From 60fb9567bf30937e6bedfa939d7c8fd4ee6a1b1c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:28 +0100
Subject: [PATCH 01/10] udp: implement complete book-keeping for encap_needed

The *encap_needed static keys are enabled by UDP tunnels
and several UDP encapsulations type, but they are never
turned off. This can cause unneeded overall performance
degradation for systems where such features are used
transiently.

This patch introduces complete book-keeping for such keys,
decreasing the usage at socket destruction time, if needed,
and avoiding that the same socket could increase the key
usage multiple times.

rfc v3 -> v1:
 - add socket lock around udp_tunnel_encap_enable()

rfc v2 -> rfc v3:
 - use udp_tunnel_encap_enable() in setsockopt()

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h      |  7 ++++++-
 include/net/udp_tunnel.h |  6 ++++++
 net/ipv4/udp.c           | 19 +++++++++++++------
 net/ipv6/udp.c           | 14 +++++++++-----
 4 files changed, 34 insertions(+), 12 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 320d49d85484..a4dafff407fb 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -49,7 +49,12 @@ struct udp_sock {
 	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
+			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
+			 encap_enabled:1; /* This socket enabled encap
+					   * processing; UDP tunnels and
+					   * different encapsulation layer set
+					   * this
+					   */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index fe680ab6b15a..3fbe56430e3b 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -165,6 +165,12 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
 
 static inline void udp_tunnel_encap_enable(struct socket *sock)
 {
+	struct udp_sock *up = udp_sk(sock->sk);
+
+	if (up->encap_enabled)
+		return;
+
+	up->encap_enabled = 1;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sock->sk->sk_family == PF_INET6)
 		ipv6_stub->udpv6_encap_enable();
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cf73c9194bb6..f81409921e27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -115,6 +115,7 @@
 #include "udp_impl.h"
 #include <net/sock_reuseport.h>
 #include <net/addrconf.h>
+#include <net/udp_tunnel.h>
 
 struct udp_table udp_table __read_mostly;
 EXPORT_SYMBOL(udp_table);
@@ -2395,11 +2396,15 @@ void udp_destroy_sock(struct sock *sk)
 	bool slow = lock_sock_fast(sk);
 	udp_flush_pending_frames(sk);
 	unlock_sock_fast(sk, slow);
-	if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
-		void (*encap_destroy)(struct sock *sk);
-		encap_destroy = READ_ONCE(up->encap_destroy);
-		if (encap_destroy)
-			encap_destroy(sk);
+	if (static_branch_unlikely(&udp_encap_needed_key)) {
+		if (up->encap_type) {
+			void (*encap_destroy)(struct sock *sk);
+			encap_destroy = READ_ONCE(up->encap_destroy);
+			if (encap_destroy)
+				encap_destroy(sk);
+		}
+		if (up->encap_enabled)
+			static_branch_disable(&udp_encap_needed_key);
 	}
 }
 
@@ -2444,7 +2449,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 			/* FALLTHROUGH */
 		case UDP_ENCAP_L2TPINUDP:
 			up->encap_type = val;
-			udp_encap_enable();
+			lock_sock(sk);
+			udp_tunnel_encap_enable(sk->sk_socket);
+			release_sock(sk);
 			break;
 		default:
 			err = -ENOPROTOOPT;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a25571c12a8a..bdf7e071a63b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1456,11 +1456,15 @@ void udpv6_destroy_sock(struct sock *sk)
 	udp_v6_flush_pending_frames(sk);
 	release_sock(sk);
 
-	if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
-		void (*encap_destroy)(struct sock *sk);
-		encap_destroy = READ_ONCE(up->encap_destroy);
-		if (encap_destroy)
-			encap_destroy(sk);
+	if (static_branch_unlikely(&udpv6_encap_needed_key)) {
+		if (up->encap_type) {
+			void (*encap_destroy)(struct sock *sk);
+			encap_destroy = READ_ONCE(up->encap_destroy);
+			if (encap_destroy)
+				encap_destroy(sk);
+		}
+		if (up->encap_enabled)
+			static_branch_disable(&udpv6_encap_needed_key);
 	}
 
 	inet6_destroy_sock(sk);

From e20cf8d3f1f763ad28a9cb3b41305b8a8a42653e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:29 +0100
Subject: [PATCH 02/10] udp: implement GRO for plain UDP sockets.

This is the RX counterpart of commit bec1f6f69736 ("udp: generate gso
with UDP_SEGMENT"). When UDP_GRO is enabled, such socket is also
eligible for GRO in the rx path: UDP segments directed to such socket
are assembled into a larger GSO_UDP_L4 packet.

The core UDP GRO support is enabled with setsockopt(UDP_GRO).

Initial benchmark numbers:

Before:
udp rx:   1079 MB/s   769065 calls/s

After:
udp rx:   1466 MB/s    24877 calls/s

This change introduces a side effect in respect to UDP tunnels:
after a UDP tunnel creation, now the kernel performs a lookup per ingress
UDP packet, while before such lookup happened only if the ingress packet
carried a valid internal header csum.

rfc v2 -> rfc v3:
 - fixed typos in macro name and comments
 - really enforce UDP_GRO_CNT_MAX, instead of UDP_GRO_CNT_MAX + 1
 - acquire socket lock in UDP_GRO setsockopt

rfc v1 -> rfc v2:
 - use a new option to enable UDP GRO
 - use static keys to protect the UDP GRO socket lookup

