Merge branch 'icmp-reply-optimize'

Jesper Dangaard Brouer says:

====================
net: optimize ICMP-reply code path

This patchset is optimizing the ICMP-reply code path, for ICMP packets
that gets rate limited. A remote party can easily trigger this code
path by sending packets to port number with no listening service.

Generally the patchset moves the sysctl_icmp_msgs_per_sec ratelimit
checking to earlier in the code path and removes an allocation.

Use-case: The specific case I experienced this being a bottleneck is,
sending UDP packets to a port with no listener, which obviously result
in kernel replying with ICMP Destination Unreachable (type:3), Port
Unreachable (code:3), which cause the bottleneck.

 After Eric and Paolo optimized the UDP socket code, the kernels PPS
processing capabilities is lower for no-listen ports, than normal UDP
sockets.  This is bad for capacity planning when restarting a service.

UDP no-listen benchmark 8xCPUs using pktgen_sample04_many_flows.sh:
 Baseline: 6.6 Mpps
 Patch:   14.7 Mpps
Driver mlx5 at 50Gbit/s.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 123 insertions, 70 deletions

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 0777ea949223..fc310db2708b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -209,19 +209,17 @@ static struct sock *icmp_sk(struct net *net)
 	return *this_cpu_ptr(net->ipv4.icmp_sk);
 }
 
+/* Called with BH disabled */
 static inline struct sock *icmp_xmit_lock(struct net *net)
 {
 	struct sock *sk;
 
-	local_bh_disable();
-
 	sk = icmp_sk(net);
 
 	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
 		/* This can happen if the output path signals a
 		 * dst_link_failure() for an outgoing ICMP packet.
 		 */
-		local_bh_enable();
 		return NULL;
 	}
 	return sk;
@@ -229,7 +227,7 @@ static inline struct sock *icmp_xmit_lock(struct net *net)
 
 static inline void icmp_xmit_unlock(struct sock *sk)
 {
-	spin_unlock_bh(&sk->sk_lock.slock);
+	spin_unlock(&sk->sk_lock.slock);
 }
 
 int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
@@ -282,6 +280,33 @@ bool icmp_global_allow(void)
 }
 EXPORT_SYMBOL(icmp_global_allow);
 
+static bool icmpv4_mask_allow(struct net *net, int type, int code)
+{
+	if (type > NR_ICMP_TYPES)
+		return true;
+
+	/* Don't limit PMTU discovery. */
+	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+		return true;
+
+	/* Limit if icmp type is enabled in ratemask. */
+	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+		return true;
+
+	return false;
+}
+
+static bool icmpv4_global_allow(struct net *net, int type, int code)
+{
+	if (icmpv4_mask_allow(net, type, code))
+		return true;
+
+	if (icmp_global_allow())
+		return true;
+
+	return false;
+}
+
 /*
  *	Send an ICMP frame.
  */
@@ -290,34 +315,22 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 			       struct flowi4 *fl4, int type, int code)
 {
 	struct dst_entry *dst = &rt->dst;
+	struct inet_peer *peer;
 	bool rc = true;
+	int vif;
 
-	if (type > NR_ICMP_TYPES)
-		goto out;
-
-	/* Don't limit PMTU discovery. */
-	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+	if (icmpv4_mask_allow(net, type, code))
 		goto out;
 
 	/* No rate limit on loopback */
 	if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
 		goto out;
 
-	/* Limit if icmp type is enabled in ratemask. */
-	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
-		goto out;
-
-	rc = false;
-	if (icmp_global_allow()) {
-		int vif = l3mdev_master_ifindex(dst->dev);
-		struct inet_peer *peer;
-
-		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
-		rc = inet_peer_xrlim_allow(peer,
-					   net->ipv4.sysctl_icmp_ratelimit);
-		if (peer)
-			inet_putpeer(peer);
-	}
+	vif = l3mdev_master_ifindex(dst->dev);
+	peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
+	rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+	if (peer)
+		inet_putpeer(peer);
 out:
 	return rc;
 }
@@ -396,13 +409,22 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	struct inet_sock *inet;
 	__be32 daddr, saddr;
 	u32 mark = IP4_REPLY_MARK(net, skb->mark);
+	int type = icmp_param->data.icmph.type;
+	int code = icmp_param->data.icmph.code;
 
