From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 5 Jul 2018 14:34:32 +0800
Subject: net: limit each hash list length to MAX_GRO_SKBS
Patch-mainline: v4.19-rc1
Git-commit: 6312fe77751f57d4fa2b28abeef84c6a95c28136
References: bsc#1109837

After commit 07d78363dcff ("net: Convert NAPI gro list into a small hash
table.")' there is 8 hash buckets, which allows more flows to be held for
merging.  but MAX_GRO_SKBS, the total held skb for merging, is 8 skb still,
limit the hash table performance.

keep MAX_GRO_SKBS as 8 skb, but limit each hash list length to 8 skb, not
the total 8 skb

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 include/linux/netdevice.h |    7 ++++-
 net/core/dev.c            |   56 ++++++++++++++++++----------------------------
 2 files changed, 29 insertions(+), 34 deletions(-)

--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -301,6 +301,11 @@ struct netdev_boot_setup {
 
 int __init netdev_boot_setup(char *str);
 
+struct gro_list {
+	struct list_head	list;
+	int			count;
+};
+
 /*
  * Structure for NAPI scheduling similar to tasklet but with weighting
  */
@@ -322,7 +327,7 @@ struct napi_struct {
 	int			poll_owner;
 #endif
 	struct net_device	*dev;
-	struct list_head	gro_hash[GRO_HASH_BUCKETS];
+	struct gro_list		gro_hash[GRO_HASH_BUCKETS];
 	struct sk_buff		*skb;
 	struct hrtimer		timer;
 	struct list_head	dev_list;
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -148,7 +148,6 @@
 
 #include "net-sysfs.h"
 
-/* Instead of increasing this, you should create a hash table. */
 #define MAX_GRO_SKBS 8
 
 /* This should be increased if a protocol with a bigger head is added. */
@@ -5126,9 +5125,10 @@ out:
 	return netif_receive_skb_internal(skb);
 }
 
-static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *head,
+static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 				   bool flush_old)
 {
+	struct list_head *head = &napi->gro_hash[index].list;
 	struct sk_buff *skb, *p;
 
 	list_for_each_entry_safe_reverse(skb, p, head, list) {
@@ -5137,22 +5137,20 @@ static void __napi_gro_flush_chain(struc
 		list_del_init(&skb->list);
 		napi_gro_complete(skb);
 		napi->gro_count--;
+		napi->gro_hash[index].count--;
 	}
 }
 
-/* napi->gro_hash contains packets ordered by age.
+/* napi->gro_hash[].list contains packets ordered by age.
  * youngest packets at the head of it.
  * Complete skbs in reverse order to reduce latencies.
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	int i;
-
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		struct list_head *head = &napi->gro_hash[i];
+	u32 i;
 
-		__napi_gro_flush_chain(napi, head, flush_old);
-	}
+	for (i = 0; i < GRO_HASH_BUCKETS; i++)
+		__napi_gro_flush_chain(napi, i, flush_old);
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
@@ -5164,7 +5162,7 @@ static struct list_head *gro_list_prepar
 	struct list_head *head;
 	struct sk_buff *p;
 
-	head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)];
+	head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list;
 	list_for_each_entry(p, head, list) {
 		unsigned long diffs;
 
@@ -5232,27 +5230,13 @@ static void gro_pull_from_frag0(struct s
 	}
 }
 
-static void gro_flush_oldest(struct napi_struct *napi)
+static void gro_flush_oldest(struct list_head *head)
 {
-	struct sk_buff *oldest = NULL;
-	unsigned long age = jiffies;
-	int i;
-
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		struct list_head *head = &napi->gro_hash[i];
-		struct sk_buff *skb;
-
-		if (list_empty(head))
-			continue;
+	struct sk_buff *oldest;
 
-		skb = list_last_entry(head, struct sk_buff, list);
-		if (!oldest || time_before(NAPI_GRO_CB(skb)->age, age)) {
-			oldest = skb;
-			age = NAPI_GRO_CB(skb)->age;
-		}
-	}
+	oldest = list_last_entry(head, struct sk_buff, list);
 
-	/* We are called with napi->gro_count >= MAX_GRO_SKBS, so this is
+	/* We are called with head length >= MAX_GRO_SKBS, so this is
 	 * impossible.
 	 */
 	if (WARN_ON_ONCE(!oldest))
@@ -5267,6 +5251,7 @@ static void gro_flush_oldest(struct napi
 
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
 	struct list_head *head = &offload_base;
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
@@ -5333,6 +5318,7 @@ static enum gro_result dev_gro_receive(s
 		list_del_init(&pp->list);
 		napi_gro_complete(pp);
 		napi->gro_count--;
+		napi->gro_hash[hash].count--;
 	}
 
 	if (same_flow)
@@ -5341,10 +5327,11 @@ static enum gro_result dev_gro_receive(s
 	if (NAPI_GRO_CB(skb)->flush)
 		goto normal;
 
-	if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
-		gro_flush_oldest(napi);
+	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;
 	NAPI_GRO_CB(skb)->age = jiffies;
@@ -5980,8 +5967,10 @@ void netif_napi_add(struct net_device *d
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
-	for (i = 0; i < GRO_HASH_BUCKETS; i++)
-		INIT_LIST_HEAD(&napi->gro_hash[i]);
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		INIT_LIST_HEAD(&napi->gro_hash[i].list);
+		napi->gro_hash[i].count = 0;
+	}
 	napi->skb = NULL;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
@@ -6021,8 +6010,9 @@ static void flush_gro_hash(struct napi_s
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
 		struct sk_buff *skb, *n;
 
-		list_for_each_entry_safe(skb, n, &napi->gro_hash[i], list)
+		list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list)
 			kfree_skb(skb);
+		napi->gro_hash[i].count = 0;
 	}
 }