diff options
Diffstat (limited to 'mm/khugepaged.c')
| -rw-r--r-- | mm/khugepaged.c | 125 |
1 files changed, 72 insertions, 53 deletions
diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 2d0d58fb4e7f..3beb4ad2ee5e 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -88,7 +88,7 @@ static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 -static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); +static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __read_mostly; @@ -422,19 +422,17 @@ void __khugepaged_enter(struct mm_struct *mm) struct mm_slot *slot; int wakeup; + /* __khugepaged_exit() must not run from under us */ + VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); + if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) + return; + mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; - /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); - if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { - mm_slot_free(mm_slot_cache, mm_slot); - return; - } - spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* @@ -513,7 +511,7 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte, struct folio *folio, *tmp; while (--_pte >= pte) { - pte_t pteval = *_pte; + pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) @@ -557,7 +555,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { - pte_t pteval = *_pte; + pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; @@ -701,7 +699,7 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte, for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { - pteval = *_pte; + pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { @@ -799,7 +797,7 @@ static int __collapse_huge_page_copy(pte_t *pte, */ for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR; _pte++, page++, _address += PAGE_SIZE) { - pteval = *_pte; + pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, _address); continue; @@ -946,10 +944,6 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, return SCAN_SUCCEED; } -/* - * See pmd_trans_unstable() for how the result may change out from - * underneath us, even if we hold mmap_lock in read. - */ static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) @@ -961,11 +955,6 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm, return SCAN_PMD_NULL; pmde = pmdp_get_lockless(*pmd); - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* See comments in pmd_none_or_trans_huge_or_clear_bad() */ - barrier(); -#endif if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) @@ -998,9 +987,8 @@ static int check_pmd_still_valid(struct mm_struct *mm, * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. - * Note that if false is returned, mmap_lock will be released. + * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ - static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, @@ -1009,23 +997,37 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm, int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); + int result; + pte_t *pte = NULL; + spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, - .pgoff = linear_page_index(vma, haddr), + .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; - vmf.pte = pte_offset_map(pmd, address); - vmf.orig_pte = *vmf.pte; - if (!is_swap_pte(vmf.orig_pte)) { - pte_unmap(vmf.pte); - continue; + if (!pte++) { + pte = pte_offset_map_nolock(mm, pmd, address, &ptl); + if (!pte) { + mmap_read_unlock(mm); + result = SCAN_PMD_NULL; + goto out; + } } + + vmf.orig_pte = ptep_get_lockless(pte); + if (!is_swap_pte(vmf.orig_pte)) + continue; + + vmf.pte = pte; + vmf.ptl = ptl; ret = do_swap_page(&vmf); + /* Which unmaps pte (after perhaps re-checking the entry) */ + pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. @@ -1034,24 +1036,29 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm, * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { - trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); /* Likely, but not guaranteed, that page lock failed */ - return SCAN_PAGE_LOCK; + result = SCAN_PAGE_LOCK; + goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); - trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); - return SCAN_FAIL; + result = SCAN_FAIL; + goto out; } swapped_in++; } - /* Drain LRU add pagevec to remove extra pin on the swapped in pages */ + if (pte) + pte_unmap(pte); + + /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); - trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1); - return SCAN_SUCCEED; + result = SCAN_SUCCEED; +out: + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); + return result; } static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, @@ -1151,9 +1158,6 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow @@ -1168,13 +1172,18 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); - spin_lock(pte_ptl); - result = __collapse_huge_page_isolate(vma, address, pte, cc, - &compound_pagelist); - spin_unlock(pte_ptl); + pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); + if (pte) { + result = __collapse_huge_page_isolate(vma, address, pte, cc, + &compound_pagelist); + spin_unlock(pte_ptl); + } else { + result = SCAN_PMD_NULL; + } if (unlikely(result != SCAN_SUCCEED)) { - pte_unmap(pte); + if (pte) + pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* @@ -1258,9 +1267,14 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!pte) { + result = SCAN_PMD_NULL; + goto out; + } + for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { - pte_t pteval = *_pte; + pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || @@ -1627,25 +1641,28 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * lockless_pages_from_mm() and the hardware page walker can access page * tables while all the high-level locks are held in write mode. */ - start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); result = SCAN_FAIL; + start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); + if (!start_pte) + goto drop_immap; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; + pte_t ptent = ptep_get(pte); /* empty pte, skip */ - if (pte_none(*pte)) + if (pte_none(ptent)) continue; /* page swapped out, abort */ - if (!pte_present(*pte)) { + if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } - page = vm_normal_page(vma, addr, *pte); + page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* @@ -1661,10 +1678,11 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; + pte_t ptent = ptep_get(pte); - if (pte_none(*pte)) + if (pte_none(ptent)) continue; - page = vm_normal_page(vma, addr, *pte); + page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) goto abort; page_remove_rmap(page, vma, false); @@ -1702,6 +1720,7 @@ drop_hpage: abort: pte_unmap_unlock(start_pte, ptl); +drop_immap: i_mmap_unlock_write(vma->vm_file->f_mapping); goto drop_hpage; } @@ -1953,7 +1972,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, result = SCAN_FAIL; goto xa_unlocked; } - /* drain pagevecs to help isolate_lru_page() */ + /* drain lru cache to help isolate_lru_page() */ lru_add_drain(); page = folio_file_page(folio, index); } else if (trylock_page(page)) { @@ -1969,7 +1988,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); - /* drain pagevecs to help isolate_lru_page() */ + /* drain lru cache to help isolate_lru_page() */ lru_add_drain(); page = find_lock_page(mapping, index); if (unlikely(page == NULL)) { |