page);
		goto out;
	}
925
	count_vm_event(THP_FAULT_ALLOC);
926

A
Andrea Arcangeli 已提交
927 928 929 930 931 932 933
	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
		put_page(new_page);
		put_page(page);
		ret |= VM_FAULT_OOM;
		goto out;
	}

934 935 936 937 938
	copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
	__SetPageUptodate(new_page);

	spin_lock(&mm->page_table_lock);
	put_page(page);
A
Andrea Arcangeli 已提交
939 940
	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
		mem_cgroup_uncharge_page(new_page);
941
		put_page(new_page);
A
Andrea Arcangeli 已提交
942
	} else {
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
		pmd_t entry;
		VM_BUG_ON(!PageHead(page));
		entry = mk_pmd(new_page, vma->vm_page_prot);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		entry = pmd_mkhuge(entry);
		pmdp_clear_flush_notify(vma, haddr, pmd);
		page_add_new_anon_rmap(new_page, vma, haddr);
		set_pmd_at(mm, haddr, pmd, entry);
		update_mmu_cache(vma, address, entry);
		page_remove_rmap(page);
		put_page(page);
		ret |= VM_FAULT_WRITE;
	}
out_unlock:
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
}

struct page *follow_trans_huge_pmd(struct mm_struct *mm,
				   unsigned long addr,
				   pmd_t *pmd,
				   unsigned int flags)
{
	struct page *page = NULL;

	assert_spin_locked(&mm->page_table_lock);

	if (flags & FOLL_WRITE && !pmd_write(*pmd))
		goto out;

	page = pmd_page(*pmd);
	VM_BUG_ON(!PageHead(page));
	if (flags & FOLL_TOUCH) {
		pmd_t _pmd;
		/*
		 * We should set the dirty bit only for FOLL_WRITE but
		 * for now the dirty bit in the pmd is meaningless.
		 * And if the dirty bit will become meaningful and
		 * we'll only set it with FOLL_WRITE, an atomic
		 * set_bit will be required on the pmd to set the
		 * young bit, instead of the current set_pmd_at.
		 */
		_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
		set_pmd_at(mm, addr & HPAGE_PMD_MASK, pmd, _pmd);
	}
	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
	VM_BUG_ON(!PageCompound(page));
	if (flags & FOLL_GET)
		get_page(page);

out:
	return page;
}

int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
		 pmd_t *pmd)
{
	int ret = 0;

	spin_lock(&tlb->mm->page_table_lock);
	if (likely(pmd_trans_huge(*pmd))) {
		if (unlikely(pmd_trans_splitting(*pmd))) {
			spin_unlock(&tlb->mm->page_table_lock);
			wait_split_huge_page(vma->anon_vma,
					     pmd);
		} else {
			struct page *page;
			pgtable_t pgtable;
			pgtable = get_pmd_huge_pte(tlb->mm);
			page = pmd_page(*pmd);
			pmd_clear(pmd);
			page_remove_rmap(page);
			VM_BUG_ON(page_mapcount(page) < 0);
			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
			VM_BUG_ON(!PageHead(page));
			spin_unlock(&tlb->mm->page_table_lock);
			tlb_remove_page(tlb, page);
			pte_free(tlb->mm, pgtable);
			ret = 1;
		}
	} else
		spin_unlock(&tlb->mm->page_table_lock);

	return ret;
}

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
int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, unsigned long end,
		unsigned char *vec)
{
	int ret = 0;

	spin_lock(&vma->vm_mm->page_table_lock);
	if (likely(pmd_trans_huge(*pmd))) {
		ret = !pmd_trans_splitting(*pmd);
		spin_unlock(&vma->vm_mm->page_table_lock);
		if (unlikely(!ret))
			wait_split_huge_page(vma->anon_vma, pmd);
		else {
			/*
			 * All logical pages in the range are present
			 * if backed by a huge page.
			 */
			memset(vec, 1, (end - addr) >> PAGE_SHIFT);
		}
	} else
		spin_unlock(&vma->vm_mm->page_table_lock);

	return ret;
}

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
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, pgprot_t newprot)
{
	struct mm_struct *mm = vma->vm_mm;
	int ret = 0;

	spin_lock(&mm->page_table_lock);
	if (likely(pmd_trans_huge(*pmd))) {
		if (unlikely(pmd_trans_splitting(*pmd))) {
			spin_unlock(&mm->page_table_lock);
			wait_split_huge_page(vma->anon_vma, pmd);
		} else {
			pmd_t entry;

			entry = pmdp_get_and_clear(mm, addr, pmd);
			entry = pmd_modify(entry, newprot);
			set_pmd_at(mm, addr, pmd, entry);
			spin_unlock(&vma->vm_mm->page_table_lock);
			flush_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE);
			ret = 1;
		}
	} else
		spin_unlock(&vma->vm_mm->page_table_lock);

	return ret;
}

1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106
pmd_t *page_check_address_pmd(struct page *page,
			      struct mm_struct *mm,
			      unsigned long address,
			      enum page_check_address_pmd_flag flag)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd, *ret = NULL;

	if (address & ~HPAGE_PMD_MASK)
		goto out;

