diff options
Diffstat (limited to 'mm/huge_memory.c')
| -rw-r--r-- | mm/huge_memory.c | 6238 |
1 files changed, 4201 insertions, 2037 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 243e710c6039..f7c565f11a98 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1,12 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 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. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mmu_notifier.h> @@ -14,24 +16,45 @@ #include <linux/swap.h> #include <linux/shrinker.h> #include <linux/mm_inline.h> -#include <linux/kthread.h> +#include <linux/swapops.h> +#include <linux/backing-dev.h> +#include <linux/dax.h> +#include <linux/mm_types.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> +#include <linux/memremap.h> #include <linux/pagemap.h> +#include <linux/debugfs.h> #include <linux/migrate.h> #include <linux/hashtable.h> +#include <linux/userfaultfd_k.h> +#include <linux/page_idle.h> +#include <linux/shmem_fs.h> +#include <linux/oom.h> +#include <linux/numa.h> +#include <linux/page_owner.h> +#include <linux/sched/sysctl.h> +#include <linux/memory-tiers.h> +#include <linux/compat.h> +#include <linux/pgalloc.h> +#include <linux/pgalloc_tag.h> +#include <linux/pagewalk.h> #include <asm/tlb.h> -#include <asm/pgalloc.h> #include "internal.h" +#include "swap.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/thp.h> /* - * 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. + * By default, transparent hugepage support is disabled in order to avoid + * risking an increased memory footprint for applications that are not + * guaranteed to benefit from it. When transparent hugepage support is + * enabled, it 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 @@ -40,169 +63,182 @@ unsigned long transparent_hugepage_flags __read_mostly = #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)| #endif - (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)| + (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)| (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); +static struct shrinker *deferred_split_shrinker; +static unsigned long deferred_split_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long deferred_split_scan(struct shrinker *shrink, + struct shrink_control *sc); +static bool split_underused_thp = true; -#define MM_SLOTS_HASH_BITS 10 -static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); +static atomic_t huge_zero_refcount; +struct folio *huge_zero_folio __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL; +unsigned long huge_anon_orders_always __read_mostly; +unsigned long huge_anon_orders_madvise __read_mostly; +unsigned long huge_anon_orders_inherit __read_mostly; +static bool anon_orders_configured __initdata; + +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + struct inode *inode; -static struct kmem_cache *mm_slot_cache __read_mostly; + if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return false; -/** - * 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; -}; + if (!vma->vm_file) + return false; -/** - * 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), -}; + inode = file_inode(vma->vm_file); + return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); +} -static int set_recommended_min_free_kbytes(void) +unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, + vm_flags_t vm_flags, + enum tva_type type, + unsigned long orders) { - struct zone *zone; - int nr_zones = 0; - unsigned long recommended_min; + const bool smaps = type == TVA_SMAPS; + const bool in_pf = type == TVA_PAGEFAULT; + const bool forced_collapse = type == TVA_FORCED_COLLAPSE; + unsigned long supported_orders; + + /* Check the intersection of requested and supported orders. */ + if (vma_is_anonymous(vma)) + supported_orders = THP_ORDERS_ALL_ANON; + else if (vma_is_special_huge(vma)) + supported_orders = THP_ORDERS_ALL_SPECIAL; + else + supported_orders = THP_ORDERS_ALL_FILE_DEFAULT; - if (!khugepaged_enabled()) + orders &= supported_orders; + if (!orders) return 0; - for_each_populated_zone(zone) - nr_zones++; + if (!vma->vm_mm) /* vdso */ + return 0; + + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags, forced_collapse)) + return 0; - /* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */ - recommended_min = pageblock_nr_pages * nr_zones * 2; + /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ + if (vma_is_dax(vma)) + return in_pf ? orders : 0; /* - * 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. + * khugepaged special VMA and hugetlb VMA. + * Must be checked after dax since some dax mappings may have + * VM_MIXEDMAP set. */ - recommended_min += pageblock_nr_pages * nr_zones * - MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; + if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED)) + return 0; - /* 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); + /* + * Check alignment for file vma and size for both file and anon vma by + * filtering out the unsuitable orders. + * + * Skip the check for page fault. Huge fault does the check in fault + * handlers. + */ + if (!in_pf) { + int order = highest_order(orders); + unsigned long addr; + + while (orders) { + addr = vma->vm_end - (PAGE_SIZE << order); + if (thp_vma_suitable_order(vma, addr, order)) + break; + order = next_order(&orders, order); + } - if (recommended_min > min_free_kbytes) - min_free_kbytes = recommended_min; - setup_per_zone_wmarks(); - return 0; -} -late_initcall(set_recommended_min_free_kbytes); + if (!orders) + return 0; + } -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; - } + /* + * Enabled via shmem mount options or sysfs settings. + * Must be done before hugepage flags check since shmem has its + * own flags. + */ + if (!in_pf && shmem_file(vma->vm_file)) + return orders & shmem_allowable_huge_orders(file_inode(vma->vm_file), + vma, vma->vm_pgoff, 0, + forced_collapse); - if (!list_empty(&khugepaged_scan.mm_head)) - wake_up_interruptible(&khugepaged_wait); + if (!vma_is_anonymous(vma)) { + /* + * Enforce THP collapse requirements as necessary. Anonymous vmas + * were already handled in thp_vma_allowable_orders(). + */ + if (!forced_collapse && + (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) && + !hugepage_global_always()))) + return 0; - set_recommended_min_free_kbytes(); - } else if (khugepaged_thread) { - kthread_stop(khugepaged_thread); - khugepaged_thread = NULL; + /* + * Trust that ->huge_fault() handlers know what they are doing + * in fault path. + */ + if (((in_pf || smaps)) && vma->vm_ops->huge_fault) + return orders; + /* Only regular file is valid in collapse path */ + if (((!in_pf || smaps)) && file_thp_enabled(vma)) + return orders; + return 0; } - return err; -} - -static atomic_t huge_zero_refcount; -static struct page *huge_zero_page __read_mostly; + if (vma_is_temporary_stack(vma)) + return 0; -static inline bool is_huge_zero_page(struct page *page) -{ - return ACCESS_ONCE(huge_zero_page) == page; -} + /* + * THPeligible bit of smaps should show 1 for proper VMAs even + * though anon_vma is not initialized yet. + * + * Allow page fault since anon_vma may be not initialized until + * the first page fault. + */ + if (!vma->anon_vma) + return (smaps || in_pf) ? orders : 0; -static inline bool is_huge_zero_pmd(pmd_t pmd) -{ - return is_huge_zero_page(pmd_page(pmd)); + return orders; } -static struct page *get_huge_zero_page(void) +static bool get_huge_zero_folio(void) { - struct page *zero_page; + struct folio *zero_folio; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) - return ACCESS_ONCE(huge_zero_page); + return true; - zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, + zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO | __GFP_ZEROTAGS) & + ~__GFP_MOVABLE, HPAGE_PMD_ORDER); - if (!zero_page) { + if (!zero_folio) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); - return NULL; + return false; } - count_vm_event(THP_ZERO_PAGE_ALLOC); + /* Ensure zero folio won't have large_rmappable flag set. */ + folio_clear_large_rmappable(zero_folio); preempt_disable(); - if (cmpxchg(&huge_zero_page, NULL, zero_page)) { + if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) { preempt_enable(); - __free_page(zero_page); + folio_put(zero_folio); goto retry; } + WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio)); /* 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); + count_vm_event(THP_ZERO_PAGE_ALLOC); + return true; } -static void put_huge_zero_page(void) +static void put_huge_zero_folio(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -211,108 +247,109 @@ static void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } -static int shrink_huge_zero_page(struct shrinker *shrink, - struct shrink_control *sc) +struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) { - if (!sc->nr_to_scan) - /* we can free zero page only if last reference remains */ - return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; + if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) + return huge_zero_folio; - 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); - } + if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm)) + return READ_ONCE(huge_zero_folio); - return 0; + if (!get_huge_zero_folio()) + return NULL; + + if (mm_flags_test_and_set(MMF_HUGE_ZERO_FOLIO, mm)) + put_huge_zero_folio(); + + return READ_ONCE(huge_zero_folio); } -static struct shrinker huge_zero_page_shrinker = { - .shrink = shrink_huge_zero_page, - .seeks = DEFAULT_SEEKS, -}; +void mm_put_huge_zero_folio(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) + return; -#ifdef CONFIG_SYSFS + if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm)) + put_huge_zero_folio(); +} -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) +static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink, + struct shrink_control *sc) { - 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"); + /* we can free zero page only if last reference remains */ + return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; } -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 unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { + struct folio *zero_folio = xchg(&huge_zero_folio, NULL); + BUG_ON(zero_folio == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); + folio_put(zero_folio); + return HPAGE_PMD_NR; + } + + return 0; } +static struct shrinker *huge_zero_folio_shrinker; + +#ifdef CONFIG_SYSFS 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); + const char *output; + + if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags)) + output = "[always] madvise never"; + else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + &transparent_hugepage_flags)) + output = "always [madvise] never"; + else + output = "always madvise [never]"; + + return sysfs_emit(buf, "%s\n", output); } + 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); + ssize_t ret = count; + + if (sysfs_streq(buf, "always")) { + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "never")) { + clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else + ret = -EINVAL; if (ret > 0) { - int err; - - mutex_lock(&khugepaged_mutex); - err = start_khugepaged(); - mutex_unlock(&khugepaged_mutex); - + int err = start_stop_khugepaged(); if (err) ret = err; } - return ret; } -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) +static struct kobj_attribute enabled_attr = __ATTR_RW(enabled); + +ssize_t single_hugepage_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)); + return sysfs_emit(buf, "%d\n", + !!test_bit(flag, &transparent_hugepage_flags)); } -static ssize_t single_flag_store(struct kobject *kobj, +ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) @@ -334,262 +371,458 @@ static ssize_t single_flag_store(struct kobject *kobj, 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); + const char *output; + + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, + &transparent_hugepage_flags)) + output = "[always] defer defer+madvise madvise never"; + else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, + &transparent_hugepage_flags)) + output = "always [defer] defer+madvise madvise never"; + else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, + &transparent_hugepage_flags)) + output = "always defer [defer+madvise] madvise never"; + else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, + &transparent_hugepage_flags)) + output = "always defer defer+madvise [madvise] never"; + else + output = "always defer defer+madvise madvise [never]"; + + return sysfs_emit(buf, "%s\n", output); } + 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); + if (sysfs_streq(buf, "always")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "defer+madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "defer")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "madvise")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else if (sysfs_streq(buf, "never")) { + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); + clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); + } else + return -EINVAL; + + return count; } -static struct kobj_attribute defrag_attr = - __ATTR(defrag, 0644, defrag_show, defrag_store); +static struct kobj_attribute defrag_attr = __ATTR_RW(defrag); static ssize_t use_zero_page_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { - return single_flag_show(kobj, attr, buf, - TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); + return single_hugepage_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, + return single_hugepage_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) +static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page); + +static ssize_t hpage_pmd_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return single_flag_show(kobj, attr, buf, - TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); + return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE); } -static ssize_t debug_cow_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static struct kobj_attribute hpage_pmd_size_attr = + __ATTR_RO(hpage_pmd_size); + +static ssize_t split_underused_thp_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return single_flag_store(kobj, attr, buf, count, - TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); + return sysfs_emit(buf, "%d\n", split_underused_thp); } -static struct kobj_attribute debug_cow_attr = - __ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store); -#endif /* CONFIG_DEBUG_VM */ + +static ssize_t split_underused_thp_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err = kstrtobool(buf, &split_underused_thp); + + if (err < 0) + return err; + + return count; +} + +static struct kobj_attribute split_underused_thp_attr = __ATTR( + shrink_underused, 0644, split_underused_thp_show, split_underused_thp_store); static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, &use_zero_page_attr.attr, -#ifdef CONFIG_DEBUG_VM - &debug_cow_attr.attr, + &hpage_pmd_size_attr.attr, +#ifdef CONFIG_SHMEM + &shmem_enabled_attr.attr, #endif + &split_underused_thp_attr.attr, NULL, }; -static struct attribute_group hugepage_attr_group = { +static const 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) +static void hugepage_exit_sysfs(struct kobject *hugepage_kobj); +static void thpsize_release(struct kobject *kobj); +static DEFINE_SPINLOCK(huge_anon_orders_lock); +static LIST_HEAD(thpsize_list); + +static ssize_t anon_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); + int order = to_thpsize(kobj)->order; + const char *output; + + if (test_bit(order, &huge_anon_orders_always)) + output = "[always] inherit madvise never"; + else if (test_bit(order, &huge_anon_orders_inherit)) + output = "always [inherit] madvise never"; + else if (test_bit(order, &huge_anon_orders_madvise)) + output = "always inherit [madvise] never"; + else + output = "always inherit madvise [never]"; + + return sysfs_emit(buf, "%s\n", output); } -static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static ssize_t anon_enabled_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; + int order = to_thpsize(kobj)->order; + ssize_t ret = count; + + if (sysfs_streq(buf, "always")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_inherit); + clear_bit(order, &huge_anon_orders_madvise); + set_bit(order, &huge_anon_orders_always); + spin_unlock(&huge_anon_orders_lock); + } else if (sysfs_streq(buf, "inherit")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_always); + clear_bit(order, &huge_anon_orders_madvise); + set_bit(order, &huge_anon_orders_inherit); + spin_unlock(&huge_anon_orders_lock); + } else if (sysfs_streq(buf, "madvise")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_always); + clear_bit(order, &huge_anon_orders_inherit); + set_bit(order, &huge_anon_orders_madvise); + spin_unlock(&huge_anon_orders_lock); + } else if (sysfs_streq(buf, "never")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_always); + clear_bit(order, &huge_anon_orders_inherit); + clear_bit(order, &huge_anon_orders_madvise); + spin_unlock(&huge_anon_orders_lock); + } else + ret = -EINVAL; - khugepaged_scan_sleep_millisecs = msecs; - wake_up_interruptible(&khugepaged_wait); + if (ret > 0) { + int err; - return count; + err = start_stop_khugepaged(); + if (err) + ret = err; + } + return ret; } -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 struct kobj_attribute anon_enabled_attr = + __ATTR(enabled, 0644, anon_enabled_show, anon_enabled_store); -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; +static struct attribute *anon_ctrl_attrs[] = { + &anon_enabled_attr.attr, + NULL, +}; - err = strict_strtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) - return -EINVAL; +static const struct attribute_group anon_ctrl_attr_grp = { + .attrs = anon_ctrl_attrs, +}; - khugepaged_alloc_sleep_millisecs = msecs; - wake_up_interruptible(&khugepaged_wait); +static struct attribute *file_ctrl_attrs[] = { +#ifdef CONFIG_SHMEM + &thpsize_shmem_enabled_attr.attr, +#endif + NULL, +}; - return count; -} -static struct kobj_attribute alloc_sleep_millisecs_attr = - __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, - alloc_sleep_millisecs_store); +static const struct attribute_group file_ctrl_attr_grp = { + .attrs = file_ctrl_attrs, +}; -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; +static struct attribute *any_ctrl_attrs[] = { + NULL, +}; - err = strict_strtoul(buf, 10, &pages); - if (err || !pages || pages > UINT_MAX) - return -EINVAL; +static const struct attribute_group any_ctrl_attr_grp = { + .attrs = any_ctrl_attrs, +}; - khugepaged_pages_to_scan = pages; +static const struct kobj_type thpsize_ktype = { + .release = &thpsize_release, + .sysfs_ops = &kobj_sysfs_ops, +}; - return count; -} -static struct kobj_attribute pages_to_scan_attr = - __ATTR(pages_to_scan, 0644, pages_to_scan_show, - pages_to_scan_store); +DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}}; -static ssize_t pages_collapsed_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) +static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item) { - return sprintf(buf, "%u\n", khugepaged_pages_collapsed); -} -static struct kobj_attribute pages_collapsed_attr = - __ATTR_RO(pages_collapsed); + unsigned long sum = 0; + int cpu; -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); + for_each_possible_cpu(cpu) { + struct mthp_stat *this = &per_cpu(mthp_stats, cpu); -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); + sum += this->stats[order][item]; + } + + return sum; } -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) +#define DEFINE_MTHP_STAT_ATTR(_name, _index) \ +static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ +{ \ + int order = to_thpsize(kobj)->order; \ + \ + return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index)); \ +} \ +static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); +DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); +DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); +DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT); +DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN); +DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK); +DEFINE_MTHP_STAT_ATTR(swpin_fallback_charge, MTHP_STAT_SWPIN_FALLBACK_CHARGE); +DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); +DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); +#ifdef CONFIG_SHMEM +DEFINE_MTHP_STAT_ATTR(shmem_alloc, MTHP_STAT_SHMEM_ALLOC); +DEFINE_MTHP_STAT_ATTR(shmem_fallback, MTHP_STAT_SHMEM_FALLBACK); +DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE); +#endif +DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT); +DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED); +DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED); +DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON); +DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED); + +static struct attribute *anon_stats_attrs[] = { + &anon_fault_alloc_attr.attr, + &anon_fault_fallback_attr.attr, + &anon_fault_fallback_charge_attr.attr, +#ifndef CONFIG_SHMEM + &zswpout_attr.attr, + &swpin_attr.attr, + &swpin_fallback_attr.attr, + &swpin_fallback_charge_attr.attr, + &swpout_attr.attr, + &swpout_fallback_attr.attr, +#endif + &split_deferred_attr.attr, + &nr_anon_attr.attr, + &nr_anon_partially_mapped_attr.attr, + NULL, +}; + +static struct attribute_group anon_stats_attr_grp = { + .name = "stats", + .attrs = anon_stats_attrs, +}; + +static struct attribute *file_stats_attrs[] = { +#ifdef CONFIG_SHMEM + &shmem_alloc_attr.attr, + &shmem_fallback_attr.attr, + &shmem_fallback_charge_attr.attr, +#endif + NULL, +}; + +static struct attribute_group file_stats_attr_grp = { + .name = "stats", + .attrs = file_stats_attrs, +}; + +static struct attribute *any_stats_attrs[] = { +#ifdef CONFIG_SHMEM + &zswpout_attr.attr, + &swpin_attr.attr, + &swpin_fallback_attr.attr, + &swpin_fallback_charge_attr.attr, + &swpout_attr.attr, + &swpout_fallback_attr.attr, +#endif + &split_attr.attr, + &split_failed_attr.attr, + NULL, +}; + +static struct attribute_group any_stats_attr_grp = { + .name = "stats", + .attrs = any_stats_attrs, +}; + +static int sysfs_add_group(struct kobject *kobj, + const struct attribute_group *grp) { - return sprintf(buf, "%u\n", khugepaged_max_ptes_none); + int ret = -ENOENT; + + /* + * If the group is named, try to merge first, assuming the subdirectory + * was already created. This avoids the warning emitted by + * sysfs_create_group() if the directory already exists. + */ + if (grp->name) + ret = sysfs_merge_group(kobj, grp); + if (ret) + ret = sysfs_create_group(kobj, grp); + + return ret; } -static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) + +static struct thpsize *thpsize_create(int order, struct kobject *parent) { - int err; - unsigned long max_ptes_none; + unsigned long size = (PAGE_SIZE << order) / SZ_1K; + struct thpsize *thpsize; + int ret = -ENOMEM; - err = strict_strtoul(buf, 10, &max_ptes_none); - if (err || max_ptes_none > HPAGE_PMD_NR-1) - return -EINVAL; + thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL); + if (!thpsize) + goto err; - khugepaged_max_ptes_none = max_ptes_none; + thpsize->order = order; - return count; + ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent, + "hugepages-%lukB", size); + if (ret) { + kfree(thpsize); + goto err; + } + + + ret = sysfs_add_group(&thpsize->kobj, &any_ctrl_attr_grp); + if (ret) + goto err_put; + + ret = sysfs_add_group(&thpsize->kobj, &any_stats_attr_grp); + if (ret) + goto err_put; + + if (BIT(order) & THP_ORDERS_ALL_ANON) { + ret = sysfs_add_group(&thpsize->kobj, &anon_ctrl_attr_grp); + if (ret) + goto err_put; + + ret = sysfs_add_group(&thpsize->kobj, &anon_stats_attr_grp); + if (ret) + goto err_put; + } + + if (BIT(order) & THP_ORDERS_ALL_FILE_DEFAULT) { + ret = sysfs_add_group(&thpsize->kobj, &file_ctrl_attr_grp); + if (ret) + goto err_put; + + ret = sysfs_add_group(&thpsize->kobj, &file_stats_attr_grp); + if (ret) + goto err_put; + } + + return thpsize; +err_put: + kobject_put(&thpsize->kobj); +err: + return ERR_PTR(ret); } -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 void thpsize_release(struct kobject *kobj) +{ + kfree(to_thpsize(kobj)); +} static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; + struct thpsize *thpsize; + unsigned long orders; + int order; + + /* + * Default to setting PMD-sized THP to inherit the global setting and + * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time + * constant so we have to do this here. + */ + if (!anon_orders_configured) + huge_anon_orders_inherit = BIT(PMD_ORDER); *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"); + pr_err("failed to create transparent hugepage kobject\n"); return -ENOMEM; } err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); if (err) { - printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n"); + pr_err("failed to register transparent hugepage group\n"); goto delete_obj; } err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); if (err) { - printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n"); + pr_err("failed to register transparent hugepage group\n"); goto remove_hp_group; } + orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT; + order = highest_order(orders); + while (orders) { + thpsize = thpsize_create(order, *hugepage_kobj); + if (IS_ERR(thpsize)) { + pr_err("failed to create thpsize for order %d\n", order); + err = PTR_ERR(thpsize); + goto remove_all; + } + list_add(&thpsize->node, &thpsize_list); + order = next_order(&orders, order); + } + return 0; +remove_all: + hugepage_exit_sysfs(*hugepage_kobj); + return err; remove_hp_group: sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group); delete_obj: @@ -599,6 +832,13 @@ delete_obj: static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj) { + struct thpsize *thpsize, *tmp; + + list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) { + list_del(&thpsize->node); + kobject_put(&thpsize->kobj); + } + sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group); sysfs_remove_group(hugepage_kobj, &hugepage_attr_group); kobject_put(hugepage_kobj); @@ -614,42 +854,104 @@ static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) } #endif /* CONFIG_SYSFS */ +static int __init thp_shrinker_init(void) +{ + deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | + SHRINKER_MEMCG_AWARE | + SHRINKER_NONSLAB, + "thp-deferred_split"); + if (!deferred_split_shrinker) + return -ENOMEM; + + deferred_split_shrinker->count_objects = deferred_split_count; + deferred_split_shrinker->scan_objects = deferred_split_scan; + shrinker_register(deferred_split_shrinker); + + if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) { + /* + * Bump the reference of the huge_zero_folio and do not + * initialize the shrinker. + * + * huge_zero_folio will always be NULL on failure. We assume + * that get_huge_zero_folio() will most likely not fail as + * thp_shrinker_init() is invoked early on during boot. + */ + if (!get_huge_zero_folio()) + pr_warn("Allocating persistent huge zero folio failed\n"); + return 0; + } + + huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero"); + if (!huge_zero_folio_shrinker) { + shrinker_free(deferred_split_shrinker); + return -ENOMEM; + } + + huge_zero_folio_shrinker->count_objects = shrink_huge_zero_folio_count; + huge_zero_folio_shrinker->scan_objects = shrink_huge_zero_folio_scan; + shrinker_register(huge_zero_folio_shrinker); + + return 0; +} + +static void __init thp_shrinker_exit(void) +{ + shrinker_free(huge_zero_folio_shrinker); + shrinker_free(deferred_split_shrinker); +} + static int __init hugepage_init(void) { int err; struct kobject *hugepage_kobj; if (!has_transparent_hugepage()) { - transparent_hugepage_flags = 0; + transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED; return -EINVAL; } + /* + * hugepages can't be allocated by the buddy allocator + */ + MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER); + err = hugepage_init_sysfs(&hugepage_kobj); if (err) - return err; + goto err_sysfs; - err = khugepaged_slab_init(); + err = khugepaged_init(); if (err) - goto out; + goto err_slab; - register_shrinker(&huge_zero_page_shrinker); + err = thp_shrinker_init(); + if (err) + goto err_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))) + if (totalram_pages() < MB_TO_PAGES(512)) { transparent_hugepage_flags = 0; + return 0; + } - start_khugepaged(); + err = start_stop_khugepaged(); + if (err) + goto err_khugepaged; return 0; -out: +err_khugepaged: + thp_shrinker_exit(); +err_shrinker: + khugepaged_destroy(); +err_slab: hugepage_exit_sysfs(hugepage_kobj); +err_sysfs: return err; } -module_init(hugepage_init) +subsys_initcall(hugepage_init); static int __init setup_transparent_hugepage(char *str) { @@ -677,2123 +979,3985 @@ static int __init setup_transparent_hugepage(char *str) } out: if (!ret) - printk(KERN_WARNING - "transparent_hugepage= cannot parse, ignored\n"); + pr_warn("transparent_hugepage= cannot parse, ignored\n"); return ret; } __setup("transparent_hugepage=", setup_transparent_hugepage); +static char str_dup[PAGE_SIZE] __initdata; +static int __init setup_thp_anon(char *str) +{ + char *token, *range, *policy, *subtoken; + unsigned long always, inherit, madvise; + char *start_size, *end_size; + int start, end, nr; + char *p; + + if (!str || strlen(str) + 1 > PAGE_SIZE) + goto err; + strscpy(str_dup, str); + + always = huge_anon_orders_always; + madvise = huge_anon_orders_madvise; + inherit = huge_anon_orders_inherit; + p = str_dup; + while ((token = strsep(&p, ";")) != NULL) { + range = strsep(&token, ":"); + policy = token; + + if (!policy) + goto err; + + while ((subtoken = strsep(&range, ",")) != NULL) { + if (strchr(subtoken, '-')) { + start_size = strsep(&subtoken, "-"); + end_size = subtoken; + + start = get_order_from_str(start_size, THP_ORDERS_ALL_ANON); + end = get_order_from_str(end_size, THP_ORDERS_ALL_ANON); + } else { + start_size = end_size = subtoken; + start = end = get_order_from_str(subtoken, + THP_ORDERS_ALL_ANON); + } + + if (start == -EINVAL) { + pr_err("invalid size %s in thp_anon boot parameter\n", start_size); + goto err; + } + + if (end == -EINVAL) { + pr_err("invalid size %s in thp_anon boot parameter\n", end_size); + goto err; + } + + if (start < 0 || end < 0 || start > end) + goto err; + + nr = end - start + 1; + if (!strcmp(policy, "always")) { + bitmap_set(&always, start, nr); + bitmap_clear(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + } else if (!strcmp(policy, "madvise")) { + bitmap_set(&madvise, start, nr); + bitmap_clear(&inherit, start, nr); + bitmap_clear(&always, start, nr); + } else if (!strcmp(policy, "inherit")) { + bitmap_set(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + bitmap_clear(&always, start, nr); + } else if (!strcmp(policy, "never")) { + bitmap_clear(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + bitmap_clear(&always, start, nr); + } else { + pr_err("invalid policy %s in thp_anon boot parameter\n", policy); + goto err; + } + } + } + + huge_anon_orders_always = always; + huge_anon_orders_madvise = madvise; + huge_anon_orders_inherit = inherit; + anon_orders_configured = true; + return 1; + +err: + pr_warn("thp_anon=%s: error parsing string, ignoring setting\n", str); + return 0; +} +__setup("thp_anon=", setup_thp_anon); + pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) - pmd = pmd_mkwrite(pmd); + pmd = pmd_mkwrite(pmd, vma); return pmd; } -static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma) +static struct deferred_split *split_queue_node(int nid) { - pmd_t entry; - entry = mk_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - entry = pmd_mkhuge(entry); - return entry; + struct pglist_data *pgdata = NODE_DATA(nid); + + return &pgdata->deferred_split_queue; } -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) +#ifdef CONFIG_MEMCG +static inline +struct mem_cgroup *folio_split_queue_memcg(struct folio *folio, + struct deferred_split *queue) { - pgtable_t pgtable; + if (mem_cgroup_disabled()) + return NULL; + if (split_queue_node(folio_nid(folio)) == queue) + return NULL; + return container_of(queue, struct mem_cgroup, deferred_split_queue); +} - VM_BUG_ON(!PageCompound(page)); - pgtable = pte_alloc_one(mm, haddr); - if (unlikely(!pgtable)) - return VM_FAULT_OOM; +static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memcg) +{ + return memcg ? &memcg->deferred_split_queue : split_queue_node(nid); +} +#else +static inline +struct mem_cgroup *folio_split_queue_memcg(struct folio *folio, + struct deferred_split *queue) +{ + return NULL; +} + +static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memcg) +{ + return split_queue_node(nid); +} +#endif + +static struct deferred_split *split_queue_lock(int nid, struct mem_cgroup *memcg) +{ + struct deferred_split *queue; - clear_huge_page(page, haddr, HPAGE_PMD_NR); +retry: + queue = memcg_split_queue(nid, memcg); + spin_lock(&queue->split_queue_lock); /* - * The memory barrier inside __SetPageUptodate makes sure that - * clear_huge_page writes become visible before the set_pmd_at() + * There is a period between setting memcg to dying and reparenting + * deferred split queue, and during this period the THPs in the deferred + * split queue will be hidden from the shrinker side. + */ + if (unlikely(memcg_is_dying(memcg))) { + spin_unlock(&queue->split_queue_lock); + memcg = parent_mem_cgroup(memcg); + goto retry; + } + + return queue; +} + +static struct deferred_split * +split_queue_lock_irqsave(int nid, struct mem_cgroup *memcg, unsigned long *flags) +{ + struct deferred_split *queue; + +retry: + queue = memcg_split_queue(nid, memcg); + spin_lock_irqsave(&queue->split_queue_lock, *flags); + if (unlikely(memcg_is_dying(memcg))) { + spin_unlock_irqrestore(&queue->split_queue_lock, *flags); + memcg = parent_mem_cgroup(memcg); + goto retry; + } + + return queue; +} + +static struct deferred_split *folio_split_queue_lock(struct folio *folio) +{ + return split_queue_lock(folio_nid(folio), folio_memcg(folio)); +} + +static struct deferred_split * +folio_split_queue_lock_irqsave(struct folio *folio, unsigned long *flags) +{ + return split_queue_lock_irqsave(folio_nid(folio), folio_memcg(folio), flags); +} + +static inline void split_queue_unlock(struct deferred_split *queue) +{ + spin_unlock(&queue->split_queue_lock); +} + +static inline void split_queue_unlock_irqrestore(struct deferred_split *queue, + unsigned long flags) +{ + spin_unlock_irqrestore(&queue->split_queue_lock, flags); +} + +static inline bool is_transparent_hugepage(const struct folio *folio) +{ + if (!folio_test_large(folio)) + return false; + + return is_huge_zero_folio(folio) || + folio_test_large_rmappable(folio); +} + +static unsigned long __thp_get_unmapped_area(struct file *filp, + unsigned long addr, unsigned long len, + loff_t off, unsigned long flags, unsigned long size, + vm_flags_t vm_flags) +{ + loff_t off_end = off + len; + loff_t off_align = round_up(off, size); + unsigned long len_pad, ret, off_sub; + + if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) + return 0; + + if (off_end <= off_align || (off_end - off_align) < size) + return 0; + + len_pad = len + size; + if (len_pad < len || (off + len_pad) < off) + return 0; + + ret = mm_get_unmapped_area_vmflags(filp, addr, len_pad, + off >> PAGE_SHIFT, flags, vm_flags); + + /* + * The failure might be due to length padding. The caller will retry + * without the padding. + */ + if (IS_ERR_VALUE(ret)) + return 0; + + /* + * Do not try to align to THP boundary if allocation at the address + * hint succeeds. + */ + if (ret == addr) + return addr; + + off_sub = (off - ret) & (size - 1); + + if (mm_flags_test(MMF_TOPDOWN, current->mm) && !off_sub) + return ret + size; + + ret += off_sub; + return ret; +} + +unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) +{ + unsigned long ret; + loff_t off = (loff_t)pgoff << PAGE_SHIFT; + + ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags); + if (ret) + return ret; + + return mm_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, + vm_flags); +} + +unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); +} +EXPORT_SYMBOL_GPL(thp_get_unmapped_area); + +static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, + unsigned long addr) +{ + gfp_t gfp = vma_thp_gfp_mask(vma); + const int order = HPAGE_PMD_ORDER; + struct folio *folio; + + folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK); + + if (unlikely(!folio)) { + count_vm_event(THP_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + return NULL; + } + + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { + folio_put(folio); + count_vm_event(THP_FAULT_FALLBACK); + count_vm_event(THP_FAULT_FALLBACK_CHARGE); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); + return NULL; + } + folio_throttle_swaprate(folio, gfp); + + /* + * When a folio is not zeroed during allocation (__GFP_ZERO not used) + * or user folios require special handling, folio_zero_user() is used to + * make sure that the page corresponding to the faulting address will be + * hot in the cache after zeroing. + */ + if (user_alloc_needs_zeroing()) + folio_zero_user(folio, addr); + /* + * The memory barrier inside __folio_mark_uptodate makes sure that + * folio_zero_user writes become visible before the set_pmd_at() * write. */ - __SetPageUptodate(page); + __folio_mark_uptodate(folio); + return folio; +} - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_none(*pmd))) { - spin_unlock(&mm->page_table_lock); - mem_cgroup_uncharge_page(page); - put_page(page); - pte_free(mm, pgtable); +void map_anon_folio_pmd_nopf(struct folio *folio, pmd_t *pmd, + struct vm_area_struct *vma, unsigned long haddr) +{ + pmd_t entry; + + entry = folio_mk_pmd(folio, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + set_pmd_at(vma->vm_mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, haddr, pmd); + deferred_split_folio(folio, false); +} + +static void map_anon_folio_pmd_pf(struct folio *folio, pmd_t *pmd, + struct vm_area_struct *vma, unsigned long haddr) +{ + map_anon_folio_pmd_nopf(folio, pmd, vma, haddr); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + count_vm_event(THP_FAULT_ALLOC); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); +} + +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + pgtable_t pgtable; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) { + ret = VM_FAULT_OOM; + goto release; + } + + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_none(*vmf->pmd))) { + goto unlock_release; } else { - pmd_t entry; - entry = mk_huge_pmd(page, 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); - mm->nr_ptes++; - spin_unlock(&mm->page_table_lock); + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto unlock_release; + + /* Deliver the page fault to userland */ + if (userfaultfd_missing(vma)) { + spin_unlock(vmf->ptl); + folio_put(folio); + pte_free(vma->vm_mm, pgtable); + ret = handle_userfault(vmf, VM_UFFD_MISSING); + VM_BUG_ON(ret & VM_FAULT_FALLBACK); + return ret; + } + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); + map_anon_folio_pmd_pf(folio, vmf->pmd, vma, haddr); + mm_inc_nr_ptes(vma->vm_mm); + spin_unlock(vmf->ptl); } return 0; -} +unlock_release: + spin_unlock(vmf->ptl); +release: + if (pgtable) + pte_free(vma->vm_mm, pgtable); + folio_put(folio); + return ret; -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) +vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf) { - return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp), - HPAGE_PMD_ORDER, vma, haddr, nd); + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = 0; + spinlock_t *ptl; + softleaf_t entry; + struct page *page; + struct folio *folio; + + if (vmf->flags & FAULT_FLAG_VMA_LOCK) { + vma_end_read(vma); + return VM_FAULT_RETRY; + } + + ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) { + spin_unlock(ptl); + return 0; + } + + entry = softleaf_from_pmd(vmf->orig_pmd); + page = softleaf_to_page(entry); + folio = page_folio(page); + vmf->page = page; + vmf->pte = NULL; + if (folio_trylock(folio)) { + folio_get(folio); + spin_unlock(ptl); + ret = page_pgmap(page)->ops->migrate_to_ram(vmf); + folio_unlock(folio); + folio_put(folio); + } else { + spin_unlock(ptl); + } + + return ret; } -#ifndef CONFIG_NUMA -static inline struct page *alloc_hugepage(int defrag) +/* + * always: directly stall for all thp allocations + * defer: wake kswapd and fail if not immediately available + * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise + * fail if not immediately available + * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately + * available + * never: never stall for any thp allocation + */ +gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) { - return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), - HPAGE_PMD_ORDER); + const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE); + + /* Always do synchronous compaction */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); + + /* Kick kcompactd and fail quickly */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + + /* Synchronous compaction if madvised, otherwise kick kcompactd */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); + + /* Only do synchronous compaction if madvised */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + + return GFP_TRANSHUGE_LIGHT; } -#endif -static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, +/* Caller must hold page table lock. */ +static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, - struct page *zero_page) + struct folio *zero_folio) { pmd_t entry; - if (!pmd_none(*pmd)) - return false; - entry = mk_pmd(zero_page, vma->vm_page_prot); - entry = pmd_wrprotect(entry); - entry = pmd_mkhuge(entry); + entry = folio_mk_pmd(zero_folio, vma->vm_page_prot); + entry = pmd_mkspecial(entry); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); - mm->nr_ptes++; - return true; + mm_inc_nr_ptes(mm); } -int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - unsigned int flags) +vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { - struct page *page; - unsigned long haddr = address & HPAGE_PMD_MASK; - pte_t *pte; + struct vm_area_struct *vma = vmf->vma; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + vm_fault_t ret; - if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) { - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; - if (unlikely(khugepaged_enter(vma))) + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) + return VM_FAULT_FALLBACK; + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; + khugepaged_enter_vma(vma, vma->vm_flags); + + if (!