From 6a8e0596f00469c15ec556b9f3624acd2e9a04f9 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:10 -0700 Subject: mm: rmap: introduce pfn_mkclean_range() to cleans PTEs The page_mkclean_one() is supposed to be used with the pfn that has a associated struct page, but not all the pfns (e.g. DAX) have a struct page. Introduce a new function pfn_mkclean_range() to cleans the PTEs (including PMDs) mapped with range of pfns which has no struct page associated with them. This helper will be used by DAX device in the next patch to make pfns clean. Link: https://lkml.kernel.org/r/20220403053957.10770-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alistair Popple Cc: Al Viro Cc: Christoph Hellwig Cc: Dan Williams Cc: Hugh Dickins Cc: Jan Kara Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Ross Zwisler Cc: Xiongchun Duan Cc: Xiyu Yang Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 17230c458341..8573aae50d96 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -261,6 +261,9 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); +int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, + struct vm_area_struct *vma); + void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* -- cgit v1.2.3 From fb3d824d1a46c5bb0584ea88f32dc2495544aebf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap() ... and move the special check for pinned pages into page_try_dup_anon_rmap() to prepare for tracking exclusive anonymous pages via a new pageflag, clearing it only after making sure that there are no GUP pins on the anonymous page. We really only care about pins on anonymous pages, because they are prone to getting replaced in the COW handler once mapped R/O. For !anon pages in cow-mappings (!VM_SHARED && VM_MAYWRITE) we shouldn't really care about that, at least not that I could come up with an example. Let's drop the is_cow_mapping() check from page_needs_cow_for_dma(), as we know we're dealing with anonymous pages. Also, drop the handling of pinned pages from copy_huge_pud() and add a comment if ever supporting anonymous pages on the PUD level. This is a preparation for tracking exclusivity of anonymous pages in the rmap code, and disallowing marking a page shared (-> failing to duplicate) if there are GUP pins on a page. Link: https://lkml.kernel.org/r/20220428083441.37290-5-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 5 +---- include/linux/rmap.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- mm/huge_memory.c | 27 ++++++++------------------- mm/hugetlb.c | 16 +++++++++------- mm/memory.c | 17 ++++++++++++----- mm/migrate.c | 2 +- 6 files changed, 79 insertions(+), 37 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index a02812178562..9ee3ae51e8e3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1575,16 +1575,13 @@ static inline bool page_maybe_dma_pinned(struct page *page) /* * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. + * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) { - if (!is_cow_mapping(vma->vm_flags)) - return false; - VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8573aae50d96..73f41544084f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -12,6 +12,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -182,11 +183,57 @@ void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); -static inline void page_dup_rmap(struct page *page, bool compound) +static inline void __page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } +static inline void page_dup_file_rmap(struct page *page, bool compound) +{ + __page_dup_rmap(page, compound); +} + +/** + * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped + * anonymous page + * @page: the page to duplicate the mapping for + * @compound: the page is mapped as compound or as a small page + * @vma: the source vma + * + * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq. + * + * Duplicating the mapping can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * If duplicating the mapping succeeds, the page has to be mapped R/O into + * the parent and the child. It must *not* get mapped writable after this call. + * + * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + */ +static inline int page_try_dup_anon_rmap(struct page *page, bool compound, + struct vm_area_struct *vma) +{ + VM_BUG_ON_PAGE(!PageAnon(page), page); + + /* + * If this page may have been pinned by the parent process, + * don't allow to duplicate the mapping but instead require to e.g., + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future on write faults. + */ + if (likely(!is_device_private_page(page) && + unlikely(page_needs_cow_for_dma(vma, page)))) + return -EBUSY; + + /* + * It's okay to share the anon page between both processes, mapping + * the page R/O into both processes. + */ + __page_dup_rmap(page, compound); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c468fee595ff..baf4ea6d8e1a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1097,23 +1097,16 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - /* - * If this page is a potentially pinned page, split and retry the fault - * with smaller page size. Normally this should not happen because the - * userspace should use MADV_DONTFORK upon pinned regions. This is a - * best effort that the pinned pages won't be replaced by another - * random page during the coming copy-on-write. - */ - if (unlikely(page_needs_cow_for_dma(src_vma, src_page))) { + get_page(src_page); + if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) { + /* Page maybe pinned: split and retry the fault on PTEs. */ + put_page(src_page); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); return -EAGAIN; } - - get_page(src_page); - page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); out_zero_page: mm_inc_nr_ptes(dst_mm); @@ -1217,14 +1210,10 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* No huge zero pud yet */ } - /* Please refer to comments in copy_huge_pmd() */ - if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) { - spin_unlock(src_ptl); - spin_unlock(dst_ptl); - __split_huge_pud(vma, src_pud, addr); - return -EAGAIN; - } - + /* + * TODO: once we support anonymous pages, use page_try_dup_anon_rmap() + * and split if duplicating fails. + */ pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); set_pud_at(dst_mm, addr, dst_pud, pud); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7389cd8a9a87..7a6052a984e9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4806,15 +4806,18 @@ again: get_page(ptepage); /* - * This is a rare case where we see pinned hugetlb - * pages while they're prone to COW. We need to do the - * COW earlier during fork. + * Failing to duplicate the anon rmap is a rare case + * where we see pinned hugetlb pages while they're + * prone to COW. We need to do the COW earlier during + * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ - if (unlikely(page_needs_cow_for_dma(vma, ptepage))) { + if (!PageAnon(ptepage)) { + page_dup_file_rmap(ptepage, true); + } else if (page_try_dup_anon_rmap(ptepage, true, vma)) { pte_t src_pte_old = entry; struct page *new; @@ -4861,7 +4864,6 @@ again: entry = huge_pte_wrprotect(entry); } - page_dup_rmap(ptepage, true); set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(npages, dst); } @@ -5541,7 +5543,7 @@ retry: ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, haddr, ptep, new_pte); @@ -5902,7 +5904,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_unlock; if (vm_shared) { - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); } else { ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); diff --git a/mm/memory.c b/mm/memory.c index 9bdfce15e98f..9f5f829a1b1f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -825,7 +825,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ get_page(page); rss[mm_counter(page)]++; - page_dup_rmap(page, false); + /* Cannot fail as these pages cannot get pinned. */ + BUG_ON(page_try_dup_anon_rmap(page, false, src_vma)); /* * We do not preserve soft-dirty information, because so @@ -921,18 +922,24 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, struct page *page; page = vm_normal_page(src_vma, addr, pte); - if (page && unlikely(page_needs_cow_for_dma(src_vma, page))) { + if (page && PageAnon(page)) { /* * If this page may have been pinned by the parent process, * copy the page immediately for the child