aboutsummaryrefslogtreecommitdiff
path: root/tools/testing/selftests/net
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/net')
-rw-r--r--tools/testing/selftests/net/.gitignore2
-rw-r--r--tools/testing/selftests/net/Makefile8
-rw-r--r--tools/testing/selftests/net/bind_bhash_test.c119
-rw-r--r--tools/testing/selftests/net/bpf/Makefile2
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh61
-rwxr-xr-xtools/testing/selftests/net/fib_nexthop_nongw.sh119
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile2
-rwxr-xr-xtools/testing/selftests/net/forwarding/lib.sh6
-rw-r--r--tools/testing/selftests/net/io_uring_zerocopy_tx.c605
-rwxr-xr-xtools/testing/selftests/net/io_uring_zerocopy_tx.sh131
-rw-r--r--tools/testing/selftests/net/mptcp/Makefile3
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh48
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c2
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_inq.c2
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_sockopt.c2
-rw-r--r--tools/testing/selftests/net/mptcp/pm_nl_ctl.c73
-rwxr-xr-xtools/testing/selftests/net/mptcp/userspace_pm.sh32
-rw-r--r--tools/testing/selftests/net/tun.c162
-rwxr-xr-xtools/testing/selftests/net/udpgro.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_bench.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_frglist.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_fwd.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgso_bench.sh2
-rwxr-xr-xtools/testing/selftests/net/veth.sh6
24 files changed, 1240 insertions, 155 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index b984f8c8d523..ffc35a22e914 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -36,5 +36,5 @@ test_unix_oob
gro
ioam6_parser
toeplitz
+tun
cmsg_sender
-bind_bhash_test
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 464df13831f2..d0460a969060 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -11,7 +11,7 @@ TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh
TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh
-TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh
+TEST_PROGS += fin_ack_lat.sh fib_nexthop_multiprefix.sh fib_nexthops.sh fib_nexthop_nongw.sh
TEST_PROGS += altnames.sh icmp.sh icmp_redirect.sh ip6_gre_headroom.sh
TEST_PROGS += route_localnet.sh
TEST_PROGS += reuseaddr_ports_exhausted.sh
@@ -54,21 +54,19 @@ TEST_GEN_FILES += ipsec
TEST_GEN_FILES += ioam6_parser
TEST_GEN_FILES += gro
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun
TEST_GEN_FILES += toeplitz
TEST_GEN_FILES += cmsg_sender
TEST_GEN_FILES += stress_reuseport_listen
TEST_PROGS += test_vxlan_vnifiltering.sh
-TEST_GEN_FILES += bind_bhash_test
+TEST_GEN_FILES += io_uring_zerocopy_tx
TEST_FILES := settings
-KSFT_KHDR_INSTALL := 1
include ../lib.mk
include bpf/Makefile
$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
-$(OUTPUT)/bind_bhash_test: LDLIBS += -lpthread
$(OUTPUT)/tcp_inq: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/net/bind_bhash_test.c b/tools/testing/selftests/net/bind_bhash_test.c
deleted file mode 100644
index 252e73754e76..000000000000
--- a/tools/testing/selftests/net/bind_bhash_test.c
+++ /dev/null
@@ -1,119 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This times how long it takes to bind to a port when the port already
- * has multiple sockets in its bhash table.
- *
- * In the setup(), we populate the port's bhash table with
- * MAX_THREADS * MAX_CONNECTIONS number of entries.
- */
-
-#include <unistd.h>
-#include <stdio.h>
-#include <netdb.h>
-#include <pthread.h>
-
-#define MAX_THREADS 600
-#define MAX_CONNECTIONS 40
-
-static const char *bind_addr = "::1";
-static const char *port;
-
-static int fd_array[MAX_THREADS][MAX_CONNECTIONS];
-
-static int bind_socket(int opt, const char *addr)
-{
- struct addrinfo *res, hint = {};
- int sock_fd, reuse = 1, err;
-
- sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
- if (sock_fd < 0) {
- perror("socket fd err");
- return -1;
- }
-
- hint.ai_family = AF_INET6;
- hint.ai_socktype = SOCK_STREAM;
-
- err = getaddrinfo(addr, port, &hint, &res);
- if (err) {
- perror("getaddrinfo failed");
- return -1;
- }
-
- if (opt) {
- err = setsockopt(sock_fd, SOL_SOCKET, opt, &reuse, sizeof(reuse));
- if (err) {
- perror("setsockopt failed");
- return -1;
- }
- }
-
- err = bind(sock_fd, res->ai_addr, res->ai_addrlen);
- if (err) {
- perror("failed to bind to port");
- return -1;
- }
-
- return sock_fd;
-}
-
-static void *setup(void *arg)
-{
- int sock_fd, i;
- int *array = (int *)arg;
-
- for (i = 0; i < MAX_CONNECTIONS; i++) {
- sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, bind_addr);
- if (sock_fd < 0)
- return NULL;
- array[i] = sock_fd;
- }
-
- return NULL;
-}
-
-int main(int argc, const char *argv[])
-{
- int listener_fd, sock_fd, i, j;
- pthread_t tid[MAX_THREADS];
- clock_t begin, end;
-
- if (argc != 2) {
- printf("Usage: listener <port>\n");
- return -1;
- }
-
- port = argv[1];
-
- listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, bind_addr);
- if (listen(listener_fd, 100) < 0) {
- perror("listen failed");
- return -1;
- }
-
- /* Set up threads to populate the bhash table entry for the port */
- for (i = 0; i < MAX_THREADS; i++)
- pthread_create(&tid[i], NULL, setup, fd_array[i]);
-
- for (i = 0; i < MAX_THREADS; i++)
- pthread_join(tid[i], NULL);
-
- begin = clock();
-
- /* Bind to the same port on a different address */
- sock_fd = bind_socket(0, "2001:0db8:0:f101::1");
-
- end = clock();
-
- printf("time spent = %f\n", (double)(end - begin) / CLOCKS_PER_SEC);
-
- /* clean up */
- close(sock_fd);
- close(listener_fd);
- for (i = 0; i < MAX_THREADS; i++) {
- for (j = 0; i < MAX_THREADS; i++)
- close(fd_array[i][j]);
- }
-
- return 0;
-}
diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile
index 8a69c91fcca0..8ccaf8732eb2 100644
--- a/tools/testing/selftests/net/bpf/Makefile
+++ b/tools/testing/selftests/net/bpf/Makefile
@@ -2,7 +2,7 @@
CLANG ?= clang
CCINCLUDE += -I../../bpf
-CCINCLUDE += -I../../../lib
+CCINCLUDE += -I../../../../lib
CCINCLUDE += -I../../../../../usr/include/
TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 54701c8b0cd7..03b586760164 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -70,6 +70,10 @@ NSB_LO_IP6=2001:db8:2::2
NL_IP=172.17.1.1
NL_IP6=2001:db8:4::1
+# multicast and broadcast addresses
+MCAST_IP=224.0.0.1
+BCAST_IP=255.255.255.255
+
MD5_PW=abc123
MD5_WRONG_PW=abc1234
@@ -308,6 +312,9 @@ addr2str()
127.0.0.1) echo "loopback";;
::1) echo "IPv6 loopback";;
+ ${BCAST_IP}) echo "broadcast";;
+ ${MCAST_IP}) echo "multicast";;
+
${NSA_IP}) echo "ns-A IP";;
${NSA_IP6}) echo "ns-A IPv6";;
${NSA_LO_IP}) echo "ns-A loopback IP";;
@@ -1793,12 +1800,33 @@ ipv4_addr_bind_novrf()
done
#
- # raw socket with nonlocal bind
+ # tests for nonlocal bind
#
a=${NL_IP}
log_start
- run_cmd nettest -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b
- log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after device bind"
+ run_cmd nettest -s -R -f -l ${a} -b
+ log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address"
+
+ log_start
+ run_cmd nettest -s -f -l ${a} -b
+ log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address"
+
+ log_start
+ run_cmd nettest -s -D -P icmp -f -l ${a} -b
+ log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address"
+
+ #
+ # check that ICMP sockets cannot bind to broadcast and multicast addresses
+ #
+ a=${BCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address"
+
+ a=${MCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to multicast address"
#
# tcp sockets
@@ -1850,13 +1878,34 @@ ipv4_addr_bind_vrf()
log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind"
#
- # raw socket with nonlocal bind
+ # tests for nonlocal bind
#
a=${NL_IP}
log_start
- run_cmd nettest -s -R -P icmp -f -l ${a} -I ${VRF} -b
+ run_cmd nettest -s -R -f -l ${a} -I ${VRF} -b
log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind"
+ log_start
+ run_cmd nettest -s -f -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 0 "TCP socket bind to nonlocal address after VRF bind"
+
+ log_start
+ run_cmd nettest -s -D -P icmp -f -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 0 "ICMP socket bind to nonlocal address after VRF bind"
+
+ #
+ # check that ICMP sockets cannot bind to broadcast and multicast addresses
+ #
+ a=${BCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to broadcast address after VRF bind"
+
+ a=${MCAST_IP}
+ log_start
+ run_cmd nettest -s -D -P icmp -l ${a} -I ${VRF} -b
+ log_test_addr ${a} $? 1 "ICMP socket bind to multicast address after VRF bind"
+
#
# tcp sockets
#
@@ -1889,10 +1938,12 @@ ipv4_addr_bind()
log_subsection "No VRF"
setup
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
ipv4_addr_bind_novrf
log_subsection "With VRF"
setup "yes"
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
ipv4_addr_bind_vrf
}
diff --git a/tools/testing/selftests/net/fib_nexthop_nongw.sh b/tools/testing/selftests/net/fib_nexthop_nongw.sh
new file mode 100755
index 000000000000..b7b928b38ce4
--- /dev/null
+++ b/tools/testing/selftests/net/fib_nexthop_nongw.sh
@@ -0,0 +1,119 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# ns: h1 | ns: h2
+# 192.168.0.1/24 |
+# eth0 |
+# | 192.168.1.1/32
+# veth0 <---|---> veth1
+# Validate source address selection for route without gateway
+
+PAUSE_ON_FAIL=no
+VERBOSE=0
+ret=0
+
+################################################################################
+# helpers
+
+log_test()
+{
+ local rc=$1
+ local expected=$2
+ local msg="$3"
+
+ if [ ${rc} -eq ${expected} ]; then
+ printf "TEST: %-60s [ OK ]\n" "${msg}"
+ nsuccess=$((nsuccess+1))
+ else
+ ret=1
+ nfail=$((nfail+1))
+ printf "TEST: %-60s [FAIL]\n" "${msg}"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "hit enter to continue, 'q' to quit"
+ read a
+ [ "$a" = "q" ] && exit 1
+ fi
+ fi
+
+ [ "$VERBOSE" = "1" ] && echo
+}
+
+run_cmd()
+{
+ local cmd="$*"
+ local out
+ local rc
+
+ if [ "$VERBOSE" = "1" ]; then
+ echo "COMMAND: $cmd"
+ fi
+
+ out=$(eval $cmd 2>&1)
+ rc=$?
+ if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+ echo "$out"
+ fi
+
+ [ "$VERBOSE" = "1" ] && echo
+
+ return $rc
+}
+
+################################################################################
+# config
+setup()
+{
+ ip netns add h1
+ ip -n h1 link set lo up
+ ip netns add h2
+ ip -n h2 link set lo up
+
+ # Add a fake eth0 to support an ip address
+ ip -n h1 link add name eth0 type dummy
+ ip -n h1 link set eth0 up
+ ip -n h1 address add 192.168.0.1/24 dev eth0
+
+ # Configure veths (same @mac, arp off)
+ ip -n h1 link add name veth0 type veth peer name veth1 netns h2
+ ip -n h1 link set veth0 up
+
+ ip -n h2 link set veth1 up
+
+ # Configure @IP in the peer netns
+ ip -n h2 address add 192.168.1.1/32 dev veth1
+ ip -n h2 route add default dev veth1
+
+ # Add a nexthop without @gw and use it in a route
+ ip -n h1 nexthop add id 1 dev veth0
+ ip -n h1 route add 192.168.1.1 nhid 1
+}
+
+cleanup()
+{
+ ip netns del h1 2>/dev/null
+ ip netns del h2 2>/dev/null
+}
+
+trap cleanup EXIT
+
+################################################################################
+# main
+
+while getopts :pv o
+do
+ case $o in
+ p) PAUSE_ON_FAIL=yes;;
+ v) VERBOSE=1;;
+ esac
+done
+
+cleanup
+setup
+
+run_cmd ip -netns h1 route get 192.168.1.1
+log_test $? 0 "nexthop: get route with nexthop without gw"
+run_cmd ip netns exec h1 ping -c1 192.168.1.1
+log_test $? 0 "nexthop: ping through nexthop without gw"
+
+exit $ret
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 8f481218a492..57b84e0c879e 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -37,6 +37,7 @@ TEST_PROGS = bridge_igmp.sh \
ipip_hier_gre_key.sh \
ipip_hier_gre_keys.sh \
ipip_hier_gre.sh \
+ local_termination.sh \
loopback.sh \
mirror_gre_bound.sh \
mirror_gre_bridge_1d.sh \
@@ -52,6 +53,7 @@ TEST_PROGS = bridge_igmp.sh \
mirror_gre_vlan_bridge_1q.sh \
mirror_gre_vlan.sh \
mirror_vlan.sh \
+ no_forwarding.sh \
pedit_dsfield.sh \
pedit_ip.sh \
pedit_l4port.sh \
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 37ae49d47853..3ffb9d6c0950 100755
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1240,6 +1240,7 @@ learning_test()
