From e739718444f7bf2fa3d70d101761ad83056ca628 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 28 Jul 2023 17:07:05 -0700 Subject: net/sched: taprio: Limit TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME to INT_MAX. syzkaller found zero division error [0] in div_s64_rem() called from get_cycle_time_elapsed(), where sched->cycle_time is the divisor. We have tests in parse_taprio_schedule() so that cycle_time will never be 0, and actually cycle_time is not 0 in get_cycle_time_elapsed(). The problem is that the types of divisor are different; cycle_time is s64, but the argument of div_s64_rem() is s32. syzkaller fed this input and 0x100000000 is cast to s32 to be 0. @TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME={0xc, 0x8, 0x100000000} We use s64 for cycle_time to cast it to ktime_t, so let's keep it and set max for cycle_time. While at it, we prevent overflow in setup_txtime() and add another test in parse_taprio_schedule() to check if cycle_time overflows. Also, we add a new tdc test case for this issue. [0]: divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 1 PID: 103 Comm: kworker/1:3 Not tainted 6.5.0-rc1-00330-g60cc1f7d0605 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:div_s64_rem include/linux/math64.h:42 [inline] RIP: 0010:get_cycle_time_elapsed net/sched/sch_taprio.c:223 [inline] RIP: 0010:find_entry_to_transmit+0x252/0x7e0 net/sched/sch_taprio.c:344 Code: 3c 02 00 0f 85 5e 05 00 00 48 8b 4c 24 08 4d 8b bd 40 01 00 00 48 8b 7c 24 48 48 89 c8 4c 29 f8 48 63 f7 48 99 48 89 74 24 70 <48> f7 fe 48 29 d1 48 8d 04 0f 49 89 cc 48 89 44 24 20 49 8d 85 10 RSP: 0018:ffffc90000acf260 EFLAGS: 00010206 RAX: 177450e0347560cf RBX: 0000000000000000 RCX: 177450e0347560cf RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000100000000 RBP: 0000000000000056 R08: 0000000000000000 R09: ffffed10020a0934 R10: ffff8880105049a7 R11: ffff88806cf3a520 R12: ffff888010504800 R13: ffff88800c00d800 R14: ffff8880105049a0 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88806cf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f0edf84f0e8 CR3: 000000000d73c002 CR4: 0000000000770ee0 PKRU: 55555554 Call Trace: get_packet_txtime net/sched/sch_taprio.c:508 [inline] taprio_enqueue_one+0x900/0xff0 net/sched/sch_taprio.c:577 taprio_enqueue+0x378/0xae0 net/sched/sch_taprio.c:658 dev_qdisc_enqueue+0x46/0x170 net/core/dev.c:3732 __dev_xmit_skb net/core/dev.c:3821 [inline] __dev_queue_xmit+0x1b2f/0x3000 net/core/dev.c:4169 dev_queue_xmit include/linux/netdevice.h:3088 [inline] neigh_resolve_output net/core/neighbour.c:1552 [inline] neigh_resolve_output+0x4a7/0x780 net/core/neighbour.c:1532 neigh_output include/net/neighbour.h:544 [inline] ip6_finish_output2+0x924/0x17d0 net/ipv6/ip6_output.c:135 __ip6_finish_output+0x620/0xaa0 net/ipv6/ip6_output.c:196 ip6_finish_output net/ipv6/ip6_output.c:207 [inline] NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip6_output+0x206/0x410 net/ipv6/ip6_output.c:228 dst_output include/net/dst.h:458 [inline] NF_HOOK.constprop.0+0xea/0x260 include/linux/netfilter.h:303 ndisc_send_skb+0x872/0xe80 net/ipv6/ndisc.c:508 ndisc_send_ns+0xb5/0x130 net/ipv6/ndisc.c:666 addrconf_dad_work+0xc14/0x13f0 net/ipv6/addrconf.c:4175 process_one_work+0x92c/0x13a0 kernel/workqueue.c:2597 worker_thread+0x60f/0x1240 kernel/workqueue.c:2748 kthread+0x2fe/0x3f0 kernel/kthread.c:389 ret_from_fork+0x2c/0x50 arch/x86/entry/entry_64.S:308 Modules linked in: Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Co-developed-by: Eric Dumazet Co-developed-by: Pedro Tammela Acked-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/qdiscs/taprio.json | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index a44455372646..08d4861c2e78 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -131,5 +131,30 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] + }, + { + "id": "3e1e", + "name": "Add taprio Qdisc with an invalid cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle 1: taprio num_tc 3 map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@0 1@0 base-time 1000000000 sched-entry S 01 300000 flags 0x1 clockid CLOCK_TAI cycle-time 4294967296 || /bin/true", + "$IP link set dev $ETH up", + "$IP addr add 10.10.10.10/24 dev $ETH" + ], + "cmdUnderTest": "/bin/true", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] } ] -- cgit v1.2.3 From 3ff1617450eceb290ac17120fc172815e09a93cf Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 31 Jul 2023 11:15:53 -0700 Subject: selftest: net: Assert on a proper value in so_incoming_cpu.c. Dan Carpenter reported an error spotted by Smatch. ./tools/testing/selftests/net/so_incoming_cpu.c:163 create_clients() error: uninitialized symbol 'ret'. The returned value of sched_setaffinity() should be checked with ASSERT_EQ(), but the value was not saved in a proper variable, resulting in an error above. Let's save the returned value of with sched_setaffinity(). Fixes: 6df96146b202 ("selftest: Add test for SO_INCOMING_CPU.") