e1000: switch to napi_consume_skb()

In order to take the best from per-cpu NAPI skbuff_head caches and
CPU cycles, let's switch from dev_kfree_skb_any(), which passes skb
back to the mm layer, to napi_consume_skb(), which feeds those
caches on non-zero budget instead (falls back to the former on 0).
Do the replacement in e1000_unmap_and_free_tx_resource(). There are
4 call sites of this function throughout the driver:
 * e1000_clean_tx_ring(). Slowpath, process context, cleans the
   whole Tx ring on ifdown. Use budget of 0 here;
 * e1000_tx_map(). Hotpath, net Tx softirq, unmaps the buffers in
   case of error. Use 0 as well;
 * e1000_clean_tx_irq(). Hotpath, NAPI Tx completion polling cycle.
   As the driver doesn't count completed Tx entries towards the NAPI
   budget, just use the poll budget of 64 to utilize caches.

Apart from being a preparation for switching to napi_build_skb(),
this is useful on its own as well, as napi_consume_skb() flushes
skb caches by batches of 32 instead of one-at-a-time.
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Tony Brelinski <tony.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

drivers/net/ethernet/intel/e1000/e1000_main.c

@@ -1953,7 +1953,8 @@ void e1000_free_all_tx_resources(struct e1000_adapter *adapter)
 
 static void
 e1000_unmap_and_free_tx_resource(struct e1000_adapter *adapter,
-				 struct e1000_tx_buffer *buffer_info)
+				 struct e1000_tx_buffer *buffer_info,
+				 int budget)
 {
 	if (buffer_info->dma) {
 		if (buffer_info->mapped_as_page)
@@ -1966,7 +1967,7 @@ e1000_unmap_and_free_tx_resource(struct e1000_adapter *adapter,
 		buffer_info->dma = 0;
 	}
 	if (buffer_info->skb) {
-		dev_kfree_skb_any(buffer_info->skb);
+		napi_consume_skb(buffer_info->skb, budget);
 		buffer_info->skb = NULL;
 	}
 	buffer_info->time_stamp = 0;
@@ -1990,7 +1991,7 @@ static void e1000_clean_tx_ring(struct e1000_adapter *adapter,
 
 	for (i = 0; i < tx_ring->count; i++) {
 		buffer_info = &tx_ring->buffer_info[i];
-		e1000_unmap_and_free_tx_resource(adapter, buffer_info);
+		e1000_unmap_and_free_tx_resource(adapter, buffer_info, 0);
 	}
 
 	netdev_reset_queue(adapter->netdev);
@@ -2958,7 +2959,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter,
 			i += tx_ring->count;
 		i--;
 		buffer_info = &tx_ring->buffer_info[i];
-		e1000_unmap_and_free_tx_resource(adapter, buffer_info);
+		e1000_unmap_and_free_tx_resource(adapter, buffer_info, 0);
 	}
 
 	return 0;
@@ -3856,7 +3857,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 				}
 
 			}
-			e1000_unmap_and_free_tx_resource(adapter, buffer_info);
+			e1000_unmap_and_free_tx_resource(adapter, buffer_info,
+							 64);
 			tx_desc->upper.data = 0;
 
 			if (unlikely(++i == tx_ring->count))