diff options
Diffstat (limited to 'mm/huge_memory.c')
| -rw-r--r-- | mm/huge_memory.c | 2408 |
1 files changed, 1672 insertions, 736 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 89f58c7603b2..d3e66136e41a 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> @@ -20,6 +19,7 @@ #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> @@ -38,6 +38,8 @@ #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/compat.h> +#include <linux/pgalloc_tag.h> +#include <linux/pagewalk.h> #include <asm/tlb.h> #include <asm/pgalloc.h> @@ -71,40 +73,57 @@ 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; + +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return false; + + 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, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { + bool smaps = tva_flags & TVA_SMAPS; + bool in_pf = tva_flags & TVA_IN_PF; + bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS; + unsigned long supported_orders; + /* Check the intersection of requested and supported orders. */ - orders &= vma_is_anonymous(vma) ? - THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE; + 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; - /* - * 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)) - return 0; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ @@ -147,9 +166,9 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) - return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, - !enforce_sysfs, vma->vm_mm, vm_flags) - ? orders : 0; + return shmem_allowable_huge_orders(file_inode(vma->vm_file), + vma, vma->vm_pgoff, 0, + !enforce_sysfs); if (!vma_is_anonymous(vma)) { /* @@ -191,24 +210,26 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, static bool get_huge_zero_page(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_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); @@ -226,10 +247,10 @@ 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); + return READ_ONCE(huge_zero_folio); if (!get_huge_zero_page()) return NULL; @@ -237,10 +258,10 @@ struct page *mm_get_huge_zero_page(struct mm_struct *mm) if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); - 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(); @@ -257,10 +278,10 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { - struct page *zero_page = xchg(&huge_zero_page, NULL); - BUG_ON(zero_page == NULL); + 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; } @@ -425,6 +446,27 @@ 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, @@ -433,6 +475,7 @@ static struct attribute *hugepage_attr[] = { #ifdef CONFIG_SHMEM &shmem_enabled_attr.attr, #endif + &split_underused_thp_attr.attr, NULL, }; @@ -445,16 +488,8 @@ static void thpsize_release(struct kobject *kobj); static DEFINE_SPINLOCK(huge_anon_orders_lock); static LIST_HEAD(thpsize_list); -struct thpsize { - struct kobject kobj; - struct list_head node; - int order; -}; - -#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) - -static ssize_t thpsize_enabled_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +static ssize_t anon_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { int order = to_thpsize(kobj)->order; const char *output; @@ -471,9 +506,9 @@ static ssize_t thpsize_enabled_show(struct kobject *kobj, return sysfs_emit(buf, "%s\n", output); } -static ssize_t thpsize_enabled_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static ssize_t anon_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) { int order = to_thpsize(kobj)->order; ssize_t ret = count; @@ -505,19 +540,45 @@ static ssize_t thpsize_enabled_store(struct kobject *kobj, } else ret = -EINVAL; + if (ret > 0) { + int err; + + err = start_stop_khugepaged(); + if (err) + ret = err; + } return ret; } -static struct kobj_attribute thpsize_enabled_attr = - __ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store); +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 *thpsize_attrs[] = { - &thpsize_enabled_attr.attr, +static struct attribute *file_ctrl_attrs[] = { +#ifdef CONFIG_SHMEM + &thpsize_shmem_enabled_attr.attr, +#endif NULL, }; -static const struct attribute_group thpsize_attr_group = { - .attrs = thpsize_attrs, +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 = { @@ -525,31 +586,179 @@ static const struct kobj_type thpsize_ktype = { .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; + int ret = -ENOMEM; thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL); if (!thpsize) - return ERR_PTR(-ENOMEM); + goto err; + + thpsize->order = order; ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent, "hugepages-%lukB", size); if (ret) { kfree(thpsize); - return ERR_PTR(ret); + goto err; } - ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group); - if (ret) { - kobject_put(&thpsize->kobj); - return ERR_PTR(ret); + + 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; } - thpsize->order = order; return thpsize; +err_put: + kobject_put(&thpsize->kobj); +err: + return ERR_PTR(ret); } static void thpsize_release(struct kobject *kobj) @@ -569,7 +778,8 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time * constant so we have to do this here. */ - huge_anon_orders_inherit = BIT(PMD_ORDER); + 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)) { @@ -589,7 +799,7 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) goto remove_hp_group; } - orders = THP_ORDERS_ALL_ANON; + orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT; order = highest_order(orders); while (orders) { thpsize = thpsize_create(order, *hugepage_kobj); @@ -684,11 +894,6 @@ static int __init hugepage_init(void) * hugepages can't be allocated by the buddy allocator */ MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_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); err = hugepage_init_sysfs(&hugepage_kobj); if (err) @@ -759,6 +964,92 @@ 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)) @@ -788,33 +1079,25 @@ struct deferred_split *get_deferred_split_queue(struct folio *folio) } #endif -void folio_prep_large_rmappable(struct folio *folio) -{ - if (!folio || !folio_test_large(folio)) - return; - if (folio_order(folio) > 1) - INIT_LIST_HEAD(&folio->_deferred_list); - folio_set_large_rmappable(folio); -} - -static inline bool is_transparent_hugepage(struct folio *folio) +static inline bool is_transparent_hugepage(const struct folio *folio) { if (!folio_test_large(folio)) return false; - return is_huge_zero_page(&folio->page) || + 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, off_sub; - if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall()) + if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) return 0; if (off_end <= off_align || (off_end - off_align) < size) @@ -824,8 +1107,8 @@ 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(current->mm, filp, addr, len_pad, + off >> PAGE_SHIFT, flags, vm_flags); /* * The failure might be due to length padding. The caller will retry @@ -843,67 +1126,117 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, off_sub = (off - ret) & (size - 1); - if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown && - !off_sub) + if (test_bit(MMF_TOPDOWN, ¤t->mm->flags) && !