lan966x: Don't use xdp_frame when action is XDP_TX

When the action of an xdp program was XDP_TX, lan966x was creating
a xdp_frame and use this one to send the frame back. But it is also
possible to send back the frame without needing a xdp_frame, because
it is possible to send it back using the page.
And then once the frame is transmitted is possible to use directly
page_pool_recycle_direct as lan966x is using page pools.
This would save some CPU usage on this path, which results in higher
number of transmitted frames. Bellow are the statistics:
Frame size:    Improvement:
64                ~8%
256              ~11%
512               ~8%
1000              ~0%
1500              ~0%

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20230422142344.3630602-1-horatiu.vultur@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 23 insertions, 12 deletions

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 2ed76bb61a73..bd72fbc2220f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -390,6 +390,7 @@ static void lan966x_fdma_stop_netdev(struct lan966x *lan966x)
 static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 {
 	struct lan966x_tx *tx = &lan966x->tx;
+	struct lan966x_rx *rx = &lan966x->rx;
 	struct lan966x_tx_dcb_buf *dcb_buf;
 	struct xdp_frame_bulk bq;
 	struct lan966x_db *db;
@@ -432,7 +433,8 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 			if (dcb_buf->xdp_ndo)
 				xdp_return_frame_bulk(dcb_buf->data.xdpf, &bq);
 			else
-				xdp_return_frame_rx_napi(dcb_buf->data.xdpf);
+				page_pool_recycle_direct(rx->page_pool,
+							 dcb_buf->data.page);
 		}
 
 		clear = true;
@@ -699,15 +701,14 @@ static void lan966x_fdma_tx_start(struct lan966x_tx *tx, int next_to_use)
 	tx->last_in_use = next_to_use;
 }
 
-int lan966x_fdma_xmit_xdpf(struct lan966x_port *port,
-			   struct xdp_frame *xdpf,
-			   struct page *page,
-			   bool dma_map)
+int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 {
 	struct lan966x *lan966x = port->lan966x;
 	struct lan966x_tx_dcb_buf *next_dcb_buf;
 	struct lan966x_tx *tx = &lan966x->tx;
+	struct xdp_frame *xdpf;
 	dma_addr_t dma_addr;
+	struct page *page;
 	int next_to_use;
 	__be32 *ifh;
 	int ret = 0;
@@ -722,8 +723,13 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port,
 		goto out;
 	}
 
+	/* Get the next buffer */
+	next_dcb_buf = &tx->dcbs_buf[next_to_use];
+
 	/* Generate new IFH */
-	if (dma_map) {
+	if (!len) {
+		xdpf = ptr;
+
 		if (xdpf->headroom < IFH_LEN_BYTES) {
 			ret = NETDEV_TX_OK;
 			goto out;
@@ -743,11 +749,16 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port,
 			goto out;
 		}
 
+		next_dcb_buf->data.xdpf = xdpf;
+		next_dcb_buf->len = xdpf->len + IFH_LEN_BYTES;
+
 		/* Setup next dcb */
 		lan966x_fdma_tx_setup_dcb(tx, next_to_use,
 					  xdpf->len + IFH_LEN_BYTES,
 					  dma_addr);
 	} else {
+		page = ptr;
+
 		ifh = page_address(page) + XDP_PACKET_HEADROOM;
 		memset(ifh, 0x0, sizeof(__be32) * IFH_LEN);
 		lan966x_ifh_set_bypass(ifh, 1);
@@ -756,21 +767,21 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port,
 		dma_addr = page_pool_get_dma_addr(page);
 		dma_sync_single_for_device(lan966x->dev,
 					   dma_addr + XDP_PACKET_HEADROOM,
-					   xdpf->len + IFH_LEN_BYTES,
+					   len + IFH_LEN_BYTES,
 					   DMA_TO_DEVICE);
 
+		next_dcb_buf->data.page = page;
+		next_dcb_buf->len = len + IFH_LEN_BYTES;
+
 		/* Setup next dcb */
 		lan966x_fdma_tx_setup_dcb(tx, next_to_use,
-					  xdpf->len + IFH_LEN_BYTES,
+					  len + IFH_LEN_BYTES,
 					  dma_addr + XDP_PACKET_HEADROOM);
 	}
 
 	/* Fill up the buffer */
-	next_dcb_buf = &tx->dcbs_buf[next_to_use];
 	next_dcb_buf->use_skb = false;
-	next_dcb_buf->data.xdpf = xdpf;
-	next_dcb_buf->xdp_ndo = dma_map;
-	next_dcb_buf->len = xdpf->len + IFH_LEN_BYTES;
+	next_dcb_buf->xdp_ndo = !len;
 	next_dcb_buf->dma_addr = dma_addr;
 	next_dcb_buf->used = true;
 	next_dcb_buf->ptp = false;