1 files changed, 137 insertions, 70 deletions

diff --git a/mm/gup.c b/mm/gup.c
index b2b4d4263768..9e17d8db2d6b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -848,7 +848,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 						unsigned long nr_pages,
 						struct page **pages,
 						struct vm_area_struct **vmas,
-						int *locked, bool notify_drop,
+						int *locked,
 						unsigned int flags)
 {
 	long ret, pages_done;
@@ -922,7 +922,7 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		pages++;
 		start += PAGE_SIZE;
 	}
-	if (notify_drop && lock_dropped && *locked) {
+	if (lock_dropped && *locked) {
 		/*
 		 * We must let the caller know we temporarily dropped the lock
 		 * and so the critical section protected by it was lost.
@@ -959,36 +959,12 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 			   int *locked)
 {
 	return __get_user_pages_locked(current, current->mm, start, nr_pages,
-				       pages, NULL, locked, true,
+				       pages, NULL, locked,
 				       gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
 /*
- * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows for
- * tsk, mm to be specified.
- *
- * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the
- * caller if required (just like with __get_user_pages). "FOLL_GET"
- * is set implicitly if "pages" is non-NULL.
- */
-static __always_inline long __get_user_pages_unlocked(struct task_struct *tsk,
-		struct mm_struct *mm, unsigned long start,
-		unsigned long nr_pages, struct page **pages,
-		unsigned int gup_flags)
-{
-	long ret;
-	int locked = 1;
-
-	down_read(&mm->mmap_sem);
-	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, NULL,
-				      &locked, false, gup_flags);
-	if (locked)
-		up_read(&mm->mmap_sem);
-	return ret;
-}
-
-/*
  * get_user_pages_unlocked() is suitable to replace the form:
  *
  *      down_read(&mm->mmap_sem);
@@ -1006,8 +982,16 @@ static __always_inline long __get_user_pages_unlocked(struct task_struct *tsk,
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 			     struct page **pages, unsigned int gup_flags)
 {
-	return __get_user_pages_unlocked(current, current->mm, start, nr_pages,
-					 pages, gup_flags | FOLL_TOUCH);
+	struct mm_struct *mm = current->mm;
+	int locked = 1;
+	long ret;
+
+	down_read(&mm->mmap_sem);
+	ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+				      &locked, gup_flags | FOLL_TOUCH);
+	if (locked)
+		up_read(&mm->mmap_sem);
+	return ret;
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
@@ -1073,7 +1057,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 		struct vm_area_struct **vmas, int *locked)
 {
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
-				       locked, true,
+				       locked,
 				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
 }
 EXPORT_SYMBOL(get_user_pages_remote);
@@ -1090,11 +1074,75 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 		struct vm_area_struct **vmas)
 {
 	return __get_user_pages_locked(current, current->mm, start, nr_pages,
-				       pages, vmas, NULL, false,
+				       pages, vmas, NULL,
 				       gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
+#ifdef CONFIG_FS_DAX
+/*
+ * This is the same as get_user_pages() in that it assumes we are
+ * operating on the current task's mm, but it goes further to validate
+ * that the vmas associated with the address range are suitable for
+ * longterm elevated page reference counts. For example, filesystem-dax
+ * mappings are subject to the lifetime enforced by the filesystem and
+ * we need guarantees that longterm users like RDMA and V4L2 only
+ * establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * "longterm" == userspace controlled elevated page count lifetime.
+ * Contrast this to iov_iter_get_pages() usages which are transient.
+ */
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas_arg)
+{
+	struct vm_area_struct **vmas = vmas_arg;
+	struct vm_area_struct *vma_prev = NULL;
+	long rc, i;
+
+	if (!pages)
+		return -EINVAL;
+
+	if (!vmas) {
+		vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
+			       GFP_KERNEL);
+		if (!vmas)
+			return -ENOMEM;
+	}
+
+	rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+
+	for (i = 0; i < rc; i++) {
+		struct vm_area_struct *vma = vmas[i];
+
+		if (vma == vma_prev)
+			continue;
+
+		vma_prev = vma;
+
+		if (vma_is_fsdax(vma))
+			break;
+	}
+
+	/*
+	 * Either get_user_pages() failed, or the vma validation
+	 * succeeded, in either case we don't need to put_page() before
+	 * returning.
+	 */
+	if (i >= rc)
+		goto out;
+
+	for (i = 0; i < rc; i++)
+		put_page(pages[i]);
+	rc = -EOPNOTSUPP;
+out:
+	if (vmas != vmas_arg)
+		kfree(vmas);
+	return rc;
+}
+EXPORT_SYMBOL(get_user_pages_longterm);
+#endif /* CONFIG_FS_DAX */
+
 /**
  * populate_vma_page_range() -  populate a range of pages in the vma.
  * @vma:   target vma
@@ -1643,6 +1691,47 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+static void gup_pgd_range(unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pgd_t *pgdp;
+
+	pgdp = pgd_offset(current->mm, addr);
+	do {
+		pgd_t pgd = READ_ONCE(*pgdp);
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			return;
+		if (unlikely(pgd_huge(pgd))) {
+			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+					  pages, nr))
+				return;
+		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
+					 PGDIR_SHIFT, next, write, pages, nr))
+				return;
+		} else if (!gup_p4d_range(pgd, addr, next, write, pages, nr))
+			return;
+	} while (pgdp++, addr = next, addr != end);
+}
+
+#ifndef gup_fast_permitted
+/*
+ * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * we need to fall back to the slow version:
+ */
+bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	return end >= start;
+}
+#endif
+
 /*
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP. It will only return non-negative values.
@@ -1650,10 +1739,8 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages)
 {
-	struct mm_struct *mm = current->mm;
 	unsigned long addr, len, end;
-	unsigned long next, flags;
-	pgd_t *pgdp;
+	unsigned long flags;
 	int nr = 0;
 
 	start &= PAGE_MASK;
@@ -1677,45 +1764,15 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	 * block IPIs that come from THPs splitting.
 	 */
 
-	local_irq_save(flags);
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd_t pgd = READ_ONCE(*pgdp);
-
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (unlikely(pgd_huge(pgd))) {
-			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
-					  pages, &nr))
-				break;
-		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
-			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
-					 PGDIR_SHIFT, next, write, pages, &nr))
-				break;
-		} else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-	local_irq_restore(flags);
+	if (gup_fast_permitted(start, nr_pages, write)) {
+		local_irq_save(flags);
+		gup_pgd_range(addr, end, write, pages, &nr);
+		local_irq_restore(flags);
+	}
 
 	return nr;
 }
 
-#ifndef gup_fast_permitted
-/*
- * Check if it's allowed to use __get_user_pages_fast() for the range, or
- * we need to fall back to the slow version:
- */
-bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
-{
-	unsigned long len, end;
-
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-	return end >= start;
-}
-#endif
-
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
@@ -1735,12 +1792,22 @@ bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
+	unsigned long addr, len, end;
 	int nr = 0, ret = 0;
 
 	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					(void __user *)start, len)))
+		return 0;
 
 	if (gup_fast_permitted(start, nr_pages, write)) {
-		nr = __get_user_pages_fast(start, nr_pages, write, pages);
+		local_irq_disable();
+		gup_pgd_range(addr, end, write, pages, &nr);
+		local_irq_enable();
 		ret = nr;
 	}