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/rmap.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) (limited to 'include/linux/rmap.h') 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 */ -- 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 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 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 *, -- 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 -- 1 file changed, 2 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); -- 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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (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); -- 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 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (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 *, -- 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 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (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 */ -- 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/rmap.h | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'include/linux/rmap.h') 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 */ -- cgit v1.2.3