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;

	pud = pud_offset(pgd, address);
	if (!pud_present(*pud))
		goto out;

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		goto out;
	if (pmd_page(*pmd) != page)
		goto out;
1107 1108 1109 1110 1111 1112 1113 1114 1115 1116
	/*
	 * split_vma() may create temporary aliased mappings. There is
	 * no risk as long as all huge pmd are found and have their
	 * splitting bit set before __split_huge_page_refcount
	 * runs. Finding the same huge pmd more than once during the
	 * same rmap walk is not a problem.
	 */
	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
	    pmd_trans_splitting(*pmd))
		goto out;
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
	if (pmd_trans_huge(*pmd)) {
		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
			  !pmd_trans_splitting(*pmd));
		ret = pmd;
	}
out:
	return ret;
}

static int __split_huge_page_splitting(struct page *page,
				       struct vm_area_struct *vma,
				       unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t *pmd;
	int ret = 0;

	spin_lock(&mm->page_table_lock);
	pmd = page_check_address_pmd(page, mm, address,
				     PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
	if (pmd) {
		/*
		 * We can't temporarily set the pmd to null in order
		 * to split it, the pmd must remain marked huge at all
		 * times or the VM won't take the pmd_trans_huge paths
1142
		 * and it won't wait on the anon_vma->root->mutex to
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157
		 * serialize against split_huge_page*.
		 */
		pmdp_splitting_flush_notify(vma, address, pmd);
		ret = 1;
	}
	spin_unlock(&mm->page_table_lock);

	return ret;
}

static void __split_huge_page_refcount(struct page *page)
{
	int i;
	unsigned long head_index = page->index;
	struct zone *zone = page_zone(page);
1158
	int zonestat;
1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175

	/* prevent PageLRU to go away from under us, and freeze lru stats */
	spin_lock_irq(&zone->lru_lock);
	compound_lock(page);

	for (i = 1; i < HPAGE_PMD_NR; i++) {
		struct page *page_tail = page + i;

		/* tail_page->_count cannot change */
		atomic_sub(atomic_read(&page_tail->_count), &page->_count);
		BUG_ON(page_count(page) <= 0);
		atomic_add(page_mapcount(page) + 1, &page_tail->_count);
		BUG_ON(atomic_read(&page_tail->_count) <= 0);

		/* after clearing PageTail the gup refcount can be released */
		smp_mb();

1176 1177 1178 1179 1180 1181
		/*
		 * retain hwpoison flag of the poisoned tail page:
		 *   fix for the unsuitable process killed on Guest Machine(KVM)
		 *   by the memory-failure.
		 */
		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
		page_tail->flags |= (page->flags &
				     ((1L << PG_referenced) |
				      (1L << PG_swapbacked) |
				      (1L << PG_mlocked) |
				      (1L << PG_uptodate)));
		page_tail->flags |= (1L << PG_dirty);

		/*
		 * 1) clear PageTail before overwriting first_page
		 * 2) clear PageTail before clearing PageHead for VM_BUG_ON
		 */
		smp_wmb();

		/*
		 * __split_huge_page_splitting() already set the
		 * splitting bit in all pmd that could map this
		 * hugepage, that will ensure no CPU can alter the
		 * mapcount on the head page. The mapcount is only
		 * accounted in the head page and it has to be
		 * transferred to all tail pages in the below code. So
		 * for this code to be safe, the split the mapcount
		 * can't change. But that doesn't mean userland can't
		 * keep changing and reading the page contents while
		 * we transfer the mapcount, so the pmd splitting
		 * status is achieved setting a reserved bit in the
		 * pmd, not by clearing the present bit.
		*/
		BUG_ON(page_mapcount(page_tail));
		page_tail->_mapcount = page->_mapcount;

		BUG_ON(page_tail->mapping);
		page_tail->mapping = page->mapping;

		page_tail->index = ++head_index;

		BUG_ON(!PageAnon(page_tail));
		BUG_ON(!PageUptodate(page_tail));
		BUG_ON(!PageDirty(page_tail));
		BUG_ON(!PageSwapBacked(page_tail));

1222 1223
		mem_cgroup_split_huge_fixup(page, page_tail);

1224 1225 1226
		lru_add_page_tail(zone, page, page_tail);
	}

1227 1228 1229
	__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
	__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);

1230 1231 1232 1233 1234 1235 1236 1237 1238
	/*
	 * A hugepage counts for HPAGE_PMD_NR pages on the LRU statistics,
	 * so adjust those appropriately if this page is on the LRU.
	 */
	if (PageLRU(page)) {
		zonestat = NR_LRU_BASE + page_lru(page);
		__mod_zone_page_state(zone, zonestat, -(HPAGE_PMD_NR-1));
	}

