diff options
Diffstat (limited to 'mm/huge_memory.c')
| -rw-r--r-- | mm/huge_memory.c | 3967 |
1 files changed, 2814 insertions, 1153 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index abe6cfd92ffa..f7c565f11a98 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -8,7 +8,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> @@ -20,9 +19,9 @@ #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/pfn_t.h> #include <linux/mman.h> #include <linux/memremap.h> #include <linux/pagemap.h> @@ -37,9 +36,12 @@ #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" @@ -65,53 +67,97 @@ unsigned long transparent_hugepage_flags __read_mostly = (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); -static struct shrinker deferred_split_shrinker; +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; static atomic_t huge_zero_refcount; -struct page *huge_zero_page __read_mostly; +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; -bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, - bool smaps, bool in_pf, bool enforce_sysfs) +static inline bool file_thp_enabled(struct vm_area_struct *vma) { - if (!vma->vm_mm) /* vdso */ - return false; + struct inode *inode; - /* - * Explicitly disabled through madvise or prctl, or some - * architectures may disable THP for some mappings, for - * example, s390 kvm. - * */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) return false; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) + + if (!vma->vm_file) return false; + inode = file_inode(vma->vm_file); + + return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); +} + +unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, + vm_flags_t vm_flags, + enum tva_type type, + unsigned long orders) +{ + 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; + + orders &= supported_orders; + if (!orders) + return 0; + + if (!vma->vm_mm) /* vdso */ + return 0; + + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags, forced_collapse)) + return 0; + /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ if (vma_is_dax(vma)) - return in_pf; + return in_pf ? orders : 0; /* - * Special VMA and hugetlb VMA. + * khugepaged special VMA and hugetlb VMA. * Must be checked after dax since some dax mappings may have * VM_MIXEDMAP set. */ - if (vm_flags & VM_NO_KHUGEPAGED) - return false; + if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED)) + return 0; /* - * Check alignment for file vma and size for both file and anon vma. + * 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. And this check is not suitable for huge PUD fault. + * handlers. */ - if (!in_pf && - !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE))) - return false; + 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 (!orders) + return 0; + } /* * Enabled via shmem mount options or sysfs settings. @@ -119,23 +165,34 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) - return shmem_huge_enabled(vma, !enforce_sysfs); - - /* Enforce sysfs THP requirements as necessary */ - if (enforce_sysfs && - (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) && - !hugepage_flags_always()))) - return false; + return orders & shmem_allowable_huge_orders(file_inode(vma->vm_file), + vma, vma->vm_pgoff, 0, + forced_collapse); - /* Only regular file is valid */ - if (!in_pf && file_thp_enabled(vma)) - return true; + 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; - if (!vma_is_anonymous(vma)) - return false; + /* + * 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; + } if (vma_is_temporary_stack(vma)) - return false; + return 0; /* * THPeligible bit of smaps should show 1 for proper VMAs even @@ -145,31 +202,34 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, * the first page fault. */ if (!vma->anon_vma) - return (smaps || in_pf); + return (smaps || in_pf) ? orders : 0; - return true; + return orders; } -static bool 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 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 false; } + /* 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_pages(zero_page, compound_order(zero_page)); + folio_put(zero_folio); goto retry; } - WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); + 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); @@ -178,7 +238,7 @@ retry: 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 @@ -187,52 +247,54 @@ static void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } -struct page *mm_get_huge_zero_page(struct mm_struct *mm) +struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) { - if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) - return READ_ONCE(huge_zero_page); + if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) + return huge_zero_folio; + + if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm)) + return READ_ONCE(huge_zero_folio); - if (!get_huge_zero_page()) + if (!get_huge_zero_folio()) return NULL; - if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) - put_huge_zero_page(); + if (mm_flags_test_and_set(MMF_HUGE_ZERO_FOLIO, mm)) + put_huge_zero_folio(); - return READ_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_folio); } -void mm_put_huge_zero_page(struct mm_struct *mm) +void mm_put_huge_zero_folio(struct mm_struct *mm) { - if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) - put_huge_zero_page(); + if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) + return; + + if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm)) + put_huge_zero_folio(); } -static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, - struct shrink_control *sc) +static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink, + struct shrink_control *sc) { /* we can free zero page only if last reference remains */ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; } -static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, - struct shrink_control *sc) +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 page *zero_page = xchg(&huge_zero_page, NULL); - BUG_ON(zero_page == NULL); + struct folio *zero_folio = xchg(&huge_zero_folio, NULL); + BUG_ON(zero_folio == NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); - __free_pages(zero_page, compound_order(zero_page)); + folio_put(zero_folio); return HPAGE_PMD_NR; } return 0; } -static struct shrinker huge_zero_page_shrinker = { - .count_objects = shrink_huge_zero_page_count, - .scan_objects = shrink_huge_zero_page_scan, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *huge_zero_folio_shrinker; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, @@ -390,6 +452,27 @@ static ssize_t hpage_pmd_size_show(struct kobject *kobj, 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 sysfs_emit(buf, "%d\n", split_underused_thp); +} + +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, @@ -398,6 +481,7 @@ static struct attribute *hugepage_attr[] = { #ifdef CONFIG_SHMEM &shmem_enabled_attr.attr, #endif + &split_underused_thp_attr.attr, NULL, }; @@ -405,9 +489,303 @@ static const struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; +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) +{ + 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 anon_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + 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; + + if (ret > 0) { + int err; + + err = start_stop_khugepaged(); + if (err) + ret = err; + } + return ret; +} + +static struct kobj_attribute anon_enabled_attr = + __ATTR(enabled, 0644, anon_enabled_show, anon_enabled_store); + +static struct attribute *anon_ctrl_attrs[] = { + &anon_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group anon_ctrl_attr_grp = { + .attrs = anon_ctrl_attrs, +}; + +static struct attribute *file_ctrl_attrs[] = { +#ifdef CONFIG_SHMEM + &thpsize_shmem_enabled_attr.attr, +#endif + NULL, +}; + +static const struct attribute_group file_ctrl_attr_grp = { + .attrs = file_ctrl_attrs, +}; + +static struct attribute *any_ctrl_attrs[] = { + NULL, +}; + +static const struct attribute_group any_ctrl_attr_grp = { + .attrs = any_ctrl_attrs, +}; + +static const struct kobj_type thpsize_ktype = { + .release = &thpsize_release, + .sysfs_ops = &kobj_sysfs_ops, +}; + +DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}}; + +static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item) +{ + unsigned long sum = 0; + int cpu; + + for_each_possible_cpu(cpu) { + struct mthp_stat *this = &per_cpu(mthp_stats, cpu); + + sum += this->stats[order][item]; + } + + return sum; +} + +#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) +{ + 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 struct thpsize *thpsize_create(int order, struct kobject *parent) +{ + unsigned long size = (PAGE_SIZE << order) / SZ_1K; + struct thpsize *thpsize; + int ret = -ENOMEM; + + thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL); + if (!thpsize) + goto err; + + thpsize->order = order; + + 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 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)) { @@ -427,8 +805,24 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) 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: @@ -438,6 +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); @@ -453,29 +854,66 @@ 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()) { - /* - * Hardware doesn't support hugepages, hence disable - * DAX PMD support. - */ - transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX; + 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_ORDER); - /* - * we use page->mapping and page->index in second tail page - * as list_head: assuming THP order >= 2 - */ - MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2); + MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER); err = hugepage_init_sysfs(&hugepage_kobj); if (err) @@ -485,19 +923,16 @@ static int __init hugepage_init(void) if (err) goto err_slab; - err = register_shrinker(&huge_zero_page_shrinker, "thp-zero"); - if (err) - goto err_hzp_shrinker; - err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split"); + err = thp_shrinker_init(); if (err) - goto err_split_shrinker; + 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; } @@ -508,10 +943,8 @@ static int __init hugepage_init(void) return 0; err_khugepaged: - unregister_shrinker(&deferred_split_shrinker); -err_split_shrinker: - unregister_shrinker(&huge_zero_page_shrinker); -err_hzp_shrinker: + thp_shrinker_exit(); +err_shrinker: khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); @@ -551,61 +984,216 @@ out: } __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 struct deferred_split *split_queue_node(int nid) +{ + struct pglist_data *pgdata = NODE_DATA(nid); + + return &pgdata->deferred_split_queue; +} + #ifdef CONFIG_MEMCG -static inline struct deferred_split *get_deferred_split_queue(struct page *page) +static inline +struct mem_cgroup *folio_split_queue_memcg(struct folio *folio, + struct deferred_split *queue) { - struct mem_cgroup *memcg = page_memcg(compound_head(page)); - struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); + 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); +} - if (memcg) - return &memcg->deferred_split_queue; - else - return &pgdat->deferred_split_queue; +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 deferred_split *get_deferred_split_queue(struct page *page) +static inline +struct mem_cgroup *folio_split_queue_memcg(struct folio *folio, + struct deferred_split *queue) { - struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); + return NULL; +} - return &pgdat->deferred_split_queue; +static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memcg) +{ + return split_queue_node(nid); } #endif -void prep_transhuge_page(struct page *page) +static struct deferred_split *split_queue_lock(int nid, struct mem_cgroup *memcg) { + struct deferred_split *queue; + +retry: + queue = memcg_split_queue(nid, memcg); + spin_lock(&queue->split_queue_lock); /* - * we use page->mapping and page->index in second tail page - * as list_head: assuming THP order >= 2 + * 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; + } - INIT_LIST_HEAD(page_deferred_list(page)); - set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); + return queue; } -static inline bool is_transparent_hugepage(struct page *page) +static struct deferred_split *folio_split_queue_lock(struct folio *folio) { - if (!PageCompound(page)) + 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; - page = compound_head(page); - return is_huge_zero_page(page) || - page[1].compound_dtor == TRANSHUGE_PAGE_DTOR; + 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) + 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; + 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; @@ -614,8 +1202,8 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, if (len_pad < len || (off + len_pad) < off) return 0; - ret = current->mm->get_unmapped_area(filp, addr, len_pad, - off >> PAGE_SHIFT, flags); + 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 @@ -631,41 +1219,115 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, if (ret == addr) return addr; - ret += (off - ret) & (size - 1); + 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(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +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); + ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags); if (ret) return ret; - return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); + 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 vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, - struct page *page, gfp_t gfp) +static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, + unsigned long addr) { - struct vm_area_struct *vma = vmf->vma; - pgtable_t pgtable; - unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - vm_fault_t ret = 0; + gfp_t gfp = vma_thp_gfp_mask(vma); + const int order = HPAGE_PMD_ORDER; + struct folio *folio; - VM_BUG_ON_PAGE(!PageCompound(page), page); + folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK); - if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) { - put_page(page); + 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); - return VM_FAULT_FALLBACK; + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); + return NULL; } - cgroup_throttle_swaprate(page, gfp); + 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. + */ + __folio_mark_uptodate(folio); + return folio; +} + +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)) { @@ -673,20 +1335,10 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, goto release; } - clear_huge_page(page, vmf->address, HPAGE_PMD_NR); - /* - * The memory barrier inside __SetPageUptodate makes sure that - * clear_huge_page writes become visible before the set_pmd_at() - * write. - */ - __SetPageUptodate(page); - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { - pmd_t entry; - ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; @@ -694,25 +1346,16 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); - put_page(page); + 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; } - - entry = mk_huge_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr); - lru_cache_add_inactive_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); - set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); - update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + map_anon_folio_pmd_pf(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); - count_vm_event(THP_FAULT_ALLOC); - count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; @@ -721,11 +1364,49 @@ unlock_release: release: if (pgtable) pte_free(vma->vm_mm, pgtable); - put_page(page); + folio_put(folio); return ret; } +vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf) +{ + 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; +} + /* * always: directly stall for all thp allocations * defer: wake kswapd and fail if not immediately available @@ -762,15 +1443,13 @@ gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) } /* Caller must hold page table lock. */ -static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, +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; - entry = mk_pmd(zero_page, vma->vm_page_prot); - 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_inc_nr_ptes(mm); @@ -779,27 +1458,28 @@ static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - gfp_t gfp; - struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + vm_fault_t ret; - if (!transhuge_vma_suitable(vma, haddr)) + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return VM_FAULT_FALLBACK; - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; + 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 page *zero_page; + struct folio *zero_folio; vm_fault_t ret; + pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) return VM_FAULT_OOM; - zero_page = mm_get_huge_zero_page(vma->vm_mm); - if (unlikely(!zero_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); return VM_FAULT_FALLBACK; @@ -817,8 +1497,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { - set_huge_zero_page(pgtable, vma->vm_mm, vma, - haddr, vmf->pmd, zero_page); + 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); } @@ -828,27 +1508,43 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } return ret; } - gfp = vma_thp_gfp_mask(vma); - folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); - if (unlikely(!folio)) { - count_vm_event(THP_FAULT_FALLBACK); - return VM_FAULT_FALLBACK; - } - return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); + + return __do_huge_pmd_anonymous_page(vmf); } -static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, - pgtable_t pgtable) +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; - pmd_t entry; + 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_t_to_pfn(pfn)) { + if (pmd_pfn(*pmd) != pfn) { WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); goto out_unlock; } @@ -857,13 +1553,23 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) update_mmu_cache_pmd(vma, addr, pmd); } - goto out_unlock; } - entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); - if (pfn_t_devmap(pfn)) - entry = pmd_mkdevmap(entry); + 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); + } if (write) { entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); @@ -882,54 +1588,61 @@ out_unlock: spin_unlock(ptl); if (pgtable) pte_free(mm, pgtable); + return VM_FAULT_NOPAGE; } /** - * vmf_insert_pfn_pmd_prot - insert a pmd size pfn + * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert - * @pgprot: page protection to use * @write: whether it's a write fault * - * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and - * also consult the vmf_insert_mixed_prot() documentation when - * @pgprot != @vmf->vma->vm_page_prot. + * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ -vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write) +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; - pgtable_t pgtable = NULL; + pgprot_t pgprot = vma->vm_page_prot; + struct folio_or_pfn fop = { + .pfn = pfn, + }; /* * 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. */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && - !pfn_t_devmap(pfn)); + 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)); - if (addr < vma->vm_start || addr >= vma->vm_end) - return VM_FAULT_SIGBUS; + pfnmap_setup_cachemode_pfn(pfn, &pgprot); - if (arch_needs_pgtable_deposit()) { - pgtable = pte_alloc_one(vma->vm_mm); - if (!pgtable) - return VM_FAULT_OOM; - } + return insert_pmd(vma, addr, vmf->pmd, fop, pgprot, write); +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); - track_pfn_insert(vma, &pgprot, pfn); +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, + }; - insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); - return VM_FAULT_NOPAGE; + 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_pfn_pmd_prot); +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) @@ -939,20 +1652,24 @@ static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) return pud; } -static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, pfn_t pfn, pgprot_t prot, bool write) +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; - pud_t entry; 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 (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { - WARN_ON_ONCE(!is_huge_zero_pud(*pud)); + 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)) @@ -961,117 +1678,169 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, goto out_unlock; } - entry = pud_mkhuge(pfn_t_pud(pfn, prot)); - if (pfn_t_devmap(pfn)) - entry = pud_mkdevmap(entry); + 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_prot - insert a pud size pfn + * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert - * @pgprot: page protection to use * @write: whether it's a write fault * - * Insert a pud size pfn. See vmf_insert_pfn() for additional info and - * also consult the vmf_insert_mixed_prot() documentation when - * @pgprot != @vmf->vma->vm_page_prot. + * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ -vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write) +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, + }; /* * 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. */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && - !pfn_t_devmap(pfn)); + 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)); - if (addr < vma->vm_start || addr >= vma->vm_end) - return VM_FAULT_SIGBUS; + pfnmap_setup_cachemode_pfn(pfn, &pgprot); - track_pfn_insert(vma, &pgprot, pfn); + return insert_pud(vma, addr, vmf->pud, fop, pgprot, write); +} +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); - insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write); - return VM_FAULT_NOPAGE; +/** + * 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_pfn_pud_prot); +EXPORT_SYMBOL_GPL(vmf_insert_folio_pud); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, bool write) +/** + * 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 _pmd; + pmd_t entry; - _pmd = pmd_mkyoung(*pmd); + entry = pmd_mkyoung(*pmd); if (write) - _pmd = pmd_mkdirty(_pmd); + entry = pmd_mkdirty(entry); if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, - pmd, _pmd, write)) + pmd, entry, write)) { update_mmu_cache_pmd(vma, addr, pmd); + return true; + } + + return false; } -struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags, struct dev_pagemap **pgmap) +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) { - unsigned long pfn = pmd_pfn(*pmd); - struct mm_struct *mm = vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pmd_lockptr(mm, pmd)); - - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == - (FOLL_PIN | FOLL_GET))) - return NULL; - - if (flags & FOLL_WRITE && !pmd_write(*pmd)) - return NULL; + 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_present(*pmd) && pmd_devmap(*pmd)) - /* pass */; - else - return NULL; + 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); + } - if (flags & FOLL_TOUCH) - touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); + src_folio = softleaf_to_folio(entry); + VM_WARN_ON(!folio_test_large(src_folio)); - /* - * device mapped pages can only be returned if the - * caller will manage the page reference count. - */ - if (!(flags & (FOLL_GET | FOLL_PIN))) - return ERR_PTR(-EEXIST); - - pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; - *pgmap = get_dev_pagemap(pfn, *pgmap); - if (!*pgmap) - return ERR_PTR(-EFAULT); - page = pfn_to_page(pfn); - ret = try_grab_page(page, flags); - if (ret) - page = ERR_PTR(ret); + 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); + } - return page; + 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, @@ -1080,10 +1849,30 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; + struct folio *src_folio; pmd_t pmd; 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; + } + /* Skip if can be re-fill on fault */ if (!vma_is_anonymous(dst_vma)) return 0; @@ -1099,31 +1888,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION - if (unlikely(is_swap_pmd(pmd))) { - swp_entry_t entry = pmd_to_swp_entry(pmd); - - VM_BUG_ON(!is_pmd_migration_entry(pmd)); - if (!is_readable_migration_entry(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); - } - 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); + 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; } -#endif if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); @@ -1136,25 +1907,26 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ if (is_huge_zero_pmd(pmd)) { /* - * 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. */ - mm_get_huge_zero_page(dst_mm); + mm_get_huge_zero_folio(dst_mm); goto out_zero_page; } src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + src_folio = page_folio(src_page); - get_page(src_page); - if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) { + 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. */ - put_page(src_page); + 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, NULL); + __split_huge_pmd(src_vma, src_pmd, addr, false); return -EAGAIN; } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); @@ -1164,7 +1936,9 @@ out_zero_page: pmdp_set_wrprotect(src_mm, addr, src_pmd); if (!userfaultfd_wp(dst_vma)) pmd = pmd_clear_uffd_wp(pmd); - pmd = pmd_mkold(pmd_wrprotect(pmd)); + pmd = pmd_wrprotect(pmd); +set_pmd: + pmd = pmd_mkold(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; @@ -1176,8 +1950,8 @@ out: } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static void touch_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, bool write) +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write) { pud_t _pud; @@ -1189,54 +1963,6 @@ static void touch_pud(struct vm_area_struct *vma, unsigned long addr, update_mmu_cache_pud(vma, addr, pud); } -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags, struct dev_pagemap **pgmap) -{ - unsigned long pfn = pud_pfn(*pud); - struct mm_struct *mm = vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pud_lockptr(mm, pud)); - - if (flags & FOLL_WRITE && !pud_write(*pud)) - return NULL; - - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == - (FOLL_PIN | FOLL_GET))) - return NULL; - - if (pud_present(*pud) && pud_devmap(*pud)) - /* pass */; - else - return NULL; - - if (flags & FOLL_TOUCH) - touch_pud(vma, addr, pud, flags & FOLL_WRITE); - - /* - * device mapped pages can only be returned if the - * caller will manage the page reference count. - * - * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here: - */ - if (!(flags & (FOLL_GET | FOLL_PIN))) - return ERR_PTR(-EEXIST); - - pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; - *pgmap = get_dev_pagemap(pfn, *pgmap); - if (!*pgmap) - return ERR_PTR(-EFAULT); - page = pfn_to_page(pfn); - - ret = try_grab_page(page, flags); - if (ret) - page = ERR_PTR(ret); - - return page; -} - 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) @@ -1251,24 +1977,18 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pud = *src_pud; - if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud))) + if (unlikely(!pud_trans_huge(pud))) goto out_unlock; /* - * When page table lock is held, the huge zero pud should not be - * under splitting since we don't split the page itself, only pud to - * a page table. + * TODO: once we support anonymous pages, use + * folio_try_dup_anon_rmap_*() and split if duplicating fails. */ - if (is_huge_zero_pud(pud)) { - /* No huge zero pud yet */ + if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) { + pudp_set_wrprotect(src_mm, addr, src_pud); + pud = pud_wrprotect(pud); } - - /* - * TODO: once we support anonymous pages, use page_try_dup_anon_rmap() - * and split if duplicating fails. - */ - pudp_set_wrprotect(src_mm, addr, src_pud); - pud = pud_mkold(pud_wrprotect(pud)); + pud = pud_mkold(pud); set_pud_at(dst_mm, addr, dst_pud, pud); ret = 0; @@ -1292,18 +2012,46 @@ unlock: } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -void huge_pmd_set_accessed(struct vm_fault *vmf) +bool huge_pmd_set_accessed(struct vm_fault *vmf) { bool write = vmf->flags & FAULT_FLAG_WRITE; - vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) - goto unlock; + return false; - touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); + return touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); +} + +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; } vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) @@ -1318,8 +2066,15 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); - if (is_huge_zero_pmd(orig_pmd)) + 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; + } spin_lock(vmf->ptl); @@ -1359,7 +2114,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) /* * See do_wp_page(): we can only reuse the folio exclusively if * there are no additional references. Note that we always drain - * the LRU pagevecs immediately after adding a THP. + * the LRU cache immediately after adding a THP. */ if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio) * folio_nr_pages(folio)) @@ -1369,7 +2124,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) if (folio_ref_count(folio) == 1) { pmd_t entry; - page_move_anon_rmap(page, vma); + folio_move_anon_rmap(folio, vma); + SetPageAnonExclusive(page); folio_unlock(folio); reuse: if (unlikely(unshare)) { @@ -1388,7 +2144,7 @@ unlock_fallback: folio_unlock(folio); spin_unlock(vmf->ptl); fallback: - __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); + __split_huge_pmd(vma, vmf->pmd, vmf->address, false); return VM_FAULT_FALLBACK; } @@ -1405,7 +2161,7 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma, return false; /* Do we need write faults for softdirty tracking? */ - if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + if (pmd_needs_soft_dirty_wp(vma, pmd)) return false; /* Do we need write faults for uffd-wp tracking? */ @@ -1422,109 +2178,27 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma, return pmd_dirty(pmd); } -/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ -static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, - struct vm_area_struct *vma, - unsigned int flags) -{ - /* If the pmd is writable, we can write to the page. */ - if (pmd_write(pmd)) - return true; - - /* Maybe FOLL_FORCE is set to override it? */ - if (!(flags & FOLL_FORCE)) - return false; - - /* But FOLL_FORCE has no effect on shared mappings */ - if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) - return false; - - /* ... or read-only private ones */ - if (!