diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 9baea23cace5b767fc53b83b0e4121809100be60..62cf42708667131179e6504353f7747522dd0c55 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1044,6 +1044,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, __ptep_set_wrprotect(mm, address, ptep); } +static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, cydp_t flags) +{ + pte_t old_pte; + + do { + old_pte = pte; + + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + + pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), + pte_val(old_pte), pte_val(pte)); + } while (pte_val(pte) != pte_val(old_pte)); +} + +static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + pte = __ptep_get(ptep); + + if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) + __set_pte(ptep, pte_mkclean(pte_mkold(pte))); + else + __clear_young_dirty_pte(vma, addr, ptep, pte, flags); + + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, @@ -1209,6 +1249,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); +extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -1433,6 +1476,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } +#define clear_young_dirty_ptes clear_young_dirty_ptes +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); + else + contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); +} + #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get @@ -1452,6 +1506,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags +#define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 1b64b4c3f8bf8af49d53d1d835ad9eaa3dda5407..a3edced29ac1383564f432139ed01def1913d28b 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -361,6 +361,35 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes); +void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + /* + * We can safely clear access/dirty without needing to unfold from + * the architectures perspective, even when contpte is set. If the + * range starts or ends midway through a contpte block, we can just + * expand to include the full contpte block. While this is not + * exactly what the core-mm asked for, it tracks access/dirty per + * folio, not per page. And since we only create a contpte block + * when it is covered by a single folio, we can get away with + * clearing access/dirty for the whole block. + */ + unsigned long start = addr; + unsigned long end = start + nr * PAGE_SIZE; + + if (pte_cont(__ptep_get(ptep + nr - 1))) + end = ALIGN(end, CONT_PTE_SIZE); + + if (pte_cont(__ptep_get(ptep))) { + start = ALIGN_DOWN(start, CONT_PTE_SIZE); + ptep = contpte_align_down(ptep); + } + + __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags); +} +EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); + int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index dc1ef76c8fc939458b5a53eda7cba522489ca661..a49e6d6aecbfb42fa84d269c6261f03c77fae5e6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1409,6 +1409,15 @@ enum fault_flag { typedef unsigned int __bitwise zap_flags_t; +/* Flags for clear_young_dirty_ptes(). */ +typedef int __bitwise cydp_t; + +/* Clear the access bit */ +#define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) + +/* Clear the dirty bit */ +#define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) + /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f18c56df9b7e6e96e6994d2a76e27a7e9eb59b7c..17805ee1cf24f57742951b70c7821782f6e2ac42 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -356,36 +356,6 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, } #endif -#ifndef mkold_ptes -/** - * mkold_ptes - Mark PTEs that map consecutive pages of the same folio as old. - * @vma: VMA the pages are mapped into. - * @addr: Address the first page is mapped at. - * @ptep: Page table pointer for the first entry. - * @nr: Number of entries to mark old. - * - * May be overridden by the architecture; otherwise, implemented as a simple - * loop over ptep_test_and_clear_young(). - * - * Note that PTE bits in the PTE range besides the PFN can differ. For example, - * some PTEs might be write-protected. - * - * Context: The caller holds the page table lock. The PTEs map consecutive - * pages that belong to the same folio. The PTEs are all in the same PMD. - */ -static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep, unsigned int nr) -{ - for (;;) { - ptep_test_and_clear_young(vma, addr, ptep); - if (--nr == 0) - break; - ptep++; - addr += PAGE_SIZE; - } -} -#endif - #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, @@ -484,6 +454,50 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef clear_young_dirty_ptes +/** + * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the + * same folio as old/clean. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old/clean. + * @flags: Flags to modify the PTE batch semantics. + * + * May be overridden by the architecture; otherwise, implemented by + * get_and_clear/modify/set for each pte in the range. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + if (flags == CYDP_CLEAR_YOUNG) + ptep_test_and_clear_young(vma, addr, ptep); + else { + pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); + } + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/mm/internal.h b/mm/internal.h index 6cd124cd175a8c6764e63a8b7a503a8a1cfc5dac..b2ac97a81765d701f8ddd0fddb827050b9ac2e40 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -163,6 +163,8 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. + * @any_dirty: Optional pointer to indicate whether any entry except the + * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. @@ -178,18 +180,20 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, - bool *any_writable, bool *any_young) + bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; - bool writable, young; + bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; + if (any_dirty) + *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); @@ -205,6 +209,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); + if (any_dirty) + dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) @@ -222,6 +228,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, *any_writable |= writable; if (any_young) *any_young |= young; + if (any_dirty) + *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); diff --git a/mm/madvise.c b/mm/madvise.c index 4952ee49536935dc604186d175811e020ec6d2e8..7d64cf8d037bd2f49115e360e115ad0c2dace5a5 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -339,6 +339,18 @@ static inline bool can_do_file_pageout(struct vm_area_struct *vma) file_permission(vma->vm_file, MAY_WRITE) == 0; } +static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, + struct folio *folio, pte_t *ptep, + pte_t pte, bool *any_young, + bool *any_dirty) +{ + const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; + int max_nr = (end - addr) / PAGE_SIZE; + + return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, + any_young, any_dirty); +} + static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -462,13 +474,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, * next pte in the range. */ if (folio_test_large(folio)) { - const fpb_t fpb_flags = FPB_IGNORE_DIRTY | - FPB_IGNORE_SOFT_DIRTY; - int max_nr = (end - addr) / PAGE_SIZE; bool any_young; - nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, - fpb_flags, NULL, &any_young); + nr = madvise_folio_pte_batch(addr, end, folio, pte, + ptent, &any_young, NULL); if (any_young) ptent = pte_mkyoung(ptent); @@ -513,7 +522,8 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, continue; if (pte_young(ptent)) { - mkold_ptes(vma, addr, pte, nr); + clear_young_dirty_ptes(vma, addr, pte, nr, + CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } @@ -639,6 +649,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { + const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; @@ -693,44 +704,57 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, continue; /* - * If pmd isn't transhuge but the folio is large and - * is owned by only this process, split it and - * deactivate all pages. + * If we encounter a large folio, only split it if it is not + * fully mapped within the range we are operating on. Otherwise + * leave it as is so that it can be marked as lazyfree. If we + * fail to split a folio, leave it in place and advance to the + * next pte in the range. */ if (folio_test_large(folio)) { - int err; + bool any_young, any_dirty; - if (folio_likely_mapped_shared(folio)) - break; - if (!folio_trylock(folio)) - break; - folio_get(folio); - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(start_pte, ptl); - start_pte = NULL; - err = split_folio(folio); - folio_unlock(folio); - folio_put(folio); - if (err) - break; - start_pte = pte = - pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!start_pte) - break; - arch_enter_lazy_mmu_mode(); - pte--; - addr -= PAGE_SIZE; - continue; + nr = madvise_folio_pte_batch(addr, end, folio, pte, + ptent, &any_young, &any_dirty); + + if (nr < folio_nr_pages(folio)) { + int err; + + if (folio_likely_mapped_shared(folio)) + continue; + if (!folio_trylock(folio)) + continue; + folio_get(folio); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(start_pte, ptl); + start_pte = NULL; + err = split_folio(folio); + folio_unlock(folio); + folio_put(folio); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + start_pte = pte; + if (!start_pte) + break; + arch_enter_lazy_mmu_mode(); + if (!err) + nr = 0; + continue; + } + + if (any_young) + ptent = pte_mkyoung(ptent); + if (any_dirty) + ptent = pte_mkdirty(ptent); } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* - * If folio is shared with others, we mustn't clear - * the folio's dirty flag. + * If we have a large folio at this point, we know it is + * fully mapped so if its mapcount is the same as its + * number of pages, it must be exclusive. */ - if (folio_mapcount(folio) != 1) { + if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } @@ -746,19 +770,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, } if (pte_young(ptent) || pte_dirty(ptent)) { - /* - * Some of architecture(ex, PPC) don't update TLB - * with set_pte_at and tlb_remove_tlb_entry so for - * the portability, remap the pte with old|clean - * after pte clearing. - */ - ptent = ptep_get_and_clear_full(mm, addr, pte, - tlb->fullmm); - - ptent = pte_mkold(ptent); - ptent = pte_mkclean(ptent); - set_pte_at(mm, addr, pte, ptent); - tlb_remove_tlb_entry(tlb, pte, addr); + clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); + tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } diff --git a/mm/memory.c b/mm/memory.c index 11ae72ce127307903ccdb8d7c9921823b48da25f..5f8e255a0edf5536901c90721db21826e7cacf6b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -990,7 +990,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma flags |= FPB_IGNORE_SOFT_DIRTY; nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags, - &any_writable, NULL); + &any_writable, NULL, NULL); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, @@ -1782,7 +1782,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags, - NULL, NULL); + NULL, NULL, NULL); zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush,