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>

3 files changed, 74 insertions, 20 deletions

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);
 
 /*
diff --git a/mm/internal.h b/mm/internal.h
index 6293468fd7b7..69a5eabe0943 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -525,26 +525,22 @@ void mlock_page_drain_remote(int cpu);
 extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 
 /*
- * At what user virtual address is page expected in vma?
- * Returns -EFAULT if all of the page is outside the range of vma.
- * If page is a compound head, the entire compound page is considered.
+ * Return the start of user virtual address at the specific offset within
+ * a vma.
  */
 static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
+vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
+		  struct vm_area_struct *vma)
 {
-	pgoff_t pgoff;
 	unsigned long address;
 
-	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
-	pgoff = page_to_pgoff(page);
 	if (pgoff >= vma->vm_pgoff) {
 		address = vma->vm_start +
 			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 		/* Check for address beyond vma (or wrapped through 0?) */
 		if (address < vma->vm_start || address >= vma->vm_end)
 			address = -EFAULT;
-	} else if (PageHead(page) &&
-		   pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+	} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
 		/* Test above avoids possibility of wrap to 0 on 32-bit */
 		address = vma->vm_start;
 	} else {
@@ -554,6 +550,18 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 }
 
 /*
+ * Return the start of user virtual address of a page within a vma.
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
+ */
+static inline unsigned long
+vma_address(struct page *page, struct vm_area_struct *vma)
+{
+	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
+	return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma);
+}
+
+/*
  * Then at what user virtual address will none of the range be found in vma?
  * Assumes that vma_address() already returned a good starting address.
  */
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