net: ethernet: mediatek: enhance RX path by aggregating more SKBs into NAPI

The patch adds support for aggregating more SKBs feed into NAPI in
order to get more benefits from generic receive offload (GRO) by
peeking at the RX ring status and moving more packets right before
returning from NAPI RX polling handler if NAPI budgets are still
available and some packets already present in hardware.
Signed-off-by: NSean Wang <sean.wang@mediatek.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/mediatek/mtk_eth_soc.c

@@ -898,14 +898,14 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 		done++;
 	}
-	/* make sure that all changes to the dma ring are flushed before
-	 * we continue
-	 */
-	wmb();
-	mtk_w32(eth, ring->calc_idx, MTK_PRX_CRX_IDX0);
 
-	if (done < budget)
-		mtk_w32(eth, MTK_RX_DONE_INT, MTK_PDMA_INT_STATUS);
+	if (done) {
+		/* make sure that all changes to the dma ring are flushed before
+		 * we continue
+		 */
+		wmb();
+		mtk_w32(eth, ring->calc_idx, MTK_PRX_CRX_IDX0);
+	}
 
 	return done;
 }
@@ -1025,10 +1025,13 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget)
 	struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi);
 	u32 status, mask;
 	int rx_done = 0;
+	int remain_budget = budget;
 
 	mtk_handle_status_irq(eth);
+
+poll_again:
 	mtk_w32(eth, MTK_RX_DONE_INT, MTK_PDMA_INT_STATUS);
-	rx_done = mtk_poll_rx(napi, budget, eth);
+	rx_done = mtk_poll_rx(napi, remain_budget, eth);
 
 	if (unlikely(netif_msg_intr(eth))) {
 		status = mtk_r32(eth, MTK_PDMA_INT_STATUS);
@@ -1037,18 +1040,18 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget)
 			 "done rx %d, intr 0x%08x/0x%x\n",
 			 rx_done, status, mask);
 	}
-
-	if (rx_done == budget)
+	if (rx_done == remain_budget)
 		return budget;
 
 	status = mtk_r32(eth, MTK_PDMA_INT_STATUS);
-	if (status & MTK_RX_DONE_INT)
-		return budget;
-
+	if (status & MTK_RX_DONE_INT) {
+		remain_budget -= rx_done;
+		goto poll_again;
+	}
 	napi_complete(napi);
 	mtk_irq_enable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 
-	return rx_done;
+	return rx_done + budget - remain_budget;
 }
 
 static int mtk_tx_alloc(struct mtk_eth *eth)