diff options
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r-- | mm/huge_memory.c | 1909 |
1 files changed, 315 insertions, 1594 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 343a2b7..3647334 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -18,7 +18,6 @@ #include <linux/mm_inline.h> #include <linux/swapops.h> #include <linux/dax.h> -#include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/pfn_t.h> @@ -30,39 +29,12 @@ #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> +#include <linux/shmem_fs.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" -enum scan_result { - SCAN_FAIL, - SCAN_SUCCEED, - SCAN_PMD_NULL, - SCAN_EXCEED_NONE_PTE, - SCAN_PTE_NON_PRESENT, - SCAN_PAGE_RO, - SCAN_NO_REFERENCED_PAGE, - SCAN_PAGE_NULL, - SCAN_SCAN_ABORT, - SCAN_PAGE_COUNT, - SCAN_PAGE_LRU, - SCAN_PAGE_LOCK, - SCAN_PAGE_ANON, - SCAN_PAGE_COMPOUND, - SCAN_ANY_PROCESS, - SCAN_VMA_NULL, - SCAN_VMA_CHECK, - SCAN_ADDRESS_RANGE, - SCAN_SWAP_CACHE_PAGE, - SCAN_DEL_PAGE_LRU, - SCAN_ALLOC_HUGE_PAGE_FAIL, - SCAN_CGROUP_CHARGE_FAIL -}; - -#define CREATE_TRACE_POINTS -#include <trace/events/huge_memory.h> - /* * By default transparent hugepage support is disabled in order that avoid * to risk increase the memory footprint of applications without a guaranteed @@ -82,127 +54,8 @@ unsigned long transparent_hugepage_flags __read_mostly = (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); -/* default scan 8*512 pte (or vmas) every 30 second */ -static unsigned int khugepaged_pages_to_scan __read_mostly; -static unsigned int khugepaged_pages_collapsed; -static unsigned int khugepaged_full_scans; -static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; -/* during fragmentation poll the hugepage allocator once every minute */ -static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; -static unsigned long khugepaged_sleep_expire; -static struct task_struct *khugepaged_thread __read_mostly; -static DEFINE_MUTEX(khugepaged_mutex); -static DEFINE_SPINLOCK(khugepaged_mm_lock); -static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); -/* - * default collapse hugepages if there is at least one pte mapped like - * it would have happened if the vma was large enough during page - * fault. - */ -static unsigned int khugepaged_max_ptes_none __read_mostly; - -static int khugepaged(void *none); -static int khugepaged_slab_init(void); -static void khugepaged_slab_exit(void); - -#define MM_SLOTS_HASH_BITS 10 -static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); - -static struct kmem_cache *mm_slot_cache __read_mostly; - -/** - * struct mm_slot - hash lookup from mm to mm_slot - * @hash: hash collision list - * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head - * @mm: the mm that this information is valid for - */ -struct mm_slot { - struct hlist_node hash; - struct list_head mm_node; - struct mm_struct *mm; -}; - -/** - * struct khugepaged_scan - cursor for scanning - * @mm_head: the head of the mm list to scan - * @mm_slot: the current mm_slot we are scanning - * @address: the next address inside that to be scanned - * - * There is only the one khugepaged_scan instance of this cursor structure. - */ -struct khugepaged_scan { - struct list_head mm_head; - struct mm_slot *mm_slot; - unsigned long address; -}; -static struct khugepaged_scan khugepaged_scan = { - .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), -}; - static struct shrinker deferred_split_shrinker; -static void set_recommended_min_free_kbytes(void) -{ - struct zone *zone; - int nr_zones = 0; - unsigned long recommended_min; - - for_each_populated_zone(zone) - nr_zones++; - - /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ - recommended_min = pageblock_nr_pages * nr_zones * 2; - - /* - * Make sure that on average at least two pageblocks are almost free - * of another type, one for a migratetype to fall back to and a - * second to avoid subsequent fallbacks of other types There are 3 - * MIGRATE_TYPES we care about. - */ - recommended_min += pageblock_nr_pages * nr_zones * - MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; - - /* don't ever allow to reserve more than 5% of the lowmem */ - recommended_min = min(recommended_min, - (unsigned long) nr_free_buffer_pages() / 20); - recommended_min <<= (PAGE_SHIFT-10); - - if (recommended_min > min_free_kbytes) { - if (user_min_free_kbytes >= 0) - pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", - min_free_kbytes, recommended_min); - - min_free_kbytes = recommended_min; - } - setup_per_zone_wmarks(); -} - -static int start_stop_khugepaged(void) -{ - int err = 0; - if (khugepaged_enabled()) { - if (!khugepaged_thread) - khugepaged_thread = kthread_run(khugepaged, NULL, - "khugepaged"); - if (IS_ERR(khugepaged_thread)) { - pr_err("khugepaged: kthread_run(khugepaged) failed\n"); - err = PTR_ERR(khugepaged_thread); - khugepaged_thread = NULL; - goto fail; - } - - if (!list_empty(&khugepaged_scan.mm_head)) - wake_up_interruptible(&khugepaged_wait); - - set_recommended_min_free_kbytes(); - } else if (khugepaged_thread) { - kthread_stop(khugepaged_thread); - khugepaged_thread = NULL; - } -fail: - return err; -} - static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; @@ -328,12 +181,7 @@ static ssize_t enabled_store(struct kobject *kobj, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG); if (ret > 0) { - int err; - - mutex_lock(&khugepaged_mutex); - err = start_stop_khugepaged(); - mutex_unlock(&khugepaged_mutex); - + int err = start_stop_khugepaged(); if (err) ret = err; } @@ -343,7 +191,7 @@ static ssize_t enabled_store(struct kobject *kobj, static struct kobj_attribute enabled_attr = __ATTR(enabled, 0644, enabled_show, enabled_store); -static ssize_t single_flag_show(struct kobject *kobj, +ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { @@ -351,7 +199,7 @@ static ssize_t single_flag_show(struct kobject *kobj, !!test_bit(flag, &transparent_hugepage_flags)); } -static ssize_t single_flag_store(struct kobject *kobj, +ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) @@ -406,13 +254,13 @@ static struct kobj_attribute defrag_attr = static ssize_t use_zero_page_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return single_flag_show(kobj, attr, buf, + return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static ssize_t use_zero_page_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - return single_flag_store(kobj, attr, buf, count, + return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static struct kobj_attribute use_zero_page_attr = @@ -421,14 +269,14 @@ static struct kobj_attribute use_zero_page_attr = static ssize_t debug_cow_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return single_flag_show(kobj, attr, buf, + return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); } static ssize_t debug_cow_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - return single_flag_store(kobj, attr, buf, count, + return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG); } static struct kobj_attribute debug_cow_attr = @@ -439,6 +287,9 @@ static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, &use_zero_page_attr.attr, +#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE) + &shmem_enabled_attr.attr, +#endif #ifdef CONFIG_DEBUG_VM &debug_cow_attr.attr, #endif @@ -449,171 +300,6 @@ static struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; -static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs); -} - -static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long msecs; - int err; - - err = kstrtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) - return -EINVAL; - - khugepaged_scan_sleep_millisecs = msecs; - khugepaged_sleep_expire = 0; - wake_up_interruptible(&khugepaged_wait); - - return count; -} -static struct kobj_attribute scan_sleep_millisecs_attr = - __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, - scan_sleep_millisecs_store); - -static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs); -} - -static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long msecs; - int err; - - err = kstrtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) - return -EINVAL; - - khugepaged_alloc_sleep_millisecs = msecs; - khugepaged_sleep_expire = 0; - wake_up_interruptible(&khugepaged_wait); - - return count; -} -static struct kobj_attribute alloc_sleep_millisecs_attr = - __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, - alloc_sleep_millisecs_store); - -static ssize_t pages_to_scan_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_pages_to_scan); -} -static ssize_t pages_to_scan_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err; - unsigned long pages; - - err = kstrtoul(buf, 10, &pages); - if (err || !pages || pages > UINT_MAX) - return -EINVAL; - - khugepaged_pages_to_scan = pages; - - return count; -} -static struct kobj_attribute pages_to_scan_attr = - __ATTR(pages_to_scan, 0644, pages_to_scan_show, - pages_to_scan_store); - -static ssize_t pages_collapsed_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_pages_collapsed); -} -static struct kobj_attribute pages_collapsed_attr = - __ATTR_RO(pages_collapsed); - -static ssize_t full_scans_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_full_scans); -} -static struct kobj_attribute full_scans_attr = - __ATTR_RO(full_scans); - -static ssize_t khugepaged_defrag_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return single_flag_show(kobj, attr, buf, - TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); -} -static ssize_t khugepaged_defrag_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - return single_flag_store(kobj, attr, buf, count, - TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); -} -static struct kobj_attribute khugepaged_defrag_attr = - __ATTR(defrag, 0644, khugepaged_defrag_show, - khugepaged_defrag_store); - -/* - * max_ptes_none controls if khugepaged should collapse hugepages over - * any unmapped ptes in turn potentially increasing the memory - * footprint of the vmas. When max_ptes_none is 0 khugepaged will not - * reduce the available free memory in the system as it - * runs. Increasing max_ptes_none will instead potentially reduce the - * free memory in the system during the khugepaged scan. - */ -static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", khugepaged_max_ptes_none); -} -static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - int err; - unsigned long max_ptes_none; - - err = kstrtoul(buf, 10, &max_ptes_none); - if (err || max_ptes_none > HPAGE_PMD_NR-1) - return -EINVAL; - - khugepaged_max_ptes_none = max_ptes_none; - - return count; -} -static struct kobj_attribute khugepaged_max_ptes_none_attr = - __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, - khugepaged_max_ptes_none_store); - -static struct attribute *khugepaged_attr[] = { - &khugepaged_defrag_attr.attr, - &khugepaged_max_ptes_none_attr.attr, - &pages_to_scan_attr.attr, - &pages_collapsed_attr.attr, - &full_scans_attr.attr, - &scan_sleep_millisecs_attr.attr, - &alloc_sleep_millisecs_attr.attr, - NULL, -}; - -static struct attribute_group khugepaged_attr_group = { - .attrs = khugepaged_attr, - .name = "khugepaged", -}; - static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; @@ -672,8 +358,6 @@ static int __init hugepage_init(void) return -EINVAL; } - khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; - khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; /* * hugepages can't be allocated by the buddy allocator */ @@ -688,7 +372,7 @@ static int __init hugepage_init(void) if (err) goto err_sysfs; - err = khugepaged_slab_init(); + err = khugepaged_init(); if (err) goto err_slab; @@ -719,7 +403,7 @@ err_khugepaged: err_split_shrinker: unregister_shrinker(&huge_zero_page_shrinker); err_hzp_shrinker: - khugepaged_slab_exit(); + khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); err_sysfs: @@ -765,11 +449,6 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) return pmd; } -static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) -{ - return pmd_mkhuge(mk_pmd(page, prot)); -} - static inline struct list_head *page_deferred_list(struct page *page) { /* @@ -790,26 +469,23 @@ void prep_transhuge_page(struct page *page) set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); } -static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - struct page *page, gfp_t gfp, - unsigned int flags) +static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page, + gfp_t gfp) { + struct vm_area_struct *vma = fe->vma; struct mem_cgroup *memcg; pgtable_t pgtable; - spinlock_t *ptl; - unsigned long haddr = address & HPAGE_PMD_MASK; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - pgtable = pte_alloc_one(mm, haddr); + pgtable = pte_alloc_one(vma->vm_mm, haddr); if (unlikely(!pgtable)) { mem_cgroup_cancel_charge(page, memcg, true); put_page(page); @@ -824,12 +500,12 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, */ __SetPageUptodate(page); - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_none(*pmd))) { - spin_unlock(ptl); + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_none(*fe->pmd))) { + spin_unlock(fe->ptl); mem_cgroup_cancel_charge(page, memcg, true); put_page(page); - pte_free(mm, pgtable); + pte_free(vma->vm_mm, pgtable); } else { pmd_t entry; @@ -837,12 +513,11 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, if (userfaultfd_missing(vma)) { int ret; - spin_unlock(ptl); + spin_unlock(fe->ptl); mem_cgroup_cancel_charge(page, memcg, true); put_page(page); - pte_free(mm, pgtable); - ret = handle_userfault(vma, address, flags, - VM_UFFD_MISSING); + pte_free(vma->vm_mm, pgtable); + ret = handle_userfault(fe, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } @@ -852,11 +527,11 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, page_add_new_anon_rmap(page, vma, haddr, true); mem_cgroup_commit_charge(page, memcg, false, true); lru_cache_add_active_or_unevictable(page, vma); - pgtable_trans_huge_deposit(mm, pmd, pgtable); - set_pmd_at(mm, haddr, pmd, entry); - add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); - atomic_long_inc(&mm->nr_ptes); - spin_unlock(ptl); + pgtable_trans_huge_deposit(vma->vm_mm, fe->pmd, pgtable); + set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&vma->vm_mm->nr_ptes); + spin_unlock(fe->ptl); count_vm_event(THP_FAULT_ALLOC); } @@ -883,12 +558,6 @@ static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) return GFP_TRANSHUGE | reclaim_flags; } -/* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ -static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) -{ - return GFP_TRANSHUGE | (khugepaged_defrag() ? __GFP_DIRECT_RECLAIM : 0); -} - /* Caller must hold page table lock. */ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, @@ -906,13 +575,12 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, return true; } -int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - unsigned int flags) +int do_huge_pmd_anonymous_page(struct fault_env *fe) { + struct vm_area_struct *vma = fe->vma; gfp_t gfp; struct page *page; - unsigned long haddr = address & HPAGE_PMD_MASK; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return VM_FAULT_FALLBACK; @@ -920,42 +588,40 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; if (unlikely(khugepaged_enter(vma, vma->vm_flags))) return VM_FAULT_OOM; - if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm) && + if (!(fe->flags & FAULT_FLAG_WRITE) && + !