# FDB entry was installed.
bridge link set dev $br_port1 flood off
+ ip link set $host1_if promisc on
tc qdisc add dev $host1_if ingress
tc filter add dev $host1_if ingress protocol ip pref 1 handle 101 \
flower dst_mac $mac action drop
@@ -1250,7 +1251,7 @@ learning_test()
tc -j -s filter show dev $host1_if ingress \
| jq -e ".[] | select(.options.handle == 101) \
| select(.options.actions[0].stats.packets == 1)" &> /dev/null
- check_fail $? "Packet reached second host when should not"
+ check_fail $? "Packet reached first host when should not"
$MZ $host1_if -c 1 -p 64 -a $mac -t ip -q
sleep 1
@@ -1289,6 +1290,7 @@ learning_test()
tc filter del dev $host1_if ingress protocol ip pref 1 handle 101 flower
tc qdisc del dev $host1_if ingress
+ ip link set $host1_if promisc off
bridge link set dev $br_port1 flood on
@@ -1306,6 +1308,7 @@ flood_test_do()
# Add an ACL on `host2_if` which will tell us whether the packet
# was flooded to it or not.
+ ip link set $host2_if promisc on
tc qdisc add dev $host2_if ingress
tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \
flower dst_mac $mac action drop
@@ -1323,6 +1326,7 @@ flood_test_do()
tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower
tc qdisc del dev $host2_if ingress
+ ip link set $host2_if promisc off
return $err
}
diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c
new file mode 100644
index 000000000000..9d64c560a2d6
--- /dev/null
+++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c
@@ -0,0 +1,605 @@
+/* SPDX-License-Identifier: MIT */
+/* based on linux-kernel/tools/testing/selftests/net/msg_zerocopy.c */
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/io_uring.h>
+#include <linux/ipv6.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+
+#define NOTIF_TAG 0xfffffffULL
+#define NONZC_TAG 0
+#define ZC_TAG 1
+
+enum {
+ MODE_NONZC = 0,
+ MODE_ZC = 1,
+ MODE_ZC_FIXED = 2,
+ MODE_MIXED = 3,
+};
+
+static bool cfg_flush = false;
+static bool cfg_cork = false;
+static int cfg_mode = MODE_ZC_FIXED;
+static int cfg_nr_reqs = 8;
+static int cfg_family = PF_UNSPEC;
+static int cfg_payload_len;
+static int cfg_port = 8000;
+static int cfg_runtime_ms = 4200;
+
+static socklen_t cfg_alen;
+static struct sockaddr_storage cfg_dst_addr;
+
+static char payload[IP_MAXPACKET] __attribute__((aligned(4096)));
+
+struct io_sq_ring {
+ unsigned *head;
+ unsigned *tail;
+ unsigned *ring_mask;
+ unsigned *ring_entries;
+ unsigned *flags;
+ unsigned *array;
+};
+
+struct io_cq_ring {
+ unsigned *head;
+ unsigned *tail;
+ unsigned *ring_mask;
+ unsigned *ring_entries;
+ struct io_uring_cqe *cqes;
+};
+
+struct io_uring_sq {
+ unsigned *khead;
+ unsigned *ktail;
+ unsigned *kring_mask;
+ unsigned *kring_entries;
+ unsigned *kflags;
+ unsigned *kdropped;
+ unsigned *array;
+ struct io_uring_sqe *sqes;
+
+ unsigned sqe_head;
+ unsigned sqe_tail;
+
+ size_t ring_sz;
+};
+
+struct io_uring_cq {
+ unsigned *khead;
+ unsigned *ktail;
+ unsigned *kring_mask;
+ unsigned *kring_entries;
+ unsigned *koverflow;
+ struct io_uring_cqe *cqes;
+
+ size_t ring_sz;
+};
+
+struct io_uring {
+ struct io_uring_sq sq;
+ struct io_uring_cq cq;
+ int ring_fd;
+};
+
+#ifdef __alpha__
+# ifndef __NR_io_uring_setup
+# define __NR_io_uring_setup 535
+# endif
+# ifndef __NR_io_uring_enter
+# define __NR_io_uring_enter 536
+# endif
+# ifndef __NR_io_uring_register
+# define __NR_io_uring_register 537
+# endif
+#else /* !__alpha__ */
+# ifndef __NR_io_uring_setup
+# define __NR_io_uring_setup 425
+# endif
+# ifndef __NR_io_uring_enter
+# define __NR_io_uring_enter 426
+# endif
+# ifndef __NR_io_uring_register
+# define __NR_io_uring_register 427
+# endif
+#endif
+
+#if defined(__x86_64) || defined(__i386__)
+#define read_barrier() __asm__ __volatile__("":::"memory")
+#define write_barrier() __asm__ __volatile__("":::"memory")
+#else
+
+#define read_barrier() __sync_synchronize()
+#define write_barrier() __sync_synchronize()
+#endif
+
+static int io_uring_setup(unsigned int entries, struct io_uring_params *p)
+{
+ return syscall(__NR_io_uring_setup, entries, p);
+}
+
+static int io_uring_enter(int fd, unsigned int to_submit,
+ unsigned int min_complete,
+ unsigned int flags, sigset_t *sig)
+{
+ return syscall(__NR_io_uring_enter, fd, to_submit, min_complete,
+ flags, sig, _NSIG / 8);
+}
+
+static int io_uring_register_buffers(struct io_uring *ring,
+ const struct iovec *iovecs,
+ unsigned nr_iovecs)
+{
+ int ret;
+
+ ret = syscall(__NR_io_uring_register, ring->ring_fd,
+ IORING_REGISTER_BUFFERS, iovecs, nr_iovecs);
+ return (ret < 0) ? -errno : ret;
+}
+
+static int io_uring_register_notifications(struct io_uring *ring,
+ unsigned nr,
+ struct io_uring_notification_slot *slots)
+{
+ int ret;
+ struct io_uring_notification_register r = {
+ .nr_slots = nr,
+ .data = (unsigned long)slots,
+ };
+
+ ret = syscall(__NR_io_uring_register, ring->ring_fd,
+ IORING_REGISTER_NOTIFIERS, &r, sizeof(r));
+ return (ret < 0) ? -errno : ret;
+}
+
+static int io_uring_mmap(int fd, struct io_uring_params *p,
+ struct io_uring_sq *sq, struct io_uring_cq *cq)
+{
+ size_t size;
+ void *ptr;
+ int ret;
+
+ sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned);
+ ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING);
+ if (ptr == MAP_FAILED)
+ return -errno;
+ sq->khead = ptr + p->sq_off.head;
+ sq->ktail = ptr + p->sq_off.tail;
+ sq->kring_mask = ptr + p->sq_off.ring_mask;
+ sq->kring_entries = ptr + p->sq_off.ring_entries;
