udp: implement GRO support

index 320d49d85484..a4dafff407fb 100644
@@ -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.

index fe680ab6b15a..3fbe56430e3b 100644
@@ -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();

index 1976fddb9e00..0ed715a72249 100644
@@ -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);

@@ -2398,11 +2399,15 @@ 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);
 	}
 }
 

@@ -2447,7 +2452,9 @@ 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;

index d2d97d07ef27..fc0ce6c59ebb 100644
@@ -1458,11 +1458,15 @@ 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);

index a4dafff407fb..f613b329852e 100644
@@ -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.

index 09502de447f5..30baccb6c9c4 100644
@@ -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 */

index 0ed715a72249..0d447fd194c5 100644
@@ -2476,6 +2476,14 @@ 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).
 	 */

158 lines not on this page · raw message

index 1b8e161ac527..828b2457f97b 100644
@@ -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);
 }

index f613b329852e..e23d5024f42f 100644
@@ -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)
 

index 0d447fd194c5..725ece9d78af 100644
@@ -1714,6 +1714,10 @@ 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);
 

index fc0ce6c59ebb..8e76e719305c 100644
@@ -421,6 +421,9 @@ 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);
 

index 72593e171d14..cece69b5c531 100644
@@ -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);

87 lines not on this page · raw message

index 829650540780..daf80863d3a5 100644
@@ -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);

index 96577e742afd..3065226bdc57 100644
@@ -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);

@@ -411,13 +409,19 @@ 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;
 }
 

index e23d5024f42f..0a9c54e76305 100644
@@ -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)
 

58 lines not on this page · raw message

index 725ece9d78af..73926352960c 100644
@@ -1909,7 +1909,7 @@ 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);

@@ -2012,6 +2012,27 @@ 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.
  */

index 8e76e719305c..f7666e34fec9 100644
@@ -558,7 +558,7 @@ 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);

@@ -641,6 +641,28 @@ 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,

index 727cf67a3f75..8f48d7fb32cf 100644
@@ -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);

new file mode 100644
index 000000000000..43b0ef1001ed
@@ -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";

214 lines not on this page · raw message

index e821564053cf..4074538b5df5 100644
@@ -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,