diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 17e59e9e8064..02b018469bb9 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -34,8 +34,18 @@
 #include <linux/ptr_ring.h>
 #include <linux/dma-direction.h>
 
-#define PP_FLAG_DMA_MAP 1 /* Should page_pool do the DMA map/unmap */
-#define PP_FLAG_ALL	PP_FLAG_DMA_MAP
+#define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
+					* map/unmap
+					*/
+#define PP_FLAG_DMA_SYNC_DEV	BIT(1) /* If set all pages that the driver gets
+					* from page_pool will be
+					* DMA-synced-for-device according to
+					* the length provided by the device
+					* driver.
+					* Please note DMA-sync-for-CPU is still
+					* device driver responsibility
+					*/
+#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)
 
 /*
  * Fast allocation side cache array/stack
@@ -65,6 +75,8 @@ struct page_pool_params {
 	int		nid;  /* Numa node id to allocate from pages from */
 	struct device	*dev; /* device, for DMA pre-mapping purposes */
 	enum dma_data_direction dma_dir; /* DMA mapping direction */
+	unsigned int	max_len; /* max DMA sync memory size */
+	unsigned int	offset;  /* DMA addr offset */
 };
 
 struct page_pool {
@@ -149,8 +161,8 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 #endif
 
 /* Never call this directly, use helpers below */
-void __page_pool_put_page(struct page_pool *pool,
-			  struct page *page, bool allow_direct);
+void __page_pool_put_page(struct page_pool *pool, struct page *page,
+			  unsigned int dma_sync_size, bool allow_direct);
 
 static inline void page_pool_put_page(struct page_pool *pool,
 				      struct page *page, bool allow_direct)
@@ -159,14 +171,14 @@ static inline void page_pool_put_page(struct page_pool *pool,
 	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
 	 */
 #ifdef CONFIG_PAGE_POOL
-	__page_pool_put_page(pool, page, allow_direct);
+	__page_pool_put_page(pool, page, -1, allow_direct);
 #endif
 }
 /* Very limited use-cases allow recycle direct */
 static inline void page_pool_recycle_direct(struct page_pool *pool,
 					    struct page *page)
 {
-	__page_pool_put_page(pool, page, true);
+	__page_pool_put_page(pool, page, -1, true);
 }
 
 /* Disconnects a page (from a page_pool).  API users can have a need
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 53681aedd134..96365f98fa95 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -47,6 +47,21 @@ static int page_pool_init(struct page_pool *pool,
 	    (pool->p.dma_dir != DMA_BIDIRECTIONAL))
 		return -EINVAL;
 
+	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+		/* In order to request DMA-sync-for-device the page
+		 * needs to be mapped
+		 */
+		if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+			return -EINVAL;
+
+		if (!pool->p.max_len)
+			return -EINVAL;
+
+		/* pool->p.offset has to be set according to the address
+		 * offset used by the DMA engine to start copying rx data
+		 */
+	}
+
 	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
 		return -ENOMEM;
 
@@ -115,6 +130,16 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
 	return page;
 }
 
+static void page_pool_dma_sync_for_device(struct page_pool *pool,
+					  struct page *page,
+					  unsigned int dma_sync_size)
+{
+	dma_sync_size = min(dma_sync_size, pool->p.max_len);
+	dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+					 pool->p.offset, dma_sync_size,
+					 pool->p.dma_dir);
+}
+
 /* slow path */
 noinline
 static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
@@ -159,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
 	}
 	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);
+
 skip_dma_map:
 	/* Track how many pages are held 'in-flight' */
 	pool->pages_state_hold_cnt++;
@@ -292,8 +320,8 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
 	return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid;
 }
 
-void __page_pool_put_page(struct page_pool *pool,
-			  struct page *page, bool allow_direct)
+void __page_pool_put_page(struct page_pool *pool, struct page *page,
+			  unsigned int dma_sync_size, bool allow_direct)
 {
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
@@ -305,6 +333,10 @@ void __page_pool_put_page(struct page_pool *pool,
 		   pool_page_reusable(pool, page))) {
 		/* Read barrier done in page_ref_count / READ_ONCE */
 
+		if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+			page_pool_dma_sync_for_device(pool, page,
+						      dma_sync_size);
+
 		if (allow_direct && in_serving_softirq())
 			if (__page_pool_recycle_direct(page, pool))
 				return;