Newer
Older
/*
* 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>
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <linux/hashtable.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
* By default transparent hugepage support is disabled in order that avoid
* to risk increase the memory footprint of applications without a guaranteed
* benefit. When transparent hugepage support is enabled, is for all mappings,
* and khugepaged scans all mappings.
* Defrag is invoked by khugepaged hugepage allocations and by page faults
* for all hugepage allocations.
unsigned long transparent_hugepage_flags __read_mostly =
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_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 khugepaged_slab_init(void);
#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),
};
static int set_recommended_min_free_kbytes(void)
{
struct zone *zone;
int nr_zones = 0;
unsigned long recommended_min;
if (!khugepaged_enabled())
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
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);
static int start_khugepaged(void)
{
int err = 0;
if (khugepaged_enabled()) {
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;
}
if (!list_empty(&khugepaged_scan.mm_head))
set_recommended_min_free_kbytes();
} else if (khugepaged_thread) {
kthread_stop(khugepaged_thread);
khugepaged_thread = NULL;
}
static atomic_t huge_zero_refcount;
static struct page *huge_zero_page __read_mostly;
static inline bool is_huge_zero_page(struct page *page)
return ACCESS_ONCE(huge_zero_page) == page;
static inline bool is_huge_zero_pmd(pmd_t pmd)
{
return is_huge_zero_page(pmd_page(pmd));
static struct page *get_huge_zero_page(void)
{
struct page *zero_page;
retry:
if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
return ACCESS_ONCE(huge_zero_page);
zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
if (!zero_page) {
count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
}
count_vm_event(THP_ZERO_PAGE_ALLOC);
if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
preempt_enable();
__free_page(zero_page);
goto retry;
}
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
preempt_enable();
return ACCESS_ONCE(huge_zero_page);
static void put_huge_zero_page(void)
/*
* Counter should never go to zero here. Only shrinker can put
* last reference.
*/
BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
struct shrink_control *sc)
/* we can free zero page only if last reference remains */
return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
}
static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
__free_page(zero_page);
return HPAGE_PMD_NR;
static struct shrinker huge_zero_page_shrinker = {
.count_objects = shrink_huge_zero_page_count,
.scan_objects = shrink_huge_zero_page_scan,
.seeks = DEFAULT_SEEKS,
};
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
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)
{
ssize_t ret;
ret = double_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
if (ret > 0) {
int err;
mutex_lock(&khugepaged_mutex);
err = start_khugepaged();
mutex_unlock(&khugepaged_mutex);
}
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)
{
return sprintf(buf, "%d\n",
!!test_bit(flag, &transparent_hugepage_flags));
static ssize_t single_flag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count,
enum transparent_hugepage_flag flag)
{
unsigned long value;
int ret;
ret = kstrtoul(buf, 10, &value);
if (ret < 0)
return ret;
if (value > 1)
return -EINVAL;
if (value)
set_bit(flag, &transparent_hugepage_flags);
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
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);
static ssize_t use_zero_page_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static ssize_t use_zero_page_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
return single_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static struct kobj_attribute use_zero_page_attr =
__ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_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,
&use_zero_page_attr.attr,
#ifdef CONFIG_DEBUG_VM
&debug_cow_attr.attr,
#endif
NULL,
};
static struct attribute_group hugepage_attr_group = {
.attrs = hugepage_attr,
};
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);
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
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 = kstrtoul(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 = kstrtoul(buf, 10, &pages);
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
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
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 = 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 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",
static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
printk(KERN_ERR "hugepage: failed to create transparent hugepage kobject\n");
err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n");
err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n");
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
return 0;
remove_hp_group:
sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
delete_obj:
kobject_put(*hugepage_kobj);
return err;
}
static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
kobject_put(hugepage_kobj);
}
#else
static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
return 0;
}
static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
}
#endif /* CONFIG_SYSFS */
static int __init hugepage_init(void)
{
int err;
struct kobject *hugepage_kobj;
if (!has_transparent_hugepage()) {
transparent_hugepage_flags = 0;
return -EINVAL;
}
err = hugepage_init_sysfs(&hugepage_kobj);
if (err)
return err;
err = khugepaged_slab_init();
if (err)
goto out;
register_shrinker(&huge_zero_page_shrinker);
/*
* 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;
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
}
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);
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 inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
entry = mk_pmd(page, prot);
entry = pmd_mkhuge(entry);
return entry;
}
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)
{
pgtable_t pgtable;
VM_BUG_ON(!PageCompound(page));
pgtable = pte_alloc_one(mm, haddr);
if (unlikely(!pgtable))
return VM_FAULT_OOM;
clear_huge_page(page, haddr, HPAGE_PMD_NR);
/*
* The memory barrier inside __SetPageUptodate makes sure that
* clear_huge_page writes become visible before the set_pmd_at()
* write.
