selftests: udp gso

Validate udp gso, including edge cases (such as min/max gso sizes).

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 504 insertions, 1 deletions

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 5559f6add046..67a26240407c 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -8,3 +8,4 @@ reuseport_bpf_numa
 reuseport_dualstack
 reuseaddr_conflict
 tcp_mmap
+udpgso
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c3761c35f542..db3303348315 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,12 +5,13 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 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 in_netns.sh pmtu.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh udpgso.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_FILES += tcp_mmap
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
+TEST_GEN_PROGS += udpgso
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
new file mode 100644
index 000000000000..58cabfc66bf8
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.c
@@ -0,0 +1,485 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <net/if.h>
+#include <linux/in.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <netinet/if_ether.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU	0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT		103
+#endif
+
+#define CONST_MTU_TEST	1500
+
+#define CONST_HDRLEN_V4		(sizeof(struct iphdr) + sizeof(struct udphdr))
+#define CONST_HDRLEN_V6		(sizeof(struct ip6_hdr) + sizeof(struct udphdr))
+
+#define CONST_MSS_V4		(CONST_MTU_TEST - CONST_HDRLEN_V4)
+#define CONST_MSS_V6		(CONST_MTU_TEST - CONST_HDRLEN_V6)
+
+#define CONST_MAX_SEGS_V4	(ETH_MAX_MTU / CONST_MSS_V4)
+#define CONST_MAX_SEGS_V6	(ETH_MAX_MTU / CONST_MSS_V6)
+
+static bool		cfg_do_ipv4;
+static bool		cfg_do_ipv6;
+static bool		cfg_do_connectionless;
+static bool		cfg_do_setsockopt;
+static int		cfg_specific_test_id = -1;
+
+static const char	cfg_ifname[] = "lo";
+static unsigned short	cfg_port = 9000;
+
+static char buf[ETH_MAX_MTU];
+
+struct testcase {
+	int tlen;		/* send() buffer size, may exceed mss */
+	bool tfail;		/* send() call is expected to fail */
+	int gso_len;		/* mss after applying gso */
+	int r_num_mss;		/* recv(): number of calls of full mss */
+	int r_len_last;		/* recv(): size of last non-mss dgram, if any */
+};
+
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+struct testcase testcases_v4[] = {
+	{
+		/* no GSO: send a single byte */
+		.tlen = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* no GSO: send a single MSS */
+		.tlen = CONST_MSS_V4,
+		.r_num_mss = 1,
+	},
+	{
+		/* no GSO: send a single MSS + 1B: fail */
+		.tlen = CONST_MSS_V4 + 1,
+		.tfail = true,
+	},
+	{
+		/* send a single MSS: will fail with GSO, because the segment
+		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+		 */
+		.tlen = CONST_MSS_V4,
+		.gso_len = CONST_MSS_V4,
+		.tfail = true,
+		.r_num_mss = 1,
+	},
+	{
+		/* send a single MSS + 1B */
+		.tlen = CONST_MSS_V4 + 1,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* send exactly 2 MSS */
+		.tlen = CONST_MSS_V4 * 2,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = 2,
+	},
+	{
+		/* send 2 MSS + 1B */
+		.tlen = (CONST_MSS_V4 * 2) + 1,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = 2,
+		.r_len_last = 1,
+	},
+	{
+		/* send MAX segs */
+		.tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4),
+	},
+
+	{
+		/* send MAX bytes */
+		.tlen = ETH_MAX_MTU - CONST_HDRLEN_V4,
+		.gso_len = CONST_MSS_V4,
+		.r_num_mss = CONST_MAX_SEGS_V4,
+		.r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 -
+			      (CONST_MAX_SEGS_V4 * CONST_MSS_V4),
+	},
+	{
+		/* send MAX + 1: fail */
+		.tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1,
+		.gso_len = CONST_MSS_V4,
+		.tfail = true,
+	},
+	{
+		/* EOL */
+	}
+};
+
+#ifndef IP6_MAX_MTU
+#define IP6_MAX_MTU	(ETH_MAX_MTU + sizeof(struct ip6_hdr))
