netdev - [PATCH][RFC] udp: cache sock to avoid searching it twice

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <1541744479-12810-1-git-send-email-lirongqing@baidu.com>
Date:   Fri,  9 Nov 2018 14:21:19 +0800
From:   Li RongQing <lirongqing@...du.com>
To:     netdev@...r.kernel.org
Subject: [PATCH][RFC] udp: cache sock to avoid searching it twice

GRO for UDP needs to lookup socket twice, first is in gro receive,
second is gro complete, so if store sock to skb to avoid looking up
twice, this can give small performance boost

netperf -t UDP_RR -l 10

Before:
	Rate per sec: 28746.01
After:
	Rate per sec: 29401.67

Signed-off-by: Li RongQing <lirongqing@...du.com>
---
 net/ipv4/udp_offload.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0646d61f4fa8..429570112a33 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -408,6 +408,11 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 
 	if (udp_sk(sk)->gro_enabled) {
 		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
+
+		if (!IS_ERR(pp) && NAPI_GRO_CB(pp)->count > 1) {
+			sock_hold(sk);
+			pp->sk = sk;
+		}
 		rcu_read_unlock();
 		return pp;
 	}
@@ -444,6 +449,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
 	pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
 
+	if (!IS_ERR(pp) && NAPI_GRO_CB(pp)->count > 1) {
+		sock_hold(sk);
+		pp->sk = sk;
+	}
 out_unlock:
 	rcu_read_unlock();
 	skb_gro_flush_final(skb, pp, flush);
@@ -502,7 +511,9 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 	uh->len = newlen;
 
 	rcu_read_lock();
-	sk = (*lookup)(skb, uh->source, uh->dest);
+	sk = skb->sk;
+	if (!sk)
+		sk = (*lookup)(skb, uh->source, uh->dest);
 	if (sk && udp_sk(sk)->gro_enabled) {
 		err = udp_gro_complete_segment(skb);
 	} else if (sk && udp_sk(sk)->gro_complete) {
@@ -516,6 +527,11 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 		err = udp_sk(sk)->gro_complete(sk, skb,
 				nhoff + sizeof(struct udphdr));
 	}
+
+	if (skb->sk) {
+		sock_put(skb->sk);
+		skb->sk = NULL;
+	}
 	rcu_read_unlock();
 
 	if (skb->remcsum_offload)
-- 
2.16.2