1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335
	ClearPageCompound(page);
	compound_unlock(page);
	spin_unlock_irq(&zone->lru_lock);

	for (i = 1; i < HPAGE_PMD_NR; i++) {
		struct page *page_tail = page + i;
		BUG_ON(page_count(page_tail) <= 0);
		/*
		 * Tail pages may be freed if there wasn't any mapping
		 * like if add_to_swap() is running on a lru page that
		 * had its mapping zapped. And freeing these pages
		 * requires taking the lru_lock so we do the put_page
		 * of the tail pages after the split is complete.
		 */
		put_page(page_tail);
	}

	/*
	 * Only the head page (now become a regular page) is required
	 * to be pinned by the caller.
	 */
	BUG_ON(page_count(page) <= 0);
}

static int __split_huge_page_map(struct page *page,
				 struct vm_area_struct *vma,
				 unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t *pmd, _pmd;
	int ret = 0, i;
	pgtable_t pgtable;
	unsigned long haddr;

	spin_lock(&mm->page_table_lock);
	pmd = page_check_address_pmd(page, mm, address,
				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
	if (pmd) {
		pgtable = get_pmd_huge_pte(mm);
		pmd_populate(mm, &_pmd, pgtable);

		for (i = 0, haddr = address; i < HPAGE_PMD_NR;
		     i++, haddr += PAGE_SIZE) {
			pte_t *pte, entry;
			BUG_ON(PageCompound(page+i));
			entry = mk_pte(page + i, vma->vm_page_prot);
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
			if (!pmd_write(*pmd))
				entry = pte_wrprotect(entry);
			else
				BUG_ON(page_mapcount(page) != 1);
			if (!pmd_young(*pmd))
				entry = pte_mkold(entry);
			pte = pte_offset_map(&_pmd, haddr);
			BUG_ON(!pte_none(*pte));
			set_pte_at(mm, haddr, pte, entry);
			pte_unmap(pte);
		}

		mm->nr_ptes++;
		smp_wmb(); /* make pte visible before pmd */
		/*
		 * Up to this point the pmd is present and huge and
		 * userland has the whole access to the hugepage
		 * during the split (which happens in place). If we
		 * overwrite the pmd with the not-huge version
		 * pointing to the pte here (which of course we could
		 * if all CPUs were bug free), userland could trigger
		 * a small page size TLB miss on the small sized TLB
		 * while the hugepage TLB entry is still established
		 * in the huge TLB. Some CPU doesn't like that. See
		 * http://support.amd.com/us/Processor_TechDocs/41322.pdf,
		 * Erratum 383 on page 93. Intel should be safe but is
		 * also warns that it's only safe if the permission
		 * and cache attributes of the two entries loaded in
		 * the two TLB is identical (which should be the case
		 * here). But it is generally safer to never allow
		 * small and huge TLB entries for the same virtual
		 * address to be loaded simultaneously. So instead of
		 * doing "pmd_populate(); flush_tlb_range();" we first
		 * mark the current pmd notpresent (atomically because
		 * here the pmd_trans_huge and pmd_trans_splitting
		 * must remain set at all times on the pmd until the
		 * split is complete for this pmd), then we flush the
		 * SMP TLB and finally we write the non-huge version
		 * of the pmd entry with pmd_populate.
		 */
		set_pmd_at(mm, address, pmd, pmd_mknotpresent(*pmd));
		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
		pmd_populate(mm, pmd, pgtable);
		ret = 1;
	}
	spin_unlock(&mm->page_table_lock);

	return ret;
}

1336
/* must be called with anon_vma->root->mutex hold */
1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354
static void __split_huge_page(struct page *page,
			      struct anon_vma *anon_vma)
{
	int mapcount, mapcount2;
	struct anon_vma_chain *avc;

	BUG_ON(!PageHead(page));
	BUG_ON(PageTail(page));

	mapcount = 0;
	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long addr = vma_address(page, vma);
		BUG_ON(is_vma_temporary_stack(vma));
		if (addr == -EFAULT)
			continue;
		mapcount += __split_huge_page_splitting(page, vma, addr);
	}
1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367
	/*
	 * It is critical that new vmas are added to the tail of the
	 * anon_vma list. This guarantes that if copy_huge_pmd() runs
	 * and establishes a child pmd before
	 * __split_huge_page_splitting() freezes the parent pmd (so if
	 * we fail to prevent copy_huge_pmd() from running until the
	 * whole __split_huge_page() is complete), we will still see
	 * the newly established pmd of the child later during the
	 * walk, to be able to set it as pmd_trans_splitting too.
	 */
	if (mapcount != page_mapcount(page))
		printk(KERN_ERR "mapcount %d page_mapcount %d\n",
		       mapcount, page_mapcount(page));
1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380
	BUG_ON(mapcount != page_mapcount(page));

	__split_huge_page_refcount(page);

	mapcount2 = 0;
	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long addr = vma_address(page, vma);
		BUG_ON(is_vma_temporary_stack(vma));
		if (addr == -EFAULT)
			continue;
		mapcount2 += __split_huge_page_map(page, vma, addr);
	}
1381 1382 1383
	if (mapcount != mapcount2)
		printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n",
		       mapcount, mapcount2, page_mapcount(page));
1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401
	BUG_ON(mapcount != mapcount2);
}

int split_huge_page(struct page *page)
{
	struct anon_vma *anon_vma;
	int ret = 1;