(vma->vm_flags & VM_MAYWRITE)) - return false; - - /* ... or already writable ones that just need to take a write fault */ - if (vma->vm_flags & VM_WRITE) - return false; - - /* - * See can_change_pte_writable(): we broke COW and could map the page - * writable if we have an exclusive anonymous page ... - */ - if (!page || !PageAnon(page) || !PageAnonExclusive(page)) - return false; - - /* ... and a write-fault isn't required for other reasons. */ - if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) - return false; - return !userfaultfd_huge_pmd_wp(vma, pmd); -} - -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags) -{ - struct mm_struct *mm = vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pmd_lockptr(mm, pmd)); - - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); - - if ((flags & FOLL_WRITE) && - !can_follow_write_pmd(*pmd, page, vma, flags)) - return NULL; - - /* Avoid dumping huge zero page */ - if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) - return ERR_PTR(-EFAULT); - - /* Full NUMA hinting faults to serialise migration in fault paths */ - if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags)) - return NULL; - - if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page)) - return ERR_PTR(-EMLINK); - - VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && - !PageAnonExclusive(page), page); - - ret = try_grab_page(page, flags); - if (ret) - return ERR_PTR(ret); - - if (flags & FOLL_TOUCH) - touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); - - page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; - VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); - - return page; -} - /* 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; - pmd_t oldpmd = vmf->orig_pmd; - pmd_t pmd; - struct page *page; + struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = NUMA_NO_NODE; - int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); - bool migrated = false, writable = false; + 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); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + old_pmd = pmdp_get(vmf->pmd); + + if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) { spin_unlock(vmf->ptl); - goto out; + return 0; } - pmd = pmd_modify(oldpmd, vma->vm_page_prot); + pmd = pmd_modify(old_pmd, vma->vm_page_prot); /* * Detect now whether the PMD could be writable; this information @@ -1535,63 +2209,50 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) can_change_pmd_writable(vma, vmf->address, pmd)) writable = true; - page = vm_normal_page_pmd(vma, haddr, pmd); - if (!page) + folio = vm_normal_folio_pmd(vma, haddr, pmd); + if (!folio) goto out_map; - /* See similar comment in do_numa_page for explanation */ - if (!writable) - flags |= TNF_NO_GROUP; + nid = folio_nid(folio); - page_nid = page_to_nid(page); - /* - * For memory tiering mode, cpupid of slow memory page is used - * to record page access time. So use default value. - */ - if (node_is_toptier(page_nid)) - last_cpupid = page_cpupid_last(page); - target_nid = numa_migrate_prep(page, vma, haddr, page_nid, - &flags); - - if (target_nid == NUMA_NO_NODE) { - put_page(page); + 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; - migrated = migrate_misplaced_page(page, vma, target_nid); - if (migrated) { + if (!migrate_misplaced_folio(folio, target_nid)) { flags |= TNF_MIGRATED; - page_nid = target_nid; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { - spin_unlock(vmf->ptl); - goto out; - } - goto out_map; + nid = target_nid; + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } -out: - if (page_nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, - flags); - - return 0; - + 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; + } out_map: /* Restore the PMD */ - pmd = pmd_modify(oldpmd, vma->vm_page_prot); + pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot); pmd = pmd_mkyoung(pmd); if (writable) - pmd = pmd_mkwrite(pmd); + 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); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; } /* @@ -1603,7 +2264,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, { spinlock_t *ptl; pmd_t orig_pmd; - struct page *page; + struct folio *folio; struct mm_struct *mm = tlb->mm; bool ret = false; @@ -1619,19 +2280,19 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(orig_pmd)); + !pmd_is_migration_entry(orig_pmd)); goto out; } - page = pmd_page(orig_pmd); + folio = pmd_folio(orig_pmd); /* - * If other processes are mapping this page, we couldn't discard - * the page unless they all do MADV_FREE so let's skip the page. + * 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 (total_mapcount(page) != 1) + if (folio_maybe_mapped_shared(folio)) goto out; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto out; /* @@ -1639,17 +2300,17 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, * will deactivate only them. */ if (next - addr != HPAGE_PMD_SIZE) { - get_page(page); + folio_get(folio); spin_unlock(ptl); - split_huge_page(page); - unlock_page(page); - put_page(page); + split_folio(folio); + folio_unlock(folio); + folio_put(folio); goto out_unlocked; } - if (PageDirty(page)) - ClearPageDirty(page); - unlock_page(page); + if (folio_test_dirty(folio)) + folio_clear_dirty(folio); + folio_unlock(folio); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); @@ -1660,7 +2321,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } - mark_page_lazyfree(page); + folio_mark_lazyfree(folio); ret = true; out: spin_unlock(ptl); @@ -1696,45 +2357,64 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, */ 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_special_huge(vma)) { + 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)) { - zap_deposited_table(tlb->mm, pmd); + if (!vma_is_dax(vma) || arch_needs_pgtable_deposit()) + zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else { - struct page *page = NULL; + struct folio *folio = NULL; int flush_needed = 1; if (pmd_present(orig_pmd)) { - page = pmd_page(orig_pmd); - page_remove_rmap(page, vma, true); - VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); + struct page *page = pmd_page(orig_pmd); + + 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 (thp_migration_supported()) { - swp_entry_t entry; + } else if (pmd_is_valid_softleaf(orig_pmd)) { + const softleaf_t entry = softleaf_from_pmd(orig_pmd); - VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); - entry = pmd_to_swp_entry(orig_pmd); - page = pfn_swap_entry_to_page(entry); + folio = softleaf_to_folio(entry); flush_needed = 0; - } else - WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); - if (PageAnon(page)) { + if (!thp_migration_supported()) + WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); + } + + 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(page), -HPAGE_PMD_NR); + add_mm_counter(tlb->mm, mm_counter_file(folio), + -HPAGE_PMD_NR); + + /* + * 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 (folio_is_device_private(folio)) { + folio_remove_rmap_pmd(folio, &folio->page, vma); + WARN_ON_ONCE(folio_mapcount(folio) < 0); + folio_put(folio); } spin_unlock(ptl); if (flush_needed) - tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE); + tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE); } return 1; } @@ -1756,12 +2436,25 @@ static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, static pmd_t move_soft_dirty_pmd(pmd_t pmd) { -#ifdef CONFIG_MEM_SOFT_DIRTY - if (unlikely(is_pmd_migration_entry(pmd))) - pmd = pmd_swp_mksoft_dirty(pmd); - else if (pmd_present(pmd)) - pmd = pmd_mksoft_dirty(pmd); -#endif + 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 pmd; +} + +static pmd_t clear_uffd_wp_pmd(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); + return pmd; } @@ -1775,9 +2468,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, /* * 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)); return false; } @@ -1802,6 +2496,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, 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); @@ -1813,6 +2509,42 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, return false; } +static void change_non_present_huge_pmd(struct mm_struct *mm, + unsigned long addr, pmd_t *pmd, bool uffd_wp, + bool uffd_wp_resolve) +{ + softleaf_t entry = softleaf_from_pmd(*pmd); + const struct folio *folio = softleaf_to_folio(entry); + pmd_t newpmd; + + 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; + } + + 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 * - 0 if PMD could not be locked @@ -1841,36 +2573,14 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (!ptl) return 0; -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION - if (is_swap_pmd(*pmd)) { - swp_entry_t entry = pmd_to_swp_entry(*pmd); - struct page *page = pfn_swap_entry_to_page(entry); - - VM_BUG_ON(!is_pmd_migration_entry(*pmd)); - if (is_writable_migration_entry(entry)) { - pmd_t newpmd; - /* - * A protection check is difficult so - * just be safe and disable write - */ - if (PageAnon(page)) - 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); - if (pmd_swp_uffd_wp(*pmd)) - newpmd = pmd_swp_mkuffd_wp(newpmd); - set_pmd_at(mm, addr, pmd, newpmd); - } + if (thp_migration_supported() && pmd_is_valid_softleaf(*pmd)) { + change_non_present_huge_pmd(mm, addr, pmd, uffd_wp, + uffd_wp_resolve); goto unlock; } -#endif if (prot_numa) { - struct page *page; - bool toptier; + /* * Avoid trapping faults against the zero page. The read-only * data is likely to be read-cached on the local CPU and @@ -1882,19 +2592,9 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_protnone(*pmd)) goto unlock; - page = pmd_page(*pmd); - toptier = node_is_toptier(page_to_nid(page)); - /* - * Skip scanning top tier node if normal numa - * balancing is disabled - */ - if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && - toptier) + if (!folio_can_map_prot_numa(pmd_folio(*pmd), vma, + vma_is_single_threaded_private(vma))) goto unlock; - - if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && - !toptier) - xchg_page_access_time(page, jiffies_to_msecs(jiffies)); } /* * In case prot_numa, we are under mmap_read_lock(mm). It's critical @@ -1920,22 +2620,20 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, oldpmd = pmdp_invalidate_ad(vma, addr, pmd); entry = pmd_modify(oldpmd, newprot); - if (uffd_wp) { - entry = pmd_wrprotect(entry); + if (uffd_wp) entry = pmd_mkuffd_wp(entry); - } else if (uffd_wp_resolve) { + else if (uffd_wp_resolve) /* * Leave the write bit to be handled by PF interrupt * handler, then things like COW could be properly * handled. */ 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); + entry = pmd_mkwrite(entry, vma); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); @@ -1948,6 +2646,173 @@ unlock: } /* + * 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) +{ + struct mm_struct *mm = vma->vm_mm; + pud_t oldpud, entry; + spinlock_t *ptl; + + tlb_change_page_size(tlb, HPAGE_PUD_SIZE); + + /* NUMA balancing doesn't apply to dax */ + if (cp_flags & MM_CP_PROT_NUMA) + return 1; + + /* + * 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; + + /* + * Can't clear PUD or it can race with concurrent zapping. See + * change_huge_pmd(). + */ + 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 + +#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) +{ + 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; + + 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; + } + + 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; + } + + src_page = pmd_page(src_pmdval); + + 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); + + 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; + } + if (src_folio) { + if (folio_maybe_dma_pinned(src_folio) || + !PageAnonExclusive(&src_folio->page)) { + err = -EBUSY; + goto unlock_ptls; + } + + 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; + } + + 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); + } + 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 */ + +/* * 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 @@ -1956,9 +2821,9 @@ unlock: spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { spinlock_t *ptl; + ptl = pmd_lock(vma->vm_mm, pmd); - if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || - pmd_devmap(*pmd))) + if (likely(pmd_is_huge(*pmd))) return ptl; spin_unlock(ptl); return NULL; @@ -1975,7 +2840,7 @@ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) spinlock_t *ptl; ptl = pud_lock(vma->vm_mm, pud); - if (likely(pud_trans_huge(*pud) || pud_devmap(*pud))) + if (likely(pud_trans_huge(*pud))) return ptl; spin_unlock(ptl); return NULL; @@ -1986,19 +2851,33 @@ 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; - pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm); + 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_special_huge(vma)) { + if (!vma_is_dax(vma) && vma_is_special_huge(vma)) { spin_unlock(ptl); /* No zero page support yet */ } else { - /* No support for anonymous PUD pages yet */ - BUG(); + 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; } @@ -2006,14 +2885,33 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, 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) && !pud_devmap(*pud)); + VM_BUG_ON(!pud_trans_huge(*pud)); count_vm_event(THP_SPLIT_PUD); - pudp_huge_clear_flush_notify(vma, haddr, 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, @@ -2022,22 +2920,23 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, spinlock_t *ptl; struct mmu_notifier_range range; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + 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) && !pud_devmap(*pud))) + if (unlikely(!pud_trans_huge(*pud))) goto out; __split_huge_pud_locked(vma, pud, range.start); out: spin_unlock(ptl); - /* - * No need to double call mmu_notifier->invalidate_range() callback as - * the above pudp_huge_clear_flush_notify() did already call it. - */ - mmu_notifier_invalidate_range_only_end(&range); + 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 */ @@ -2046,7 +2945,9 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable; - pmd_t _pmd; + pmd_t _pmd, old_pmd; + unsigned long addr; + pte_t *pte; int i; /* @@ -2057,20 +2958,25 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, * * See Documentation/mm/mmu_notifier.rst */ - pmdp_huge_clear_flush(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; - entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); + 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; + + entry = pfn_pte(my_zero_pfn(addr), 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); + 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); } @@ -2079,55 +2985,59 @@ 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 young, write, soft_dirty, pmd_migration = false, uffd_wp = false; + 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_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd) - && !pmd_devmap(*pmd)); + + VM_WARN_ON_ONCE(!pmd_is_valid_softleaf(*pmd) && !pmd_trans_huge(*pmd)); count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { - old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it */ if (arch_needs_pgtable_deposit()) zap_deposited_table(mm, pmd); - if (vma_is_special_huge(vma)) + if (!vma_is_dax(vma) && vma_is_special_huge(vma)) return; - if (unlikely(is_pmd_migration_entry(old_pmd))) { - swp_entry_t entry; + if (unlikely(pmd_is_migration_entry(old_pmd))) { + const softleaf_t old_entry = softleaf_from_pmd(old_pmd); - entry = pmd_to_swp_entry(old_pmd); - page = pfn_swap_entry_to_page(entry); + folio = softleaf_to_folio(old_entry); + } else if (is_huge_zero_pmd(old_pmd)) { + return; } else { page = pmd_page(old_pmd); - if (!PageDirty(page) && pmd_dirty(old_pmd)) - set_page_dirty(page); - if (!PageReferenced(page) && pmd_young(old_pmd)) - SetPageReferenced(page); - page_remove_rmap(page, vma, true); - put_page(page); + 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(page), -HPAGE_PMD_NR); + add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR); return; } if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling - * mmu_notifier_invalidate_range() see comments below inside - * __split_huge_pmd() ? + * 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 @@ -2136,53 +3046,92 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, return __split_huge_zero_page_pmd(vma, haddr, 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/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. - */ - old_pmd = pmdp_invalidate(vma, haddr, pmd); + if (pmd_is_migration_entry(*pmd)) { + softleaf_t entry; - pmd_migration = is_pmd_migration_entry(old_pmd); - if (unlikely(pmd_migration)) { - swp_entry_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); - entry = pmd_to_swp_entry(old_pmd); - page = pfn_swap_entry_to_page(entry); - write = is_writable_migration_entry(entry); + write = softleaf_is_migration_write(entry); if (PageAnon(page)) - anon_exclusive = is_readable_exclusive_migration_entry(entry); - young = is_migration_entry_young(entry); - dirty = is_migration_entry_dirty(entry); + 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 { + /* + * 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. + */ + old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); + folio = page_folio(page); if (pmd_dirty(old_pmd)) { dirty = true; - SetPageDirty(page); + 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_BUG_ON_PAGE(!page_count(page), page); + VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); /* * Without "freeze", we'll simply split the PMD, propagating the @@ -2197,13 +3146,21 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, * In case we cannot clear PageAnonExclusive(), split the PMD * only and let try_to_migrate_one() fail later. * - * See page_try_share_anon_rmap(): invalidate PMD first. + * See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ - anon_exclusive = PageAnon(page) && PageAnonExclusive(page); - if (freeze && anon_exclusive && page_try_share_anon_rmap(page)) + anon_exclusive = PageAnonExclusive(page); + if (freeze && anon_exclusive && + folio_try_share_anon_rmap_pmd(folio, page)) freeze = false; - if (!freeze) - page_ref_add(page, HPAGE_PMD_NR - 1); + 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); + } } /* @@ -2213,15 +3170,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); - for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { - pte_t entry, *pte; - /* - * Note that NUMA hinting access restrictions are not - * transferred to avoid any possibility of altering - * permissions across VMAs. - */ - if (freeze || pmd_migration) { - swp_entry_t swp_entry; + pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte); + + /* + * 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)); @@ -2240,37 +3200,61 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_swp_mksoft_dirty(entry); if (uffd_wp) entry = pte_swp_mkuffd_wp(entry); - } else { - entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); - entry = maybe_mkwrite(entry, vma); - if (anon_exclusive) - SetPageAnonExclusive(page + i); - if (!young) - entry = pte_mkold(entry); - /* NOTE: this may set soft-dirty too on some archs */ - if (dirty) - entry = pte_mkdirty(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) { /* - * NOTE: this needs to happen after pte_mkdirty, - * because some archs (sparc64, loongarch) could - * set hw write bit when mkdirty. + * anon_exclusive was already propagated to the relevant + * pages corresponding to the pte entries when freeze + * is false. */ - if (!write) - entry = pte_wrprotect(entry); + 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_mksoft_dirty(entry); + entry = pte_swp_mksoft_dirty(entry); if (uffd_wp) - entry = pte_mkuffd_wp(entry); - page_add_anon_rmap(page + i, vma, addr, false); + entry = pte_swp_mkuffd_wp(entry); + VM_WARN_ON(!pte_none(ptep_get(pte + i))); + set_pte_at(mm, addr, pte + i, entry); } - pte = pte_offset_map(&_pmd, addr); - BUG_ON(!pte_none(*pte)); - set_pte_at(mm, addr, pte, entry); - pte_unmap(pte); + } 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_migration) - page_remove_rmap(page, vma, true); + if (!pmd_is_migration_entry(*pmd)) + folio_remove_rmap_pmd(folio, page, vma); if (freeze) put_page(page); @@ -2278,63 +3262,39 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pmd_populate(mm, pmd, pgtable); } +void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, bool freeze) +{ + 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); +} + void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct folio *folio) + unsigned long address, bool freeze) { spinlock_t *ptl; struct mmu_notifier_range range; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + 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); - - /* - * If caller asks to setup a migration entry, we need a folio to check - * pmd against. Otherwise we can end up replacing wrong folio. - */ - VM_BUG_ON(freeze && !folio); - VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); - - if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) { - /* - * It's safe to call pmd_page when folio is set because it's - * guaranteed that pmd is present. - */ - if (folio && folio != page_folio(pmd_page(*pmd))) - goto out; - __split_huge_pmd_locked(vma, pmd, range.start, freeze); - } - -out: + split_huge_pmd_locked(vma, range.start, pmd, freeze); spin_unlock(ptl); - /* - * No need to double call mmu_notifier->invalidate_range() callback. - * They are 3 cases to consider inside __split_huge_pmd_locked(): - * 1) pmdp_huge_clear_flush_notify() call invalidate_range() obvious - * 2) __split_huge_zero_page_pmd() read only zero page and any write - * fault will trigger a flush_notify before pointing to a new page - * (it is fine if the secondary mmu keeps pointing to the old zero - * page in the meantime) - * 3) Split a huge pmd into pte pointing to the same page. No need - * to invalidate secondary tlb entry they are all still valid. - * any further changes to individual pte will notify. So no need - * to call