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(current->mm, 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; - struct folio *folio = page_folio(page); - 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_FOLIO(!folio_test_large(folio), folio); + folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK); + + if (unlikely(!folio)) { + count_vm_event(THP_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + return NULL; + } + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); - 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; } folio_throttle_swaprate(folio, gfp); - pgtable = pte_alloc_one(vma->vm_mm); - if (unlikely(!pgtable)) { - ret = VM_FAULT_OOM; - goto release; - } - - clear_huge_page(page, vmf->address, HPAGE_PMD_NR); + /* + * 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 - * clear_huge_page writes become visible before the set_pmd_at() + * folio_zero_user writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); + return folio; +} + +static void map_anon_folio_pmd(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); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + count_vm_event(THP_FAULT_ALLOC); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); +} + +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + pgtable_t pgtable; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) { + ret = VM_FAULT_OOM; + goto release; + } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { - pmd_t entry; - ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; @@ -917,19 +1250,11 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, 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); - folio_add_new_anon_rmap(folio, vma, haddr); - folio_add_lru_vma(folio, 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(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); + deferred_split_folio(folio, false); spin_unlock(vmf->ptl); - count_vm_event(THP_FAULT_ALLOC); - count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; @@ -979,15 +1304,12 @@ 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); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); mm_inc_nr_ptes(mm); @@ -996,27 +1318,28 @@ 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 (!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; @@ -1034,8 +1357,8 @@ 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); } @@ -1045,29 +1368,24 @@ 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, +static int 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 mm_struct *mm = vma->vm_mm; pmd_t entry; - spinlock_t *ptl; - ptl = pmd_lock(mm, pmd); + lockdep_assert_held(pmd_lockptr(mm, pmd)); + if (!pmd_none(*pmd)) { if (write) { if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); - goto out_unlock; + return -EEXIST; } entry = pmd_mkyoung(*pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); @@ -1075,12 +1393,14 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, update_mmu_cache_pmd(vma, addr, pmd); } - goto out_unlock; + return -EEXIST; } entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); + else + entry = pmd_mkspecial(entry); if (write) { entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); @@ -1089,16 +1409,11 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); - pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); - -out_unlock: - spin_unlock(ptl); - if (pgtable) - pte_free(mm, pgtable); + return 0; } /** @@ -1117,6 +1432,8 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; pgtable_t pgtable = NULL; + spinlock_t *ptl; + int error; /* * If we had pmd_special, we could avoid all these restrictions, @@ -1138,13 +1455,58 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) return VM_FAULT_OOM; } - track_pfn_insert(vma, &pgprot, pfn); + pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot); + + ptl = pmd_lock(vma->vm_mm, vmf->pmd); + error = insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, + pgtable); + spin_unlock(ptl); + if (error && pgtable) + pte_free(vma->vm_mm, pgtable); - insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, + bool write) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address & PMD_MASK; + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pgtable_t pgtable = NULL; + int error; + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER)) + 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, vmf->pmd); + if (pmd_none(*vmf->pmd)) { + folio_get(folio); + folio_add_file_rmap_pmd(folio, &folio->page, vma); + add_mm_counter(mm, mm_counter_file(folio), HPAGE_PMD_NR); + } + error = insert_pfn_pmd(vma, addr, vmf->pmd, + pfn_to_pfn_t(folio_pfn(folio)), vma->vm_page_prot, + write, pgtable); + spin_unlock(ptl); + if (error && pgtable) + pte_free(mm, pgtable); + + return VM_FAULT_NOPAGE; +} +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) { @@ -1159,35 +1521,30 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, struct mm_struct *mm = vma->vm_mm; pgprot_t prot = vma->vm_page_prot; pud_t entry; - spinlock_t *ptl; - ptl = pud_lock(mm, pud); if (!pud_none(*pud)) { if (write) { - if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { - WARN_ON_ONCE(!is_huge_zero_pud(*pud)); - goto out_unlock; - } + if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn))) + return; entry = pud_mkyoung(*pud); entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); if (pudp_set_access_flags(vma, addr, pud, entry, 1)) update_mmu_cache_pud(vma, addr, pud); } - goto out_unlock; + return; } entry = pud_mkhuge(pfn_t_pud(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); + else + 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); } /** @@ -1205,6 +1562,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) unsigned long addr = vmf->address & PUD_MASK; struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; + spinlock_t *ptl; /* * If we had pud_special, we could avoid all these restrictions, @@ -1220,16 +1578,63 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; - track_pfn_insert(vma, &pgprot, pfn); + pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot); + ptl = pud_lock(vma->vm_mm, vmf->pud); insert_pfn_pud(vma, addr, vmf->pud, pfn, write); + spin_unlock(ptl); + return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); + +/** + * vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry + * @vmf: Structure describing the fault + * @folio: folio to insert + * @write: whether it's a write fault + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, + bool write) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address & PUD_MASK; + pud_t *pud = vmf->pud; + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER)) + return VM_FAULT_SIGBUS; + + ptl = pud_lock(mm, pud); + + /* + * If there is already an entry present we assume the folio is + * already mapped, hence no need to take another reference. We + * still call insert_pfn_pud() though in case the mapping needs + * upgrading to writeable. + */ + if (pud_none(*vmf->pud)) { + folio_get(folio); + folio_add_file_rmap_pud(folio, &folio->page, vma); + add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR); + } + insert_pfn_pud(vma, addr, vmf->pud, pfn_to_pfn_t(folio_pfn(folio)), + write); + spin_unlock(ptl); + + return VM_FAULT_NOPAGE; +} +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) +void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write) { pmd_t _pmd; @@ -1274,7 +1679,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); - ret = try_grab_page(page, flags); + ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); @@ -1292,6 +1697,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pgtable_t pgtable = NULL; int ret = -ENOMEM; + pmd = pmdp_get_lockless(src_pmd); + if (unlikely(pmd_present(pmd) && pmd_special(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; @@ -1344,11 +1767,11 @@ 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; } @@ -1357,13 +1780,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, src_folio = page_folio(src_page); folio_get(src_folio); - if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, src_vma))) { + if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, dst_vma, src_vma))) { /* Page maybe pinned: split and retry the fault on PTEs. */ folio_put(src_folio); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); - __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); + __split_huge_pmd(src_vma, src_pmd, addr, false); return -EAGAIN; } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); @@ -1373,7 +1796,9 @@ 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; @@ -1385,8 +1810,8 @@ 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; @@ -1398,49 +1823,6 @@ 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; - - 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) @@ -1459,20 +1841,14 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, 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. - */ - if (is_huge_zero_pud(pud)) { - /* No huge zero pud yet */ - } - - /* * TODO: once we support anonymous pages, use * folio_try_dup_anon_rmap_*() and split if duplicating fails. */ - pudp_set_wrprotect(src_mm, addr, src_pud); - pud = pud_mkold(pud_wrprotect(pud)); + if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) { + pudp_set_wrprotect(src_mm, addr, src_pud); + pud = pud_wrprotect(pud); + } + pud = pud_mkold(pud); set_pud_at(dst_mm, addr, dst_pud, pud); ret = 0; @@ -1510,6 +1886,38 @@ unlock: spin_unlock(vmf->ptl); } +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(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) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; @@ -1522,8 +1930,15 @@ 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); @@ -1593,7 +2008,7 @@ 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; } @@ -1610,7 +2025,7 @@ 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? */ @@ -1627,108 +2042,27 @@ 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); - - if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, 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 folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; int nid = NUMA_NO_NODE; - int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); - bool migrated = false, writable = false; + 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 @@ -1743,56 +2077,46 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) if (!folio) goto out_map; - /* See similar comment in do_numa_page for explanation */ - if (!writable) - flags |= TNF_NO_GROUP; - nid = folio_nid(folio); - /* - * For memory tiering mode, cpupid of slow memory page is used - * to record page access time. So use default value. - */ - if (node_is_toptier(nid)) - last_cpupid = folio_last_cpupid(folio); - target_nid = numa_migrate_prep(folio, vma, haddr, nid, &flags); - if (target_nid == NUMA_NO_NODE) { - folio_put(folio); + + target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable, + &last_cpupid); + if (target_nid == NUMA_NO_NODE) + goto out_map; + if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { + flags |= TNF_MIGRATE_FAIL; goto out_map; } - + /* The folio is isolated and isolation code holds a folio reference. */ spin_unlock(vmf->ptl); writable = false; - migrated = migrate_misplaced_folio(folio, vma, target_nid); - if (migrated) { + if (!migrate_misplaced_folio(folio, target_nid)) { flags |= TNF_MIGRATED; 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; - } - -out: - if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; + } - 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, 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; } /* @@ -1824,12 +2148,12 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, goto out; } - folio = pfn_folio(pmd_pfn(orig_pmd)); + folio = pmd_folio(orig_pmd); /* * If other processes are mapping this folio, we couldn't discard * the folio unless they all do MADV_FREE so let's skip the folio. */ - if (folio_estimated_sharers(folio) != 1) + if (folio_maybe_mapped_shared(folio)) goto out; if (!folio_trylock(folio)) @@ -1899,12 +2223,13 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, 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 folio *folio = NULL; @@ -1915,7 +2240,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, folio = page_folio(page); folio_remove_rmap_pmd(folio, page, vma); - VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); + WARN_ON_ONCE(folio_mapcount(folio) < 0); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { swp_entry_t entry; @@ -1935,6 +2260,14 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, zap_deposited_table(tlb->mm, pmd); 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); } spin_unlock(ptl); @@ -1970,6 +2303,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) return pmd; } +static pmd_t clear_uffd_wp_pmd(pmd_t pmd) +{ + if (pmd_present(pmd)) + pmd = pmd_clear_uffd_wp(pmd); + else if (is_swap_pmd(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); + + return pmd; +} + bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { @@ -2008,6 +2351,8 @@ 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); @@ -2094,7 +2439,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_protnone(*pmd)) goto unlock; - folio = page_folio(pmd_page(*pmd)); + folio = pmd_folio(*pmd); toptier = node_is_toptier(folio_nid(folio)); /* * Skip scanning top tier node if normal numa @@ -2104,8 +2449,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, toptier) goto unlock; - if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && - !toptier) + if (folio_use_access_time(folio)) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); } @@ -2158,6 +2502,53 @@ unlock: return ret; } +/* + * 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 @@ -2268,14 +2659,14 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm } folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + src_folio->index = linear_page_index(dst_vma, dst_addr); - _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); + _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 = mk_huge_pmd(src_page, dst_vma->vm_page_prot); + _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot); } set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); @@ -2337,19 +2728,33 @@ 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(vma, 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; } @@ -2357,6 +2762,10 @@ 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); @@ -2364,7 +2773,22 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, count_vm_event(THP_SPLIT_PUD); - pudp_huge_clear_flush(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, @@ -2386,6 +2810,11 @@ out: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); } +#else +void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ +} #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, @@ -2459,13 +2888,15 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, */ 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; entry = pmd_to_swp_entry(old_pmd); folio = pfn_swap_entry_folio(entry); + } else if (is_huge_zero_pmd(old_pmd)) { + return; } else { page = pmd_page(old_pmd); folio = page_folio(page); @@ -2493,32 +2924,11 @@ 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); - - pmd_migration = is_pmd_migration_entry(old_pmd); + pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; + old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); @@ -2529,6 +2939,30 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } 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)) { @@ -2646,8 +3080,17 @@ 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_devmap(*pmd) || + is_pmd_migration_entry(*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; @@ -2657,39 +3100,20 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, (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); 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) @@ -2701,13 +3125,13 @@ 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); @@ -2715,16 +3139,9 @@ 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) @@ -2750,7 +3167,82 @@ static void unmap_folio(struct folio *folio) try_to_unmap_flush(); } -static void remap_page(struct folio *folio, unsigned long nr) +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, int flags) { int i = 0; @@ -2758,7 +3250,7 @@ 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; @@ -2766,225 +3258,378 @@ 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(PageLRU(tail), head); + VM_BUG_ON_FOLIO(folio_test_lru(new_folio), folio); lockdep_assert_held(&lruvec->lru_lock); 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 folio *folio, int tail, - struct lruvec *lruvec, struct list_head *list, - unsigned int new_order) +/* Racy check whether the huge page can be split */ +bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { - struct page *head = &folio->page; - struct page *page_tail = head + tail; - /* - * 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 *)page_tail; + int extra_pins; - VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail); + /* 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; +} + +/* + * 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) +{ + long new_nr_pages = 1 << new_order; + long nr_pages = 1 << old_order; + long i; /* - * 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 &= ~PAGE_FLAGS_CHECK_AT_PREP; + new_folio->flags |= (folio->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_2 + (1L << PG_arch_2) | +#endif +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 + (1L << PG_arch_3) | #endif - (1L << PG_dirty) | - LRU_GEN_MASK | LRU_REFS_MASK)); + (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; + new_folio->mapping = folio->mapping; + new_folio->index = folio->index + i; - /* - * page->private should not be set in tail pages. Fix up and warn once - * if private is unexpectedly set. - */ - if (unlikely(page_tail->private)) { - VM_WARN_ON_ONCE_PAGE(true, page_tail); - page_tail->private = 0; - } - if (folio_test_swapcache(folio)) - new_folio->swap.val = folio->swap.val + tail; + /* + * page->private should not be set in tail pages. Fix up and warn once + * if private is unexpectedly set. + */ + if (unlikely(new_folio->private)) { + VM_WARN_ON_ONCE_PAGE(true, new_head); + new_folio->private = NULL; + } - /* Page flags must be visible before we make the page non-compound. */ - smp_wmb(); + if (folio_test_swapcache(folio)) + new_folio->swap.val = folio->swap.val + i; - /* - * Clear PageTail before unfreezing page refcount. - * - * After successful get_page_unless_zero() might follow put_page() - * which needs correct compound_head(). - */ - clear_compound_head(page_tail); - if (new_order) { - prep_compound_page(page_tail, new_order); - folio_prep_large_rmappable(new_folio); - } + /* Page flags must be visible before we make the page non-compound. */ + smp_wmb(); - /* Finally unfreeze refcount. Additional reference from page cache. */ - page_ref_unfreeze(page_tail, - 1 + ((!folio_test_anon(folio) || folio_test_swapcache(folio)) ? - folio_nr_pages(new_folio) : 0)); + /* + * 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); + 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)); + folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio)); + } - /* - * always add to the tail because some iterators expect new - * pages to show after the currently processed elements - e.g. - * migrate_pages - */ - lru_add_page_tail(head, page_tail, lruvec, list); + if (new_order) + folio_set_order(folio, new_order); + else + ClearPageCompound(&folio->page); } -static void __split_huge_page(struct page *page, struct list_head *list, - pgoff_t end, unsigned int new_order) +/* + * It splits an unmapped @folio to lower order smaller folios in two ways. + * @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. + * @lock_at: the folio containing @lock_at is left locked for caller. + * @list: the after split folios will be added to @list if it is not NULL, + * otherwise to LRU lists. + * @end: the end of the file @folio maps to. -1 if @folio is anonymous memory. + * @xas: xa_state pointing to folio->mapping->i_pages and locked by caller + * @mapping: @folio->mapping + * @uniform_split: 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 + * uniform_split is true. + * 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 @page's order becomes @new_order. This is done when + * uniform_split is false. + * + * The high level flow for these two methods are: + * 1. uniform split: a single __split_folio_to_order() is called to split the + * @folio into @new_order, then we traverse all the resulting folios one by + * one in PFN ascending order and perform stats, unfreeze, adding to list, + * and file mapping index operations. + * 2. non-uniform split: in general, folio_order - @new_order calls to + * __split_folio_to_order() are made in a for loop to split the @folio + * to one lower order at a time. The resulting small folios are processed + * like what is done during the traversal in 1, except the one containing + * @page, which is split in next for loop. + * + * After splitting, the caller's folio reference will be transferred to the + * folio containing @page. The other folios may be freed if they are not mapped. + * + * In terms of locking, after splitting, + * 1. uniform split leaves @page (or the folio contains it) locked; + * 2. buddy allocator like (non-uniform) split leaves @folio locked. + * + * + * For !uniform_split, when -ENOMEM is returned, the original folio might be + * split. The caller needs to check the input folio. + */ +static int __split_unmapped_folio(struct folio *folio, int new_order, + struct page *split_at, struct page *lock_at, + struct list_head *list, pgoff_t end, + struct xa_state *xas, struct address_space *mapping, + bool uniform_split) { - struct folio *folio = page_folio(page); - struct page *head = &folio->page; struct lruvec *lruvec; struct address_space *swap_cache = NULL; - unsigned long offset = 0; - int i, nr_dropped = 0; - unsigned int new_nr = 1 << new_order; + struct folio *origin_folio = folio; + struct folio *next_folio = folio_next(folio); + struct folio *new_folio; + struct folio *next; int order = folio_order(folio); - unsigned int nr = 1 << order; + int split_order; + int start_order = uniform_split ? new_order : order - 1; + int nr_dropped = 0; + int ret = 0; + bool stop_split = false; - /* complete memcg works before add pages to LRU */ - split_page_memcg(head, order, new_order); + if (folio_test_swapcache(folio)) { + VM_BUG_ON(mapping); + + /* a swapcache folio can only be uniformly split to order-0 */ + if (!uniform_split || new_order != 0) + return -EINVAL; - if (folio_test_anon(folio) && folio_test_swapcache(folio)) { - offset = swp_offset(folio->swap); swap_cache = swap_address_space(folio->swap); xa_lock(&swap_cache->i_pages); } + if (folio_test_anon(folio)) + mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); + /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ lruvec = folio_lruvec_lock(folio); - ClearPageHasHWPoisoned(head); - - for (i = nr - new_nr; i >= new_nr; i -= new_nr) { - __split_huge_page_tail(folio, i, lruvec, list, new_order); - /* 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(folio->mapping)) - nr_dropped++; - 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(&folio->mapping->i_pages, head[i].index, - head + i, 0); - } else if (swap_cache) { - __xa_store(&swap_cache->i_pages, offset + i, - head + i, 0); + folio_clear_has_hwpoisoned(folio); + + /* + * split to new_order one order at a time. For uniform split, + * folio is split to new_order directly. + */ + for (split_order = start_order; + split_order >= new_order && !stop_split; + split_order--) { + int old_order = folio_order(folio); + struct folio *release; + struct folio *end_folio = folio_next(folio); + + /* order-1 anonymous folio is not supported */ + if (folio_test_anon(folio) && split_order == 1) + continue; + if (uniform_split && split_order != new_order) + 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 (uniform_split) + 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)) { + ret = xas_error(xas); + stop_split = true; + goto after_split; + } + } } - } - if (!new_order) - ClearPageCompound(head); - else { - struct folio *new_folio = (struct folio *)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); - folio_set_order(new_folio, new_order); - } - unlock_page_lruvec(lruvec); - /* Caller disabled irqs, so they are still disabled here */ + __split_folio_to_order(folio, old_order, split_order); - split_page_owner(head, order, new_order); +after_split: + /* + * Iterate through after-split folios and perform related + * operations. But in buddy allocator like split, the folio + * containing the specified page is skipped until its order + * is new_order, since the folio will be worked on in next + * iteration. + */ + for (release = folio; release != end_folio; release = next) { + next = folio_next(release); + /* + * for buddy allocator like split, the folio containing + * page will be split next and should not be released, + * until the folio's