+ sq->kflags = ptr + p->sq_off.flags;
+ sq->kdropped = ptr + p->sq_off.dropped;
+ sq->array = ptr + p->sq_off.array;
+
+ size = p->sq_entries * sizeof(struct io_uring_sqe);
+ sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES);
+ if (sq->sqes == MAP_FAILED) {
+ ret = -errno;
+err:
+ munmap(sq->khead, sq->ring_sz);
+ return ret;
+ }
+
+ cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe);
+ ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING);
+ if (ptr == MAP_FAILED) {
+ ret = -errno;
+ munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe));
+ goto err;
+ }
+ cq->khead = ptr + p->cq_off.head;
+ cq->ktail = ptr + p->cq_off.tail;
+ cq->kring_mask = ptr + p->cq_off.ring_mask;
+ cq->kring_entries = ptr + p->cq_off.ring_entries;
+ cq->koverflow = ptr + p->cq_off.overflow;
+ cq->cqes = ptr + p->cq_off.cqes;
+ return 0;
+}
+
+static int io_uring_queue_init(unsigned entries, struct io_uring *ring,
+ unsigned flags)
+{
+ struct io_uring_params p;
+ int fd, ret;
+
+ memset(ring, 0, sizeof(*ring));
+ memset(&p, 0, sizeof(p));
+ p.flags = flags;
+
+ fd = io_uring_setup(entries, &p);
+ if (fd < 0)
+ return fd;
+ ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq);
+ if (!ret)
+ ring->ring_fd = fd;
+ else
+ close(fd);
+ return ret;
+}
+
+static int io_uring_submit(struct io_uring *ring)
+{
+ struct io_uring_sq *sq = &ring->sq;
+ const unsigned mask = *sq->kring_mask;
+ unsigned ktail, submitted, to_submit;
+ int ret;
+
+ read_barrier();
+ if (*sq->khead != *sq->ktail) {
+ submitted = *sq->kring_entries;
+ goto submit;
+ }
+ if (sq->sqe_head == sq->sqe_tail)
+ return 0;
+
+ ktail = *sq->ktail;
+ to_submit = sq->sqe_tail - sq->sqe_head;
+ for (submitted = 0; submitted < to_submit; submitted++) {
+ read_barrier();
+ sq->array[ktail++ & mask] = sq->sqe_head++ & mask;
+ }
+ if (!submitted)
+ return 0;
+
+ if (*sq->ktail != ktail) {
+ write_barrier();
+ *sq->ktail = ktail;
+ write_barrier();
+ }
+submit:
+ ret = io_uring_enter(ring->ring_fd, submitted, 0,
+ IORING_ENTER_GETEVENTS, NULL);
+ return ret < 0 ? -errno : ret;
+}
+
+static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
+ const void *buf, size_t len, int flags)
+{
+ memset(sqe, 0, sizeof(*sqe));
+ sqe->opcode = (__u8) IORING_OP_SEND;
+ sqe->fd = sockfd;
+ sqe->addr = (unsigned long) buf;
+ sqe->len = len;
+ sqe->msg_flags = (__u32) flags;
+}
+
+static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd,
+ const void *buf, size_t len, int flags,
+ unsigned slot_idx, unsigned zc_flags)
+{
+ io_uring_prep_send(sqe, sockfd, buf, len, flags);
+ sqe->opcode = (__u8) IORING_OP_SENDZC_NOTIF;
+ sqe->notification_idx = slot_idx;
+ sqe->ioprio = zc_flags;
+}
+
+static struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring)
+{
+ struct io_uring_sq *sq = &ring->sq;
+
+ if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries)
+ return NULL;
+ return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask];
+}
+
+static int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr)
+{
+ struct io_uring_cq *cq = &ring->cq;
+ const unsigned mask = *cq->kring_mask;
+ unsigned head = *cq->khead;
+ int ret;
+
+ *cqe_ptr = NULL;
+ do {
+ read_barrier();
+ if (head != *cq->ktail) {
+ *cqe_ptr = &cq->cqes[head & mask];
+ break;
+ }
+ ret = io_uring_enter(ring->ring_fd, 0, 1,
+ IORING_ENTER_GETEVENTS, NULL);
+ if (ret < 0)
+ return -errno;
+ } while (1);
+
+ return 0;
+}
+
+static inline void io_uring_cqe_seen(struct io_uring *ring)
+{
+ *(&ring->cq)->khead += 1;
+ write_barrier();
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void do_setsockopt(int fd, int level, int optname, int val)
+{
+ if (setsockopt(fd, level, optname, &val, sizeof(val)))
+ error(1, errno, "setsockopt %d.%d: %d", level, optname, val);
+}
+
+static int do_setup_tx(int domain, int type, int protocol)
+{
+ int fd;
+
+ fd = socket(domain, type, protocol);
+ if (fd == -1)
+ error(1, errno, "socket t");
+
+ do_setsockopt(fd, SOL_SOCKET, SO_SNDBUF, 1 << 21);
+
+ if (connect(fd, (void *) &cfg_dst_addr, cfg_alen))
+ error(1, errno, "connect");
+ return fd;
+}
+
+static void do_tx(int domain, int type, int protocol)
+{
+ struct io_uring_notification_slot b[1] = {{.tag = NOTIF_TAG}};
+ struct io_uring_sqe *sqe;
+ struct io_uring_cqe *cqe;
+ unsigned long packets = 0, bytes = 0;
+ struct io_uring ring;
+ struct iovec iov;
+ uint64_t tstop;
+ int i, fd, ret;
+ int compl_cqes = 0;
+
+ fd = do_setup_tx(domain, type, protocol);
+
+ ret = io_uring_queue_init(512, &ring, 0);
+ if (ret)
+ error(1, ret, "io_uring: queue init");
+
+ ret = io_uring_register_notifications(&ring, 1, b);
+ if (ret)
+ error(1, ret, "io_uring: tx ctx registration");
+
+ iov.iov_base = payload;
+ iov.iov_len = cfg_payload_len;
+
+ ret = io_uring_register_buffers(&ring, &iov, 1);
+ if (ret)
+ error(1, ret, "io_uring: buffer registration");
+
+ tstop = gettimeofday_ms() + cfg_runtime_ms;
+ do {
+ if (cfg_cork)
+ do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 1);
+
+ for (i = 0; i < cfg_nr_reqs; i++) {
+ unsigned zc_flags = 0;
+ unsigned buf_idx = 0;
+ unsigned slot_idx = 0;
+ unsigned mode = cfg_mode;
+ unsigned msg_flags = 0;
+
+ if (cfg_mode == MODE_MIXED)
+ mode = rand() % 3;
+
+ sqe = io_uring_get_sqe(&ring);
+
+ if (mode == MODE_NONZC) {
+ io_uring_prep_send(sqe, fd, payload,
+ cfg_payload_len, msg_flags);
+ sqe->user_data = NONZC_TAG;
+ } else {
+ if (cfg_flush) {
+ zc_flags |= IORING_RECVSEND_NOTIF_FLUSH;