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { - spinlock_t *ptl; pgtable_t pgtable; struct page *zero_page; bool set; int ret; - pgtable = pte_alloc_one(mm, haddr); + pgtable = pte_alloc_one(vma->vm_mm, haddr); if (unlikely(!pgtable)) return VM_FAULT_OOM; zero_page = get_huge_zero_page(); if (unlikely(!zero_page)) { - pte_free(mm, pgtable); + pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - ptl = pmd_lock(mm, pmd); + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); ret = 0; set = false; - if (pmd_none(*pmd)) { + if (pmd_none(*fe->pmd)) { if (userfaultfd_missing(vma)) { - spin_unlock(ptl); - ret = handle_userfault(vma, address, flags, - VM_UFFD_MISSING); + spin_unlock(fe->ptl); + ret = handle_userfault(fe, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { - set_huge_zero_page(pgtable, mm, vma, - haddr, pmd, - zero_page); - spin_unlock(ptl); + set_huge_zero_page(pgtable, vma->vm_mm, vma, + haddr, fe->pmd, zero_page); + spin_unlock(fe->ptl); set = true; } } else - spin_unlock(ptl); + spin_unlock(fe->ptl); if (!set) { - pte_free(mm, pgtable); + pte_free(vma->vm_mm, pgtable); put_huge_zero_page(); } return ret; @@ -967,8 +633,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_FALLBACK; } prep_transhuge_page(page); - return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp, - flags); + return __do_huge_pmd_anonymous_page(fe, page, gfp); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1080,14 +745,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct page *src_page; pmd_t pmd; pgtable_t pgtable = NULL; - int ret; + int ret = -ENOMEM; - if (!vma_is_dax(vma)) { - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; - } + /* Skip if can be re-fill on fault */ + if (!vma_is_anonymous(vma)) + return 0; + + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1095,7 +761,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) { + if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } @@ -1118,16 +784,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (!vma_is_dax(vma)) { - /* thp accounting separate from pmd_devmap accounting */ - src_page = pmd_page(pmd); - VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - get_page(src_page); - page_dup_rmap(src_page, true); - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); - atomic_long_inc(&dst_mm->nr_ptes); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - } + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&dst_mm->nr_ptes); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); @@ -1141,38 +804,31 @@ out: return ret; } -void huge_pmd_set_accessed(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmd, pmd_t orig_pmd, - int dirty) +void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd) { - spinlock_t *ptl; pmd_t entry; unsigned long haddr; - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, orig_pmd))) + fe->ptl = pmd_lock(fe->vma->vm_mm, fe->pmd); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); - haddr = address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty)) - update_mmu_cache_pmd(vma, address, pmd); + haddr = fe->address & HPAGE_PMD_MASK; + if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry, + fe->flags & FAULT_FLAG_WRITE)) + update_mmu_cache_pmd(fe->vma, fe->address, fe->pmd); unlock: - spin_unlock(ptl); + spin_unlock(fe->ptl); } -static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmd, pmd_t orig_pmd, - struct page *page, - unsigned long haddr) +static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd, + struct page *page) { + struct vm_area_struct *vma = fe->vma; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; struct mem_cgroup *memcg; - spinlock_t *ptl; pgtable_t pgtable; pmd_t _pmd; int ret = 0, i; @@ -1189,11 +845,11 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, for (i = 0; i < HPAGE_PMD_NR; i++) { pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE | - __GFP_OTHER_NODE, - vma, address, page_to_nid(page)); + __GFP_OTHER_NODE, vma, + fe->address, page_to_nid(page)); if (unlikely(!pages[i] || - mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL, - &memcg, false))) { + mem_cgroup_try_charge(pages[i], vma->vm_mm, + GFP_KERNEL, &memcg, false))) { if (pages[i]) put_page(pages[i]); while (--i >= 0) { @@ -1219,41 +875,41 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end); - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, orig_pmd))) + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) goto out_free_pages; VM_BUG_ON_PAGE(!PageHead(page), page); - pmdp_huge_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); + pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, fe->pmd); + pmd_populate(vma->vm_mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; + pte_t entry; entry = mk_pte(pages[i], vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - page_add_new_anon_rmap(pages[i], vma, haddr, false); + page_add_new_anon_rmap(pages[i], fe->vma, haddr, false); mem_cgroup_commit_charge(pages[i], memcg, false, false); lru_cache_add_active_or_unevictable(pages[i], vma); - pte = pte_offset_map(&_pmd, haddr); - VM_BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); - pte_unmap(pte); + fe->pte = pte_offset_map(&_pmd, haddr); + VM_BUG_ON(!pte_none(*fe->pte)); + set_pte_at(vma->vm_mm, haddr, fe->pte, entry); + pte_unmap(fe->pte); } kfree(pages); smp_wmb(); /* make pte visible before pmd */ - pmd_populate(mm, pmd, pgtable); + pmd_populate(vma->vm_mm, fe->pmd, pgtable); page_remove_rmap(page, true); - spin_unlock(ptl); + spin_unlock(fe->ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); ret |= VM_FAULT_WRITE; put_page(page); @@ -1262,8 +918,8 @@ out: return ret; out_free_pages: - spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + spin_unlock(fe->ptl); + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); for (i = 0; i < HPAGE_PMD_NR; i++) { memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); @@ -1274,25 +930,23 @@ out_free_pages: goto out; } -int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, pmd_t orig_pmd) +int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd) { - spinlock_t *ptl; - int ret = 0; + struct vm_area_struct *vma = fe->vma; struct page *page = NULL, *new_page; struct mem_cgroup *memcg; - unsigned long haddr; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ gfp_t huge_gfp; /* for allocation and charge */ + int ret = 0; - ptl = pmd_lockptr(mm, pmd); + fe->ptl = pmd_lockptr(vma->vm_mm, fe->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); - haddr = address & HPAGE_PMD_MASK; if (is_huge_zero_pmd(orig_pmd)) goto alloc; - spin_lock(ptl); - if (unlikely(!pmd_same(*pmd, orig_pmd))) + spin_lock(fe->ptl); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) goto out_unlock; page = pmd_page(orig_pmd); @@ -1305,13 +959,13 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - if (pmdp_set_access_flags(vma, haddr, pmd, entry, 1)) - update_mmu_cache_pmd(vma, address, pmd); + if (pmdp_set_access_flags(vma, haddr, fe->pmd, entry, 1)) + update_mmu_cache_pmd(vma, fe->address, fe->pmd); ret |= VM_FAULT_WRITE; goto out_unlock; } get_page(page); - spin_unlock(ptl); + spin_unlock(fe->ptl); alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { @@ -1324,13 +978,12 @@ alloc: prep_transhuge_page(new_page); } else { if (!page) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, fe->pmd, fe->address); ret |= VM_FAULT_FALLBACK; } else { - ret = do_huge_pmd_wp_page_fallback(mm, vma, address, - pmd, orig_pmd, page, haddr); + ret = do_huge_pmd_wp_page_fallback(fe, orig_pmd, page); if (ret & VM_FAULT_OOM) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, fe->pmd, fe->address); ret |= VM_FAULT_FALLBACK; } put_page(page); @@ -1339,14 +992,12 @@ alloc: goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg, - true))) { + if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm, + huge_gfp, &memcg, true))) { put_page(new_page); - if (page) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, fe->pmd, fe->address); + if (page) put_page(page); - } else - split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); goto out; @@ -1362,13 +1013,13 @@ alloc: mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end); - spin_lock(ptl); + spin_lock(fe->ptl); if (page) put_page(page); - if (unlikely(!pmd_same(*pmd, orig_pmd))) { - spin_unlock(ptl); + if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) { + spin_unlock(fe->ptl); mem_cgroup_cancel_charge(new_page, memcg, true); put_page(new_page); goto out_mn; @@ -1376,14 +1027,14 @@ alloc: pmd_t entry; entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - pmdp_huge_clear_flush_notify(vma, haddr, pmd); + pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd); page_add_new_anon_rmap(new_page, vma, haddr, true); mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_active_or_unevictable(new_page, vma); - set_pmd_at(mm, haddr, pmd, entry); - update_mmu_cache_pmd(vma, address, pmd); + set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry); + update_mmu_cache_pmd(vma, fe->address, fe->pmd); if (!page) { - add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); put_huge_zero_page(); } else { VM_BUG_ON_PAGE(!PageHead(page), page); @@ -1392,13 +1043,13 @@ alloc: } ret |= VM_FAULT_WRITE; } - spin_unlock(ptl); + spin_unlock(fe->ptl); out_mn: - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); out: return ret; out_unlock: - spin_unlock(ptl); + spin_unlock(fe->ptl); return ret; } @@ -1432,6 +1083,8 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, * We don't mlock() pte-mapped THPs. This way we can avoid * leaking mlocked pages into non-VM_LOCKED VMAs. * + * For anon THP: + * * In most cases the pmd is the only mapping of the page as we * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for * writable private mappings in populate_vma_page_range(). @@ -1439,15 +1092,26 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, * The only scenario when we have the page shared here is if we * mlocking read-only mapping shared over fork(). We skip * mlocking such pages. + * + * For file THP: + * + * We can expect PageDoubleMap() to be stable under page lock: + * for file pages we set it in page_add_file_rmap(), which + * requires page to be locked. */ - if (compound_mapcount(page) == 1 && !PageDoubleMap(page) && - page->mapping && trylock_page(page)) { - lru_add_drain(); - if (page->mapping) - mlock_vma_page(page); - unlock_page(page); - } + + if (PageAnon(page) && compound_mapcount(page) != 1) + goto skip_mlock; + if (PageDoubleMap(page) || !page->mapping) + goto skip_mlock; + if (!trylock_page(page)) + goto skip_mlock; + lru_add_drain(); + if (page->mapping && !PageDoubleMap(page)) + mlock_vma_page(page); + unlock_page(page); } +skip_mlock: page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page), page); if (flags & FOLL_GET) @@ -1458,13 +1122,12 @@ out: } /* NUMA hinting page fault entry point for trans huge pmds */ -int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, pmd_t *pmdp) +int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd) { - spinlock_t *ptl; + struct vm_area_struct *vma = fe->vma; struct anon_vma *anon_vma = NULL; struct page *page; - unsigned long haddr = addr & HPAGE_PMD_MASK; + unsigned long haddr = fe->address & HPAGE_PMD_MASK; int page_nid = -1, this_nid = numa_node_id(); int target_nid, last_cpupid = -1; bool page_locked; @@ -1475,8 +1138,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* A PROT_NONE fault should not end up here */ BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); - ptl = pmd_lock(mm, pmdp); - if (unlikely(!pmd_same(pmd, *pmdp))) + fe->ptl = pmd_lock(vma->vm_mm, fe->pmd); + if (unlikely(!pmd_same(pmd, *fe->pmd))) goto out_unlock; /* @@ -1484,9 +1147,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * without disrupting NUMA hinting information. Do not relock and * check_same as the page may no longer be mapped. */ - if (unlikely(pmd_trans_migrating(*pmdp))) { - page = pmd_page(*pmdp); - spin_unlock(ptl); + if (unlikely(pmd_trans_migrating(*fe->pmd))) { + page = pmd_page(*fe->pmd); + spin_unlock(fe->ptl); wait_on_page_locked(page); goto out; } @@ -1519,7 +1182,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { - spin_unlock(ptl); + spin_unlock(fe->ptl); wait_on_page_locked(page); page_nid = -1; goto out; @@ -1530,12 +1193,12 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * to serialises splits */ get_page(page); - spin_unlock(ptl); + spin_unlock(fe->ptl); anon_vma = page_lock_anon_vma_read(page); /* Confirm the PMD did not change while page_table_lock was released */ - spin_lock(ptl); - if (unlikely(!pmd_same(pmd, *pmdp))) { + spin_lock(fe->ptl); + if (unlikely(!pmd_same(pmd, *fe->pmd))) { unlock_page(page); put_page(page); page_nid = -1; @@ -1553,9 +1216,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * Migrate the THP to the requested node, returns with page unlocked * and access rights restored. */ - spin_unlock(ptl); - migrated = migrate_misplaced_transhuge_page(mm, vma, - pmdp, pmd, addr, page, target_nid); + spin_unlock(fe->ptl); + migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma, + fe->pmd, pmd, fe->address, page, target_nid); if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; @@ -1570,18 +1233,18 @@ clear_pmdnuma: pmd = pmd_mkyoung(pmd); if (was_writable) pmd = pmd_mkwrite(pmd); - set_pmd_at(mm, haddr, pmdp, pmd); - update_mmu_cache_pmd(vma, addr, pmdp); + set_pmd_at(vma->vm_mm, haddr, fe->pmd, pmd); + update_mmu_cache_pmd(vma, fe->address, fe->pmd); unlock_page(page); out_unlock: - spin_unlock(ptl); + spin_unlock(fe->ptl); out: if (anon_vma) page_unlock_anon_vma_read(anon_vma); if (page_nid != -1) - task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); + task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, fe->flags); return 0; } @@ -1684,12 +1347,18 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, struct page *page = pmd_page(orig_pmd); page_remove_rmap(page, true); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); - add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); VM_BUG_ON_PAGE(!PageHead(page), page); - pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); - atomic_long_dec(&tlb->mm->nr_ptes); + if (PageAnon(page)) { + pgtable_t pgtable; + pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); + pte_free(tlb->mm, pgtable); + atomic_long_dec(&tlb->mm->nr_ptes); + add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); + } else { + add_mm_counter(tlb->mm, MM_FILEPAGES, -HPAGE_PMD_NR); + } spin_unlock(ptl); - tlb_remove_page(tlb, page); + tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE); } return 1; } @@ -1779,7 +1448,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mkwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); - BUG_ON(!preserve_write && pmd_write(entry)); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && + pmd_write(entry)); } spin_unlock(ptl); } @@ -1788,10 +1458,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, } /* - * Returns true if a given pmd maps a thp, false otherwise. + * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. * - * Note that if it returns true, this routine returns without unlocking page - * table lock. So callers must unlock it. + * Note that if it returns page table lock pointer, this routine returns without + * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { @@ -1803,1040 +1473,6 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) return NULL; } -#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) - -int hugepage_madvise(struct vm_area_struct *vma, - unsigned long *vm_flags, int advice) -{ - switch (advice) { - case MADV_HUGEPAGE: -#ifdef CONFIG_S390 - /* - * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 - * can't handle this properly after s390_enable_sie, so we simply - * ignore the madvise to prevent qemu from causing a SIGSEGV. - */ - if (mm_has_pgste(vma->vm_mm)) - return 0; -#endif - /* - * Be somewhat over-protective like KSM for now! - */ - if (*vm_flags & VM_NO_THP) - return -EINVAL; - *vm_flags &= ~VM_NOHUGEPAGE; - *vm_flags |= VM_HUGEPAGE; - /* - * If the vma become good for khugepaged to scan, - * register it here without waiting a page fault that - * may not happen any time soon. - */ - if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags))) - return -ENOMEM; - break; - case MADV_NOHUGEPAGE: - /* - * Be somewhat over-protective like KSM for now! - */ - if (*vm_flags & VM_NO_THP) - return -EINVAL; - *vm_flags &= ~VM_HUGEPAGE; - *vm_flags |= VM_NOHUGEPAGE; - /* - * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning - * this vma even if we leave the mm registered in khugepaged if - * it got registered before VM_NOHUGEPAGE was set. - */ - break; - } - - return 0; -} - -static int __init khugepaged_slab_init(void) -{ - mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", - sizeof(struct mm_slot), - __alignof__(struct mm_slot), 0, NULL); - if (!mm_slot_cache) - return -ENOMEM; - - return 0; -} - -static void __init khugepaged_slab_exit(void) -{ - kmem_cache_destroy(mm_slot_cache); -} - -static inline struct mm_slot *alloc_mm_slot(void) -{ - if (!mm_slot_cache) /* initialization failed */ - return NULL; - return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); -} - -static inline void free_mm_slot(struct mm_slot *mm_slot) -{ - kmem_cache_free(mm_slot_cache, mm_slot); -} - -static struct mm_slot *get_mm_slot(struct mm_struct *mm) -{ - struct mm_slot *mm_slot; - - hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) - if (mm == mm_slot->mm) - return mm_slot; - - return NULL; -} - -static void insert_to_mm_slots_hash(struct mm_struct *mm, - struct mm_slot *mm_slot) -{ - mm_slot->mm = mm; - hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); -} - -static inline int khugepaged_test_exit(struct mm_struct *mm) -{ - return atomic_read(&mm->mm_users) == 0; -} - -int __khugepaged_enter(struct mm_struct *mm) -{ - struct mm_slot *mm_slot; - int wakeup; - - mm_slot = alloc_mm_slot(); - if (!mm_slot) - return -ENOMEM; - - /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); - if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { - free_mm_slot(mm_slot); - return 0; - } - - spin_lock(&khugepaged_mm_lock); - insert_to_mm_slots_hash(mm, mm_slot); - /* - * Insert just behind the scanning cursor, to let the area settle - * down a little. - */ - wakeup = list_empty(&khugepaged_scan.mm_head); - list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); - spin_unlock(&khugepaged_mm_lock); - - atomic_inc(&mm->mm_count); - if (wakeup) - wake_up_interruptible(&khugepaged_wait); - - return 0; -} - -int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - unsigned long hstart, hend; - if (!vma->anon_vma) - /* - * Not yet faulted in so we will register later in the - * page fault if needed. - */ - return 0; - if (vma->vm_ops || (vm_flags & VM_NO_THP)) - /* khugepaged not yet working on file or special mappings */ - return 0; - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart < hend) - return khugepaged_enter(vma, vm_flags); - return 0; -} - -void __khugepaged_exit(struct mm_struct *mm) -{ - struct mm_slot *mm_slot; - int free = 0; - - spin_lock(&khugepaged_mm_lock); - mm_slot = get_mm_slot(mm); - if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { - hash_del(&mm_slot->hash); - list_del(&mm_slot->mm_node); - free = 1; - } - spin_unlock(&khugepaged_mm_lock); - - if (free) { - clear_bit(MMF_VM_HUGEPAGE, &mm->flags); - free_mm_slot(mm_slot); - mmdrop(mm); - } else if (mm_slot) { - /* - * This is required to serialize against - * khugepaged_test_exit() (which is guaranteed to run - * under mmap sem read mode). Stop here (after we - * return all pagetables will be destroyed) until - * khugepaged has finished working on the pagetables - * under the mmap_sem. - */ - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); - } -} - -static void release_pte_page(struct page *page) -{ - /* 0 stands for page_is_file_cache(page) == false */ - dec_zone_page_state(page, NR_ISOLATED_ANON + 0); - unlock_page(page); - putback_lru_page(page); -} - -static void release_pte_pages(pte_t *pte, pte_t *_pte) -{ - while (--_pte >= pte) { - pte_t pteval = *_pte; - if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval))) - release_pte_page(pte_page(pteval)); - } -} - -static int __collapse_huge_page_isolate(struct vm_area_struct *vma, - unsigned long address, - pte_t *pte) -{ - struct page *page = NULL; - pte_t *_pte; - int none_or_zero = 0, result = 0; - bool referenced = false, writable = false; - - for (_pte = pte; _pte < pte+HPAGE_PMD_NR; - _pte++, address += PAGE_SIZE) { - pte_t pteval = *_pte; - if (pte_none(pteval) || (pte_present(pteval) && - is_zero_pfn(pte_pfn(pteval)))) { - if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) { - continue; - } else { - result = SCAN_EXCEED_NONE_PTE; - goto out; - } - } - if (!pte_present(pteval)) { - result = SCAN_PTE_NON_PRESENT; - goto out; - } - page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) { - result = SCAN_PAGE_NULL; - goto out; - } - - VM_BUG_ON_PAGE(PageCompound(page), page); - VM_BUG_ON_PAGE(!PageAnon(page), page); - VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - - /* - * We can do it before isolate_lru_page because the - * page can't be freed from under us. NOTE: PG_lock - * is needed to serialize against split_huge_page - * when invoked from the VM. - */ - if (!trylock_page(page)) { - result = SCAN_PAGE_LOCK; - goto out; - } - - /* - * cannot use mapcount: can't collapse if there's a gup pin. - * The page must only be referenced by the scanned process - * and page swap cache. - */ - if (page_count(page) != 1 + !!PageSwapCache(page)) { - unlock_page(page); - result = SCAN_PAGE_COUNT; - goto out; - } - if (pte_write(pteval)) { - writable = true; - } else { - if (PageSwapCache(page) && - !reuse_swap_page(page, NULL)) { - unlock_page(page); - result = SCAN_SWAP_CACHE_PAGE; - goto out; - } - /* - * Page is not in the swap cache. It can be collapsed - * into a THP. - */ - } - - /* - * Isolate the page to avoid collapsing an hugepage - * currently in use by the VM. - */ - if (isolate_lru_page(page)) { - unlock_page(page); - result = SCAN_DEL_PAGE_LRU; - goto out; - } - /* 0 stands for page_is_file_cache(page) == false */ - inc_zone_page_state(page, NR_ISOLATED_ANON + 0); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageLRU(page), page); - - /* If there is no mapped pte young don't collapse the page */ - if (pte_young(pteval) || - page_is_young(page) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) - referenced = true; - } - if (likely(writable)) { - if (likely(referenced)) { - result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page, none_or_zero, - referenced, writable, result); - return 1; - } - } else { - result = SCAN_PAGE_RO; - } - -out: - release_pte_pages(pte, _pte); - trace_mm_collapse_huge_page_isolate(page, none_or_zero, - referenced, writable, result); - return 0; -} - -static void __collapse_huge_page_copy(pte_t *pte, struct page *page, - struct vm_area_struct *vma, - unsigned long address, - spinlock_t *ptl) -{ - pte_t *_pte; - for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) { - pte_t pteval = *_pte; - struct page *src_page; - - if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { - clear_user_highpage(page, address); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); - if (is_zero_pfn(pte_pfn(pteval))) { - /* - * ptl mostly unnecessary. - */ - spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); - spin_unlock(ptl); - } - } else { - src_page = pte_page(pteval); - copy_user_highpage(page, src_page, address, vma); - VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page); - release_pte_page(src_page); - /* - * ptl mostly unnecessary, but preempt has to - * be disabled to update the per-cpu stats - * inside page_remove_rmap(). - */ - spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); - page_remove_rmap(src_page, false); - spin_unlock(ptl); - free_page_and_swap_cache(src_page); - } - - address += PAGE_SIZE; - page++; - } -} - -static void khugepaged_alloc_sleep(void) -{ - DEFINE_WAIT(wait); - - add_wait_queue(&khugepaged_wait, &wait); - freezable_schedule_timeout_interruptible( - msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); - remove_wait_queue(&khugepaged_wait, &wait); -} - -static int khugepaged_node_load[MAX_NUMNODES]; - -static bool khugepaged_scan_abort(int nid) -{ - int i; - - /* - * If zone_reclaim_mode is disabled, then no extra effort is made to - * allocate memory locally. - */ - if (!zone_reclaim_mode) - return false; - - /* If there is a count for this node already, it must be acceptable */ - if (khugepaged_node_load[nid]) - return false; - - for (i = 0; i < MAX_NUMNODES; i++) { - if (!khugepaged_node_load[i]) - continue; - if (node_distance(nid, i) > RECLAIM_DISTANCE) - return true; - } - return false; -} - -#ifdef CONFIG_NUMA -static int khugepaged_find_target_node(void) -{ - static int last_khugepaged_target_node = NUMA_NO_NODE; - int nid, target_node = 0, max_value = 0; - - /* find first node with max normal pages hit */ - for (nid = 0; nid < MAX_NUMNODES; nid++) - if (khugepaged_node_load[nid] > max_value) { - max_value = khugepaged_node_load[nid]; - target_node = nid; - } - - /* do some balance if several nodes have the same hit record */ - if (target_node <= last_khugepaged_target_node) - for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; - nid++) - if (max_value == khugepaged_node_load[nid]) { - target_node = nid; - break; - } - - last_khugepaged_target_node = target_node; - return target_node; -} - -static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) -{ - if (IS_ERR(*hpage)) { - if (!