(vmf->flags & FAULT_FLAG_WRITE) && + !mm_forbids_zeropage(vma->vm_mm) && + transparent_hugepage_use_zero_page()) { + pgtable_t pgtable; + struct folio *zero_folio; + vm_fault_t ret; + + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) 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)) - return VM_FAULT_OOM; - zero_page = get_huge_zero_page(); - if (unlikely(!zero_page)) { - pte_free(mm, pgtable); - count_vm_event(THP_FAULT_FALLBACK); - goto out; - } - spin_lock(&mm->page_table_lock); - set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, - zero_page); - spin_unlock(&mm->page_table_lock); - 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)) { + zero_folio = mm_get_huge_zero_folio(vma->vm_mm); + if (unlikely(!zero_folio)) { + pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); - goto out; + return VM_FAULT_FALLBACK; } - count_vm_event(THP_FAULT_ALLOC); - if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { - put_page(page); - goto out; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + ret = 0; + if (pmd_none(*vmf->pmd)) { + ret = check_stable_address_space(vma->vm_mm); + if (ret) { + spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); + } else if (userfaultfd_missing(vma)) { + spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); + ret = handle_userfault(vmf, VM_UFFD_MISSING); + VM_BUG_ON(ret & VM_FAULT_FALLBACK); + } else { + set_huge_zero_folio(pgtable, vma->vm_mm, vma, + haddr, vmf->pmd, zero_folio); + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + spin_unlock(vmf->ptl); + } + } else { + spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); } - if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, - page))) { - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; + return ret; + } + + return __do_huge_pmd_anonymous_page(vmf); +} + +struct folio_or_pfn { + union { + struct folio *folio; + unsigned long pfn; + }; + bool is_folio; +}; + +static vm_fault_t insert_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, struct folio_or_pfn fop, pgprot_t prot, + bool write) +{ + struct mm_struct *mm = vma->vm_mm; + pgtable_t pgtable = NULL; + spinlock_t *ptl; + pmd_t entry; + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + + ptl = pmd_lock(mm, pmd); + if (!pmd_none(*pmd)) { + const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) : + fop.pfn; + + if (write) { + if (pmd_pfn(*pmd) != pfn) { + WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); + goto out_unlock; + } + entry = pmd_mkyoung(*pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) + update_mmu_cache_pmd(vma, addr, pmd); } + goto out_unlock; + } - return 0; + if (fop.is_folio) { + entry = folio_mk_pmd(fop.folio, vma->vm_page_prot); + + if (is_huge_zero_folio(fop.folio)) { + entry = pmd_mkspecial(entry); + } else { + folio_get(fop.folio); + folio_add_file_rmap_pmd(fop.folio, &fop.folio->page, vma); + add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PMD_NR); + } + } else { + entry = pmd_mkhuge(pfn_pmd(fop.pfn, prot)); + entry = pmd_mkspecial(entry); } -out: + if (write) { + entry = pmd_mkyoung(pmd_mkdirty(entry)); + entry = maybe_pmd_mkwrite(entry, vma); + } + + if (pgtable) { + pgtable_trans_huge_deposit(mm, pmd, pgtable); + mm_inc_nr_ptes(mm); + pgtable = NULL; + } + + set_pmd_at(mm, addr, pmd, entry); + update_mmu_cache_pmd(vma, addr, pmd); + +out_unlock: + spin_unlock(ptl); + if (pgtable) + pte_free(mm, pgtable); + return VM_FAULT_NOPAGE; +} + +/** + * vmf_insert_pfn_pmd - insert a pmd size pfn + * @vmf: Structure describing the fault + * @pfn: pfn to insert + * @write: whether it's a write fault + * + * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, + bool write) +{ + unsigned long addr = vmf->address & PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + pgprot_t pgprot = vma->vm_page_prot; + struct folio_or_pfn fop = { + .pfn = pfn, + }; + /* - * 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 we had pmd_special, we could avoid all these restrictions, + * but we need to be consistent with PTEs and architectures that + * can't support a 'special' bit. */ - if (unlikely(pmd_none(*pmd)) && - 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; + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + + pfnmap_setup_cachemode_pfn(pfn, &pgprot); + + return insert_pmd(vma, addr, vmf->pmd, fop, pgprot, write); +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); + +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, + bool write) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address & PMD_MASK; + struct folio_or_pfn fop = { + .folio = folio, + .is_folio = true, + }; + + if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER)) + return VM_FAULT_SIGBUS; + + return insert_pmd(vma, addr, vmf->pmd, fop, vma->vm_page_prot, write); +} +EXPORT_SYMBOL_GPL(vmf_insert_folio_pmd); + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pud = pud_mkwrite(pud); + return pud; +} + +static vm_fault_t insert_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, struct folio_or_pfn fop, pgprot_t prot, bool write) +{ + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pud_t entry; + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + ptl = pud_lock(mm, pud); + if (!pud_none(*pud)) { + const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) : + fop.pfn; + + if (write) { + if (WARN_ON_ONCE(pud_pfn(*pud) != pfn)) + goto out_unlock; + entry = pud_mkyoung(*pud); + entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); + if (pudp_set_access_flags(vma, addr, pud, entry, 1)) + update_mmu_cache_pud(vma, addr, pud); + } + goto out_unlock; + } + + if (fop.is_folio) { + entry = folio_mk_pud(fop.folio, vma->vm_page_prot); + + folio_get(fop.folio); + folio_add_file_rmap_pud(fop.folio, &fop.folio->page, vma); + add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PUD_NR); + } else { + entry = pud_mkhuge(pfn_pud(fop.pfn, prot)); + entry = pud_mkspecial(entry); + } + if (write) { + entry = pud_mkyoung(pud_mkdirty(entry)); + entry = maybe_pud_mkwrite(entry, vma); + } + set_pud_at(mm, addr, pud, entry); + update_mmu_cache_pud(vma, addr, pud); +out_unlock: + spin_unlock(ptl); + return VM_FAULT_NOPAGE; +} + +/** + * vmf_insert_pfn_pud - insert a pud size pfn + * @vmf: Structure describing the fault + * @pfn: pfn to insert + * @write: whether it's a write fault + * + * Insert a pud size pfn. See vmf_insert_pfn() for additional info. + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, + bool write) +{ + unsigned long addr = vmf->address & PUD_MASK; + struct vm_area_struct *vma = vmf->vma; + pgprot_t pgprot = vma->vm_page_prot; + struct folio_or_pfn fop = { + .pfn = pfn, + }; + /* - * 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(). + * If we had pud_special, we could avoid all these restrictions, + * but we need to be consistent with PTEs and architectures that + * can't support a 'special' bit. */ - pte = pte_offset_map(pmd, address); - return handle_pte_fault(mm, vma, address, pte, pmd, flags); + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + + pfnmap_setup_cachemode_pfn(pfn, &pgprot); + + return insert_pud(vma, addr, vmf->pud, fop, pgprot, write); +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); + +/** + * vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry + * @vmf: Structure describing the fault + * @folio: folio to insert + * @write: whether it's a write fault + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, + bool write) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address & PUD_MASK; + struct folio_or_pfn fop = { + .folio = folio, + .is_folio = true, + }; + + if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER)) + return VM_FAULT_SIGBUS; + + return insert_pud(vma, addr, vmf->pud, fop, vma->vm_page_prot, write); +} +EXPORT_SYMBOL_GPL(vmf_insert_folio_pud); +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + +/** + * touch_pmd - Mark page table pmd entry as accessed and dirty (for write) + * @vma: The VMA covering @addr + * @addr: The virtual address + * @pmd: pmd pointer into the page table mapping @addr + * @write: Whether it's a write access + * + * Return: whether the pmd entry is changed + */ +bool touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write) +{ + pmd_t entry; + + entry = pmd_mkyoung(*pmd); + if (write) + entry = pmd_mkdirty(entry); + if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, + pmd, entry, write)) { + update_mmu_cache_pmd(vma, addr, pmd); + return true; + } + + return false; +} + +static void copy_huge_non_present_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 *dst_vma, struct vm_area_struct *src_vma, + pmd_t pmd, pgtable_t pgtable) +{ + softleaf_t entry = softleaf_from_pmd(pmd); + struct folio *src_folio; + + VM_WARN_ON_ONCE(!pmd_is_valid_softleaf(pmd)); + + if (softleaf_is_migration_write(entry) || + softleaf_is_migration_read_exclusive(entry)) { + entry = make_readable_migration_entry(swp_offset(entry)); + pmd = swp_entry_to_pmd(entry); + if (pmd_swp_soft_dirty(*src_pmd)) + pmd = pmd_swp_mksoft_dirty(pmd); + if (pmd_swp_uffd_wp(*src_pmd)) + pmd = pmd_swp_mkuffd_wp(pmd); + set_pmd_at(src_mm, addr, src_pmd, pmd); + } else if (softleaf_is_device_private(entry)) { + /* + * For device private entries, since there are no + * read exclusive entries, writable = !readable + */ + if (softleaf_is_device_private_write(entry)) { + entry = make_readable_device_private_entry(swp_offset(entry)); + pmd = swp_entry_to_pmd(entry); + + if (pmd_swp_soft_dirty(*src_pmd)) + pmd = pmd_swp_mksoft_dirty(pmd); + if (pmd_swp_uffd_wp(*src_pmd)) + pmd = pmd_swp_mkuffd_wp(pmd); + set_pmd_at(src_mm, addr, src_pmd, pmd); + } + + src_folio = softleaf_to_folio(entry); + VM_WARN_ON(!folio_test_large(src_folio)); + + folio_get(src_folio); + /* + * folio_try_dup_anon_rmap_pmd does not fail for + * device private entries. + */ + folio_try_dup_anon_rmap_pmd(src_folio, &src_folio->page, + dst_vma, src_vma); + } + + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm_inc_nr_ptes(dst_mm); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_swp_clear_uffd_wp(pmd); + set_pmd_at(dst_mm, addr, dst_pmd, pmd); } 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 vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { + spinlock_t *dst_ptl, *src_ptl; struct page *src_page; + struct folio *src_folio; pmd_t pmd; - pgtable_t pgtable; - int ret; + pgtable_t pgtable = NULL; + int ret = -ENOMEM; + + pmd = pmdp_get_lockless(src_pmd); + if (unlikely(pmd_present(pmd) && pmd_special(pmd) && + !is_huge_zero_pmd(pmd))) { + dst_ptl = pmd_lock(dst_mm, dst_pmd); + src_ptl = pmd_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + /* + * No need to recheck the pmd, it can't change with write + * mmap lock held here. + * + * Meanwhile, making sure it's not a CoW VMA with writable + * mapping, otherwise it means either the anon page wrongly + * applied special bit, or we made the PRIVATE mapping be + * able to wrongly write to the backend MMIO. + */ + VM_WARN_ON_ONCE(is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd)); + goto set_pmd; + } - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); + /* Skip if can be re-fill on fault */ + if (!vma_is_anonymous(dst_vma)) + return 0; + + pgtable = pte_alloc_one(dst_mm); if (unlikely(!pgtable)) goto out; - spin_lock(&dst_mm->page_table_lock); - spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING); + 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(thp_migration_supported() && + pmd_is_valid_softleaf(pmd))) { + copy_huge_non_present_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, + dst_vma, src_vma, pmd, pgtable); + ret = 0; + goto out_unlock; + } + if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } /* - * mm->page_table_lock is enough to be sure that huge zero pmd is not + * 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. + * mm_get_huge_zero_folio() will never allocate a new + * folio 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, - zero_page); - BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */ - ret = 0; - goto out_unlock; + mm_get_huge_zero_folio(dst_mm); + goto out_zero_page; } - 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); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + src_folio = page_folio(src_page); - pmdp_set_wrprotect(src_mm, addr, src_pmd); - pmd = pmd_mkold(pmd_wrprotect(pmd)); + folio_get(src_folio); + if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, dst_vma, src_vma))) { + /* Page maybe pinned: split and retry the fault on PTEs. */ + folio_put(src_folio); + pte_free(dst_mm, pgtable); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pmd(src_vma, src_pmd, addr, false); + return -EAGAIN; + } + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); +out_zero_page: + mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + pmdp_set_wrprotect(src_mm, addr, src_pmd); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_clear_uffd_wp(pmd); + pmd = pmd_wrprotect(pmd); +set_pmd: + pmd = pmd_mkold(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); - dst_mm->nr_ptes++; ret = 0; out_unlock: - spin_unlock(&src_mm->page_table_lock); - spin_unlock(&dst_mm->page_table_lock); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); out: return ret; } -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) +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write) { - pmd_t entry; - unsigned long haddr; - - spin_lock(&mm->page_table_lock); - 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: - spin_unlock(&mm->page_table_lock); + pud_t _pud; + + _pud = pud_mkyoung(*pud); + if (write) + _pud = pud_mkdirty(_pud); + if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, + pud, _pud, write)) + update_mmu_cache_pud(vma, addr, pud); } -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) +int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + struct vm_area_struct *vma) { - 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 */ + spinlock_t *dst_ptl, *src_ptl; + pud_t pud; + int ret; - page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!page) { - ret |= VM_FAULT_OOM; - goto out; - } + dst_ptl = pud_lock(dst_mm, dst_pud); + src_ptl = pud_lockptr(src_mm, src_pud); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) { - put_page(page); - ret |= VM_FAULT_OOM; - goto out; + ret = -EAGAIN; + pud = *src_pud; + if (unlikely(!pud_trans_huge(pud))) + goto out_unlock; + + /* + * TODO: once we support anonymous pages, use + * folio_try_dup_anon_rmap_*() and split if duplicating fails. + */ + if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) { + pudp_set_wrprotect(src_mm, addr, src_pud); + pud = pud_wrprotect(pud); } + pud = pud_mkold(pud); + set_pud_at(dst_mm, addr, dst_pud, pud); - clear_user_highpage(page, address); - __SetPageUptodate(page); + ret = 0; +out_unlock: + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + return ret; +} - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); +void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) +{ + bool write = vmf->flags & FAULT_FLAG_WRITE; - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(*pmd, orig_pmd))) - goto out_free_page; + vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); + if (unlikely(!pud_same(*vmf->pud, orig_pud))) + goto unlock; - pmdp_clear_flush(vma, haddr, pmd); - /* leave pmd empty until pte is filled */ + touch_pud(vmf->vma, vmf->address, vmf->pud, write); +unlock: + spin_unlock(vmf->ptl); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); +bool huge_pmd_set_accessed(struct vm_fault *vmf) +{ + bool write = vmf->flags & FAULT_FLAG_WRITE; - 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); - spin_unlock(&mm->page_table_lock); - put_huge_zero_page(); - inc_mm_counter(mm, MM_ANONPAGES); + if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) + return false; - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + return touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); +} - ret |= VM_FAULT_WRITE; -out: +static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct mmu_notifier_range range; + struct folio *folio; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) + goto release; + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + (void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd); + map_anon_folio_pmd_pf(folio, vmf->pmd, vma, haddr); + goto unlock; +release: + folio_put(folio); +unlock: + spin_unlock(vmf->ptl); + mmu_notifier_invalidate_range_end(&range); return ret; -out_free_page: - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - mem_cgroup_uncharge_page(page); - put_page(page); - goto out; } -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) +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { - pgtable_t pgtable; - pmd_t _pmd; - int ret = 0, i; - struct page **pages; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - - pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR, - GFP_KERNEL); - if (unlikely(!pages)) { - ret |= VM_FAULT_OOM; - goto out; + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + struct page *page; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + pmd_t orig_pmd = vmf->orig_pmd; + + vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); + VM_BUG_ON_VMA(!vma->anon_vma, vma); + + if (is_huge_zero_pmd(orig_pmd)) { + vm_fault_t ret = do_huge_zero_wp_pmd(vmf); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + + /* Fallback to splitting PMD if THP cannot be allocated */ + goto fallback; } - for (i = 0; i < HPAGE_PMD_NR; i++) { - pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE | - __GFP_OTHER_NODE, - vma, address, page_to_nid(page)); - if (unlikely(!pages[i] || - mem_cgroup_newpage_charge(pages[i], mm, - GFP_KERNEL))) { - if (pages[i]) - put_page(pages[i]); - mem_cgroup_uncharge_start(); - while (--i >= 0) { - mem_cgroup_uncharge_page(pages[i]); - put_page(pages[i]); - } - mem_cgroup_uncharge_end(); - kfree(pages); - ret |= VM_FAULT_OOM; - goto out; + spin_lock(vmf->ptl); + + if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { + spin_unlock(vmf->ptl); + return 0; + } + + page = pmd_page(orig_pmd); + folio = page_folio(page); + VM_BUG_ON_PAGE(!PageHead(page), page); + + /* Early check when only holding the PT lock. */ + if (PageAnonExclusive(page)) + goto reuse; + + if (!folio_trylock(folio)) { + folio_get(folio); + spin_unlock(vmf->ptl); + folio_lock(folio); + spin_lock(vmf->ptl); + if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { + spin_unlock(vmf->ptl); + folio_unlock(folio); + folio_put(folio); + return 0; } + folio_put(folio); } - for (i = 0; i < HPAGE_PMD_NR; i++) { - copy_user_highpage(pages[i], page + i, - haddr + PAGE_SIZE * i, vma); - __SetPageUptodate(pages[i]); - cond_resched(); + /* Recheck after temporarily dropping the PT lock. */ + if (PageAnonExclusive(page)) { + folio_unlock(folio); + goto reuse; } - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + /* + * See do_wp_page(): we can only reuse the folio exclusively if + * there are no additional references. Note that we always drain + * the LRU cache immediately after adding a THP. + */ + if (folio_ref_count(folio) > + 1 + folio_test_swapcache(folio) * folio_nr_pages(folio)) + goto unlock_fallback; + if (folio_test_swapcache(folio)) + folio_free_swap(folio); + if (folio_ref_count(folio) == 1) { + pmd_t entry; - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(*pmd, orig_pmd))) - goto out_free_pages; - VM_BUG_ON(!PageHead(page)); + folio_move_anon_rmap(folio, vma); + SetPageAnonExclusive(page); + folio_unlock(folio); +reuse: + if (unlikely(unshare)) { + spin_unlock(vmf->ptl); + return 0; + } + entry = pmd_mkyoung(orig_pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + spin_unlock(vmf->ptl); + return 0; + } + +unlock_fallback: + folio_unlock(folio); + spin_unlock(vmf->ptl); +fallback: + __split_huge_pmd(vma, vmf->pmd, vmf->address, false); + return VM_FAULT_FALLBACK; +} - pmdp_clear_flush(vma, haddr, pmd); - /* leave pmd empty until pte is filled */ +static inline bool can_change_pmd_writable(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd) +{ + struct page *page; - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); + if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE))) + return false; - 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); + /* Don't touch entries that are not even readable (NUMA hinting). */ + if (pmd_protnone(pmd)) + return false; + + /* Do we need write faults for softdirty tracking? */ + if (pmd_needs_soft_dirty_wp(vma, pmd)) + return false; + + /* Do we need write faults for uffd-wp tracking? */ + if (userfaultfd_huge_pmd_wp(vma, pmd)) + return false; + + if (!