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h      |   3 +-
 include/uapi/linux/udp.h |   1 +
 net/ipv4/udp.c           |   8 +++
 net/ipv4/udp_offload.c   | 109 +++++++++++++++++++++++++++++++--------
 net/ipv6/udp_offload.c   |   6 +--
 5 files changed, 99 insertions(+), 28 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index a4dafff407fb..f613b329852e 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -50,11 +50,12 @@ struct udp_sock {
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
 			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
-			 encap_enabled:1; /* This socket enabled encap
+			 encap_enabled:1, /* This socket enabled encap
 					   * processing; UDP tunnels and
 					   * different encapsulation layer set
 					   * this
 					   */
+			 gro_enabled:1;	/* Can accept GRO packets */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 09502de447f5..30baccb6c9c4 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -33,6 +33,7 @@ struct udphdr {
 #define UDP_NO_CHECK6_TX 101	/* Disable sending checksum for UDP6X */
 #define UDP_NO_CHECK6_RX 102	/* Disable accpeting checksum for UDP6 */
 #define UDP_SEGMENT	103	/* Set GSO segmentation size */
+#define UDP_GRO		104	/* This socket can receive UDP GRO packets */
 
 /* UDP encapsulation types */
 #define UDP_ENCAP_ESPINUDP_NON_IKE	1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f81409921e27..9fc08b098ced 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2473,6 +2473,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		up->gso_size = val;
 		break;
 
+	case UDP_GRO:
+		lock_sock(sk);
+		if (valbool)
+			udp_tunnel_encap_enable(sk->sk_socket);
+		up->gro_enabled = valbool;
+		release_sock(sk);
+		break;
+
 	/*
 	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
 	 */
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 802f2bc00d69..0646d61f4fa8 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -343,6 +343,54 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	return segs;
 }
 
+#define UDP_GRO_CNT_MAX 64
+static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
+					       struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+	struct sk_buff *pp = NULL;
+	struct udphdr *uh2;
+	struct sk_buff *p;
+
+	/* requires non zero csum, for symmetry with GSO */
+	if (!uh->check) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	/* pull encapsulating udp header */
+	skb_gro_pull(skb, sizeof(struct udphdr));
+	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
+
+	list_for_each_entry(p, head, list) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		uh2 = udp_hdr(p);
+
+		/* Match ports only, as csum is always non zero */
+		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+
+		/* Terminate the flow on len mismatch or if it grow "too much".
+		 * Under small packet flood GRO count could elsewhere grow a lot
+		 * leading to execessive truesize values
+		 */
+		if (!skb_gro_receive(p, skb) &&
+		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
+			pp = p;
+		else if (uh->len != uh2->len)
+			pp = p;
+
+		return pp;
+	}
+
+	/* mismatch, but we never need to flush */
+	return NULL;
+}
+
 struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 				struct udphdr *uh, udp_lookup_t lookup)
 {
@@ -353,23 +401,27 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	int flush = 1;
 	struct sock *sk;
 
+	rcu_read_lock();
+	sk = (*lookup)(skb, uh->source, uh->dest);
+	if (!sk)
+		goto out_unlock;
+
+	if (udp_sk(sk)->gro_enabled) {
+		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
+		rcu_read_unlock();
+		return pp;
+	}
+
 	if (NAPI_GRO_CB(skb)->encap_mark ||
 	    (skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
-	     !NAPI_GRO_CB(skb)->csum_valid))
-		goto out;
+	     !NAPI_GRO_CB(skb)->csum_valid) ||
+	    !udp_sk(sk)->gro_receive)
+		goto out_unlock;
 
 	/* mark that this skb passed once through the tunnel gro layer */
 	NAPI_GRO_CB(skb)->encap_mark = 1;
 
-	rcu_read_lock();
-	sk = (*lookup)(skb, uh->source, uh->dest);
-
-	if (sk && udp_sk(sk)->gro_receive)
-		goto unflush;
-	goto out_unlock;
-
-unflush:
 	flush = 0;
 
 	list_for_each_entry(p, head, list) {
@@ -394,7 +446,6 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 
 out_unlock:
 	rcu_read_unlock();
-out:
 	skb_gro_flush_final(skb, pp, flush);
 	return pp;
 }
@@ -427,6 +478,19 @@ static struct sk_buff *udp4_gro_receive(struct list_head *head,
 	return NULL;
 }
 
+static int udp_gro_complete_segment(struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	skb->csum_start = (unsigned char *)uh - skb->head;
+	skb->csum_offset = offsetof(struct udphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+	return 0;
+}
+
 int udp_gro_complete(struct sk_buff *skb, int nhoff,
 		     udp_lookup_t lookup)
 {
@@ -437,16 +501,21 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 
 	uh->len = newlen;
 
-	/* Set encapsulation before calling into inner gro_complete() functions
-	 * to make them set up the inner offsets.
-	 */
-	skb->encapsulation = 1;
-
 	rcu_read_lock();
 	sk = (*lookup)(skb, uh->source, uh->dest);
-	if (sk && udp_sk(sk)->gro_complete)
+	if (sk && udp_sk(sk)->gro_enabled) {
+		err = udp_gro_complete_segment(skb);
+	} else if (sk && udp_sk(sk)->gro_complete) {
+		skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
+					: SKB_GSO_UDP_TUNNEL;
+
+		/* Set encapsulation before calling into inner gro_complete()
+		 * functions to make them set up the inner offsets.
+		 */
+		skb->encapsulation = 1;
 		err = udp_sk(sk)->gro_complete(sk, skb,
 				nhoff + sizeof(struct udphdr));
+	}
 	rcu_read_unlock();
 
 	if (skb->remcsum_offload)
@@ -461,13 +530,9 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+	if (uh->check)
 		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
 					  iph->daddr, 0);
-	} else {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
-	}
 
 	return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
 }
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 1b8e161ac527..828b2457f97b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -147,13 +147,9 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (uh->check) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+	if (uh->check)
 		uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
 					  &ipv6h->daddr, 0);
-	} else {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
-	}
 
 	return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
 }

From bcd1665e3569b0a6f569514f023a41fc7df0b4a3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:30 +0100
Subject: [PATCH 03/10] udp: add support for UDP_GRO cmsg