+ compl_cqes++;
+ }
+ io_uring_prep_sendzc(sqe, fd, payload,
+ cfg_payload_len,
+ msg_flags, slot_idx, zc_flags);
+ if (mode == MODE_ZC_FIXED) {
+ sqe->ioprio |= IORING_RECVSEND_FIXED_BUF;
+ sqe->buf_index = buf_idx;
+ }
+ sqe->user_data = ZC_TAG;
+ }
+ }
+
+ ret = io_uring_submit(&ring);
+ if (ret != cfg_nr_reqs)
+ error(1, ret, "submit");
+
+ for (i = 0; i < cfg_nr_reqs; i++) {
+ ret = io_uring_wait_cqe(&ring, &cqe);
+ if (ret)
+ error(1, ret, "wait cqe");
+
+ if (cqe->user_data == NOTIF_TAG) {
+ compl_cqes--;
+ i--;
+ } else if (cqe->user_data != NONZC_TAG &&
+ cqe->user_data != ZC_TAG) {
+ error(1, cqe->res, "invalid user_data");
+ } else if (cqe->res <= 0 && cqe->res != -EAGAIN) {
+ error(1, cqe->res, "send failed");
+ } else {
+ if (cqe->res > 0) {
+ packets++;
+ bytes += cqe->res;
+ }
+ /* failed requests don't flush */
+ if (cfg_flush &&
+ cqe->res <= 0 &&
+ cqe->user_data == ZC_TAG)
+ compl_cqes--;
+ }
+ io_uring_cqe_seen(&ring);
+ }
+ if (cfg_cork)
+ do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0);
+ } while (gettimeofday_ms() < tstop);
+
+ if (close(fd))
+ error(1, errno, "close");
+
+ fprintf(stderr, "tx=%lu (MB=%lu), tx/s=%lu (MB/s=%lu)\n",
+ packets, bytes >> 20,
+ packets / (cfg_runtime_ms / 1000),
+ (bytes >> 20) / (cfg_runtime_ms / 1000));
+
+ while (compl_cqes) {
+ ret = io_uring_wait_cqe(&ring, &cqe);
+ if (ret)
+ error(1, ret, "wait cqe");
+ io_uring_cqe_seen(&ring);
+ compl_cqes--;
+ }
+}
+
+static void do_test(int domain, int type, int protocol)
+{
+ int i;
+
+ for (i = 0; i < IP_MAXPACKET; i++)
+ payload[i] = 'a' + (i % 26);
+ do_tx(domain, type, protocol);
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-f] [-n<N>] [-z0] [-s<payload size>] "
+ "(-4|-6) [-t<time s>] -D<dst_ip> udp", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ const int max_payload_len = sizeof(payload) -
+ sizeof(struct ipv6hdr) -
+ sizeof(struct tcphdr) -
+ 40 /* max tcp options */;
+ struct sockaddr_in6 *addr6 = (void *) &cfg_dst_addr;
+ struct sockaddr_in *addr4 = (void *) &cfg_dst_addr;
+ char *daddr = NULL;
+ int c;
+
+ if (argc <= 1)
+ usage(argv[0]);
+ cfg_payload_len = max_payload_len;
+
+ while ((c = getopt(argc, argv, "46D:p:s:t:n:fc:m:")) != -1) {
+ switch (c) {
+ case '4':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET6;
+ cfg_alen = sizeof(struct sockaddr_in6);
+ break;
+ case 'D':
+ daddr = optarg;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 's':
+ cfg_payload_len = strtoul(optarg, NULL, 0);
+ break;
+ case 't':
+ cfg_runtime_ms = 200 + strtoul(optarg, NULL, 10) * 1000;
+ break;
+ case 'n':
+ cfg_nr_reqs = strtoul(optarg, NULL, 0);
+ break;
+ case 'f':
+ cfg_flush = 1;
+ break;
+ case 'c':
+ cfg_cork = strtol(optarg, NULL, 0);
+ break;
+ case 'm':
+ cfg_mode = strtol(optarg, NULL, 0);
+ break;
+ }
+ }
+
+ switch (cfg_family) {
+ case PF_INET:
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (daddr &&
+ inet_pton(AF_INET, daddr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", daddr);
+ break;
+ case PF_INET6:
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (daddr &&
+ inet_pton(AF_INET6, daddr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", daddr);
+ break;
+ default:
+ error(1, 0, "illegal domain");
+ }
+
+ if (cfg_payload_len > max_payload_len)
+ error(1, 0, "-s: payload exceeds max (%d)", max_payload_len);
+ if (cfg_mode == MODE_NONZC && cfg_flush)
+ error(1, 0, "-f: only zerocopy modes support notifications");
+ if (optind != argc - 1)
+ usage(argv[0]);
+}
+
+int main(int argc, char **argv)
+{
+ const char *cfg_test = argv[argc - 1];
+
+ parse_opts(argc, argv);
+
+ if (!strcmp(cfg_test, "tcp"))
+ do_test(cfg_family, SOCK_STREAM, 0);
+ else if (!strcmp(cfg_test, "udp"))
+ do_test(cfg_family, SOCK_DGRAM, 0);
+ else
+ error(1, 0, "unknown cfg_test %s", cfg_test);
+ return 0;
+}
diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
new file mode 100755
index 000000000000..6a65e4437640
--- /dev/null
+++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
@@ -0,0 +1,131 @@
+#!/bin/bash
+#
+# Send data between two processes across namespaces
+# Run twice: once without and once with zerocopy
+
+set -e
+
+readonly DEV="veth0"
+readonly DEV_MTU=65535
+readonly BIN_TX="./io_uring_zerocopy_tx"
+readonly BIN_RX="./msg_zerocopy"
+
+readonly RAND="$(mktemp -u XXXXXX)"
+readonly NSPREFIX="ns-${RAND}"
+readonly NS1="${NSPREFIX}1"
+readonly NS2="${NSPREFIX}2"
+
+readonly SADDR4='192.168.1.1'
+readonly DADDR4='192.168.1.2'
+readonly SADDR6='fd::1'
+readonly DADDR6='fd::2'
+
+readonly path_sysctl_mem="net.core.optmem_max"
+
+# No arguments: automated test
+if [[ "$#" -eq "0" ]]; then
+ IPs=( "4" "6" )
+ protocols=( "tcp" "udp" )
+
+ for IP in "${IPs[@]}"; do
+ for proto in "${protocols[@]}"; do
+ for mode in $(seq 1 3); do
+ $0 "$IP" "$proto" -m "$mode" -t 1 -n 32
+ $0 "$IP" "$proto" -m "$mode" -t 1 -n 32 -f
+ $0 "$IP" "$proto" -m "$mode" -t 1 -n 32 -c -f
+ done
+ done
+ done
+
+ echo "OK. All tests passed"
+ exit 0
+fi
+
+# Argument parsing
+if [[ "$#" -lt "2" ]]; then
+ echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>"
+ exit 1
+fi
+
+readonly IP="$1"
+shift
+readonly TXMODE="$1"
+shift
+readonly EXTRA_ARGS="$@"
+
+# Argument parsing: configure addresses
+if [[ "${IP}" == "4" ]]; then
+ readonly SADDR="${SADDR4}"
+ readonly DADDR="${DADDR4}"
+elif [[ "${IP}" == "6" ]]; then
+ readonly SADDR="${SADDR6}"
+ readonly DADDR="${DADDR6}"
+else