	BUG_ON(!PageAnon(page));
	anon_vma = page_lock_anon_vma(page);
	if (!anon_vma)
		goto out;
	ret = 0;
	if (!PageCompound(page))
		goto out_unlock;

	BUG_ON(!PageSwapBacked(page));
	__split_huge_page(page, anon_vma);
1402
	count_vm_event(THP_SPLIT);
1403 1404 1405 1406 1407 1408 1409 1410

	BUG_ON(PageCompound(page));
out_unlock:
	page_unlock_anon_vma(anon_vma);
out:
	return ret;
}

1411 1412 1413
#define VM_NO_THP (VM_SPECIAL|VM_INSERTPAGE|VM_MIXEDMAP|VM_SAO| \
		   VM_HUGETLB|VM_SHARED|VM_MAYSHARE)

1414 1415
int hugepage_madvise(struct vm_area_struct *vma,
		     unsigned long *vm_flags, int advice)
A
Andrea Arcangeli 已提交
1416
{
A
Andrea Arcangeli 已提交
1417 1418 1419 1420 1421
	switch (advice) {
	case MADV_HUGEPAGE:
		/*
		 * Be somewhat over-protective like KSM for now!
		 */
1422
		if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP))
A
Andrea Arcangeli 已提交
1423 1424 1425
			return -EINVAL;
		*vm_flags &= ~VM_NOHUGEPAGE;
		*vm_flags |= VM_HUGEPAGE;
1426 1427 1428 1429 1430 1431 1432
		/*
		 * 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 (unlikely(khugepaged_enter_vma_merge(vma)))
			return -ENOMEM;
A
Andrea Arcangeli 已提交
1433 1434 1435 1436 1437
		break;
	case MADV_NOHUGEPAGE:
		/*
		 * Be somewhat over-protective like KSM for now!
		 */
1438
		if (*vm_flags & (VM_NOHUGEPAGE | VM_NO_THP))
A
Andrea Arcangeli 已提交
1439 1440 1441
			return -EINVAL;
		*vm_flags &= ~VM_HUGEPAGE;
		*vm_flags |= VM_NOHUGEPAGE;
1442 1443 1444 1445 1446
		/*
		 * 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.
		 */
A
Andrea Arcangeli 已提交
1447 1448
		break;
	}
A
Andrea Arcangeli 已提交
1449 1450 1451 1452

	return 0;
}

A
Andrea Arcangeli 已提交
1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
static int __init khugepaged_slab_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;

	return 0;
}

static void __init khugepaged_slab_free(void)
{
	kmem_cache_destroy(mm_slot_cache);
	mm_slot_cache = NULL;
}

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 int __init mm_slots_hash_init(void)
{
	mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head),
				GFP_KERNEL);
	if (!mm_slots_hash)
		return -ENOMEM;
	return 0;
}

#if 0
static void __init mm_slots_hash_free(void)
{
	kfree(mm_slots_hash);
	mm_slots_hash = NULL;
}
#endif

static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	struct hlist_head *bucket;
	struct hlist_node *node;

	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
				% MM_SLOTS_HASH_HEADS];
	hlist_for_each_entry(mm_slot, node, bucket, hash) {
		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)
{
	struct hlist_head *bucket;

	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
				% MM_SLOTS_HASH_HEADS];
	mm_slot->mm = mm;
	hlist_add_head(&mm_slot->hash, bucket);
}

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

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(khugepaged_test_exit(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);

	atomic_inc(&mm->mm_count);
	if (wakeup)
		wake_up_interruptible(&khugepaged_wait);

	return 0;
}

int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
{
	unsigned long hstart, hend;
	if (!vma->anon_vma)
		/*
		 * Not yet faulted in so we will register later in the
		 * page fault if needed.
		 */
		return 0;
1572
	if (vma->vm_ops)
A
Andrea Arcangeli 已提交
1573 1574
		/* khugepaged not yet working on file or special mappings */
		return 0;
1575 1576 1577 1578 1579
	/*
	 * If is_pfn_mapping() is true is_learn_pfn_mapping() must be
	 * true too, verify it here.
	 */
	VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP);
A
Andrea Arcangeli 已提交
1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703
	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
	hend = vma->vm_end & HPAGE_PMD_MASK;
	if (hstart < hend)
		return khugepaged_enter(vma);
	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) {
		hlist_del(&mm_slot->hash);
		list_del(&mm_slot->mm_node);
		free = 1;
	}

	if (free) {
		spin_unlock(&khugepaged_mm_lock);
		clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
		free_mm_slot(mm_slot);
		mmdrop(mm);
	} else if (mm_slot) {
		spin_unlock(&khugepaged_mm_lock);
		/*
		 * 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);
	} else
		spin_unlock(&khugepaged_mm_lock);
}