When UDP GRO is enabled, the UDP_GRO cmsg will carry the ingress
datagram size. User-space can use such info to compute the original
packets layout.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h | 11 +++++++++++
 net/ipv4/udp.c      |  4 ++++
 net/ipv6/udp.c      |  3 +++
 3 files changed, 18 insertions(+)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index f613b329852e..e23d5024f42f 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -121,6 +121,17 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
+static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
+				 struct sk_buff *skb)
+{
+	int gso_size;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		gso_size = skb_shinfo(skb)->gso_size;
+		put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size);
+	}
+}
+
 #define udp_portaddr_for_each_entry(__sk, list) \
 	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9fc08b098ced..dddc6fe90f51 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1711,6 +1711,10 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 		*addr_len = sizeof(*sin);
 	}
+
+	if (udp_sk(sk)->gro_enabled)
+		udp_cmsg_recv(msg, sk, skb);
+
 	if (inet->cmsg_flags)
 		ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index bdf7e071a63b..4c79dc5329bc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -417,6 +417,9 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		*addr_len = sizeof(*sin6);
 	}
 
+	if (udp_sk(sk)->gro_enabled)
+		udp_cmsg_recv(msg, sk, skb);
+
 	if (np->rxopt.all)
 		ip6_datagram_recv_common_ctl(sk, msg, skb);
 

From 68cb7d531e6a87250a51b8a4ee1c79b3445aeff3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:31 +0100
Subject: [PATCH 04/10] ip: factor out protocol delivery helper

So that we can re-use it at the UDP level in a later patch

rfc v3 -> v1
 - add the helper declaration into the ip header

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  1 +
 net/ipv4/ip_input.c | 79 ++++++++++++++++++++++-----------------------
 2 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 462182f78236..8866bfce6121 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -155,6 +155,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 		 struct net_device *orig_dev);
 int ip_local_deliver(struct sk_buff *skb);
+void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 35a786c0aaa0..72250b4e466d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -188,51 +188,50 @@ bool ip_call_ra_chain(struct sk_buff *skb)
 	return false;
 }
 
+void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
+{
+	const struct net_protocol *ipprot;
+	int raw, ret;
+
+resubmit:
+	raw = raw_local_deliver(skb, protocol);
+
+	ipprot = rcu_dereference(inet_protos[protocol]);
+	if (ipprot) {
+		if (!ipprot->no_policy) {
+			if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				kfree_skb(skb);
+				return;
+			}
+			nf_reset(skb);
+		}
+		ret = ipprot->handler(skb);
+		if (ret < 0) {
+			protocol = -ret;
+			goto resubmit;
+		}
+		__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+	} else {
+		if (!raw) {
+			if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+				__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
+				icmp_send(skb, ICMP_DEST_UNREACH,
+					  ICMP_PROT_UNREACH, 0);
+			}
+			kfree_skb(skb);
+		} else {
+			__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
+			consume_skb(skb);
+		}
+	}
+}
+
 static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	__skb_pull(skb, skb_network_header_len(skb));
 
 	rcu_read_lock();
-	{
-		int protocol = ip_hdr(skb)->protocol;
-		const struct net_protocol *ipprot;
-		int raw;
-
-	resubmit:
-		raw = raw_local_deliver(skb, protocol);
-
-		ipprot = rcu_dereference(inet_protos[protocol]);
-		if (ipprot) {
-			int ret;
-
-			if (!ipprot->no_policy) {
-				if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-					kfree_skb(skb);
-					goto out;
-				}
-				nf_reset(skb);
-			}
-			ret = ipprot->handler(skb);
-			if (ret < 0) {
-				protocol = -ret;
-				goto resubmit;
-			}
-			__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
-		} else {
-			if (!raw) {
-				if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
-					__IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS);
-					icmp_send(skb, ICMP_DEST_UNREACH,
-						  ICMP_PROT_UNREACH, 0);
-				}
-				kfree_skb(skb);
-			} else {
-				__IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS);
-				consume_skb(skb);
-			}
-		}
-	}
- out:
+	ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol);
 	rcu_read_unlock();
 
 	return 0;

From 80bde363f9a43d942e404821b966e362131cd0ca Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:32 +0100
Subject: [PATCH 05/10] ipv6: factor out protocol delivery helper

So that we can re-use it at the UDP level in the next patch

rfc v3 -> v1:
 - add the helper declaration into the ipv6 header

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h   |  2 ++
 net/ipv6/ip6_input.c | 28 ++++++++++++++++------------
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 829650540780..daf80863d3a5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -975,6 +975,8 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip6_forward(struct sk_buff *skb);
 int ip6_input(struct sk_buff *skb);
 int ip6_mc_input(struct sk_buff *skb);
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+			      bool have_final);
 
 int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index df58e1100226..3c06cc9e9b79 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -319,28 +319,26 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
 /*
  *	Deliver the packet to the host
  */
-
-
-static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+			      bool have_final)
 {
 	const struct inet6_protocol *ipprot;
 	struct inet6_dev *idev;
 	unsigned int nhoff;
-	int nexthdr;
 	bool raw;
-	bool have_final = false;
 