+ echo "Invalid IP version ${IP}"
+ exit 1
+fi
+
+# Argument parsing: select receive mode
+#
+# This differs from send mode for
+# - packet: use raw recv, because packet receives skb clones
+# - raw_hdrinc: use raw recv, because hdrincl is a tx-only option
+case "${TXMODE}" in
+'packet' | 'packet_dgram' | 'raw_hdrincl')
+ RXMODE='raw'
+ ;;
+*)
+ RXMODE="${TXMODE}"
+ ;;
+esac
+
+# Start of state changes: install cleanup handler
+save_sysctl_mem="$(sysctl -n ${path_sysctl_mem})"
+
+cleanup() {
+ ip netns del "${NS2}"
+ ip netns del "${NS1}"
+ sysctl -w -q "${path_sysctl_mem}=${save_sysctl_mem}"
+}
+
+trap cleanup EXIT
+
+# Configure system settings
+sysctl -w -q "${path_sysctl_mem}=1000000"
+
+# Create virtual ethernet pair between network namespaces
+ip netns add "${NS1}"
+ip netns add "${NS2}"
+
+ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \
+ peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}"
+
+# Bring the devices up
+ip -netns "${NS1}" link set "${DEV}" up
+ip -netns "${NS2}" link set "${DEV}" up
+
+# Set fixed MAC addresses on the devices
+ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02
+ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06
+
+# Add fixed IP addresses to the devices
+ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}"
+ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
+ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad
+ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad
+
+# Optionally disable sg or csum offload to test edge cases
+# ip netns exec "${NS1}" ethtool -K "${DEV}" sg off
+
+do_test() {
+ local readonly ARGS="$1"
+
+ echo "ipv${IP} ${TXMODE} ${ARGS}"
+ ip netns exec "${NS2}" "${BIN_RX}" "-${IP}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" -r "${RXMODE}" &
+ sleep 0.2
+ ip netns exec "${NS1}" "${BIN_TX}" "-${IP}" -t 1 -D "${DADDR}" ${ARGS} "${TXMODE}"
+ wait
+}
+
+do_test "${EXTRA_ARGS}"
+echo ok
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index f905d5358e68..43a723626126 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -1,12 +1,11 @@
# SPDX-License-Identifier: GPL-2.0
top_srcdir = ../../../../..
-KSFT_KHDR_INSTALL := 1
CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
- simult_flows.sh mptcp_sockopt.sh
+ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh
TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 9dd43d7d957b..515859a5168b 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -61,6 +61,39 @@ chk_msk_nr()
__chk_nr "grep -c token:" $*
}
+wait_msk_nr()
+{
+ local condition="grep -c token:"
+ local expected=$1
+ local timeout=20
+ local msg nr
+ local max=0
+ local i=0
+
+ shift 1
+ msg=$*
+
+ while [ $i -lt $timeout ]; do
+ nr=$(ss -inmHMN $ns | $condition)
+ [ $nr == $expected ] && break;
+ [ $nr -gt $max ] && max=$nr
+ i=$((i + 1))
+ sleep 1
+ done
+
+ printf "%-50s" "$msg"
+ if [ $i -ge $timeout ]; then
+ echo "[ fail ] timeout while expecting $expected max $max last $nr"
+ ret=$test_cnt
+ elif [ $nr != $expected ]; then
+ echo "[ fail ] expected $expected found $nr"
+ ret=$test_cnt
+ else
+ echo "[ ok ]"
+ fi
+ test_cnt=$((test_cnt+1))
+}
+
chk_msk_fallback_nr()
{
__chk_nr "grep -c fallback" $*
@@ -146,7 +179,7 @@ ip -n $ns link set dev lo up
echo "a" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -l -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \
0.0.0.0 >/dev/null &
wait_local_port_listen $ns 10000
chk_msk_nr 0 "no msk on netns creation"
@@ -155,7 +188,7 @@ chk_msk_listen 10000
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \
127.0.0.1 >/dev/null &
wait_connected $ns 10000
chk_msk_nr 2 "after MPC handshake "
@@ -167,13 +200,13 @@ flush_pids
echo "a" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \
0.0.0.0 >/dev/null &
wait_local_port_listen $ns 10001
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \
127.0.0.1 >/dev/null &
wait_connected $ns 10001
chk_msk_fallback_nr 1 "check fallback"
@@ -184,7 +217,7 @@ for I in `seq 1 $NR_CLIENTS`; do
echo "a" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p $((I+10001)) -l -w 10 \
+ ./mptcp_connect -p $((I+10001)) -l -w 20 \
-t ${timeout_poll} 0.0.0.0 >/dev/null &
done
wait_local_port_listen $ns $((NR_CLIENTS + 10001))
@@ -193,12 +226,11 @@ for I in `seq 1 $NR_CLIENTS`; do
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p $((I+10001)) -w 10 \
+ ./mptcp_connect -p $((I+10001)) -w 20 \
-t ${timeout_poll} 127.0.0.1 >/dev/null &
done
-sleep 1.5
-chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
+wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
flush_pids
exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 8628aa61b763..e2ea6c126c99 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -265,7 +265,7 @@ static void sock_test_tcpulp(int sock, int proto, unsigned int line)
static int sock_listen_mptcp(const char * const listenaddr,
const char * const port)
{
- int sock;
+ int sock = -1;
struct addrinfo hints = {
.ai_protocol = IPPROTO_TCP,
.ai_socktype = SOCK_STREAM,
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 29f75e2a1116..8672d898f8cd 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -88,7 +88,7 @@ static void xgetaddrinfo(const char *node, const char *service,
static int sock_listen_mptcp(const char * const listenaddr,
const char * const port)
{
- int sock;
+ int sock = -1;
struct addrinfo hints = {
.ai_protocol = IPPROTO_TCP,
.ai_socktype = SOCK_STREAM,