static void release_pte_page(struct page *page)
{
	/* 0 stands for page_is_file_cache(page) == false */
	dec_zone_page_state(page, NR_ISOLATED_ANON + 0);
	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))
			release_pte_page(pte_page(pteval));
	}
}

static void release_all_pte_pages(pte_t *pte)
{
	release_pte_pages(pte, pte + HPAGE_PMD_NR);
}

static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
					unsigned long address,
					pte_t *pte)
{
	struct page *page;
	pte_t *_pte;
	int referenced = 0, isolated = 0, none = 0;
	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
	     _pte++, address += PAGE_SIZE) {
		pte_t pteval = *_pte;
		if (pte_none(pteval)) {
			if (++none <= khugepaged_max_ptes_none)
				continue;
			else {
				release_pte_pages(pte, _pte);
				goto out;
			}
		}
		if (!pte_present(pteval) || !pte_write(pteval)) {
			release_pte_pages(pte, _pte);
			goto out;
		}
		page = vm_normal_page(vma, address, pteval);
		if (unlikely(!page)) {
			release_pte_pages(pte, _pte);
			goto out;
		}
		VM_BUG_ON(PageCompound(page));
		BUG_ON(!PageAnon(page));
		VM_BUG_ON(!PageSwapBacked(page));

		/* cannot use mapcount: can't collapse if there's a gup pin */
		if (page_count(page) != 1) {
			release_pte_pages(pte, _pte);
			goto out;
		}
		/*
		 * 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)) {
			release_pte_pages(pte, _pte);
			goto out;
		}
		/*
		 * Isolate the page to avoid collapsing an hugepage
		 * currently in use by the VM.
		 */
		if (isolate_lru_page(page)) {
			unlock_page(page);
			release_pte_pages(pte, _pte);
			goto out;
		}
		/* 0 stands for page_is_file_cache(page) == false */
		inc_zone_page_state(page, NR_ISOLATED_ANON + 0);
		VM_BUG_ON(!PageLocked(page));
		VM_BUG_ON(PageLRU(page));

		/* If there is no mapped pte young don't collapse the page */
A
Andrea Arcangeli 已提交
1704 1705
		if (pte_young(pteval) || PageReferenced(page) ||
		    mmu_notifier_test_young(vma->vm_mm, address))
A
Andrea Arcangeli 已提交
1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757
			referenced = 1;
	}
	if (unlikely(!referenced))
		release_all_pte_pages(pte);
	else
		isolated = 1;
out:
	return isolated;
}

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;
	for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) {
		pte_t pteval = *_pte;
		struct page *src_page;

		if (pte_none(pteval)) {
			clear_user_highpage(page, address);
			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
		} else {
			src_page = pte_page(pteval);
			copy_user_highpage(page, src_page, address, vma);
			VM_BUG_ON(page_mapcount(src_page) != 1);
			VM_BUG_ON(page_count(src_page) != 2);
			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);
			spin_unlock(ptl);
			free_page_and_swap_cache(src_page);
		}

		address += PAGE_SIZE;
		page++;
	}
}

static void collapse_huge_page(struct mm_struct *mm,
			       unsigned long address,
1758
			       struct page **hpage,
1759 1760
			       struct vm_area_struct *vma,
			       int node)
A
Andrea Arcangeli 已提交
1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd, _pmd;
	pte_t *pte;
	pgtable_t pgtable;
	struct page *new_page;
	spinlock_t *ptl;
	int isolated;
	unsigned long hstart, hend;

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
1773
#ifndef CONFIG_NUMA
1774
	up_read(&mm->mmap_sem);
A
Andrea Arcangeli 已提交
1775
	VM_BUG_ON(!*hpage);
1776
	new_page = *hpage;
1777 1778
#else
	VM_BUG_ON(*hpage);
1779 1780 1781 1782 1783 1784 1785 1786 1787 1788
	/*
	 * Allocate the page while the vma is still valid and under
	 * the mmap_sem read mode so there is no memory allocation
	 * later when we take the mmap_sem in write mode. This is more
	 * friendly behavior (OTOH it may actually hide bugs) to
	 * filesystems in userland with daemons allocating memory in
	 * the userland I/O paths.  Allocating memory with the
	 * mmap_sem in read mode is good idea also to allow greater
	 * scalability.
	 */
1789
	new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
1790
				      node, __GFP_OTHER_NODE);
1791 1792 1793 1794 1795 1796

	/*
	 * After allocating the hugepage, release the mmap_sem read lock in
	 * preparation for taking it in write mode.
	 */
	up_read(&mm->mmap_sem);
1797
	if (unlikely(!new_page)) {
1798
		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
1799 1800 1801
		*hpage = ERR_PTR(-ENOMEM);
		return;
	}
1802 1803
#endif

1804
	count_vm_event(THP_COLLAPSE_ALLOC);
1805
	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
1806
#ifdef CONFIG_NUMA
1807
		put_page(new_page);
1808
#endif
1809 1810
		return;
	}
A
Andrea Arcangeli 已提交
1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826

