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 <songmuchun@bytedance.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 54 insertions, 11 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index c194ec913c68..ad509b3a89ee 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -929,12 +929,12 @@ int folio_referenced(struct folio *folio, int is_locked,
 	return pra.referenced;
 }
 
-static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
-			    unsigned long address, void *arg)
+static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
 {
-	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+	int cleaned = 0;
+	struct vm_area_struct *vma = pvmw->vma;
 	struct mmu_notifier_range range;
-	int *cleaned = arg;
+	unsigned long address = pvmw->address;
 
 	/*
 	 * We have to assume the worse case ie pmd for invalidation. Note that
@@ -942,16 +942,16 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 	 */
 	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
 				0, vma, vma->vm_mm, address,
-				vma_address_end(&pvmw));
+				vma_address_end(pvmw));
 	mmu_notifier_invalidate_range_start(&range);
 
-	while (page_vma_mapped_walk(&pvmw)) {
+	while (page_vma_mapped_walk(pvmw)) {
 		int ret = 0;
 
-		address = pvmw.address;
-		if (pvmw.pte) {
+		address = pvmw->address;
+		if (pvmw->pte) {
 			pte_t entry;
-			pte_t *pte = pvmw.pte;
+			pte_t *pte = pvmw->pte;
 
 			if (!pte_dirty(*pte) && !pte_write(*pte))
 				continue;
@@ -964,7 +964,7 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 			ret = 1;
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			pmd_t *pmd = pvmw.pmd;
+			pmd_t *pmd = pvmw->pmd;
 			pmd_t entry;
 
 			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
@@ -991,11 +991,22 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
 		 * See Documentation/vm/mmu_notifier.rst
 		 */
 		if (ret)
-			(*cleaned)++;
+			cleaned++;
 	}
 
 	mmu_notifier_invalidate_range_end(&range);
 
+	return cleaned;
+}
+
+static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
+			     unsigned long address, void *arg)
+{
+	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
+	int *cleaned = arg;
+
+	*cleaned += page_vma_mkclean_one(&pvmw);
+
 	return true;
 }
 
@@ -1033,6 +1044,38 @@ int folio_mkclean(struct folio *folio)
 EXPORT_SYMBOL_GPL(folio_mkclean);
 
 /**
+ * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
+ *                     [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
+ *                     within the @vma of shared mappings. And since clean PTEs
+ *                     should also be readonly, write protects them too.
+ * @pfn: start pfn.
+ * @nr_pages: number of physically contiguous pages srarting with @pfn.
+ * @pgoff: page offset that the @pfn mapped with.
+ * @vma: vma that @pfn mapped within.
+ *
+ * Returns the number of cleaned PTEs (including PMDs).
+ */
+int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
+		      struct vm_area_struct *vma)
+{
+	struct page_vma_mapped_walk pvmw = {
+		.pfn		= pfn,
+		.nr_pages	= nr_pages,
+		.pgoff		= pgoff,
+		.vma		= vma,
+		.flags		= PVMW_SYNC,
+	};
+
+	if (invalid_mkclean_vma(vma, NULL))
+		return 0;
+
+	pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma);
+	VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma);
+
+	return page_vma_mkclean_one(&pvmw);
+}
+
+/**
  * page_move_anon_rmap - move a page to our anon_vma
  * @page:	the page to move to our anon_vma
  * @vma:	the vma the page belongs to