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index ac9a4d9c1764..ae61f39556ca 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -136,7 +136,7 @@ static void xgetaddrinfo(const char *node, const char *service,
static int sock_listen_mptcp(const char * const listenaddr,
const char * const port)
{
- int sock;
+ int sock = -1;
struct addrinfo hints = {
.ai_protocol = IPPROTO_TCP,
.ai_socktype = SOCK_STREAM,
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 6a2f4b981e1d..cb79f0719e3b 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -39,7 +39,7 @@ static void syntax(char *argv[])
fprintf(stderr, "\tdsf lip <local-ip> lport <local-port> rip <remote-ip> rport <remote-port> token <token>\n");
fprintf(stderr, "\tdel <id> [<ip>]\n");
fprintf(stderr, "\tget <id>\n");
- fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>]\n");
+ fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>] [token <token>] [rip <ip>] [rport <port>]\n");
fprintf(stderr, "\tflush\n");
fprintf(stderr, "\tdump\n");
fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n");
@@ -1279,7 +1279,10 @@ int set_flags(int fd, int pm_family, int argc, char *argv[])
struct rtattr *rta, *nest;
struct nlmsghdr *nh;
u_int32_t flags = 0;
+ u_int32_t token = 0;
+ u_int16_t rport = 0;
u_int16_t family;
+ void *rip = NULL;
int nest_start;
int use_id = 0;
u_int8_t id;
@@ -1339,7 +1342,13 @@ int set_flags(int fd, int pm_family, int argc, char *argv[])
error(1, 0, " missing flags keyword");
for (; arg < argc; arg++) {
- if (!strcmp(argv[arg], "flags")) {
+ if (!strcmp(argv[arg], "token")) {
+ if (++arg >= argc)
+ error(1, 0, " missing token value");
+
+ /* token */
+ token = atoi(argv[arg]);
+ } else if (!strcmp(argv[arg], "flags")) {
char *tok, *str;
/* flags */
@@ -1378,12 +1387,72 @@ int set_flags(int fd, int pm_family, int argc, char *argv[])
rta->rta_len = RTA_LENGTH(2);
memcpy(RTA_DATA(rta), &port, 2);
off += NLMSG_ALIGN(rta->rta_len);
+ } else if (!strcmp(argv[arg], "rport")) {
+ if (++arg >= argc)
+ error(1, 0, " missing remote port");
+
+ rport = atoi(argv[arg]);
+ } else if (!strcmp(argv[arg], "rip")) {
+ if (++arg >= argc)
+ error(1, 0, " missing remote ip");
+
+ rip = argv[arg];
} else {
error(1, 0, "unknown keyword %s", argv[arg]);
}
}
nest->rta_len = off - nest_start;
+ /* token */
+ if (token) {
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ATTR_TOKEN;
+ rta->rta_len = RTA_LENGTH(4);
+ memcpy(RTA_DATA(rta), &token, 4);
+ off += NLMSG_ALIGN(rta->rta_len);
+ }
+
+ /* remote addr/port */
+ if (rip) {
+ nest_start = off;
+ nest = (void *)(data + off);
+ nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR_REMOTE;
+ nest->rta_len = RTA_LENGTH(0);
+ off += NLMSG_ALIGN(nest->rta_len);
+
+ /* addr data */
+ rta = (void *)(data + off);
+ if (inet_pton(AF_INET, rip, RTA_DATA(rta))) {
+ family = AF_INET;
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4;
+ rta->rta_len = RTA_LENGTH(4);
+ } else if (inet_pton(AF_INET6, rip, RTA_DATA(rta))) {
+ family = AF_INET6;
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6;
+ rta->rta_len = RTA_LENGTH(16);
+ } else {
+ error(1, errno, "can't parse ip %s", (char *)rip);
+ }
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* family */
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY;
+ rta->rta_len = RTA_LENGTH(2);
+ memcpy(RTA_DATA(rta), &family, 2);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ if (rport) {
+ rta = (void *)(data + off);
+ rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT;
+ rta->rta_len = RTA_LENGTH(2);
+ memcpy(RTA_DATA(rta), &rport, 2);
+ off += NLMSG_ALIGN(rta->rta_len);
+ }
+
+ nest->rta_len = off - nest_start;
+ }
+
do_nl_req(fd, nh, off, 0);
return 0;
}
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 78d0bb640b11..abe3d4ebe554 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -770,10 +770,42 @@ test_subflows()
rm -f "$evts"
}
+test_prio()
+{
+ local count
+
+ # Send MP_PRIO signal from client to server machine
+ ip netns exec "$ns2" ./pm_nl_ctl set 10.0.1.2 port "$client4_port" flags backup token "$client4_token" rip 10.0.1.1 rport "$server4_port"
+ sleep 0.5
+
+ # Check TX
+ stdbuf -o0 -e0 printf "MP_PRIO TX \t"
+ count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}')
+ [ -z "$count" ] && count=0
+ if [ $count != 1 ]; then
+ stdbuf -o0 -e0 printf "[FAIL]\n"
+ exit 1
+ else
+ stdbuf -o0 -e0 printf "[OK]\n"
+ fi
+
+ # Check RX
+ stdbuf -o0 -e0 printf "MP_PRIO RX \t"
+ count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}')
+ [ -z "$count" ] && count=0
+ if [ $count != 1 ]; then
+ stdbuf -o0 -e0 printf "[FAIL]\n"
+ exit 1
+ else
+ stdbuf -o0 -e0 printf "[OK]\n"
+ fi
+}
+
make_connection
make_connection "v6"
test_announce
test_remove
test_subflows
+test_prio
exit 0
diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
new file mode 100644
index 000000000000..fa83918b62d1
--- /dev/null
+++ b/tools/testing/selftests/net/tun.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+
+#include "../kselftest_harness.h"
+
+static int tun_attach(int fd, char *dev)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, dev);
+ ifr.ifr_flags = IFF_ATTACH_QUEUE;
+
+ return ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+}
+
+static int tun_detach(int fd, char *dev)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, dev);
+ ifr.ifr_flags = IFF_DETACH_QUEUE;
+
+ return ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+}
+
+static int tun_alloc(char *dev)
+{
+ struct ifreq ifr;