 	/*
 	 *	Parse extension headers
 	 */
 
-	rcu_read_lock();
 resubmit:
 	idev = ip6_dst_idev(skb_dst(skb));
-	if (!pskb_pull(skb, skb_transport_offset(skb)))
-		goto discard;
 	nhoff = IP6CB(skb)->nhoff;
-	nexthdr = skb_network_header(skb)[nhoff];
+	if (!have_final) {
+		if (!pskb_pull(skb, skb_transport_offset(skb)))
+			goto discard;
+		nexthdr = skb_network_header(skb)[nhoff];
+	}
 
 resubmit_final:
 	raw = raw6_local_deliver(skb, nexthdr);
@@ -423,13 +421,19 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
 			consume_skb(skb);
 		}
 	}
-	rcu_read_unlock();
-	return 0;
+	return;
 
 discard:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
-	rcu_read_unlock();
 	kfree_skb(skb);
+}
+
+static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	rcu_read_lock();
+	ip6_protocol_deliver_rcu(net, skb, 0, false);
+	rcu_read_unlock();
+
 	return 0;
 }
 

From cf329aa42b6659204fee865bbce0ea20462552eb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:33 +0100
Subject: [PATCH 06/10] udp: cope with UDP GRO packet misdirection

In some scenarios, the GRO engine can assemble an UDP GRO packet
that ultimately lands on a non GRO-enabled socket.
This patch tries to address the issue explicitly checking for the UDP
socket features before enqueuing the packet, and eventually segmenting
the unexpected GRO packet, as needed.

We must also cope with re-insertion requests: after segmentation the
UDP code calls the helper introduced by the previous patches, as needed.

Segmentation is performed by a common helper, which takes care of
updating socket and protocol stats is case of failure.

rfc v3 -> v1
 - fix compile issues with rxrpc
 - when gso_segment returns NULL, treat is as an error
 - added 'ipv4' argument to udp_rcv_segment()

rfc v2 -> rfc v3
 - moved udp_rcv_segment() into net/udp.h, account errors to socket
   and ns, always return NULL or segs list

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h |  6 ++++++
 include/net/udp.h   | 45 +++++++++++++++++++++++++++++++++++++--------
 net/ipv4/udp.c      | 23 ++++++++++++++++++++++-
 net/ipv6/udp.c      | 24 +++++++++++++++++++++++-
 4 files changed, 88 insertions(+), 10 deletions(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index e23d5024f42f..0a9c54e76305 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -132,6 +132,12 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
 	}
 }
 
+static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
+{
+	return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) &&
+	       skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4;
+}
+
 #define udp_portaddr_for_each_entry(__sk, list) \
 	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 
diff --git a/include/net/udp.h b/include/net/udp.h
index a496e441645e..eccca2325ee6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -417,17 +417,24 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off,
 } while(0)
 
 #if IS_ENABLED(CONFIG_IPV6)
-#define __UDPX_INC_STATS(sk, field)					\
-do {									\
-	if ((sk)->sk_family == AF_INET)					\
-		__UDP_INC_STATS(sock_net(sk), field, 0);		\
-	else								\
-		__UDP6_INC_STATS(sock_net(sk), field, 0);		\
-} while (0)
+#define __UDPX_MIB(sk, ipv4)						\
+({									\
+	ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics :	\
+				 sock_net(sk)->mib.udp_statistics) :	\
+		(IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 :	\
+				 sock_net(sk)->mib.udp_stats_in6);	\
+})
 #else
-#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0)
+#define __UDPX_MIB(sk, ipv4)						\
+({									\
+	IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics :		\
+			 sock_net(sk)->mib.udp_statistics;		\
+})
 #endif
 
+#define __UDPX_INC_STATS(sk, field) \
+	__SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field)
+
 #ifdef CONFIG_PROC_FS
 struct udp_seq_afinfo {
 	sa_family_t			family;
@@ -461,4 +468,26 @@ DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
 void udpv6_encap_enable(void);
 #endif
 
+static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
+					      struct sk_buff *skb, bool ipv4)
+{
+	struct sk_buff *segs;
+
+	/* the GSO CB lays after the UDP one, no need to save and restore any
+	 * CB fragment
+	 */
+	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	if (unlikely(IS_ERR_OR_NULL(segs))) {
+		int segs_nr = skb_shinfo(skb)->gso_segs;
+
+		atomic_add(segs_nr, &sk->sk_drops);
+		SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr);
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	consume_skb(skb);
+	return segs;
+}
+
 #endif	/* _UDP_H */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dddc6fe90f51..3488650b90ac 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1906,7 +1906,7 @@ EXPORT_SYMBOL(udp_encap_enable);
  * Note that in the success and error cases, the skb is assumed to
  * have either been requeued or freed.
  */
-static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
@@ -2009,6 +2009,27 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return -1;
 }
 
+static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *next, *segs;
+	int ret;
+
+	if (likely(!udp_unexpected_gso(sk, skb)))
+		return udp_queue_rcv_one_skb(sk, skb);
+
+	BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET);
+	__skb_push(skb, -skb_mac_offset(skb));
+	segs = udp_rcv_segment(sk, skb, true);
+	for (skb = segs; skb; skb = next) {
+		next = skb->next;
+		__skb_pull(skb, skb_transport_offset(skb));
+		ret = udp_queue_rcv_one_skb(sk, skb);
+		if (ret > 0)
+			ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret);
+	}
+	return 0;
+}
+
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4c79dc5329bc..c55698d19d68 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -554,7 +554,7 @@ void udpv6_encap_enable(void)
 }
 EXPORT_SYMBOL(udpv6_encap_enable);
 
-static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
@@ -637,6 +637,28 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return -1;
 }
 
