Commit 61d90309 authored by David Hildenbrand's avatar David Hildenbrand Committed by Andrew Morton
Browse files

mm/rmap: introduce folio_try_dup_anon_rmap_[pte|ptes|pmd]()

The last user of page_needs_cow_for_dma() and __page_dup_rmap() are gone,
remove them.

Add folio_try_dup_anon_rmap_ptes() right away, we want to perform rmap
baching during fork() soon.

Link: https://lkml.kernel.org/r/20231220224504.646757-35-david@redhat.com


Signed-off-by: default avatarDavid Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent d8ef5e31
Loading
Loading
Loading
Loading
+0 −6
Original line number Diff line number Diff line
@@ -1975,12 +1975,6 @@ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma,
	return folio_maybe_dma_pinned(folio);
}

static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
					  struct page *page)
{
	return folio_needs_cow_for_dma(vma, page_folio(page));
}

/**
 * is_zero_page - Query if a page is a zero page
 * @page: The page to query
+106 −44
Original line number Diff line number Diff line
@@ -362,68 +362,130 @@ static inline void folio_dup_file_rmap_pmd(struct folio *folio,
#endif
}

static inline void __page_dup_rmap(struct page *page, bool compound)
static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *src_vma,
		enum rmap_level level)
{
	VM_WARN_ON(folio_test_hugetlb(page_folio(page)));
	bool maybe_pinned;
	int i;

	if (compound) {
		struct folio *folio = (struct folio *)page;
	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
	__folio_rmap_sanity_checks(folio, page, nr_pages, level);

		VM_BUG_ON_PAGE(compound && !PageHead(page), page);
		atomic_inc(&folio->_entire_mapcount);
	} else {
	/*
	 * If this folio may have been pinned by the parent process,
	 * don't allow to duplicate the mappings but instead require to e.g.,
	 * copy the subpage immediately for the child so that we'll always
	 * guarantee the pinned folio won't be randomly replaced in the
	 * future on write faults.
	 */
	maybe_pinned = likely(!folio_is_device_private(folio)) &&
		       unlikely(folio_needs_cow_for_dma(src_vma, folio));

	/*
	 * No need to check+clear for already shared PTEs/PMDs of the
	 * folio. But if any page is PageAnonExclusive, we must fallback to
	 * copying if the folio maybe pinned.
	 */
	switch (level) {
	case RMAP_LEVEL_PTE:
		if (unlikely(maybe_pinned)) {
			for (i = 0; i < nr_pages; i++)
				if (PageAnonExclusive(page + i))
					return -EBUSY;
		}
		do {
			if (PageAnonExclusive(page))
				ClearPageAnonExclusive(page);
			atomic_inc(&page->_mapcount);
		} while (page++, --nr_pages > 0);
		break;
	case RMAP_LEVEL_PMD:
		if (PageAnonExclusive(page)) {
			if (unlikely(maybe_pinned))
				return -EBUSY;
			ClearPageAnonExclusive(page);
		}
		atomic_inc(&folio->_entire_mapcount);
		break;
	}
	return 0;
}

/**
 * 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
 * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range
 *				  of a folio
 * @folio:	The folio to duplicate the mappings of
 * @page:	The first page to duplicate the mappings of
 * @nr_pages:	The number of pages of which the mapping will be duplicated
 * @src_vma:	The vm area from which the mappings are duplicated
 *
 * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq.
 * The page range of the folio is defined by [page, page + nr_pages)
 *
 * Duplicating the mapping can only fail if the page may be pinned; device
 * private pages cannot get pinned and consequently this function cannot fail.
 * The caller needs to hold the page table lock and the
 * vma->vma_mm->write_protect_seq.
 *
 * 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.
 * Duplicating the mappings can only fail if the folio may be pinned; device
 * private folios cannot get pinned and consequently this function cannot fail
 * for them.
 *
 * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
 * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in
 * the parent and the child. They must *not* be writable after this call
 * succeeded.
 *
 * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise.
 */
static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
					 struct vm_area_struct *vma)
static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
		struct page *page, int nr_pages, struct vm_area_struct *src_vma)
{
	VM_BUG_ON_PAGE(!PageAnon(page), page);

	/*
	 * No need to check+clear for already shared pages, including KSM
	 * pages.
	 */
	if (!PageAnonExclusive(page))
		goto dup;
	return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma,
					 RMAP_LEVEL_PTE);
}
#define folio_try_dup_anon_rmap_pte(folio, page, vma) \
	folio_try_dup_anon_rmap_ptes(folio, page, 1, vma)

	/*
	 * 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.
/**
 * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range
 *				 of a folio
 * @folio:	The folio to duplicate the mapping of
 * @page:	The first page to duplicate the mapping of
 * @src_vma:	The vm area from which the mapping is duplicated
 *
 * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
 *
 * The caller needs to hold the page table lock and the
 * vma->vma_mm->write_protect_seq.
 *
 * Duplicating the mapping can only fail if the folio may be pinned; device
 * private folios cannot get pinned and consequently this function cannot fail
 * for them.
 *
 * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in
 * the parent and the child. They must *not* be writable after this call
 * succeeded.
 *
 * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
 */
	if (likely(!is_device_private_page(page)) &&
	    unlikely(page_needs_cow_for_dma(vma, page)))
static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
		struct page *page, struct vm_area_struct *src_vma)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma,
					 RMAP_LEVEL_PMD);
#else
	WARN_ON_ONCE(true);
	return -EBUSY;
#endif
}

	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;
static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
					 struct vm_area_struct *vma)
{
	struct folio *folio = page_folio(page);

	if (likely(!compound))
		return folio_try_dup_anon_rmap_pte(folio, page, vma);
	return folio_try_dup_anon_rmap_pmd(folio, page, vma);
}

/**