[PATCH wireless-next 8/8] wifi: rt2x00usb: use a threaded NAPI with GRO for RX

[Ho Jie Feng <hjf3108@gmail.com>]

GRO makes sense now that RX aggregation is enabled, since multiple
frames arrive at once.

This code is referenced from commit 5323d3e50c20
("wifi: mt76: mt76u: use a threaded NAPI for the RX path")

Test results:
   before after
TX 30.5   30.5
RX 80.9   161.7

Signed-off-by: Ho Jie Feng <hjf3108@gmail.com>
---
 drivers/net/wireless/ralink/rt2x00/rt2x00.h   |  7 ++-
 .../net/wireless/ralink/rt2x00/rt2x00dev.c    |  6 ++-
 .../net/wireless/ralink/rt2x00/rt2x00usb.c    | 49 ++++++++++++++++---
 3 files changed, 52 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 5bc077fce9cbf..a120adb18f4b8 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -955,9 +955,14 @@ struct rt2x00_dev {
 	/**
 	 * Scheduled work for TX/RX done handling (USB devices)
 	 */
-	struct work_struct rxdone_work;
 	struct work_struct txdone_work;
 
+	/*
+	 * NAPI context for RX done handling (USB devices).
+	 */
+	struct net_device *napi_dev;
+	struct napi_struct napi;
+
 	/*
 	 * Powersaving work
 	 */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
index 351e7da178279..4527fdf905b15 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
@@ -846,7 +846,11 @@ static void rt2x00lib_rxdone_skb(struct queue_entry *entry)
 	rx_status->bw = rxdesc.bw;
 	rx_status->antenna = rt2x00dev->link.ant.active.rx;
 
-	ieee80211_rx_ni(rt2x00dev->hw, entry->skb);
+	if (rt2x00dev->napi_dev)
+		ieee80211_rx_napi(rt2x00dev->hw, NULL, entry->skb,
+				  &rt2x00dev->napi);
+	else
+		ieee80211_rx_ni(rt2x00dev->hw, entry->skb);
 }
 
 void rt2x00lib_rxdone(struct queue_entry *entry, unsigned int len, gfp_t gfp)
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
index 4519a20a7f4bc..d11244a2c4f2e 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
@@ -341,10 +341,10 @@ static bool rt2x00usb_kick_tx_entry(struct queue_entry *entry, void *data)
 /*
  * RX data handlers.
  */
-static void rt2x00usb_work_rxdone(struct work_struct *work)
+static int rt2x00usb_poll_rxdone(struct napi_struct *napi, int budget)
 {
 	struct rt2x00_dev *rt2x00dev =
-	    container_of(work, struct rt2x00_dev, rxdone_work);
+	    container_of(napi, struct rt2x00_dev, napi);
 	struct queue_entry_priv_usb *entry_priv;
 	struct queue_entry *entry;
 	struct skb_frame_desc *skbdesc;
@@ -368,8 +368,12 @@ static void rt2x00usb_work_rxdone(struct work_struct *work)
 		 */
 		entry_priv = entry->priv_data;
 		rt2x00lib_rxdone(entry, entry_priv->urb->actual_length,
-				 GFP_KERNEL);
+				 GFP_ATOMIC);
 	}
+
+	napi_complete(napi);
+
+	return 0;
 }
 
 static void rt2x00usb_interrupt_rxdone(struct urb *urb)
@@ -396,7 +400,7 @@ static void rt2x00usb_interrupt_rxdone(struct urb *urb)
 	/*
 	 * Schedule the delayed work for processing RX data
 	 */
-	queue_work(rt2x00dev->workqueue, &rt2x00dev->rxdone_work);
+	napi_schedule(&rt2x00dev->napi);
 }
 
