Merge branch 'page_pool-DMA-sync'

Lorenzo Bianconi says:

====================
add DMA-sync-for-device capability to page_pool API

Introduce the possibility to sync DMA memory for device in the page_pool API.
This feature allows to sync proper DMA size and not always full buffer
(dma_sync_single_for_device can be very costly).
Please note DMA-sync-for-CPU is still device driver responsibility.
Relying on page_pool DMA sync mvneta driver improves XDP_DROP pps of
about 170Kpps:

- XDP_DROP DMA sync managed by mvneta driver: ~420Kpps
- XDP_DROP DMA sync managed by page_pool API: ~585Kpps

Do not change naming convention for the moment since the changes will hit other
drivers as well. I will address it in another series.

Changes since v4:
- do not allow the driver to set max_len to 0
- convert PP_FLAG_DMA_MAP/PP_FLAG_DMA_SYNC_DEV to BIT() macro

Changes since v3:
- move dma_sync_for_device before putting the page in ptr_ring in
__page_pool_recycle_into_ring since ptr_ring can be consumed
concurrently. Simplify the code moving dma_sync_for_device
before running __page_pool_recycle_direct/__page_pool_recycle_into_ring

Changes since v2:
- rely on PP_FLAG_DMA_SYNC_DEV flag instead of dma_sync

Changes since v1:
- rename sync in dma_sync
- set dma_sync_size to 0xFFFFFFFF in page_pool_recycle_direct and
page_pool_put_page routines
- Improve documentation
====================

Acked-by: Ilias Apalodimas <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/marvell/mvneta.c

···
 			    struct mvneta_rx_queue *rxq,
 			    gfp_t gfp_mask)
 {
-	enum dma_data_direction dma_dir;
 	dma_addr_t phys_addr;
 	struct page *page;
 
···
 		return -ENOMEM;
 
 	phys_addr = page_pool_get_dma_addr(page) + pp->rx_offset_correction;
-	dma_dir = page_pool_get_dma_dir(rxq->page_pool);
-	dma_sync_single_for_device(pp->dev->dev.parent, phys_addr,
-				   MVNETA_MAX_RX_BUF_SIZE, dma_dir);
 	mvneta_rx_desc_fill(rx_desc, phys_addr, page, rxq);
 
 	return 0;
···
 		err = xdp_do_redirect(pp->dev, xdp, prog);
 		if (err) {
 			ret = MVNETA_XDP_DROPPED;
-			xdp_return_buff(xdp);
+			__page_pool_put_page(rxq->page_pool,
+					virt_to_head_page(xdp->data),
+					xdp->data_end - xdp->data_hard_start,
+					true);
 		} else {
 			ret = MVNETA_XDP_REDIR;
 		}
···
 	case XDP_TX:
 		ret = mvneta_xdp_xmit_back(pp, xdp);
 		if (ret != MVNETA_XDP_TX)
-			xdp_return_buff(xdp);
+			__page_pool_put_page(rxq->page_pool,
+					virt_to_head_page(xdp->data),
+					xdp->data_end - xdp->data_hard_start,
+					true);
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
···
 		trace_xdp_exception(pp->dev, prog, act);
 		/* fall through */
 	case XDP_DROP:
-		page_pool_recycle_direct(rxq->page_pool,
-					 virt_to_head_page(xdp->data));
+		__page_pool_put_page(rxq->page_pool,
+				     virt_to_head_page(xdp->data),
+				     xdp->data_end - xdp->data_hard_start,
+				     true);
 		ret = MVNETA_XDP_DROPPED;
 		break;
 	}
···
 	struct bpf_prog *xdp_prog = READ_ONCE(pp->xdp_prog);
 	struct page_pool_params pp_params = {
 		.order = 0,
-		.flags = PP_FLAG_DMA_MAP,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.pool_size = size,
 		.nid = cpu_to_node(0),
 		.dev = pp->dev->dev.parent,
 		.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
+		.offset = pp->rx_offset_correction,
+		.max_len = MVNETA_MAX_RX_BUF_SIZE,
 	};
 	int err;
 

include/net/page_pool.h

···
 #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
···
 	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 {
···
 #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)
···
 	 * 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

net/core/page_pool.c

···
 	    (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;
 
···
 	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,
···
 		return NULL;
 	}
 	page->dma_addr = 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' */
···
 	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
···
 	if (likely(page_ref_count(page) == 1 &&
 		   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))