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-kselftest/fe376760-33b6-4fc9-88e8-178e809af1ac@moroto.mountain/ Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230731181553.5392-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/so_incoming_cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c index 0e04f9fef986..a14818164102 100644 --- a/tools/testing/selftests/net/so_incoming_cpu.c +++ b/tools/testing/selftests/net/so_incoming_cpu.c @@ -159,7 +159,7 @@ void create_clients(struct __test_metadata *_metadata, /* Make sure SYN will be processed on the i-th CPU * and finally distributed to the i-th listener. */ - sched_setaffinity(0, sizeof(cpu_set), &cpu_set); + ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set); ASSERT_EQ(ret, 0); for (j = 0; j < CLIENT_PER_SERVER; j++) { -- cgit v1.2.3 From 8c82d2bf5944123d8e90d01bf27655497d9aa321 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 12 Jul 2023 12:35:14 -0700 Subject: selftests/riscv: fix potential build failure during the "emit_tests" step The riscv selftests (which were modeled after the arm64 selftests) are improperly declaring the "emit_tests" target to depend upon the "all" target. This approach, when combined with commit 9fc96c7c19df ("selftests: error out if kernel header files are not yet built"), has caused build failures [1] on arm64, and is likely to cause similar failures for riscv. To fix this, simply remove the unnecessary "all" dependency from the emit_tests target. The dependency is still effectively honored, because again, invocation is via "install", which also depends upon "all". An alternative approach would be to harden the emit_tests target so that it can depend upon "all", but that's a lot more complicated and hard to get right, and doesn't seem worth it, especially given that emit_tests should probably not be overridden at all. [1] https://lore.kernel.org/20230710-kselftest-fix-arm64-v1-1-48e872844f25@kernel.org Fixes: 9fc96c7c19df ("selftests: error out if kernel header files are not yet built") Signed-off-by: John Hubbard Tested-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230712193514.740033-1-jhubbard@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- tools/testing/selftests/riscv/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 9dd629cc86aa..f4b3d5c9af5b 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -43,7 +43,7 @@ run_tests: all done # Avoid any output on non riscv on emit_tests -emit_tests: all +emit_tests: @for DIR in $(RISCV_SUBTARGETS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ -- cgit v1.2.3 From 25696067202f047e22c1562f1f56b0e2eb547d1a Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Thu, 13 Jul 2023 13:58:29 +0200 Subject: selftests: riscv: Fix compilation error with vstate_exec_nolibc.c The following error happens: In file included from vstate_exec_nolibc.c:2: /usr/include/riscv64-linux-gnu/sys/prctl.h:42:12: error: conflicting types for ‘prctl’; h ave ‘int(int, ...)’ 42 | extern int prctl (int __option, ...) __THROW; | ^~~~~ In file included from ./../../../../include/nolibc/nolibc.h:99, from : ./../../../../include/nolibc/sys.h:892:5: note: previous definition of ‘prctl’ with type ‘int(int, long unsigned int, long unsigned int, long unsigned int, long unsigned int) ’ 892 | int prctl(int option, unsigned long arg2, unsigned long arg3, | ^~~~~ Fix this by not including , which is not needed here since prctl syscall is directly called using its number. Fixes: 7cf6198ce22d ("selftests: Test RISC-V Vector prctl interface") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230713115829.110421-1-alexghiti@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 5cbc392944a6..2c0d2b1126c1 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#include - #define THIS_PROGRAM "./vstate_exec_nolibc" int main(int argc, char **argv) -- cgit v1.2.3 From 3c50c8b240390907c9a33c86d25d850520db6dfa Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 3 Aug 2023 10:54:54 +0200 Subject: test/vsock: remove vsock_perf executable on `make clean` We forgot to add vsock_perf to the rm command in the `clean` target, so now we have a left over after `make clean` in tools/testing/vsock. Fixes: 8abbffd27ced ("test/vsock: vsock_perf utility") Cc: AVKrasnov@sberdevices.ru Signed-off-by: Stefano Garzarella Reviewed-by: Simon Horman Tested-by: Simon Horman # build-tested Link: https://lore.kernel.org/r/20230803085454.30897-1-sgarzare@redhat.com Signed-off-by: Jakub Kicinski --- tools/testing/vsock/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 43a254f0e14d..21a98ba565ab 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -8,5 +8,5 @@ vsock_perf: vsock_perf.o CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean clean: - ${RM} *.o *.d vsock_test vsock_diag_test + ${RM} *.o *.d vsock_test vsock_diag_test vsock_perf -include *.d -- cgit v1.2.3 From cac7ea57a06016e4914848b707477fb07ee4ae1c Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 27 Jul 2023 17:09:30 +0100 Subject: radix tree test suite: fix incorrect allocation size for pthreads Currently the pthread allocation for each array item is based on the size of a pthread_t pointer and should be the size of the pthread_t structure, so the allocation is under-allocating the correct size. Fix this by using the size of each element in the pthreads array. Static analysis cppcheck reported: tools/testing/radix-tree/regression1.c:180:2: warning: Size of pointer 'threads' used instead of size of its data. [pointerSize] Link: https://lkml.kernel.org/r/20230727160930.632674-1-colin.i.king@gmail.com Fixes: 1366c37ed84b ("radix tree test harness") Signed-off-by: Colin Ian King Cc: Konstantin Khlebnikov Cc: Matthew Wilcox (Oracle) Cc: Signed-off-by: Andrew Morton --- tools/testing/radix-tree/regression1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index a61c7bcbc72d..63f468bf8245 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -177,7 +177,7 @@ void regression1_test(void) nr_threads = 2; pthread_barrier_init(&worker_barrier, NULL, nr_threads); - threads = malloc(nr_threads * sizeof(pthread_t *)); + threads = malloc(nr_threads * sizeof(*threads)); for (i = 0; i < nr_threads; i++) { arg = i; -- cgit v1.2.3 From 65294de30cb8bc7659e445f7be2846af9ed35499 Mon Sep 17 00:00:00 2001 From: Ayush Jain Date: Fri, 28 Jul 2023 22:09:51 +0530 Subject: selftests: mm: ksm: fix incorrect evaluation of parameter A missing break in kms_tests leads to kselftest hang when the parameter -s is used. In current code flow because of missing break in -s, -t parses args spilled from -s and as -t accepts only valid values as 0,1 so any arg in -s >1 or <0, gets in ksm_test failure This went undetected since, before the addition of option -t, the next case -M would immediately break out of the switch statement but that is no longer the case Add the missing break statement. ----Before---- ./ksm_tests -H -s 100 Invalid merge type ----After---- ./ksm_tests -H -s 100 Number of normal pages: 0 Number of huge pages: 50 Total size: 100 MiB Total time: 0.401732682 s Average speed: 248.922 MiB/s Link: https://lkml.kernel.org/r/20230728163952.4634-1-ayush.jain3@amd.com Fixes: 07115fcc15b4 ("selftests/mm: add new selftests for KSM") Signed-off-by: Ayush Jain Reviewed-by: David Hildenbrand Cc: Stefan Roesch Cc: Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/ksm_tests.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 435acebdc325..380b691d3eb9 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -831,6 +831,7 @@ int main(int argc, char *argv[]) printf("Size must be greater than 0\n"); return KSFT_FAIL; } + break; case 't': { int tmp = atoi(optarg); -- cgit v1.2.3 From fac2650276eced3c94bcdbc21d0e5be637c1e582 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 1 Aug 2023 09:56:32 -0400 Subject: selftests: cgroup: fix test_kmem_basic false positives This test fails routinely in our prod testing environment, and I can reproduce it locally as well. The test allocates dcache inside a cgroup, then drops the memory limit and checks that usage drops correspondingly. The reason it fails is because dentries are freed with an RCU delay - a debugging sleep shows that usage drops as expected shortly after. Insert a 1s sleep after dropping the limit. This should be good enough, assuming that machines running those tests are otherwise not very busy. Link: https://lkml.kernel.org/r/20230801135632.1768830-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Paul E. McKenney Cc: Michal Hocko Cc: Roman Gushchin Signed-off-by: Andrew Morton --- tools/testing/selftests/cgroup/test_kmem.