*wait) - return false; - - *wait = false; - *hpage = NULL; - khugepaged_alloc_sleep(); - } else if (*hpage) { - put_page(*hpage); - *hpage = NULL; - } - - return true; -} - -static struct page * -khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, - unsigned long address, int node) -{ - VM_BUG_ON_PAGE(*hpage, *hpage); - - /* - * Before allocating the hugepage, release the mmap_sem read lock. - * The allocation can take potentially a long time if it involves - * sync compaction, and we do not need to hold the mmap_sem during - * that. We will recheck the vma after taking it again in write mode. - */ - up_read(&mm->mmap_sem); - - *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); - if (unlikely(!*hpage)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - *hpage = ERR_PTR(-ENOMEM); - return NULL; - } - - prep_transhuge_page(*hpage); - count_vm_event(THP_COLLAPSE_ALLOC); - return *hpage; -} -#else -static int khugepaged_find_target_node(void) -{ - return 0; -} - -static inline struct page *alloc_khugepaged_hugepage(void) -{ - struct page *page; - - page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(), - HPAGE_PMD_ORDER); - if (page) - prep_transhuge_page(page); - return page; -} - -static struct page *khugepaged_alloc_hugepage(bool *wait) -{ - struct page *hpage; - - do { - hpage = alloc_khugepaged_hugepage(); - if (!hpage) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - if (!*wait) - return NULL; - - *wait = false; - khugepaged_alloc_sleep(); - } else - count_vm_event(THP_COLLAPSE_ALLOC); - } while (unlikely(!hpage) && likely(khugepaged_enabled())); - - return hpage; -} - -static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) -{ - if (!*hpage) - *hpage = khugepaged_alloc_hugepage(wait); - - if (unlikely(!*hpage)) - return false; - - return true; -} - -static struct page * -khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, - unsigned long address, int node) -{ - up_read(&mm->mmap_sem); - VM_BUG_ON(!*hpage); - - return *hpage; -} -#endif - -static bool hugepage_vma_check(struct vm_area_struct *vma) -{ - if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || - (vma->vm_flags & VM_NOHUGEPAGE)) - return false; - if (!vma->anon_vma || vma->vm_ops) - return false; - if (is_vma_temporary_stack(vma)) - return false; - return !(vma->vm_flags & VM_NO_THP); -} - -static void collapse_huge_page(struct mm_struct *mm, - unsigned long address, - struct page **hpage, - struct vm_area_struct *vma, - int node) -{ - pmd_t *pmd, _pmd; - pte_t *pte; - pgtable_t pgtable; - struct page *new_page; - spinlock_t *pmd_ptl, *pte_ptl; - int isolated = 0, result = 0; - unsigned long hstart, hend; - struct mem_cgroup *memcg; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - gfp_t gfp; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - - /* Only allocate from the target node */ - gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_OTHER_NODE | __GFP_THISNODE; - - /* release the mmap_sem read lock. */ - new_page = khugepaged_alloc_page(hpage, gfp, mm, address, node); - if (!new_page) { - result = SCAN_ALLOC_HUGE_PAGE_FAIL; - goto out_nolock; - } - - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { - result = SCAN_CGROUP_CHARGE_FAIL; - goto out_nolock; - } - - /* - * Prevent all access to pagetables with the exception of - * gup_fast later hanlded by the ptep_clear_flush and the VM - * handled by the anon_vma lock + PG_lock. - */ - down_write(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) { - result = SCAN_ANY_PROCESS; - goto out; - } - - vma = find_vma(mm, address); - if (!vma) { - result = SCAN_VMA_NULL; - goto out; - } - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (address < hstart || address + HPAGE_PMD_SIZE > hend) { - result = SCAN_ADDRESS_RANGE; - goto out; - } - if (!hugepage_vma_check(vma)) { - result = SCAN_VMA_CHECK; - goto out; - } - pmd = mm_find_pmd(mm, address); - if (!pmd) { - result = SCAN_PMD_NULL; - goto out; - } - - anon_vma_lock_write(vma->anon_vma); - - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - - mmun_start = address; - mmun_end = address + HPAGE_PMD_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ - /* - * After this gup_fast can't run anymore. This also removes - * any huge TLB entry from the CPU so we won't allow - * huge and small TLB entries for the same virtual address - * to avoid the risk of CPU bugs in that area. - */ - _pmd = pmdp_collapse_flush(vma, address, pmd); - spin_unlock(pmd_ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - - spin_lock(pte_ptl); - isolated = __collapse_huge_page_isolate(vma, address, pte); - spin_unlock(pte_ptl); - - if (unlikely(!isolated)) { - pte_unmap(pte); - spin_lock(pmd_ptl); - BUG_ON(!pmd_none(*pmd)); - /* - * We can only use set_pmd_at when establishing - * hugepmds and never for establishing regular pmds that - * points to regular pagetables. Use pmd_populate for that - */ - pmd_populate(mm, pmd, pmd_pgtable(_pmd)); - spin_unlock(pmd_ptl); - anon_vma_unlock_write(vma->anon_vma); - result = SCAN_FAIL; - goto out; - } - - /* - * All pages are isolated and locked so anon_vma rmap - * can't run anymore. - */ - anon_vma_unlock_write(vma->anon_vma); - - __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl); - pte_unmap(pte); - __SetPageUptodate(new_page); - pgtable = pmd_pgtable(_pmd); - - _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); - _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); - - /* - * spin_lock() below is not the equivalent of smp_wmb(), so - * this is needed to avoid the copy_huge_page writes to become - * visible after the set_pmd_at() write. - */ - smp_wmb(); - - spin_lock(pmd_ptl); - BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address, true); - mem_cgroup_commit_charge(new_page, memcg, false, true); - lru_cache_add_active_or_unevictable(new_page, vma); - pgtable_trans_huge_deposit(mm, pmd, pgtable); - set_pmd_at(mm, address, pmd, _pmd); - update_mmu_cache_pmd(vma, address, pmd); - spin_unlock(pmd_ptl); - - *hpage = NULL; - - khugepaged_pages_collapsed++; - result = SCAN_SUCCEED; -out_up_write: - up_write(&mm->mmap_sem); - trace_mm_collapse_huge_page(mm, isolated, result); - return; - -out_nolock: - trace_mm_collapse_huge_page(mm, isolated, result); - return; -out: - mem_cgroup_cancel_charge(new_page, memcg, true); - goto out_up_write; -} - -static int khugepaged_scan_pmd(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, - struct page **hpage) -{ - pmd_t *pmd; - pte_t *pte, *_pte; - int ret = 0, none_or_zero = 0, result = 0; - struct page *page = NULL; - unsigned long _address; - spinlock_t *ptl; - int node = NUMA_NO_NODE; - bool writable = false, referenced = false; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - - pmd = mm_find_pmd(mm, address); - if (!pmd) { - result = SCAN_PMD_NULL; - goto out; - } - - memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; - _pte++, _address += PAGE_SIZE) { - pte_t pteval = *_pte; - if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { - if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) { - continue; - } else { - result = SCAN_EXCEED_NONE_PTE; - goto out_unmap; - } - } - if (!pte_present(pteval)) { - result = SCAN_PTE_NON_PRESENT; - goto out_unmap; - } - if (pte_write(pteval)) - writable = true; - - page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) { - result = SCAN_PAGE_NULL; - goto out_unmap; - } - - /* TODO: teach khugepaged to