#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/page_table_check.h>
#include <linux/rcupdate_wait.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/dax.h>
#include <linux/ksm.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
#include "mm_slot.h"
enum scan_result {
SCAN_FAIL,
SCAN_SUCCEED,
SCAN_PMD_NULL,
SCAN_PMD_NONE,
SCAN_PMD_MAPPED,
SCAN_EXCEED_NONE_PTE,
SCAN_EXCEED_SWAP_PTE,
SCAN_EXCEED_SHARED_PTE,
SCAN_PTE_NON_PRESENT,
SCAN_PTE_UFFD_WP,
SCAN_PTE_MAPPED_HUGEPAGE,
SCAN_LACK_REFERENCED_PAGE,
SCAN_PAGE_NULL,
SCAN_SCAN_ABORT,
SCAN_PAGE_COUNT,
SCAN_PAGE_LRU,
SCAN_PAGE_LOCK,
SCAN_PAGE_ANON,
SCAN_PAGE_COMPOUND,
SCAN_ANY_PROCESS,
SCAN_VMA_NULL,
SCAN_VMA_CHECK,
SCAN_ADDRESS_RANGE,
SCAN_DEL_PAGE_LRU,
SCAN_ALLOC_HUGE_PAGE_FAIL,
SCAN_CGROUP_CHARGE_FAIL,
SCAN_TRUNCATED,
SCAN_PAGE_HAS_PRIVATE,
SCAN_STORE_FAILED,
SCAN_COPY_MC,
SCAN_PAGE_FILLED,
};
#define CREATE_TRACE_POINTS
#include <trace/events/huge_memory.h>
static struct task_struct *khugepaged_thread __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
static unsigned long khugepaged_sleep_expire;
static DEFINE_SPINLOCK(khugepaged_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
unsigned int khugepaged_max_ptes_none __read_mostly;
static unsigned int khugepaged_max_ptes_swap __read_mostly;
static unsigned int khugepaged_max_ptes_shared __read_mostly;
#define MM_SLOTS_HASH_BITS 10
static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
static struct kmem_cache *mm_slot_cache __ro_after_init;
struct collapse_control {
bool is_khugepaged;
u32 node_load[MAX_NUMNODES];
nodemask_t alloc_nmask;
};
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),
};
#ifdef CONFIG_SYSFS
static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(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 int msecs;
int err;
err = kstrtouint(buf, 10, &msecs);
if (err)
return -EINVAL;
khugepaged_scan_sleep_millisecs = msecs;
khugepaged_sleep_expire = 0;
wake_up_interruptible(&khugepaged_wait);
return count;
}
static struct kobj_attribute scan_sleep_millisecs_attr =
__ATTR_RW(scan_sleep_millisecs);
static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(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 int msecs;
int err;
err = kstrtouint(buf, 10, &msecs);
if (err)
return -EINVAL;
khugepaged_alloc_sleep_millisecs = msecs;
khugepaged_sleep_expire = 0;
wake_up_interruptible(&khugepaged_wait);
return count;
}
static struct kobj_attribute alloc_sleep_millisecs_attr =
__ATTR_RW(alloc_sleep_millisecs);
static ssize_t pages_to_scan_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(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)
{
unsigned int pages;
int err;
err = kstrtouint(buf, 10, &pages);
if (err || !pages)
return -EINVAL;
khugepaged_pages_to_scan = pages;
return count;
}
static struct kobj_attribute pages_to_scan_attr =
__ATTR_RW(pages_to_scan);
static ssize_t pages_collapsed_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(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 sysfs_emit(buf, "%u\n", khugepaged_full_scans);
}
static struct kobj_attribute full_scans_attr =
__ATTR_RO(full_scans);
static ssize_t defrag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_hugepage_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static ssize_t defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
return single_hugepage_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static struct kobj_attribute khugepaged_defrag_attr =
__ATTR_RW(defrag);
static ssize_t max_ptes_none_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none);
}
static ssize_t 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_RW(max_ptes_none);
static ssize_t max_ptes_swap_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap);
}
static ssize_t max_ptes_swap_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_swap;
err = kstrtoul(buf, 10, &max_ptes_swap);
if (err || max_ptes_swap > HPAGE_PMD_NR - 1)
return -EINVAL;
khugepaged_max_ptes_swap = max_ptes_swap;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_swap_attr =
__ATTR_RW(max_ptes_swap);
static ssize_t max_ptes_shared_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared);
}
static ssize_t max_ptes_shared_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_shared;
err = kstrtoul(buf, 10, &max_ptes_shared);
if (err || max_ptes_shared > HPAGE_PMD_NR - 1)
return -EINVAL;
khugepaged_max_ptes_shared = max_ptes_shared;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_shared_attr =
__ATTR_RW(max_ptes_shared);
static struct attribute *khugepaged_attr[] = {
&khugepaged_defrag_attr.attr,
&khugepaged_max_ptes_none_attr.attr,
&khugepaged_max_ptes_swap_attr.attr,
&khugepaged_max_ptes_shared_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,
};
struct attribute_group khugepaged_attr_group = {
.attrs = khugepaged_attr,
.name = "khugepaged",
};
#endif
int hugepage_madvise(struct vm_area_struct *vma,
vm_flags_t *vm_flags, int advice)
{
switch (advice) {
case MADV_HUGEPAGE:
#ifdef CONFIG_S390
if (mm_has_pgste(vma->vm_mm))
return 0;
#endif
*vm_flags &= ~VM_NOHUGEPAGE;
*vm_flags |= VM_HUGEPAGE;
khugepaged_enter_vma(vma, *vm_flags);
break;
case MADV_NOHUGEPAGE:
*vm_flags &= ~VM_HUGEPAGE;
*vm_flags |= VM_NOHUGEPAGE;
break;
}
return 0;
}
int __init khugepaged_init(void)
{
mm_slot_cache = KMEM_CACHE(mm_slot, 0);
if (!mm_slot_cache)
return -ENOMEM;
khugepaged_pages_to_scan = HPAGE_PMD_NR * 8;
khugepaged_max_ptes_none = HPAGE_PMD_NR - 1;
khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8;
khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2;
return 0;
}
void __init khugepaged_destroy(void)
{
kmem_cache_destroy(mm_slot_cache);
}
static inline int hpage_collapse_test_exit(struct mm_struct *mm)
{
return atomic_read(&mm->mm_users) == 0;
}
static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
{
return hpage_collapse_test_exit(mm) ||
mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm);
}
static bool hugepage_pmd_enabled(void)
{
if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
hugepage_global_enabled())
return true;
if (test_bit(PMD_ORDER, &huge_anon_orders_always))
return true;
if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
return true;
if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
hugepage_global_enabled())
return true;
if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled())
return true;
return false;
}
void __khugepaged_enter(struct mm_struct *mm)
{
struct mm_slot *slot;
int wakeup;
VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm);
if (unlikely(mm_flags_test_and_set(MMF_VM_HUGEPAGE, mm)))
return;
slot = mm_slot_alloc(mm_slot_cache);
if (!slot)
return;
spin_lock(&khugepaged_mm_lock);
mm_slot_insert(mm_slots_hash, mm, slot);
wakeup = list_empty(&khugepaged_scan.mm_head);
list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head);
spin_unlock(&khugepaged_mm_lock);
mmgrab(mm);
if (wakeup)
wake_up_interruptible(&khugepaged_wait);
}
void khugepaged_enter_vma(struct vm_area_struct *vma,
vm_flags_t vm_flags)
{
if (!mm_flags_test(MMF_VM_HUGEPAGE, vma->vm_mm) &&
hugepage_pmd_enabled()) {
if (thp_vma_allowable_order(vma, vm_flags, TVA_KHUGEPAGED, PMD_ORDER))
__khugepaged_enter(vma->vm_mm);
}
}
void __khugepaged_exit(struct mm_struct *mm)
{
struct mm_slot *slot;
int free = 0;
spin_lock(&khugepaged_mm_lock);
slot = mm_slot_lookup(mm_slots_hash, mm);
if (slot && khugepaged_scan.mm_slot != slot) {
hash_del(&slot->hash);
list_del(&slot->mm_node);
free = 1;
}
spin_unlock(&khugepaged_mm_lock);
if (free) {
mm_flags_clear(MMF_VM_HUGEPAGE, mm);
mm_slot_free(mm_slot_cache, slot);
mmdrop(mm);
} else if (slot) {
mmap_write_lock(mm);
mmap_write_unlock(mm);
}
}
static void release_pte_folio(struct folio *folio)
{
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
-folio_nr_pages(folio));
folio_unlock(folio);
folio_putback_lru(folio);
}
static void release_pte_pages(pte_t *pte, pte_t *_pte,
struct list_head *compound_pagelist)
{
struct folio *folio, *tmp;
while (--_pte >= pte) {
pte_t pteval = ptep_get(_pte);
unsigned long pfn;
if (pte_none(pteval))
continue;
pfn = pte_pfn(pteval);
if (is_zero_pfn(pfn))
continue;
folio = pfn_folio(pfn);
if (folio_test_large(folio))
continue;
release_pte_folio(folio);
}
list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) {
list_del(&folio->lru);
release_pte_folio(folio);
}
}
static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
unsigned long start_addr,
pte_t *pte,
struct collapse_control *cc,
struct list_head *compound_pagelist)
{
struct page *page = NULL;
struct folio *folio = NULL;
unsigned long addr = start_addr;
pte_t *_pte;
int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, addr += PAGE_SIZE) {
pte_t pteval = ptep_get(_pte);
if (pte_none(pteval) || (pte_present(pteval) &&
is_zero_pfn(pte_pfn(pteval)))) {
++none_or_zero;
if (!userfaultfd_armed(vma) &&
(!cc->is_khugepaged ||
none_or_zero <= khugepaged_max_ptes_none)) {
continue;
} else {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
goto out;
}
}
if (!pte_present(pteval)) {
result = SCAN_PTE_NON_PRESENT;
goto out;
}
if (pte_uffd_wp(pteval)) {
result = SCAN_PTE_UFFD_WP;
goto out;
}
page = vm_normal_page(vma, addr, pteval);
if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
result = SCAN_PAGE_NULL;
goto out;
}
folio = page_folio(page);
VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio);
if (folio_maybe_mapped_shared(folio)) {
++shared;
if (cc->is_khugepaged &&
shared > khugepaged_max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
goto out;
}
}
if (folio_test_large(folio)) {
struct folio *f;
list_for_each_entry(f, compound_pagelist, lru) {
if (folio == f)
goto next;
}
}
if (!folio_trylock(folio)) {
result = SCAN_PAGE_LOCK;
goto out;
}
if (folio_expected_ref_count(folio) != folio_ref_count(folio)) {
folio_unlock(folio);
result = SCAN_PAGE_COUNT;
goto out;
}
if (!folio_isolate_lru(folio)) {
folio_unlock(folio);
result = SCAN_DEL_PAGE_LRU;
goto out;
}
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
if (folio_test_large(folio))
list_add_tail(&folio->lru, compound_pagelist);
next:
if (cc->is_khugepaged &&
(pte_young(pteval) || folio_test_young(folio) ||
folio_test_referenced(folio) ||
mmu_notifier_test_young(vma->vm_mm, addr)))
referenced++;
}
if (unlikely(cc->is_khugepaged && !referenced)) {
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
trace_mm_collapse_huge_page_isolate(folio, none_or_zero,
referenced, result);
return result;
}
out:
release_pte_pages(pte, _pte, compound_pagelist);
trace_mm_collapse_huge_page_isolate(folio, none_or_zero,
referenced, result);
return result;
}
static void __collapse_huge_page_copy_succeeded(pte_t *pte,
struct vm_area_struct *vma,
unsigned long address,
spinlock_t *ptl,
struct list_head *compound_pagelist)
{
unsigned long end = address + HPAGE_PMD_SIZE;
struct folio *src, *tmp;
pte_t pteval;
pte_t *_pte;
unsigned int nr_ptes;
for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte += nr_ptes,
address += nr_ptes * PAGE_SIZE) {
nr_ptes = 1;
pteval = ptep_get(_pte);
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
if (is_zero_pfn(pte_pfn(pteval))) {
spin_lock(ptl);
ptep_clear(vma->vm_mm, address, _pte);
spin_unlock(ptl);
ksm_might_unmap_zero_page(vma->vm_mm, pteval);
}
} else {
struct page *src_page = pte_page(pteval);
src = page_folio(src_page);
if (folio_test_large(src)) {
unsigned int max_nr_ptes = (end - address) >> PAGE_SHIFT;
nr_ptes = folio_pte_batch(src, _pte, pteval, max_nr_ptes);
} else {
release_pte_folio(src);
}
spin_lock(ptl);
clear_ptes(vma->vm_mm, address, _pte, nr_ptes);
folio_remove_rmap_ptes(src, src_page, nr_ptes, vma);
spin_unlock(ptl);
free_swap_cache(src);
folio_put_refs(src, nr_ptes);
}
}
list_for_each_entry_safe(src, tmp, compound_pagelist, lru) {
list_del(&src->lru);