+static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *next, *segs;
+	int ret;
+
+	if (likely(!udp_unexpected_gso(sk, skb)))
+		return udpv6_queue_rcv_one_skb(sk, skb);
+
+	__skb_push(skb, -skb_mac_offset(skb));
+	segs = udp_rcv_segment(sk, skb, false);
+	for (skb = segs; skb; skb = next) {
+		next = skb->next;
+		__skb_pull(skb, skb_transport_offset(skb));
+
+		ret = udpv6_queue_rcv_one_skb(sk, skb);
+		if (ret > 0)
+			ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
+						 true);
+	}
+	return 0;
+}
+
 static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 				   __be16 loc_port, const struct in6_addr *loc_addr,
 				   __be16 rmt_port, const struct in6_addr *rmt_addr,

From 0a9ac2e95409169ed42ea66dd4270bc16b868e21 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:34 +0100
Subject: [PATCH 07/10] selftests: add GRO support to udp bench rx program

And fix a couple of buglets (port option processing,
clean termination on SIGINT). This is preparatory work
for GRO tests.

rfc v2 -> rfc v3:
 - use ETH_MAX_MTU

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgso_bench_rx.c | 37 +++++++++++++++----
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 727cf67a3f75..8f48d7fb32cf 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -31,9 +31,15 @@
 #include <sys/wait.h>
 #include <unistd.h>
 
+#ifndef UDP_GRO
+#define UDP_GRO		104
+#endif
+
 static int  cfg_port		= 8000;
 static bool cfg_tcp;
 static bool cfg_verify;
+static bool cfg_read_all;
+static bool cfg_gro_segment;
 
 static bool interrupted;
 static unsigned long packets, bytes;
@@ -63,6 +69,8 @@ static void do_poll(int fd)
 
 	do {
 		ret = poll(&pfd, 1, 10);
+		if (interrupted)
+			break;
 		if (ret == -1)
 			error(1, errno, "poll");
 		if (ret == 0)
@@ -70,7 +78,7 @@ static void do_poll(int fd)
 		if (pfd.revents != POLLIN)
 			error(1, errno, "poll: 0x%x expected 0x%x\n",
 					pfd.revents, POLLIN);
-	} while (!ret && !interrupted);
+	} while (!ret);
 }
 
 static int do_socket(bool do_tcp)
@@ -102,6 +110,8 @@ static int do_socket(bool do_tcp)
 			error(1, errno, "listen");
 
 		do_poll(accept_fd);
+		if (interrupted)
+			exit(0);
 
 		fd = accept(accept_fd, NULL, NULL);
 		if (fd == -1)
@@ -167,10 +177,10 @@ static void do_verify_udp(const char *data, int len)
 /* Flush all outstanding datagrams. Verify first few bytes of each. */
 static void do_flush_udp(int fd)
 {
-	static char rbuf[ETH_DATA_LEN];
+	static char rbuf[ETH_MAX_MTU];
 	int ret, len, budget = 256;
 
-	len = cfg_verify ? sizeof(rbuf) : 0;
+	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
 		/* MSG_TRUNC will make return value full datagram length */
 		ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
@@ -178,7 +188,7 @@ static void do_flush_udp(int fd)
 			return;
 		if (ret == -1)
 			error(1, errno, "recv");
-		if (len) {
+		if (len && cfg_verify) {
 			if (ret == 0)
 				error(1, errno, "recv: 0 byte datagram\n");
 
@@ -192,23 +202,30 @@ static void do_flush_udp(int fd)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+	error(1, 0, "Usage: %s [-Grtv] [-p port]", filepath);
 }
 
 static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "ptv")) != -1) {
+	while ((c = getopt(argc, argv, "Gp:rtv")) != -1) {
 		switch (c) {
+		case 'G':
+			cfg_gro_segment = true;
+			break;
 		case 'p':
-			cfg_port = htons(strtoul(optarg, NULL, 0));
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'r':
+			cfg_read_all = true;
 			break;
 		case 't':
 			cfg_tcp = true;
 			break;
 		case 'v':
 			cfg_verify = true;
+			cfg_read_all = true;
 			break;
 		}
 	}
@@ -227,6 +244,12 @@ static void do_recv(void)
 
 	fd = do_socket(cfg_tcp);
 
+	if (cfg_gro_segment && !cfg_tcp) {
+		int val = 1;
+		if (setsockopt(fd, IPPROTO_UDP, UDP_GRO, &val, sizeof(val)))
+			error(1, errno, "setsockopt UDP_GRO");
+	}
+
 	treport = gettimeofday_ms() + 1000;
 	do {
 		do_poll(fd);

From bd8e1afe6436558de3a7b25eaef34b69d98e5719 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:35 +0100
Subject: [PATCH 08/10] selftests: add dummy xdp test helper

This trivial XDP program does nothing, but will be used by the
next patch to test the GRO path in a net namespace, leveraging
the veth XDP implementation.