 	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
 		return;
 
+	/* Needed by both icmp_global_allow and icmp_xmit_lock */
+	local_bh_disable();
+
+	/* global icmp_msgs_per_sec */
+	if (!icmpv4_global_allow(net, type, code))
+		goto out_bh_enable;
+
 	sk = icmp_xmit_lock(net);
 	if (!sk)
-		return;
+		goto out_bh_enable;
 	inet = inet_sk(sk);
 
 	icmp_param->data.icmph.checksum = 0;
@@ -433,12 +455,13 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		goto out_unlock;
-	if (icmpv4_xrlim_allow(net, rt, &fl4, icmp_param->data.icmph.type,
-			       icmp_param->data.icmph.code))
+	if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
 		icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
 	ip_rt_put(rt);
 out_unlock:
 	icmp_xmit_unlock(sk);
+out_bh_enable:
+	local_bh_enable();
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -571,7 +594,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 {
 	struct iphdr *iph;
 	int room;
-	struct icmp_bxm *icmp_param;
+	struct icmp_bxm icmp_param;
 	struct rtable *rt = skb_rtable(skb_in);
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
@@ -648,13 +671,16 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		}
 	}
 
-	icmp_param = kmalloc(sizeof(*icmp_param), GFP_ATOMIC);
-	if (!icmp_param)
-		return;
+	/* Needed by both icmp_global_allow and icmp_xmit_lock */
+	local_bh_disable();
+
+	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
+	if (!icmpv4_global_allow(net, type, code))
+		goto out_bh_enable;
 
 	sk = icmp_xmit_lock(net);
 	if (!sk)
-		goto out_free;
+		goto out_bh_enable;
 
 	/*
 	 *	Construct source address and options.
@@ -681,7 +707,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 					  iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
+	if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
 		goto out_unlock;
 
 
@@ -689,25 +715,26 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	 *	Prepare data for ICMP header.
 	 */
 
-	icmp_param->data.icmph.type	 = type;
-	icmp_param->data.icmph.code	 = code;
-	icmp_param->data.icmph.un.gateway = info;
-	icmp_param->data.icmph.checksum	 = 0;
-	icmp_param->skb	  = skb_in;
-	icmp_param->offset = skb_network_offset(skb_in);
+	icmp_param.data.icmph.type	 = type;
+	icmp_param.data.icmph.code	 = code;
+	icmp_param.data.icmph.un.gateway = info;
+	icmp_param.data.icmph.checksum	 = 0;
+	icmp_param.skb	  = skb_in;
+	icmp_param.offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
 	sk->sk_mark = mark;
 	ipc.addr = iph->saddr;
-	ipc.opt = &icmp_param->replyopts.opt;
+	ipc.opt = &icmp_param.replyopts.opt;
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
-			       type, code, icmp_param);
+			       type, code, &icmp_param);
 	if (IS_ERR(rt))
 		goto out_unlock;
 
+	/* peer icmp_ratelimit */
 	if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code))
 		goto ende;
 
@@ -716,21 +743,21 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	room = dst_mtu(&rt->dst);
 	if (room > 576)
 		room = 576;
-	room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.opt.optlen;
+	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
 	room -= sizeof(struct icmphdr);
 
-	icmp_param->data_len = skb_in->len - icmp_param->offset;
-	if (icmp_param->data_len > room)
-		icmp_param->data_len = room;
-	icmp_param->head_len = sizeof(struct icmphdr);
+	icmp_param.data_len = skb_in->len - icmp_param.offset;
+	if (icmp_param.data_len > room)
+		icmp_param.data_len = room;
+	icmp_param.head_len = sizeof(struct icmphdr);
 