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 258ddc565deb..1b2cec9d18a4 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -70,6 +70,10 @@ static int test_kmem_basic(const char *root) goto cleanup; cg_write(cg, "memory.high", "1M"); + + /* wait for RCU freeing */ + sleep(1); + slab1 = cg_read_key_long(cg, "memory.stat", "slab "); if (slab1 <= 0) goto cleanup; -- cgit v1.2.3 From d5ad9aae13dcced333c1a7816ff0a4fbbb052466 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 4 Aug 2023 20:22:11 +0100 Subject: selftests/rseq: Fix build with undefined __weak Commit 3bcbc20942db ("selftests/rseq: Play nice with binaries statically linked against glibc 2.35+") which is now in Linus' tree introduced uses of __weak but did nothing to ensure that a definition is provided for it resulting in build failures for the rseq tests: rseq.c:41:1: error: unknown type name '__weak' __weak ptrdiff_t __rseq_offset; ^ rseq.c:41:17: error: expected ';' after top level declarator __weak ptrdiff_t __rseq_offset; ^ ; rseq.c:42:1: error: unknown type name '__weak' __weak unsigned int __rseq_size; ^ rseq.c:43:1: error: unknown type name '__weak' __weak unsigned int __rseq_flags; Fix this by using the definition from tools/include compiler.h. Fixes: 3bcbc20942db ("selftests/rseq: Play nice with binaries statically linked against glibc 2.35+") Signed-off-by: Mark Brown Message-Id: <20230804-kselftest-rseq-build-v1-1-015830b66aa9@kernel.org> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/rseq/Makefile | 4 +++- tools/testing/selftests/rseq/rseq.c | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index b357ba24af06..7a957c7d459a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,8 +4,10 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif +top_srcdir = ../../../.. + CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ - $(CLANG_FLAGS) + $(CLANG_FLAGS) -I$(top_srcdir)/tools/include LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index a723da253244..96e812bdf8a4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -31,6 +31,8 @@ #include #include +#include + #include "../kselftest.h" #include "rseq.h" -- cgit v1.2.3 From 136a1b434bbb90c5e50831646ad0680c744c79bb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 3 Aug 2023 17:26:50 +0200 Subject: selftests: net: test vxlan pmtu exceptions with tcp TCP might get stuck if a nonlinear skb exceeds the path MTU, icmp error contains an incorrect icmp checksum in that case. Extend the existing test for vxlan to also send at least 1MB worth of data via TCP in addition to the existing 'large icmp packet adds route exception'. On my test VM this fails due to 0-size output file without "tunnels: fix kasan splat when generating ipv4 pmtu error". Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230803152653.29535-3-fw@strlen.de Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/pmtu.sh | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index dfe3d287f01d..f838dd370f6a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -361,6 +361,7 @@ err_buf= tcpdump_pids= nettest_pids= socat_pids= +tmpoutfile= err() { err_buf="${err_buf}${1} @@ -951,6 +952,7 @@ cleanup() { ip link del veth_A-R1 2>/dev/null ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null + rm -f "$tmpoutfile" } mtu() { @@ -1328,6 +1330,39 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" + + tmpoutfile=$(mktemp) + + # Flush Exceptions, retry with TCP + run_cmd ${ns_a} ip route flush cached ${dst} + run_cmd ${ns_b} ip route flush cached ${dst} + run_cmd ${ns_c} ip route flush cached ${dst} + + for target in "${ns_a}" "${ns_c}" ; do + if [ ${family} -eq 4 ]; then + TCPDST=TCP:${dst}:50000 + else + TCPDST="TCP:[${dst}]:50000" + fi + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + + sleep 1 + + dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + + size=$(du -sb $tmpoutfile) + size=${size%%/tmp/*} + + [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + done + + rm -f "$tmpoutfile" + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp: exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp exceeding link layer MTU on locally bridged ${type} interface" } test_pmtu_ipv4_br_vxlan4_exception() { -- cgit v1.2.3 From aaf2123a5cf46dbd97f84b6eee80269758064d93 Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Thu, 3 Aug 2023 18:27:27 +0200 Subject: selftests: mptcp: join: fix 'delete and re-add' test mptcp_join 'delete and re-add' test fails when using ip mptcp: $ ./mptcp_join.sh -iI 002 delete and re-add before delete[ ok ] mptcp_info subflows=1 [ ok ] Error: argument "ADDRESS" is wrong: invalid for non-zero id address after delete[fail] got 2:2 subflows expected 1 This happens because endpoint delete includes an ip address while id is not 0, contrary to what is indicated in the ip mptcp man page: "When used with the delete id operation, an IFADDR is only included when the ID is 0." This fixes the issue using the $addr variable in pm_nl_del_endpoint() only when id is 0. Fixes: 34aa6e3bccd8 ("selftests: mptcp: add ip mptcp wrappers") Cc: stable@vger.kernel.org Signed-off-by: Andrea Claudi Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-1-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c2096ac97ef..067fabc401f1 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -705,6 +705,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr -- cgit v1.2.3 From c8c101ae390a3e817369e94a6f12a1ddea420702 Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Thu, 3 Aug 2023 18:27:28 +0200 Subject: selftests: mptcp: join: fix 'implicit EP' test mptcp_join 'implicit EP' test currently fails when using ip mptcp: $ ./mptcp_join.sh -iI 001 implicit EP creation[fail] expected '10.0.2.2 10.0.2.2 id 1 implicit' found '10.0.2.2 id 1 rawflags 10 ' Error: too many addresses or duplicate one: -22. ID change is prevented[fail] expected '10.0.2.2 10.0.2.2 id 1 implicit' found '10.0.2.2 id 1 rawflags 10 ' modif is allowed[fail] expected '10.0.2.2 10.0.2.2 id 1 signal' found '10.0.2.2 id 1 signal ' This happens because of two reasons: - iproute v6.3.0 does not support the implicit flag, fixed with iproute2-next commit 3a2535a41854 ("mptcp: add support for implicit flag") - pm_nl_check_endpoint wrongly expects the ip address to be repeated two times in iproute output, and does not account for a final whitespace in it. This fixes the issue trimming the whitespace in the output string and removing the double address in the expected string. Fixes: 69c6ce7b6eca ("selftests: mptcp: add implicit endpoint test case") Cc: stable@vger.kernel.org Signed-off-by: Andrea Claudi Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-2-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 067fabc401f1..d01b73a8ed0f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -796,10 +796,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" -- cgit v1.2.3 From 913f60cacda73ccac8eead94983e5884c03e04cd Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 10:52:31 +0300 Subject: nexthop: Fix infinite nexthop dump when using maximum nexthop ID A netlink dump callback can return a positive number to signal that more information needs to be dumped or zero to signal that the dump is complete. In the second case, the core netlink code will append the NLMSG_DONE message to the skb in order to indicate to user space that the dump is complete. The nexthop dump callback always returns a positive number if nexthops were filled in the provided skb, even if the dump is complete. This means that a dump will span at least two recvmsg() calls as long as nexthops are present. In the last recvmsg() call the dump callback will not fill in any nexthops because the previous call indicated that the dump should restart from the last dumped nexthop ID plus one. # ip nexthop add id 1 blackhole # strace -e sendto,recvmsg -s 5 ip nexthop sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOP, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691394315, nlmsg_pid=0}, {nh_family=AF_UNSPEC, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 36 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[{nlmsg_len=36, nlmsg_type=RTM_NEWNEXTHOP, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394315, nlmsg_pid=343}, {nh_family=AF_INET, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}, [[{nla_len=8, nla_type=NHA_ID}, 