order is new_order or stop_split + * is set to true by the above xas_split() failure. + */ + if (release == page_folio(split_at)) { + folio = release; + if (split_order != new_order && !stop_split) + continue; + } + if (folio_test_anon(release)) { + mod_mthp_stat(folio_order(release), + MTHP_STAT_NR_ANON, 1); + } - /* See comment in __split_huge_page_tail() */ - if (folio_test_anon(folio)) { - /* Additional pin to swap cache */ - if (folio_test_swapcache(folio)) { - folio_ref_add(folio, 1 + new_nr); - xa_unlock(&swap_cache->i_pages); - } else { - folio_ref_inc(folio); + /* + * origin_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. + */ + if (release == origin_folio) + continue; + + folio_ref_unfreeze(release, 1 + + ((mapping || swap_cache) ? + folio_nr_pages(release) : 0)); + + lru_add_split_folio(origin_folio, release, lruvec, + list); + + /* Some pages can be beyond EOF: drop them from cache */ + if (release->index >= end) { + if (shmem_mapping(mapping)) + nr_dropped += folio_nr_pages(release); + else if (folio_test_clear_dirty(release)) + folio_account_cleaned(release, + inode_to_wb(mapping->host)); + __filemap_remove_folio(release, NULL); + folio_put_refs(release, folio_nr_pages(release)); + } else if (mapping) { + __xa_store(&mapping->i_pages, + release->index, release, 0); + } else if (swap_cache) { + __xa_store(&swap_cache->i_pages, + swap_cache_index(release->swap), + release, 0); + } } - } else { - /* Additional pin to page cache */ - folio_ref_add(folio, 1 + new_nr); - xa_unlock(&folio->mapping->i_pages); } + + /* + * Unfreeze origin_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 origin_folio and its caller can + * see stale page cache entries. + */ + folio_ref_unfreeze(origin_folio, 1 + + ((mapping || swap_cache) ? folio_nr_pages(origin_folio) : 0)); + + unlock_page_lruvec(lruvec); + + if (swap_cache) + xa_unlock(&swap_cache->i_pages); + if (mapping) + xa_unlock(&mapping->i_pages); + + /* Caller disabled irqs, so they are still disabled here */ local_irq_enable(); if (nr_dropped) - shmem_uncharge(folio->mapping->host, nr_dropped); - remap_page(folio, nr); + shmem_uncharge(mapping->host, nr_dropped); - if (folio_test_swapcache(folio)) - split_swap_cluster(folio->swap); + remap_page(origin_folio, 1 << order, + folio_test_anon(origin_folio) ? + RMP_USE_SHARED_ZEROPAGE : 0); /* - * set page to its compound_head when split to non order-0 pages, so - * we can skip unlocking it below, since PG_locked is transferred to - * the compound_head of the page and the caller will unlock it. + * At this point, folio should contain the specified page. + * For uniform split, it is left for caller to unlock. + * For buddy allocator like split, the first after-split folio is left + * for caller to unlock. */ - if (new_order) - page = compound_head(page); - - for (i = 0; i < nr; i += new_nr) { - struct page *subpage = head + i; - struct folio *new_folio = page_folio(subpage); - if (subpage == page) + for (new_folio = origin_folio; new_folio != next_folio; new_folio = next) { + next = folio_next(new_folio); + if (new_folio == page_folio(lock_at)) continue; - folio_unlock(new_folio); + 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 @@ -2992,59 +3637,94 @@ static void __split_huge_page(struct page *page, struct list_head *list, * requires taking the lru_lock so we do the put_page * of the tail pages after the split is complete. */ - free_page_and_swap_cache(subpage); + free_folio_and_swap_cache(new_folio); } + return ret; } -/* Racy check whether the huge page can be split */ -bool can_split_folio(struct folio *folio, int *pextra_pins) +bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, + bool warns) { - int extra_pins; + 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"); + return new_order != 1; + } else if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && + !mapping_large_folio_support(folio->mapping)) { + /* + * No split if the file system does not support large folio. + * Note that we might still have THPs in such mappings due to + * CONFIG_READ_ONLY_THP_FOR_FS. 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; + } - /* 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; + /* Only swapping a whole PMD-mapped folio is supported */ + if (folio_test_swapcache(folio)) { + VM_WARN_ONCE(warns, + "Cannot split swapcache folio to non-0 order"); + return false; + } + + return true; +} + +/* See comments in non_uniform_split_supported() */ +bool uniform_split_supported(struct folio *folio, unsigned int new_order, + bool warns) +{ + if (folio_test_anon(folio)) { + VM_WARN_ONCE(warns && new_order == 1, + "Cannot split to order-1 folio"); + return new_order != 1; + } else if (new_order) { + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && + !mapping_large_folio_support(folio->mapping)) { + VM_WARN_ONCE(warns, + "Cannot split file folio to non-0 order"); + return false; + } + } + + if (new_order && folio_test_swapcache(folio)) { + VM_WARN_ONCE(warns, + "Cannot split swapcache folio to non-0 order"); + return false; + } + + return true; } /* - * This function splits huge page into pages in @new_order. @page can point to - * any subpage of huge page to split. Split doesn't change the position of - * @page. + * __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 + * @uniform_split: perform uniform split or not (non-uniform split) * - * NOTE: order-1 anonymous folio is not supported because _deferred_list, - * which is used by partially mapped folios, is stored in subpage 2 and an - * order-1 folio only has subpage 0 and 1. File-backed order-1 folios are OK, - * since they do not use _deferred_list. - * - * 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. + * 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(). * - * Pages in new_order will inherit mapping, flags, and so on from the hugepage. - * - * GUP pin and PG_locked transferred to @page or the compound page @page belongs - * to. Rest subpages can be freed if they are not mapped. - * - * 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_to_order(struct page *page, struct list_head *list, - unsigned int new_order) +static int __folio_split(struct folio *folio, unsigned int new_order, + struct page *split_at, struct page *lock_at, + struct list_head *list, bool uniform_split) { - struct folio *folio = page_folio(page); struct deferred_split *ds_queue = get_deferred_split_queue(folio); - /* reset xarray order to new order after split */ - XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order); - struct anon_vma *anon_vma = NULL; + XA_STATE(xas, &folio->mapping->i_pages, folio->index); + bool is_anon = folio_test_anon(folio); struct address_space *mapping = NULL; + struct anon_vma *anon_vma = NULL; + int order = folio_order(folio); int extra_pins, ret; pgoff_t end; bool is_hzp; @@ -3052,35 +3732,20 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); - if (new_order >= folio_order(folio)) + if (folio != page_folio(split_at) || folio != page_folio(lock_at)) return -EINVAL; - /* Cannot split anonymous THP to order-1 */ - if (new_order == 1 && folio_test_anon(folio)) { - VM_WARN_ONCE(1, "Cannot split to order-1 folio"); + if (new_order >= folio_order(folio)) return -EINVAL; - } - if (new_order) { - /* Only swapping a whole PMD-mapped folio is supported */ - if (folio_test_swapcache(folio)) - return -EINVAL; - /* Split shmem folio to non-zero order not supported */ - if (shmem_mapping(folio->mapping)) { - VM_WARN_ONCE(1, - "Cannot split shmem folio to non-0 order"); - return -EINVAL; - } - /* No split if the file system does not support large folio */ - if (!mapping_large_folio_support(folio->mapping)) { - VM_WARN_ONCE(1, - "Cannot split file folio to non-0 order"); - return -EINVAL; - } - } + if (uniform_split && !uniform_split_supported(folio, new_order, true)) + return -EINVAL; + if (!uniform_split && + !non_uniform_split_supported(folio, new_order, true)) + return -EINVAL; - is_hzp = is_huge_zero_page(&folio->page); + is_hzp = is_huge_zero_folio(folio); if (is_hzp) { pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); return -EBUSY; @@ -3089,7 +3754,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, 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 @@ -3107,16 +3772,30 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, mapping = NULL; anon_vma_lock_write(anon_vma); } else { + unsigned int min_order; gfp_t gfp; mapping = folio->mapping; /* Truncated ? */ + /* + * TODO: add support for large shmem folio in swap cache. + * When shmem is in swap cache, mapping is NULL and + * folio_test_swapcache() is true. + */ if (!mapping) { ret = -EBUSY; goto out; } + min_order = mapping_min_folio_order(folio->mapping); + if (new_order < min_order) { + VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u", + min_order); + ret = -EINVAL; + goto out; + } + gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); @@ -3125,21 +3804,24 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, goto out; } - xas_split_alloc(&xas, folio, folio_order(folio), gfp); - if (xas_error(&xas)) { - ret = xas_error(&xas); - goto out; + if (uniform_split) { + xas_set_order(&xas, folio->index, new_order); + xas_split_alloc(&xas, folio, folio_order(folio), 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)) @@ -3150,7 +3832,7 @@ int split_huge_page_to_list_to_order(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; } @@ -3176,6 +3858,11 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (folio_order(folio) > 1 && !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; + if (folio_test_partially_mapped(folio)) { + folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } /* * Reinitialize page_deferred_list after removing the * page from the split_queue, otherwise a subsequent @@ -3188,7 +3875,6 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (mapping) { int nr = folio_nr_pages(folio); - xas_split(&xas, folio, folio_order(folio)); if (folio_test_pmd_mappable(folio) && new_order < HPAGE_PMD_ORDER) { if (folio_test_swapbacked(folio)) { @@ -3202,15 +3888,16 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, } } - __split_huge_page(page, list, end, new_order); - ret = 0; + ret = __split_unmapped_folio(folio, new_order, + split_at, lock_at, list, end, &xas, mapping, + uniform_split); } else { spin_unlock(&ds_queue->split_queue_lock); fail: if (mapping) xas_unlock(&xas); local_irq_enable(); - remap_page(folio, folio_nr_pages(folio)); + remap_page(folio, folio_nr_pages(folio), 0); ret = -EAGAIN; } @@ -3223,36 +3910,161 @@ out_unlock: i_mmap_unlock_read(mapping); out: xas_destroy(&xas); - count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + if (order == HPAGE_PMD_ORDER) + count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + count_mthp_stat(order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED); return ret; } -void folio_undo_large_rmappable(struct folio *folio) +/* + * 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 folio *folio = page_folio(page); + + return __folio_split(folio, new_order, &folio->page, page, list, true); +} + +/* + * 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 + * + * return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be + * split but not to @new_order, the caller needs to check) + * + * 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. + */ +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, + false); +} + +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) +{ + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + return split_huge_page_to_list_to_order(&folio->page, list, ret); +} + +/* + * __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; - if (folio_order(folio) <= 1) - return; - - /* - * At this point, there is no one trying to add the folio to - * deferred_list. If folio is not in deferred_list, it's safe - * to check without acquiring the split_queue_lock. - */ - if (data_race(list_empty(&folio->_deferred_list))) - return; + WARN_ON_ONCE(folio_ref_count(folio)); + WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio)); ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; + if (folio_test_partially_mapped(folio)) { + folio_clear_partially_mapped(folio); + mod_mthp_stat(folio_order(folio), + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); + } list_del_init(&folio->_deferred_list); + unqueued = true; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + return unqueued; /* useful for debug warnings */ } -void deferred_split_folio(struct folio *folio) +/* 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(folio); #ifdef CONFIG_MEMCG @@ -3267,25 +4079,34 @@ void deferred_split_folio(struct folio *folio) 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 folio, it is - * unnecessary to handle it again in shrinker. - * - * Check the swapcache flag to determine if the folio is being - * handled by page reclaim since THP swap