collapse THP mapped with pte */ - if (PageCompound(page)) { - result = SCAN_PAGE_COMPOUND; - goto out_unmap; - } - - /* - * Record which node the original page is from and save this - * information to khugepaged_node_load[]. - * Khupaged will allocate hugepage from the node has the max - * hit record. - */ - node = page_to_nid(page); - if (khugepaged_scan_abort(node)) { - result = SCAN_SCAN_ABORT; - goto out_unmap; - } - khugepaged_node_load[node]++; - if (!PageLRU(page)) { - result = SCAN_PAGE_LRU; - goto out_unmap; - } - if (PageLocked(page)) { - result = SCAN_PAGE_LOCK; - goto out_unmap; - } - if (!PageAnon(page)) { - result = SCAN_PAGE_ANON; - goto out_unmap; - } - - /* - * cannot use mapcount: can't collapse if there's a gup pin. - * The page must only be referenced by the scanned process - * and page swap cache. - */ - if (page_count(page) != 1 + !!PageSwapCache(page)) { - result = SCAN_PAGE_COUNT; - goto out_unmap; - } - if (pte_young(pteval) || - page_is_young(page) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) - referenced = true; - } - if (writable) { - if (referenced) { - result = SCAN_SUCCEED; - ret = 1; - } else { - result = SCAN_NO_REFERENCED_PAGE; - } - } else { - result = SCAN_PAGE_RO; - } -out_unmap: - pte_unmap_unlock(pte, ptl); - if (ret) { - node = khugepaged_find_target_node(); - /* collapse_huge_page will return with the mmap_sem released */ - collapse_huge_page(mm, address, hpage, vma, node); - } -out: - trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, - none_or_zero, result); - return ret; -} - -static void collect_mm_slot(struct mm_slot *mm_slot) -{ - struct mm_struct *mm = mm_slot->mm; - - VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); - - if (khugepaged_test_exit(mm)) { - /* free mm_slot */ - hash_del(&mm_slot->hash); - list_del(&mm_slot->mm_node); - - /* - * Not strictly needed because the mm exited already. - * - * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); - */ - - /* khugepaged_mm_lock actually not necessary for the below */ - free_mm_slot(mm_slot); - mmdrop(mm); - } -} - -static unsigned int khugepaged_scan_mm_slot(unsigned int pages, - struct page **hpage) - __releases(&khugepaged_mm_lock) - __acquires(&khugepaged_mm_lock) -{ - struct mm_slot *mm_slot; - struct mm_struct *mm; - struct vm_area_struct *vma; - int progress = 0; - - VM_BUG_ON(!pages); - VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); - - if (khugepaged_scan.mm_slot) - mm_slot = khugepaged_scan.mm_slot; - else { - mm_slot = list_entry(khugepaged_scan.mm_head.next, - struct mm_slot, mm_node); - khugepaged_scan.address = 0; - khugepaged_scan.mm_slot = mm_slot; - } - spin_unlock(&khugepaged_mm_lock); - - mm = mm_slot->mm; - down_read(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) - vma = NULL; - else - vma = find_vma(mm, khugepaged_scan.address); - - progress++; - for (; vma; vma = vma->vm_next) { - unsigned long hstart, hend; - - cond_resched(); - if (unlikely(khugepaged_test_exit(mm))) { - progress++; - break; - } - if (!hugepage_vma_check(vma)) { -skip: - progress++; - continue; - } - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart >= hend) - goto skip; - if (khugepaged_scan.address > hend) - goto skip; - if (khugepaged_scan.address < hstart) - khugepaged_scan.address = hstart; - VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); - - while (khugepaged_scan.address < hend) { - int ret; - cond_resched(); - if (unlikely(khugepaged_test_exit(mm))) - goto breakouterloop; - - VM_BUG_ON(khugepaged_scan.address < hstart || - khugepaged_scan.address + HPAGE_PMD_SIZE > - hend); - ret = khugepaged_scan_pmd(mm, vma, - khugepaged_scan.address, - hpage); - /* move to next address */ - khugepaged_scan.address += HPAGE_PMD_SIZE; - progress += HPAGE_PMD_NR; - if (ret) - /* we released mmap_sem so break loop */ - goto breakouterloop_mmap_sem; - if (progress >= pages) - goto breakouterloop; - } - } -breakouterloop: - up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */ -breakouterloop_mmap_sem: - - spin_lock(&khugepaged_mm_lock); - VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); - /* - * Release the current mm_slot if this mm is about to die, or - * if we scanned all vmas of this mm. - */ - if (khugepaged_test_exit(mm) || !vma) { - /* - * Make sure that if mm_users is reaching zero while - * khugepaged runs here, khugepaged_exit will find - * mm_slot not pointing to the exiting mm. - */ - if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { - khugepaged_scan.mm_slot = list_entry( - mm_slot->mm_node.next, - struct mm_slot, mm_node); - khugepaged_scan.address = 0; - } else { - khugepaged_scan.mm_slot = NULL; - khugepaged_full_scans++; - } - - collect_mm_slot(mm_slot); - } - - return progress; -} - -static int khugepaged_has_work(void) -{ - return !list_empty(&khugepaged_scan.mm_head) && - khugepaged_enabled(); -} - -static int khugepaged_wait_event(void) -{ - return !list_empty(&khugepaged_scan.mm_head) || - kthread_should_stop(); -} - -static void khugepaged_do_scan(void) -{ - struct page *hpage = NULL; - unsigned int progress = 0, pass_through_head = 0; - unsigned int pages = khugepaged_pages_to_scan; - bool wait = true; - - barrier(); /* write khugepaged_pages_to_scan to local stack */ - - while (progress < pages) { - if (!khugepaged_prealloc_page(&hpage, &wait)) - break; - - cond_resched(); - - if (unlikely(kthread_should_stop() || try_to_freeze())) - break; - - spin_lock(&khugepaged_mm_lock); - if (!khugepaged_scan.mm_slot) - pass_through_head++; - if (khugepaged_has_work() && - pass_through_head < 2) - progress += khugepaged_scan_mm_slot(pages - progress, - &hpage); - else - progress = pages; - spin_unlock(&khugepaged_mm_lock); - } - - if (!IS_ERR_OR_NULL(hpage)) - put_page(hpage); -} - -static bool khugepaged_should_wakeup(void) -{ - return kthread_should_stop() || - time_after_eq(jiffies, khugepaged_sleep_expire); -} - -static void khugepaged_wait_work(void) -{ - if (khugepaged_has_work()) { - const unsigned long scan_sleep_jiffies = - msecs_to_jiffies(khugepaged_scan_sleep_millisecs); - - if (!scan_sleep_jiffies) - return; - - khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; - wait_event_freezable_timeout(khugepaged_wait, - khugepaged_should_wakeup(), - scan_sleep_jiffies); - return; - } - - if (khugepaged_enabled()) - wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); -} - -static int khugepaged(void *none) -{ - struct mm_slot *mm_slot; - - set_freezable(); - set_user_nice(current, MAX_NICE); - - while (!kthread_should_stop()) { - khugepaged_do_scan(); - khugepaged_wait_work(); - } - - spin_lock(&khugepaged_mm_lock); - mm_slot = khugepaged_scan.mm_slot; - khugepaged_scan.mm_slot = NULL; - if (mm_slot) - collect_mm_slot(mm_slot); - spin_unlock(&khugepaged_mm_lock); - return 0; -} - static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd) { @@ -2883,10 +1519,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, count_vm_event(THP_SPLIT_PMD); - if (vma_is_dax(vma)) { - pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + if (!vma_is_anonymous(vma)) { + _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); if (is_huge_zero_pmd(_pmd)) put_huge_zero_page(); + if (vma_is_dax(vma)) + return; + page = pmd_page(_pmd); + if (!PageReferenced(page) && pmd_young(_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + add_mm_counter(mm, MM_FILEPAGES, -HPAGE_PMD_NR); return; } else if (is_huge_zero_pmd(*pmd)) { return __split_huge_zero_page_pmd(vma, haddr, pmd); @@ -2942,7 +1586,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { /* Last compound_mapcount is gone. */ - __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + __dec_zone_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* No need in mapcount reference anymore */ for (i = 0; i < HPAGE_PMD_NR; i++) @@ -3076,12 +1720,15 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void freeze_page(struct page *page) { - enum ttu_flags ttu_flags = TTU_MIGRATION | TTU_IGNORE_MLOCK | - TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED; + enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | + TTU_RMAP_LOCKED; int