so that we'll always * guarantee the pinned page won't be randomly replaced in the * future. */ - return copy_present_page(dst_vma, src_vma, dst_pte, src_pte, - addr, rss, prealloc, page); + get_page(page); + if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) { + /* Page maybe pinned, we have to copy. */ + put_page(page); + return copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, page); + } + rss[mm_counter(page)]++; } else if (page) { get_page(page); - page_dup_rmap(page, false); + page_dup_file_rmap(page, false); rss[mm_counter(page)]++; } diff --git a/mm/migrate.c b/mm/migrate.c index 77592288fbc0..6ca6e89ded94 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -234,7 +234,7 @@ static bool remove_migration_pte(struct folio *folio, if (folio_test_anon(folio)) hugepage_add_anon_rmap(new, vma, pvmw.address); else - page_dup_rmap(new, true); + page_dup_file_rmap(new, true); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } else #endif -- cgit v1.2.3 From 14f9135d547060d1d0c182501201f8da19895fe3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: convert RMAP flags to a proper distinct rmap_t type We want to pass the flags to more than one anon rmap function, getting rid of special "do_page_add_anon_rmap()". So let's pass around a distinct __bitwise type and refine documentation. Link: https://lkml.kernel.org/r/20220428083441.37290-6-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 22 ++++++++++++++++++---- mm/memory.c | 6 +++--- mm/rmap.c | 7 ++++--- 3 files changed, 25 insertions(+), 10 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 73f41544084f..c53a38151089 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -160,9 +160,23 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *page_get_anon_vma(struct page *page); -/* bitflags for do_page_add_anon_rmap() */ -#define RMAP_EXCLUSIVE 0x01 -#define RMAP_COMPOUND 0x02 +/* RMAP flags, currently only relevant for some anon rmap operations. */ +typedef int __bitwise rmap_t; + +/* + * No special request: if the page is a subpage of a compound page, it is + * mapped via a PTE. The mapped (sub)page is possibly shared between processes. + */ +#define RMAP_NONE ((__force rmap_t)0) + +/* The (sub)page is exclusive to a single process. */ +#define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) + +/* + * The compound page is not mapped via PTEs, but instead via a single PMD and + * should be accounted accordingly. + */ +#define RMAP_COMPOUND ((__force rmap_t)BIT(1)) /* * rmap interfaces called when adding or removing pte of page @@ -171,7 +185,7 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, int flags); + unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); void page_add_file_rmap(struct page *, struct vm_area_struct *, diff --git a/mm/memory.c b/mm/memory.c index 9f5f829a1b1f..4cd8cadf1268 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3511,10 +3511,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; struct swap_info_struct *si = NULL; + rmap_t rmap_flags = RMAP_NONE; swp_entry_t entry; pte_t pte; int locked; - int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; @@ -3689,7 +3689,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; - exclusive = RMAP_EXCLUSIVE; + rmap_flags |= RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) @@ -3705,7 +3705,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); + do_page_add_anon_rmap(page, vma, vmf->address, rmap_flags); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); diff --git a/mm/rmap.c b/mm/rmap.c index 91a63dc636ad..23a41132995e 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1181,7 +1181,8 @@ static void __page_check_anon_rmap(struct page *page, void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { - do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); + do_page_add_anon_rmap(page, vma, address, + compound ? RMAP_COMPOUND : RMAP_NONE); } /* @@ -1190,7 +1191,7 @@ void page_add_anon_rmap(struct page *page, * Everybody else should continue to use page_add_anon_rmap above. */ void do_page_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, int flags) + struct vm_area_struct *vma, unsigned long address, rmap_t flags) { bool compound = flags & RMAP_COMPOUND; bool first; @@ -1229,7 +1230,7 @@ void do_page_add_anon_rmap(struct page *page, /* address might be in next vma when migration races vma_adjust */ else if (first) __page_set_anon_rmap(page, vma, address, - flags & RMAP_EXCLUSIVE); + !!(flags & RMAP_EXCLUSIVE)); else __page_check_anon_rmap(page, vma, address); -- cgit v1.2.3 From f1e2db12e45baaa2d366f87c885968096c2ff5aa Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: remove do_page_add_anon_rmap() ... and instead convert page_add_anon_rmap() to accept flags. Passing flags instead of bools is usually nicer either way, and we want to more often also pass RMAP_EXCLUSIVE in follow up patches when detecting that an anonymous page is exclusive: for example, when restoring an anonymous page from a writable migration entry. This is a preparation for marking an anonymous page inside page_add_anon_rmap() as exclusive when RMAP_EXCLUSIVE is passed. Link: https://lkml.kernel.org/r/20220428083441.37290-7-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 -- mm/huge_memory.c | 2 +- mm/ksm.c | 2 +- mm/memory.c | 4 ++-- mm/migrate.c | 3 ++- mm/rmap.c | 14 +------------- mm/swapfile.c | 2 +- 7 files changed, 8 insertions(+), 21 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c53a38151089..643801a937f3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -183,8 +183,6 @@ typedef int __bitwise rmap_t; */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); -void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index baf4ea6d8e1a..6232b6817fab 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3072,7 +3072,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); if (PageAnon(new)) - page_add_anon_rmap(new, vma, mmun_start, true); + page_add_anon_rmap(new, vma, mmun_start, RMAP_COMPOUND); else page_add_file_rmap(new, vma, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); diff --git a/mm/ksm.c b/mm/ksm.c index 94bb0f049806..2b6692a7df6a 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1156,7 +1156,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, */ if (!is_zero_pfn(page_to_pfn(kpage))) { get_page(kpage); - page_add_anon_rmap(kpage, vma, addr, false); + page_add_anon_rmap(kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage), diff --git a/mm/memory.c b/mm/memory.c index 4cd8cadf1268..8e92010f3d89 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -725,7 +725,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, * created when the swap entry was made. */ if (PageAnon(page)) - page_add_anon_rmap(page, vma, address, false); + page_add_anon_rmap(page, vma, address, RMAP_NONE); else /* * Currently device exclusive access only supports anonymous @@ -3705,7 +3705,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, rmap_flags); + page_add_anon_rmap(page, vma, vmf->address, rmap_flags); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); diff --git a/mm/migrate.c b/mm/migrate.c index 6ca6e89ded94..381c7e05e8d4 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -240,7 +240,8 @@ static bool remove_migration_pte(struct folio *folio, #endif { if (folio_test_anon(folio)) - page_add_anon_rmap(new, vma, pvmw.address, false); + page_add_anon_rmap(new, vma, pvmw.address, + RMAP_NONE); else page_add_file_rmap(new, vma, false); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); diff --git a/mm/rmap.c b/mm/rmap.c index 23a41132995e..a0cbbf201c98 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1171,7 +1171,7 @@ static void __page_check_anon_rmap(struct page *page, * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped - * @compound: charge the page as compound or small page + * @flags: the rmap flags * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, @@ -1179,18 +1179,6 @@ static void __page_check_anon_rmap(struct page *page, * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, bool compound) -{ - do_page_add_anon_rmap(page, vma, address, - compound ? RMAP_COMPOUND : RMAP_NONE); -} - -/* - * Special version of the above for do_swap_page, which often runs - * into pages that are exclusively owned by the current process. - * Everybody else should continue to use