node_stat_sub_folio(src, NR_ISOLATED_ANON +
folio_is_file_lru(src));
folio_unlock(src);
free_swap_cache(src);
folio_putback_lru(src);
}
}
static void __collapse_huge_page_copy_failed(pte_t *pte,
pmd_t *pmd,
pmd_t orig_pmd,
struct vm_area_struct *vma,
struct list_head *compound_pagelist)
{
spinlock_t *pmd_ptl;
pmd_ptl = pmd_lock(vma->vm_mm, pmd);
pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd));
spin_unlock(pmd_ptl);
release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist);
}
static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio,
pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma,
unsigned long address, spinlock_t *ptl,
struct list_head *compound_pagelist)
{
unsigned int i;
int result = SCAN_SUCCEED;
for (i = 0; i < HPAGE_PMD_NR; i++) {
pte_t pteval = ptep_get(pte + i);
struct page *page = folio_page(folio, i);
unsigned long src_addr = address + i * PAGE_SIZE;
struct page *src_page;
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
clear_user_highpage(page, src_addr);
continue;
}
src_page = pte_page(pteval);
if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) {
result = SCAN_COPY_MC;
break;
}
}
if (likely(result == SCAN_SUCCEED))
__collapse_huge_page_copy_succeeded(pte, vma, address, ptl,
compound_pagelist);
else
__collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma,
compound_pagelist);
return result;
}
static void khugepaged_alloc_sleep(void)
{
DEFINE_WAIT(wait);
add_wait_queue(&khugepaged_wait, &wait);
__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
remove_wait_queue(&khugepaged_wait, &wait);
}
struct collapse_control khugepaged_collapse_control = {
.is_khugepaged = true,
};
static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc)
{
int i;
if (!node_reclaim_enabled())
return false;
if (cc->node_load[nid])
return false;
for (i = 0; i < MAX_NUMNODES; i++) {
if (!cc->node_load[i])
continue;
if (node_distance(nid, i) > node_reclaim_distance)
return true;
}
return false;
}
#define khugepaged_defrag() \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG))
static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void)
{
return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT;
}
#ifdef CONFIG_NUMA
static int hpage_collapse_find_target_node(struct collapse_control *cc)
{
int nid, target_node = 0, max_value = 0;
for (nid = 0; nid < MAX_NUMNODES; nid++)
if (cc->node_load[nid] > max_value) {
max_value = cc->node_load[nid];
target_node = nid;
}
for_each_online_node(nid) {
if (max_value == cc->node_load[nid])
node_set(nid, cc->alloc_nmask);
}
return target_node;
}
#else
static int hpage_collapse_find_target_node(struct collapse_control *cc)
{
return 0;
}
#endif
static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
bool expect_anon,
struct vm_area_struct **vmap,
struct collapse_control *cc)
{
struct vm_area_struct *vma;
enum tva_type type = cc->is_khugepaged ? TVA_KHUGEPAGED :
TVA_FORCED_COLLAPSE;
if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
return SCAN_ANY_PROCESS;
*vmap = vma = find_vma(mm, address);
if (!vma)
return SCAN_VMA_NULL;
if (!thp_vma_suitable_order(vma, address, PMD_ORDER))
return SCAN_ADDRESS_RANGE;
if (!thp_vma_allowable_order(vma, vma->vm_flags, type, PMD_ORDER))
return SCAN_VMA_CHECK;
if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap)))
return SCAN_PAGE_ANON;
return SCAN_SUCCEED;
}
static inline int check_pmd_state(pmd_t *pmd)
{
pmd_t pmde = pmdp_get_lockless(pmd);
if (pmd_none(pmde))
return SCAN_PMD_NONE;
if (is_pmd_migration_entry(pmde))
return SCAN_PMD_MAPPED;
if (!pmd_present(pmde))
return SCAN_PMD_NULL;
if (pmd_trans_huge(pmde))
return SCAN_PMD_MAPPED;
if (pmd_bad(pmde))
return SCAN_PMD_NULL;
return SCAN_SUCCEED;
}
static int find_pmd_or_thp_or_none(struct mm_struct *mm,
unsigned long address,
pmd_t **pmd)
{
*pmd = mm_find_pmd(mm, address);
if (!*pmd)
return SCAN_PMD_NULL;
return check_pmd_state(*pmd);
}
static int check_pmd_still_valid(struct mm_struct *mm,
unsigned long address,
pmd_t *pmd)
{
pmd_t *new_pmd;
int result = find_pmd_or_thp_or_none(mm, address, &new_pmd);
if (result != SCAN_SUCCEED)
return result;
if (new_pmd != pmd)
return SCAN_FAIL;
return SCAN_SUCCEED;
}
static int __collapse_huge_page_swapin(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long start_addr, pmd_t *pmd,
int referenced)
{
int swapped_in = 0;
vm_fault_t ret = 0;
unsigned long addr, end = start_addr + (HPAGE_PMD_NR * PAGE_SIZE);
int result;
pte_t *pte = NULL;
spinlock_t *ptl;
for (addr = start_addr; addr < end; addr += PAGE_SIZE) {
struct vm_fault vmf = {
.vma = vma,
.address = addr,
.pgoff = linear_page_index(vma, addr),
.flags = FAULT_FLAG_ALLOW_RETRY,
.pmd = pmd,
};
if (!pte++) {
pte = pte_offset_map_ro_nolock(mm, pmd, addr, &ptl);
if (!pte) {
mmap_read_unlock(mm);
result = SCAN_PMD_NULL;
goto out;
}
}
vmf.orig_pte = ptep_get_lockless(pte);
if (!is_swap_pte(vmf.orig_pte))
continue;
vmf.pte = pte;
vmf.ptl = ptl;
ret = do_swap_page(&vmf);
pte = NULL;
if (ret & VM_FAULT_RETRY) {
result = SCAN_PAGE_LOCK;
goto out;
}
if (ret & VM_FAULT_ERROR) {
mmap_read_unlock(mm);
result = SCAN_FAIL;
goto out;
}
swapped_in++;
}
if (pte)
pte_unmap(pte);
if (swapped_in)
lru_add_drain();
result = SCAN_SUCCEED;
out:
trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result);
return result;
}
static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm,
struct collapse_control *cc)
{
gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() :
GFP_TRANSHUGE);
int node = hpage_collapse_find_target_node(cc);
struct folio *folio;
folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask);
if (!folio) {
*foliop = NULL;
count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
return SCAN_ALLOC_HUGE_PAGE_FAIL;
}
count_vm_event(THP_COLLAPSE_ALLOC);
if (unlikely(mem_cgroup_charge(folio, mm, gfp))) {
folio_put(folio);
*foliop = NULL;
return SCAN_CGROUP_CHARGE_FAIL;
}
count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1);