1], {nla_len=4, nla_type=NHA_BLACKHOLE}]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 36 id 1 blackhole recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 20 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394315, nlmsg_pid=343}, 0], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 20 +++ exited with 0 +++ This behavior is both inefficient and buggy. If the last nexthop to be dumped had the maximum ID of 0xffffffff, then the dump will restart from 0 (0xffffffff + 1) and never end: # ip nexthop add id $((2**32-1)) blackhole # ip nexthop id 4294967295 blackhole id 4294967295 blackhole [...] Fix by adjusting the dump callback to return zero when the dump is complete. After the fix only one recvmsg() call is made and the NLMSG_DONE message is appended to the RTM_NEWNEXTHOP response: # ip nexthop add id $((2**32-1)) blackhole # strace -e sendto,recvmsg -s 5 ip nexthop sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOP, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691394080, nlmsg_pid=0}, {nh_family=AF_UNSPEC, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 56 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[[{nlmsg_len=36, nlmsg_type=RTM_NEWNEXTHOP, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394080, nlmsg_pid=342}, {nh_family=AF_INET, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}, [[{nla_len=8, nla_type=NHA_ID}, 4294967295], {nla_len=4, nla_type=NHA_BLACKHOLE}]], [{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394080, nlmsg_pid=342}, 0]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 56 id 4294967295 blackhole +++ exited with 0 +++ Note that if the NLMSG_DONE message cannot be appended because of size limitations, then another recvmsg() will be needed, but the core netlink code will not invoke the dump callback and simply reply with a NLMSG_DONE message since it knows that the callback previously returned zero. Add a test that fails before the fix: # ./fib_nexthops.sh -t basic [...] TEST: Maximum nexthop ID dump [FAIL] [...] And passes after it: # ./fib_nexthops.sh -t basic [...] TEST: Maximum nexthop ID dump [ OK ] [...] Fixes: ab84be7e54fc ("net: Initial nexthop code") Reported-by: Petr Machata Closes: https://lore.kernel.org/netdev/87sf91enuf.fsf@nvidia.com/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230808075233.3337922-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 6 +----- tools/testing/selftests/net/fib_nexthops.sh | 5 +++++ 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'tools/testing') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f95142e56da0..179e50d8fe07 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0f5e88c8f4ff..10aa059b9f06 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1981,6 +1981,11 @@ basic() run_cmd "$IP link set dev lo up" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) blackhole" + run_cmd "timeout 5 $IP nexthop" + log_test $? 0 "Maximum nexthop ID dump" + # # groups # -- cgit v1.2.3 From 8743aeff5bc4dcb5b87b43765f48d5ac3ad7dd9f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 10:52:33 +0300 Subject: nexthop: Fix infinite nexthop bucket dump when using maximum nexthop ID A netlink dump callback can return a positive number to signal that more information needs to be dumped or zero to signal that the dump is complete. In the second case, the core netlink code will append the NLMSG_DONE message to the skb in order to indicate to user space that the dump is complete. The nexthop bucket dump callback always returns a positive number if nexthop buckets were filled in the provided skb, even if the dump is complete. This means that a dump will span at least two recvmsg() calls as long as nexthop buckets are present. In the last recvmsg() call the dump callback will not fill in any nexthop buckets because the previous call indicated that the dump should restart from the last dumped nexthop ID plus one. # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id 10 group 1 type resilient buckets 2 # strace -e sendto,recvmsg -s 5 ip nexthop bucket sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOPBUCKET, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691396980, nlmsg_pid=0}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 128 