[PATCH 11/46] mm/huge_memory: properly handle refcounted PUD mappings on fork

[David Hildenbrand (Arm)]

copy_huge_pud() copies device-DAX entries without taking a folio reference
or updating mapcounts and the child's RSS.

For example, MADV_GUARD_INSTALL sets VM_MAYBE_GUARD on a device-DAX VMA,
forcing copy_page_range() to traverse the whole VMA on fork. Any remaining
huge PUDs are then copied without accounting for the new mappings.
Unmapping them in the child decrements accounting that was never added.

Use vm_normal_page_pud() to identify refcounted mappings. Take a folio
reference and add the child's PUD rmap and RSS accounting before installing
the copied entry. Pass src and dst VMAs consistently instead of src and
dst MM. Move the TODO.

Fixes: aed877c2b4257 ("device/dax: properly refcount device dax pages when mapping")
Cc: stable at vger.kernel.org
Signed-off-by: David Hildenbrand (Arm) <david at kernel.org>
---
 include/linux/huge_mm.h |  5 ++---
 mm/huge_memory.c        | 27 +++++++++++++++++++--------
 mm/memory.c             |  4 +---
 3 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c745f7ad22987..fac05120ab774 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -12,9 +12,8 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
 bool huge_pmd_set_accessed(struct vm_fault *vmf);
-int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
-		  struct vm_area_struct *vma);
+int copy_huge_pud(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		pud_t *dst_pud, pud_t *src_pud, unsigned long addr);
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4c0194af9016d..283c4bc8b927c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2072,11 +2072,13 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr,
 		update_mmu_cache_pud(vma, addr, pud);
 }
 
-int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
-		  struct vm_area_struct *vma)
+int copy_huge_pud(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		pud_t *dst_pud, pud_t *src_pud, unsigned long addr)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	spinlock_t *dst_ptl, *src_ptl;
+	struct page *page;
 	pud_t pud;
 	int ret;
 
@@ -2089,11 +2091,20 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (unlikely(!pud_trans_huge(pud)))
 		goto out_unlock;
 
-	/*
-	 * TODO: once we support anonymous pages, use
-	 * folio_try_dup_anon_rmap_*() and split if duplicating fails.
-	 */
-	if (vma_is_cow_mapping(vma) && pud_write(pud)) {
+	page = vm_normal_page_pud(src_vma, addr, pud);
+	if (page) {
+		struct folio *folio = page_folio(page);
+
+		folio_get(folio);
+		/*
+		 * TODO: once we support anonymous pages, use
+		 * folio_try_dup_anon_rmap_*() and split if duplicating fails.
+		 */
+		folio_add_file_rmap_pud(folio, page, dst_vma);
+		add_mm_counter(dst_mm, mm_counter_file(folio), HPAGE_PUD_NR);
+	}
+
+	if (vma_is_cow_mapping(src_vma) && pud_write(pud)) {
 		pudp_set_wrprotect(src_mm, addr, src_pud);
 		pud = pud_wrprotect(pud);
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 5d6d695675bce..0f4db5080e371 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1463,7 +1463,6 @@ copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	       unsigned long end)
 {
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
-	struct mm_struct *src_mm = src_vma->vm_mm;
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
@@ -1477,8 +1476,7 @@ copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 			int err;
 
 			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
-			err = copy_huge_pud(dst_mm, src_mm,
-					    dst_pud, src_pud, addr, src_vma);
+			err = copy_huge_pud(dst_vma, src_vma, dst_pud, src_pud, addr);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)

-- 
2.43.0