sfc: Properly sync RX DMA buffer when it is not the last in the page

[ Upstream commit 3a68f19d ]

We may currently allocate two RX DMA buffers to a page, and only unmap
the page when the second is completed.  We do not sync the first RX
buffer to be completed; this can result in packet loss or corruption
if the last RX buffer completed in a NAPI poll is the first in a page
and is not DMA-coherent.  (In the middle of a NAPI poll, we will
handle the following RX completion and unmap the page *before* looking
at the content of the first buffer.)
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

drivers/net/ethernet/sfc/rx.c

@@ -246,7 +246,8 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 }
 
 static void efx_unmap_rx_buffer(struct efx_nic *efx,
-				struct efx_rx_buffer *rx_buf)
+				struct efx_rx_buffer *rx_buf,
+				unsigned int used_len)
 {
 	if (rx_buf->is_page && rx_buf->u.page) {
 		struct efx_rx_page_state *state;
@@ -257,6 +258,10 @@ static void efx_unmap_rx_buffer(struct efx_nic *efx,
 				       state->dma_addr,
 				       efx_rx_buf_size(efx),
 				       PCI_DMA_FROMDEVICE);
+		} else if (used_len) {
+			dma_sync_single_for_cpu(&efx->pci_dev->dev,
+						rx_buf->dma_addr, used_len,
+						DMA_FROM_DEVICE);
 		}
 	} else if (!rx_buf->is_page && rx_buf->u.skb) {
 		pci_unmap_single(efx->pci_dev, rx_buf->dma_addr,
@@ -279,7 +284,7 @@ static void efx_free_rx_buffer(struct efx_nic *efx,
 static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue,
 			       struct efx_rx_buffer *rx_buf)
 {
-	efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
+	efx_unmap_rx_buffer(rx_queue->efx, rx_buf, 0);
 	efx_free_rx_buffer(rx_queue->efx, rx_buf);
 }
 
@@ -550,10 +555,10 @@ void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
 		goto out;
 	}
 
-	/* Release card resources - assumes all RX buffers consumed in-order
-	 * per RX queue
+	/* Release and/or sync DMA mapping - assumes all RX buffers
+	 * consumed in-order per RX queue
 	 */
-	efx_unmap_rx_buffer(efx, rx_buf);
+	efx_unmap_rx_buffer(efx, rx_buf, len);
 
 	/* Prefetch nice and early so data will (hopefully) be in cache by
 	 * the time we look at it.