usbnet: optimize usbnet_bh() to reduce CPU load

The current source pushes skb into dev-done queue by calling
skb_dequeue_tail() and then pop it by skb_dequeue() to branch to
rx_cleanup state for freeing urb/skb in usbnet_bh(). It takes extra CPU
load, 2.21% (skb_queue_tail) as follows,

-   11.58%     0.26%  swapper          [k] usbnet_bh
   - 11.32% usbnet_bh
      - 6.43% skb_dequeue
           6.34% _raw_spin_unlock_irqrestore
      - 2.21% skb_queue_tail
           2.19% _raw_spin_unlock_irqrestore
      - 1.68% consume_skb
         - 0.97% kfree_skbmem
              0.80% kmem_cache_free
           0.53% skb_release_data

To reduce the extra CPU load use return values to call helper function
usb_free_skb() to free the resources instead of calling skb_queue_tail()
and skb_dequeue() for push and pop respectively.

-    7.87%     0.25%  swapper          [k] usbnet_bh
   - 7.62% usbnet_bh
      - 4.81% skb_dequeue
           4.74% _raw_spin_unlock_irqrestore
      - 1.75% consume_skb
         - 0.98% kfree_skbmem
              0.78% kmem_cache_free
           0.58% skb_release_data
        0.53% smsc95xx_rx_fixup
Signed-off-by: Leesoo Ahn <lsahn@ooseel.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/usb/usbnet.c

@@ -555,32 +555,30 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 
 /*-------------------------------------------------------------------------*/
 
-static inline void rx_process (struct usbnet *dev, struct sk_buff *skb)
+static inline int rx_process(struct usbnet *dev, struct sk_buff *skb)
 {
 	if (dev->driver_info->rx_fixup &&
 	    !dev->driver_info->rx_fixup (dev, skb)) {
 		/* With RX_ASSEMBLE, rx_fixup() must update counters */
 		if (!(dev->driver_info->flags & FLAG_RX_ASSEMBLE))
 			dev->net->stats.rx_errors++;
-		goto done;
+		return -EPROTO;
 	}
 	// else network stack removes extra byte if we forced a short packet
 
 	/* all data was already cloned from skb inside the driver */
 	if (dev->driver_info->flags & FLAG_MULTI_PACKET)
-		goto done;
+		return -EALREADY;
 
 	if (skb->len < ETH_HLEN) {
 		dev->net->stats.rx_errors++;
 		dev->net->stats.rx_length_errors++;
 		netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len);
-	} else {
-		usbnet_skb_return(dev, skb);
-		return;
+		return -EPROTO;
 	}
 
-done:
-	skb_queue_tail(&dev->done, skb);
+	usbnet_skb_return(dev, skb);
+	return 0;
 }
 
 /*-------------------------------------------------------------------------*/
@@ -1514,6 +1512,14 @@ static int rx_alloc_submit(struct usbnet *dev, gfp_t flags)
 	return ret;
 }
 
+static inline void usb_free_skb(struct sk_buff *skb)
+{
+	struct skb_data *entry = (struct skb_data *)skb->cb;
+
+	usb_free_urb(entry->urb);
+	dev_kfree_skb(skb);
+}
+
 /*-------------------------------------------------------------------------*/
 
 // tasklet (work deferred from completions, in_irq) or timer
@@ -1528,15 +1534,14 @@ static void usbnet_bh (struct timer_list *t)
 		entry = (struct skb_data *) skb->cb;
 		switch (entry->state) {
 		case rx_done:
-			entry->state = rx_cleanup;
-			rx_process (dev, skb);
+			if (rx_process(dev, skb))
+				usb_free_skb(skb);
 			continue;
 		case tx_done:
 			kfree(entry->urb->sg);
 			fallthrough;
 		case rx_cleanup:
-			usb_free_urb (entry->urb);
-			dev_kfree_skb (skb);
+			usb_free_skb(skb);
 			continue;
 		default:
 			netdev_dbg(dev->net, "bogus skb state %d\n", entry->state);