net: convert gro_count to bitmask

gro_hash size is 192 bytes, and uses 3 cache lines, if there is few
flows, gro_hash may be not fully used, so it is unnecessary to iterate
all gro_hash in napi_gro_flush(), to occupy unnecessary cacheline.

convert gro_count to a bitmask, and rename it as gro_bitmask, each bit
represents a element of gro_hash, only flush a gro_hash element if the
related bit is set, to speed up napi_gro_flush().

and update gro_bitmask only if it will be changed, to reduce cache
update

Suggested-by: Eric Dumazet <[email protected]>
Signed-off-by: Li RongQing <[email protected]>
Cc: Stefano Brivio <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: lrq-max

include/linux/netdevice.h

@@ -308,9 +308,14 @@ struct gro_list {
 };
 
 /*
- * Structure for NAPI scheduling similar to tasklet but with weighting
+ * size of gro hash buckets, must less than bit number of
+ * napi_struct::gro_bitmask
  */
 #define GRO_HASH_BUCKETS	8
+
+/*
+ * Structure for NAPI scheduling similar to tasklet but with weighting
+ */
 struct napi_struct {
 	/* The poll_list must only be managed by the entity which
 	 * changes the state of the NAPI_STATE_SCHED bit.  This means
@@ -322,7 +327,7 @@ struct napi_struct {
 
 	unsigned long		state;
 	int			weight;
-	unsigned int		gro_count;
+	unsigned long		gro_bitmask;
 	int			(*poll)(struct napi_struct *, int);
 #ifdef CONFIG_NETPOLL
 	int			poll_owner;

net/core/dev.c

@@ -5282,9 +5282,11 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 		list_del(&skb->list);
 		skb->next = NULL;
 		napi_gro_complete(skb);
-		napi->gro_count--;
 		napi->gro_hash[index].count--;
 	}
+
+	if (!napi->gro_hash[index].count)
+		__clear_bit(index, &napi->gro_bitmask);
 }
 
 /* napi->gro_hash[].list contains packets ordered by age.
@@ -5295,8 +5297,10 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
 	u32 i;
 
-	for (i = 0; i < GRO_HASH_BUCKETS; i++)
-		__napi_gro_flush_chain(napi, i, flush_old);
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		if (test_bit(i, &napi->gro_bitmask))
+			__napi_gro_flush_chain(napi, i, flush_old);
+	}
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
@@ -5388,8 +5392,8 @@ static void gro_flush_oldest(struct list_head *head)
 	if (WARN_ON_ONCE(!oldest))
 		return;
 
-	/* Do not adjust napi->gro_count, caller is adding a new SKB to
-	 * the chain.
+	/* Do not adjust napi->gro_hash[].count, caller is adding a new
+	 * SKB to the chain.
 	 */
 	list_del(&oldest->list);
 	napi_gro_complete(oldest);
@@ -5464,7 +5468,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		list_del(&pp->list);
 		pp->next = NULL;
 		napi_gro_complete(pp);
-		napi->gro_count--;
 		napi->gro_hash[hash].count--;
 	}
 
@@ -5477,7 +5480,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
 		gro_flush_oldest(gro_head);
 	} else {
-		napi->gro_count++;
 		napi->gro_hash[hash].count++;
 	}
 	NAPI_GRO_CB(skb)->count = 1;
@@ -5492,6 +5494,13 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (grow > 0)
 		gro_pull_from_frag0(skb, grow);
 ok:
+	if (napi->gro_hash[hash].count) {
+		if (!test_bit(hash, &napi->gro_bitmask))
+			__set_bit(hash, &napi->gro_bitmask);
+	} else if (test_bit(hash, &napi->gro_bitmask)) {
+		__clear_bit(hash, &napi->gro_bitmask);
+	}
+
 	return ret;
 
 normal:
@@ -5890,7 +5899,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	if (n->gro_count) {
+	if (n->gro_bitmask) {
 		unsigned long timeout = 0;
 
 		if (work_done)
@@ -6099,7 +6108,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
-	if (napi->gro_count && !napi_disable_pending(napi) &&
+	if (napi->gro_bitmask && !napi_disable_pending(napi) &&
 	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
 		__napi_schedule_irqoff(napi);
 
@@ -6114,7 +6123,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 	INIT_LIST_HEAD(&napi->poll_list);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
-	napi->gro_count = 0;
+	napi->gro_bitmask = 0;
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
 		INIT_LIST_HEAD(&napi->gro_hash[i].list);
 		napi->gro_hash[i].count = 0;
@@ -6174,7 +6183,7 @@ void netif_napi_del(struct napi_struct *napi)
 	napi_free_frags(napi);
 
 	flush_gro_hash(napi);
-	napi->gro_count = 0;
+	napi->gro_bitmask = 0;
 }
 EXPORT_SYMBOL(netif_napi_del);
 
@@ -6216,7 +6225,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	if (n->gro_count) {
+	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
 		 */
@@ -9272,6 +9281,9 @@ static struct hlist_head * __net_init netdev_create_hash(void)
 /* Initialize per network namespace state */
 static int __net_init netdev_init(struct net *net)
 {
+	BUILD_BUG_ON(GRO_HASH_BUCKETS >
+			FIELD_SIZEOF(struct napi_struct, gro_bitmask));
+
 	if (net != &init_net)
 		INIT_LIST_HEAD(&net->dev_base_head);