Message-ID: <f891079f-f1c9-4920-8804-c668df4ea5d6@redhat.com>
Date:   Tue, 5 Dec 2023 14:11:52 +0100
From:   David Hildenbrand <david@...hat.com>
To:     linux-kernel@...r.kernel.org
Cc:     linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
        "Matthew Wilcox (Oracle)" <willy@...radead.org>,
        Hugh Dickins <hughd@...gle.com>,
        Ryan Roberts <ryan.roberts@....com>,
        Yin Fengwei <fengwei.yin@...el.com>,
        Mike Kravetz <mike.kravetz@...cle.com>,
        Muchun Song <muchun.song@...ux.dev>,
        Peter Xu <peterx@...hat.com>
Subject: Re: [PATCH RFC 34/39] mm/rmap: introduce
 folio_try_dup_anon_rmap_[pte|ptes|pmd]()

On 04.12.23 15:21, David Hildenbrand wrote:
> 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.
> 
> Signed-off-by: David Hildenbrand <david@...hat.com>
> ---

This is what I currently have (- any renaming):


 From 89c3180d6bbbf2236329b405b11e6a8a3cc2c088 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@...hat.com>
Date: Thu, 30 Nov 2023 10:15:17 +0100
Subject: [PATCH] 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.

Signed-off-by: David Hildenbrand <david@...hat.com>
---
  include/linux/mm.h   |   6 --
  include/linux/rmap.h | 143 ++++++++++++++++++++++++++++++-------------
  2 files changed, 99 insertions(+), 50 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 24c1c7c5a99c0..f7565b35ae931 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1964,12 +1964,6 @@ 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
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 06951909bb39b..98862ab7347f2 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -354,68 +354,123 @@ static inline void folio_dup_file_rmap_pmd(struct folio *folio,
  #endif
  }
  
-static inline void __page_dup_rmap(struct page *page, bool compound)
+static inline int __folio_try_dup_anon_rmap(struct folio *folio,
+		struct page *page, unsigned int nr_pages,
+		struct vm_area_struct *src_vma, enum rmap_mode mode)
  {
-	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, mode);
  
-		VM_BUG_ON_PAGE(compound && !PageHead(page), page);
+	/*
+	 * 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.
+	 */
+	if (likely(mode == RMAP_MODE_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);
+	} else if (mode == RMAP_MODE_PMD) {
+		if (PageAnonExclusive(page)) {
+			if (unlikely(maybe_pinned))
+				return -EBUSY;
+			ClearPageAnonExclusive(page);
+		}
  		atomic_inc(&folio->_entire_mapcount);
-	} else {
-		atomic_inc(&page->_mapcount);
  	}
+	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.
+ *
+ * Duplicating the mappings can only fail if the folio may be pinned; device
+ * private folios cannot get pinned and consequently this function cannot fail.
+ *
+ * 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.
+ *
+ * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise.
+ */
+static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
+		struct page *page, unsigned int nr_pages,
+		struct vm_area_struct *src_vma)
+{
+	return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma,
+					 RMAP_MODE_PTE);
+}
+#define folio_try_dup_anon_rmap_pte(folio, page, vma) \
+	folio_try_dup_anon_rmap_ptes(folio, page, 1, vma)
+
+/**
+ * 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.
   *
- * 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.
+ * 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.
   *
   * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
   */
+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_MODE_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
  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);
-
-	/*
-	 * No need to check+clear for already shared pages, including KSM
-	 * pages.
-	 */
-	if (!PageAnonExclusive(page))
-		goto dup;
+	struct folio *folio = page_folio(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;
-
-	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;
+	if (likely(!compound))
+		return folio_try_dup_anon_rmap_pte(folio, page, vma);
+	return folio_try_dup_anon_rmap_pmd(folio, page, vma);
  }
  
  /**
-- 
2.41.0


-- 
Cheers,

David / dhildenb

Powered by blists - more mailing lists