It's added here, despite its 'net' usage, to avoid the duplication
of the llc-related makefile boilerplate.

rfc v3 -> v1:
 - move the helper implementation into the bpf directory, don't
   touch udpgso_bench_rx

rfc v2 -> rfc v3:
 - move 'x' option handling here

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/Makefile    |  3 ++-
 tools/testing/selftests/bpf/xdp_dummy.c | 13 +++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/xdp_dummy.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4e7970..4a54236475ae 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -37,7 +37,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
-	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
+	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o \
+	xdp_dummy.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/xdp_dummy.c b/tools/testing/selftests/bpf/xdp_dummy.c
new file mode 100644
index 000000000000..43b0ef1001ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

From e87f53b4fab72f95952c17f672088e082e8e79ab Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:36 +0100
Subject: [PATCH 09/10] selftests: add some benchmark for UDP GRO

Run on top of veth pair, using a dummy XDP program to enable the GRO.

 rfc v3 -> v1:
  - use ip route to attach the xdp helper to the veth

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile        |  1 +
 tools/testing/selftests/net/udpgro_bench.sh | 93 +++++++++++++++++++++
 2 files changed, 94 insertions(+)
 create mode 100755 tools/testing/selftests/net/udpgro_bench.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 256d82d5fa87..b1bba2f60467 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,6 +7,7 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
+TEST_PROGS += udpgro_bench.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
new file mode 100755
index 000000000000..9ef4b1ee0f76
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -0,0 +1,93 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro benchmarks
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+	local -r jobs="$(jobs -p)"
+	local -r ns="$(ip netns list|grep $PEER_NS)"
+
+	[ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null
+	[ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+run_one() {
+	# use 'rx' as separator between sender args and receiver args
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	ip netns add "${PEER_NS}"
+	ip -netns "${PEER_NS}" link set lo up
+	ip link add type veth
+	ip link set dev veth0 up
+	ip addr add dev veth0 192.168.1.2/24
+	ip addr add dev veth0 2001:db8::2/64 nodad
+
+	ip link set dev veth1 netns "${PEER_NS}"
+	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+	ip -netns "${PEER_NS}" link set dev veth1 up
+
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
+
+	# Hack: let bg programs complete the startup
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+}
+
+run_in_netns() {
+	local -r args=$@
+
+	./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+	local -r args=$@
+
+	echo "udp gso - over veth touching data"
+	run_in_netns ${args} -S rx
+
+	echo "udp gso and gro - over veth touching data"
+	run_in_netns ${args} -S rx -G
+}
+
+run_tcp() {
+	local -r args=$@
+
+	echo "tcp - over veth touching data"
+	run_in_netns ${args} -t rx
+}
+
+run_all() {
+	local -r core_args="-l 4"
+	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+	echo "ipv4"
+	run_tcp "${ipv4_args}"
+	run_udp "${ipv4_args}"
+
+	echo "ipv6"
+	run_tcp "${ipv4_args}"
+	run_udp "${ipv6_args}"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+	echo "Missing xdp_dummy helper. Build bpf selftest first"
+	exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+	run_all
+elif [[ $1 == "__subprocess" ]]; then
+	shift
+	run_one $@
+else
+	run_in_netns $@
+fi

From 3327a9c46352f111697d93d6134e7bf37c6bffca Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Nov 2018 12:38:37 +0100
Subject: [PATCH 10/10] selftests: add functionals test for UDP GRO

Extends the existing udp programs to allow checking for proper
GRO aggregation/GSO size, and run the tests via a shell script, using
a veth pair with XDP program attached to trigger the GRO code path.

rfc v3 -> v1:
 - use ip route to attach the xdp helper to the veth

rfc v2 -> rfc v3:
 - add missing test program options documentation
 - fix sporatic test failures (receiver faster than sender)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile          |   2 +-
 tools/testing/selftests/net/udpgro.sh         | 148 ++++++++++++++++++
 tools/testing/selftests/net/udpgro_bench.sh   |   8 +-
 tools/testing/selftests/net/udpgso_bench.sh   |   2 +-
 tools/testing/selftests/net/udpgso_bench_rx.c | 123 +++++++++++++--
 tools/testing/selftests/net/udpgso_bench_tx.c |  22 ++-
 6 files changed, 282 insertions(+), 23 deletions(-)
 create mode 100755 tools/testing/selftests/net/udpgro.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b1bba2f60467..eec359895feb 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
-TEST_PROGS += udpgro_bench.sh
+TEST_PROGS += udpgro_bench.sh udpgro.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
new file mode 100755
index 000000000000..e94ef8067173
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -0,0 +1,148 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro functional tests.
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+	local -r jobs="$(jobs -p)"
+	local -r ns="$(ip netns list|grep $PEER_NS)"
+
+	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+	[ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+cfg_veth() {
+	ip netns add "${PEER_NS}"
+	ip -netns "${PEER_NS}" link set lo up
+	ip link add type veth
+	ip link set dev veth0 up
+	ip addr add dev veth0 192.168.1.2/24
+	ip addr add dev veth0 2001:db8::2/64 nodad
+
+	ip link set dev veth1 netns "${PEER_NS}"
+	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+	ip -netns "${PEER_NS}" link set dev veth1 up
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+}
+
+run_one() {
+	# use 'rx' as separator between sender args and receiver args
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	cfg_veth
+
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+		echo "ok" || \
+		echo "failed" &
+
+	# Hack: let bg programs complete the startup
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+	wait $(jobs -p)
+}
+
+run_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess $2 rx -G -r $3
+}
+
+run_one_nat() {
+	# use 'rx' as separator between sender args and receiver args
+	local addr1 addr2 pid family="" ipt_cmd=ip6tables
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	if [[ ${tx_args} = *-4* ]]; then
+		ipt_cmd=iptables
+		family=-4
+		addr1=192.168.1.1
+		addr2=192.168.1.3/24
+	else
+		addr1=2001:db8::1
+		addr2="2001:db8::3/64 nodad"
+	fi
+
+	cfg_veth
+	ip -netns "${PEER_NS}" addr add dev veth1 ${addr2}
+
+	# fool the GRO engine changing the destination address ...
+	ip netns exec "${PEER_NS}" $ipt_cmd -t nat -I PREROUTING -d ${addr1} -j DNAT --to-destination ${addr2%/*}
+
+	# ... so that GRO will match the UDP_GRO enabled socket, but packets
+	# will land on the 'plain' one
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
+	pid=$!
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${family} -b ${addr2%/*} ${rx_args} && \
+		echo "ok" || \
+		echo "failed"&
+
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+	kill -INT $pid
+	wait $(jobs -p)
+}
+
+run_nat_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess_nat $2 rx -r $3
+}
+
+run_all() {
+	local -r core_args="-l 4"
+	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+	echo "ipv4"
+	run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+
+	# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
+	# when GRO does not take place
+	run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+
+	# the GSO packets are aggregated because:
+	# * veth schedule napi after each xmit
+	# * segmentation happens in BH context, veth napi poll is delayed after
+	#   the transmission of the last segment
+	run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+	run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+	run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+
+	run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+
+	echo "ipv6"
+	run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+	run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+	run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+	run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+	run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+	run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+
+	run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+	echo "Missing xdp_dummy helper. Build bpf selftest first"
+	exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+	run_all
+elif [[ $1 == "__subprocess" ]]; then
+	shift
+	run_one $@
+elif [[ $1 == "__subprocess_nat" ]]; then
+	shift
+	run_one_nat $@
+fi
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 9ef4b1ee0f76..820bc50f6b68 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -18,7 +18,9 @@ run_one() {
 	# use 'rx' as separator between sender args and receiver args
 	local -r all="$@"
 	local -r tx_args=${all%rx*}
-	local -r rx_args=${all#*rx}
+	local rx_args=${all#*rx}
+
+	[[ "${tx_args}" == *"-4"* ]] && rx_args="${rx_args} -4"
 