+ int fd, err;
+
+ fd = open("/dev/net/tun", O_RDWR);
+ if (fd < 0) {
+ fprintf(stderr, "can't open tun: %s\n", strerror(errno));
+ return fd;
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, dev);
+ ifr.ifr_flags = IFF_TAP | IFF_NAPI | IFF_MULTI_QUEUE;
+
+ err = ioctl(fd, TUNSETIFF, (void *) &ifr);
+ if (err < 0) {
+ fprintf(stderr, "can't TUNSETIFF: %s\n", strerror(errno));
+ close(fd);
+ return err;
+ }
+ strcpy(dev, ifr.ifr_name);
+ return fd;
+}
+
+static int tun_delete(char *dev)
+{
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg ifm;
+ unsigned char data[64];
+ } req;
+ struct rtattr *rta;
+ int ret, rtnl;
+
+ rtnl = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+ if (rtnl < 0) {
+ fprintf(stderr, "can't open rtnl: %s\n", strerror(errno));
+ return 1;
+ }
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_ALIGN(NLMSG_LENGTH(sizeof(req.ifm)));
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_type = RTM_DELLINK;
+
+ req.ifm.ifi_family = AF_UNSPEC;
+
+ rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nh.nlmsg_len));
+ rta->rta_type = IFLA_IFNAME;
+ rta->rta_len = RTA_LENGTH(IFNAMSIZ);
+ req.nh.nlmsg_len += rta->rta_len;
+ memcpy(RTA_DATA(rta), dev, IFNAMSIZ);
+
+ ret = send(rtnl, &req, req.nh.nlmsg_len, 0);
+ if (ret < 0)
+ fprintf(stderr, "can't send: %s\n", strerror(errno));
+ ret = (unsigned int)ret != req.nh.nlmsg_len;
+
+ close(rtnl);
+ return ret;
+}
+
+FIXTURE(tun)
+{
+ char ifname[IFNAMSIZ];
+ int fd, fd2;
+};
+
+FIXTURE_SETUP(tun)
+{
+ memset(self->ifname, 0, sizeof(self->ifname));
+
+ self->fd = tun_alloc(self->ifname);
+ ASSERT_GE(self->fd, 0);
+
+ self->fd2 = tun_alloc(self->ifname);
+ ASSERT_GE(self->fd2, 0);
+}
+
+FIXTURE_TEARDOWN(tun)
+{
+ if (self->fd >= 0)
+ close(self->fd);
+ if (self->fd2 >= 0)
+ close(self->fd2);
+}
+
+TEST_F(tun, delete_detach_close) {
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), -1);
+ EXPECT_EQ(errno, 22);
+}
+
+TEST_F(tun, detach_delete_close) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_F(tun, detach_close_delete) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ close(self->fd);
+ self->fd = -1;
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_F(tun, reattach_delete_close) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_attach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_F(tun, reattach_close_delete) {
+ EXPECT_EQ(tun_detach(self->fd, self->ifname), 0);
+ EXPECT_EQ(tun_attach(self->fd, self->ifname), 0);
+ close(self->fd);
+ self->fd = -1;
+ EXPECT_EQ(tun_delete(self->ifname), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index f8a19f548ae9..ebbd0b282432 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -34,7 +34,7 @@ cfg_veth() {
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 "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp
}
run_one() {
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 820bc50f6b68..fad2d1a71cac 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -34,7 +34,7 @@ run_one() {
ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
ip -netns "${PEER_NS}" link set dev veth1 up
- ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp
ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index 807b74c8fd80..832c738cc3c2 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -36,7 +36,7 @@ run_one() {
ip netns exec "${PEER_NS}" ethtool -K veth1 rx-gro-list on
- ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp
tc -n "${PEER_NS}" qdisc add dev veth1 clsact
tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action
tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 6f05e06f6761..1bcd82e1f662 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -46,7 +46,7 @@ create_ns() {
ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
done
- ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+ ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null
}
create_vxlan_endpoint() {
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 80b5d352702e..dc932fd65363 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -120,7 +120,7 @@ run_all() {
run_udp "${ipv4_args}"
echo "ipv6"
- run_tcp "${ipv4_args}"
+ run_tcp "${ipv6_args}"
run_udp "${ipv6_args}"
}
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 19eac3e44c06..430895d1a2b6 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -289,14 +289,14 @@ if [ $CPUS -gt 1 ]; then
ip netns exec $NS_SRC ethtool -L veth$SRC rx 1 tx 2 2>/dev/null
printf "%-60s" "bad setting: XDP with RX nr less than TX"
ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \
- section xdp_dummy 2>/dev/null &&\
+ section xdp 2>/dev/null &&\
echo "fail - set operation successful ?!?" || echo " ok "
# the following tests will run with multiple channels active
ip netns exec $NS_SRC ethtool -L veth$SRC rx 2
ip netns exec $NS_DST ethtool -L veth$DST rx 2
ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o \
- section xdp_dummy 2>/dev/null
+ section xdp 2>/dev/null
printf "%-60s" "bad setting: reducing RX nr below peer TX with XDP set"
ip netns exec $NS_DST ethtool -L veth$DST rx 1 2>/dev/null &&\
echo "fail - set operation successful ?!?" || echo " ok "
@@ -311,7 +311,7 @@ if [ $CPUS -gt 2 ]; then
chk_channels "setting invalid channels nr" $DST 2 2
fi
-ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp 2>/dev/null
chk_gro_flag "with xdp attached - gro flag" $DST on
chk_gro_flag " - peer gro flag" $SRC off
chk_tso_flag " - tso flag" $SRC off