(vma->vm_flags & VM_SHARED)) { + /* See can_change_pte_writable(). */ + page = vm_normal_page_pmd(vma, addr, pmd); + return page && PageAnon(page) && PageAnonExclusive(page); } - kfree(pages); - smp_wmb(); /* make pte visible before pmd */ - pmd_populate(mm, pmd, pgtable); - page_remove_rmap(page); - spin_unlock(&mm->page_table_lock); + /* See can_change_pte_writable(). */ + return pmd_dirty(pmd); +} - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); +/* NUMA hinting page fault entry point for trans huge pmds */ +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + int nid = NUMA_NO_NODE; + int target_nid, last_cpupid; + pmd_t pmd, old_pmd; + bool writable = false; + int flags = 0; + + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + old_pmd = pmdp_get(vmf->pmd); + + if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) { + spin_unlock(vmf->ptl); + return 0; + } - ret |= VM_FAULT_WRITE; - put_page(page); + pmd = pmd_modify(old_pmd, vma->vm_page_prot); -out: - return ret; + /* + * Detect now whether the PMD could be writable; this information + * is only valid while holding the PT lock. + */ + writable = pmd_write(pmd); + if (!writable && vma_wants_manual_pte_write_upgrade(vma) && + can_change_pmd_writable(vma, vmf->address, pmd)) + writable = true; + + folio = vm_normal_folio_pmd(vma, haddr, pmd); + if (!folio) + goto out_map; + + nid = folio_nid(folio); + + target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable, + &last_cpupid); + if (target_nid == NUMA_NO_NODE) + goto out_map; + if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { + flags |= TNF_MIGRATE_FAIL; + goto out_map; + } + /* The folio is isolated and isolation code holds a folio reference. */ + spin_unlock(vmf->ptl); + writable = false; + + if (!migrate_misplaced_folio(folio, target_nid)) { + flags |= TNF_MIGRATED; + nid = target_nid; + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; + } -out_free_pages: - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - mem_cgroup_uncharge_start(); - for (i = 0; i < HPAGE_PMD_NR; i++) { - mem_cgroup_uncharge_page(pages[i]); - put_page(pages[i]); + flags |= TNF_MIGRATE_FAIL; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) { + spin_unlock(vmf->ptl); + return 0; } - mem_cgroup_uncharge_end(); - kfree(pages); - goto out; +out_map: + /* Restore the PMD */ + pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (writable) + pmd = pmd_mkwrite(pmd, vma); + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + spin_unlock(vmf->ptl); + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } -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) +/* + * Return true if we do MADV_FREE successfully on entire pmd page. + * Otherwise, return false. + */ +bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next) { - int ret = 0; - struct page *page = NULL, *new_page; - unsigned long haddr; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ + spinlock_t *ptl; + pmd_t orig_pmd; + struct folio *folio; + struct mm_struct *mm = tlb->mm; + bool ret = false; + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); - VM_BUG_ON(!vma->anon_vma); - haddr = address & HPAGE_PMD_MASK; + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) + goto out_unlocked; + + orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) - goto alloc; - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(*pmd, orig_pmd))) - goto out_unlock; + goto out; - page = pmd_page(orig_pmd); - VM_BUG_ON(!PageCompound(page) || !PageHead(page)); - 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_pmd(vma, address, pmd); - ret |= VM_FAULT_WRITE; - goto out_unlock; + if (unlikely(!pmd_present(orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !pmd_is_migration_entry(orig_pmd)); + goto out; } - get_page(page); - spin_unlock(&mm->page_table_lock); -alloc: - if (transparent_hugepage_enabled(vma) && - !transparent_hugepage_debug_cow()) - new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - else - new_page = NULL; - if (unlikely(!new_page)) { - count_vm_event(THP_FAULT_FALLBACK); - if (is_huge_zero_pmd(orig_pmd)) { - ret = do_huge_pmd_wp_zero_page_fallback(mm, vma, - address, pmd, orig_pmd, haddr); - } else { - ret = do_huge_pmd_wp_page_fallback(mm, vma, address, - pmd, orig_pmd, page, haddr); - if (ret & VM_FAULT_OOM) - split_huge_page(page); - put_page(page); - } + folio = pmd_folio(orig_pmd); + /* + * If other processes are mapping this folio, we couldn't discard + * the folio unless they all do MADV_FREE so let's skip the folio. + */ + if (folio_maybe_mapped_shared(folio)) goto out; - } - count_vm_event(THP_FAULT_ALLOC); - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { - put_page(new_page); - if (page) { - split_huge_page(page); - put_page(page); - } - ret |= VM_FAULT_OOM; + if (!folio_trylock(folio)) goto out; + + /* + * If user want to discard part-pages of THP, split it so MADV_FREE + * will deactivate only them. + */ + if (next - addr != HPAGE_PMD_SIZE) { + folio_get(folio); + spin_unlock(ptl); + split_folio(folio); + folio_unlock(folio); + folio_put(folio); + goto out_unlocked; } - if (is_huge_zero_pmd(orig_pmd)) - clear_huge_page(new_page, haddr, HPAGE_PMD_NR); - else - copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR); - __SetPageUptodate(new_page); + if (folio_test_dirty(folio)) + folio_clear_dirty(folio); + folio_unlock(folio); - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { + pmdp_invalidate(vma, addr, pmd); + orig_pmd = pmd_mkold(orig_pmd); + orig_pmd = pmd_mkclean(orig_pmd); - spin_lock(&mm->page_table_lock); - if (page) - put_page(page); - if (unlikely(!pmd_same(*pmd, orig_pmd))) { - spin_unlock(&mm->page_table_lock); - mem_cgroup_uncharge_page(new_page); - put_page(new_page); - goto out_mn; - } else { - pmd_t entry; - entry = mk_huge_pmd(new_page, vma); - pmdp_clear_flush(vma, haddr, pmd); - page_add_new_anon_rmap(new_page, vma, haddr); - set_pmd_at(mm, haddr, pmd, entry); - update_mmu_cache_pmd(vma, address, pmd); - if (is_huge_zero_pmd(orig_pmd)) { - add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); - put_huge_zero_page(); - } else { - VM_BUG_ON(!PageHead(page)); - page_remove_rmap(page); - put_page(page); - } - ret |= VM_FAULT_WRITE; + set_pmd_at(mm, addr, pmd, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } - spin_unlock(&mm->page_table_lock); -out_mn: - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + + folio_mark_lazyfree(folio); + ret = true; out: - return ret; -out_unlock: - spin_unlock(&mm->page_table_lock); + spin_unlock(ptl); +out_unlocked: return ret; } -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags) +static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd) { - struct mm_struct *mm = vma->vm_mm; - struct page *page = NULL; - - assert_spin_locked(&mm->page_table_lock); - - if (flags & FOLL_WRITE && !pmd_write(*pmd)) - goto out; - - /* Avoid dumping huge zero page */ - if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) - return ERR_PTR(-EFAULT); - - 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)); - if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, - pmd, _pmd, 1)) - update_mmu_cache_pmd(vma, addr, pmd); - } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - if (page->mapping && trylock_page(page)) { - lru_add_drain(); - if (page->mapping) - mlock_vma_page(page); - unlock_page(page); - } - } - page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; - VM_BUG_ON(!PageCompound(page)); - if (flags & FOLL_GET) - get_page_foll(page); + pgtable_t pgtable; -out: - return page; + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pte_free(mm, pgtable); + mm_dec_nr_ptes(mm); } -/* NUMA hinting page fault entry point for trans huge pmds */ -int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, pmd_t *pmdp) +int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr) { - struct page *page; - unsigned long haddr = addr & HPAGE_PMD_MASK; - int target_nid; - int current_nid = -1; - bool migrated; - - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) - goto out_unlock; + pmd_t orig_pmd; + spinlock_t *ptl; - page = pmd_page(pmd); - get_page(page); - current_nid = page_to_nid(page); - count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) - count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); - target_nid = mpol_misplaced(page, vma, haddr); - if (target_nid == -1) { - put_page(page); - goto clear_pmdnuma; - } + ptl = __pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + /* + * For architectures like ppc64 we look at deposited pgtable + * when calling pmdp_huge_get_and_clear. So do the + * pgtable_trans_huge_withdraw after finishing pmdp related + * operations. + */ + orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd, + tlb->fullmm); + arch_check_zapped_pmd(vma, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + if (!vma_is_dax(vma) && vma_is_special_huge(vma)) { + if (arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); + spin_unlock(ptl); + } else if (is_huge_zero_pmd(orig_pmd)) { + if (!vma_is_dax(vma) || arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); + spin_unlock(ptl); + } else { + struct folio *folio = NULL; + int flush_needed = 1; - /* Acquire the page lock to serialise THP migrations */ - spin_unlock(&mm->page_table_lock); - lock_page(page); + if (pmd_present(orig_pmd)) { + struct page *page = pmd_page(orig_pmd); - /* Confirm the PTE did not while locked */ - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) { - unlock_page(page); - put_page(page); - goto out_unlock; - } - spin_unlock(&mm->page_table_lock); + folio = page_folio(page); + folio_remove_rmap_pmd(folio, page, vma); + WARN_ON_ONCE(folio_mapcount(folio) < 0); + VM_BUG_ON_PAGE(!PageHead(page), page); + } else if (pmd_is_valid_softleaf(orig_pmd)) { + const softleaf_t entry = softleaf_from_pmd(orig_pmd); - /* Migrate the THP to the requested node */ - migrated = migrate_misplaced_transhuge_page(mm, vma, - pmdp, pmd, addr, page, target_nid); - if (!migrated) - goto check_same; + folio = softleaf_to_folio(entry); + flush_needed = 0; - task_numa_fault(target_nid, HPAGE_PMD_NR, true); - return 0; + if (!thp_migration_supported()) + WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); + } -check_same: - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) - goto out_unlock; -clear_pmdnuma: - pmd = pmd_mknonnuma(pmd); - set_pmd_at(mm, haddr, pmdp, pmd); - VM_BUG_ON(pmd_numa(*pmdp)); - update_mmu_cache_pmd(vma, addr, pmdp); -out_unlock: - spin_unlock(&mm->page_table_lock); - if (current_nid != -1) - task_numa_fault(current_nid, HPAGE_PMD_NR, false); - return 0; -} + if (folio_test_anon(folio)) { + zap_deposited_table(tlb->mm, pmd); + add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); + } else { + if (arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); + add_mm_counter(tlb->mm, mm_counter_file(folio), + -HPAGE_PMD_NR); -int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, - pmd_t *pmd, unsigned long addr) -{ - int ret = 0; + /* + * Use flush_needed to indicate whether the PMD entry + * is present, instead of checking pmd_present() again. + */ + if (flush_needed && pmd_young(orig_pmd) && + likely(vma_has_recency(vma))) + folio_mark_accessed(folio); + } - if (__pmd_trans_huge_lock(pmd, vma) == 1) { - struct page *page; - pgtable_t pgtable; - pmd_t orig_pmd; - /* - * For architectures like ppc64 we look at deposited pgtable - * when calling pmdp_get_and_clear. So do the - * pgtable_trans_huge_withdraw after finishing pmdp related - * operations. - */ - orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd); - tlb_remove_pmd_tlb_entry(tlb, pmd, addr); - pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); - if (is_huge_zero_pmd(orig_pmd)) { - tlb->mm->nr_ptes--; - spin_unlock(&tlb->mm->page_table_lock); - put_huge_zero_page(); - } else { - page = pmd_page(orig_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)); - tlb->mm->nr_ptes--; - spin_unlock(&tlb->mm->page_table_lock); - tlb_remove_page(tlb, page); + if (folio_is_device_private(folio)) { + folio_remove_rmap_pmd(folio, &folio->page, vma); + WARN_ON_ONCE(folio_mapcount(folio) < 0); + folio_put(folio); } - pte_free(tlb->mm, pgtable); - ret = 1; + + spin_unlock(ptl); + if (flush_needed) + tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE); } - return ret; + return 1; } -int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec) +#ifndef pmd_move_must_withdraw +static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, + spinlock_t *old_pmd_ptl, + struct vm_area_struct *vma) { - int ret = 0; + /* + * With split pmd lock we also need to move preallocated + * PTE page table if new_pmd is on different PMD page table. + * + * We also don't deposit and withdraw tables for file pages. + */ + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); +} +#endif - if (__pmd_trans_huge_lock(pmd, vma) == 1) { - /* - * All logical pages in the range are present - * if backed by a huge page. - */ - spin_unlock(&vma->vm_mm->page_table_lock); - memset(vec, 1, (end - addr) >> PAGE_SHIFT); - ret = 1; +static pmd_t move_soft_dirty_pmd(pmd_t pmd) +{ + if (pgtable_supports_soft_dirty()) { + if (unlikely(pmd_is_migration_entry(pmd))) + pmd = pmd_swp_mksoft_dirty(pmd); + else if (pmd_present(pmd)) + pmd = pmd_mksoft_dirty(pmd); } - return ret; + return pmd; } -int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, - unsigned long old_addr, - unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd) +static pmd_t clear_uffd_wp_pmd(pmd_t pmd) { - int ret = 0; - pmd_t pmd; + if (pmd_none(pmd)) + return pmd; + if (pmd_present(pmd)) + pmd = pmd_clear_uffd_wp(pmd); + else + pmd = pmd_swp_clear_uffd_wp(pmd); - struct mm_struct *mm = vma->vm_mm; + return pmd; +} - if ((old_addr & ~HPAGE_PMD_MASK) || - (new_addr & ~HPAGE_PMD_MASK) || - old_end - old_addr < HPAGE_PMD_SIZE || - (new_vma->vm_flags & VM_NOHUGEPAGE)) - goto out; +bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) +{ + spinlock_t *old_ptl, *new_ptl; + pmd_t pmd; + struct mm_struct *mm = vma->vm_mm; + bool force_flush = false; /* * The destination pmd shouldn't be established, free_pgtables() - * should have release it. + * should have released it; but move_page_tables() might have already + * inserted a page table, if racing against shmem/file collapse. */ - if (WARN_ON(!pmd_none(*new_pmd))) { + if (!pmd_none(*new_pmd)) { VM_BUG_ON(pmd_trans_huge(*new_pmd)); - goto out; + return false; } - ret = __pmd_trans_huge_lock(old_pmd, vma); - if (ret == 1) { - pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); + /* + * We don't have to worry about the ordering of src and dst + * ptlocks because exclusive mmap_lock prevents deadlock. + */ + old_ptl = __pmd_trans_huge_lock(old_pmd, vma); + if (old_ptl) { + new_ptl = pmd_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); + if (pmd_present(pmd)) + force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); - set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); - spin_unlock(&mm->page_table_lock); + + if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) { + pgtable_t pgtable; + pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); + pgtable_trans_huge_deposit(mm, new_pmd, pgtable); + } + pmd = move_soft_dirty_pmd(pmd); + if (vma_has_uffd_without_event_remap(vma)) + pmd = clear_uffd_wp_pmd(pmd); + set_pmd_at(mm, new_addr, new_pmd, pmd); + if (force_flush) + flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + spin_unlock(old_ptl); + return true; } -out: - return ret; + return false; } -int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot, int prot_numa) +static void change_non_present_huge_pmd(struct mm_struct *mm, + unsigned long addr, pmd_t *pmd, bool uffd_wp, + bool uffd_wp_resolve) { - struct mm_struct *mm = vma->vm_mm; - int ret = 0; + softleaf_t entry = softleaf_from_pmd(*pmd); + const struct folio *folio = softleaf_to_folio(entry); + pmd_t newpmd; - if (__pmd_trans_huge_lock(pmd, vma) == 1) { - pmd_t entry; - entry = pmdp_get_and_clear(mm, addr, pmd); - if (!prot_numa) { - entry = pmd_modify(entry, newprot); - BUG_ON(pmd_write(entry)); - } else { - struct page *page = pmd_page(*pmd); - - /* only check non-shared pages */ - if (page_mapcount(page) == 1 && - !pmd_numa(*pmd)) { - entry = pmd_mknuma(entry); - } - } - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(&vma->vm_mm->page_table_lock); - ret = 1; + VM_WARN_ON(!pmd_is_valid_softleaf(*pmd)); + if (softleaf_is_migration_write(entry)) { + /* + * A protection check is difficult so + * just be safe and disable write + */ + if (folio_test_anon(folio)) + entry = make_readable_exclusive_migration_entry(swp_offset(entry)); + else + entry = make_readable_migration_entry(swp_offset(entry)); + newpmd = swp_entry_to_pmd(entry); + if (pmd_swp_soft_dirty(*pmd)) + newpmd = pmd_swp_mksoft_dirty(newpmd); + } else if (softleaf_is_device_private_write(entry)) { + entry = make_readable_device_private_entry(swp_offset(entry)); + newpmd = swp_entry_to_pmd(entry); + } else { + newpmd = *pmd; } - return ret; + if (uffd_wp) + newpmd = pmd_swp_mkuffd_wp(newpmd); + else if (uffd_wp_resolve) + newpmd = pmd_swp_clear_uffd_wp(newpmd); + if (!pmd_same(*pmd, newpmd)) + set_pmd_at(mm, addr, pmd, newpmd); } /* - * Returns 1 if a given pmd maps a stable (not under splitting) thp. - * Returns -1 if it maps a thp under splitting. Returns 0 otherwise. - * - * Note that if it returns 1, this routine returns without unlocking page - * table locks. So callers must unlock them. + * Returns + * - 0 if PMD could not be locked + * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary + * or if prot_numa but THP migration is not supported + * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ -int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) -{ - spin_lock(&vma->vm_mm->page_table_lock); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&vma->vm_mm->page_table_lock); - wait_split_huge_page(vma->anon_vma, pmd); - return -1; - } else { - /* Thp mapped by 'pmd' is stable, so we can - * handle it as it is. */ - return 1; - } +int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) +{ + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pmd_t oldpmd, entry; + bool prot_numa = cp_flags & MM_CP_PROT_NUMA; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + int ret = 1; + + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + + if (prot_numa && !thp_migration_supported()) + return 1; + + ptl = __pmd_trans_huge_lock(pmd, vma); + if (!ptl) + return 0; + + if (thp_migration_supported() && pmd_is_valid_softleaf(*pmd)) { + change_non_present_huge_pmd(mm, addr, pmd, uffd_wp, + uffd_wp_resolve); + goto unlock; } - spin_unlock(&vma->vm_mm->page_table_lock); - return 0; -} -pmd_t *page_check_address_pmd(struct page *page, - struct mm_struct *mm, - unsigned long address, - enum page_check_address_pmd_flag flag) -{ - pmd_t *pmd, *ret = NULL; + if (prot_numa) { - if (address & ~HPAGE_PMD_MASK) - goto out; + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (is_huge_zero_pmd(*pmd)) + goto unlock; - pmd = mm_find_pmd(mm, address); - if (!pmd) - goto out; - if (pmd_none(*pmd)) - goto out; - if (pmd_page(*pmd) != page) - goto out; + if (pmd_protnone(*pmd)) + goto unlock; + + if (!folio_can_map_prot_numa(pmd_folio(*pmd), vma, + vma_is_single_threaded_private(vma))) + goto unlock; + } /* - * 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. + * In case prot_numa, we are under mmap_read_lock(mm). It's critical + * to not clear pmd intermittently to avoid race with MADV_DONTNEED + * which is also under mmap_read_lock(mm): + * + * CPU0: CPU1: + * change_huge_pmd(prot_numa=1) + * pmdp_huge_get_and_clear_notify() + * madvise_dontneed() + * zap_pmd_range() + * pmd_trans_huge(*pmd) == 0 (without ptl) + * // skip the pmd + * set_pmd_at(); + * // pmd is re-established + * + * The race makes MADV_DONTNEED miss the huge pmd and don't clear it + * which may break userspace. + * + * pmdp_invalidate_ad() is required to make sure we don't miss + * dirty/young flags set by hardware. */ - if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG && - pmd_trans_splitting(*pmd)) - goto out; - if (pmd_trans_huge(*pmd)) { - VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG && - !pmd_trans_splitting(*pmd)); - ret = pmd; - } -out: - return ret; -} + oldpmd = pmdp_invalidate_ad(vma, addr, pmd); -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; - /* For mmu_notifiers */ - const unsigned long mmun_start = address; - const unsigned long mmun_end = address + HPAGE_PMD_SIZE; - - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); - pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG); - if (pmd) { + entry = pmd_modify(oldpmd, newprot); + if (uffd_wp) + entry = pmd_mkuffd_wp(entry); + else if (uffd_wp_resolve) /* - * 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 - * and it won't wait on the anon_vma->root->rwsem to - * serialize against split_huge_page*. + * Leave the write bit to be handled by PF interrupt + * handler, then things like COW could be properly + * handled. */ - pmdp_splitting_flush(vma, address, pmd); - ret = 1; - } - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + entry = pmd_clear_uffd_wp(entry); + + /* See change_pte_range(). */ + if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) && + can_change_pmd_writable(vma, addr, entry)) + entry = pmd_mkwrite(entry, vma); + + ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); + if (huge_pmd_needs_flush(oldpmd, entry)) + tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE); +unlock: + spin_unlock(ptl); return ret; } -static void __split_huge_page_refcount(struct page *page, - struct list_head *list) +/* + * Returns: + * + * - 0: if pud leaf changed from under us + * - 1: if pud can be skipped + * - HPAGE_PUD_NR: if pud was successfully processed + */ +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pudp, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) { - int i; - struct zone *zone = page_zone(page); - struct lruvec *lruvec; - int tail_count = 0; - - /* prevent PageLRU to go away from under us, and freeze lru stats */ - spin_lock_irq(&zone->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, zone); - - compound_lock(page); - /* complete memcg works before add pages to LRU */ - mem_cgroup_split_huge_fixup(page); - - for (i = HPAGE_PMD_NR - 1; i >= 1; i--) { - struct page *page_tail = page + i; - - /* tail_page->_mapcount cannot change */ - BUG_ON(page_mapcount(page_tail) < 0); - tail_count += page_mapcount(page_tail); - /* check for overflow */ - BUG_ON(tail_count < 0); - BUG_ON(atomic_read(&page_tail->_count) != 0); - /* - * tail_page->_count is zero and not changing from - * under us. But get_page_unless_zero() may be running - * from under us on the tail_page. If we used - * atomic_set() below instead of atomic_add(), we - * would then run atomic_set() concurrently with - * get_page_unless_zero(), and atomic_set() is - * implemented in C not using locked ops. spin_unlock - * on x86 sometime uses locked ops because of PPro - * errata 66, 92, so unless somebody can guarantee - * atomic_set() here would be safe on all archs (and - * not only on x86), it's safer to use atomic_add(). - */ - atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1, - &page_tail->_count); + struct mm_struct *mm = vma->vm_mm; + pud_t oldpud, entry; + spinlock_t *ptl; - /* after clearing PageTail the gup refcount can be released */ - smp_mb(); + tlb_change_page_size(tlb, HPAGE_PUD_SIZE); - /* - * 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; - page_tail->flags |= (page->flags & - ((1L << PG_referenced) | - (1L << PG_swapbacked) | - (1L << PG_mlocked) | - (1L << PG_uptodate))); - page_tail->flags |= (1L << PG_dirty); - - /* clear PageTail before overwriting first_page */ - smp_wmb(); + /* NUMA balancing doesn't apply to dax */ + if (cp_flags & MM_CP_PROT_NUMA) + return 1; - /* - * __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. - */ - page_tail->_mapcount = page->_mapcount; - - BUG_ON(page_tail->mapping); - page_tail->mapping = page->mapping; - - page_tail->index = page->index + i; - page_nid_xchg_last(page_tail, page_nid_last(page)); - - BUG_ON(!PageAnon(page_tail)); - BUG_ON(!PageUptodate(page_tail)); - BUG_ON(!PageDirty(page_tail)); - BUG_ON(!PageSwapBacked(page_tail)); - - lru_add_page_tail(page, page_tail, lruvec, list); - } - atomic_sub(tail_count, &page->_count); - BUG_ON(atomic_read(&page->_count) <= 0); - - __mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1); - __mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR); - - 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); - } + /* + * Huge entries on userfault-wp only works with anonymous, while we + * don't have anonymous PUDs yet. + */ + if (WARN_ON_ONCE(cp_flags & MM_CP_UFFD_WP_ALL)) + return 1; + + ptl = __pud_trans_huge_lock(pudp, vma); + if (!ptl) + return 0; /* - * Only the head page (now become a regular page) is required - * to be pinned by the caller. + * Can't clear PUD or it can race with concurrent zapping. See + * change_huge_pmd(). */ - BUG_ON(page_count(page) <= 0); + oldpud = pudp_invalidate(vma, addr, pudp); + entry = pud_modify(oldpud, newprot); + set_pud_at(mm, addr, pudp, entry); + tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE); + + spin_unlock(ptl); + return HPAGE_PUD_NR; } +#endif -static int __split_huge_page_map(struct page *page, - struct vm_area_struct *vma, - unsigned long address) +#ifdef CONFIG_USERFAULTFD +/* + * The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by + * the caller, but it must return after releasing the page_table_lock. + * Just move the page from src_pmd to dst_pmd if possible. + * Return zero if succeeded in moving the page, -EAGAIN if it needs to be + * repeated by the caller, or other errors in case of failure. + */ +int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + unsigned long dst_addr, unsigned long src_addr) { - 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 = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); - - haddr = address; - for (i = 0; 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); - if (pmd_numa(*pmd)) - entry = pte_mknuma(entry); - pte = pte_offset_map(&_pmd, haddr); - BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); - pte_unmap(pte); - } + pmd_t _dst_pmd, src_pmdval; + struct page *src_page; + struct folio *src_folio; + spinlock_t *src_ptl, *dst_ptl; + pgtable_t src_pgtable; + struct mmu_notifier_range range; + int err = 0; - 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. - */ - pmdp_invalidate(vma, address, pmd); - pmd_populate(mm, pmd, pgtable); - ret = 1; + src_pmdval = *src_pmd; + src_ptl = pmd_lockptr(mm, src_pmd); + + lockdep_assert_held(src_ptl); + vma_assert_locked(src_vma); + vma_assert_locked(dst_vma); + + /* Sanity checks before the operation */ + if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) || + WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) { + spin_unlock(src_ptl); + return -EINVAL; } - spin_unlock(&mm->page_table_lock); - return ret; -} + if (!pmd_trans_huge(src_pmdval)) { + spin_unlock(src_ptl); + if (pmd_is_migration_entry(src_pmdval)) { + pmd_migration_entry_wait(mm, &src_pmdval); + return -EAGAIN; + } + return -ENOENT; + } -/* must be called with anon_vma->root->rwsem held */ -static void __split_huge_page(struct page *page, - struct anon_vma *anon_vma, - struct list_head *list) -{ - int mapcount, mapcount2; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct anon_vma_chain *avc; + src_page = pmd_page(src_pmdval); - BUG_ON(!PageHead(page)); - BUG_ON(PageTail(page)); + if (!is_huge_zero_pmd(src_pmdval)) { + if (unlikely(!PageAnonExclusive(src_page))) { + spin_unlock(src_ptl); + return -EBUSY; + } + + src_folio = page_folio(src_page); + folio_get(src_folio); + } else + src_folio = NULL; + + spin_unlock(src_ptl); + + flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr, + src_addr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + + if (src_folio) + folio_lock(src_folio); - mapcount = 0; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long addr = vma_address(page, vma); - BUG_ON(is_vma_temporary_stack(vma)); - mapcount += __split_huge_page_splitting(page, vma, addr); + dst_ptl = pmd_lockptr(mm, dst_pmd); + double_pt_lock(src_ptl, dst_ptl); + if (unlikely(!pmd_same(*src_pmd, src_pmdval) || + !pmd_same(*dst_pmd, dst_pmdval))) { + err = -EAGAIN; + goto unlock_ptls; } - /* - * 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)); - BUG_ON(mapcount != page_mapcount(page)); + if (src_folio) { + if (folio_maybe_dma_pinned(src_folio) || + !PageAnonExclusive(&src_folio->page)) { + err = -EBUSY; + goto unlock_ptls; + } - __split_huge_page_refcount(page, list); + if (WARN_ON_ONCE(!folio_test_head(src_folio)) || + WARN_ON_ONCE(!folio_test_anon(src_folio))) { + err = -EBUSY; + goto unlock_ptls; + } + + src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); + /* Folio got pinned from under us. Put it back and fail the move. */ + if (folio_maybe_dma_pinned(src_folio)) { + set_pmd_at(mm, src_addr, src_pmd, src_pmdval); + err = -EBUSY; + goto unlock_ptls; + } - mapcount2 = 0; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long addr = vma_address(page, vma); - BUG_ON(is_vma_temporary_stack(vma)); - mapcount2 += __split_huge_page_map(page, vma, addr); + folio_move_anon_rmap(src_folio, dst_vma); + src_folio->index = linear_page_index(dst_vma, dst_addr); + + _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot); + /* Follow mremap() behavior and treat the entry dirty after the move */ + _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); + } else { + src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); + _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot); } - if (mapcount != mapcount2) - printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n", - mapcount, mapcount2, page_mapcount(page)); - BUG_ON(mapcount != mapcount2); + set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); + + src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd); + pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable); +unlock_ptls: + double_pt_unlock(src_ptl, dst_ptl); + /* unblock rmap walks */ + if (src_folio) + folio_unlock(src_folio); + mmu_notifier_invalidate_range_end(&range); + if (src_folio) + folio_put(src_folio); + return err; } +#endif /* CONFIG_USERFAULTFD */ /* - * Split a hugepage into normal pages. This doesn't change the position of head - * page. If @list is null, tail pages will be added to LRU list, otherwise, to - * @list. Both head page and tail pages will inherit mapping, flags, and so on - * from the hugepage. - * Return 0 if the hugepage is split successfully otherwise return 1. + * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. + * + * Note that if it returns page table lock pointer, this routine returns without + * unlocking page table lock. So callers must unlock it. */ -int split_huge_page_to_list(struct page *page, struct list_head *list) +spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { - struct anon_vma *anon_vma; - int ret = 1; + spinlock_t *ptl; - BUG_ON(is_huge_zero_page(page)); - BUG_ON(!PageAnon(page)); + ptl = pmd_lock(vma->vm_mm, pmd); + if (likely(pmd_is_huge(*pmd))) + return ptl; + spin_unlock(ptl); + return NULL; +} - /* - * The caller does not necessarily hold an mmap_sem that would prevent - * the anon_vma disappearing so we first we take a reference to it - * and then lock the anon_vma for write. This is similar to - * page_lock_anon_vma_read except the write lock is taken to serialise - * against parallel split or collapse operations. - */ - anon_vma = page_get_anon_vma(page); - if (!anon_vma) - goto out; - anon_vma_lock_write(anon_vma); +/* + * Returns page table lock pointer if a given pud maps a thp, NULL otherwise. + * + * Note that if it returns page table lock pointer, this routine returns without + * unlocking page table lock. So callers must unlock it. + */ +spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) +{ + spinlock_t *ptl; - ret = 0; - if (!PageCompound(page)) - goto out_unlock; + ptl = pud_lock(vma->vm_mm, pud); + if (likely(pud_trans_huge(*pud))) + return ptl; + spin_unlock(ptl); + return NULL; +} - BUG_ON(!PageSwapBacked(page)); - __split_huge_page(page, anon_vma, list); - count_vm_event(THP_SPLIT); +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pud, unsigned long addr) +{ + spinlock_t *ptl; + pud_t orig_pud; + + ptl = __pud_trans_huge_lock(pud, vma); + if (!ptl) + return 0; + + orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm); + arch_check_zapped_pud(vma, orig_pud); + tlb_remove_pud_tlb_entry(tlb, pud, addr); + if (!vma_is_dax(vma) && vma_is_special_huge(vma)) { + spin_unlock(ptl); + /* No zero page support yet */ + } else { + struct page *page = NULL; + struct folio *folio; + + /* No support for anonymous PUD pages or migration yet */ + VM_WARN_ON_ONCE(vma_is_anonymous(vma) || + !pud_present(orig_pud)); + + page = pud_page(orig_pud); + folio = page_folio(page); + folio_remove_rmap_pud(folio, page, vma); + add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PUD_NR); + + spin_unlock(ptl); + tlb_remove_page_size(tlb, page, HPAGE_PUD_SIZE); + } + return 1; +} + +static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, + unsigned long haddr) +{ + struct folio *folio; + struct page *page; + pud_t old_pud; + + VM_BUG_ON(haddr & ~HPAGE_PUD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); + VM_BUG_ON(!pud_trans_huge(*pud)); + + count_vm_event(THP_SPLIT_PUD); + + old_pud = pudp_huge_clear_flush(vma, haddr, pud); + + if (!vma_is_dax(vma)) + return; + + page = pud_page(old_pud); + folio = page_folio(page); + + if (!folio_test_dirty(folio) && pud_dirty(old_pud)) + folio_mark_dirty(folio); + if (!folio_test_referenced(folio) && pud_young(old_pud)) + folio_set_referenced(folio); + folio_remove_rmap_pud(folio, page, vma); + folio_put(folio); + add_mm_counter(vma->vm_mm, mm_counter_file(folio), + -HPAGE_PUD_NR); +} + +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ + spinlock_t *ptl; + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, + address & HPAGE_PUD_MASK, + (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE); + mmu_notifier_invalidate_range_start(&range); + ptl = pud_lock(vma->vm_mm, pud); + if (unlikely(!pud_trans_huge(*pud))) + goto out; + __split_huge_pud_locked(vma, pud, range.start); - BUG_ON(PageCompound(page)); -out_unlock: - anon_vma_unlock_write(anon_vma); - put_anon_vma(anon_vma); out: - return ret; + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(&range); +} +#else +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ } +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + +static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, + unsigned long haddr, pmd_t *pmd) +{ + struct mm_struct *mm = vma->vm_mm; + pgtable_t pgtable; + pmd_t _pmd, old_pmd; + unsigned long addr; + pte_t *pte; + int i; + + /* + * Leave pmd empty until pte is filled note that it is fine to delay + * notification until mmu_notifier_invalidate_range_end() as we are + * replacing a zero pmd write protected page with a zero pte write + * protected page. + * + * See Documentation/mm/mmu_notifier.rst + */ + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); + + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte); + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { + pte_t entry; -#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) + entry = pfn_pte(my_zero_pfn(addr), vma->vm_page_prot); + entry = pte_mkspecial(entry); + if (pmd_uffd_wp(old_pmd)) + entry = pte_mkuffd_wp(entry); + VM_BUG_ON(!pte_none(ptep_get(pte))); + set_pte_at(mm, addr, pte, entry); + pte++; + } + pte_unmap(pte - 1); + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); +} -int hugepage_madvise(struct vm_area_struct *vma, - unsigned long *vm_flags, int advice) +static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long haddr, bool freeze) { struct mm_struct *mm = vma->vm_mm; + struct folio *folio; + struct page *page; + pgtable_t pgtable; + pmd_t old_pmd, _pmd; + bool soft_dirty, uffd_wp = false, young = false, write = false; + bool anon_exclusive = false, dirty = false; + unsigned long addr; + pte_t *pte; + int i; + + VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); + + VM_WARN_ON_ONCE(!pmd_is_valid_softleaf(*pmd) && !pmd_trans_huge(*pmd)); - switch (advice) { - case MADV_HUGEPAGE: + count_vm_event(THP_SPLIT_PMD); + + if (!vma_is_anonymous(vma)) { + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); /* - * Be somewhat over-protective like KSM for now! + * We are going to unmap this huge page. So + * just go ahead and zap it */ - if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) - return -EINVAL; - if (mm->def_flags & VM_NOHUGEPAGE) - return -EINVAL; - *vm_flags &= ~VM_NOHUGEPAGE; - *vm_flags |= VM_HUGEPAGE; + if (arch_needs_pgtable_deposit()) + zap_deposited_table(mm, pmd); + if (!vma_is_dax(vma) && vma_is_special_huge(vma)) + return; + if (unlikely(pmd_is_migration_entry(old_pmd))) { + const softleaf_t old_entry = softleaf_from_pmd(old_pmd); + + folio = softleaf_to_folio(old_entry); + } else if (is_huge_zero_pmd(old_pmd)) { + return; + } else { + page = pmd_page(old_pmd); + folio = page_folio(page); + if (!folio_test_dirty(folio) && pmd_dirty(old_pmd)) + folio_mark_dirty(folio); + if (!folio_test_referenced(folio) && pmd_young(old_pmd)) + folio_set_referenced(folio); + folio_remove_rmap_pmd(folio, page, vma); + folio_put(folio); + } + add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR); + return; + } + + if (is_huge_zero_pmd(*pmd)) { /* - * If the vma become good for khugepaged to scan, - * register it here without waiting a page fault that - * may not happen any time soon. + * FIXME: Do we want to invalidate secondary mmu by calling + * mmu_notifier_arch_invalidate_secondary_tlbs() see comments below + * inside __split_huge_pmd() ? + * + * We are going from a zero huge page write protected to zero + * small page also write protected so it does not seems useful + * to invalidate secondary mmu at this time. */ - if (unlikely(khugepaged_enter_vma_merge(vma))) - return -ENOMEM; - break; - case MADV_NOHUGEPAGE: + return __split_huge_zero_page_pmd(vma, haddr, pmd); + } + + if (pmd_is_migration_entry(*pmd)) { + softleaf_t entry; + + old_pmd = *pmd; + entry = softleaf_from_pmd(old_pmd); + page = softleaf_to_page(entry); + folio = page_folio(page); + + soft_dirty = pmd_swp_soft_dirty(old_pmd); + uffd_wp = pmd_swp_uffd_wp(old_pmd); + + write = softleaf_is_migration_write(entry); + if (PageAnon(page)) + anon_exclusive = softleaf_is_migration_read_exclusive(entry); + young = softleaf_is_migration_young(entry); + dirty = softleaf_is_migration_dirty(entry); + } else if (pmd_is_device_private_entry(*pmd)) { + softleaf_t entry; + + old_pmd = *pmd; + entry = softleaf_from_pmd(old_pmd); + page = softleaf_to_page(entry); + folio = page_folio(page); + + soft_dirty = pmd_swp_soft_dirty(old_pmd); + uffd_wp = pmd_swp_uffd_wp(old_pmd); + + write = softleaf_is_device_private_write(entry); + anon_exclusive = PageAnonExclusive(page); + + /* + * Device private THP should be treated the same as regular + * folios w.r.t anon exclusive handling. See the comments for + * folio handling and anon_exclusive below. + */ + if (freeze && anon_exclusive && + folio_try_share_anon_rmap_pmd(folio, page)) + freeze = false; + if (!freeze) { + rmap_t rmap_flags = RMAP_NONE; + + folio_ref_add(folio, HPAGE_PMD_NR - 1); + if (anon_exclusive) + rmap_flags |= RMAP_EXCLUSIVE; + + folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR, + vma, haddr, rmap_flags); + } + } else { /* - * Be somewhat over-protective like KSM for now! + * 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/TechDocs/41322_10h_Rev_Gd.pdf, Erratum + * 383 on page 105. 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_pmd_tlb_range();" we first mark the current pmd + * notpresent (atomically because here the pmd_trans_huge 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. */ - if (*vm_flags & (VM_NOHUGEPAGE | VM_NO_THP)) - return -EINVAL; - *vm_flags &= ~VM_HUGEPAGE; - *vm_flags |= VM_NOHUGEPAGE; + old_pmd = pmdp_invalidate(vma, haddr, pmd); + page = pmd_page(old_pmd); + folio = page_folio(page); + if (pmd_dirty(old_pmd)) { + dirty = true; + folio_set_dirty(folio); + } + write = pmd_write(old_pmd); + young = pmd_young(old_pmd); + soft_dirty = pmd_soft_dirty(old_pmd); + uffd_wp = pmd_uffd_wp(old_pmd); + + VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + /* - * 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. + * Without "freeze", we'll simply split the PMD, propagating the + * PageAnonExclusive() flag for each PTE by setting it for + * each subpage -- no need to (temporarily) clear. + * + * With "freeze" we want to replace mapped pages by + * migration entries right away. This is only possible if we + * managed to clear PageAnonExclusive() -- see + * set_pmd_migration_entry(). + * + * In case we cannot clear PageAnonExclusive(), split the PMD + * only and let try_to_migrate_one() fail later. + * + * See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ - break; + anon_exclusive = PageAnonExclusive(page); + if (freeze && anon_exclusive && + folio_try_share_anon_rmap_pmd(folio, page)) + freeze = false; + if (!freeze) { + rmap_t rmap_flags = RMAP_NONE; + + folio_ref_add(folio, HPAGE_PMD_NR - 1); + if (anon_exclusive) + rmap_flags |= RMAP_EXCLUSIVE; + folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR, + vma, haddr, rmap_flags); + } } - return 0; -} + /* + * Withdraw the table only after we mark the pmd entry invalid. + * This's critical for some architectures (Power). + */ + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); -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; + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte); - return 0; + /* + * Note that NUMA hinting access restrictions are not transferred to + * avoid any possibility of altering permissions across VMAs. + */ + if (freeze || pmd_is_migration_entry(old_pmd)) { + pte_t entry; + swp_entry_t swp_entry; + + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { + if (write) + swp_entry = make_writable_migration_entry( + page_to_pfn(page + i)); + else if (anon_exclusive) + swp_entry = make_readable_exclusive_migration_entry( + page_to_pfn(page + i)); + else + swp_entry = make_readable_migration_entry( + page_to_pfn(page + i)); + if (young) + swp_entry = make_migration_entry_young(swp_entry); + if (dirty) + swp_entry = make_migration_entry_dirty(swp_entry); + entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); + if (uffd_wp) + entry = pte_swp_mkuffd_wp(entry); + VM_WARN_ON(!pte_none(ptep_get(pte + i))); + set_pte_at(mm, addr, pte + i, entry); + } + } else if (pmd_is_device_private_entry(old_pmd)) { + pte_t entry; + swp_entry_t swp_entry; + + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { + /* + * anon_exclusive was already propagated to the relevant + * pages corresponding to the pte entries when freeze + * is false. + */ + if (write) + swp_entry = make_writable_device_private_entry( + page_to_pfn(page + i)); + else + swp_entry = make_readable_device_private_entry( + page_to_pfn(page + i)); + /* + * Young and dirty bits are not progated via swp_entry + */ + entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); + if (uffd_wp) + entry = pte_swp_mkuffd_wp(entry); + VM_WARN_ON(!pte_none(ptep_get(pte + i))); + set_pte_at(mm, addr, pte + i, entry); + } + } else { + pte_t entry; + + entry = mk_pte(page, READ_ONCE(vma->vm_page_prot)); + if (write) + entry = pte_mkwrite(entry, vma); + if (!young) + entry = pte_mkold(entry); + /* NOTE: this may set soft-dirty too on some archs */ + if (dirty) + entry = pte_mkdirty(entry); + if (soft_dirty) + entry = pte_mksoft_dirty(entry); + if (uffd_wp) + entry = pte_mkuffd_wp(entry); + + for (i = 0; i < HPAGE_PMD_NR; i++) + VM_WARN_ON(!pte_none(ptep_get(pte + i))); + + set_ptes(mm, haddr, pte, entry, HPAGE_PMD_NR); + } + pte_unmap(pte); + + if (!pmd_is_migration_entry(*pmd)) + folio_remove_rmap_pmd(folio, page, vma); + if (freeze) + put_page(page); + + smp_wmb(); /* make pte visible before pmd */ + pmd_populate(mm, pmd, pgtable); } -static inline struct mm_slot *alloc_mm_slot(void) +void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, bool freeze) { - if (!mm_slot_cache) /* initialization failed */ - return NULL; - return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); + VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE)); + if (pmd_trans_huge(*pmd) || pmd_is_valid_softleaf(*pmd)) + __split_huge_pmd_locked(vma, pmd, address, freeze); } -static inline void free_mm_slot(struct mm_slot *mm_slot) +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address, bool freeze) { - kmem_cache_free(mm_slot_cache, mm_slot); + spinlock_t *ptl; + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, + address & HPAGE_PMD_MASK, + (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + ptl = pmd_lock(vma->vm_mm, pmd); + split_huge_pmd_locked(vma, range.start, pmd, freeze); + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(&range); } -static struct mm_slot *get_mm_slot(struct mm_struct *mm) +void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, + bool freeze) { - struct mm_slot *mm_slot; + pmd_t *pmd = mm_find_pmd(vma->vm_mm, address); - hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) - if (mm == mm_slot->mm) - return mm_slot; + if (!pmd) + return; - return NULL; + __split_huge_pmd(vma, pmd, address, freeze); } -static void insert_to_mm_slots_hash(struct mm_struct *mm, - struct mm_slot *mm_slot) +static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) { - mm_slot->mm = mm; - hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); + /* + * If the new address isn't hpage aligned and it could previously + * contain an hugepage: check if we need to split an huge pmd. + */ + if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) && + range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE), + ALIGN(address, HPAGE_PMD_SIZE))) + split_huge_pmd_address(vma, address, false); } -static inline int khugepaged_test_exit(struct mm_struct *mm) +void vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + struct vm_area_struct *next) { - return atomic_read(&mm->mm_users) == 0; + /* Check if we need to split start first. */ + split_huge_pmd_if_needed(vma, start); + + /* Check if we need to split end next. */ + split_huge_pmd_if_needed(vma, end); + + /* If we're incrementing next->vm_start, we might need to split it. */ + if (next) + split_huge_pmd_if_needed(next, end); } -int __khugepaged_enter(struct mm_struct *mm) +static void unmap_folio(struct folio *folio) { - struct mm_slot *mm_slot; - int wakeup; + enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC | + TTU_BATCH_FLUSH; - mm_slot = alloc_mm_slot(); - if (!mm_slot) - return -ENOMEM; + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); - /* __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; + if (folio_test_pmd_mappable(folio)) + ttu_flags |= TTU_SPLIT_HUGE_PMD; + + /* + * Anon pages need migration entries to preserve them, but file + * pages can simply be left unmapped, then faulted back on demand. + * If that is ever changed (perhaps for mlock), update remap_page(). + */ + if (folio_test_anon(folio)) + try_to_migrate(folio, ttu_flags); + else + try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); + + try_to_unmap_flush(); +} + +static bool __discard_anon_folio_pmd_locked(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp, + struct folio *folio) +{ + struct mm_struct *mm = vma->vm_mm; + int ref_count, map_count; + pmd_t orig_pmd = *pmdp; + + if (pmd_dirty(orig_pmd)) + folio_set_dirty(folio); + if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { + folio_set_swapbacked(folio); + return false; } - spin_lock(&khugepaged_mm_lock); - insert_to_mm_slots_hash(mm, mm_slot); + orig_pmd = pmdp_huge_clear_flush(vma, addr, pmdp); + /* - * Insert just behind the scanning cursor, to let the area settle - * down a little. + * Syncing against concurrent GUP-fast: + * - clear PMD; barrier; read refcount + * - inc refcount; barrier; read PMD */ - wakeup = list_empty(&khugepaged_scan.mm_head); - list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); - spin_unlock(&khugepaged_mm_lock); + smp_mb(); - atomic_inc(&mm->mm_count); - if (wakeup) - wake_up_interruptible(&khugepaged_wait); + ref_count = folio_ref_count(folio); + map_count = folio_mapcount(folio); - return 0; + /* + * Order reads for folio refcount and dirty flag + * (see comments in __remove_mapping()). + */ + smp_rmb(); + + /* + * If the folio or its PMD is redirtied at this point, or if there + * are unexpected references, we will give up to discard this folio + * and remap it. + * + * The only folio refs must be one from isolation plus the rmap(s). + */ + if (pmd_dirty(orig_pmd)) + folio_set_dirty(folio); + if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { + folio_set_swapbacked(folio); + set_pmd_at(mm, addr, pmdp, orig_pmd); + return false; + } + + if (ref_count != map_count + 1) { + set_pmd_at(mm, addr, pmdp, orig_pmd); + return false; + } + + folio_remove_rmap_pmd(folio, pmd_page(orig_pmd), vma); + zap_deposited_table(mm, pmdp); + add_mm_counter(mm, MM_ANONPAGES, -HPAGE_PMD_NR); + if (vma->vm_flags & VM_LOCKED) + mlock_drain_local(); + folio_put(folio); + + return true; } -int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmdp, struct folio *folio) { - 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; - if (vma->vm_ops) - /* khugepaged not yet working on file or special mappings */ - return 0; - VM_BUG_ON(vma->vm_flags & VM_NO_THP); - 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; + VM_WARN_ON_FOLIO(!folio_test_pmd_mappable(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + VM_WARN_ON_FOLIO(folio_test_swapbacked(folio), folio); + VM_WARN_ON_ONCE(!IS_ALIGNED(addr, HPAGE_PMD_SIZE)); + + return __discard_anon_folio_pmd_locked(vma, addr, pmdp, folio); } -void __khugepaged_exit(struct mm_struct *mm) +static void remap_page(struct folio *folio, unsigned long nr, int flags) { - struct mm_slot *mm_slot; - int free = 0; + int i = 0; - spin_lock(&khugepaged_mm_lock); - mm_slot = get_mm_slot(mm); - if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { - hash_del(&mm_slot->hash); - list_del(&mm_slot->mm_node); - free = 1; + /* If unmap_folio() uses try_to_migrate() on file, remove this check */ + if (!folio_test_anon(folio)) + return; + for (;;) { + remove_migration_ptes(folio, folio, RMP_LOCKED | flags); + i += folio_nr_pages(folio); + if (i >= nr) + break; + folio = folio_next(folio); } - spin_unlock(&khugepaged_mm_lock); +} - if (free) { - clear_bit(MMF_VM_HUGEPAGE, &mm->flags); - free_mm_slot(mm_slot); - mmdrop(mm); - } else if (mm_slot) { - /* - * This is required to serialize against - * khugepaged_test_exit() (which is guaranteed to run - * under mmap sem read mode). Stop here (after we - * return all pagetables will be destroyed) until - * khugepaged has finished working on the pagetables - * under the mmap_sem. - */ - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); +static void lru_add_split_folio(struct folio *folio, struct folio *new_folio, + struct lruvec *lruvec, struct list_head *list) +{ + VM_BUG_ON_FOLIO(folio_test_lru(new_folio), folio); + lockdep_assert_held(&lruvec->lru_lock); + + if (folio_is_device_private(folio)) + return; + + if (list) { + /* page reclaim is reclaiming a huge page */ + VM_WARN_ON(folio_test_lru(folio)); + folio_get(new_folio); + list_add_tail(&new_folio->lru, list); + } else { + /* head is still on lru (and we have it frozen) */ + VM_WARN_ON(!folio_test_lru(folio)); + if (folio_test_unevictable(folio)) + new_folio->mlock_count = 0; + else + list_add_tail(&new_folio->lru, &folio->lru); + folio_set_lru(new_folio); } } -static void release_pte_page(struct page *page) +/* Racy check whether the huge page can be split */ +bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { - /* 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); + int extra_pins; + + /* Additional pins from page cache */ + if (folio_test_anon(folio)) + extra_pins = folio_test_swapcache(folio) ? + folio_nr_pages(folio) : 0; + else + extra_pins = folio_nr_pages(folio); + if (pextra_pins) + *pextra_pins = extra_pins; + return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - + caller_pins; } -static void release_pte_pages(pte_t *pte, pte_t *_pte) +static bool page_range_has_hwpoisoned(struct page *page, long nr_pages) { - while (--_pte >= pte) { - pte_t pteval = *_pte; - if (!pte_none(pteval)) - release_pte_page(pte_page(pteval)); - } + for (; nr_pages; page++, nr_pages--) + if (PageHWPoison(page)) + return true; + return false; } -static int __collapse_huge_page_isolate(struct vm_area_struct *vma, - unsigned long address, - pte_t *pte) +/* + * It splits @folio into @new_order folios and copies the @folio metadata to + * all the resulting folios. + */ +static void __split_folio_to_order(struct folio *folio, int old_order, + int new_order) { - struct page *page; - pte_t *_pte; - int referenced = 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 - goto out; - } - if (!pte_present(pteval) || !pte_write(pteval)) - goto out; - page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) - goto out; + /* Scan poisoned pages when split a poisoned folio to large folios */ + const bool handle_hwpoison = folio_test_has_hwpoisoned(folio) && new_order; + long new_nr_pages = 1 << new_order; + long nr_pages = 1 << old_order; + long i; + + folio_clear_has_hwpoisoned(folio); + + /* Check first new_nr_pages since the loop below skips them */ + if (handle_hwpoison && + page_range_has_hwpoisoned(folio_page(folio, 0), new_nr_pages)) + folio_set_has_hwpoisoned(folio); + /* + * Skip the first new_nr_pages, since the new folio from them have all + * the flags from the original folio. + */ + for (i = new_nr_pages; i < nr_pages; i += new_nr_pages) { + struct page *new_head = &folio->page + i; + /* + * Careful: new_folio is not a "real" folio before we cleared PageTail. + * Don't pass it around before clear_compound_head(). + */ + struct folio *new_folio = (struct folio *)new_head; - VM_BUG_ON(PageCompound(page)); - BUG_ON(!PageAnon(page)); - VM_BUG_ON(!PageSwapBacked(page)); + VM_BUG_ON_PAGE(atomic_read(&new_folio->_mapcount) != -1, new_head); - /* cannot use mapcount: can't collapse if there's a gup pin */ - if (page_count(page) != 1) - 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. + * Clone page flags before unfreezing refcount. + * + * After successful get_page_unless_zero() might follow flags change, + * for example lock_page() which set PG_waiters. + * + * Note that for mapped sub-pages of an anonymous THP, + * PG_anon_exclusive has been cleared in unmap_folio() and is stored in + * the migration entry instead from where remap_page() will restore it. + * We can still have PG_anon_exclusive set on effectively unmapped and + * unreferenced sub-pages of an anonymous THP: we can simply drop + * PG_anon_exclusive (-> PG_mappedtodisk) for these here. */ - if (!trylock_page(page)) - goto out; + new_folio->flags.f &= ~PAGE_FLAGS_CHECK_AT_PREP; + new_folio->flags.f |= (folio->flags.f & + ((1L << PG_referenced) | + (1L << PG_swapbacked) | + (1L << PG_swapcache) | + (1L << PG_mlocked) | + (1L << PG_uptodate) | + (1L << PG_active) | + (1L << PG_workingset) | + (1L << PG_locked) | + (1L << PG_unevictable) | +#ifdef CONFIG_ARCH_USES_PG_ARCH_2 + (1L << PG_arch_2) | +#endif +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 + (1L << PG_arch_3) | +#endif + (1L << PG_dirty) | + LRU_GEN_MASK | LRU_REFS_MASK)); + + if (handle_hwpoison && + page_range_has_hwpoisoned(new_head, new_nr_pages)) + folio_set_has_hwpoisoned(new_folio); + + new_folio->mapping = folio->mapping; + new_folio->index = folio->index + i; + + if (folio_test_swapcache(folio)) + new_folio->swap.val = folio->swap.val + i; + + /* Page flags must be visible before we make the page non-compound. */ + smp_wmb(); + /* - * Isolate the page to avoid collapsing an hugepage - * currently in use by the VM. + * Clear PageTail before unfreezing page refcount. + * + * After successful get_page_unless_zero() might follow put_page() + * which needs correct compound_head(). */ - if (isolate_lru_page(page)) { - unlock_page(page); - goto out; + clear_compound_head(new_head); + if (new_order) { + prep_compound_page(new_head, new_order); + folio_set_large_rmappable(new_folio); } - /* 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 */ - if (pte_young(pteval) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) - referenced = 1; + if (folio_test_young(folio)) + folio_set_young(new_folio); + if (folio_test_idle(folio)) + folio_set_idle(new_folio); +#ifdef CONFIG_MEMCG + new_folio->memcg_data = folio->memcg_data; +#endif + + folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio)); } - if (likely(referenced)) - return 1; -out: - release_pte_pages(pte, _pte); - return 0; + + if (new_order) + folio_set_order(folio, new_order); + else + ClearPageCompound(&folio->page); } -static void __collapse_huge_page_copy(pte_t *pte, struct page *page, - struct vm_area_struct *vma, - unsigned long address, - spinlock_t *ptl) +/** + * __split_unmapped_folio() - splits an unmapped @folio to lower order folios in + * two ways: uniform split or non-uniform split. + * @folio: the to-be-split folio + * @new_order: the smallest order of the after split folios (since buddy + * allocator like split generates folios with orders from @folio's + * order - 1 to new_order). + * @split_at: in buddy allocator like split, the folio containing @split_at + * will be split until its order becomes @new_order. + * @xas: xa_state pointing to folio->mapping->i_pages and locked by caller + * @mapping: @folio->mapping + * @split_type: if the split is uniform or not (buddy allocator like split) + * + * + * 1. uniform split: the given @folio into multiple @new_order small folios, + * where all small folios have the same order. This is done when + * split_type is SPLIT_TYPE_UNIFORM. + * 2. buddy allocator like (non-uniform) split: the given @folio is split into + * half and one of the half (containing the given page) is split into half + * until the given @folio's order becomes @new_order. This is done when + * split_type is SPLIT_TYPE_NON_UNIFORM. + * + * The high level flow for these two methods are: + * + * 1. uniform split: @xas is split with no expectation of failure and a single + * __split_folio_to_order() is called to split the @folio into @new_order + * along with stats update. + * 2. non-uniform split: folio_order - @new_order calls to + * __split_folio_to_order() are expected to be made in a for loop to split + * the @folio to one lower order at a time. The folio containing @split_at + * is split in each iteration. @xas is split into half in each iteration and + * can fail. A failed @xas split leaves split folios as is without merging + * them back. + * + * After splitting, the caller's folio reference will be transferred to the + * folio containing @split_at. The caller needs to unlock and/or free + * after-split folios if necessary. + * + * Return: 0 - successful, <0 - failed (if -ENOMEM is returned, @folio might be + * split but not to @new_order, the caller needs to check) + */ +static int __split_unmapped_folio(struct folio *folio, int new_order, + struct page *split_at, struct xa_state *xas, + struct address_space *mapping, enum split_type split_type) { - pte_t *_pte; - for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) { - pte_t pteval = *_pte; - struct page *src_page; + const bool is_anon = folio_test_anon(folio); + int old_order = folio_order(folio); + int start_order = split_type == SPLIT_TYPE_UNIFORM ? new_order : old_order - 1; + int split_order; - 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); - 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); + /* + * split to new_order one order at a time. For uniform split, + * folio is split to new_order directly. + */ + for (split_order = start_order; + split_order >= new_order; + split_order--) { + int nr_new_folios = 1UL << (old_order - split_order); + + /* order-1 anonymous folio is not supported */ + if (is_anon && split_order == 1) + continue; + + if (mapping) { /* - * paravirt calls inside pte_clear here are - * superfluous. + * uniform split has xas_split_alloc() called before + * irq is disabled to allocate enough memory, whereas + * non-uniform split can handle ENOMEM. */ - pte_clear(vma->vm_mm, address, _pte); - page_remove_rmap(src_page); - spin_unlock(ptl); - free_page_and_swap_cache(src_page); + if (split_type == SPLIT_TYPE_UNIFORM) + xas_split(xas, folio, old_order); + else { + xas_set_order(xas, folio->index, split_order); + xas_try_split(xas, folio, old_order); + if (xas_error(xas)) + return xas_error(xas); + } } - address += PAGE_SIZE; - page++; + folio_split_memcg_refs(folio, old_order, split_order); + split_page_owner(&folio->page, old_order, split_order); + pgalloc_tag_split(folio, old_order, split_order); + __split_folio_to_order(folio, old_order, split_order); + + if (is_anon) { + mod_mthp_stat(old_order, MTHP_STAT_NR_ANON, -1); + mod_mthp_stat(split_order, MTHP_STAT_NR_ANON, nr_new_folios); + } + /* + * If uniform split, the process is complete. + * If non-uniform, continue splitting the folio at @split_at + * as long as the next @split_order is >= @new_order. + */ + folio = page_folio(split_at); + old_order = split_order; } -} -static void khugepaged_alloc_sleep(void) -{ - wait_event_freezable_timeout(khugepaged_wait, false, - msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); + return 0; } -#ifdef CONFIG_NUMA -static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) +bool folio_split_supported(struct folio *folio, unsigned int new_order, + enum split_type split_type, bool warns) { - if (IS_ERR(*hpage)) { - if (!*wait) + if (folio_test_anon(folio)) { + /* order-1 is not supported for anonymous THP. */ + VM_WARN_ONCE(warns && new_order == 1, + "Cannot split to order-1 folio"); + if (new_order == 1) + return false; + } else if (split_type == SPLIT_TYPE_NON_UNIFORM || new_order) { + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && + !mapping_large_folio_support(folio->mapping)) { + /* + * We can always split a folio down to a single page + * (new_order == 0) uniformly. + * + * For any other scenario + * a) uniform split targeting a large folio + * (new_order > 0) + * b) any non-uniform split + * we must confirm that the file system supports large + * folios. + * + * Note that we might still have THPs in such + * mappings, which is created from khugepaged when + * CONFIG_READ_ONLY_THP_FOR_FS is enabled. But in that + * case, the mapping does not actually support large + * folios properly. + */ + VM_WARN_ONCE(warns, + "Cannot split file folio to non-0 order"); return false; + } + } - *wait = false; - *hpage = NULL; - khugepaged_alloc_sleep(); - } else if (*hpage) { - put_page(*hpage); - *hpage = NULL; + /* + * swapcache folio could only be split to order 0 + * + * non-uniform split creates after-split folios with orders from + * folio_order(folio) - 1 to new_order, making it not suitable for any + * swapcache folio split. Only uniform split to order-0 can be used + * here. + */ + if ((split_type == SPLIT_TYPE_NON_UNIFORM || new_order) && folio_test_swapcache(folio)) { + VM_WARN_ONCE(warns, + "Cannot split swapcache folio to non-0 order"); + return false; } return true; } -static struct page -*khugepaged_alloc_page(struct page **hpage, struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - int node) +static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int new_order, + struct page *split_at, struct xa_state *xas, + struct address_space *mapping, bool do_lru, + struct list_head *list, enum split_type split_type, + pgoff_t end, int *nr_shmem_dropped, int extra_pins) { - VM_BUG_ON(*hpage); + struct folio *end_folio = folio_next(folio); + struct folio *new_folio, *next; + int old_order = folio_order(folio); + int ret = 0; + struct deferred_split *ds_queue; + + VM_WARN_ON_ONCE(!mapping && end); + /* Prevent deferred_split_scan() touching ->_refcount */ + ds_queue = folio_split_queue_lock(folio); + if (folio_ref_freeze(folio, 1 + extra_pins)) { + struct swap_cluster_info *ci = NULL; + struct lruvec *lruvec; + int expected_refs; + + if (old_order > 1) { + if (!list_empty(&folio->_deferred_list)) { + ds_queue->split_queue_len--; + /* + * Reinitialize page_deferred_list after removing the + * page from the split_queue, otherwise a subsequent + * split will see list corruption when checking the + * page_deferred_list. + */ + list_del_init(&folio->_deferred_list); + } + if (folio_test_partially_mapped(folio)) { + folio_clear_partially_mapped(folio); + mod_mthp_stat(old_order, + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } + } + split_queue_unlock(ds_queue); + if (mapping) { + int nr = folio_nr_pages(folio); + + if (folio_test_pmd_mappable(folio) && + new_order < HPAGE_PMD_ORDER) { + if (folio_test_swapbacked(folio)) { + lruvec_stat_mod_folio(folio, + NR_SHMEM_THPS, -nr); + } else { + lruvec_stat_mod_folio(folio, + NR_FILE_THPS, -nr); + filemap_nr_thps_dec(mapping); + } + } + } + + if (folio_test_swapcache(folio)) { + if (mapping) { + VM_WARN_ON_ONCE_FOLIO(mapping, folio); + return -EINVAL; + } + + ci = swap_cluster_get_and_lock(folio); + } + + /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ + if (do_lru) + lruvec = folio_lruvec_lock(folio); + + ret = __split_unmapped_folio(folio, new_order, split_at, xas, + mapping, split_type); + + /* + * Unfreeze after-split folios and put them back to the right + * list. @folio should be kept frozon until page cache + * entries are updated with all the other after-split folios + * to prevent others seeing stale page cache entries. + * As a result, new_folio starts from the next folio of + * @folio. + */ + for (new_folio = folio_next(folio); new_folio != end_folio; + new_folio = next) { + unsigned long nr_pages = folio_nr_pages(new_folio); + + next = folio_next(new_folio); + + zone_device_private_split_cb(folio, new_folio); + + expected_refs = folio_expected_ref_count(new_folio) + 1; + folio_ref_unfreeze(new_folio, expected_refs); + + if (do_lru) + lru_add_split_folio(folio, new_folio, lruvec, list); + + /* + * Anonymous folio with swap cache. + * NOTE: shmem in swap cache is not supported yet. + */ + if (ci) { + __swap_cache_replace_folio(ci, folio, new_folio); + continue; + } + + /* Anonymous folio without swap cache */ + if (!mapping) + continue; + + /* Add the new folio to the page cache. */ + if (new_folio->index < end) { + __xa_store(&mapping->i_pages, new_folio->index, + new_folio, 0); + continue; + } + + VM_WARN_ON_ONCE(!nr_shmem_dropped); + /* Drop folio beyond EOF: ->index >= end */ + if (shmem_mapping(mapping) && nr_shmem_dropped) + *nr_shmem_dropped += nr_pages; + else if (folio_test_clear_dirty(new_folio)) + folio_account_cleaned( + new_folio, inode_to_wb(mapping->host)); + __filemap_remove_folio(new_folio, NULL); + folio_put_refs(new_folio, nr_pages); + } + + zone_device_private_split_cb(folio, NULL); + /* + * Unfreeze @folio only after all page cache entries, which + * used to point to it, have been updated with new folios. + * Otherwise, a parallel folio_try_get() can grab @folio + * and its caller can see stale page cache entries. + */ + expected_refs = folio_expected_ref_count(folio) + 1; + folio_ref_unfreeze(folio, expected_refs); + + if (do_lru) + unlock_page_lruvec(lruvec); + + if (ci) + swap_cluster_unlock(ci); + } else { + split_queue_unlock(ds_queue); + return -EAGAIN; + } + + return ret; +} + +/** + * __folio_split() - split a folio at @split_at to a @new_order folio + * @folio: folio to split + * @new_order: the order of the new folio + * @split_at: a page within the new folio + * @lock_at: a page within @folio to be left locked to caller + * @list: after-split folios will be put on it if non NULL + * @split_type: perform uniform split or not (non-uniform split) + * + * It calls __split_unmapped_folio() to perform uniform and non-uniform split. + * It is in charge of checking whether the split is supported or not and + * preparing @folio for __split_unmapped_folio(). + * + * After splitting, the after-split folio containing @lock_at remains locked + * and others are unlocked: + * 1. for uniform split, @lock_at points to one of @folio's subpages; + * 2. for buddy allocator like (non-uniform) split, @lock_at points to @folio. + * + * Return: 0 - successful, <0 - failed (if -ENOMEM is returned, @folio might be + * split but not to @new_order, the caller needs to check) + */ +static int __folio_split(struct folio *folio, unsigned int new_order, + struct page *split_at, struct page *lock_at, + struct list_head *list, enum split_type split_type) +{ + XA_STATE(xas, &folio->mapping->i_pages, folio->index); + struct folio *end_folio = folio_next(folio); + bool is_anon = folio_test_anon(folio); + struct address_space *mapping = NULL; + struct anon_vma *anon_vma = NULL; + int old_order = folio_order(folio); + struct folio *new_folio, *next; + int nr_shmem_dropped = 0; + int remap_flags = 0; + int extra_pins, ret; + pgoff_t end = 0; + bool is_hzp; + + VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); + VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); + + if (folio != page_folio(split_at) || folio != page_folio(lock_at)) + return -EINVAL; + /* - * 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. + * Folios that just got truncated cannot get split. Signal to the + * caller that there was a race. + * + * TODO: this will also currently refuse shmem folios that are in the + * swapcache. */ - *hpage = alloc_hugepage_vma(khugepaged_defrag(), vma, address, - node, __GFP_OTHER_NODE); + if (!is_anon && !folio->mapping) + return -EBUSY; + + if (new_order >= old_order) + return -EINVAL; + + if (!folio_split_supported(folio, new_order, split_type, /* warn = */ true)) + return -EINVAL; + + is_hzp = is_huge_zero_folio(folio); + if (is_hzp) { + pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); + return -EBUSY; + } + + if (folio_test_writeback(folio)) + return -EBUSY; + + if (is_anon) { + /* + * The caller does not necessarily hold an mmap_lock that would + * prevent the anon_vma disappearing so we first we take a + * reference to it and then lock the anon_vma for write. This + * is similar to folio_lock_anon_vma_read except the write lock + * is taken to serialise against parallel split or collapse + * operations. + */ + anon_vma = folio_get_anon_vma(folio); + if (!anon_vma) { + ret = -EBUSY; + goto out; + } + anon_vma_lock_write(anon_vma); + mapping = NULL; + } else { + unsigned int min_order; + gfp_t gfp; + + mapping = folio->mapping; + min_order = mapping_min_folio_order(folio->mapping); + if (new_order < min_order) { + ret = -EINVAL; + goto out; + } + + gfp = current_gfp_context(mapping_gfp_mask(mapping) & + GFP_RECLAIM_MASK); + + if (!filemap_release_folio(folio, gfp)) { + ret = -EBUSY; + goto out; + } + + if (split_type == SPLIT_TYPE_UNIFORM) { + xas_set_order(&xas, folio->index, new_order); + xas_split_alloc(&xas, folio, old_order, gfp); + if (xas_error(&xas)) { + ret = xas_error(&xas); + goto out; + } + } + + anon_vma = NULL; + i_mmap_lock_read(mapping); + + /* + *__split_unmapped_folio() may need to trim off pages beyond + * EOF: but on 32-bit, i_size_read() takes an irq-unsafe + * seqlock, which cannot be nested inside the page tree lock. + * So note end now: i_size itself may be changed at any moment, + * but folio lock is good enough to serialize the trimming. + */ + end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + if (shmem_mapping(mapping)) + end = shmem_fallocend(mapping->host, end); + } /* - * After allocating the hugepage, release the mmap_sem read lock in - * preparation for taking it in write mode. + * Racy check if we can split the page, before unmap_folio() will + * split PMDs */ - up_read(&mm->mmap_sem); - if (unlikely(!*hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - *hpage = ERR_PTR(-ENOMEM); - return NULL; + if (!can_split_folio(folio, 1, &extra_pins)) { + ret = -EAGAIN; + goto out_unlock; + } + + unmap_folio(folio); + + /* block interrupt reentry in xa_lock and spinlock */ + local_irq_disable(); + if (mapping) { + /* + * Check if the folio is present in page cache. + * We assume all tail are present too, if folio is there. + */ + xas_lock(&xas); + xas_reset(&xas); + if (xas_load(&xas) != folio) { + ret = -EAGAIN; + goto fail; + } } - count_vm_event(THP_COLLAPSE_ALLOC); - return *hpage; + ret = __folio_freeze_and_split_unmapped(folio, new_order, split_at, &xas, mapping, + true, list, split_type, end, &nr_shmem_dropped, + extra_pins); +fail: + if (mapping) + xas_unlock(&xas); + + local_irq_enable(); + + if (nr_shmem_dropped) + shmem_uncharge(mapping->host, nr_shmem_dropped); + + if (!ret && is_anon && !folio_is_device_private(folio)) + remap_flags = RMP_USE_SHARED_ZEROPAGE; + + remap_page(folio, 1 << old_order, remap_flags); + + /* + * Unlock all after-split folios except the one containing + * @lock_at page. If @folio is not split, it will be kept locked. + */ + for (new_folio = folio; new_folio != end_folio; new_folio = next) { + next = folio_next(new_folio); + if (new_folio == page_folio(lock_at)) + continue; + + folio_unlock(new_folio); + /* + * Subpages 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. + */ + free_folio_and_swap_cache(new_folio); + } + +out_unlock: + if (anon_vma) { + anon_vma_unlock_write(anon_vma); + put_anon_vma(anon_vma); + } + if (mapping) + i_mmap_unlock_read(mapping); +out: + xas_destroy(&xas); + if (old_order == HPAGE_PMD_ORDER) + count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + count_mthp_stat(old_order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED); + return ret; } -#else -static struct page *khugepaged_alloc_hugepage(bool *wait) + +/** + * folio_split_unmapped() - split a large anon folio that is already unmapped + * @folio: folio to split + * @new_order: the order of folios after split + * + * This function is a helper for splitting folios that have already been + * unmapped. The use case is that the device or the CPU can refuse to migrate + * THP pages in the middle of migration, due to allocation issues on either + * side. + * + * anon_vma_lock is not required to be held, mmap_read_lock() or + * mmap_write_lock() should be held. @folio is expected to be locked by the + * caller. device-private and non device-private folios are supported along + * with folios that are in the swapcache. @folio should also be unmapped and + * isolated from LRU (if applicable) + * + * Upon return, the folio is not remapped, split folios are not added to LRU, + * free_folio_and_swap_cache() is not called, and new folios remain locked. + * + * Return: 0 on success, -EAGAIN if the folio cannot be split (e.g., due to + * insufficient reference count or extra pins). + */ +int folio_split_unmapped(struct folio *folio, unsigned int new_order) { - struct page *hpage; + int extra_pins, ret = 0; - do { - hpage = alloc_hugepage(khugepaged_defrag()); - if (!hpage) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - if (!*wait) - return NULL; + VM_WARN_ON_ONCE_FOLIO(folio_mapped(folio), folio); + VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); + VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); + VM_WARN_ON_ONCE_FOLIO(!folio_test_anon(folio), folio); - *wait = false; - khugepaged_alloc_sleep(); - } else - count_vm_event(THP_COLLAPSE_ALLOC); - } while (unlikely(!hpage) && likely(khugepaged_enabled())); + if (!can_split_folio(folio, 1, &extra_pins)) + return -EAGAIN; - return hpage; + local_irq_disable(); + ret = __folio_freeze_and_split_unmapped(folio, new_order, &folio->page, NULL, + NULL, false, NULL, SPLIT_TYPE_UNIFORM, + 0, NULL, extra_pins); + local_irq_enable(); + return ret; } -static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) +/* + * This function splits a large folio into smaller folios of order @new_order. + * @page can point to any page of the large folio to split. The split operation + * does not change the position of @page. + * + * Prerequisites: + * + * 1) The caller must hold a reference on the @page's owning folio, also known + * as the large folio. + * + * 2) The large folio must be locked. + * + * 3) The folio must not be pinned. Any unexpected folio references, including + * GUP pins, will result in the folio not getting split; instead, the caller + * will receive an -EAGAIN. + * + * 4) @new_order > 1, usually. Splitting to order-1 anonymous folios is not + * supported for non-file-backed folios, because folio->_deferred_list, which + * is used by partially mapped folios, is stored in subpage 2, but an order-1 + * folio only has subpages 0 and 1. File-backed order-1 folios are supported, + * since they do not use _deferred_list. + * + * After splitting, the caller's folio reference will be transferred to @page, + * resulting in a raised refcount of @page after this call. The other pages may + * be freed if they are not mapped. + * + * If @list is null, tail pages will be added to LRU list, otherwise, to @list. + * + * Pages in @new_order will inherit the mapping, flags, and so on from the + * huge page. + * + * Returns 0 if the huge page was split successfully. + * + * Returns -EAGAIN if the folio has unexpected reference (e.g., GUP) or if + * the folio was concurrently removed from the page cache. + * + * Returns -EBUSY when trying to split the huge zeropage, if the folio is + * under writeback, if fs-specific folio metadata cannot currently be + * released, or if some unexpected race happened (e.g., anon VMA disappeared, + * truncation). + * + * Callers should ensure that the order respects the address space mapping + * min-order if one is set for non-anonymous folios. + * + * Returns -EINVAL when trying to split to an order that is incompatible + * with the folio. Splitting to order 0 is compatible with all folios. + */ +int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list, + unsigned int new_order) { - if (!*hpage) - *hpage = khugepaged_alloc_hugepage(wait); - - if (unlikely(!*hpage)) - return false; + struct folio *folio = page_folio(page); - return true; + return __folio_split(folio, new_order, &folio->page, page, list, + SPLIT_TYPE_UNIFORM); } -static struct page -*khugepaged_alloc_page(struct page **hpage, struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - int node) +/** + * folio_split() - split a folio at @split_at to a @new_order folio + * @folio: folio to split + * @new_order: the order of the new folio + * @split_at: a page within the new folio + * @list: after-split folios are added to @list if not null, otherwise to LRU + * list + * + * It has the same prerequisites and returns as + * split_huge_page_to_list_to_order(). + * + * Split a folio at @split_at to a new_order folio, leave the + * remaining subpages of the original folio as large as possible. For example, + * in the case of splitting an order-9 folio at its third order-3 subpages to + * an order-3 folio, there are 2^(9-3)=64 order-3 subpages in the order-9 folio. + * After the split, there will be a group of folios with different orders and + * the new folio containing @split_at is marked in bracket: + * [order-4, {order-3}, order-3, order-5, order-6, order-7, order-8]. + * + * After split, folio is left locked for caller. + * + * Return: 0 - successful, <0 - failed (if -ENOMEM is returned, @folio might be + * split but not to @new_order, the caller needs to check) + */ +int folio_split(struct folio *folio, unsigned int new_order, + struct page *split_at, struct list_head *list) { - up_read(&mm->mmap_sem); - VM_BUG_ON(!*hpage); - return *hpage; + return __folio_split(folio, new_order, split_at, &folio->page, list, + SPLIT_TYPE_NON_UNIFORM); } -#endif -static bool hugepage_vma_check(struct vm_area_struct *vma) +int min_order_for_split(struct folio *folio) { - if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || - (vma->vm_flags & VM_NOHUGEPAGE)) - return false; + if (folio_test_anon(folio)) + return 0; - if (!vma->anon_vma || vma->vm_ops) - return false; - if (is_vma_temporary_stack(vma)) - return false; - VM_BUG_ON(vma->vm_flags & VM_NO_THP); - return true; + if (!folio->mapping) { + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_SPLIT_PAGE_FAILED); + return -EBUSY; + } + + return mapping_min_folio_order(folio->mapping); } -static void collapse_huge_page(struct mm_struct *mm, - unsigned long address, - struct page **hpage, - struct vm_area_struct *vma, - int node) +int split_folio_to_list(struct folio *folio, struct list_head *list) { - pmd_t *pmd, _pmd; - pte_t *pte; - pgtable_t pgtable; - struct page *new_page; - spinlock_t *ptl; - int isolated; - unsigned long hstart, hend; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ + return split_huge_page_to_list_to_order(&folio->page, list, 0); +} + +/* + * __folio_unqueue_deferred_split() is not to be called directly: + * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h + * limits its calls to those folios which may have a _deferred_list for + * queueing THP splits, and that list is (racily observed to be) non-empty. + * + * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is + * zero: because even when split_queue_lock is held, a non-empty _deferred_list + * might be in use on deferred_split_scan()'s unlocked on-stack list. + * + * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is + * therefore important to unqueue deferred split before changing folio memcg. + */ +bool __folio_unqueue_deferred_split(struct folio *folio) +{ + struct deferred_split *ds_queue; + unsigned long flags; + bool unqueued = false; + + WARN_ON_ONCE(folio_ref_count(folio)); + WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg_charged(folio)); + + ds_queue = folio_split_queue_lock_irqsave(folio, &flags); + if (!list_empty(&folio->_deferred_list)) { + ds_queue->split_queue_len--; + if (folio_test_partially_mapped(folio)) { + folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } + list_del_init(&folio->_deferred_list); + unqueued = true; + } + split_queue_unlock_irqrestore(ds_queue, flags); - VM_BUG_ON(address & ~HPAGE_PMD_MASK); + return unqueued; /* useful for debug warnings */ +} + +/* partially_mapped=false won't clear PG_partially_mapped folio flag */ +void deferred_split_folio(struct folio *folio, bool partially_mapped) +{ + struct deferred_split *ds_queue; + unsigned long flags; - /* release the mmap_sem read lock. */ - new_page = khugepaged_alloc_page(hpage, mm, vma, address, node); - if (!new_page) + /* + * Order 1 folios have no space for a deferred list, but we also + * won't waste much memory by not adding them to the deferred list. + */ + if (folio_order(folio) <= 1) return; - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) + if (!partially_mapped && !split_underused_thp) return; /* - * 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. + * Exclude swapcache: originally to avoid a corrupt deferred split + * queue. Nowadays that is fully prevented by memcg1_swapout(); + * but if page reclaim is already handling the same folio, it is + * unnecessary to handle it again in the shrinker, so excluding + * swapcache here may still be a useful optimization. */ - down_write(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) - goto out; + if (folio_test_swapcache(folio)) + return; - 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; - if (!hugepage_vma_check(vma)) - goto out; - pmd = mm_find_pmd(mm, address); - if (!pmd) - goto out; - if (pmd_trans_huge(*pmd)) - goto out; + ds_queue = folio_split_queue_lock_irqsave(folio, &flags); + if (partially_mapped) { + if (!folio_test_partially_mapped(folio)) { + folio_set_partially_mapped(folio); + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_DEFERRED_SPLIT_PAGE); + count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1); - anon_vma_lock_write(vma->anon_vma); + } + } else { + /* partially mapped folios cannot become non-partially mapped */ + VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio); + } + if (list_empty(&folio->_deferred_list)) { + struct mem_cgroup *memcg; + + memcg = folio_split_queue_memcg(folio, ds_queue); + list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); + ds_queue->split_queue_len++; + if (memcg) + set_shrinker_bit(memcg, folio_nid(folio), + shrinker_id(deferred_split_shrinker)); + } + split_queue_unlock_irqrestore(ds_queue, flags); +} - pte = pte_offset_map(pmd, address); - ptl = pte_lockptr(mm, pmd); +static unsigned long deferred_split_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct pglist_data *pgdata = NODE_DATA(sc->nid); + struct deferred_split *ds_queue = &pgdata->deferred_split_queue; - mmun_start = address; - mmun_end = address + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - 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(vma, address, pmd); - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); +#ifdef CONFIG_MEMCG + if (sc->memcg) + ds_queue = &sc->memcg->deferred_split_queue; +#endif + return READ_ONCE(ds_queue->split_queue_len); +} - spin_lock(ptl); - isolated = __collapse_huge_page_isolate(vma, address, pte); - spin_unlock(ptl); +static bool thp_underused(struct folio *folio) +{ + int num_zero_pages = 0, num_filled_pages = 0; + int i; + + if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1) + return false; + + if (folio_contain_hwpoisoned_page(folio)) + return false; - if (unlikely(!isolated)) { - pte_unmap(pte); - spin_lock(&mm->page_table_lock); - BUG_ON(!pmd_none(*pmd)); + for (i = 0; i < folio_nr_pages(folio); i++) { + if (pages_identical(folio_page(folio, i), ZERO_PAGE(0))) { + if (++num_zero_pages > khugepaged_max_ptes_none) + return true; + } else { + /* + * Another path for early exit once the number + * of non-zero filled pages exceeds threshold. + */ + if (++num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) + return false; + } + } + return false; +} + +static unsigned long deferred_split_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct deferred_split *ds_queue; + unsigned long flags; + struct folio *folio, *next; + int split = 0, i; + struct folio_batch fbatch; + + folio_batch_init(&fbatch); + +retry: + ds_queue = split_queue_lock_irqsave(sc->nid, sc->memcg, &flags); + /* Take pin on all head pages to avoid freeing them under us */ + list_for_each_entry_safe(folio, next, &ds_queue->split_queue, + _deferred_list) { + if (folio_try_get(folio)) { + folio_batch_add(&fbatch, folio); + } else if (folio_test_partially_mapped(folio)) { + /* We lost race with folio_put() */ + folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } + list_del_init(&folio->_deferred_list); + ds_queue->split_queue_len--; + if (!