 	ip netns add "${PEER_NS}"
 	ip -netns "${PEER_NS}" link set lo up
@@ -51,10 +53,10 @@ run_udp() {
 	local -r args=$@
 
 	echo "udp gso - over veth touching data"
-	run_in_netns ${args} -S rx
+	run_in_netns ${args} -S 0 rx
 
 	echo "udp gso and gro - over veth touching data"
-	run_in_netns ${args} -S rx -G
+	run_in_netns ${args} -S 0 rx -G
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 99e537ab5ad9..0f0628613f81 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -34,7 +34,7 @@ run_udp() {
 	run_in_netns ${args}
 
 	echo "udp gso"
-	run_in_netns ${args} -S
+	run_in_netns ${args} -S 0
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 8f48d7fb32cf..0c960f673324 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -40,6 +40,12 @@ static bool cfg_tcp;
 static bool cfg_verify;
 static bool cfg_read_all;
 static bool cfg_gro_segment;
+static int  cfg_family		= PF_INET6;
+static int  cfg_alen 		= sizeof(struct sockaddr_in6);
+static int  cfg_expected_pkt_nr;
+static int  cfg_expected_pkt_len;
+static int  cfg_expected_gso_size;
+static struct sockaddr_storage cfg_bind_addr;
 
 static bool interrupted;
 static unsigned long packets, bytes;
@@ -50,6 +56,29 @@ static void sigint_handler(int signum)
 		interrupted = true;
 }
 
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (domain) {
+	case PF_INET:
+		addr4->sin_family = AF_INET;
+		addr4->sin_port = htons(cfg_port);
+		if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+			error(1, 0, "ipv4 parse error: %s", str_addr);
+		break;
+	case PF_INET6:
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_port = htons(cfg_port);
+		if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+			error(1, 0, "ipv6 parse error: %s", str_addr);
+		break;
+	default:
+		error(1, 0, "illegal domain");
+	}
+}
+
 static unsigned long gettimeofday_ms(void)
 {
 	struct timeval tv;
@@ -83,10 +112,9 @@ static void do_poll(int fd)
 
 static int do_socket(bool do_tcp)
 {
-	struct sockaddr_in6 addr = {0};
 	int fd, val;
 
-	fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+	fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
 	if (fd == -1)
 		error(1, errno, "socket");
 
@@ -97,10 +125,7 @@ static int do_socket(bool do_tcp)
 	if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
 		error(1, errno, "setsockopt reuseport");
 
-	addr.sin6_family =	PF_INET6;
-	addr.sin6_port =	htons(cfg_port);
-	addr.sin6_addr =	in6addr_any;
-	if (bind(fd, (void *) &addr, sizeof(addr)))
+	if (bind(fd, (void *)&cfg_bind_addr, cfg_alen))
 		error(1, errno, "bind");
 
 	if (do_tcp) {
@@ -174,52 +199,117 @@ static void do_verify_udp(const char *data, int len)
 	}
 }
 
+static int recv_msg(int fd, char *buf, int len, int *gso_size)
+{
+	char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	struct cmsghdr *cmsg;
+	uint16_t *gsosizeptr;
+	int ret;
+
+	iov.iov_base = buf;
+	iov.iov_len = len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	*gso_size = -1;
+	ret = recvmsg(fd, &msg, MSG_TRUNC | MSG_DONTWAIT);
+	if (ret != -1) {
+		for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL;
+		     cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+			if (cmsg->cmsg_level == SOL_UDP
+			    && cmsg->cmsg_type == UDP_GRO) {
+				gsosizeptr = (uint16_t *) CMSG_DATA(cmsg);
+				*gso_size = *gsosizeptr;
+				break;
+			}
+		}
+	}
+	return ret;
+}
+
 /* Flush all outstanding datagrams. Verify first few bytes of each. */
 static void do_flush_udp(int fd)
 {
 	static char rbuf[ETH_MAX_MTU];
-	int ret, len, budget = 256;
+	int ret, len, gso_size, budget = 256;
 