*foliop = folio;
return SCAN_SUCCEED;
}
static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
int referenced, int unmapped,
struct collapse_control *cc)
{
LIST_HEAD(compound_pagelist);
pmd_t *pmd, _pmd;
pte_t *pte;
pgtable_t pgtable;
struct folio *folio;
spinlock_t *pmd_ptl, *pte_ptl;
int result = SCAN_FAIL;
struct vm_area_struct *vma;
struct mmu_notifier_range range;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
mmap_read_unlock(mm);
result = alloc_charge_folio(&folio, mm, cc);
if (result != SCAN_SUCCEED)
goto out_nolock;
mmap_read_lock(mm);
result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
if (result != SCAN_SUCCEED) {
mmap_read_unlock(mm);
goto out_nolock;
}
result = find_pmd_or_thp_or_none(mm, address, &pmd);
if (result != SCAN_SUCCEED) {
mmap_read_unlock(mm);
goto out_nolock;
}
if (unmapped) {
result = __collapse_huge_page_swapin(mm, vma, address, pmd,
referenced);
if (result != SCAN_SUCCEED)
goto out_nolock;
}
mmap_read_unlock(mm);
mmap_write_lock(mm);
result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
if (result != SCAN_SUCCEED)
goto out_up_write;
vma_start_write(vma);
result = check_pmd_still_valid(mm, address, pmd);
if (result != SCAN_SUCCEED)
goto out_up_write;
anon_vma_lock_write(vma->anon_vma);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address,
address + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
pmd_ptl = pmd_lock(mm, pmd);
_pmd = pmdp_collapse_flush(vma, address, pmd);
spin_unlock(pmd_ptl);
mmu_notifier_invalidate_range_end(&range);
tlb_remove_table_sync_one();
pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
if (pte) {
result = __collapse_huge_page_isolate(vma, address, pte, cc,
&compound_pagelist);
spin_unlock(pte_ptl);
} else {
result = SCAN_PMD_NULL;
}
if (unlikely(result != SCAN_SUCCEED)) {
if (pte)
pte_unmap(pte);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
pmd_populate(mm, pmd, pmd_pgtable(_pmd));
spin_unlock(pmd_ptl);
anon_vma_unlock_write(vma->anon_vma);
goto out_up_write;
}
anon_vma_unlock_write(vma->anon_vma);
result = __collapse_huge_page_copy(pte, folio, pmd, _pmd,
vma, address, pte_ptl,
&compound_pagelist);
pte_unmap(pte);
if (unlikely(result != SCAN_SUCCEED))
goto out_up_write;
__folio_mark_uptodate(folio);
pgtable = pmd_pgtable(_pmd);
_pmd = folio_mk_pmd(folio, vma->vm_page_prot);
_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
spin_lock(pmd_ptl);
BUG_ON(!pmd_none(*pmd));
folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
folio_add_lru_vma(folio, vma);
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, address, pmd, _pmd);
update_mmu_cache_pmd(vma, address, pmd);
deferred_split_folio(folio, false);
spin_unlock(pmd_ptl);
folio = NULL;
result = SCAN_SUCCEED;
out_up_write:
mmap_write_unlock(mm);
out_nolock:
if (folio)
folio_put(folio);
trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result);
return result;
}
static int hpage_collapse_scan_pmd(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long start_addr, bool *mmap_locked,
struct collapse_control *cc)
{
pmd_t *pmd;
pte_t *pte, *_pte;
int result = SCAN_FAIL, referenced = 0;
int none_or_zero = 0, shared = 0;
struct page *page = NULL;
struct folio *folio = NULL;
unsigned long addr;
spinlock_t *ptl;
int node = NUMA_NO_NODE, unmapped = 0;
VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
result = find_pmd_or_thp_or_none(mm, start_addr, &pmd);
if (result != SCAN_SUCCEED)
goto out;
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl);
if (!pte) {
result = SCAN_PMD_NULL;
goto out;
}
for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
_pte++, addr += PAGE_SIZE) {
pte_t pteval = ptep_get(_pte);
if (is_swap_pte(pteval)) {
++unmapped;
if (!cc->is_khugepaged ||
unmapped <= khugepaged_max_ptes_swap) {
if (pte_swp_uffd_wp_any(pteval)) {
result = SCAN_PTE_UFFD_WP;
goto out_unmap;
}
continue;
} else {
result = SCAN_EXCEED_SWAP_PTE;
count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
goto out_unmap;
}
}
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
++none_or_zero;
if (!userfaultfd_armed(vma) &&
(!cc->is_khugepaged ||
none_or_zero <= khugepaged_max_ptes_none)) {
continue;
} else {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
goto out_unmap;
}
}
if (pte_uffd_wp(pteval)) {
result = SCAN_PTE_UFFD_WP;
goto out_unmap;
}
page = vm_normal_page(vma, addr, pteval);
if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
result = SCAN_PAGE_NULL;
goto out_unmap;
}
folio = page_folio(page);
if (!folio_test_anon(folio)) {
result = SCAN_PAGE_ANON;
goto out_unmap;
}
if (folio_maybe_mapped_shared(folio)) {
++shared;
if (cc->is_khugepaged &&
shared > khugepaged_max_ptes_shared) {
result = SCAN_EXCEED_SHARED_PTE;
count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
goto out_unmap;
}
}
node = folio_nid(folio);
if (hpage_collapse_scan_abort(node, cc)) {
result = SCAN_SCAN_ABORT;
goto out_unmap;
}
cc->node_load[node]++;
if (!folio_test_lru(folio)) {
result = SCAN_PAGE_LRU;
goto out_unmap;
}
if (folio_test_locked(folio)) {
result = SCAN_PAGE_LOCK;
goto out_unmap;
}
if (folio_expected_ref_count(folio) != folio_ref_count(folio)) {
result = SCAN_PAGE_COUNT;
goto out_unmap;
}
if (cc->is_khugepaged &&
(pte_young(pteval) || folio_test_young(folio) ||
folio_test_referenced(folio) ||
mmu_notifier_test_young(vma->vm_mm, addr)))
referenced++;
}
if (cc->is_khugepaged &&
(!referenced ||
(unmapped && referenced < HPAGE_PMD_NR / 2))) {
result = SCAN_LACK_REFERENCED_PAGE;
} else {
result = SCAN_SUCCEED;
}
out_unmap:
pte_unmap_unlock(pte, ptl);
if (result == SCAN_SUCCEED) {
result = collapse_huge_page(mm, start_addr, referenced,
unmapped, cc);
*mmap_locked = false;
}
out:
trace_mm_khugepaged_scan_pmd(mm, folio, referenced,
none_or_zero, result, unmapped);
return result;
}
static void collect_mm_slot(struct mm_slot *slot)
{
struct mm_struct *mm = slot->mm;