	/*
	 * Prevent all access to pagetables with the exception of
	 * gup_fast later hanlded by the ptep_clear_flush and the VM
	 * handled by the anon_vma lock + PG_lock.
	 */
	down_write(&mm->mmap_sem);
	if (unlikely(khugepaged_test_exit(mm)))
		goto out;

	vma = find_vma(mm, address);
	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)
		goto out;

1827 1828
	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
	    (vma->vm_flags & VM_NOHUGEPAGE))
A
Andrea Arcangeli 已提交
1829 1830
		goto out;

1831
	if (!vma->anon_vma || vma->vm_ops)
A
Andrea Arcangeli 已提交
1832
		goto out;
1833 1834
	if (is_vma_temporary_stack(vma))
		goto out;
1835 1836 1837 1838 1839
	/*
	 * If is_pfn_mapping() is true is_learn_pfn_mapping() must be
	 * true too, verify it here.
	 */
	VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP);
A
Andrea Arcangeli 已提交
1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;

	pud = pud_offset(pgd, address);
	if (!pud_present(*pud))
		goto out;

	pmd = pmd_offset(pud, address);
	/* pmd can't go away or become huge under us */
	if (!pmd_present(*pmd) || pmd_trans_huge(*pmd))
		goto out;

	anon_vma_lock(vma->anon_vma);

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

	spin_lock(&mm->page_table_lock); /* 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_clear_flush_notify(vma, address, pmd);
	spin_unlock(&mm->page_table_lock);

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

	if (unlikely(!isolated)) {
1874
		pte_unmap(pte);
A
Andrea Arcangeli 已提交
1875 1876 1877 1878 1879
		spin_lock(&mm->page_table_lock);
		BUG_ON(!pmd_none(*pmd));
		set_pmd_at(mm, address, pmd, _pmd);
		spin_unlock(&mm->page_table_lock);
		anon_vma_unlock(vma->anon_vma);
1880
		goto out;
A
Andrea Arcangeli 已提交
1881 1882 1883 1884 1885 1886 1887 1888 1889
	}

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

	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
1890
	pte_unmap(pte);
A
Andrea Arcangeli 已提交
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
	__SetPageUptodate(new_page);
	pgtable = pmd_pgtable(_pmd);
	VM_BUG_ON(page_count(pgtable) != 1);
	VM_BUG_ON(page_mapcount(pgtable) != 0);

	_pmd = mk_pmd(new_page, vma->vm_page_prot);
	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
	_pmd = pmd_mkhuge(_pmd);

	/*
	 * 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(&mm->page_table_lock);
	BUG_ON(!pmd_none(*pmd));
	page_add_new_anon_rmap(new_page, vma, address);
	set_pmd_at(mm, address, pmd, _pmd);
	update_mmu_cache(vma, address, entry);
	prepare_pmd_huge_pte(pgtable, mm);
	mm->nr_ptes--;
	spin_unlock(&mm->page_table_lock);

1916
#ifndef CONFIG_NUMA
A
Andrea Arcangeli 已提交
1917
	*hpage = NULL;
1918
#endif
A
Andrea Arcangeli 已提交
1919
	khugepaged_pages_collapsed++;
1920
out_up_write:
A
Andrea Arcangeli 已提交
1921
	up_write(&mm->mmap_sem);
1922 1923
	return;

1924
out:
1925
	mem_cgroup_uncharge_page(new_page);
1926 1927 1928
#ifdef CONFIG_NUMA
	put_page(new_page);
#endif
1929
	goto out_up_write;
A
Andrea Arcangeli 已提交
1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
}

static int khugepaged_scan_pmd(struct mm_struct *mm,
			       struct vm_area_struct *vma,
			       unsigned long address,
			       struct page **hpage)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte, *_pte;
	int ret = 0, referenced = 0, none = 0;
	struct page *page;
	unsigned long _address;
	spinlock_t *ptl;
1945
	int node = -1;
A
Andrea Arcangeli 已提交
1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;

	pud = pud_offset(pgd, address);
	if (!pud_present(*pud))
		goto out;

	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd) || pmd_trans_huge(*pmd))
		goto out;

	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 (pte_none(pteval)) {
			if (++none <= khugepaged_max_ptes_none)
				continue;
			else
				goto out_unmap;
		}
		if (!pte_present(pteval) || !pte_write(pteval))
			goto out_unmap;
		page = vm_normal_page(vma, _address, pteval);
		if (unlikely(!page))
			goto out_unmap;
1976 1977 1978 1979 1980 1981 1982
		/*
		 * Chose the node of the first page. This could
		 * be more sophisticated and look at more pages,
		 * but isn't for now.
		 */
		if (node == -1)
			node = page_to_nid(page);
A
Andrea Arcangeli 已提交
1983 1984 1985 1986 1987 1988
		VM_BUG_ON(PageCompound(page));
		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
			goto out_unmap;
		/* cannot use mapcount: can't collapse if there's a gup pin */
		if (page_count(page) != 1)
			goto out_unmap;
A
Andrea Arcangeli 已提交
1989 1990
		if (pte_young(pteval) || PageReferenced(page) ||
		    mmu_notifier_test_young(vma->vm_mm, address))
A
Andrea Arcangeli 已提交
1991 1992 1993 1994 1995 1996
			referenced = 1;
	}
	if (referenced)
		ret = 1;
out_unmap:
	pte_unmap_unlock(pte, ptl);
1997 1998
	if (ret)
		/* collapse_huge_page will return with the mmap_sem released */
1999
		collapse_huge_page(mm, address, hpage, vma, node);
A
Andrea Arcangeli 已提交
2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064
out:
	return ret;
}

