How about moving the flags into the union?  A bit messy, but we don't
have to play games with __packed__.

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1210a8e41fad..f374d2f06255 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -68,16 +68,22 @@ struct mem_cgroup;
 #endif
 
 struct page {
-	unsigned long flags;		/* Atomic flags, some possibly
-					 * updated asynchronously */
 	/*
-	 * Five words (20/40 bytes) are available in this union.
-	 * WARNING: bit 0 of the first word is used for PageTail(). That
-	 * means the other users of this union MUST NOT use the bit to
+	 * This union is six words (24 / 48 bytes) in size.
+	 * The first word is reserved for atomic flags, often updated
+	 * asynchronously.  Use the PageFoo() macros to access it.  Some
+	 * of the flags can be reused for your own purposes, but the
+	 * word as a whole often contains other information and overwriting
+	 * it will cause functions like page_zone() and page_node() to stop
+	 * working correctly.
+	 *
+	 * Bit 0 of the second word is used for PageTail(). That
+	 * means the other users of this union MUST leave the bit zero to
 	 * avoid collision and false-positive PageTail().
 	 */
 	union {
 		struct {	/* Page cache and anonymous pages */
+			unsigned long flags;
 			/**
 			 * @lru: Pageout list, eg. active_list protected by
 			 * lruvec->lru_lock.  Sometimes used as a generic list
@@ -96,6 +102,8 @@ struct page {
 			unsigned long private;
 		};
 		struct {	/* page_pool used by netstack */
+			unsigned long _pp_flags;
+			unsigned long _pp_pad;
 			/**
 			 * @dma_addr: might require a 64-bit value even on
 			 * 32-bit architectures.
@@ -103,6 +111,7 @@ struct page {
 			dma_addr_t dma_addr;
 		};
 		struct {	/* slab, slob and slub */
+			unsigned long _slab_flags;
 			union {
 				struct list_head slab_list;
 				struct {	/* Partial pages */
@@ -130,6 +139,7 @@ struct page {
 			};
 		};
 		struct {	/* Tail pages of compound page */
+			unsigned long _tail1_flags;
 			unsigned long compound_head;	/* Bit zero is set */
 
 			/* First tail page only */
@@ -139,12 +149,14 @@ struct page {
 			unsigned int compound_nr; /* 1 << compound_order */
 		};
 		struct {	/* Second tail page of compound page */
+			unsigned long _tail2_flags;
 			unsigned long _compound_pad_1;	/* compound_head */
 			atomic_t hpage_pinned_refcount;
 			/* For both global and memcg */
 			struct list_head deferred_list;
 		};
 		struct {	/* Page table pages */
+			unsigned long _pt_flags;
 			unsigned long _pt_pad_1;	/* compound_head */
 			pgtable_t pmd_huge_pte; /* protected by page->ptl */
 			unsigned long _pt_pad_2;	/* mapping */
@@ -159,6 +171,7 @@ struct page {
 #endif
 		};
 		struct {	/* ZONE_DEVICE pages */
+			unsigned long _zd_flags;
 			/** @pgmap: Points to the hosting device page map. */
 			struct dev_pagemap *pgmap;
 			void *zone_device_data;
@@ -174,8 +187,11 @@ struct page {
 			 */
 		};
 
-		/** @rcu_head: You can use this to free a page by RCU. */
-		struct rcu_head rcu_head;
+		struct {
+			unsigned long _rcu_flags;
+			/** @rcu_head: You can use this to free a page by RCU. */
+			struct rcu_head rcu_head;
+		};
 	};
 
 	union {		/* This union is 4 bytes in size. */