page_add_anon_rmap above. - */ -void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { bool compound = flags & RMAP_COMPOUND; diff --git a/mm/swapfile.c b/mm/swapfile.c index 63c61f8b2611..1ba525a2179d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1800,7 +1800,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); if (page == swapcache) { - page_add_anon_rmap(page, vma, addr, false); + page_add_anon_rmap(page, vma, addr, RMAP_NONE); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_inactive_or_unevictable(page, vma); -- cgit v1.2.3 From 28c5209dfd5f86f4398ce01bfac8508b2c4d4050 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: pass rmap flags to hugepage_add_anon_rmap() Let's prepare for passing RMAP_EXCLUSIVE, similarly as we do for page_add_anon_rmap() now. RMAP_COMPOUND is implicit for hugetlb pages and ignored. Link: https://lkml.kernel.org/r/20220428083441.37290-8-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 +- mm/migrate.c | 3 ++- mm/rmap.c | 9 ++++++--- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 643801a937f3..90e1e6925789 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -191,7 +191,7 @@ void page_add_file_rmap(struct page *, struct vm_area_struct *, void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); diff --git a/mm/migrate.c b/mm/migrate.c index 381c7e05e8d4..92e932f08be5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -232,7 +232,8 @@ static bool remove_migration_pte(struct folio *folio, pte = pte_mkhuge(pte); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) - hugepage_add_anon_rmap(new, vma, pvmw.address); + hugepage_add_anon_rmap(new, vma, pvmw.address, + RMAP_NONE); else page_dup_file_rmap(new, true); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); diff --git a/mm/rmap.c b/mm/rmap.c index a0cbbf201c98..32630f1b1ee1 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2391,9 +2391,11 @@ void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc) * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. + * + * RMAP_COMPOUND is ignored. */ -void hugepage_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, + unsigned long address, rmap_t flags) { struct anon_vma *anon_vma = vma->anon_vma; int first; @@ -2403,7 +2405,8 @@ void hugepage_add_anon_rmap(struct page *page, /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(compound_mapcount_ptr(page)); if (first) - __page_set_anon_rmap(page, vma, address, 0); + __page_set_anon_rmap(page, vma, address, + !!(flags & RMAP_EXCLUSIVE)); } void hugepage_add_new_anon_rmap(struct page *page, -- cgit v1.2.3 From 40f2bbf71161fa9195c7869004290003af152375 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: drop "compound" parameter from page_add_new_anon_rmap() New anonymous pages are always mapped natively: only THP/khugepaged code maps a new compound anonymous page and passes "true". Otherwise, we're just dealing with simple, non-compound pages. Let's give the interface clearer semantics and document these. Remove the PageTransCompound() sanity check from page_add_new_anon_rmap(). Link: https://lkml.kernel.org/r/20220428083441.37290-9-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 3 ++- kernel/events/uprobes.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/memory.c | 10 +++++----- mm/migrate_device.c | 2 +- mm/rmap.c | 11 ++++++----- mm/swapfile.c | 2 +- mm/userfaultfd.c | 2 +- 9 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 90e1e6925789..e4156921eea9 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -185,11 +185,12 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); + unsigned long address); void page_add_file_rmap(struct page *, struct vm_area_struct *, bool compound); void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); + void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 6418083901d4..4ef5385815d3 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); - page_add_new_anon_rmap(new_page, vma, addr, false); + page_add_new_anon_rmap(new_page, vma, addr); lru_cache_add_inactive_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6232b6817fab..c0365280b481 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -647,7 +647,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr, true); + page_add_new_anon_rmap(page, vma, haddr); lru_cache_add_inactive_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ac53ad2c9bb1..a2560f970881 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1183,7 +1183,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address, true); + page_add_new_anon_rmap(new_page, vma, address); lru_cache_add_inactive_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); diff --git a/mm/memory.c b/mm/memory.c index 8e92010f3d89..3dedb575baef 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -893,7 +893,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); - page_add_new_anon_rmap(new_page, dst_vma, addr, false); + page_add_new_anon_rmap(new_page, dst_vma, addr); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; @@ -3058,7 +3058,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * some TLBs while the old PTE remains in others. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); + page_add_new_anon_rmap(new_page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -3702,7 +3702,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); + page_add_new_anon_rmap(page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(page, vma); } else { page_add_anon_rmap(page, vma, vmf->address, rmap_flags); @@ -3852,7 +3852,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); + page_add_new_anon_rmap(page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -4039,7 +4039,7 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 70c7dc05bbfc..fb6d7d5499f5 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -610,7 +610,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); if (!is_zone_device_page(page)) lru_cache_add_inactive_or_unevictable(page, vma); get_page(page); diff --git a/mm/rmap.c b/mm/rmap.c index 32630f1b1ee1..90f92c53476f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1226,19 +1226,22 @@ void page_add_anon_rmap(struct page *page, } /** - * page_add_new_anon_rmap - add pte mapping to a new anonymous page + * page_add_new_anon_rmap - add mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped - * @compound: charge the page as compound or small page + * + * If it's a compound page, it is accounted as a compound page. As the page + * is new, it's assume to get mapped exclusively by a single process. * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, bool compound) + struct vm_area_struct *vma, unsigned long address) { + const bool compound = PageCompound(page); int nr = compound ? thp_nr_pages(page) : 1; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); @@ -1251,8 +1254,6 @@ void page_add_new_anon_rmap(struct page *page, __mod_lruvec_page_state(page, NR_ANON_THPS, nr); } else { - /* Anon THP always mapped first with PMD */ - VM_BUG_ON_PAGE(PageTransCompound(page), page); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 1ba525a2179d..0ad7ed7ded21 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1802,7 +1802,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (page == swapcache) { page_add_anon_rmap(page, vma, addr, RMAP_NONE); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } set_pte_at(vma->vm_mm, addr, pte, diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index e9bb6db002aa..dae25d985d15 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -104,7 +104,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, lru_cache_add(page); page_add_file_rmap(page, dst_vma, false); } else { - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + page_add_new_anon_rmap(page, dst_vma, dst_addr); lru_cache_add_inactive_or_unevictable(page, dst_vma); } -- cgit v1.2.3 From 6c287605fd56466e645693eff3ae7c08fba56e0a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm: remember exclusively mapped anonymous pages with PG_anon_exclusive Let's mark exclusively mapped anonymous pages with PG_anon_exclusive as exclusive, and use that information to make GUP pins reliable and stay consistent with the page mapped into the page table even if the page table entry gets write-protected. With that information at hand, we can extend our COW logic to always reuse anonymous pages that are exclusive. For