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

	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));

	if (khugepaged_test_exit(mm)) {
		/* free mm_slot */
		hlist_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);
	}
}

static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
					    struct page **hpage)
{
	struct mm_slot *mm_slot;
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	int progress = 0;

	VM_BUG_ON(!pages);
	VM_BUG_ON(!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;
	down_read(&mm->mmap_sem);
	if (unlikely(khugepaged_test_exit(mm)))
		vma = NULL;
	else
		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;
		}

2065 2066 2067
		if ((!(vma->vm_flags & VM_HUGEPAGE) &&
		     !khugepaged_always()) ||
		    (vma->vm_flags & VM_NOHUGEPAGE)) {
2068
		skip:
A
Andrea Arcangeli 已提交
2069 2070 2071
			progress++;
			continue;
		}
2072
		if (!vma->anon_vma || vma->vm_ops)
2073 2074 2075
			goto skip;
		if (is_vma_temporary_stack(vma))
			goto skip;
2076 2077 2078 2079 2080 2081
		/*
		 * If is_pfn_mapping() is true is_learn_pfn_mapping()
		 * must be true too, verify it here.
		 */
		VM_BUG_ON(is_linear_pfn_mapping(vma) ||
			  vma->vm_flags & VM_NO_THP);
A
Andrea Arcangeli 已提交
2082 2083 2084

		hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
		hend = vma->vm_end & HPAGE_PMD_MASK;
2085 2086 2087 2088
		if (hstart >= hend)
			goto skip;
		if (khugepaged_scan.address > hend)
			goto skip;
A
Andrea Arcangeli 已提交
2089 2090
		if (khugepaged_scan.address < hstart)
			khugepaged_scan.address = hstart;
2091
		VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
A
Andrea Arcangeli 已提交
2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119

		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);
			ret = khugepaged_scan_pmd(mm, vma,
						  khugepaged_scan.address,
						  hpage);
			/* 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);
2120
	VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
A
Andrea Arcangeli 已提交
2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168
	/*
	 * 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) ||
		!khugepaged_enabled();
}

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

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

	while (progress < pages) {
		cond_resched();

2169
#ifndef CONFIG_NUMA
A
Andrea Arcangeli 已提交
2170 2171
		if (!*hpage) {
			*hpage = alloc_hugepage(khugepaged_defrag());
2172 2173
			if (unlikely(!*hpage)) {
				count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
A
Andrea Arcangeli 已提交
2174
				break;
2175 2176
			}
			count_vm_event(THP_COLLAPSE_ALLOC);
A
Andrea Arcangeli 已提交
2177
		}
2178 2179 2180 2181
#else
		if (IS_ERR(*hpage))
			break;
#endif
A
Andrea Arcangeli 已提交
2182

2183 2184 2185
		if (unlikely(kthread_should_stop() || freezing(current)))
			break;

A
Andrea Arcangeli 已提交
2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198
		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);
	}
}

2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209
static void khugepaged_alloc_sleep(void)
{
	DEFINE_WAIT(wait);
	add_wait_queue(&khugepaged_wait, &wait);
	schedule_timeout_interruptible(
		msecs_to_jiffies(
			khugepaged_alloc_sleep_millisecs));
	remove_wait_queue(&khugepaged_wait, &wait);
}

#ifndef CONFIG_NUMA
A
Andrea Arcangeli 已提交
2210 2211 2212 2213 2214 2215
static struct page *khugepaged_alloc_hugepage(void)
{
	struct page *hpage;

	do {
		hpage = alloc_hugepage(khugepaged_defrag());
2216 2217
		if (!hpage) {
			count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
2218
			khugepaged_alloc_sleep();
2219 2220
		} else
			count_vm_event(THP_COLLAPSE_ALLOC);
A
Andrea Arcangeli 已提交
2221 2222 2223 2224
	} while (unlikely(!hpage) &&
		 likely(khugepaged_enabled()));
	return hpage;
}
2225
#endif
A
Andrea Arcangeli 已提交
2226 2227 2228 2229 2230

static void khugepaged_loop(void)
{
	struct page *hpage;

