ip_tunnel: Create percpu gro_cell

In the ipip tunnel, the skb->queue_mapping is lost in ipip_rcv().
All skb will be queued to the same cell->napi_skbs.  The
gro_cell_poll is pinned to one core under load.  In production traffic,
we also see severe rx_dropped in the tunl iface and it is probably due to
this limit: skb_queue_len(&cell->napi_skbs) > netdev_max_backlog.

This patch is trying to alloc_percpu(struct gro_cell) and schedule
gro_cell_poll to process the skb in the same core.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/gro_cells.h

@@ -8,25 +8,23 @@
 struct gro_cell {
 	struct sk_buff_head	napi_skbs;
 	struct napi_struct	napi;
-} ____cacheline_aligned_in_smp;
+};
 
 struct gro_cells {
-	unsigned int		gro_cells_mask;
-	struct gro_cell		*cells;
+	struct gro_cell __percpu	*cells;
 };
 
 static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
-	struct gro_cell *cell = gcells->cells;
+	struct gro_cell *cell;
 	struct net_device *dev = skb->dev;
 
-	if (!cell || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) {
+	if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) {
 		netif_rx(skb);
 		return;
 	}
 
-	if (skb_rx_queue_recorded(skb))
-		cell += skb_get_rx_queue(skb) & gcells->gro_cells_mask;
+	cell = this_cpu_ptr(gcells->cells);
 
 	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
 		atomic_long_inc(&dev->rx_dropped);
@@ -72,15 +70,12 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
 {
 	int i;
 
-	gcells->gro_cells_mask = roundup_pow_of_two(netif_get_num_default_rss_queues()) - 1;
-	gcells->cells = kcalloc(gcells->gro_cells_mask + 1,
-				sizeof(struct gro_cell),
-				GFP_KERNEL);
+	gcells->cells = alloc_percpu(struct gro_cell);
 	if (!gcells->cells)
 		return -ENOMEM;
 
-	for (i = 0; i <= gcells->gro_cells_mask; i++) {
-		struct gro_cell *cell = gcells->cells + i;
+	for_each_possible_cpu(i) {
+		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		skb_queue_head_init(&cell->napi_skbs);
 		netif_napi_add(dev, &cell->napi, gro_cell_poll, 64);
@@ -91,16 +86,16 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
 
 static inline void gro_cells_destroy(struct gro_cells *gcells)
 {
-	struct gro_cell *cell = gcells->cells;
 	int i;
 
-	if (!cell)
+	if (!gcells->cells)
 		return;
-	for (i = 0; i <= gcells->gro_cells_mask; i++,cell++) {
+	for_each_possible_cpu(i) {
+		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 		netif_napi_del(&cell->napi);
 		skb_queue_purge(&cell->napi_skbs);
 	}
-	kfree(gcells->cells);
+	free_percpu(gcells->cells);
 	gcells->cells = NULL;
 }