+#endif
+
+struct testcase testcases_v6[] = {
+	{
+		/* no GSO: send a single byte */
+		.tlen = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* no GSO: send a single MSS */
+		.tlen = CONST_MSS_V6,
+		.r_num_mss = 1,
+	},
+	{
+		/* no GSO: send a single MSS + 1B: fail */
+		.tlen = CONST_MSS_V6 + 1,
+		.tfail = true,
+	},
+	{
+		/* send a single MSS: will fail with GSO, because the segment
+		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+		 */
+		.tlen = CONST_MSS_V6,
+		.gso_len = CONST_MSS_V6,
+		.tfail = true,
+		.r_num_mss = 1,
+	},
+	{
+		/* send a single MSS + 1B */
+		.tlen = CONST_MSS_V6 + 1,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = 1,
+		.r_len_last = 1,
+	},
+	{
+		/* send exactly 2 MSS */
+		.tlen = CONST_MSS_V6 * 2,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = 2,
+	},
+	{
+		/* send 2 MSS + 1B */
+		.tlen = (CONST_MSS_V6 * 2) + 1,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = 2,
+		.r_len_last = 1,
+	},
+	{
+		/* send MAX segs */
+		.tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6),
+	},
+
+	{
+		/* send MAX bytes */
+		.tlen = IP6_MAX_MTU - CONST_HDRLEN_V6,
+		.gso_len = CONST_MSS_V6,
+		.r_num_mss = CONST_MAX_SEGS_V6,
+		.r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 -
+			      (CONST_MAX_SEGS_V6 * CONST_MSS_V6),
+	},
+	{
+		/* send MAX + 1: fail */
+		.tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1,
+		.gso_len = CONST_MSS_V6,
+		.tfail = true,
+	},
+	{
+		/* EOL */
+	}
+};
+
+static unsigned int get_device_mtu(int fd, const char *ifname)
+{
+	struct ifreq ifr;
+
+	memset(&ifr, 0, sizeof(ifr));
+
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCGIFMTU, &ifr))
+		error(1, errno, "ioctl get mtu");
+
+	return ifr.ifr_mtu;
+}
+
+static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu)
+{
+	struct ifreq ifr;
+
+	memset(&ifr, 0, sizeof(ifr));
+
+	ifr.ifr_mtu = mtu;
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCSIFMTU, &ifr))
+		error(1, errno, "ioctl set mtu");
+}
+
+static void set_device_mtu(int fd, int mtu)
+{
+	int val;
+
+	val = get_device_mtu(fd, cfg_ifname);
+	fprintf(stderr, "device mtu (orig): %u\n", val);
+
+	__set_device_mtu(fd, cfg_ifname, mtu);
+	val = get_device_mtu(fd, cfg_ifname);
+	if (val != mtu)
+		error(1, 0, "unable to set device mtu to %u\n", val);
+
+	fprintf(stderr, "device mtu (test): %u\n", val);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+	int level, name, val;
+
+	if (is_ipv4) {
+		level	= SOL_IP;
+		name	= IP_MTU_DISCOVER;
+		val	= IP_PMTUDISC_DO;
+	} else {
+		level	= SOL_IPV6;
+		name	= IPV6_MTU_DISCOVER;
+		val	= IPV6_PMTUDISC_DO;
+	}
+
+	if (setsockopt(fd, level, name, &val, sizeof(val)))
+		error(1, errno, "setsockopt path mtu");
+}
+
+static bool send_one(int fd, int len, int gso_len,
+		     struct sockaddr *addr, socklen_t alen)
+{
+	char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	struct cmsghdr *cm;
+	int ret;
+
+	iov.iov_base = buf;
+	iov.iov_len = len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	msg.msg_name = addr;
+	msg.msg_namelen = alen;
+
+	if (gso_len && !cfg_do_setsockopt) {
+		msg.msg_control = control;
+		msg.msg_controllen = sizeof(control);
+
+		cm = CMSG_FIRSTHDR(&msg);
+		cm->cmsg_level = SOL_UDP;
+		cm->cmsg_type = UDP_SEGMENT;
+		cm->cmsg_len = CMSG_LEN(sizeof(uint16_t));
+		*((uint16_t *) CMSG_DATA(cm)) = gso_len;
+	}
+
+	ret = sendmsg(fd, &msg, 0);
+	if (ret == -1 && (errno == EMSGSIZE || errno == ENOMEM))
+		return false;
+	if (ret == -1)
+		error(1, errno, "sendmsg");
+	if (ret != len)
+		error(1, 0, "sendto: %d != %u", ret, len);
+
+	return true;
+}
+
+static int recv_one(int fd, int flags)
+{
+	int ret;
+
+	ret = recv(fd, buf, sizeof(buf), flags);
+	if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT))
+		return 0;
+	if (ret == -1)
+		error(1, errno, "recv");
+
+	return ret;
+}
+
+static void run_one(struct testcase *test, int fdt, int fdr,