lockdep_assert_held(&khugepaged_mm_lock);
if (hpage_collapse_test_exit(mm)) {
hash_del(&slot->hash);
list_del(&slot->mm_node);
mm_slot_free(mm_slot_cache, slot);
mmdrop(mm);
}
}
static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmdp, struct folio *folio, struct page *page)
{
struct mm_struct *mm = vma->vm_mm;
struct vm_fault vmf = {
.vma = vma,
.address = addr,
.flags = 0,
};
pgd_t *pgdp;
p4d_t *p4dp;
pud_t *pudp;
mmap_assert_locked(vma->vm_mm);
if (!pmdp) {
pgdp = pgd_offset(mm, addr);
p4dp = p4d_alloc(mm, pgdp, addr);
if (!p4dp)
return SCAN_FAIL;
pudp = pud_alloc(mm, p4dp, addr);
if (!pudp)
return SCAN_FAIL;
pmdp = pmd_alloc(mm, pudp, addr);
if (!pmdp)
return SCAN_FAIL;
}
vmf.pmd = pmdp;
if (do_set_pmd(&vmf, folio, page))
return SCAN_FAIL;
folio_get(folio);
return SCAN_SUCCEED;
}
int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
bool install_pmd)
{
int nr_mapped_ptes = 0, result = SCAN_FAIL;
unsigned int nr_batch_ptes;
struct mmu_notifier_range range;
bool notified = false;
unsigned long haddr = addr & HPAGE_PMD_MASK;
unsigned long end = haddr + HPAGE_PMD_SIZE;
struct vm_area_struct *vma = vma_lookup(mm, haddr);
struct folio *folio;
pte_t *start_pte, *pte;
pmd_t *pmd, pgt_pmd;
spinlock_t *pml = NULL, *ptl;
int i;
mmap_assert_locked(mm);
if (!vma || !vma->vm_file ||
!range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE))
return SCAN_VMA_CHECK;
result = find_pmd_or_thp_or_none(mm, haddr, &pmd);
if (result == SCAN_PMD_MAPPED)
return result;
if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_FORCED_COLLAPSE, PMD_ORDER))
return SCAN_VMA_CHECK;
if (userfaultfd_wp(vma))
return SCAN_PTE_UFFD_WP;
folio = filemap_lock_folio(vma->vm_file->f_mapping,
linear_page_index(vma, haddr));
if (IS_ERR(folio))
return SCAN_PAGE_NULL;
if (folio_order(folio) != HPAGE_PMD_ORDER) {
result = SCAN_PAGE_COMPOUND;
goto drop_folio;
}
result = find_pmd_or_thp_or_none(mm, haddr, &pmd);
switch (result) {
case SCAN_SUCCEED:
break;
case SCAN_PMD_NULL:
case SCAN_PMD_NONE:
goto maybe_install_pmd;
default:
goto drop_folio;
}
result = SCAN_FAIL;
start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
if (!start_pte)
goto drop_folio;
for (i = 0, addr = haddr, pte = start_pte;
i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
struct page *page;
pte_t ptent = ptep_get(pte);
if (pte_none(ptent))
continue;
if (!pte_present(ptent)) {
result = SCAN_PTE_NON_PRESENT;
goto abort;
}
page = vm_normal_page(vma, addr, ptent);
if (WARN_ON_ONCE(page && is_zone_device_page(page)))
page = NULL;
if (folio_page(folio, i) != page)
goto abort;
}
pte_unmap_unlock(start_pte, ptl);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
haddr, haddr + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
notified = true;
if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED))
pml = pmd_lock(mm, pmd);
start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl);
if (!start_pte)
goto abort;
if (!pml)
spin_lock(ptl);
else if (ptl != pml)
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd))))
goto abort;
for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR;
i += nr_batch_ptes, addr += nr_batch_ptes * PAGE_SIZE,
pte += nr_batch_ptes) {
unsigned int max_nr_batch_ptes = (end - addr) >> PAGE_SHIFT;
struct page *page;
pte_t ptent = ptep_get(pte);
nr_batch_ptes = 1;
if (pte_none(ptent))
continue;
if (!pte_present(ptent)) {
result = SCAN_PTE_NON_PRESENT;
goto abort;
}
page = vm_normal_page(vma, addr, ptent);
if (folio_page(folio, i) != page)
goto abort;
nr_batch_ptes = folio_pte_batch(folio, pte, ptent, max_nr_batch_ptes);
clear_ptes(mm, addr, pte, nr_batch_ptes);
folio_remove_rmap_ptes(folio, page, nr_batch_ptes, vma);
nr_mapped_ptes += nr_batch_ptes;
}
if (!pml)
spin_unlock(ptl);
if (nr_mapped_ptes) {
folio_ref_sub(folio, nr_mapped_ptes);
add_mm_counter(mm, mm_counter_file(folio), -nr_mapped_ptes);
}
if (!pml) {
pml = pmd_lock(mm, pmd);
if (ptl != pml) {
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) {
flush_tlb_mm(mm);
goto unlock;
}
}
}
pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd);
pmdp_get_lockless_sync();
pte_unmap_unlock(start_pte, ptl);
if (ptl != pml)
spin_unlock(pml);
mmu_notifier_invalidate_range_end(&range);
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, haddr, pgt_pmd);
pte_free_defer(mm, pmd_pgtable(pgt_pmd));
maybe_install_pmd:
result = install_pmd
? set_huge_pmd(vma, haddr, pmd, folio, &folio->page)
: SCAN_SUCCEED;
goto drop_folio;
abort:
if (nr_mapped_ptes) {
flush_tlb_mm(mm);
folio_ref_sub(folio, nr_mapped_ptes);
add_mm_counter(mm, mm_counter_file(folio), -nr_mapped_ptes);
}
unlock:
if (start_pte)
pte_unmap_unlock(start_pte, ptl);
if (pml && pml != ptl)
spin_unlock(pml);
if (notified)
mmu_notifier_invalidate_range_end(&range);
drop_folio:
folio_unlock(folio);
folio_put(folio);
return result;
}
static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
{
struct vm_area_struct *vma;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
struct mmu_notifier_range range;
struct mm_struct *mm;
unsigned long addr;
pmd_t *pmd, pgt_pmd;
spinlock_t *pml;
spinlock_t *ptl;
bool success = false;
if (READ_ONCE(vma->anon_vma))
continue;
addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
if (addr & ~HPAGE_PMD_MASK ||
vma->vm_end < addr + HPAGE_PMD_SIZE)
continue;
mm = vma->vm_mm;
if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED)
continue;
if (hpage_collapse_test_exit(mm))
continue;
if (userfaultfd_wp(vma))
continue;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
addr, addr + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
pml = pmd_lock(mm, pmd);
if (check_pmd_state(pmd) != SCAN_SUCCEED)
goto drop_pml;
ptl = pte_lockptr(mm, pmd);
if (ptl != pml)
spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) {
pgt_pmd = pmdp_collapse_flush(vma, addr, pmd);
pmdp_get_lockless_sync();
success = true;
}
if (ptl != pml)
spin_unlock(ptl);
drop_pml:
spin_unlock(pml);
