The anonymous page fault handler in do_anonymous_page() open-codes the sequence to map a newly allocated anonymous folio at the PTE level: - construct the PTE entry - add rmap - add to LRU - set the PTEs - update the MMU cache. Introduce a two helpers to consolidate this duplicated logic, mirroring the existing map_anon_folio_pmd_nopf() pattern for PMD-level mappings: map_anon_folio_pte_nopf(): constructs the PTE entry, takes folio references, adds anon rmap and LRU. This function also handles the uffd_wp that can occur in the pf variant. map_anon_folio_pte_pf(): extends the nopf variant to handle MM_ANONPAGES counter updates, and mTHP fault allocation statistics for the page fault path. The zero-page read path in do_anonymous_page() is also untangled from the shared setpte label, since it does not allocate a folio and should not share the same mapping sequence as the write path. Make nr_pages = 1 rather than relying on the variable. This makes it more clear that we are operating on the zero page only. This refactoring will also help reduce code duplication between mm/memory.c and mm/khugepaged.c, and provides a clean API for PTE-level anonymous folio mapping that can be reused by future callers. Signed-off-by: Nico Pache --- include/linux/mm.h | 4 ++++ mm/memory.c | 59 +++++++++++++++++++++++++++++++--------------- 2 files changed, 44 insertions(+), 19 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 13336340612e..3ebf143c7502 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4901,4 +4901,8 @@ static inline bool snapshot_page_is_faithful(const struct page_snapshot *ps) void snapshot_page(struct page_snapshot *ps, const struct page *page); +void map_anon_folio_pte_nopf(struct folio *folio, pte_t *pte, + struct vm_area_struct *vma, unsigned long addr, + bool uffd_wp); + #endif /* _LINUX_MM_H */ diff --git a/mm/memory.c b/mm/memory.c index 9385842c3503..a1a364e1fdcd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5189,6 +5189,36 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) return folio_prealloc(vma->vm_mm, vma, vmf->address, true); } +void map_anon_folio_pte_nopf(struct folio *folio, pte_t *pte, + struct vm_area_struct *vma, unsigned long addr, + bool uffd_wp) +{ + unsigned int nr_pages = folio_nr_pages(folio); + pte_t entry = folio_mk_pte(folio, vma->vm_page_prot); + + entry = pte_sw_mkyoung(entry); + + if (vma->vm_flags & VM_WRITE) + entry = pte_mkwrite(pte_mkdirty(entry), vma); + if (uffd_wp) + entry = pte_mkuffd_wp(entry); + + folio_ref_add(folio, nr_pages - 1); + folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + set_ptes(vma->vm_mm, addr, pte, entry, nr_pages); + update_mmu_cache_range(NULL, vma, addr, pte, nr_pages); +} + +static void map_anon_folio_pte_pf(struct folio *folio, pte_t *pte, + struct vm_area_struct *vma, unsigned long addr, + unsigned int nr_pages, bool uffd_wp) +{ + map_anon_folio_pte_nopf(folio, pte, vma, addr, uffd_wp); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); + count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); +} + /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -5235,7 +5265,14 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } - goto setpte; + if (vmf_orig_pte_uffd_wp(vmf)) + entry = pte_mkuffd_wp(entry); + set_pte_at(vma->vm_mm, addr, vmf->pte, entry); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache_range(vmf, vma, addr, vmf->pte, + /*nr_pages=*/ 1); + goto unlock; } /* Allocate our own private page. */ @@ -5259,11 +5296,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) */ __folio_mark_uptodate(folio); - entry = folio_mk_pte(folio, vma->vm_page_prot); - entry = pte_sw_mkyoung(entry); - if (vma->vm_flags & VM_WRITE) - entry = pte_mkwrite(pte_mkdirty(entry), vma); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) goto release; @@ -5285,19 +5317,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) folio_put(folio); return handle_userfault(vmf, VM_UFFD_MISSING); } - - folio_ref_add(folio, nr_pages - 1); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); - count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); - folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); - folio_add_lru_vma(folio, vma); -setpte: - if (vmf_orig_pte_uffd_wp(vmf)) - entry = pte_mkuffd_wp(entry); - set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages); - - /* No need to invalidate - it was non-present before */ - update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages); + map_anon_folio_pte_pf(folio, vmf->pte, vma, addr, nr_pages, + vmf_orig_pte_uffd_wp(vmf)); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); -- 2.53.0 In order to add mTHP support to khugepaged, we will often be checking if a given order is (or is not) a PMD order. Some places in the kernel already use this check, so lets create a simple helper function to keep the code clean and readable. Acked-by: David Hildenbrand (Arm) Reviewed-by: Wei Yang Reviewed-by: Lance Yang Reviewed-by: Barry Song Reviewed-by: Zi Yan Reviewed-by: Pedro Falcato Reviewed-by: Lorenzo Stoakes Suggested-by: Lorenzo Stoakes Signed-off-by: Nico Pache --- include/linux/huge_mm.h | 5 +++++ mm/huge_memory.c | 2 +- mm/khugepaged.c | 6 +++--- mm/memory.c | 2 +- mm/mempolicy.c | 2 +- mm/page_alloc.c | 4 ++-- mm/shmem.c | 3 +-- 7 files changed, 14 insertions(+), 10 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a4d9f964dfde..bd7f0e1d8094 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -771,6 +771,11 @@ static inline bool pmd_is_huge(pmd_t pmd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline bool is_pmd_order(unsigned int order) +{ + return order == HPAGE_PMD_ORDER; +} + static inline int split_folio_to_list_to_order(struct folio *folio, struct list_head *list, int new_order) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8003d3a49822..a688d5ff806e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4100,7 +4100,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order, i_mmap_unlock_read(mapping); out: xas_destroy(&xas); - if (old_order == HPAGE_PMD_ORDER) + if (is_pmd_order(old_order)) count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); count_mthp_stat(old_order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED); return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c85d7381adb5..2ef4b972470b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1533,7 +1533,7 @@ static enum scan_result try_collapse_pte_mapped_thp(struct mm_struct *mm, unsign if (IS_ERR(folio)) return SCAN_PAGE_NULL; - if (folio_order(folio) != HPAGE_PMD_ORDER) { + if (!is_pmd_order(folio_order(folio))) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } @@ -2016,7 +2016,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ - if (folio_order(folio) == HPAGE_PMD_ORDER && + if (is_pmd_order(folio_order(folio)) && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; @@ -2346,7 +2346,7 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, continue; } - if (folio_order(folio) == HPAGE_PMD_ORDER && + if (is_pmd_order(folio_order(folio)) && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; diff --git a/mm/memory.c b/mm/memory.c index a1a364e1fdcd..cb76fa182eab 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5427,7 +5427,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *pa if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; - if (folio_order(folio) != HPAGE_PMD_ORDER) + if (!is_pmd_order(folio_order(folio))) return ret; page = &folio->page; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e5175f1c767..e5528c35bbb8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2449,7 +2449,7 @@ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ - order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { + is_pmd_order(order) && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d88c8c67ac0b..96ffb47bcfee 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -687,7 +687,7 @@ static inline unsigned int order_to_pindex(int migratetype, int order) #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool movable; if (order > PAGE_ALLOC_COSTLY_ORDER) { - VM_BUG_ON(order != HPAGE_PMD_ORDER); + VM_BUG_ON(!is_pmd_order(order)); movable = migratetype == MIGRATE_MOVABLE; @@ -719,7 +719,7 @@ static inline bool pcp_allowed_order(unsigned int order) if (order <= PAGE_ALLOC_COSTLY_ORDER) return true; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order == HPAGE_PMD_ORDER) + if (is_pmd_order(order)) return true; #endif return false; diff --git a/mm/shmem.c b/mm/shmem.c index cfed6c3ff853..ba74803c7518 