net: Use skbufhead with raw lock

Use the rps lock as rawlock so we can keep irq-off regions. It looks low
latency. However we can't kfree() from this context therefore we defer this
to the softirq and use the tofree_queue list for it (similar to process_queue).

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/netdevice.h

@@ -2772,6 +2772,7 @@ struct softnet_data {
 	unsigned int		dropped;
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
+	struct sk_buff_head	tofree_queue;
 
 };
 

include/linux/skbuff.h

@@ -287,6 +287,7 @@ struct sk_buff_head {
 
 	__u32		qlen;
 	spinlock_t	lock;
+	raw_spinlock_t	raw_lock;
 };
 
 struct sk_buff;
@@ -1667,6 +1668,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list)
 	__skb_queue_head_init(list);
 }
 
+static inline void skb_queue_head_init_raw(struct sk_buff_head *list)
+{
+	raw_spin_lock_init(&list->raw_lock);
+	__skb_queue_head_init(list);
+}
+
 static inline void skb_queue_head_init_class(struct sk_buff_head *list,
 		struct lock_class_key *class)
 {

net/core/dev.c

@@ -217,14 +217,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
 static inline void rps_lock(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	spin_lock(&sd->input_pkt_queue.lock);
+	raw_spin_lock(&sd->input_pkt_queue.raw_lock);
 #endif
 }
 
 static inline void rps_unlock(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	spin_unlock(&sd->input_pkt_queue.lock);
+	raw_spin_unlock(&sd->input_pkt_queue.raw_lock);
 #endif
 }
 
@@ -4593,7 +4593,7 @@ static void flush_backlog(struct work_struct *work)
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&sd->tofree_queue, skb);
 			input_queue_head_incr(sd);
 		}
 	}
@@ -4603,11 +4603,14 @@ static void flush_backlog(struct work_struct *work)
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&sd->tofree_queue, skb);
 			input_queue_head_incr(sd);
 		}
 	}
+	if (!skb_queue_empty(&sd->tofree_queue))
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
 	local_bh_enable();
+
 }
 
 static void flush_all_backlogs(void)
@@ -5154,17 +5157,19 @@ static int process_backlog(struct napi_struct *napi, int quota)
 	while (again) {
 		struct sk_buff *skb;
 
+		local_irq_disable();
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			local_irq_enable();
 			rcu_read_lock();
 			__netif_receive_skb(skb);
 			rcu_read_unlock();
 			input_queue_head_incr(sd);
 			if (++work >= quota)
 				return work;
 
+			local_irq_disable();
 		}
 
-		local_irq_disable();
 		rps_lock(sd);
 		if (skb_queue_empty(&sd->input_pkt_queue)) {
 			/*
@@ -5604,13 +5609,21 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	unsigned long time_limit = jiffies +
 		usecs_to_jiffies(netdev_budget_usecs);
 	int budget = netdev_budget;
+	struct sk_buff_head tofree_q;
+	struct sk_buff *skb;
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
+	__skb_queue_head_init(&tofree_q);
+
 	local_irq_disable();
+	skb_queue_splice_init(&sd->tofree_queue, &tofree_q);
 	list_splice_init(&sd->poll_list, &list);
 	local_irq_enable();
 
+	while ((skb = __skb_dequeue(&tofree_q)))
+		kfree_skb(skb);
+
 	for (;;) {
 		struct napi_struct *n;
 
@@ -8425,6 +8438,9 @@ static int dev_cpu_dead(unsigned int oldcpu)
 		netif_rx_ni(skb);
 		input_queue_head_incr(oldsd);
 	}
+	while ((skb = __skb_dequeue(&oldsd->tofree_queue))) {
+		kfree_skb(skb);
+	}
 
 	return 0;
 }
@@ -8728,8 +8744,9 @@ static int __init net_dev_init(void)
 
 		INIT_WORK(flush, flush_backlog);
 
-		skb_queue_head_init(&sd->input_pkt_queue);
-		skb_queue_head_init(&sd->process_queue);
+		skb_queue_head_init_raw(&sd->input_pkt_queue);
+		skb_queue_head_init_raw(&sd->process_queue);
+		skb_queue_head_init_raw(&sd->tofree_queue);
 		INIT_LIST_HEAD(&sd->poll_list);
 		sd->output_queue_tailp = &sd->output_queue;
 #ifdef CONFIG_RPS