mmu_notifier_invalidate_range_end(&range);
if (success) {
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, addr, pgt_pmd);
pte_free_defer(mm, pmd_pgtable(pgt_pmd));
}
}
i_mmap_unlock_read(mapping);
}
static int collapse_file(struct mm_struct *mm, unsigned long addr,
struct file *file, pgoff_t start,
struct collapse_control *cc)
{
struct address_space *mapping = file->f_mapping;
struct page *dst;
struct folio *folio, *tmp, *new_folio;
pgoff_t index = 0, end = start + HPAGE_PMD_NR;
LIST_HEAD(pagelist);
XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
int nr_none = 0, result = SCAN_SUCCEED;
bool is_shmem = shmem_file(file);
VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
result = alloc_charge_folio(&new_folio, mm, cc);
if (result != SCAN_SUCCEED)
goto out;
mapping_set_update(&xas, mapping);
__folio_set_locked(new_folio);
if (is_shmem)
__folio_set_swapbacked(new_folio);
new_folio->index = start;
new_folio->mapping = mapping;
do {
xas_lock_irq(&xas);
xas_create_range(&xas);
if (!xas_error(&xas))
break;
xas_unlock_irq(&xas);
if (!xas_nomem(&xas, GFP_KERNEL)) {
result = SCAN_FAIL;
goto rollback;
}
} while (1);
for (index = start; index < end;) {
xas_set(&xas, index);
folio = xas_load(&xas);
VM_BUG_ON(index != xas.xa_index);
if (is_shmem) {
if (!folio) {
if (index == start) {
if (!xas_next_entry(&xas, end - 1)) {
result = SCAN_TRUNCATED;
goto xa_locked;
}
}
nr_none++;
index++;
continue;
}
if (xa_is_value(folio) || !folio_test_uptodate(folio)) {
xas_unlock_irq(&xas);
if (shmem_get_folio(mapping->host, index, 0,
&folio, SGP_NOALLOC)) {
result = SCAN_FAIL;
goto xa_unlocked;
}
lru_add_drain();
} else if (folio_trylock(folio)) {
folio_get(folio);
xas_unlock_irq(&xas);
} else {
result = SCAN_PAGE_LOCK;
goto xa_locked;
}
} else {
if (!folio || xa_is_value(folio)) {
xas_unlock_irq(&xas);
page_cache_sync_readahead(mapping, &file->f_ra,
file, index,
end - index);
lru_add_drain();
folio = filemap_lock_folio(mapping, index);
if (IS_ERR(folio)) {
result = SCAN_FAIL;
goto xa_unlocked;
}
} else if (folio_test_dirty(folio)) {
xas_unlock_irq(&xas);
filemap_flush(mapping);
result = SCAN_FAIL;
goto xa_unlocked;
} else if (folio_test_writeback(folio)) {
xas_unlock_irq(&xas);
result = SCAN_FAIL;
goto xa_unlocked;
} else if (folio_trylock(folio)) {
folio_get(folio);
xas_unlock_irq(&xas);
} else {
result = SCAN_PAGE_LOCK;
goto xa_locked;
}
}
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (unlikely(!folio_test_uptodate(folio))) {
result = SCAN_FAIL;
goto out_unlock;
}
if (folio_order(folio) == HPAGE_PMD_ORDER &&
folio->index == start) {
result = SCAN_PTE_MAPPED_HUGEPAGE;
goto out_unlock;
}
if (folio_mapping(folio) != mapping) {
result = SCAN_TRUNCATED;
goto out_unlock;
}
if (!is_shmem && (folio_test_dirty(folio) ||
folio_test_writeback(folio))) {
result = SCAN_FAIL;
goto out_unlock;
}
if (!folio_isolate_lru(folio)) {
result = SCAN_DEL_PAGE_LRU;
goto out_unlock;
}
if (!filemap_release_folio(folio, GFP_KERNEL)) {
result = SCAN_PAGE_HAS_PRIVATE;
folio_putback_lru(folio);
goto out_unlock;
}
if (folio_mapped(folio))
try_to_unmap(folio,
TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH);
xas_lock_irq(&xas);
VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio);
if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) {
result = SCAN_PAGE_COUNT;
xas_unlock_irq(&xas);
folio_putback_lru(folio);
goto out_unlock;
}
list_add_tail(&folio->lru, &pagelist);
index += folio_nr_pages(folio);
continue;
out_unlock:
folio_unlock(folio);
folio_put(folio);
goto xa_unlocked;
}
if (!is_shmem) {
filemap_nr_thps_inc(mapping);
smp_mb();
if (inode_is_open_for_write(mapping->host)) {
result = SCAN_FAIL;
filemap_nr_thps_dec(mapping);
}
}
xa_locked:
xas_unlock_irq(&xas);
xa_unlocked:
try_to_unmap_flush();
if (result == SCAN_SUCCEED && nr_none &&
!shmem_charge(mapping->host, nr_none))
result = SCAN_FAIL;
if (result != SCAN_SUCCEED) {
nr_none = 0;
goto rollback;
}
index = start;
dst = folio_page(new_folio, 0);
list_for_each_entry(folio, &pagelist, lru) {
int i, nr_pages = folio_nr_pages(folio);
while (index < folio->index) {
clear_highpage(dst);
index++;
dst++;
}
for (i = 0; i < nr_pages; i++) {
if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) {
result = SCAN_COPY_MC;
goto rollback;
}
index++;
dst++;
}
}
while (index < end) {
clear_highpage(dst);
index++;
dst++;
}
if (nr_none) {
struct vm_area_struct *vma;
int nr_none_check = 0;
i_mmap_lock_read(mapping);
xas_lock_irq(&xas);
xas_set(&xas, start);
for (index = start; index < end; index++) {
if (!xas_next(&xas)) {
xas_store(&xas, XA_RETRY_ENTRY);
if (xas_error(&xas)) {
result = SCAN_STORE_FAILED;
goto immap_locked;
}
nr_none_check++;
}
}
if (nr_none != nr_none_check) {
result = SCAN_PAGE_FILLED;
goto immap_locked;
}
vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) {
if (userfaultfd_missing(vma)) {
result = SCAN_EXCEED_NONE_PTE;
goto immap_locked;
}
}
immap_locked:
i_mmap_unlock_read(mapping);
if (result != SCAN_SUCCEED) {
xas_set(&xas, start);
for (index = start; index < end; index++) {
if (xas_next(&xas) == XA_RETRY_ENTRY)
xas_store(&xas, NULL);
}
xas_unlock_irq(&xas);
goto rollback;
}
} else {
xas_lock_irq(&xas);
}
if (is_shmem)
__lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR);
else
__lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR);
if (nr_none) {
__lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none);
__lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none);
}
folio_mark_uptodate(new_folio);
folio_ref_add(new_folio, HPAGE_PMD_NR - 1);
if (is_shmem)
folio_mark_dirty(new_folio);
folio_add_lru(new_folio);
xas_set_order(&xas, start, HPAGE_PMD_ORDER);
xas_store(&xas, new_folio);
WARN_ON_ONCE(xas_error(&xas));
xas_unlock_irq(&xas);
retract_page_tables(mapping, start);
if (cc && !cc->is_khugepaged)
result = SCAN_PTE_MAPPED_HUGEPAGE;
folio_unlock(new_folio);
list_for_each_entry_safe(folio, tmp, &pagelist, lru) {