anonymous pages that might be shared, the existing logic applies. As already documented, PG_anon_exclusive is usually only expressive in combination with a page table entry. Especially PTE vs. PMD-mapped anonymous pages require more thought, some examples: due to mremap() we can easily have a single compound page PTE-mapped into multiple page tables exclusively in a single process -- multiple page table locks apply. Further, due to MADV_WIPEONFORK we might not necessarily write-protect all PTEs, and only some subpages might be pinned. Long story short: once PTE-mapped, we have to track information about exclusivity per sub-page, but until then, we can just track it for the compound page in the head page and not having to update a whole bunch of subpages all of the time for a simple PMD mapping of a THP. For simplicity, this commit mostly talks about "anonymous pages", while it's for THP actually "the part of an anonymous folio referenced via a page table entry". To not spill PG_anon_exclusive code all over the mm code-base, we let the anon rmap code to handle all PG_anon_exclusive logic it can easily handle. If a writable, present page table entry points at an anonymous (sub)page, that (sub)page must be PG_anon_exclusive. If GUP wants to take a reliably pin (FOLL_PIN) on an anonymous page references via a present page table entry, it must only pin if PG_anon_exclusive is set for the mapped (sub)page. This commit doesn't adjust GUP, so this is only implicitly handled for FOLL_WRITE, follow-up commits will teach GUP to also respect it for FOLL_PIN without FOLL_WRITE, to make all GUP pins of anonymous pages fully reliable. Whenever an anonymous page is to be shared (fork(), KSM), or when temporarily unmapping an anonymous page (swap, migration), the relevant PG_anon_exclusive bit has to be cleared to mark the anonymous page possibly shared. Clearing will fail if there are GUP pins on the page: * For fork(), this means having to copy the page and not being able to share it. fork() protects against concurrent GUP using the PT lock and the src_mm->write_protect_seq. * For KSM, this means sharing will fail. For swap this means, unmapping will fail, For migration this means, migration will fail early. All three cases protect against concurrent GUP using the PT lock and a proper clear/invalidate+flush of the relevant page table entry. This fixes memory corruptions reported for FOLL_PIN | FOLL_WRITE, when a pinned page gets mapped R/O and the successive write fault ends up replacing the page instead of reusing it. It improves the situation for O_DIRECT/vmsplice/... that still use FOLL_GET instead of FOLL_PIN, if fork() is *not* involved, however swapout and fork() are still problematic. Properly using FOLL_PIN instead of FOLL_GET for these GUP users will fix the issue for them. I. Details about basic handling I.1. Fresh anonymous pages page_add_new_anon_rmap() and hugepage_add_new_anon_rmap() will mark the given page exclusive via __page_set_anon_rmap(exclusive=1). As that is the mechanism fresh anonymous pages come into life (besides migration code where we copy the page->mapping), all fresh anonymous pages will start out as exclusive. I.2. COW reuse handling of anonymous pages When a COW handler stumbles over a (sub)page that's marked exclusive, it simply reuses it. Otherwise, the handler tries harder under page lock to detect if the (sub)page is exclusive and can be reused. If exclusive, page_move_anon_rmap() will mark the given (sub)page exclusive. Note that hugetlb code does not yet check for PageAnonExclusive(), as it still uses the old COW logic that is prone to the COW security issue because hugetlb code cannot really tolerate unnecessary/wrong COW as huge pages are a scarce resource. I.3. Migration handling try_to_migrate() has to try marking an exclusive anonymous page shared via page_try_share_anon_rmap(). If it fails because there are GUP pins on the page, unmap fails. migrate_vma_collect_pmd() and __split_huge_pmd_locked() are handled similarly. Writable migration entries implicitly point at shared anonymous pages. For readable migration entries that information is stored via a new "readable-exclusive" migration entry, specific to anonymous pages. When restoring a migration entry in remove_migration_pte(), information about exlusivity is detected via the migration entry type, and RMAP_EXCLUSIVE is set accordingly for page_add_anon_rmap()/hugepage_add_anon_rmap() to restore that information. I.4. Swapout handling try_to_unmap() has to try marking the mapped page possibly shared via page_try_share_anon_rmap(). If it fails because there are GUP pins on the page, unmap fails. For now, information about exclusivity is lost. In the future, we might want to remember that information in the swap entry in some cases, however, it requires more thought, care, and a way to store that information in swap entries. I.5. Swapin handling do_swap_page() will never stumble over exclusive anonymous pages in the swap cache, as try_to_migrate() prohibits that. do_swap_page() always has to detect manually if an anonymous page is exclusive and has to set RMAP_EXCLUSIVE for page_add_anon_rmap() accordingly. I.6. THP handling __split_huge_pmd_locked() has to move the information about exclusivity from the PMD to the PTEs. a) In case we have a readable-exclusive PMD migration entry, simply insert readable-exclusive PTE migration entries. b) In case we have a present PMD entry and we don't want to freeze ("convert to migration entries"), simply forward PG_anon_exclusive to all sub-pages, no need to temporarily clear the bit. c) In case we have a present PMD entry and want to freeze, handle it similar to try_to_migrate(): try marking the page shared first. In case we fail, we ignore the "freeze" instruction and simply split ordinarily. try_to_migrate() will properly fail because the THP is still mapped via PTEs. When splitting a compound anonymous folio (THP), the information about exclusivity is implicitly handled via the migration entries: no need to replicate PG_anon_exclusive manually. I.7. fork() handling fork() handling is relatively easy, because PG_anon_exclusive is only expressive for some page table entry types. a) Present anonymous pages page_try_dup_anon_rmap() will mark the given subpage shared -- which will fail if the page is pinned. If it failed, we have to copy (or PTE-map a PMD to handle it on the PTE level). Note that device exclusive entries are just a pointer at a PageAnon() page. fork() will first convert a device exclusive entry to a present page table and handle it just like present anonymous pages. b) Device private entry Device private entries point at PageAnon() pages that cannot be mapped directly and, therefore, cannot get pinned. page_try_dup_anon_rmap() will mark the given subpage shared, which cannot fail because they cannot get pinned. c) HW poison entries PG_anon_exclusive will remain untouched and is stale -- the page table entry is just a placeholder after all. d) Migration entries Writable and readable-exclusive entries are converted to readable entries: possibly shared. I.8. mprotect() handling mprotect() only has to properly handle the new readable-exclusive migration entry: When write-protecting a migration entry that points at an anonymous page, remember the information about exclusivity via the "readable-exclusive" migration entry type. II. Migration and GUP-fast Whenever replacing a present page table entry that maps an exclusive anonymous page by a migration entry, we have to mark the page possibly shared and synchronize against GUP-fast by a proper clear/invalidate+flush to make the following scenario impossible: 1. try_to_migrate() places a migration entry after checking for GUP pins and marks the page possibly shared. 