mm: Fix struct page layout on 32-bit systems

32-bit architectures which expect 8-byte alignment for 8-byte integers
and need 64-bit DMA addresses (arc, arm, mips, ppc) had their struct
page inadvertently expanded in 2019.  When the dma_addr_t was added,
it forced the alignment of the union to 8 bytes, which inserted a 4 byte
gap between 'flags' and the union.

Fix this by storing the dma_addr_t in one or two adjacent unsigned longs.
This restores the alignment to that of an unsigned long, and also fixes a
potential problem where (on a big endian platform), the bit used to denote
PageTail could inadvertently get set, and a racing get_user_pages_fast()
could dereference a bogus compound_head().

Fixes: c25fff7 ("mm: add dma_addr_t to struct page")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>

include/linux/mm_types.h

@@ -97,10 +97,10 @@ struct page {
 		};
 		struct {	/* page_pool used by netstack */
 			/**
-			 * @dma_addr: might require a 64-bit value even on
+			 * @dma_addr: might require a 64-bit value on
 			 * 32-bit architectures.
 			 */
-			dma_addr_t dma_addr;
+			unsigned long dma_addr[2];
 		};
 		struct {	/* slab, slob and slub */
 			union {

include/net/page_pool.h

@@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 
 static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
 {
-	return page->dma_addr;
+	dma_addr_t ret = page->dma_addr[0];
+	if (sizeof(dma_addr_t) > sizeof(unsigned long))
+		ret |= (dma_addr_t)page->dma_addr[1] << 32;
+	return ret;
+}
+
+static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+{
+	page->dma_addr[0] = addr;
+	if (sizeof(dma_addr_t) > sizeof(unsigned long))
+		page->dma_addr[1] = addr >> 32;
 }
 
 static inline bool is_page_pool_compiled_in(void)

net/core/page_pool.c

@@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool,
 					  struct page *page,
 					  unsigned int dma_sync_size)
 {
+	dma_addr_t dma_addr = page_pool_get_dma_addr(page);
+
 	dma_sync_size = min(dma_sync_size, pool->p.max_len);
-	dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+	dma_sync_single_range_for_device(pool->p.dev, dma_addr,
 					 pool->p.offset, dma_sync_size,
 					 pool->p.dma_dir);
 }
@@ -226,7 +228,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 		put_page(page);
 		return NULL;
 	}
-	page->dma_addr = dma;
+	page_pool_set_dma_addr(page, dma);
 
 	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
 		page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
@@ -294,13 +296,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page)
 		 */
 		goto skip_dma_unmap;
 
-	dma = page->dma_addr;
+	dma = page_pool_get_dma_addr(page);
 
-	/* When page is unmapped, it cannot be returned our pool */
+	/* When page is unmapped, it cannot be returned to our pool */
 	dma_unmap_page_attrs(pool->p.dev, dma,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC);
-	page->dma_addr = 0;
+	page_pool_set_dma_addr(page, 0);
 skip_dma_unmap:
 	/* This may be the last page returned, releasing the pool, so
 	 * it is not safe to reference pool afterwards.