 	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
 		/* MSG_TRUNC will make return value full datagram length */
-		ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		if (!cfg_expected_gso_size)
+			ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		else
+			ret = recv_msg(fd, rbuf, len, &gso_size);
 		if (ret == -1 && errno == EAGAIN)
-			return;
+			break;
 		if (ret == -1)
 			error(1, errno, "recv");
+		if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len)
+			error(1, 0, "recv: bad packet len, got %d,"
+			      " expected %d\n", ret, cfg_expected_pkt_len);
 		if (len && cfg_verify) {
 			if (ret == 0)
 				error(1, errno, "recv: 0 byte datagram\n");
 
 			do_verify_udp(rbuf, ret);
 		}
+		if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size)
+			error(1, 0, "recv: bad gso size, got %d, expected %d "
+			      "(-1 == no gso cmsg))\n", gso_size,
+			      cfg_expected_gso_size);
 
 		packets++;
 		bytes += ret;
+		if (cfg_expected_pkt_nr && packets >= cfg_expected_pkt_nr)
+			break;
 	}
 }
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-Grtv] [-p port]", filepath);
+	error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath);
 }
 
 static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "Gp:rtv")) != -1) {
+	/* bind to any by default */
+	setup_sockaddr(PF_INET6, "::", &cfg_bind_addr);
+	while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) {
 		switch (c) {
+		case '4':
+			cfg_family = PF_INET;
+			cfg_alen = sizeof(struct sockaddr_in);
+			setup_sockaddr(PF_INET, "0.0.0.0", &cfg_bind_addr);
+			break;
+		case 'b':
+			setup_sockaddr(cfg_family, optarg, &cfg_bind_addr);
+			break;
 		case 'G':
 			cfg_gro_segment = true;
 			break;
+		case 'l':
+			cfg_expected_pkt_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'n':
+			cfg_expected_pkt_nr = strtoul(optarg, NULL, 0);
+			break;
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
 		case 'r':
 			cfg_read_all = true;
 			break;
+		case 'S':
+			cfg_expected_gso_size = strtol(optarg, NULL, 0);
+			break;
 		case 't':
 			cfg_tcp = true;
 			break;
@@ -240,7 +330,7 @@ static void parse_opts(int argc, char **argv)
 static void do_recv(void)
 {
 	unsigned long tnow, treport;
-	int fd;
+	int fd, loop = 0;
 
 	fd = do_socket(cfg_tcp);
 
@@ -252,6 +342,11 @@ static void do_recv(void)
 
 	treport = gettimeofday_ms() + 1000;
 	do {
+		/* force termination after the second poll(); this cope both
+		 * with sender slower than receiver and missing packet errors
+		 */
+		if (cfg_expected_pkt_nr && loop++)
+			interrupted = true;
 		do_poll(fd);
 
 		if (cfg_tcp)
@@ -272,6 +367,10 @@ static void do_recv(void)
 
 	} while (!interrupted);
 
+	if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr))
+		error(1, 0, "wrong packet number! got %ld, expected %d\n",
+		      packets, cfg_expected_pkt_nr);
+
 	if (close(fd))
 		error(1, errno, "close");
 }
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index e821564053cf..4074538b5df5 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -52,6 +52,8 @@ static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
 static bool	cfg_zerocopy;
+static int	cfg_msg_nr;
+static uint16_t	cfg_gso_size;
 
 static socklen_t cfg_alen;
 static struct sockaddr_storage cfg_dst_addr;
@@ -205,14 +207,14 @@ static void send_udp_segment_cmsg(struct cmsghdr *cm)
 
 	cm->cmsg_level = SOL_UDP;
 	cm->cmsg_type = UDP_SEGMENT;
-	cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+	cm->cmsg_len = CMSG_LEN(sizeof(cfg_gso_size));
 	valp = (void *)CMSG_DATA(cm);
-	*valp = cfg_mss;
+	*valp = cfg_gso_size;
 }
 
 static int send_udp_segment(int fd, char *data)
 {
-	char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+	char control[CMSG_SPACE(sizeof(cfg_gso_size))] = {0};
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
 	int ret;
@@ -241,7 +243,7 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+	error(1, 0, "Usage: %s [-46cmtuz] [-C cpu] [-D dst ip] [-l secs] [-m messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -250,7 +252,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+	while ((c = getopt(argc, argv, "46cC:D:l:mM:p:s:S:tuz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -279,6 +281,9 @@ static void parse_opts(int argc, char **argv)
 		case 'm':
 			cfg_sendmmsg = true;
 			break;
+		case 'M':
+			cfg_msg_nr = strtoul(optarg, NULL, 10);
+			break;
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
@@ -286,6 +291,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_payload_len = strtoul(optarg, NULL, 0);
 			break;
 		case 'S':
+			cfg_gso_size = strtoul(optarg, NULL, 0);
 			cfg_segment = true;
 			break;
 		case 't':
@@ -317,6 +323,8 @@ static void parse_opts(int argc, char **argv)
 
 	cfg_mss = ETH_DATA_LEN - hdrlen;
 	max_len = ETH_MAX_MTU - hdrlen;
+	if (!cfg_gso_size)
+		cfg_gso_size = cfg_mss;
 
 	if (cfg_payload_len > max_len)
 		error(1, 0, "payload length %u exceeds max %u",
@@ -392,10 +400,12 @@ int main(int argc, char **argv)
 		else
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
-
 		if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
 			flush_zerocopy(fd);
 
+		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
+			break;
+
 		tnow = gettimeofday_ms();
 		if (tnow > treport) {
 			fprintf(stderr,