i, ret; VM_BUG_ON_PAGE(!PageHead(page), page); + if (PageAnon(page)) + ttu_flags |= TTU_MIGRATION; + /* We only need TTU_SPLIT_HUGE_PMD once */ ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD); for (i = 1; !ret && i < HPAGE_PMD_NR; i++) { @@ -3091,7 +1738,7 @@ static void freeze_page(struct page *page) ret = try_to_unmap(page + i, ttu_flags); } - VM_BUG_ON(ret); + VM_BUG_ON_PAGE(ret, page + i - 1); } static void unfreeze_page(struct page *page) @@ -3113,15 +1760,20 @@ static void __split_huge_page_tail(struct page *head, int tail, /* * tail_page->_refcount is zero and not changing from under us. But * get_page_unless_zero() may be running from under us on the - * tail_page. If we used atomic_set() below instead of atomic_inc(), we - * would then run atomic_set() concurrently with + * tail_page. If we used atomic_set() below instead of atomic_inc() or + * atomic_add(), we would then run atomic_set() concurrently with * get_page_unless_zero(), and atomic_set() is implemented in C not * using locked ops. spin_unlock on x86 sometime uses locked ops * because of PPro errata 66, 92, so unless somebody can guarantee * atomic_set() here would be safe on all archs (and not only on x86), - * it's safer to use atomic_inc(). + * it's safer to use atomic_inc()/atomic_add(). */ - page_ref_inc(page_tail); + if (PageAnon(head)) { + page_ref_inc(page_tail); + } else { + /* Additional pin to radix tree */ + page_ref_add(page_tail, 2); + } page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & @@ -3157,25 +1809,46 @@ static void __split_huge_page_tail(struct page *head, int tail, lru_add_page_tail(head, page_tail, lruvec, list); } -static void __split_huge_page(struct page *page, struct list_head *list) +static void __split_huge_page(struct page *page, struct list_head *list, + unsigned long flags) { struct page *head = compound_head(page); struct zone *zone = page_zone(head); struct lruvec *lruvec; + pgoff_t end = -1; int i; - /* prevent PageLRU to go away from under us, and freeze lru stats */ - spin_lock_irq(&zone->lru_lock); lruvec = mem_cgroup_page_lruvec(head, zone); /* complete memcg works before add pages to LRU */ mem_cgroup_split_huge_fixup(head); - for (i = HPAGE_PMD_NR - 1; i >= 1; i--) + if (!PageAnon(page)) + end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE); + + for (i = HPAGE_PMD_NR - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); + /* Some pages can be beyond i_size: drop them from page cache */ + if (head[i].index >= end) { + __ClearPageDirty(head + i); + __delete_from_page_cache(head + i, NULL); + if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) + shmem_uncharge(head->mapping->host, 1); + put_page(head + i); + } + } ClearPageCompound(head); - spin_unlock_irq(&zone->lru_lock); + /* See comment in __split_huge_page_tail() */ + if (PageAnon(head)) { + page_ref_inc(head); + } else { + /* Additional pin to radix tree */ + page_ref_add(head, 2); + spin_unlock(&head->mapping->tree_lock); + } + + spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags); unfreeze_page(head); @@ -3198,18 +1871,22 @@ static void __split_huge_page(struct page *page, struct list_head *list) int total_mapcount(struct page *page) { - int i, ret; + int i, compound, ret; VM_BUG_ON_PAGE(PageTail(page), page); if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) + 1; - ret = compound_mapcount(page); + compound = compound_mapcount(page); if (PageHuge(page)) - return ret; + return compound; + ret = compound; for (i = 0; i < HPAGE_PMD_NR; i++) ret += atomic_read(&page[i]._mapcount) + 1; + /* File pages has compound_mapcount included in _mapcount */ + if (!PageAnon(page)) + return ret - compound * HPAGE_PMD_NR; if (PageDoubleMap(page)) ret -= HPAGE_PMD_NR; return ret; @@ -3296,36 +1973,54 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); - struct anon_vma *anon_vma; - int count, mapcount, ret; + struct anon_vma *anon_vma = NULL; + struct address_space *mapping = NULL; + int count, mapcount, extra_pins, ret; bool mlocked; unsigned long flags; VM_BUG_ON_PAGE(is_huge_zero_page(page), page); - VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page); - /* - * The caller does not necessarily hold an mmap_sem that would prevent - * the anon_vma disappearing so we first we take a reference to it - * and then lock the anon_vma for write. This is similar to - * page_lock_anon_vma_read except the write lock is taken to serialise - * against parallel split or collapse operations. - */ - anon_vma = page_get_anon_vma(head); - if (!anon_vma) { - ret = -EBUSY; - goto out; + if (PageAnon(head)) { + /* + * The caller does not necessarily hold an mmap_sem that would + * prevent the anon_vma disappearing so we first we take a + * reference to it and then lock the anon_vma for write. This + * is similar to page_lock_anon_vma_read except the write lock + * is taken to serialise against parallel split or collapse + * operations. + */ + anon_vma = page_get_anon_vma(head); + if (!anon_vma) { + ret = -EBUSY; + goto out; + } + extra_pins = 0; + mapping = NULL; + anon_vma_lock_write(anon_vma); + } else { + mapping = head->mapping; + + /* Truncated ? */ + if (!mapping) { + ret = -EBUSY; + goto out; + } + + /* Addidional pins from radix tree */ + extra_pins = HPAGE_PMD_NR; + anon_vma = NULL; + i_mmap_lock_read(mapping); } - anon_vma_lock_write(anon_vma); /* * Racy check if we can split the page, before freeze_page() will * split PMDs */ - if (total_mapcount(head) != page_count(head) - 1) { + if (total_mapcount(head) != page_count(head) - extra_pins - 1) { ret = -EBUSY; goto out_unlock; } @@ -3338,35 +2033,62 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mlocked) lru_add_drain(); + /* prevent PageLRU to go away from under us, and freeze lru stats */ + spin_lock_irqsave(&page_zone(head)->lru_lock, flags); + + if (mapping) { + void **pslot; + + spin_lock(&mapping->tree_lock); + pslot = radix_tree_lookup_slot(&mapping->page_tree, + page_index(head)); + /* + * Check if the head page is present in radix tree. + * We assume all tail are present too, if head is there. + */ + if (radix_tree_deref_slot_protected(pslot, + &mapping->tree_lock) != head) + goto fail; + } + /* Prevent deferred_split_scan() touching ->_refcount */ - spin_lock_irqsave(&pgdata->split_queue_lock, flags); + spin_lock(&pgdata->split_queue_lock); count = page_count(head); mapcount = total_mapcount(head); - if (!mapcount && count == 1) { + if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { pgdata->split_queue_len--; list_del(page_deferred_list(head)); } - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - __split_huge_page(page, list); + if (mapping) + __dec_zone_page_state(page, NR_SHMEM_THPS); + spin_unlock(&pgdata->split_queue_lock); + __split_huge_page(page, list, flags); ret = 0; - } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - pr_alert("total_mapcount: %u, page_count(): %u\n", - mapcount, count); - if (PageTail(page)) - dump_page(head, NULL); - dump_page(page, "total_mapcount(head) > 0"); - BUG(); } else { - spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); + if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { + pr_alert("total_mapcount: %u, page_count(): %u\n", + mapcount, count); + if (PageTail(page)) + dump_page(head, NULL); + dump_page(page, "total_mapcount(head) > 0"); + BUG(); + } + spin_unlock(&pgdata->split_queue_lock); +fail: if (mapping) + spin_unlock(&mapping->tree_lock); + spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags); unfreeze_page(head); ret = -EBUSY; } out_unlock: - anon_vma_unlock_write(anon_vma); - put_anon_vma(anon_vma); + if (anon_vma) { + anon_vma_unlock_write(anon_vma); + put_anon_vma(anon_vma); + } + if (mapping) + i_mmap_unlock_read(mapping); out: count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; @@ -3489,8 +2211,7 @@ static int split_huge_pages_set(void *data, u64 val) if (zone != page_zone(page)) goto next; - if (!PageHead(page) || !PageAnon(page) || - PageHuge(page)) + if (!PageHead(page) || PageHuge(page) || !PageLRU(page)) goto next; total++; |