2. GUP-fast pins the page due to lack of synchronization 3. fork() converts the "writable/readable-exclusive" migration entry into a readable migration entry 4. Migration fails due to the GUP pin (failing to freeze the refcount) 5. Migration entries are restored. PG_anon_exclusive is lost -> We have a pinned page that is not marked exclusive anymore. Note that we move information about exclusivity from the page to the migration entry as it otherwise highly overcomplicates fork() and PTE-mapping a THP. III. Swapout and GUP-fast Whenever replacing a present page table entry that maps an exclusive anonymous page by a swap entry, we have to mark the page possibly shared and synchronize against GUP-fast by a proper clear/invalidate+flush to make the following scenario impossible: 1. try_to_unmap() places a swap entry after checking for GUP pins and clears exclusivity information on the page. 2. GUP-fast pins the page due to lack of synchronization. -> We have a pinned page that is not marked exclusive anymore. If we'd ever store information about exclusivity in the swap entry, similar to migration handling, the same considerations as in II would apply. This is future work. Link: https://lkml.kernel.org/r/20220428083441.37290-13-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 40 +++++++++++++++++++++++++ include/linux/swap.h | 15 +++++++--- include/linux/swapops.h | 25 ++++++++++++++++ mm/huge_memory.c | 78 ++++++++++++++++++++++++++++++++++++++++++++----- mm/hugetlb.c | 15 +++++++--- mm/ksm.c | 13 ++++++++- mm/memory.c | 33 ++++++++++++++++----- mm/migrate.c | 14 +++++++-- mm/migrate_device.c | 21 ++++++++++++- mm/mprotect.c | 8 +++-- mm/rmap.c | 61 ++++++++++++++++++++++++++++++++++---- 11 files changed, 289 insertions(+), 34 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e4156921eea9..cbe279a6f0de 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -228,6 +228,13 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, { VM_BUG_ON_PAGE(!PageAnon(page), page); + /* + * No need to check+clear for already shared pages, including KSM + * pages. + */ + if (!PageAnonExclusive(page)) + goto dup; + /* * If this page may have been pinned by the parent process, * don't allow to duplicate the mapping but instead require to e.g., @@ -239,14 +246,47 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, unlikely(page_needs_cow_for_dma(vma, page)))) return -EBUSY; + ClearPageAnonExclusive(page); /* * It's okay to share the anon page between both processes, mapping * the page R/O into both processes. */ +dup: __page_dup_rmap(page, compound); return 0; } +/** + * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly + * shared to prepare for KSM or temporary unmapping + * @page: the exclusive anonymous page to try marking possibly shared + * + * The caller needs to hold the PT lock and has to have the page table entry + * cleared/invalidated+flushed, to properly sync against GUP-fast. + * + * This is similar to page_try_dup_anon_rmap(), however, not used during fork() + * to duplicate a mapping, but instead to prepare for KSM or temporarily + * unmapping a page (swap, migration) via page_remove_rmap(). + * + * Marking the page shared can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY + * otherwise. + */ +static inline int page_try_share_anon_rmap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); + + /* See page_try_dup_anon_rmap(). */ + if (likely(!is_device_private_page(page) && + unlikely(page_maybe_dma_pinned(page)))) + return -EBUSY; + + ClearPageAnonExclusive(page); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 27093b477c5f..e6d70a4156e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -78,12 +78,19 @@ static inline int current_is_kswapd(void) #endif /* - * NUMA node memory migration support + * Page migration support. + * + * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and + * indicates that the referenced (part of) an anonymous page is exclusive to + * a single process. For SWP_MIGRATION_WRITE, that information is implicit: + * (part of) an anonymous page that are mapped writable are exclusive to a + * single process. */ #ifdef CONFIG_MIGRATION -#define SWP_MIGRATION_NUM 2 -#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_NUM 3 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5af852b68805..6648b97244e7 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -194,6 +194,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || + swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } @@ -202,11 +203,26 @@ static inline int is_writable_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ); +} + +static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); +} + static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); @@ -224,6 +240,11 @@ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) return swp_entry(0, 0); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -244,6 +265,10 @@ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return 0; +} #endif diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cb5bcd833d9e..231911b7bf9d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1054,7 +1054,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); - if (is_writable_migration_entry(entry)) { + if (!is_readable_migration_entry(entry)) { entry = make_readable_migration_entry( swp_offset(entry)); pmd = swp_entry_to_pmd(entry); @@ -1292,6 +1292,10 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) page = pmd_page(orig_pmd); VM_BUG_ON_PAGE(!PageHead(page), page); + /* Early check when only holding the PT lock. */ + if (PageAnonExclusive(page)) + goto reuse; + if (!trylock_page(page)) { get_page(page); spin_unlock(vmf->ptl); @@ -1306,6 +1310,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) put_page(page); } + /* Recheck after temporarily dropping the PT lock. */ + if (PageAnonExclusive(page)) { + unlock_page(page); + goto reuse; + } + /* * See do_wp_page(): we can only map the page writable if there are * no additional references. Note that we always drain the LRU @@ -1319,11 +1329,12 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) pmd_t entry; page_move_anon_rmap(page, vma); + unlock_page(page); +reuse: entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - unlock_page(page); spin_unlock(vmf->ptl); return VM_FAULT_WRITE; } @@ -1708,6 +1719,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); + struct page *page = pfn_swap_entry_to_page(entry); VM_BUG_ON(!is_pmd_migration_entry(*pmd)); if (is_writable_migration_entry(entry)) { @@ -1716,8 +1728,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * A protection check is difficult so * just be safe and disable write */ - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry(swp_offset(entry)); + else + entry = make_readable_migration_entry(swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); @@ -1937,6 +1951,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable_t pgtable; pmd_t old_pmd, _pmd; bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; + bool anon_exclusive = false; unsigned long addr; int i; @@ -2018,6 +2033,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); + if (PageAnon(page)) + anon_exclusive = is_readable_exclusive_migration_entry(entry); young = false; soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); @@ -2029,8 +2046,26 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); uffd_wp = pmd_uffd_wp(old_pmd); + VM_BUG_ON_PAGE(!page_count(page), page); page_ref_add(page, HPAGE_PMD_NR - 1); + + /* + * Without "freeze", we'll simply split the PMD, propagating the + * PageAnonExclusive() flag for each PTE by setting it for + * each subpage -- no need to (temporarily) clear. + * + * With "freeze" we want to replace mapped pages by + * migration entries right away. This is only possible if we + * managed to clear PageAnonExclusive() -- see + * set_pmd_migration_entry(). + * + * In case we cannot clear PageAnonExclusive(), split the PMD + * only and let try_to_migrate_one() fail later. + */ + anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + if (freeze && anon_exclusive && page_try_share_anon_rmap(page)) + freeze = false; } /* @@ -2052,6 +2087,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (write) swp_entry = make_writable_migration_entry( page_to_pfn(page + i)); + else if (anon_exclusive) + swp_entry = make_readable_exclusive_migration_entry( + page_to_pfn(page + i)); else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); @@ -2063,6 +2101,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } else { entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); entry = maybe_mkwrite(entry, vma); + if (anon_exclusive) + SetPageAnonExclusive(page + i); if (!write) entry = pte_wrprotect(entry); if (!young) @@ -2294,6 +2334,13 @@ static void __split_huge_page_tail(struct page *head, int tail, * * After successful get_page_unless_zero() might follow flags