would add the folio 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 (folio_test_swapcache(folio)) return; - if (!list_empty(&folio->_deferred_list)) - return; - spin_lock_irqsave(&ds_queue->split_queue_lock, 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)) { - count_vm_event(THP_DEFERRED_SPLIT_PAGE); list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG @@ -3310,6 +4131,39 @@ 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; + void *kaddr; + int i; + + if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1) + return false; + + for (i = 0; i < folio_nr_pages(folio); i++) { + kaddr = kmap_local_folio(folio, i * PAGE_SIZE); + if (!memchr_inv(kaddr, 0, PAGE_SIZE)) { + num_zero_pages++; + if (num_zero_pages > khugepaged_max_ptes_none) { + kunmap_local(kaddr); + return true; + } + } else { + /* + * Another path for early exit once the number + * of non-zero filled pages exceeds threshold. + */ + num_filled_pages++; + if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) { + kunmap_local(kaddr); + return false; + } + } + kunmap_local(kaddr); + } + return false; +} + static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { @@ -3317,8 +4171,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list); - struct folio *folio, *next; - int split = 0; + struct folio *folio, *next, *prev = NULL; + int split = 0, removed = 0; #ifdef CONFIG_MEMCG if (sc->memcg) @@ -3333,6 +4187,11 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, list_move(&folio->_deferred_list, &list); } else { /* We lost race with folio_put() */ + 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); ds_queue->split_queue_len--; } @@ -3342,20 +4201,57 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_entry_safe(folio, next, &list, _deferred_list) { + bool did_split = false; + bool underused = false; + + if (!folio_test_partially_mapped(folio)) { + 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_folio(folio)) + if (!split_folio(folio)) { + did_split = true; + if (underused) + count_vm_event(THP_UNDERUSED_SPLIT_PAGE); split++; + } folio_unlock(folio); next: - folio_put(folio); + /* + * split_folio() removes folio from list on success. + * 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. + */ + if (did_split) { + ; /* folio already removed from list */ + } else if (!folio_test_partially_mapped(folio)) { + list_del_init(&folio->_deferred_list); + removed++; + } else { + /* + * That unlocked list_del_init() above would be unsafe, + * unless its folio is separated from any earlier folios + * left on the list (which may be concurrently unqueued) + * by one safe folio with refcount still raised. + */ + swap(folio, prev); + } + if (folio) + folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); + ds_queue->split_queue_len -= removed; spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + if (prev) + folio_put(prev); + /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. @@ -3423,7 +4319,8 @@ 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 int new_order) + unsigned long vaddr_end, unsigned int new_order, + long in_folio_offset) { int ret = 0; struct task_struct *task; @@ -3434,16 +4331,11 @@ 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); @@ -3464,8 +4356,10 @@ 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; @@ -3476,17 +4370,20 @@ 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; - folio = page_folio(page); if (!is_transparent_hugepage(folio)) goto next; - if (new_order >= folio_order(folio)) + 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++; @@ -3496,18 +4393,37 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, * can be split or not. So skip the check here. */ if (!folio_test_private(folio) && - !can_split_folio(folio, NULL)) + !can_split_folio(folio, 0, NULL)) goto next; if (!folio_trylock(folio)) goto next; + folio_get(folio); + folio_walk_end(&fw, vma); - if (!split_folio_to_order(folio, new_order)) - 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: folio_unlock(folio); -next: folio_put(folio); + + cond_resched(); + continue; +next: + folio_walk_end(&fw, vma); cond_resched(); } mmap_read_unlock(mm); @@ -3520,7 +4436,8 @@ out: } static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, - pgoff_t off_end, unsigned int new_order) + pgoff_t off_end, unsigned int new_order, + long in_folio_offset) { struct filename *file; struct file *candidate; @@ -3529,6 +4446,8 @@ 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)) @@ -3542,6 +4461,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, file_path, off_start, off_end); 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); @@ -3556,15 +4477,26 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, total++; nr_pages = folio_nr_pages(folio); - if (new_order >= folio_order(folio)) + if (target_order >= folio_order(folio)) goto next; if (!folio_trylock(folio)) goto next; - if (!split_folio_to_order(folio, new_order)) - 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); @@ -3595,6 +4527,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, 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) @@ -3610,42 +4543,46 @@ 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,%d", &off_start, &off_end, &new_order); - if (ret != 2 && ret != 3) { + ret = sscanf(tok_buf, "0x%lx,0x%lx,%d,%ld", &off_start, &off_end, + &new_order, &in_folio_offset); + if (ret != 2 && ret != 3 && ret != 4) { ret = -EINVAL; goto out; } - ret = split_huge_pages_in_file(file_path, off_start, off_end, new_order); + 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,%d", &pid, &vaddr_start, &vaddr_end, &new_order); + ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d,%ld", &pid, &vaddr_start, + &vaddr_end, &new_order, &in_folio_offset); if (ret == 1 && pid == 1) { split_huge_pages_all(); ret = strlen(input_buf); goto out; - } else if (ret != 3 && ret != 4) { + } else if (ret != 3 && ret != 4 && ret != 5) { ret = -EINVAL; goto out; } - ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order); + ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order, + in_folio_offset); if (!ret) ret = strlen(input_buf); out: @@ -3657,7 +4594,6 @@ 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) @@ -3735,7 +4671,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) entry = pmd_to_swp_entry(*pvmw->pmd); folio_get(folio); - pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); + 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)) |