ice: map Rx buffer pages with DMA attributes

Provide DMA_ATTR_WEAK_ORDERING and DMA_ATTR_SKIP_CPU_SYNC attributes to
the DMA API during the mapping operations on Rx side. With this change
the non-x86 platforms will be able to sync only with what is being used
(2k buffer) instead of entire page. This should yield a slight
performance improvement.

Furthermore, DMA unmap may destroy the changes that were made to the
buffer by CPU when platform is not a x86 one. DMA_ATTR_SKIP_CPU_SYNC
attribute usage fixes this issue.

Also add a sync_single_for_device call during the Rx buffer assignment,
to make sure that the cache lines are cleared before device attempting
to write to the buffer.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -282,7 +282,16 @@ void ice_clean_rx_ring(struct ice_ring *rx_ring)
 		if (!rx_buf->page)
 			continue;
 
-		dma_unmap_page(dev, rx_buf->dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(dev, rx_buf->dma,
+					      rx_buf->page_offset,
+					      ICE_RXBUF_2048, DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(dev, rx_buf->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
 		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
 
 		rx_buf->page = NULL;
@@ -409,7 +418,8 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi)
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
+				 DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
@@ -454,6 +464,12 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 		if (!ice_alloc_mapped_page(rx_ring, bi))
 			goto no_bufs;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 ICE_RXBUF_2048,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -726,8 +742,8 @@ static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
 		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
 	}
 

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -47,6 +47,9 @@
 #define ICE_TX_FLAGS_VLAN_M	0xffff0000
 #define ICE_TX_FLAGS_VLAN_S	16
 
+#define ICE_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 struct ice_tx_buf {
 	struct ice_tx_desc *next_to_watch;
 	struct sk_buff *skb;