+		    struct sockaddr *addr, socklen_t alen)
+{
+	int i, ret, val, mss;
+	bool sent;
+
+	fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+			addr->sa_family == AF_INET ? 4 : 6,
+			test->tlen, test->gso_len,
+			test->tfail ? "(fail)" : "");
+
+	val = test->gso_len;
+	if (cfg_do_setsockopt) {
+		if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
+			error(1, errno, "setsockopt udp segment");
+	}
+
+	sent = send_one(fdt, test->tlen, test->gso_len, addr, alen);
+	if (sent && test->tfail)
+		error(1, 0, "send succeeded while expecting failure");
+	if (!sent && !test->tfail)
+		error(1, 0, "send failed while expecting success");
+	if (!sent)
+		return;
+
+	mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6;
+
+	/* Recv all full MSS datagrams */
+	for (i = 0; i < test->r_num_mss; i++) {
+		ret = recv_one(fdr, 0);
+		if (ret != mss)
+			error(1, 0, "recv.%d: %d != %d", i, ret, mss);
+	}
+
+	/* Recv the non-full last datagram, if tlen was not a multiple of mss */
+	if (test->r_len_last) {
+		ret = recv_one(fdr, 0);
+		if (ret != test->r_len_last)
+			error(1, 0, "recv.%d: %d != %d (last)",
+			      i, ret, test->r_len_last);
+	}
+
+	/* Verify received all data */
+	ret = recv_one(fdr, MSG_DONTWAIT);
+	if (ret)
+		error(1, 0, "recv: unexpected datagram");
+}
+
+static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen)
+{
+	struct testcase *tests, *test;
+
+	tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6;
+
+	for (test = tests; test->tlen; test++) {
+		/* if a specific test is given, then skip all others */
+		if (cfg_specific_test_id == -1 ||
+		    cfg_specific_test_id == test - tests)
+			run_one(test, fdt, fdr, addr, alen);
+	}
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+	struct timeval tv = { .tv_usec = 100 * 1000 };
+	int fdr, fdt;
+
+	fdr = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fdr == -1)
+		error(1, errno, "socket r");
+
+	if (bind(fdr, addr, alen))
+		error(1, errno, "bind");
+
+	/* Have tests fail quickly instead of hang */
+	if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	fdt = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fdt == -1)
+		error(1, errno, "socket t");
+
+	/* Do not fragment these datagrams: only succeed if GSO works */
+	set_pmtu_discover(fdt, addr->sa_family == AF_INET);
+
+	if (cfg_do_connectionless) {
+		set_device_mtu(fdt, CONST_MTU_TEST);
+		run_all(fdt, fdr, addr, alen);
+	}
+
+	if (close(fdt))
+		error(1, errno, "close t");
+	if (close(fdr))
+		error(1, errno, "close r");
+}
+
+static void run_test_v4(void)
+{
+	struct sockaddr_in addr = {0};
+
+	addr.sin_family = AF_INET;
+	addr.sin_port = htons(cfg_port);
+	addr.sin_addr = addr4;
+
+	run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+	struct sockaddr_in6 addr = {0};
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_port = htons(cfg_port);
+	addr.sin6_addr = addr6;
+
+	run_test((void *)&addr, sizeof(addr));
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "46Cst:")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_do_ipv4 = true;
+			break;
+		case '6':
+			cfg_do_ipv6 = true;
+			break;
+		case 'C':
+			cfg_do_connectionless = true;
+			break;
+		case 's':
+			cfg_do_setsockopt = true;
+			break;
+		case 't':
+			cfg_specific_test_id = strtoul(optarg, NULL, 0);
+			break;
+		default:
+			error(1, 0, "%s: parse error", argv[0]);
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	if (cfg_do_ipv4)
+		run_test_v4();
+	if (cfg_do_ipv6)
+		run_test_v6();
+
+	fprintf(stderr, "OK\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh
new file mode 100755
index 000000000000..7977b97e060c
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso regression tests
+
+echo "ipv4 cmsg"
+./in_netns.sh ./udpgso -4 -C
+
+echo "ipv4 setsockopt"
+./in_netns.sh ./udpgso -4 -C -s
+
+echo "ipv6 cmsg"
+./in_netns.sh ./udpgso -6 -C
+
+echo "ipv6 setsockopt"
+./in_netns.sh ./udpgso -6 -C -s