mmu_notifier->invalidate_range() - */ - mmu_notifier_invalidate_range_only_end(&range); + mmu_notifier_invalidate_range_end(&range); } void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct folio *folio) + bool freeze) { pmd_t *pmd = mm_find_pmd(vma->vm_mm, address); if (!pmd) return; - __split_huge_pmd(vma, pmd, address, freeze, folio); + __split_huge_pmd(vma, pmd, address, freeze); } static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) @@ -2346,13 +3306,13 @@ static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned 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, NULL); + split_huge_pmd_address(vma, address, false); } void vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - long adjust_next) + unsigned long start, + unsigned long end, + struct vm_area_struct *next) { /* Check if we need to split start first. */ split_huge_pmd_if_needed(vma, start); @@ -2360,25 +3320,21 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, /* Check if we need to split end next. */ split_huge_pmd_if_needed(vma, end); - /* - * If we're also updating the next vma vm_start, - * check if we need to split it. - */ - if (adjust_next > 0) { - struct vm_area_struct *next = find_vma(vma->vm_mm, vma->vm_end); - unsigned long nstart = next->vm_start; - nstart += adjust_next; - split_huge_pmd_if_needed(next, nstart); - } + /* If we're incrementing next->vm_start, we might need to split it. */ + if (next) + split_huge_pmd_if_needed(next, end); } static void unmap_folio(struct folio *folio) { - enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | - TTU_SYNC; + enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC | + TTU_BATCH_FLUSH; VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + 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. @@ -2388,9 +3344,86 @@ static void unmap_folio(struct folio *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; + } + + orig_pmd = pmdp_huge_clear_flush(vma, addr, pmdp); + + /* + * Syncing against concurrent GUP-fast: + * - clear PMD; barrier; read refcount + * - inc refcount; barrier; read PMD + */ + smp_mb(); + + ref_count = folio_ref_count(folio); + map_count = folio_mapcount(folio); + + /* + * 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; +} + +bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmdp, struct folio *folio) +{ + 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); } -static void remap_page(struct folio *folio, unsigned long nr) +static void remap_page(struct folio *folio, unsigned long nr, int flags) { int i = 0; @@ -2398,7 +3431,7 @@ static void remap_page(struct folio *folio, unsigned long nr) if (!folio_test_anon(folio)) return; for (;;) { - remove_migration_ptes(folio, folio, true); + remove_migration_ptes(folio, folio, RMP_LOCKED | flags); i += folio_nr_pages(folio); if (i >= nr) break; @@ -2406,272 +3439,532 @@ static void remap_page(struct folio *folio, unsigned long nr) } } -static void lru_add_page_tail(struct page *head, struct page *tail, +static void lru_add_split_folio(struct folio *folio, struct folio *new_folio, struct lruvec *lruvec, struct list_head *list) { - VM_BUG_ON_PAGE(!PageHead(head), head); - VM_BUG_ON_PAGE(PageCompound(tail), head); - VM_BUG_ON_PAGE(PageLRU(tail), head); + 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(PageLRU(head)); - get_page(tail); - list_add_tail(&tail->lru, list); + 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(!PageLRU(head)); - if (PageUnevictable(tail)) - tail->mlock_count = 0; + VM_WARN_ON(!folio_test_lru(folio)); + if (folio_test_unevictable(folio)) + new_folio->mlock_count = 0; else - list_add_tail(&tail->lru, &head->lru); - SetPageLRU(tail); + list_add_tail(&new_folio->lru, &folio->lru); + folio_set_lru(new_folio); } } -static void __split_huge_page_tail(struct page *head, int tail, - struct lruvec *lruvec, struct list_head *list) +/* Racy check whether the huge page can be split */ +bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { - struct page *page_tail = head + tail; + 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; +} - VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail); +static bool page_range_has_hwpoisoned(struct page *page, long nr_pages) +{ + for (; nr_pages; page++, nr_pages--) + if (PageHWPoison(page)) + return true; + return false; +} +/* + * 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) +{ + /* 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); /* - * 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. + * Skip the first new_nr_pages, since the new folio from them have all + * the flags from the original folio. */ - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; - page_tail->flags |= (head->flags & - ((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_X - (1L << PG_arch_2) | - (1L << PG_arch_3) | + 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_PAGE(atomic_read(&new_folio->_mapcount) != -1, new_head); + + /* + * 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. + */ + 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 - (1L << PG_dirty) | - LRU_GEN_MASK | LRU_REFS_MASK)); +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 + (1L << PG_arch_3) | +#endif + (1L << PG_dirty) | + LRU_GEN_MASK | LRU_REFS_MASK)); - /* ->mapping in first and second tail page is replaced by other uses */ - VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, - page_tail); - page_tail->mapping = head->mapping; - page_tail->index = head->index + tail; + if (handle_hwpoison && + page_range_has_hwpoisoned(new_head, new_nr_pages)) + folio_set_has_hwpoisoned(new_folio); - /* - * page->private should not be set in tail pages with the exception - * of swap cache pages that store the swp_entry_t in tail pages. - * Fix up and warn once if private is unexpectedly set. - * - * What of 32-bit systems, on which head[1].compound_pincount overlays - * head[1].private? No problem: THP_SWAP is not enabled on 32-bit, and - * compound_pincount must be 0 for folio_ref_freeze() to have succeeded. - */ - if (!folio_test_swapcache(page_folio(head))) { - VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail); - page_tail->private = 0; + 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(); + + /* + * Clear PageTail before unfreezing page refcount. + * + * After successful get_page_unless_zero() might follow put_page() + * which needs correct compound_head(). + */ + clear_compound_head(new_head); + if (new_order) { + prep_compound_page(new_head, new_order); + folio_set_large_rmappable(new_folio); + } + + 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)); } - /* Page flags must be visible before we make the page non-compound. */ - smp_wmb(); + if (new_order) + folio_set_order(folio, new_order); + else + ClearPageCompound(&folio->page); +} + +/** + * __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) +{ + 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; /* - * Clear PageTail before unfreezing page refcount. - * - * After successful get_page_unless_zero() might follow put_page() - * which needs correct compound_head(). + * split to new_order one order at a time. For uniform split, + * folio is split to new_order directly. */ - clear_compound_head(page_tail); + 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) { + /* + * uniform split has xas_split_alloc() called before + * irq is disabled to allocate enough memory, whereas + * non-uniform split can handle ENOMEM. + */ + 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); + } + } - /* Finally unfreeze refcount. Additional reference from page cache. */ - page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || - PageSwapCache(head))); + 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 (page_is_young(head)) - set_page_young(page_tail); - if (page_is_idle(head)) - set_page_idle(page_tail); + 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; + } - page_cpupid_xchg_last(page_tail, page_cpupid_last(head)); + return 0; +} + +bool folio_split_supported(struct folio *folio, unsigned int new_order, + enum split_type split_type, bool warns) +{ + 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; + } + } /* - * always add to the tail because some iterators expect new - * pages to show after the currently processed elements - e.g. - * migrate_pages + * 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. */ - lru_add_page_tail(head, page_tail, lruvec, list); + 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 void __split_huge_page(struct page *page, struct list_head *list, - pgoff_t end) +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) { - struct folio *folio = page_folio(page); - struct page *head = &folio->page; - struct lruvec *lruvec; - struct address_space *swap_cache = NULL; - unsigned long offset = 0; - unsigned int nr = thp_nr_pages(head); - int i; + 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; - /* complete memcg works before add pages to LRU */ - split_page_memcg(head, nr); - - if (PageAnon(head) && PageSwapCache(head)) { - swp_entry_t entry = { .val = page_private(head) }; - - offset = swp_offset(entry); - swap_cache = swap_address_space(entry); - xa_lock(&swap_cache->i_pages); - } - - /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ - lruvec = folio_lruvec_lock(folio); - - ClearPageHasHWPoisoned(head); - - for (i = nr - 1; i >= 1; i--) { - __split_huge_page_tail(head, i, lruvec, list); - /* Some pages can be beyond EOF: drop them from page cache */ - if (head[i].index >= end) { - struct folio *tail = page_folio(head + i); - - if (shmem_mapping(head->mapping)) - shmem_uncharge(head->mapping->host, 1); - else if (folio_test_clear_dirty(tail)) - folio_account_cleaned(tail, - inode_to_wb(folio->mapping->host)); - __filemap_remove_folio(tail, NULL); - folio_put(tail); - } else if (!PageAnon(page)) { - __xa_store(&head->mapping->i_pages, head[i].index, - head + i, 0); - } else if (swap_cache) { - __xa_store(&swap_cache->i_pages, offset + i, - head + i, 0); + 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); - ClearPageCompound(head); - unlock_page_lruvec(lruvec); - /* Caller disabled irqs, so they are still disabled here */ + 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); + } + } + } - split_page_owner(head, nr); + if (folio_test_swapcache(folio)) { + if (mapping) { + VM_WARN_ON_ONCE_FOLIO(mapping, folio); + return -EINVAL; + } - /* See comment in __split_huge_page_tail() */ - if (PageAnon(head)) { - /* Additional pin to swap cache */ - if (PageSwapCache(head)) { - page_ref_add(head, 