change, * for example lock_page() which set PG_waiters. + * + * Note that for mapped sub-pages of an anonymous THP, + * PG_anon_exclusive has been cleared in unmap_page() and is stored in + * the migration entry instead from where remap_page() will restore it. + * We can still have PG_anon_exclusive set on effectively unmapped and + * unreferenced sub-pages of an anonymous THP: we can simply drop + * PG_anon_exclusive (-> PG_mappedtodisk) for these here. */ page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & @@ -3025,6 +3072,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; + bool anon_exclusive; pmd_t pmdval; swp_entry_t entry; pmd_t pmdswp; @@ -3034,10 +3082,19 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); + + anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + if (anon_exclusive && page_try_share_anon_rmap(page)) { + set_pmd_at(mm, address, pvmw->pmd, pmdval); + return; + } + if (pmd_dirty(pmdval)) set_page_dirty(page); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); pmdswp = swp_entry_to_pmd(entry); @@ -3071,10 +3128,17 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); - if (PageAnon(new)) - page_add_anon_rmap(new, vma, mmun_start, RMAP_COMPOUND); - else + if (PageAnon(new)) { + rmap_t rmap_flags = RMAP_COMPOUND; + + if (!is_readable_migration_entry(entry)) + rmap_flags |= RMAP_EXCLUSIVE; + + page_add_anon_rmap(new, vma, mmun_start, rmap_flags); + } else { page_add_file_rmap(new, vma, true); + } + VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new)); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 03cbb75bcb54..c0012b4a8eec 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4790,7 +4790,7 @@ again: is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); - if (is_writable_migration_entry(swp_entry) && cow) { + if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. @@ -5190,6 +5190,8 @@ retry_avoidcopy: set_huge_ptep_writable(vma, haddr, ptep); return 0; } + VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page), + old_page); /* * If the process that created a MAP_PRIVATE mapping is about to @@ -6187,12 +6189,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); + struct page *page = pfn_swap_entry_to_page(entry); - if (is_writable_migration_entry(entry)) { + if (!is_readable_migration_entry(entry)) { pte_t newpte; - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry( + swp_offset(entry)); + else + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); set_huge_swap_pte_at(mm, address, ptep, newpte, huge_page_size(h)); diff --git a/mm/ksm.c b/mm/ksm.c index 2b6692a7df6a..38360285497a 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -872,6 +872,7 @@ static inline struct stable_node *page_stable_node(struct page *page) static inline void set_page_stable_node(struct page *page, struct stable_node *stable_node) { + VM_BUG_ON_PAGE(PageAnon(page) && PageAnonExclusive(page), page); page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); } @@ -1044,6 +1045,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, int swapped; int err = -EFAULT; struct mmu_notifier_range range; + bool anon_exclusive; pvmw.address = page_address_in_vma(page, vma); if (pvmw.address == -EFAULT) @@ -1061,9 +1063,10 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) goto out_unlock; + anon_exclusive = PageAnonExclusive(page); if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) || - mm_tlb_flush_pending(mm)) { + anon_exclusive || mm_tlb_flush_pending(mm)) { pte_t entry; swapped = PageSwapCache(page); @@ -1091,6 +1094,12 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } + + if (anon_exclusive && page_try_share_anon_rmap(page)) { + set_pte_at(mm, pvmw.address, pvmw.pte, entry); + goto out_unlock; + } + if (pte_dirty(entry)) set_page_dirty(page); @@ -1149,6 +1158,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, pte_unmap_unlock(ptep, ptl); goto out_mn; } + VM_BUG_ON_PAGE(PageAnonExclusive(page), page); + VM_BUG_ON_PAGE(PageAnon(kpage) && PageAnonExclusive(kpage), kpage); /* * No need to check ksm_use_zero_pages here: we can only have a diff --git a/mm/memory.c b/mm/memory.c index 0b0727758c86..454ecc05ad85 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -720,6 +720,8 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); + VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page))); + /* * No need to take a page reference as one was already * created when the swap entry was made. @@ -796,11 +798,12 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, rss[mm_counter(page)]++; - if (is_writable_migration_entry(entry) && + if (!is_readable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* - * COW mappings require pages in both - * parent and child to be set to read. + * COW mappings require pages in both parent and child + * to be set to read. A previously exclusive entry is + * now shared. */ entry = make_readable_migration_entry( swp_offset(entry)); @@ -951,6 +954,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } + VM_BUG_ON(page && PageAnon(page) && PageAnonExclusive(page)); /* * If it's a shared mapping, mark it clean in @@ -2949,6 +2953,9 @@ static inline void wp_page_reuse(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; + + VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page)); + /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely @@ -3273,6 +3280,13 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) if (PageAnon(vmf->page)) { struct page *page = vmf->page; + /* + * If the page is exclusive to this process we must reuse the + * page without further checks. + */ + if (PageAnonExclusive(page)) + goto reuse; + /* * We have to verify under page lock: these early checks are * just an optimization to avoid locking the page and freeing @@ -3305,6 +3319,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) */ page_move_anon_rmap(page, vma); unlock_page(page); +reuse: wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == @@ -3696,11 +3711,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * that are certainly not shared because we just allocated them without * exposing them to the swapcache. */ - if ((vmf->flags & FAULT_FLAG_WRITE) && !PageKsm(page) && - (page != swapcache || page_count(page) == 1)) { - pte = maybe_mkwrite(pte_mkdirty(pte), vma); - vmf->flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; + if (!PageKsm(page) && (page != swapcache || page_count(page) == 1)) { + if (vmf->flags & FAULT_FLAG_WRITE) { + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + vmf->flags &= ~FAULT_FLAG_WRITE; + ret |= VM_FAULT_WRITE; + } rmap_flags |= RMAP_EXCLUSIVE; } flush_icache_page(vma, page); @@ -3720,6 +3736,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) page_add_anon_rmap(page, vma, vmf->address, rmap_flags); } + VM_BUG_ON(!PageAnon(page) || (pte_write(pte) && !PageAnonExclusive(page))); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); diff --git a/mm/migrate.c b/mm/migrate.c index 92e932f08be5..b2678279eb43 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -177,6 +177,7 @@ static bool remove_migration_pte(struct folio *folio, DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { + rmap_t rmap_flags = RMAP_NONE; pte_t pte; swp_entry_t entry; struct page *new; @@ -211,6 +212,9 @@ static bool remove_migration_pte(struct folio *folio, else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); + if (folio_test_anon(folio) && !is_readable_migration_entry(entry)) + rmap_flags |= RMAP_EXCLUSIVE; + if (unlikely(is_device_private_page(new))) { if (pte_write(pte)) entry = make_writable_device_private_entry( @@ -233,7 +237,7 @@ static bool remove_migration_pte(struct folio *folio, pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) hugepage_add_anon_rmap(new, vma, pvmw.address, - RMAP_NONE); + rmap_flags); else page_dup_file_rmap(new, true); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); @@ -242,7 +246,7 @@ static bool remove_migration_pte(struct folio *folio, { if (folio_test_anon(folio)) page_add_anon_rmap(new, vma, pvmw.address, - RMAP_NONE); + rmap_flags); else page_add_file_rmap(new, vma, false); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); @@ -514,6 +518,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_workingset(newfolio); if (folio_test_checked(folio)) folio_set_checked(newfolio); + /* + * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via + * migration entries. We can still have PG_anon_exclusive set on an + * effectively unmapped and unreferenced first sub-pages of an + * anonymous THP: we can simply copy it here via PG_mappedtodisk. + */ if (folio_test_mappedtodisk(folio)) folio_set_mappedtodisk(newfolio); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index fb6d7d5499f5..5052093d0262 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -184,15 +184,34 @@ again: * set up a special migration page table entry now. */ if (trylock_page(page)) { + bool anon_exclusive; pte_t swp_pte; + anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + if (anon_exclusive) { + flush_cache_page(vma, addr, pte_pfn(*ptep)); + ptep_clear_flush(vma, addr, ptep); + + if (page_try_share_anon_rmap(page)) { + set_pte_at(mm, addr, ptep, pte); + unlock_page(page); + put_page(page); + mpfn = 0; + goto next; + } + } else { + ptep_get_and_clear(mm, addr, ptep); + } + migrate->cpages++; - ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ if (mpfn & MIGRATE_PFN_WRITE) entry = make_writable_migration_entry( page_to_pfn(page)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry( + page_to_pfn(page)); else entry = make_readable_migration_entry( page_to_pfn(page)); diff --git a/mm/mprotect.c b/mm/mprotect.c index b69ce7a7b2b7..56060acdabd3 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -152,6 +152,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, pages++; } else if (is_swap_pte(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); + struct page *page = pfn_swap_entry_to_page(entry); pte_t newpte; if (is_writable_migration_entry(entry)) { @@ -159,8 +160,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * A protection check is difficult so * just be safe and disable write */ - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry( + swp_offset(entry)); + else + entry = make_readable_migration_entry(swp_offset(entry)); newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); diff --git a/mm/rmap.c b/mm/rmap.c index 90f92c53476f..0d63e7ce35cc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1088,6 +1088,7 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + struct page *subpage = page; page = compound_head(page); @@ -1101,6 +1102,7 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); + SetPageAnonExclusive(subpage); } /** @@ -1118,7 +1120,7 @@ static void __page_set_anon_rmap(struct page *page, BUG_ON(!anon_vma); if (PageAnon(page)) - return; + goto out; /* * If the page isn't exclusively mapped into this vma, @@ -1137,6 +1139,9 @@ static void __page_set_anon_rmap(struct page *page, anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); page->index = linear_page_index(vma, address); +out: + if (exclusive) + SetPageAnonExclusive(page); } /** @@ -1198,6 +1203,8 @@ void page_add_anon_rmap(struct page *page, } else { first = atomic_inc_and_test(&page->_mapcount); } + VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); + VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); if (first) { int nr = compound ? thp_nr_pages(page) : 1; @@ -1459,7 +1466,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; - bool ret = true; + bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; @@ -1515,6 +1522,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, subpage = folio_page(folio, pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; + anon_exclusive = folio_test_anon(folio) && + PageAnonExclusive(subpage); if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* @@ -1550,9 +1559,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, } } - /* Nuke the page table entry. */ + /* + * Nuke the page table entry. When having to clear + * PageAnonExclusive(), we always have to flush. + */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); - if (should_defer_flush(mm, flags)) { + if (should_defer_flush(mm, flags) && !anon_exclusive) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. @@ -1677,6 +1689,24 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, page_vma_mapped_walk_done(&pvmw); break; } + if (anon_exclusive && + page_try_share_anon_rmap(subpage)) { + swap_free(entry); + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + /* + * Note: We *don't* remember yet if the page was mapped + * exclusively in the swap entry, so swapin code has + * to re-determine that manually and might detect the + * page as possibly shared, for example, if there are + * other references on the page or if the page is under + * writeback. We made sure that there are no GUP pins + * on the page that would rely on it, so for GUP pins + * this is fine. + */ if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) @@ -1776,7 +1806,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; - bool ret = true; + bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; @@ -1837,6 +1867,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, subpage = folio_page(folio, pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; + anon_exclusive = folio_test_anon(folio) && + PageAnonExclusive(subpage); if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* @@ -1888,6 +1920,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, swp_entry_t entry; pte_t swp_pte; + if (anon_exclusive) + BUG_ON(page_try_share_anon_rmap(subpage)); + /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration @@ -1896,6 +1931,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, entry = pte_to_swp_entry(pteval); if (is_writable_device_private_entry(entry)) entry = make_writable_migration_entry(pfn); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry(pfn); else entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); @@ -1960,6 +1997,15 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, page_vma_mapped_walk_done(&pvmw); break; } + VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && + !anon_exclusive, subpage); + if (anon_exclusive && + page_try_share_anon_rmap(subpage)) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } /* * Store the pfn of the page in a special migration @@ -1969,6 +2015,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (pte_write(pteval)) entry = make_writable_migration_entry( page_to_pfn(subpage)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry( + page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); @@ -2405,6 +2454,8 @@ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(compound_mapcount_ptr(page)); + VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); + VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); if (first) __page_set_anon_rmap(page, vma, address, !!(flags & RMAP_EXCLUSIVE)); -- cgit v1.2.3 From 6d4675e601357834dadd2ba1d803f6484596015c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 19 May 2022 14:08:54 -0700 Subject: mm: don't be stuck to rmap lock on reclaim path The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended under memory pressure if processes keep working on their vmas(e.g., fork, mmap, munmap). It makes reclaim path stuck. In our real workload traces, we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it makes other processes entering direct reclaim, which were also stuck on the lock. This patch makes lru aging path try_lock mode like shink_page_list so the reclaim context will keep working with next lru pages without being stuck. if it found the rmap lock contended, it rotates the page back to head of lru in both active/inactive lrus to make them consistent behavior, which is basic starting point rather than adding more heristic. Since this patch introduces a new "contended" field as out-param along with try_lock in-param in rmap_walk_control, it's not immutable any longer if the try_lock is set so remove const keywords on rmap related functions. Since rmap walking is already expensive operation, I doubt the const would help sizable benefit( And we didn't have it until 5.17). In a heavy app workload in Android, trace shows following statistics. It almost removes rmap lock contention from reclaim path. Martin Liu reported: Before: max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function 1632 0 1631 151.542173 31672 209 page_lock_anon_vma_read 601 0 601 145.544681 28817 198 rmap_walk_file After: max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function NaN NaN NaN NaN NaN 0.0 NaN 0 0 0 0.127645 1 12 rmap_walk_file [minchan@kernel.org: add comment, per Matthew] Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org Signed-off-by: Minchan Kim Acked-by: Johannes Weiner Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: John Dias Cc: Tim Murray Cc: Matthew Wilcox Cc: Vladimir Davydov Cc: Martin Liu Cc: Minchan Kim Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/fs.h | 5 +++++ include/linux/ksm.h | 4 ++-- include/linux/rmap.h | 28 ++++++++++++++++++++-------- mm/ksm.c | 10 ++++++++-- mm/memory-failure.c | 2 +- mm/page_idle.c | 7 ++++--- mm/rmap.c | 52 +++++++++++++++++++++++++++++++++++++++++----------- mm/vmscan.c | 7 ++++++- 8 files changed, 87 insertions(+), 28 deletions(-) (limited to 'include/linux/rmap.