1 files changed, 69 insertions, 18 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86f9f8b82f8e..b49ee126d4d1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -232,7 +232,7 @@ retry:
 	return READ_ONCE(huge_zero_page);
 }
 
-static void put_huge_zero_page(void)
+void put_huge_zero_page(void)
 {
 	/*
 	 * Counter should never go to zero here. Only shrinker can put
@@ -1298,15 +1298,9 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page);
 	/*
 	 * We can only reuse the page if nobody else maps the huge page or it's
-	 * part. We can do it by checking page_mapcount() on each sub-page, but
-	 * it's expensive.
-	 * The cheaper way is to check page_count() to be equal 1: every
-	 * mapcount takes page reference reference, so this way we can
-	 * guarantee, that the PMD is the only mapping.
-	 * This can give false negative if somebody pinned the page, but that's
-	 * fine.
+	 * part.
 	 */
-	if (page_mapcount(page) == 1 && page_count(page) == 1) {
+	if (page_trans_huge_mapcount(page, NULL) == 1) {
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
@@ -1684,12 +1678,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (vma_is_dax(vma)) {
 		spin_unlock(ptl);
 		if (is_huge_zero_pmd(orig_pmd))
-			put_huge_zero_page();
+			tlb_remove_page(tlb, pmd_page(orig_pmd));
 	} else if (is_huge_zero_pmd(orig_pmd)) {
 		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
 		atomic_long_dec(&tlb->mm->nr_ptes);
 		spin_unlock(ptl);
-		put_huge_zero_page();
+		tlb_remove_page(tlb, pmd_page(orig_pmd));
 	} else {
 		struct page *page = pmd_page(orig_pmd);
 		page_remove_rmap(page, true);
@@ -1960,10 +1954,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 		 * page fault if needed.
 		 */
 		return 0;
-	if (vma->vm_ops)
+	if (vma->vm_ops || (vm_flags & VM_NO_THP))
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
@@ -2080,7 +2073,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		if (pte_write(pteval)) {
 			writable = true;
 		} else {
-			if (PageSwapCache(page) && !reuse_swap_page(page)) {
+			if (PageSwapCache(page) &&
+			    !reuse_swap_page(page, NULL)) {
 				unlock_page(page);
 				result = SCAN_SWAP_CACHE_PAGE;
 				goto out;
@@ -2352,8 +2346,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 		return false;
 	if (is_vma_temporary_stack(vma))
 		return false;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
-	return true;
+	return !(vma->vm_flags & VM_NO_THP);
 }
 
 static void collapse_huge_page(struct mm_struct *mm,
@@ -3225,6 +3218,64 @@ int total_mapcount(struct page *page)
 }
 
 /*
+ * This calculates accurately how many mappings a transparent hugepage
+ * has (unlike page_mapcount() which isn't fully accurate). This full
+ * accuracy is primarily needed to know if copy-on-write faults can
+ * reuse the page and change the mapping to read-write instead of
+ * copying them. At the same time this returns the total_mapcount too.
+ *
+ * The function returns the highest mapcount any one of the subpages
+ * has. If the return value is one, even if different processes are
+ * mapping different subpages of the transparent hugepage, they can
+ * all reuse it, because each process is reusing a different subpage.
+ *
+ * The total_mapcount is instead counting all virtual mappings of the
+ * subpages. If the total_mapcount is equal to "one", it tells the
+ * caller all mappings belong to the same "mm" and in turn the
+ * anon_vma of the transparent hugepage can become the vma->anon_vma
+ * local one as no other process may be mapping any of the subpages.
+ *
+ * It would be more accurate to replace page_mapcount() with
+ * page_trans_huge_mapcount(), however we only use
+ * page_trans_huge_mapcount() in the copy-on-write faults where we
+ * need full accuracy to avoid breaking page pinning, because
+ * page_trans_huge_mapcount() is slower than page_mapcount().
+ */
+int page_trans_huge_mapcount(struct page *page, int *total_mapcount)
+{
+	int i, ret, _total_mapcount, mapcount;
+
+	/* hugetlbfs shouldn't call it */
+	VM_BUG_ON_PAGE(PageHuge(page), page);
+
+	if (likely(!PageTransCompound(page))) {
+		mapcount = atomic_read(&page->_mapcount) + 1;
+		if (total_mapcount)
+			*total_mapcount = mapcount;
+		return mapcount;
+	}
+
+	page = compound_head(page);
+
+	_total_mapcount = ret = 0;
+	for (i = 0; i < HPAGE_PMD_NR; i++) {
+		mapcount = atomic_read(&page[i]._mapcount) + 1;
+		ret = max(ret, mapcount);
+		_total_mapcount += mapcount;
+	}
+	if (PageDoubleMap(page)) {
+		ret -= 1;
+		_total_mapcount -= HPAGE_PMD_NR;
+	}
+	mapcount = compound_mapcount(page);
+	ret += mapcount;
+	_total_mapcount += mapcount;
+	if (total_mapcount)
+		*total_mapcount = _total_mapcount;
+	return ret;
+}
+
+/*
  * This function splits huge page into normal pages. @page can point to any
  * subpage of huge page to split. Split doesn't change the position of @page.
  *
@@ -3454,7 +3505,7 @@ next:
 		}
 	}
 
-	pr_info("%lu of %lu THP split", split, total);
+	pr_info("%lu of %lu THP split\n", split, total);
 
 	return 0;
 }
@@ -3465,7 +3516,7 @@ static int __init split_huge_pages_debugfs(void)
 {
 	void *ret;
 
-	ret = debugfs_create_file("split_huge_pages", 0644, NULL, NULL,
+	ret = debugfs_create_file("split_huge_pages", 0200, NULL, NULL,
 			&split_huge_pages_fops);
 	if (!ret)
 		pr_warn("Failed to create split_huge_pages in debugfs");