list_del(&folio->lru);
folio->mapping = NULL;
folio_clear_active(folio);
folio_clear_unevictable(folio);
folio_unlock(folio);
folio_put_refs(folio, 2 + folio_nr_pages(folio));
}
goto out;
rollback:
if (nr_none) {
xas_lock_irq(&xas);
mapping->nrpages -= nr_none;
xas_unlock_irq(&xas);
shmem_uncharge(mapping->host, nr_none);
}
list_for_each_entry_safe(folio, tmp, &pagelist, lru) {
list_del(&folio->lru);
folio_unlock(folio);
folio_putback_lru(folio);
folio_put(folio);
}
if (!is_shmem && result == SCAN_COPY_MC) {
filemap_nr_thps_dec(mapping);
smp_mb();
}
new_folio->mapping = NULL;
folio_unlock(new_folio);
folio_put(new_folio);
out:
VM_BUG_ON(!list_empty(&pagelist));
trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result);
return result;
}
static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
struct file *file, pgoff_t start,
struct collapse_control *cc)
{
struct folio *folio = NULL;
struct address_space *mapping = file->f_mapping;
XA_STATE(xas, &mapping->i_pages, start);
int present, swap;
int node = NUMA_NO_NODE;
int result = SCAN_SUCCEED;
present = 0;
swap = 0;
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
rcu_read_lock();
xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) {
if (xas_retry(&xas, folio))
continue;
if (xa_is_value(folio)) {
swap += 1 << xas_get_order(&xas);
if (cc->is_khugepaged &&
swap > khugepaged_max_ptes_swap) {
result = SCAN_EXCEED_SWAP_PTE;
count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
break;
}
continue;
}
if (!folio_try_get(folio)) {
xas_reset(&xas);
continue;
}
if (unlikely(folio != xas_reload(&xas))) {
folio_put(folio);
xas_reset(&xas);
continue;
}
if (folio_order(folio) == HPAGE_PMD_ORDER &&
folio->index == start) {
result = SCAN_PTE_MAPPED_HUGEPAGE;
folio_put(folio);
break;
}
node = folio_nid(folio);
if (hpage_collapse_scan_abort(node, cc)) {
result = SCAN_SCAN_ABORT;
folio_put(folio);
break;
}
cc->node_load[node]++;
if (!folio_test_lru(folio)) {
result = SCAN_PAGE_LRU;
folio_put(folio);
break;
}
if (folio_expected_ref_count(folio) + 1 != folio_ref_count(folio)) {
result = SCAN_PAGE_COUNT;
folio_put(folio);
break;
}
present += folio_nr_pages(folio);
folio_put(folio);
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
}
rcu_read_unlock();
if (result == SCAN_SUCCEED) {
if (cc->is_khugepaged &&
present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {
result = SCAN_EXCEED_NONE_PTE;
count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
} else {
result = collapse_file(mm, addr, file, start, cc);
}
}
trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result);
return result;
}
static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
struct collapse_control *cc)
__releases(&khugepaged_mm_lock)
__acquires(&khugepaged_mm_lock)
{
struct vma_iterator vmi;
struct mm_slot *slot;
struct mm_struct *mm;
struct vm_area_struct *vma;
int progress = 0;
VM_BUG_ON(!pages);
lockdep_assert_held(&khugepaged_mm_lock);
*result = SCAN_FAIL;
if (khugepaged_scan.mm_slot) {
slot = khugepaged_scan.mm_slot;
} else {
slot = list_first_entry(&khugepaged_scan.mm_head,
struct mm_slot, mm_node);
khugepaged_scan.address = 0;
khugepaged_scan.mm_slot = slot;
}
spin_unlock(&khugepaged_mm_lock);
mm = slot->mm;
vma = NULL;
if (unlikely(!mmap_read_trylock(mm)))
goto breakouterloop_mmap_lock;
progress++;
if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
goto breakouterloop;
vma_iter_init(&vmi, mm, khugepaged_scan.address);
for_each_vma(vmi, vma) {
unsigned long hstart, hend;
cond_resched();
if (unlikely(hpage_collapse_test_exit_or_disable(mm))) {
progress++;
break;
}
if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_KHUGEPAGED, PMD_ORDER)) {
skip:
progress++;
continue;
}
hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE);
hend = round_down(vma->vm_end, HPAGE_PMD_SIZE);
if (khugepaged_scan.address > hend)
goto skip;
if (khugepaged_scan.address < hstart)
khugepaged_scan.address = hstart;
VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
while (khugepaged_scan.address < hend) {
bool mmap_locked = true;
cond_resched();
if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
goto breakouterloop;
VM_BUG_ON(khugepaged_scan.address < hstart ||
khugepaged_scan.address + HPAGE_PMD_SIZE >
hend);
if (!vma_is_anonymous(vma)) {
struct file *file = get_file(vma->vm_file);
pgoff_t pgoff = linear_page_index(vma,
khugepaged_scan.address);
mmap_read_unlock(mm);
mmap_locked = false;
*result = hpage_collapse_scan_file(mm,
khugepaged_scan.address, file, pgoff, cc);
fput(file);
if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
mmap_read_lock(mm);
if (hpage_collapse_test_exit_or_disable(mm))
goto breakouterloop;
*result = collapse_pte_mapped_thp(mm,
khugepaged_scan.address, false);
if (*result == SCAN_PMD_MAPPED)
*result = SCAN_SUCCEED;
mmap_read_unlock(mm);
}
} else {
*result = hpage_collapse_scan_pmd(mm, vma,
khugepaged_scan.address, &mmap_locked, cc);
}
if (*result == SCAN_SUCCEED)
++khugepaged_pages_collapsed;
khugepaged_scan.address += HPAGE_PMD_SIZE;
progress += HPAGE_PMD_NR;
if (!mmap_locked)
goto breakouterloop_mmap_lock;
if (progress >= pages)
goto breakouterloop;
}
}
breakouterloop:
mmap_read_unlock(mm);
breakouterloop_mmap_lock:
spin_lock(&khugepaged_mm_lock);
VM_BUG_ON(khugepaged_scan.mm_slot != slot);
if (hpage_collapse_test_exit(mm) || !vma) {
if (!list_is_last(&slot->mm_node, &khugepaged_scan.mm_head)) {
khugepaged_scan.mm_slot = list_next_entry(slot, mm_node);
khugepaged_scan.address = 0;
} else {
khugepaged_scan.mm_slot = NULL;
khugepaged_full_scans++;
}
collect_mm_slot(slot);
}
return progress;
}
static int khugepaged_has_work(void)
{
return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
}
static int khugepaged_wait_event(void)
{
return !list_empty(&khugepaged_scan.mm_head) ||
kthread_should_stop();
}
static void khugepaged_do_scan(struct collapse_control *cc)
{
