1 files changed, 59 insertions, 57 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 42b8b1fa6521..9935a4480710 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -62,11 +62,24 @@ static void put_page_refs(struct page *page, int refs)
 	put_page(page);
 }
 
-/*
- * Return the compound head page with ref appropriately incremented,
- * or NULL if that failed.
+/**
+ * try_get_compound_head() - return the compound head page with refcount
+ * appropriately incremented, or NULL if that failed.
+ *
+ * This handles potential refcount overflow correctly. It also works correctly
+ * for various lockless get_user_pages()-related callers, due to the use of
+ * page_cache_add_speculative().
+ *
+ * Even though the name includes "compound_head", this function is still
+ * appropriate for callers that have a non-compound @page to get.
+ *
+ * @page:  pointer to page to be gotten
+ * @refs:  the value to add to the page's refcount
+ *
+ * Return: head page (with refcount appropriately incremented) for success, or
+ * NULL upon failure.
  */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
+struct page *try_get_compound_head(struct page *page, int refs)
 {
 	struct page *head = compound_head(page);
 
@@ -92,10 +105,17 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
 	return head;
 }
 
-/*
+/**
  * try_grab_compound_head() - attempt to elevate a page's refcount, by a
  * flags-dependent amount.
  *
+ * Even though the name includes "compound_head", this function is still
+ * appropriate for callers that have a non-compound @page to get.
+ *
+ * @page:  pointer to page to be grabbed
+ * @refs:  the value to (effectively) add to the page's refcount
+ * @flags: gup flags: these are the FOLL_* flag values.
+ *
  * "grab" names in this file mean, "look at flags to decide whether to use
  * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
  *
@@ -103,22 +123,26 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
  * same time. (That's true throughout the get_user_pages*() and
  * pin_user_pages*() APIs.) Cases:
  *
- *    FOLL_GET: page's refcount will be incremented by 1.
- *    FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *    FOLL_GET: page's refcount will be incremented by @refs.
+ *
+ *    FOLL_PIN on compound pages that are > two pages long: page's refcount will
+ *    be incremented by @refs, and page[2].hpage_pinned_refcount will be
+ *    incremented by @refs * GUP_PIN_COUNTING_BIAS.
+ *
+ *    FOLL_PIN on normal pages, or compound pages that are two pages long:
+ *    page's refcount will be incremented by @refs * GUP_PIN_COUNTING_BIAS.
  *
  * Return: head page (with refcount appropriately incremented) for success, or
  * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's
  * considered failure, and furthermore, a likely bug in the caller, so a warning
  * is also emitted.
  */
-__maybe_unused struct page *try_grab_compound_head(struct page *page,
-						   int refs, unsigned int flags)
+struct page *try_grab_compound_head(struct page *page,
+				    int refs, unsigned int flags)
 {
 	if (flags & FOLL_GET)
 		return try_get_compound_head(page, refs);
 	else if (flags & FOLL_PIN) {
-		int orig_refs = refs;
-
 		/*
 		 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
 		 * right zone, so fail and let the caller fall back to the slow
@@ -143,6 +167,8 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page,
 		 *
 		 * However, be sure to *also* increment the normal page refcount
 		 * field at least once, so that the page really is pinned.
+		 * That's why the refcount from the earlier
+		 * try_get_compound_head() is left intact.
 		 */
 		if (hpage_pincount_available(page))
 			hpage_pincount_add(page, refs);
@@ -150,7 +176,7 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page,
 			page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1));
 
 		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
-				    orig_refs);
+				    refs);
 
 		return page;
 	}
@@ -186,10 +212,8 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
  * @flags:   gup flags: these are the FOLL_* flag values.
  *
  * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
- * time. Cases:
- *
- *    FOLL_GET: page's refcount will be incremented by 1.
- *    FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ * time. Cases: please see the try_grab_compound_head() documentation, with
+ * "refs=1".
  *
  * Return: true for success, or if no action was required (if neither FOLL_PIN
  * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
@@ -197,35 +221,10 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
  */
 bool __must_check try_grab_page(struct page *page, unsigned int flags)
 {
-	WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
+	if (!(flags & (FOLL_GET | FOLL_PIN)))
+		return true;
 