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -5558,8 +5558,7 @@ static ssize_t thpsize_shmem_enabled_store(struct kobject *kobj, spin_unlock(&huge_shmem_orders_lock); } else if (sysfs_streq(buf, "inherit")) { /* Do not override huge allocation policy with non-PMD sized mTHP */ - if (shmem_huge == SHMEM_HUGE_FORCE && - order != HPAGE_PMD_ORDER) + if (shmem_huge == SHMEM_HUGE_FORCE && !is_pmd_order(order)) return -EINVAL; spin_lock(&huge_shmem_orders_lock); -- 2.53.0 The value (HPAGE_PMD_NR - 1) is used often in the khugepaged code to signify the limit of the max_ptes_* values. Add a define for this to increase code readability and reuse. Acked-by: Pedro Falcato Reviewed-by: Zi Yan Signed-off-by: Nico Pache --- mm/khugepaged.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 2ef4b972470b..4615f34911d1 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -89,6 +89,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); * * Note that these are only respected if collapse was initiated by khugepaged. */ +#define COLLAPSE_MAX_PTES_LIMIT (HPAGE_PMD_NR - 1) unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; @@ -256,7 +257,7 @@ static ssize_t max_ptes_none_store(struct kobject *kobj, unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); - if (err || max_ptes_none > HPAGE_PMD_NR - 1) + if (err || max_ptes_none > COLLAPSE_MAX_PTES_LIMIT) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; @@ -281,7 +282,7 @@ static ssize_t max_ptes_swap_store(struct kobject *kobj, unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); - if (err || max_ptes_swap > HPAGE_PMD_NR - 1) + if (err || max_ptes_swap > COLLAPSE_MAX_PTES_LIMIT) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; @@ -307,7 +308,7 @@ static ssize_t max_ptes_shared_store(struct kobject *kobj, unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); - if (err || max_ptes_shared > HPAGE_PMD_NR - 1) + if (err || max_ptes_shared > COLLAPSE_MAX_PTES_LIMIT) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; @@ -379,7 +380,7 @@ int __init khugepaged_init(void) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; - khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; + khugepaged_max_ptes_none = COLLAPSE_MAX_PTES_LIMIT; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; -- 2.53.0 The hpage_collapse functions describe functions used by madvise_collapse and khugepaged. remove the unnecessary hpage prefix to shorten the function name. Reviewed-by: Wei Yang Reviewed-by: Lance Yang Reviewed-by: Liam R. Howlett Reviewed-by: Zi Yan Reviewed-by: Baolin Wang Reviewed-by: Lorenzo Stoakes Acked-by: David Hildenbrand (Arm) Signed-off-by: Nico Pache --- mm/khugepaged.c | 71 +++++++++++++++++++++++-------------------------- mm/mremap.c | 2 +- 2 files changed, 35 insertions(+), 38 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 4615f34911d1..64086488ca01 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -392,14 +392,14 @@ void __init khugepaged_destroy(void) kmem_cache_destroy(mm_slot_cache); } -static inline int hpage_collapse_test_exit(struct mm_struct *mm) +static inline int collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } -static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) +static inline int collapse_test_exit_or_disable(struct mm_struct *mm) { - return hpage_collapse_test_exit(mm) || + return collapse_test_exit(mm) || mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm); } @@ -433,7 +433,7 @@ void __khugepaged_enter(struct mm_struct *mm) int wakeup; /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); + VM_BUG_ON_MM(collapse_test_exit(mm), mm); if (unlikely(mm_flags_test_and_set(MMF_VM_HUGEPAGE, mm))) return; @@ -487,7 +487,7 @@ void __khugepaged_exit(struct mm_struct *mm) } else if (slot) { /* * This is required to serialize against - * hpage_collapse_test_exit() (which is guaranteed to run + * collapse_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_lock. @@ -582,7 +582,7 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } - /* See hpage_collapse_scan_pmd(). */ + /* See collapse_scan_pmd(). */ if (folio_maybe_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && @@ -833,7 +833,7 @@ static struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; -static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) +static bool collapse_scan_abort(int nid, struct collapse_control *cc) { int i; @@ -868,7 +868,7 @@ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) } #ifdef CONFIG_NUMA -static int hpage_collapse_find_target_node(struct collapse_control *cc) +static int collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; @@ -887,7 +887,7 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) return target_node; } #else -static int hpage_collapse_find_target_node(struct collapse_control *cc) +static int collapse_find_target_node(struct collapse_control *cc) { return 0; } @@ -906,7 +906,7 @@ static enum scan_result hugepage_vma_revalidate(struct mm_struct *mm, unsigned l enum tva_type type = cc->is_khugepaged ? TVA_KHUGEPAGED : TVA_FORCED_COLLAPSE; - if (unlikely(hpage_collapse_test_exit_or_disable(mm))) + if (unlikely(collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); @@ -977,7 +977,7 @@ static enum scan_result check_pmd_still_valid(struct mm_struct *mm, /* * Bring missing pages in from swap, to complete THP collapse. - * Only done if hpage_collapse_scan_pmd believes it is worthwhile. + * Only done if khugepaged_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. @@ -1063,7 +1063,7 @@ static enum scan_result alloc_charge_folio(struct folio **foliop, struct mm_stru { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); - int node = hpage_collapse_find_target_node(cc); + int node = collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); @@ -1241,10 +1241,9 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a return result; } -static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long start_addr, - bool *mmap_locked, unsigned int *cur_progress, - struct collapse_control *cc) +static enum scan_result collapse_scan_pmd(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long start_addr, bool *mmap_locked, + unsigned int *cur_progress, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; @@ -1366,7 +1365,7 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm, * hit record. */ node = folio_nid(folio); - if (hpage_collapse_scan_abort(node, cc)) { + if (collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } @@ -1432,7 +1431,7 @@ static void collect_mm_slot(struct mm_slot *slot) lockdep_assert_held(&khugepaged_mm_lock); - if (hpage_collapse_test_exit(mm)) { + if (collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); @@ -1787,7 +1786,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; - if (hpage_collapse_test_exit(mm)) + if (collapse_test_exit(mm)) continue; if (!file_backed_vma_is_retractable(vma)) @@ -2305,9 +2304,9 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, return result; } -static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, - unsigned long addr, struct file *file, pgoff_t start, - unsigned int *cur_progress, struct collapse_control *cc) +static enum scan_result collapse_scan_file(struct mm_struct *mm, unsigned long addr, + struct file *file, pgoff_t start, unsigned int *cur_progress, + struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; @@ -2362,7 +2361,7 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, } node = folio_nid(folio); - if (hpage_collapse_scan_abort(node, cc)) { + if (collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; folio_put(folio); break; @@ -2418,7 +2417,7 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, return result; } -static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result *result, +static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) @@ -2453,7 +2452,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result goto breakouterloop_mmap_lock; progress++; - if (unlikely(hpage_collapse_test_exit_or_disable(mm))) + if (unlikely(collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); @@ -2461,7 +2460,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result unsigned long hstart, hend; cond_resched(); - if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { + if (unlikely(collapse_test_exit_or_disable(mm))) { progress++; break; } @@ -2484,7 +2483,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result unsigned int cur_progress = 0; cond_resched(); - if (unlikely(hpage_collapse_test_exit_or_disable(mm))) + if (unlikely(collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || @@ -2497,13 +2496,13 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result mmap_read_unlock(mm); mmap_locked = false; - *result = hpage_collapse_scan_file(mm, + *result = collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, &cur_progress, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); - if (hpage_collapse_test_exit_or_disable(mm)) + if (collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = try_collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); @@ -2512,7 +2511,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result mmap_read_unlock(mm); } } else { - *result = hpage_collapse_scan_pmd(mm, vma, + *result = collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, &cur_progress, cc); } @@ -2546,7 +2545,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm, or THP got disabled. */ - if (hpage_collapse_test_exit_or_disable(mm) || !vma) { + if (collapse_test_exit_or_disable(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find @@ -2599,8 +2598,8 @@ static void khugepaged_do_scan(struct collapse_control *cc) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) - progress += khugepaged_scan_mm_slot(pages - progress, - &result, cc); + progress += collapse_scan_mm_slot(pages - progress, + &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); @@ -2844,8 +2843,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start, mmap_read_unlock(mm); mmap_locked = false; *lock_dropped = true; - result = hpage_collapse_scan_file(mm, addr, file, pgoff, - NULL, cc); + result = collapse_scan_file(mm, addr, file, pgoff, NULL, cc); if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !triggered_wb && mapping_can_writeback(file->f_mapping)) { @@ -2859,8 +2857,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start, } fput(file); } else { - result = hpage_collapse_scan_pmd(mm, vma, addr, - &mmap_locked, NULL, cc); + result = collapse_scan_pmd(mm, vma, addr, &mmap_locked, NULL, cc); } if (!mmap_locked) *lock_dropped = true; diff --git a/mm/mremap.c b/mm/mremap.c index 2be876a70cc0..eb222af91c2d 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -244,7 +244,7 @@ static int move_ptes(struct pagetable_move_control *pmc, goto out; } /* - * Now new_pte is none, so hpage_collapse_scan_file() path can not find + * Now new_pte is none, so collapse_scan_file() path can not find * this by traversing file->f_mapping, so there is no concurrency with * retract_page_tables(). In addition, we already hold the exclusive * mmap_lock, so this new_pte page is stable, so there is no need to get -- 2.53.0 The khugepaged daemon and madvise_collapse have two different implementations that do almost the same thing. Create collapse_single_pmd to increase code reuse and create an entry point to these two users. Refactor madvise_collapse and collapse_scan_mm_slot to use the new collapse_single_pmd function. This introduces a minor behavioral change that is most likely an undiscovered bug. The current implementation of khugepaged tests collapse_test_exit_or_disable before calling collapse_pte_mapped_thp, but we weren't doing it in the madvise_collapse case. By unifying these two callers madvise_collapse now also performs this check. We also modify the return value to be SCAN_ANY_PROCESS which properly indicates that this process is no longer valid to operate on. We also guard the khugepaged_pages_collapsed variable to ensure its only incremented for khugepaged. Reviewed-by: Lorenzo Stoakes Signed-off-by: Nico Pache --- mm/khugepaged.c | 128 ++++++++++++++++++++++++++---------------------- 1 file changed, 69 insertions(+), 59 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 64086488ca01..0058970d4579 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2417,6 +2417,70 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm, unsigned long a return result; } +/* + * Try to collapse a single PMD starting at a PMD aligned addr, and return + * the results. + */ +static enum scan_result collapse_single_pmd(unsigned long addr, + struct vm_area_struct *vma, bool *mmap_locked, + unsigned int *cur_progress, struct collapse_control *cc) +{ + struct mm_struct *mm = vma->vm_mm; + bool triggered_wb = false; + enum scan_result result; + struct file *file; + pgoff_t pgoff; + + if (vma_is_anonymous(vma)) { + result = collapse_scan_pmd(mm, vma, addr, mmap_locked, cur_progress, cc); + goto end; + } + + file = get_file(vma->vm_file); + pgoff = linear_page_index(vma, addr); + + mmap_read_unlock(mm); + *mmap_locked = false; +retry: + result = collapse_scan_file(mm, addr, file, pgoff, cur_progress, cc); + + /* + * For MADV_COLLAPSE, when encountering dirty pages, try to writeback, + * then retry the collapse one time. + */ + if (!cc->is_khugepaged && result == SCAN_PAGE_DIRTY_OR_WRITEBACK && + triggered_wb && mapping_can_writeback(file->f_mapping)) { + const loff_t lstart = (loff_t)pgoff << PAGE_SHIFT; + const loff_t lend = lstart + HPAGE_PMD_SIZE - 1; + + filemap_write_and_wait_range(file->f_mapping, lstart, lend); + triggered_wb = true; + goto retry; + } + fput(file); + + if (result != SCAN_PTE_MAPPED_HUGEPAGE) + goto end; + + mmap_read_lock(mm); + *mmap_locked = true; + if (collapse_test_exit_or_disable(mm)) { + mmap_read_unlock(mm); + *mmap_locked = false; + return SCAN_ANY_PROCESS; + } + result = try_collapse_pte_mapped_thp(mm, addr, !cc->is_khugepaged); + if (result == SCAN_PMD_MAPPED) + result = SCAN_SUCCEED; + mmap_read_unlock(mm); + *mmap_locked = false; + +end: + if (cc->is_khugepaged && result == SCAN_SUCCEED) + ++khugepaged_pages_collapsed; + return result; +} + static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) @@ -2489,36 +2553,9 @@ static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result * VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); - if (!vma_is_anonymous(vma)) { - struct file *file = get_file(vma->vm_file); - pgoff_t pgoff = linear_page_index(vma, - khugepaged_scan.address); - - mmap_read_unlock(mm); - mmap_locked = false; - *result = collapse_scan_file(mm, - khugepaged_scan.address, file, pgoff, - &cur_progress, cc); - fput(file); - if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { - mmap_read_lock(mm); - if (collapse_test_exit_or_disable(mm)) - goto breakouterloop; - *result = try_collapse_pte_mapped_thp(mm, - khugepaged_scan.address, false); - if (*result == SCAN_PMD_MAPPED) - *result = SCAN_SUCCEED; - mmap_read_unlock(mm); - } - } else { - *result = collapse_scan_pmd(mm, vma, - khugepaged_scan.address, &mmap_locked, - &cur_progress, cc); - } - - if (*result == SCAN_SUCCEED) - ++khugepaged_pages_collapsed; + *result = collapse_single_pmd(khugepaged_scan.address, + vma, &mmap_locked, &cur_progress, cc); /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += cur_progress; @@ -2819,13 +2856,12 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start, for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { enum scan_result result = SCAN_FAIL; - bool triggered_wb = false; -retry: if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; + *lock_dropped = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { @@ -2836,46 +2872,20 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start, hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); - if (!vma_is_anonymous(vma)) { - struct file *file = get_file(vma->vm_file); - pgoff_t pgoff = linear_page_index(vma, addr); - - mmap_read_unlock(mm); - mmap_locked = false; - *lock_dropped = true; - result = collapse_scan_file(mm, addr, file, pgoff, NULL, cc); - if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !triggered_wb && - mapping_can_writeback(file->f_mapping)) { - loff_t lstart = (loff_t)pgoff << PAGE_SHIFT; - loff_t lend = lstart + HPAGE_PMD_SIZE - 1; + result = collapse_single_pmd(addr, vma, &mmap_locked, NULL, cc); - filemap_write_and_wait_range(file->f_mapping, lstart, lend); - triggered_wb = true; - fput(file); - goto retry; - } - fput(file); - } else { - result = collapse_scan_pmd(mm, vma, addr, &mmap_locked, NULL, cc); - } if (!mmap_locked) *lock_dropped = true; -handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; - case SCAN_PTE_MAPPED_HUGEPAGE: - BUG_ON(mmap_locked); - mmap_read_lock(mm); - result = try_collapse_pte_mapped_thp(mm, addr, true); - mmap_read_unlock(mm); - goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_NO_PTE_TABLE: + case SCAN_PTE_MAPPED_HUGEPAGE: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_LACK_REFERENCED_PAGE: -- 2.53.0