unsigned int progress = 0, pass_through_head = 0;
unsigned int pages = READ_ONCE(khugepaged_pages_to_scan);
bool wait = true;
int result = SCAN_SUCCEED;
lru_add_drain_all();
while (true) {
cond_resched();
if (unlikely(kthread_should_stop()))
break;
spin_lock(&khugepaged_mm_lock);
if (!khugepaged_scan.mm_slot)
pass_through_head++;
if (khugepaged_has_work() &&
pass_through_head < 2)
progress += khugepaged_scan_mm_slot(pages - progress,
&result, cc);
else
progress = pages;
spin_unlock(&khugepaged_mm_lock);
if (progress >= pages)
break;
if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) {
if (!wait)
break;
wait = false;
khugepaged_alloc_sleep();
}
}
}
static bool khugepaged_should_wakeup(void)
{
return kthread_should_stop() ||
time_after_eq(jiffies, khugepaged_sleep_expire);
}
static void khugepaged_wait_work(void)
{
if (khugepaged_has_work()) {
const unsigned long scan_sleep_jiffies =
msecs_to_jiffies(khugepaged_scan_sleep_millisecs);
if (!scan_sleep_jiffies)
return;
khugepaged_sleep_expire = jiffies + scan_sleep_jiffies;
wait_event_freezable_timeout(khugepaged_wait,
khugepaged_should_wakeup(),
scan_sleep_jiffies);
return;
}
if (hugepage_pmd_enabled())
wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
}
static int khugepaged(void *none)
{
struct mm_slot *slot;
set_freezable();
set_user_nice(current, MAX_NICE);
while (!kthread_should_stop()) {
khugepaged_do_scan(&khugepaged_collapse_control);
khugepaged_wait_work();
}
spin_lock(&khugepaged_mm_lock);
slot = khugepaged_scan.mm_slot;
khugepaged_scan.mm_slot = NULL;
if (slot)
collect_mm_slot(slot);
spin_unlock(&khugepaged_mm_lock);
return 0;
}
static void set_recommended_min_free_kbytes(void)
{
struct zone *zone;
int nr_zones = 0;
unsigned long recommended_min;
if (!hugepage_pmd_enabled()) {
calculate_min_free_kbytes();
goto update_wmarks;
}
for_each_populated_zone(zone) {
if (zone_idx(zone) > gfp_zone(GFP_USER))
continue;
nr_zones++;
}
recommended_min = pageblock_nr_pages * nr_zones * 2;
recommended_min += pageblock_nr_pages * nr_zones *
MIGRATE_PCPTYPES * MIGRATE_PCPTYPES;
recommended_min = min(recommended_min,
(unsigned long) nr_free_buffer_pages() / 20);
recommended_min <<= (PAGE_SHIFT-10);
if (recommended_min > min_free_kbytes) {
if (user_min_free_kbytes >= 0)
pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n",
min_free_kbytes, recommended_min);
min_free_kbytes = recommended_min;
}
update_wmarks:
setup_per_zone_wmarks();
}
int start_stop_khugepaged(void)
{
int err = 0;
mutex_lock(&khugepaged_mutex);
if (hugepage_pmd_enabled()) {
if (!khugepaged_thread)
khugepaged_thread = kthread_run(khugepaged, NULL,
"khugepaged");
if (IS_ERR(khugepaged_thread)) {
pr_err("khugepaged: kthread_run(khugepaged) failed\n");
err = PTR_ERR(khugepaged_thread);
khugepaged_thread = NULL;
goto fail;
}
if (!list_empty(&khugepaged_scan.mm_head))
wake_up_interruptible(&khugepaged_wait);
} else if (khugepaged_thread) {
kthread_stop(khugepaged_thread);
khugepaged_thread = NULL;
}
set_recommended_min_free_kbytes();
fail:
mutex_unlock(&khugepaged_mutex);
return err;
}
void khugepaged_min_free_kbytes_update(void)
{
mutex_lock(&khugepaged_mutex);
if (hugepage_pmd_enabled() && khugepaged_thread)
set_recommended_min_free_kbytes();
mutex_unlock(&khugepaged_mutex);
}
bool current_is_khugepaged(void)
{
return kthread_func(current) == khugepaged;
}
static int madvise_collapse_errno(enum scan_result r)
{
switch (r) {
case SCAN_ALLOC_HUGE_PAGE_FAIL:
return -ENOMEM;
case SCAN_CGROUP_CHARGE_FAIL:
case SCAN_EXCEED_NONE_PTE:
return -EBUSY;
case SCAN_PAGE_COUNT:
case SCAN_PAGE_LOCK:
case SCAN_PAGE_LRU:
case SCAN_DEL_PAGE_LRU:
case SCAN_PAGE_FILLED:
return -EAGAIN;
default:
return -EINVAL;
}
}
int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
unsigned long end, bool *lock_dropped)
{
struct collapse_control *cc;
struct mm_struct *mm = vma->vm_mm;
unsigned long hstart, hend, addr;
int thps = 0, last_fail = SCAN_FAIL;
bool mmap_locked = true;
BUG_ON(vma->vm_start > start);
BUG_ON(vma->vm_end < end);
if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_FORCED_COLLAPSE, PMD_ORDER))
return -EINVAL;
cc = kmalloc(sizeof(*cc), GFP_KERNEL);
if (!cc)
return -ENOMEM;
cc->is_khugepaged = false;
mmgrab(mm);
lru_add_drain_all();
hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = end & HPAGE_PMD_MASK;
for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) {
int result = SCAN_FAIL;
if (!mmap_locked) {
cond_resched();
mmap_read_lock(mm);
mmap_locked = true;
result = hugepage_vma_revalidate(mm, addr, false, &vma,
cc);
if (result != SCAN_SUCCEED) {
last_fail = result;
goto out_nolock;
}
hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
}
mmap_assert_locked(mm);
memset(cc->node_load, 0, sizeof(cc->node_load));
nodes_clear(cc->alloc_nmask);
if (!vma_is_anonymous(vma)) {
struct file *file = get_file(vma->vm_file);
pgoff_t pgoff = linear_page_index(vma, addr);
mmap_read_unlock(mm);
mmap_locked = false;
result = hpage_collapse_scan_file(mm, addr, file, pgoff,
cc);
fput(file);
} else {
result = hpage_collapse_scan_pmd(mm, vma, addr,
&mmap_locked, cc);
}
if (!mmap_locked)
*lock_dropped = true;
handle_result:
switch (result) {
case SCAN_SUCCEED:
case SCAN_PMD_MAPPED:
++thps;
break;
case SCAN_PTE_MAPPED_HUGEPAGE:
BUG_ON(mmap_locked);
mmap_read_lock(mm);
result = collapse_pte_mapped_thp(mm, addr, true);
mmap_read_unlock(mm);
goto handle_result;
case SCAN_PMD_NULL:
case SCAN_PTE_NON_PRESENT:
case SCAN_PTE_UFFD_WP:
case SCAN_LACK_REFERENCED_PAGE:
case SCAN_PAGE_NULL:
case SCAN_PAGE_COUNT:
case SCAN_PAGE_LOCK:
case SCAN_PAGE_COMPOUND:
case SCAN_PAGE_LRU:
case SCAN_DEL_PAGE_LRU:
last_fail = result;
break;
default:
last_fail = result;
goto out_maybelock;
}
}
out_maybelock:
if (!mmap_locked)
mmap_read_lock(mm);
out_nolock:
mmap_assert_locked(mm);
mmdrop(mm);
kfree(cc);
return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0
: madvise_collapse_errno(last_fail);
}