2231 2232 2233
#ifdef CONFIG_NUMA
	hpage = NULL;
#endif
A
Andrea Arcangeli 已提交
2234
	while (likely(khugepaged_enabled())) {
2235
#ifndef CONFIG_NUMA
A
Andrea Arcangeli 已提交
2236
		hpage = khugepaged_alloc_hugepage();
2237 2238
		if (unlikely(!hpage)) {
			count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
A
Andrea Arcangeli 已提交
2239
			break;
2240 2241
		}
		count_vm_event(THP_COLLAPSE_ALLOC);
2242 2243 2244 2245 2246 2247
#else
		if (IS_ERR(hpage)) {
			khugepaged_alloc_sleep();
			hpage = NULL;
		}
#endif
A
Andrea Arcangeli 已提交
2248 2249

		khugepaged_do_scan(&hpage);
2250
#ifndef CONFIG_NUMA
A
Andrea Arcangeli 已提交
2251 2252
		if (hpage)
			put_page(hpage);
2253
#endif
2254 2255 2256
		try_to_freeze();
		if (unlikely(kthread_should_stop()))
			break;
A
Andrea Arcangeli 已提交
2257 2258 2259 2260 2261 2262 2263 2264 2265 2266
		if (khugepaged_has_work()) {
			DEFINE_WAIT(wait);
			if (!khugepaged_scan_sleep_millisecs)
				continue;
			add_wait_queue(&khugepaged_wait, &wait);
			schedule_timeout_interruptible(
				msecs_to_jiffies(
					khugepaged_scan_sleep_millisecs));
			remove_wait_queue(&khugepaged_wait, &wait);
		} else if (khugepaged_enabled())
2267 2268
			wait_event_freezable(khugepaged_wait,
					     khugepaged_wait_event());
A
Andrea Arcangeli 已提交
2269 2270 2271 2272 2273 2274 2275
	}
}

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

2276
	set_freezable();
A
Andrea Arcangeli 已提交
2277 2278 2279 2280 2281 2282 2283
	set_user_nice(current, 19);

	/* serialize with start_khugepaged() */
	mutex_lock(&khugepaged_mutex);

	for (;;) {
		mutex_unlock(&khugepaged_mutex);
2284
		VM_BUG_ON(khugepaged_thread != current);
A
Andrea Arcangeli 已提交
2285
		khugepaged_loop();
2286
		VM_BUG_ON(khugepaged_thread != current);
A
Andrea Arcangeli 已提交
2287 2288 2289 2290

		mutex_lock(&khugepaged_mutex);
		if (!khugepaged_enabled())
			break;
2291 2292
		if (unlikely(kthread_should_stop()))
			break;
A
Andrea Arcangeli 已提交
2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307
	}

	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);

	khugepaged_thread = NULL;
	mutex_unlock(&khugepaged_mutex);

	return 0;
}

2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326
void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
{
	struct page *page;

	spin_lock(&mm->page_table_lock);
	if (unlikely(!pmd_trans_huge(*pmd))) {
		spin_unlock(&mm->page_table_lock);
		return;
	}
	page = pmd_page(*pmd);
	VM_BUG_ON(!page_count(page));
	get_page(page);
	spin_unlock(&mm->page_table_lock);

	split_huge_page(page);

	put_page(page);
	BUG_ON(pmd_trans_huge(*pmd));
}
2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394

static void split_huge_page_address(struct mm_struct *mm,
				    unsigned long address)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		return;

	pud = pud_offset(pgd, address);
	if (!pud_present(*pud))
		return;

	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd))
		return;
	/*
	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
	 * materialize from under us.
	 */
	split_huge_page_pmd(mm, pmd);
}

void __vma_adjust_trans_huge(struct vm_area_struct *vma,
			     unsigned long start,
			     unsigned long end,
			     long adjust_next)
{
	/*
	 * If the new start address isn't hpage aligned and it could
	 * previously contain an hugepage: check if we need to split
	 * an huge pmd.
	 */
	if (start & ~HPAGE_PMD_MASK &&
	    (start & HPAGE_PMD_MASK) >= vma->vm_start &&
	    (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
		split_huge_page_address(vma->vm_mm, start);

	/*
	 * If the new end address isn't hpage aligned and it could
	 * previously contain an hugepage: check if we need to split
	 * an huge pmd.
	 */
	if (end & ~HPAGE_PMD_MASK &&
	    (end & HPAGE_PMD_MASK) >= vma->vm_start &&
	    (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
		split_huge_page_address(vma->vm_mm, end);

	/*
	 * If we're also updating the vma->vm_next->vm_start, if the new
	 * vm_next->vm_start isn't page aligned and it could previously
	 * contain an hugepage: check if we need to split an huge pmd.
	 */
	if (adjust_next > 0) {
		struct vm_area_struct *next = vma->vm_next;
		unsigned long nstart = next->vm_start;
		nstart += adjust_next << PAGE_SHIFT;
		if (nstart & ~HPAGE_PMD_MASK &&
		    (nstart & HPAGE_PMD_MASK) >= next->vm_start &&
		    (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end)
			split_huge_page_address(next->vm_mm, nstart);
	}
}