2); - xa_unlock(&swap_cache->i_pages); - } else { - page_ref_inc(head); + ci = swap_cluster_get_and_lock(folio); } - } else { - /* Additional pin to page cache */ - page_ref_add(head, 2); - xa_unlock(&head->mapping->i_pages); - } - local_irq_enable(); - remap_page(folio, nr); + /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ + if (do_lru) + lruvec = folio_lruvec_lock(folio); - if (PageSwapCache(head)) { - swp_entry_t entry = { .val = page_private(head) }; + ret = __split_unmapped_folio(folio, new_order, split_at, xas, + mapping, split_type); - split_swap_cluster(entry); - } + /* + * 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); - for (i = 0; i < nr; i++) { - struct page *subpage = head + i; - if (subpage == page) - continue; - unlock_page(subpage); + 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); /* - * 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. + * 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. */ - free_page_and_swap_cache(subpage); - } -} + expected_refs = folio_expected_ref_count(folio) + 1; + folio_ref_unfreeze(folio, expected_refs); -/* Racy check whether the huge page can be split */ -bool can_split_folio(struct folio *folio, int *pextra_pins) -{ - int extra_pins; + if (do_lru) + unlock_page_lruvec(lruvec); - /* 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 - 1; + if (ci) + swap_cluster_unlock(ci); + } else { + split_queue_unlock(ds_queue); + return -EAGAIN; + } + + return ret; } -/* - * This function splits huge page into normal pages. @page can point to any - * subpage of huge page to split. Split doesn't change the position of @page. - * - * Only caller must hold pin on the @page, otherwise split fails with -EBUSY. - * The huge page must be locked. - * - * If @list is null, tail pages will be added to LRU list, otherwise, to @list. +/** + * __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) * - * Both head page and tail pages will inherit mapping, flags, and so on from - * the hugepage. + * 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(). * - * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if - * they are not mapped. + * 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. * - * Returns 0 if the hugepage is split successfully. - * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under - * us. + * Return: 0 - successful, <0 - failed (if -ENOMEM is returned, @folio might be + * split but not to @new_order, the caller needs to check) */ -int split_huge_page_to_list(struct page *page, struct list_head *list) +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) { - struct folio *folio = page_folio(page); - struct deferred_split *ds_queue = get_deferred_split_queue(&folio->page); XA_STATE(xas, &folio->mapping->i_pages, folio->index); - struct anon_vma *anon_vma = NULL; + 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; + pgoff_t end = 0; bool is_hzp; - VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); + VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); - is_hzp = is_huge_zero_page(&folio->page); - VM_WARN_ON_ONCE_FOLIO(is_hzp, folio); - if (is_hzp) + if (folio != page_folio(split_at) || folio != page_folio(lock_at)) + return -EINVAL; + + /* + * 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. + */ + 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 (folio_test_anon(folio)) { + 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 @@ -2685,44 +3978,45 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ret = -EBUSY; goto out; } - end = -1; - mapping = NULL; anon_vma_lock_write(anon_vma); + mapping = NULL; } else { + unsigned int min_order; gfp_t gfp; mapping = folio->mapping; - - /* Truncated ? */ - if (!mapping) { - ret = -EBUSY; + 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 (folio_test_private(folio) && - !filemap_release_folio(folio, gfp)) { + if (!filemap_release_folio(folio, gfp)) { ret = -EBUSY; goto out; } - xas_split_alloc(&xas, folio, folio_order(folio), gfp); - if (xas_error(&xas)) { - ret = xas_error(&xas); - 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_huge_page() 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. + *__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)) @@ -2733,7 +4027,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) * Racy check if we can split the page, before unmap_folio() will * split PMDs */ - if (!can_split_folio(folio, &extra_pins)) { + if (!can_split_folio(folio, 1, &extra_pins)) { ret = -EAGAIN; goto out_unlock; } @@ -2749,42 +4043,47 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) */ xas_lock(&xas); xas_reset(&xas); - if (xas_load(&xas) != folio) + if (xas_load(&xas) != folio) { + ret = -EAGAIN; goto fail; + } } - /* Prevent deferred_split_scan() touching ->_refcount */ - spin_lock(&ds_queue->split_queue_lock); - if (folio_ref_freeze(folio, 1 + extra_pins)) { - if (!list_empty(page_deferred_list(&folio->page))) { - ds_queue->split_queue_len--; - list_del(page_deferred_list(&folio->page)); - } - spin_unlock(&ds_queue->split_queue_lock); - if (mapping) { - int nr = folio_nr_pages(folio); + 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); - xas_split(&xas, folio, folio_order(folio)); - 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); - } - } + local_irq_enable(); - __split_huge_page(page, list, end); - ret = 0; - } else { - spin_unlock(&ds_queue->split_queue_lock); -fail: - if (mapping) - xas_unlock(&xas); - local_irq_enable(); - remap_page(folio, folio_nr_pages(folio)); - ret = -EAGAIN; + 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: @@ -2796,59 +4095,249 @@ out_unlock: i_mmap_unlock_read(mapping); out: xas_destroy(&xas); - count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + 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; +} + +/** + * 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) +{ + int extra_pins, ret = 0; + + 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); + + if (!can_split_folio(folio, 1, &extra_pins)) + return -EAGAIN; + + 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; } -void free_transhuge_page(struct page *page) +/* + * 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) { - struct deferred_split *ds_queue = get_deferred_split_queue(page); + struct folio *folio = page_folio(page); + + return __folio_split(folio, new_order, &folio->page, page, list, + SPLIT_TYPE_UNIFORM); +} + +/** + * 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) +{ + return __folio_split(folio, new_order, split_at, &folio->page, list, + SPLIT_TYPE_NON_UNIFORM); +} + +int min_order_for_split(struct folio *folio) +{ + if (folio_test_anon(folio)) + return 0; + + 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); +} + +int split_folio_to_list(struct folio *folio, struct list_head *list) +{ + 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; - spin_lock_irqsave(&ds_queue->split_queue_lock, flags); - if (!list_empty(page_deferred_list(page))) { + 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--; - list_del(page_deferred_list(page)); + 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; } - spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); - free_compound_page(page); + split_queue_unlock_irqrestore(ds_queue, flags); + + return unqueued; /* useful for debug warnings */ } -void deferred_split_huge_page(struct page *page) +/* 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 = get_deferred_split_queue(page); -#ifdef CONFIG_MEMCG - struct mem_cgroup *memcg = page_memcg(compound_head(page)); -#endif + struct deferred_split *ds_queue; unsigned long flags; - VM_BUG_ON_PAGE(!PageTransHuge(page), 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 (!partially_mapped && !split_underused_thp) + return; /* - * The try_to_unmap() in page reclaim path might reach here too, - * this may cause a race condition to corrupt deferred split queue. - * And, if page reclaim is already handling the same page, it is - * unnecessary to handle it again in shrinker. - * - * Check PageSwapCache to determine if the page is being - * handled by page reclaim since THP swap would add the page into - * swap cache before calling try_to_unmap(). + * 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. */ - if (PageSwapCache(page)) + if (folio_test_swapcache(folio)) return; - spin_lock_irqsave(&ds_queue->split_queue_lock, flags); - if (list_empty(page_deferred_list(page))) { - count_vm_event(THP_DEFERRED_SPLIT_PAGE); - list_add_tail(page_deferred_list(page), &ds_queue->split_queue); + 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); + + } + } 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++; -#ifdef CONFIG_MEMCG if (memcg) - set_shrinker_bit(memcg, page_to_nid(page), - deferred_split_shrinker.id); -#endif + set_shrinker_bit(memcg, folio_nid(folio), + shrinker_id(deferred_split_shrinker)); } - spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + split_queue_unlock_irqrestore(ds_queue, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, @@ -2864,53 +4353,115 @@ static unsigned long deferred_split_count(struct shrinker *shrink, return READ_ONCE(ds_queue->split_queue_len); } +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; + + 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 pglist_data *pgdata = NODE_DATA(sc->nid); - struct deferred_split *ds_queue = &pgdata->deferred_split_queue; + struct deferred_split *ds_queue; unsigned long flags; - LIST_HEAD(list), *pos, *next; - struct page *page; - int split = 0; + struct folio *folio, *next; + int split = 0, i; + struct folio_batch fbatch; -#ifdef CONFIG_MEMCG - if (sc->memcg) - ds_queue = &sc->memcg->deferred_split_queue; -#endif + folio_batch_init(&fbatch); - spin_lock_irqsave(&ds_queue->split_queue_lock, flags); +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_safe(pos, next, &ds_queue->split_queue) { - page = list_entry((void *)pos, struct page, deferred_list); - page = compound_head(page); - if (get_page_unless_zero(page)) { - list_move(page_deferred_list(page), &list); - } else { - /* We lost race with put_compound_page() */ - list_del_init(page_deferred_list(page)); - ds_queue->split_queue_len--; + 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; } - spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + split_queue_unlock_irqrestore(ds_queue, flags); - list_for_each_safe(pos, next, &list) { - page = list_entry((void *)pos, struct page, deferred_list); - if (!trylock_page(page)) + 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; - /* split_huge_page() removes page from list on success */ - if (!split_huge_page(page)) + if (!split_folio(folio)) { + did_split = true; + if (underused) + count_vm_event(THP_UNDERUSED_SPLIT_PAGE); split++; - unlock_page(page); + } + folio_unlock(folio); next: - put_page(page); + if (did_split || !folio_test_partially_mapped(folio)) + continue; + /* + * 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. + */ + 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); - spin_lock_irqsave(&ds_queue->split_queue_lock, flags); - list_splice_tail(&list, &ds_queue->split_queue); - spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + if (sc->nr_to_scan && !list_empty(&ds_queue->split_queue)) { + cond_resched(); + goto retry; + } /* * Stop shrinker if we didn't split any page, but the queue is empty. @@ -2921,19 +4472,39 @@ next: return split; } -static struct shrinker deferred_split_shrinker = { - .count_objects = deferred_split_count, - .scan_objects = deferred_split_scan, - .seeks = DEFAULT_SEEKS, - .