diff options
Diffstat (limited to 'mm/rmap.c')
-rw-r--r-- | mm/rmap.c | 127 |
1 files changed, 94 insertions, 33 deletions
diff --git a/mm/rmap.c b/mm/rmap.c index c1286d47aa1f..b874c4761e84 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -63,6 +63,7 @@ #include <linux/hugetlb.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> +#include <linux/memremap.h> #include <asm/tlbflush.h> @@ -390,7 +391,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ - if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { + if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->degree--; continue; } @@ -424,7 +425,7 @@ static void anon_vma_ctor(void *data) init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); - anon_vma->rb_root = RB_ROOT; + anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) @@ -887,11 +888,21 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, .address = address, .flags = PVMW_SYNC, }; + unsigned long start = address, end; int *cleaned = arg; - bool invalidation_needed = false; + + /* + * We have to assume the worse case ie pmd for invalidation. Note that + * the page can not be free from this function. + */ + end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { + unsigned long cstart, cend; int ret = 0; + + cstart = address = pvmw.address; if (pvmw.pte) { pte_t entry; pte_t *pte = pvmw.pte; @@ -899,11 +910,12 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pte_dirty(*pte) && !pte_write(*pte)) continue; - flush_cache_page(vma, pvmw.address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, pvmw.address, pte); + flush_cache_page(vma, address, pte_pfn(*pte)); + entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); - set_pte_at(vma->vm_mm, pvmw.address, pte, entry); + set_pte_at(vma->vm_mm, address, pte, entry); + cend = cstart + PAGE_SIZE; ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE @@ -913,11 +925,13 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; - flush_cache_page(vma, pvmw.address, page_to_pfn(page)); - entry = pmdp_huge_clear_flush(vma, pvmw.address, pmd); + flush_cache_page(vma, address, page_to_pfn(page)); + entry = pmdp_huge_clear_flush(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); - set_pmd_at(vma->vm_mm, pvmw.address, pmd, entry); + set_pmd_at(vma->vm_mm, address, pmd, entry); + cstart &= PMD_MASK; + cend = cstart + PMD_SIZE; ret = 1; #else /* unexpected pmd-mapped page? */ @@ -926,15 +940,12 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, } if (ret) { + mmu_notifier_invalidate_range(vma->vm_mm, cstart, cend); (*cleaned)++; - invalidation_needed = true; } } - if (invalidation_needed) { - mmu_notifier_invalidate_range(vma->vm_mm, address, - address + (1UL << compound_order(page))); - } + mmu_notifier_invalidate_range_end(vma->vm_mm, start, end); return true; } @@ -1328,19 +1339,45 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, }; pte_t pteval; struct page *subpage; - bool ret = true, invalidation_needed = false; + bool ret = true; + unsigned long start = address, end; enum ttu_flags flags = (enum ttu_flags)arg; /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; + if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && + is_zone_device_page(page) && !is_device_private_page(page)) + return true; + if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_address(vma, address, - flags & TTU_MIGRATION, page); + flags & TTU_SPLIT_FREEZE, page); } + /* + * We have to assume the worse case ie pmd for invalidation. Note that + * the page can not be free in this function as call of try_to_unmap() + * must hold a reference on the page. + */ + end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); + while (page_vma_mapped_walk(&pvmw)) { +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + /* PMD-mapped THP migration entry */ + if (!pvmw.pte && (flags & TTU_MIGRATION)) { + VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); + + if (!PageAnon(page)) + continue; + + set_pmd_migration_entry(&pvmw, page); + continue; + } +#endif + /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced @@ -1368,9 +1405,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, VM_BUG_ON_PAGE(!pvmw.pte, page); subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + + if (IS_ENABLED(CONFIG_MIGRATION) && + (flags & TTU_MIGRATION) && + is_zone_device_page(page)) { + swp_entry_t entry; + pte_t swp_pte; + + pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + entry = make_migration_entry(page, 0); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + goto discard; + } if (!(flags & TTU_IGNORE_ACCESS)) { - if (ptep_clear_flush_young_notify(vma, pvmw.address, + if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { ret = false; page_vma_mapped_walk_done(&pvmw); @@ -1379,7 +1439,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* Nuke the page table entry. */ - flush_cache_page(vma, pvmw.address, pte_pfn(*pvmw.pte)); + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially @@ -1389,12 +1449,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ - pteval = ptep_get_and_clear(mm, pvmw.address, - pvmw.pte); + pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { - pteval = ptep_clear_flush(vma, pvmw.address, pvmw.pte); + pteval = ptep_clear_flush(vma, address, pvmw.pte); } /* Move the dirty bit to the page. Now the pte is gone. */ @@ -1409,12 +1468,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHuge(page)) { int nr = 1 << compound_order(page); hugetlb_count_sub(nr, mm); - set_huge_swap_pte_at(mm, pvmw.address, + set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { dec_mm_counter(mm, mm_counter(page)); - set_pte_at(mm, pvmw.address, pvmw.pte, pteval); + set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval)) { @@ -1425,7 +1484,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, */ dec_mm_counter(mm, mm_counter(page)); } else if (IS_ENABLED(CONFIG_MIGRATION) && - (flags & TTU_MIGRATION)) { + (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { swp_entry_t entry; pte_t swp_pte; /* @@ -1438,7 +1497,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; @@ -1449,6 +1508,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { WARN_ON_ONCE(1); ret = false; + /* We have to invalidate as we cleared the pte */ page_vma_mapped_walk_done(&pvmw); break; } @@ -1464,7 +1524,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * If the page was redirtied, it cannot be * discarded. Remap the page to page table. */ - set_pte_at(mm, pvmw.address, pvmw.pte, pteval); + set_pte_at(mm, address, pvmw.pte, pteval); SetPageSwapBacked(page); ret = false; page_vma_mapped_walk_done(&pvmw); @@ -1472,7 +1532,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } if (swap_duplicate(entry) < 0) { - set_pte_at(mm, pvmw.address, pvmw.pte, pteval); + set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; @@ -1488,18 +1548,18 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); } else dec_mm_counter(mm, mm_counter_file(page)); discard: page_remove_rmap(subpage, PageHuge(page)); put_page(page); - invalidation_needed = true; + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); } - if (invalidation_needed) - mmu_notifier_invalidate_range(mm, address, - address + (1UL << compound_order(page))); + mmu_notifier_invalidate_range_end(vma->vm_mm, start, end); + return ret; } @@ -1554,7 +1614,8 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if ((flags & TTU_MIGRATION) && !PageKsm(page) && PageAnon(page)) + if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) + && !PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) |