--sc->nr_to_scan) + break; + if (!folio_batch_space(&fbatch)) + break; + } + split_queue_unlock_irqrestore(ds_queue, flags); + + for (i = 0; i < folio_batch_count(&fbatch); i++) { + bool did_split = false; + bool underused = false; + struct deferred_split *fqueue; + + folio = fbatch.folios[i]; + if (!folio_test_partially_mapped(folio)) { + /* + * See try_to_map_unused_to_zeropage(): we cannot + * optimize zero-filled pages after splitting an + * mlocked folio. + */ + if (folio_test_mlocked(folio)) + goto next; + underused = thp_underused(folio); + if (!underused) + goto next; + } + if (!folio_trylock(folio)) + goto next; + if (!split_folio(folio)) { + did_split = true; + if (underused) + count_vm_event(THP_UNDERUSED_SPLIT_PAGE); + split++; + } + folio_unlock(folio); +next: + if (did_split || !folio_test_partially_mapped(folio)) + continue; /* - * We can only use set_pmd_at when establishing - * hugepmds and never for establishing regular pmds that - * points to regular pagetables. Use pmd_populate for that + * Only add back to the queue if folio is partially mapped. + * If thp_underused returns false, or if split_folio fails + * in the case it was underused, then consider it used and + * don't add it back to split_queue. */ - pmd_populate(mm, pmd, pmd_pgtable(_pmd)); - spin_unlock(&mm->page_table_lock); - anon_vma_unlock_write(vma->anon_vma); - goto out; + fqueue = folio_split_queue_lock_irqsave(folio, &flags); + if (list_empty(&folio->_deferred_list)) { + list_add_tail(&folio->_deferred_list, &fqueue->split_queue); + fqueue->split_queue_len++; + } + split_queue_unlock_irqrestore(fqueue, flags); + } + folios_put(&fbatch); + + if (sc->nr_to_scan && !list_empty(&ds_queue->split_queue)) { + cond_resched(); + goto retry; } /* - * All pages are isolated and locked so anon_vma rmap - * can't run anymore. + * Stop shrinker if we didn't split any page, but the queue is empty. + * This can happen if pages were freed under us. */ - anon_vma_unlock_write(vma->anon_vma); - - __collapse_huge_page_copy(pte, new_page, vma, address, ptl); - pte_unmap(pte); - __SetPageUptodate(new_page); - pgtable = pmd_pgtable(_pmd); + if (!split && list_empty(&ds_queue->split_queue)) + return SHRINK_STOP; + return split; +} - _pmd = mk_huge_pmd(new_page, vma); +#ifdef CONFIG_MEMCG +void reparent_deferred_split_queue(struct mem_cgroup *memcg) +{ + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct deferred_split *ds_queue = &memcg->deferred_split_queue; + struct deferred_split *parent_ds_queue = &parent->deferred_split_queue; + int nid; - /* - * 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_irq(&ds_queue->split_queue_lock); + spin_lock_nested(&parent_ds_queue->split_queue_lock, SINGLE_DEPTH_NESTING); - spin_lock(&mm->page_table_lock); - BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address); - pgtable_trans_huge_deposit(mm, pmd, pgtable); - set_pmd_at(mm, address, pmd, _pmd); - update_mmu_cache_pmd(vma, address, pmd); - spin_unlock(&mm->page_table_lock); + if (!ds_queue->split_queue_len) + goto unlock; - *hpage = NULL; + list_splice_tail_init(&ds_queue->split_queue, &parent_ds_queue->split_queue); + parent_ds_queue->split_queue_len += ds_queue->split_queue_len; + ds_queue->split_queue_len = 0; - khugepaged_pages_collapsed++; -out_up_write: - up_write(&mm->mmap_sem); - return; + for_each_node(nid) + set_shrinker_bit(parent, nid, shrinker_id(deferred_split_shrinker)); -out: - mem_cgroup_uncharge_page(new_page); - goto out_up_write; +unlock: + spin_unlock(&parent_ds_queue->split_queue_lock); + spin_unlock_irq(&ds_queue->split_queue_lock); } +#endif -static int khugepaged_scan_pmd(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - struct page **hpage) +#ifdef CONFIG_DEBUG_FS +static void split_huge_pages_all(void) { - pmd_t *pmd; - pte_t *pte, *_pte; - int ret = 0, referenced = 0, none = 0; + struct zone *zone; struct page *page; - unsigned long _address; - spinlock_t *ptl; - int node = NUMA_NO_NODE; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); + struct folio *folio; + unsigned long pfn, max_zone_pfn; + unsigned long total = 0, split = 0; - pmd = mm_find_pmd(mm, address); - if (!pmd) - goto out; - if (pmd_trans_huge(*pmd)) - goto out; + pr_debug("Split all THPs\n"); + for_each_zone(zone) { + if (!managed_zone(zone)) + continue; + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { + int nr_pages; - 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) + page = pfn_to_online_page(pfn); + if (!page || PageTail(page)) continue; - else - goto out_unmap; + folio = page_folio(page); + if (!folio_try_get(folio)) + continue; + + if (unlikely(page_folio(page) != folio)) + goto next; + + if (zone != folio_zone(folio)) + goto next; + + if (!folio_test_large(folio) + || folio_test_hugetlb(folio) + || !folio_test_lru(folio)) + goto next; + + total++; + folio_lock(folio); + nr_pages = folio_nr_pages(folio); + if (!split_folio(folio)) + split++; + pfn += nr_pages - 1; + folio_unlock(folio); +next: + folio_put(folio); + cond_resched(); } - if (!pte_present(pteval) || !pte_write(pteval)) - goto out_unmap; - page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) - goto out_unmap; - /* - * Chose the node of the first page. This could - * be more sophisticated and look at more pages, - * but isn't for now. - */ - if (node == NUMA_NO_NODE) - node = page_to_nid(page); - 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; - if (pte_young(pteval) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) - referenced = 1; - } - if (referenced) - ret = 1; -out_unmap: - pte_unmap_unlock(pte, ptl); - if (ret) - /* collapse_huge_page will return with the mmap_sem released */ - collapse_huge_page(mm, address, hpage, vma, node); -out: - return ret; + } + + pr_debug("%lu of %lu THP split\n", split, total); } -static void collect_mm_slot(struct mm_slot *mm_slot) +static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) { - struct mm_struct *mm = mm_slot->mm; - - VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); + return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || + is_vm_hugetlb_page(vma); +} - if (khugepaged_test_exit(mm)) { - /* free mm_slot */ - hash_del(&mm_slot->hash); - list_del(&mm_slot->mm_node); +static int split_huge_pages_pid(int pid, unsigned long vaddr_start, + unsigned long vaddr_end, unsigned int new_order, + long in_folio_offset) +{ + int ret = 0; + struct task_struct *task; + struct mm_struct *mm; + unsigned long total = 0, split = 0; + unsigned long addr; - /* - * Not strictly needed because the mm exited already. - * - * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); - */ + vaddr_start &= PAGE_MASK; + vaddr_end &= PAGE_MASK; - /* khugepaged_mm_lock actually not necessary for the below */ - free_mm_slot(mm_slot); - mmdrop(mm); + task = find_get_task_by_vpid(pid); + if (!task) { + ret = -ESRCH; + goto out; } -} -static unsigned int khugepaged_scan_mm_slot(unsigned int pages, - struct page **hpage) - __releases(&khugepaged_mm_lock) - __acquires(&khugepaged_mm_lock) -{ - struct mm_slot *mm_slot; - struct mm_struct *mm; - struct vm_area_struct *vma; - int progress = 0; - - VM_BUG_ON(!pages); - VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); - - if (khugepaged_scan.mm_slot) - mm_slot = khugepaged_scan.mm_slot; - else { - mm_slot = list_entry(khugepaged_scan.mm_head.next, - struct mm_slot, mm_node); - khugepaged_scan.address = 0; - khugepaged_scan.mm_slot = mm_slot; - } - spin_unlock(&khugepaged_mm_lock); - - mm = mm_slot->mm; - down_read(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) - vma = NULL; - else - vma = find_vma(mm, khugepaged_scan.address); + /* Find the mm_struct */ + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + ret = -EINVAL; + goto out; + } - progress++; - for (; vma; vma = vma->vm_next) { - unsigned long hstart, hend; + pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx], new_order: %u, in_folio_offset: %ld\n", + pid, vaddr_start, vaddr_end, new_order, in_folio_offset); - cond_resched(); - if (unlikely(khugepaged_test_exit(mm))) { - progress++; + mmap_read_lock(mm); + /* + * always increase addr by PAGE_SIZE, since we could have a PTE page + * table filled with PTE-mapped THPs, each of which is distinct. + */ + for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { + struct vm_area_struct *vma = vma_lookup(mm, addr); + struct folio_walk fw; + struct folio *folio; + struct address_space *mapping; + unsigned int target_order = new_order; + + if (!vma) break; - } - if (!hugepage_vma_check(vma)) { -skip: - progress++; + + /* skip special VMA and hugetlb VMA */ + if (vma_not_suitable_for_thp_split(vma)) { + addr = vma->vm_end; continue; } - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart >= hend) - goto skip; - if (khugepaged_scan.address > hend) - goto skip; - if (khugepaged_scan.address < hstart) - khugepaged_scan.address = hstart; - VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); - - while (khugepaged_scan.address < hend) { - int ret; - cond_resched(); - if (unlikely(khugepaged_test_exit(mm))) - goto breakouterloop; - - VM_BUG_ON(khugepaged_scan.address < hstart || - khugepaged_scan.address + HPAGE_PMD_SIZE > - hend); - 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; + + folio = folio_walk_start(&fw, vma, addr, 0); + if (!folio) + continue; + + if (!is_transparent_hugepage(folio)) + goto next; + + if (!folio_test_anon(folio)) { + mapping = folio->mapping; + target_order = max(new_order, + mapping_min_folio_order(mapping)); } - } -breakouterloop: - up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */ -breakouterloop_mmap_sem: - spin_lock(&khugepaged_mm_lock); - VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); - /* - * Release the current mm_slot if this mm is about to die, or - * if we scanned all vmas of this mm. - */ - if (khugepaged_test_exit(mm) || !vma) { + if (target_order >= folio_order(folio)) + goto next; + + total++; /* - * 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. + * For folios with private, split_huge_page_to_list_to_order() + * will try to drop it before split and then check if the folio + * can be split or not. So skip the check here. */ - 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; + if (!folio_test_private(folio) && + !can_split_folio(folio, 0, NULL)) + goto next; + + if (!folio_trylock(folio)) + goto next; + folio_get(folio); + folio_walk_end(&fw, vma); + + if (!folio_test_anon(folio) && folio->mapping != mapping) + goto unlock; + + if (in_folio_offset < 0 || + in_folio_offset >= folio_nr_pages(folio)) { + if (!split_folio_to_order(folio, target_order)) + split++; } else { - khugepaged_scan.mm_slot = NULL; - khugepaged_full_scans++; + struct page *split_at = folio_page(folio, + in_folio_offset); + if (!folio_split(folio, target_order, split_at, NULL)) + split++; } - collect_mm_slot(mm_slot); +unlock: + + folio_unlock(folio); + folio_put(folio); + + cond_resched(); + continue; +next: + folio_walk_end(&fw, vma); + cond_resched(); } + mmap_read_unlock(mm); + mmput(mm); - return progress; -} + pr_debug("%lu of %lu THP split\n", split, total); -static int khugepaged_has_work(void) -{ - return !list_empty(&khugepaged_scan.mm_head) && - khugepaged_enabled(); +out: + return ret; } -static int khugepaged_wait_event(void) +static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, + pgoff_t off_end, unsigned int new_order, + long in_folio_offset) { - return !list_empty(&khugepaged_scan.mm_head) || - kthread_should_stop(); -} + struct filename *file; + struct file *candidate; + struct address_space *mapping; + int ret = -EINVAL; + pgoff_t index; + int nr_pages = 1; + unsigned long total = 0, split = 0; + unsigned int min_order; + unsigned int target_order; + + file = getname_kernel(file_path); + if (IS_ERR(file)) + return ret; -static void khugepaged_do_scan(void) -{ - struct page *hpage = NULL; - unsigned int progress = 0, pass_through_head = 0; - unsigned int pages = khugepaged_pages_to_scan; - bool wait = true; + candidate = file_open_name(file, O_RDONLY, 0); + if (IS_ERR(candidate)) + goto out; - barrier(); /* write khugepaged_pages_to_scan to local stack */ + pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx], new_order: %u, in_folio_offset: %ld\n", + file_path, off_start, off_end, new_order, in_folio_offset); - while (progress < pages) { - if (!khugepaged_prealloc_page(&hpage, &wait)) - break; + mapping = candidate->f_mapping; + min_order = mapping_min_folio_order(mapping); + target_order = max(new_order, min_order); - cond_resched(); + for (index = off_start; index < off_end; index += nr_pages) { + struct folio *folio = filemap_get_folio(mapping, index); - if (unlikely(kthread_should_stop() || freezing(current))) - break; + nr_pages = 1; + if (IS_ERR(folio)) + continue; - spin_lock(&khugepaged_mm_lock); - if (!khugepaged_scan.mm_slot) - pass_through_head++; - if (khugepaged_has_work() && - pass_through_head < 2) - progress += khugepaged_scan_mm_slot(pages - progress, - &hpage); - else - progress = pages; - spin_unlock(&khugepaged_mm_lock); - } + if (!folio_test_large(folio)) + goto next; - if (!IS_ERR_OR_NULL(hpage)) - put_page(hpage); -} + total++; + nr_pages = folio_nr_pages(folio); -static void khugepaged_wait_work(void) -{ - try_to_freeze(); + if (target_order >= folio_order(folio)) + goto next; - if (khugepaged_has_work()) { - if (!khugepaged_scan_sleep_millisecs) - return; + if (!folio_trylock(folio)) + goto next; - wait_event_freezable_timeout(khugepaged_wait, - kthread_should_stop(), - msecs_to_jiffies(khugepaged_scan_sleep_millisecs)); - return; + if (folio->mapping != mapping) + goto unlock; + + if (in_folio_offset < 0 || in_folio_offset >= nr_pages) { + if (!split_folio_to_order(folio, target_order)) + split++; + } else { + struct page *split_at = folio_page(folio, + in_folio_offset); + if (!folio_split(folio, target_order, split_at, NULL)) + split++; + } + +unlock: + folio_unlock(folio); +next: + folio_put(folio); + cond_resched(); } - if (khugepaged_enabled()) - wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); + filp_close(candidate, NULL); + ret = 0; + + pr_debug("%lu of %lu file-backed THP split\n", split, total); +out: + putname(file); + return ret; } -static int khugepaged(void *none) +#define MAX_INPUT_BUF_SZ 255 + +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppops) { - struct mm_slot *mm_slot; + static DEFINE_MUTEX(split_debug_mutex); + ssize_t ret; + /* + * hold pid, start_vaddr, end_vaddr, new_order or + * file_path, off_start, off_end, new_order + */ + char input_buf[MAX_INPUT_BUF_SZ]; + int pid; + unsigned long vaddr_start, vaddr_end; + unsigned int new_order = 0; + long in_folio_offset = -1; - set_freezable(); - set_user_nice(current, 19); + ret = mutex_lock_interruptible(&split_debug_mutex); + if (ret) + return ret; - while (!kthread_should_stop()) { - khugepaged_do_scan(); - khugepaged_wait_work(); - } + ret = -EFAULT; - spin_lock(&khugepaged_mm_lock); - mm_slot = khugepaged_scan.mm_slot; - khugepaged_scan.mm_slot = NULL; - if (mm_slot) - collect_mm_slot(mm_slot); - spin_unlock(&khugepaged_mm_lock); - return 0; -} + memset(input_buf, 0, MAX_INPUT_BUF_SZ); + if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) + goto out; -static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, - unsigned long haddr, pmd_t *pmd) -{ - struct mm_struct *mm = vma->vm_mm; - pgtable_t pgtable; - pmd_t _pmd; - int i; + input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; - pmdp_clear_flush(vma, haddr, pmd); - /* leave pmd empty until pte is filled */ + if (input_buf[0] == '/') { + char *tok; + char *tok_buf = input_buf; + char file_path[MAX_INPUT_BUF_SZ]; + pgoff_t off_start = 0, off_end = 0; + size_t input_len = strlen(input_buf); - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); + tok = strsep(&tok_buf, ","); + if (tok && tok_buf) { + strscpy(file_path, tok); + } else { + ret = -EINVAL; + goto out; + } - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; - 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(); -} + ret = sscanf(tok_buf, "0x%lx,0x%lx,%d,%ld", &off_start, &off_end, + &new_order, &in_folio_offset); + if (ret != 2 && ret != 3 && ret != 4) { + ret = -EINVAL; + goto out; + } + ret = split_huge_pages_in_file(file_path, off_start, off_end, + new_order, in_folio_offset); + if (!ret) + ret = input_len; -void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd) -{ - struct page *page; - struct mm_struct *mm = vma->vm_mm; - unsigned long haddr = address & HPAGE_PMD_MASK; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - - BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE); - - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_trans_huge(*pmd))) { - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - return; + goto out; } - if (is_huge_zero_pmd(*pmd)) { - __split_huge_zero_page_pmd(vma, haddr, pmd); - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - return; + + ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d,%ld", &pid, &vaddr_start, + &vaddr_end, &new_order, &in_folio_offset); + if (ret == 1 && pid == 1) { + split_huge_pages_all(); + ret = strlen(input_buf); + goto out; + } else if (ret != 3 && ret != 4 && ret != 5) { + ret = -EINVAL; + goto out; } - page = pmd_page(*pmd); - VM_BUG_ON(!page_count(page)); - get_page(page); - spin_unlock(&mm->page_table_lock); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - split_huge_page(page); + ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order, + in_folio_offset); + if (!ret) + ret = strlen(input_buf); +out: + mutex_unlock(&split_debug_mutex); + return ret; - put_page(page); - BUG_ON(pmd_trans_huge(*pmd)); } -void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, - pmd_t *pmd) -{ - struct vm_area_struct *vma; +static const struct file_operations split_huge_pages_fops = { + .owner = THIS_MODULE, + .write = split_huge_pages_write, +}; - vma = find_vma(mm, address); - BUG_ON(vma == NULL); - split_huge_page_pmd(vma, address, pmd); +static int __init split_huge_pages_debugfs(void) +{ + debugfs_create_file("split_huge_pages", 0200, NULL, NULL, + &split_huge_pages_fops); + return 0; } +late_initcall(split_huge_pages_debugfs); +#endif -static void split_huge_page_address(struct mm_struct *mm, - unsigned long address) +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, + struct page *page) { - pmd_t *pmd; + struct folio *folio = page_folio(page); + struct vm_area_struct *vma = pvmw->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long address = pvmw->address; + bool anon_exclusive; + pmd_t pmdval; + swp_entry_t entry; + pmd_t pmdswp; - VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); + if (!(pvmw->pmd && !pvmw->pte)) + return 0; - pmd = mm_find_pmd(mm, address); - if (!pmd) - return; - /* - * Caller holds the mmap_sem write mode, so a huge pmd cannot - * materialize from under us. - */ - split_huge_page_pmd_mm(mm, address, pmd); + flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); + if (unlikely(!pmd_present(*pvmw->pmd))) + pmdval = pmdp_huge_get_and_clear(vma->vm_mm, address, pvmw->pmd); + else + pmdval = pmdp_invalidate(vma, address, pvmw->pmd); + + /* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ + anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page); + if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) { + set_pmd_at(mm, address, pvmw->pmd, pmdval); + return -EBUSY; + } + + if (pmd_dirty(pmdval)) + folio_mark_dirty(folio); + if (pmd_write(pmdval)) + entry = make_writable_migration_entry(page_to_pfn(page)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); + else + entry = make_readable_migration_entry(page_to_pfn(page)); + if (pmd_young(pmdval)) + entry = make_migration_entry_young(entry); + if (pmd_dirty(pmdval)) + entry = make_migration_entry_dirty(entry); + pmdswp = swp_entry_to_pmd(entry); + if (pmd_soft_dirty(pmdval)) + pmdswp = pmd_swp_mksoft_dirty(pmdswp); + if (pmd_uffd_wp(pmdval)) + pmdswp = pmd_swp_mkuffd_wp(pmdswp); + set_pmd_at(mm, address, pvmw->pmd, pmdswp); + folio_remove_rmap_pmd(folio, page, vma); + folio_put(folio); + trace_set_migration_pmd(address, pmd_val(pmdswp)); + + return 0; } -void __vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - long adjust_next) +void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { - /* - * 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); + struct folio *folio = page_folio(new); + struct vm_area_struct *vma = pvmw->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long address = pvmw->address; + unsigned long haddr = address & HPAGE_PMD_MASK; + pmd_t pmde; + softleaf_t entry; - /* - * 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 (!(pvmw->pmd && !pvmw->pte)) + return; - /* - * 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); + entry = softleaf_from_pmd(*pvmw->pmd); + folio_get(folio); + pmde = folio_mk_pmd(folio, READ_ONCE(vma->vm_page_prot)); + + if (pmd_swp_soft_dirty(*pvmw->pmd)) + pmde = pmd_mksoft_dirty(pmde); + if (softleaf_is_migration_write(entry)) + pmde = pmd_mkwrite(pmde, vma); + if (pmd_swp_uffd_wp(*pvmw->pmd)) + pmde = pmd_mkuffd_wp(pmde); + if (!softleaf_is_migration_young(entry)) + pmde = pmd_mkold(pmde); + /* NOTE: this may contain setting soft-dirty on some archs */ + if (folio_test_dirty(folio) && softleaf_is_migration_dirty(entry)) + pmde = pmd_mkdirty(pmde); + + if (folio_is_device_private(folio)) { + swp_entry_t entry; + + if (pmd_write(pmde)) + entry = make_writable_device_private_entry( + page_to_pfn(new)); + else + entry = make_readable_device_private_entry( + page_to_pfn(new)); + pmde = swp_entry_to_pmd(entry); + + if (pmd_swp_soft_dirty(*pvmw->pmd)) + pmde = pmd_swp_mksoft_dirty(pmde); + if (pmd_swp_uffd_wp(*pvmw->pmd)) + pmde = pmd_swp_mkuffd_wp(pmde); + } + + if (folio_test_anon(folio)) { + rmap_t rmap_flags = RMAP_NONE; + + if (!softleaf_is_migration_read(entry)) + rmap_flags |= RMAP_EXCLUSIVE; + + folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags); + } else { + folio_add_file_rmap_pmd(folio, new, vma); } + VM_BUG_ON(pmd_write(pmde) && folio_test_anon(folio) && !PageAnonExclusive(new)); + set_pmd_at(mm, haddr, pvmw->pmd, pmde); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache_pmd(vma, address, pvmw->pmd); + trace_remove_migration_pmd(address, pmd_val(pmde)); } +#endif |