[RFC,09/19] mm/gup: reliable R/O long-term pinning in COW mappings

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 517c8cc8ccb9..3252ed88b472 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3002,8 +3002,12 @@  static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
  * Must be called with the (sub)page that's actually referenced via the
  * page table entry, which might not necessarily be the head page for a
  * PTE-mapped THP.
+ *
+ * If the vma is NULL, we're coming from the GUP-fast path and might have
+ * to fallback to the slow path just to lookup the vma.
  */
-static inline bool gup_must_unshare(unsigned int flags, struct page *page)
+static inline bool gup_must_unshare(struct vm_area_struct *vma,
+				    unsigned int flags, struct page *page)
 {
 	/*
 	 * FOLL_WRITE is implicitly handled correctly as the page table entry
@@ -3016,8 +3020,25 @@  static inline bool gup_must_unshare(unsigned int flags, struct page *page)
 	 * Note: PageAnon(page) is stable until the page is actually getting
 	 * freed.
 	 */
-	if (!PageAnon(page))
-		return false;
+	if (!PageAnon(page)) {
+		/*
+		 * We only care about R/O long-term pining: R/O short-term
+		 * pinning does not have the semantics to observe successive
+		 * changes through the process page tables.
+		 */
+		if (!(flags & FOLL_LONGTERM))
+			return false;
+
+		/* We really need the vma ... */
+		if (!vma)
+			return true;
+
+		/*
+		 * ... because we only care about writable private ("COW")
+		 * mappings where we have to break COW early.
+		 */
+		return is_cow_mapping(vma->vm_flags);
+	}
 
 	/* Paired with a memory barrier in page_try_share_anon_rmap(). */
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
diff --git a/mm/gup.c b/mm/gup.c
index 5182abaaecde..01116699c863 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -578,7 +578,7 @@  static struct page *follow_page_pte(struct vm_area_struct *vma,
 		}
 	}
 
-	if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+	if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) {
 		page = ERR_PTR(-EMLINK);
 		goto out;
 	}
@@ -2338,7 +2338,7 @@  static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 			goto pte_unmap;
 		}
 
-		if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+		if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) {
 			gup_put_folio(folio, 1, flags);
 			goto pte_unmap;
 		}
@@ -2506,7 +2506,7 @@  static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		return 0;
 	}
 
-	if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) {
+	if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) {
 		gup_put_folio(folio, refs, flags);
 		return 0;
 	}
@@ -2572,7 +2572,7 @@  static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
-	if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) {
+	if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
 		gup_put_folio(folio, refs, flags);
 		return 0;
 	}
@@ -2612,7 +2612,7 @@  static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
-	if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) {
+	if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
 		gup_put_folio(folio, refs, flags);
 		return 0;
 	}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7173756d6868..50c673da3c6e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1404,7 +1404,7 @@  struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags))
 		return NULL;
 
-	if (!pmd_write(*pmd) && gup_must_unshare(flags, page))
+	if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
 	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3672c7e06748..d96bbc69806f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6197,7 +6197,8 @@  static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma,
 	}
 }
 
-static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte,
+static inline bool __follow_hugetlb_must_fault(struct vm_area_struct *vma,
+					       unsigned int flags, pte_t *pte,
 					       bool *unshare)
 {
 	pte_t pteval = huge_ptep_get(pte);
@@ -6209,7 +6210,7 @@  static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte,
 		return false;
 	if (flags & FOLL_WRITE)
 		return true;
-	if (gup_must_unshare(flags, pte_page(pteval))) {
+	if (gup_must_unshare(vma, flags, pte_page(pteval))) {
 		*unshare = true;
 		return true;
 	}
@@ -6338,7 +6339,7 @@  long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * directly from any kind of swap entries.
 		 */
 		if (absent ||
-		    __follow_hugetlb_must_fault(flags, pte, &unshare)) {
+		    __follow_hugetlb_must_fault(vma, flags, pte, &unshare)) {
 			vm_fault_t ret;
 			unsigned int fault_flags = 0;