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | - SHRINKER_NONSLAB, -}; +#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_irq(&ds_queue->split_queue_lock); + spin_lock_nested(&parent_ds_queue->split_queue_lock, SINGLE_DEPTH_NESTING); + + if (!ds_queue->split_queue_len) + goto unlock; + + 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; + + for_each_node(nid) + set_shrinker_bit(parent, nid, shrinker_id(deferred_split_shrinker)); + +unlock: + spin_unlock(&parent_ds_queue->split_queue_lock); + spin_unlock_irq(&ds_queue->split_queue_lock); +} +#endif #ifdef CONFIG_DEBUG_FS static void split_huge_pages_all(void) { struct zone *zone; struct page *page; + struct folio *folio; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; @@ -2946,24 +4517,32 @@ static void split_huge_pages_all(void) int nr_pages; page = pfn_to_online_page(pfn); - if (!page || !get_page_unless_zero(page)) + if (!page || PageTail(page)) + continue; + folio = page_folio(page); + if (!folio_try_get(folio)) continue; - if (zone != page_zone(page)) + if (unlikely(page_folio(page) != folio)) + goto next; + + if (zone != folio_zone(folio)) goto next; - if (!PageHead(page) || PageHuge(page) || !PageLRU(page)) + if (!folio_test_large(folio) + || folio_test_hugetlb(folio) + || !folio_test_lru(folio)) goto next; total++; - lock_page(page); - nr_pages = thp_nr_pages(page); - if (!split_huge_page(page)) + folio_lock(folio); + nr_pages = folio_nr_pages(folio); + if (!split_folio(folio)) split++; pfn += nr_pages - 1; - unlock_page(page); + folio_unlock(folio); next: - put_page(page); + folio_put(folio); cond_resched(); } } @@ -2978,7 +4557,8 @@ static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) } static int split_huge_pages_pid(int pid, unsigned long vaddr_start, - unsigned long vaddr_end) + unsigned long vaddr_end, unsigned int new_order, + long in_folio_offset) { int ret = 0; struct task_struct *task; @@ -2989,16 +4569,11 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, vaddr_start &= PAGE_MASK; vaddr_end &= PAGE_MASK; - /* Find the task_struct from pid */ - rcu_read_lock(); - task = find_task_by_vpid(pid); + task = find_get_task_by_vpid(pid); if (!task) { - rcu_read_unlock(); ret = -ESRCH; goto out; } - get_task_struct(task); - rcu_read_unlock(); /* Find the mm_struct */ mm = get_task_mm(task); @@ -3009,8 +4584,8 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, goto out; } - pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n", - pid, vaddr_start, vaddr_end); + 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); mmap_read_lock(mm); /* @@ -3019,7 +4594,10 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, */ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { struct vm_area_struct *vma = vma_lookup(mm, addr); - struct page *page; + struct folio_walk fw; + struct folio *folio; + struct address_space *mapping; + unsigned int target_order = new_order; if (!vma) break; @@ -3030,28 +4608,60 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, continue; } - /* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); - - if (IS_ERR_OR_NULL(page)) + folio = folio_walk_start(&fw, vma, addr, 0); + if (!folio) continue; - if (!is_transparent_hugepage(page)) + 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)); + } + + if (target_order >= folio_order(folio)) goto next; total++; - if (!can_split_folio(page_folio(page), NULL)) + /* + * 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 (!folio_test_private(folio) && + !can_split_folio(folio, 0, NULL)) goto next; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto next; + folio_get(folio); + folio_walk_end(&fw, vma); - if (!split_huge_page(page)) - split++; + 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 { + struct page *split_at = folio_page(folio, + in_folio_offset); + if (!folio_split(folio, target_order, split_at, NULL)) + split++; + } - unlock_page(page); +unlock: + + folio_unlock(folio); + folio_put(folio); + + cond_resched(); + continue; next: - put_page(page); + folio_walk_end(&fw, vma); cond_resched(); } mmap_read_unlock(mm); @@ -3064,7 +4674,8 @@ out: } static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, - pgoff_t off_end) + pgoff_t off_end, unsigned int new_order, + long in_folio_offset) { struct filename *file; struct file *candidate; @@ -3073,6 +4684,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, 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)) @@ -3082,17 +4695,18 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, if (IS_ERR(candidate)) goto out; - pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx]\n", - file_path, off_start, off_end); + 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); mapping = candidate->f_mapping; + min_order = mapping_min_folio_order(mapping); + target_order = max(new_order, min_order); for (index = off_start; index < off_end; index += nr_pages) { - struct folio *folio = __filemap_get_folio(mapping, index, - FGP_ENTRY, 0); + struct folio *folio = filemap_get_folio(mapping, index); nr_pages = 1; - if (xa_is_value(folio) || !folio) + if (IS_ERR(folio)) continue; if (!folio_test_large(folio)) @@ -3101,12 +4715,26 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, total++; nr_pages = folio_nr_pages(folio); + if (target_order >= folio_order(folio)) + goto next; + if (!folio_trylock(folio)) goto next; - if (!split_folio(folio)) - split++; + 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); @@ -3129,10 +4757,15 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, { static DEFINE_MUTEX(split_debug_mutex); ssize_t ret; - /* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */ + /* + * 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; ret = mutex_lock_interruptible(&split_debug_mutex); if (ret) @@ -3148,42 +4781,46 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, if (input_buf[0] == '/') { char *tok; - char *buf = input_buf; + 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); - tok = strsep(&buf, ","); - if (tok) { - strcpy(file_path, tok); + tok = strsep(&tok_buf, ","); + if (tok && tok_buf) { + strscpy(file_path, tok); } else { ret = -EINVAL; goto out; } - ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end); - if (ret != 2) { + 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); + ret = split_huge_pages_in_file(file_path, off_start, off_end, + new_order, in_folio_offset); if (!ret) ret = input_len; goto out; } - ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); + 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) { + } else if (ret != 3 && ret != 4 && ret != 5) { ret = -EINVAL; goto out; } - ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end); + ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order, + in_folio_offset); if (!ret) ret = strlen(input_buf); out: @@ -3195,7 +4832,6 @@ out: static const struct file_operations split_huge_pages_fops = { .owner = THIS_MODULE, .write = split_huge_pages_write, - .llseek = no_llseek, }; static int __init split_huge_pages_debugfs(void) @@ -3211,6 +4847,7 @@ late_initcall(split_huge_pages_debugfs); int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { + 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; @@ -3223,17 +4860,20 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, return 0; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); - pmdval = pmdp_invalidate(vma, address, pvmw->pmd); + 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 page_try_share_anon_rmap(): invalidate PMD first. */ - anon_exclusive = PageAnon(page) && PageAnonExclusive(page); - if (anon_exclusive && page_try_share_anon_rmap(page)) { + /* 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)) - set_page_dirty(page); + folio_mark_dirty(folio); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); else if (anon_exclusive) @@ -3247,9 +4887,11 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, 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); - page_remove_rmap(page, vma, true); - put_page(page); + folio_remove_rmap_pmd(folio, page, vma); + folio_put(folio); trace_set_migration_pmd(address, pmd_val(pmdswp)); return 0; @@ -3257,42 +4899,61 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { + 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; - swp_entry_t entry; + softleaf_t entry; if (!(pvmw->pmd && !pvmw->pte)) return; - entry = pmd_to_swp_entry(*pvmw->pmd); - get_page(new); - pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); + 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 (is_writable_migration_entry(entry)) - pmde = maybe_pmd_mkwrite(pmde, vma); + if (softleaf_is_migration_write(entry)) + pmde = pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) - pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); - if (!is_migration_entry_young(entry)) + 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 (PageDirty(new) && is_migration_entry_dirty(entry)) + if (folio_test_dirty(folio) && softleaf_is_migration_dirty(entry)) pmde = pmd_mkdirty(pmde); - if (PageAnon(new)) { - rmap_t rmap_flags = RMAP_COMPOUND; + 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 (!is_readable_migration_entry(entry)) + if (!softleaf_is_migration_read(entry)) rmap_flags |= RMAP_EXCLUSIVE; - page_add_anon_rmap(new, vma, haddr, rmap_flags); + folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags); } else { - page_add_file_rmap(new, vma, true); + folio_add_file_rmap_pmd(folio, new, vma); } - VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new)); + 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 */ |