*/
ptl = pmd_lock(mm, pmd);
put_page(page);
pte_free(mm, pgtable);
} else {
pmd_t entry;
entry = mk_huge_pmd(page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
page_add_new_anon_rmap(page, vma, haddr);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
atomic_long_inc(&mm->nr_ptes);
static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp;
}
static inline struct page *alloc_hugepage_vma(int defrag,
struct vm_area_struct *vma,
unsigned long haddr, int nd,
gfp_t extra_gfp)
return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp),
HPAGE_PMD_ORDER, vma, haddr, nd);
/* Caller must hold page table lock. */
static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
struct page *zero_page)
if (!pmd_none(*pmd))
return false;
entry = mk_pmd(zero_page, vma->vm_page_prot);
entry = pmd_wrprotect(entry);
entry = pmd_mkhuge(entry);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
atomic_long_inc(&mm->nr_ptes);
return true;
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;
if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
Kirill A. Shutemov
committed
return VM_FAULT_FALLBACK;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
if (unlikely(khugepaged_enter(vma)))
return VM_FAULT_OOM;
if (!(flags & FAULT_FLAG_WRITE) &&
transparent_hugepage_use_zero_page()) {
pgtable_t pgtable;
struct page *zero_page;
bool set;
pgtable = pte_alloc_one(mm, haddr);
if (unlikely(!pgtable))
zero_page = get_huge_zero_page();
if (unlikely(!zero_page)) {
pte_free(mm, pgtable);
count_vm_event(THP_FAULT_FALLBACK);
Kirill A. Shutemov
committed
return VM_FAULT_FALLBACK;
ptl = pmd_lock(mm, pmd);
set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
zero_page);
if (!set) {
pte_free(mm, pgtable);
put_huge_zero_page();
}
return 0;
page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
vma, haddr, numa_node_id(), 0);
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
Kirill A. Shutemov
committed
return VM_FAULT_FALLBACK;
}
if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
Kirill A. Shutemov
committed
return VM_FAULT_FALLBACK;
}
if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
mem_cgroup_uncharge_page(page);
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
Kirill A. Shutemov
committed
return VM_FAULT_FALLBACK;
count_vm_event(THP_FAULT_ALLOC);
}
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)
{
spinlock_t *dst_ptl, *src_ptl;
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;
dst_ptl = pmd_lock(dst_mm, dst_pmd);
src_ptl = pmd_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
ret = -EAGAIN;
pmd = *src_pmd;
if (unlikely(!pmd_trans_huge(pmd))) {
pte_free(dst_mm, pgtable);
goto out_unlock;
}
* When page table lock is held, the huge zero pmd should not be
* under splitting since we don't split the page itself, only pmd to
* a page table.
*/
if (is_huge_zero_pmd(pmd)) {
struct page *zero_page;
bool set;
/*
* get_huge_zero_page() will never allocate a new page here,
* since we already have a zero page to copy. It just takes a
* reference.
*/
zero_page = get_huge_zero_page();
set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */
ret = 0;
goto out_unlock;
}
if (unlikely(pmd_trans_splitting(pmd))) {
/* split huge page running from under us */
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
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));
pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
atomic_long_inc(&dst_mm->nr_ptes);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
void huge_pmd_set_accessed(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmd, pmd_t orig_pmd,
int dirty)
{
pmd_t entry;
unsigned long haddr;
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_same(*pmd, orig_pmd)))
goto unlock;
entry = pmd_mkyoung(orig_pmd);
haddr = address & HPAGE_PMD_MASK;
if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
update_mmu_cache_pmd(vma, address, pmd);
unlock:
static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, pmd_t orig_pmd, unsigned long haddr)
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
pgtable_t pgtable;
pmd_t _pmd;
struct page *page;
int i, ret = 0;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
if (!page) {
ret |= VM_FAULT_OOM;
goto out;
}
if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
put_page(page);
ret |= VM_FAULT_OOM;
goto out;
}
clear_user_highpage(page, address);
__SetPageUptodate(page);
mmun_start = haddr;
mmun_end = haddr + HPAGE_PMD_SIZE;
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_same(*pmd, orig_pmd)))
goto out_free_page;
pmdp_clear_flush(vma, haddr, pmd);
/* leave pmd empty until pte is filled */
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
pte_t *pte, entry;
if (haddr == (address & PAGE_MASK)) {
entry = mk_pte(page, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
page_add_new_anon_rmap(page, vma, haddr);
} else {
entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
entry = pte_mkspecial(entry);
}
pte = pte_offset_map(&_pmd, haddr);
VM_BUG_ON(!pte_none(*pte));
set_pte_at(mm, haddr, pte, entry);
pte_unmap(pte);
}
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
put_huge_zero_page();
inc_mm_counter(mm, MM_ANONPAGES);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);