 static bool rt2x00usb_kick_rx_entry(struct queue_entry *entry, void *data)
@@ -496,7 +500,7 @@ void rt2x00usb_flush_queue(struct data_queue *queue, bool drop)
 		completion = &queue->rt2x00dev->txdone_work;
 		break;
 	case QID_RX:
-		completion = &queue->rt2x00dev->rxdone_work;
+		completion = NULL;
 		break;
 	default:
 		return;
@@ -515,7 +519,13 @@ void rt2x00usb_flush_queue(struct data_queue *queue, bool drop)
 		 * Schedule the completion handler manually, when this
 		 * worker function runs, it should cleanup the queue.
 		 */
-		queue_work(queue->rt2x00dev->workqueue, completion);
+		if (completion) {
+			queue_work(queue->rt2x00dev->workqueue, completion);
+		} else {
+			local_bh_disable();
+			napi_schedule(&queue->rt2x00dev->napi);
+			local_bh_enable();
+		}
 
 		/*
 		 * Wait for a little while to give the driver
@@ -750,7 +760,7 @@ void rt2x00usb_uninitialize(struct rt2x00_dev *rt2x00dev)
 
 	usb_kill_anchored_urbs(rt2x00dev->anchor);
 	hrtimer_cancel(&rt2x00dev->txstatus_timer);
-	cancel_work_sync(&rt2x00dev->rxdone_work);
+	napi_synchronize(&rt2x00dev->napi);
 	cancel_work_sync(&rt2x00dev->txdone_work);
 
 	queue_for_each(rt2x00dev, queue)
@@ -758,6 +768,14 @@ void rt2x00usb_uninitialize(struct rt2x00_dev *rt2x00dev)
 }
 EXPORT_SYMBOL_GPL(rt2x00usb_uninitialize);
 
+static void rt2x00usb_free_napi(struct rt2x00_dev *rt2x00dev)
+{
+	napi_disable(&rt2x00dev->napi);
+	netif_napi_del(&rt2x00dev->napi);
+	free_netdev(rt2x00dev->napi_dev);
+	rt2x00dev->napi_dev = NULL;
+}
+
 int rt2x00usb_probe(struct usb_interface *usb_intf,
 		    const struct rt2x00_ops *ops)
 {
@@ -801,9 +819,21 @@ int rt2x00usb_probe(struct usb_interface *usb_intf,
 
 	rt2x00_set_chip_intf(rt2x00dev, RT2X00_CHIP_INTF_USB);
 
-	INIT_WORK(&rt2x00dev->rxdone_work, rt2x00usb_work_rxdone);
 	INIT_WORK(&rt2x00dev->txdone_work, rt2x00usb_work_txdone);
 
+	rt2x00dev->napi_dev = alloc_netdev_dummy(0);
+	if (!rt2x00dev->napi_dev) {
+		retval = -ENOMEM;
+		goto exit_free_hw;
+	}
+
+	strscpy(rt2x00dev->napi_dev->name, wiphy_name(hw->wiphy),
+		sizeof(rt2x00dev->napi_dev->name));
+	netif_napi_add(rt2x00dev->napi_dev, &rt2x00dev->napi,
+		       rt2x00usb_poll_rxdone);
+	netif_threaded_enable(rt2x00dev->napi_dev);
+	napi_enable(&rt2x00dev->napi);
+
 	init_usb_anchor(rt2x00dev->anchor);
 
 	retval = rt2x00lib_probe_dev(rt2x00dev);
@@ -814,6 +844,8 @@ int rt2x00usb_probe(struct usb_interface *usb_intf,
 
 exit_free_anchor:
 	usb_kill_anchored_urbs(rt2x00dev->anchor);
+	rt2x00usb_free_napi(rt2x00dev);
+exit_free_hw:
 	ieee80211_free_hw(hw);
 	usb_set_intfdata(usb_intf, NULL);
 
@@ -830,6 +862,7 @@ void rt2x00usb_disconnect(struct usb_interface *usb_intf)
 	 * Free all allocated data.
 	 */
 	rt2x00lib_remove_dev(rt2x00dev);
+	rt2x00usb_free_napi(rt2x00dev);
 	ieee80211_free_hw(hw);
 
 	usb_set_intfdata(usb_intf, NULL);
-- 
2.53.0