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index b81cacc51d2f..044b67f8d861 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -477,6 +477,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping) up_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0630e545f4cb..0b4f17418f64 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, } static inline void rmap_walk_ksm(struct folio *folio, - const struct rmap_walk_control *rwc) + struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index cbe279a6f0de..9ec23138e410 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -128,6 +128,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma) down_read(&anon_vma->root->rwsem); } +static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) +{ + return down_read_trylock(&anon_vma->root->rwsem); +} + static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); @@ -366,17 +371,14 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -/* - * Called by memory-failure.c to kill processes. - */ -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() + * try_lock: bail out if the rmap lock is contended + * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default @@ -384,6 +386,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); */ struct rmap_walk_control { void *arg; + bool try_lock; + bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. @@ -391,12 +395,20 @@ struct rmap_walk_control { bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); - struct anon_vma *(*anon_lock)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio, + struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); -void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); + +/* + * Called by memory-failure.c to kill processes. + */ +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc); +void page_unlock_anon_vma_read(struct anon_vma *anon_vma); #else /* !CONFIG_MMU */ diff --git a/mm/ksm.c b/mm/ksm.c index 38360285497a..9ee82c9bce94 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2610,7 +2610,7 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc) +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; @@ -2634,7 +2634,13 @@ again: struct vm_area_struct *vma; cond_resched(); - anon_vma_lock_read(anon_vma); + if (!anon_vma_trylock_read(anon_vma)) { + if (rwc->try_lock) { + rwc->contended = true; + return; + } + anon_vma_lock_read(anon_vma); + } anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, 0, ULONG_MAX) { unsigned long addr; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 01f8b63d3621..a934ee8124dd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -485,7 +485,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct anon_vma *av; pgoff_t pgoff; - av = folio_lock_anon_vma_read(folio); + av = folio_lock_anon_vma_read(folio, NULL); if (av == NULL) /* Not actually mapped anymore */ return; diff --git a/mm/page_idle.c b/mm/page_idle.c index fc0435abf909..bc08332a609c 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -86,11 +86,12 @@ static bool page_idle_clear_pte_refs_one(struct folio *folio, static void page_idle_clear_pte_refs(struct page *page) { struct folio *folio = page_folio(page); + /* - * Since rwc.arg is unused, rwc is effectively immutable, so we - * can make it static const to save some cycles and stack. + * Since rwc.try_lock is unused, rwc is effectively immutable, so we + * can make it static to save some cycles and stack. */ - static const struct rmap_walk_control rwc = { + static struct rmap_walk_control rwc = { .rmap_one = page_idle_clear_pte_refs_one, .anon_lock = folio_lock_anon_vma_read, }; diff --git a/mm/rmap.c b/mm/rmap.c index 219e287a83d2..5bcb334cd6f2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -527,9 +527,11 @@ out: * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a - * reference like with page_get_anon_vma() and then block on the mutex. + * reference like with page_get_anon_vma() and then block on the mutex + * on !rwc->try_lock case. */ -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio) +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; @@ -557,6 +559,12 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio) goto out; } + if (rwc && rwc->try_lock) { + anon_vma = NULL; + rwc->contended = true; + goto out; + } + /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; @@ -883,7 +891,8 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) * * Quick test_and_clear_referenced for all mappings of a folio, * - * Return: The number of mappings which referenced the folio. + * Return: The number of mappings which referenced the folio. Return -1 if + * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) @@ -897,6 +906,7 @@ int folio_referenced(struct folio *folio, int is_locked, .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, + .try_lock = true, }; *vm_flags = 0; @@ -927,7 +937,7 @@ int folio_referenced(struct folio *folio, int is_locked, if (we_locked) folio_unlock(folio); - return pra.referenced; + return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) @@ -2336,12 +2346,12 @@ void __put_anon_vma(struct anon_vma *anon_vma) } static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, - const struct rmap_walk_control *rwc) + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) - return rwc->anon_lock(folio); + return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() @@ -2353,7 +2363,17 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, if (!anon_vma) return NULL; + if (anon_vma_trylock_read(anon_vma)) + goto out; + + if (rwc->try_lock) { + anon_vma = NULL; + rwc->contended = true; + goto out; + } + anon_vma_lock_read(anon_vma); +out: return anon_vma; } @@ -2367,7 +2387,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, * contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, - const struct rmap_walk_control *rwc, bool locked) + struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; @@ -2415,7 +2435,7 @@ static void rmap_walk_anon(struct folio *folio, * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, - const struct rmap_walk_control *rwc, bool locked) + struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; @@ -2434,8 +2454,18 @@ static void rmap_walk_file(struct folio *folio, pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; - if (!locked) + if (!locked) { + if (i_mmap_trylock_read(mapping)) + goto lookup; + + if (rwc->try_lock) { + rwc->contended = true; + return; + } + i_mmap_lock_read(mapping); + } +lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(&folio->page, vma); @@ -2457,7 +2487,7 @@ done: i_mmap_unlock_read(mapping); } -void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc) +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); @@ -2468,7 +2498,7 @@ void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc) } /* Like rmap_walk, but caller holds relevant rmap lock */ -void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc) +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); diff --git a/mm/vmscan.c b/mm/vmscan.c index 24dbe04520cb..887edcd93a40 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1391,6 +1391,10 @@ static enum page_references folio_check_references(struct folio *folio, if (vm_flags & VM_LOCKED) return PAGEREF_ACTIVATE; + /* rmap lock contention: rotate */ + if (referenced_ptes == -1) + return PAGEREF_KEEP; + if (referenced_ptes) { /* * All mapped folios start out with page table @@ -2499,8 +2503,9 @@ static void shrink_active_list(unsigned long nr_to_scan, } } + /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, - &vm_flags)) { + &vm_flags) != 0) { /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So -- cgit v1.2.3