-	icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
+	icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
 ende:
 	ip_rt_put(rt);
 out_unlock:
 	icmp_xmit_unlock(sk);
-out_free:
-	kfree(icmp_param);
+out_bh_enable:
+	local_bh_enable();
 out:;
 }
 EXPORT_SYMBOL(icmp_send);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 3036f665e6c8..230b5aac9f03 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -110,19 +110,17 @@ static const struct inet6_protocol icmpv6_protocol = {
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
+/* Called with BH disabled */
 static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
 {
 	struct sock *sk;
 
-	local_bh_disable();
-
 	sk = icmpv6_sk(net);
 	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
 		/* This can happen if the output path (f.e. SIT or
 		 * ip6ip6 tunnel) signals dst_link_failure() for an
 		 * outgoing ICMP6 packet.
 		 */
-		local_bh_enable();
 		return NULL;
 	}
 	return sk;
@@ -130,7 +128,7 @@ static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
 
 static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
 {
-	spin_unlock_bh(&sk->sk_lock.slock);
+	spin_unlock(&sk->sk_lock.slock);
 }
 
 /*
@@ -168,6 +166,30 @@ static bool is_ineligible(const struct sk_buff *skb)
 	return false;
 }
 
+static bool icmpv6_mask_allow(int type)
+{
+	/* Informational messages are not limited. */
+	if (type & ICMPV6_INFOMSG_MASK)
+		return true;
+
+	/* Do not limit pmtu discovery, it would break it. */
+	if (type == ICMPV6_PKT_TOOBIG)
+		return true;
+
+	return false;
+}
+
+static bool icmpv6_global_allow(int type)
+{
+	if (icmpv6_mask_allow(type))
+		return true;
+
+	if (icmp_global_allow())
+		return true;
+
+	return false;
+}
+
 /*
  * Check the ICMP output rate limit
  */
@@ -178,12 +200,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	struct dst_entry *dst;
 	bool res = false;
 
-	/* Informational messages are not limited. */
-	if (type & ICMPV6_INFOMSG_MASK)
-		return true;
-
-	/* Do not limit pmtu discovery, it would break it. */
-	if (type == ICMPV6_PKT_TOOBIG)
+	if (icmpv6_mask_allow(type))
 		return true;
 
 	/*
@@ -200,20 +217,16 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	} else {
 		struct rt6_info *rt = (struct rt6_info *)dst;
 		int tmo = net->ipv6.sysctl.icmpv6_time;
+		struct inet_peer *peer;
 
 		/* Give more bandwidth to wider prefixes. */
 		if (rt->rt6i_dst.plen < 128)
 			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
 
-		if (icmp_global_allow()) {
-			struct inet_peer *peer;
-
-			peer = inet_getpeer_v6(net->ipv6.peers,
-					       &fl6->daddr, 1);
-			res = inet_peer_xrlim_allow(peer, tmo);
-			if (peer)
-				inet_putpeer(peer);
-		}
+		peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr, 1);
+		res = inet_peer_xrlim_allow(peer, tmo);
+		if (peer)
+			inet_putpeer(peer);
 	}
 	dst_release(dst);
 	return res;
@@ -474,6 +487,13 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		return;
 	}
 
+	/* Needed by both icmp_global_allow and icmpv6_xmit_lock */
+	local_bh_disable();
+
+	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
+	if (!icmpv6_global_allow(type))
+		goto out_bh_enable;
+
 	mip6_addr_swap(skb);
 
 	memset(&fl6, 0, sizeof(fl6));
@@ -492,7 +512,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 
 	sk = icmpv6_xmit_lock(net);
 	if (!sk)
-		return;
+		goto out_bh_enable;
+
 	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
@@ -552,6 +573,8 @@ out_dst_release:
 	dst_release(dst);
 out:
 	icmpv6_xmit_unlock(sk);
+out_bh_enable:
+	local_bh_enable();
 }
 
 /* Slightly more convenient version of icmp6_send.
@@ -665,9 +688,10 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
+	local_bh_disable();
 	sk = icmpv6_xmit_lock(net);
 	if (!sk)
-		return;
+		goto out_bh_enable;
 	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
@@ -709,6 +733,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	dst_release(dst);
 out:
 	icmpv6_xmit_unlock(sk);
+out_bh_enable:
+	local_bh_enable();
 }
 
 void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)