-	if (flags & FOLL_GET)
-		return try_get_page(page);
-	else if (flags & FOLL_PIN) {
-		int refs = 1;
-
-		page = compound_head(page);
-
-		if (WARN_ON_ONCE(page_ref_count(page) <= 0))
-			return false;
-
-		if (hpage_pincount_available(page))
-			hpage_pincount_add(page, 1);
-		else
-			refs = GUP_PIN_COUNTING_BIAS;
-
-		/*
-		 * Similar to try_grab_compound_head(): even if using the
-		 * hpage_pincount_add/_sub() routines, be sure to
-		 * *also* increment the normal page refcount field at least
-		 * once, so that the page really is pinned.
-		 */
-		page_ref_add(page, refs);
-
-		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1);
-	}
-
-	return true;
+	return try_grab_compound_head(page, 1, flags);
 }
 
 /**
@@ -1151,7 +1150,6 @@ static long __get_user_pages(struct mm_struct *mm,
 					 * We must stop here.
 					 */
 					BUG_ON(gup_flags & FOLL_NOWAIT);
-					BUG_ON(ret != 0);
 					goto out;
 				}
 				continue;
@@ -1276,7 +1274,7 @@ int fixup_user_fault(struct mm_struct *mm,
 		     bool *unlocked)
 {
 	struct vm_area_struct *vma;
-	vm_fault_t ret, major = 0;
+	vm_fault_t ret;
 
 	address = untagged_addr(address);
 
@@ -1296,7 +1294,6 @@ retry:
 		return -EINTR;
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
-	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, 0);
 
@@ -1475,8 +1472,8 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	unsigned long nr_pages = (end - start) / PAGE_SIZE;
 	int gup_flags;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(end   & ~PAGE_MASK);
+	VM_BUG_ON(!PAGE_ALIGNED(start));
+	VM_BUG_ON(!PAGE_ALIGNED(end));
 	VM_BUG_ON_VMA(start < vma->vm_start, vma);
 	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
 	mmap_assert_locked(mm);
@@ -1558,9 +1555,12 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
 		gup_flags |= FOLL_WRITE;
 
 	/*
-	 * See check_vma_flags(): Will return -EFAULT on incompatible mappings
-	 * or with insufficient permissions.
+	 * We want to report -EINVAL instead of -EFAULT for any permission
+	 * problems or incompatible mappings.
 	 */
+	if (check_vma_flags(vma, gup_flags))
+		return -EINVAL;
+
 	return __get_user_pages(mm, start, nr_pages, gup_flags,
 				NULL, NULL, locked);
 }
@@ -1772,7 +1772,7 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 	if (!list_empty(&movable_page_list)) {
 		ret = migrate_pages(&movable_page_list, alloc_migration_target,
 				    NULL, (unsigned long)&mtc, MIGRATE_SYNC,
-				    MR_LONGTERM_PIN);
+				    MR_LONGTERM_PIN, NULL);
 		if (ret && !list_empty(&movable_page_list))
 			putback_movable_pages(&movable_page_list);
 	}
@@ -2241,6 +2241,7 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 {
 	int nr_start = *nr;
 	struct dev_pagemap *pgmap = NULL;
+	int ret = 1;
 
 	do {
 		struct page *page = pfn_to_page(pfn);
@@ -2248,21 +2249,22 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 		pgmap = get_dev_pagemap(pfn, pgmap);
 		if (unlikely(!pgmap)) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
-			return 0;
+			ret = 0;
+			break;
 		}
 		SetPageReferenced(page);
 		pages[*nr] = page;
 		if (unlikely(!try_grab_page(page, flags))) {
 			undo_dev_pagemap(nr, nr_start, flags, pages);
-			return 0;
+			ret = 0;
+			break;
 		}
 		(*nr)++;
 		pfn++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	if (pgmap)
-		put_dev_pagemap(pgmap);
-	return 1;
+	put_dev_pagemap(pgmap);
+	return ret;
 }
 
 static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,