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[[{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396980, nlmsg_pid=347}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], [{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396980, nlmsg_pid=347}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 128 id 10 index 0 idle_time 6.66 nhid 1 id 10 index 1 idle_time 6.66 nhid 1 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 20 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396980, nlmsg_pid=347}, 0], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 20 +++ exited with 0 +++ This behavior is both inefficient and buggy. If the last nexthop to be dumped had the maximum ID of 0xffffffff, then the dump will restart from 0 (0xffffffff + 1) and never end: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id $((2**32-1)) group 1 type resilient buckets 2 # ip nexthop bucket id 4294967295 index 0 idle_time 5.55 nhid 1 id 4294967295 index 1 idle_time 5.55 nhid 1 id 4294967295 index 0 idle_time 5.55 nhid 1 id 4294967295 index 1 idle_time 5.55 nhid 1 [...] Fix by adjusting the dump callback to return zero when the dump is complete. After the fix only one recvmsg() call is made and the NLMSG_DONE message is appended to the RTM_NEWNEXTHOPBUCKET responses: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id $((2**32-1)) group 1 type resilient buckets 2 # strace -e sendto,recvmsg -s 5 ip nexthop bucket sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOPBUCKET, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691396737, nlmsg_pid=0}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 148 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[[{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396737, nlmsg_pid=350}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], [{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396737, nlmsg_pid=350}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], [{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396737, nlmsg_pid=350}, 0]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 148 id 4294967295 index 0 idle_time 6.61 nhid 1 id 4294967295 index 1 idle_time 6.61 nhid 1 +++ exited with 0 +++ Note that if the NLMSG_DONE message cannot be appended because of size limitations, then another recvmsg() will be needed, but the core netlink code will not invoke the dump callback and simply reply with a NLMSG_DONE message since it knows that the callback previously returned zero. Add a test that fails before the fix: # ./fib_nexthops.sh -t basic_res [...] TEST: Maximum nexthop ID dump [FAIL] [...] And passes after it: # ./fib_nexthops.sh -t basic_res [...] TEST: Maximum nexthop ID dump [ OK ] [...] Fixes: 8a1bbabb034d ("nexthop: Add netlink handlers for bucket dump") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230808075233.3337922-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 6 +----- tools/testing/selftests/net/fib_nexthops.sh | 5 +++++ 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'tools/testing') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f365a4f63899..be5498f5dd31 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3424,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 10aa059b9f06..df8d90b51867 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2206,6 +2206,11 @@ basic_res() run_cmd "$IP nexthop bucket list fdb" log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) group 1/2 type resilient buckets 4" + run_cmd "timeout 5 $IP nexthop bucket" + log_test $? 0 "Maximum nexthop ID dump" + # # resilient nexthop buckets get requests # -- cgit v1.2.3 From d72c83b1e4b4a36a38269c77a85ff52f95eb0d08 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:47 +0300 Subject: selftests: forwarding: Skip test when no interfaces are specified As explained in [1], the forwarding selftests are meant to be run with either physical loopbacks or veth pairs. The interfaces are expected to be specified in a user-provided forwarding.config file or as command line arguments. By default, this file is not present and the tests fail: # make -C tools/testing/selftests TARGETS=net/forwarding run_tests [...] TAP version 13 1..102 # timeout set to 45 # selftests: net/forwarding: bridge_igmp.sh # Command line is not complete. Try option "help" # Failed to create netif not ok 1 selftests: net/forwarding: bridge_igmp.sh # exit=1 [...] Fix by skipping a test if interfaces are not provided either via the configuration file or command line arguments. # make -C tools/testing/selftests TARGETS=net/forwarding run_tests [...] TAP version 13 1..102 # timeout set to 45 # selftests: net/forwarding: bridge_igmp.sh # SKIP: Cannot create interface. Name not specified ok 1 selftests: net/forwarding: bridge_igmp.sh # SKIP [1] tools/testing/selftests/net/forwarding/README Fixes: 81573b18f26d ("selftests/net/forwarding: add Makefile to install tests") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/856d454e-f83c-20cf-e166-6dc06cbc1543@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/lib.sh | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9ddb68dd6a08..975fc5168c63 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -225,6 +225,11 @@ create_netif_veth() for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) + if [ -z ${NETIFS[p$i]} ]; then + echo "SKIP: Cannot create interface. Name not specified" + exit $ksft_skip + fi + ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then ip link add ${NETIFS[p$i]} type veth \ -- cgit v1.2.3 From 0529883ad102f6c04e19fb7018f31e1bda575bbe Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:48 +0300 Subject: selftests: forwarding: Switch off timeout The default timeout for selftests is 45 seconds, but it is not enough for forwarding selftests which can takes minutes to finish depending on the number of tests cases: # make -C tools/testing/selftests TARGETS=net/forwarding run_tests TAP version 13 1..102 # timeout set to 45 # selftests: net/forwarding: bridge_igmp.sh # TEST: IGMPv2 report 239.10.10.10 [ OK ] # TEST: IGMPv2 leave 239.10.10.10 [ OK ] # TEST: IGMPv3 report 239.10.10.10 is_include [ OK ] # TEST: IGMPv3 report 239.10.10.10 include -> allow [ OK ] # not ok 1 selftests: net/forwarding: bridge_igmp.sh # TIMEOUT 45 seconds Fix by switching off the timeout and setting it to 0. A similar change was done for BPF selftests in commit 6fc5916cc256 ("selftests: bpf: Switch off timeout"). Fixes: 81573b18f26d ("selftests/net/forwarding: add Makefile to install tests") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/8d149f8c-818e-d141-a0ce-a6bae606bc22@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/settings | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/net/forwarding/settings (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/settings @@ -0,0 +1 @@ +timeout=0 -- cgit v1.2.3 From ab2eda04e2c2116910b9d77ccc82e727efa71d49 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:49 +0300 Subject: selftests: forwarding: bridge_mdb: Check iproute2 version The selftest relies on iproute2 changes present in version 6.3, but the test does not check for it, resulting in error: # ./bridge_mdb.sh INFO: # Host entries configuration tests TEST: Common host entries configuration tests (IPv4) [FAIL] Managed to add IPv4 host entry with a filter mode TEST: Common host entries configuration tests (IPv6) [FAIL] Managed to add IPv6 host entry with a filter mode TEST: Common host entries configuration tests (L2) [FAIL] Managed to add L2 host entry with a filter mode INFO: # Port group entries configuration tests - (*, G) Command "replace" is unknown, try "bridge mdb help". [...] Fix by skipping the test if iproute2 is too old. Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/6b04b2ba-2372-6f6b-3ac8-b7cba1cfae83@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_mdb.sh | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index ae3f9462a2b6..6f830b5f03c9 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -1206,6 +1206,11 @@ ctrl_test() ctrl_mldv2_is_in_test } +if ! bridge mdb help 2>&1 | grep -q "replace"; then + echo "SKIP: iproute2 too old, missing bridge mdb replace support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From 6bdf3d9765f4e0eebfd919e70acc65bce5daa9b9 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:50 +0300 Subject: selftests: forwarding: bridge_mdb_max: Check iproute2 version The selftest relies on iproute2 changes present in version 6.3, but the test does not check for it, resulting in errors: # ./bridge_mdb_max.sh INFO: 802.1d tests TEST: cfg4: port: ngroups reporting [FAIL] Number of groups was null, now is null, but 5 expected TEST: ctl4: port: ngroups reporting [FAIL] Number of groups was null, now is null, but 5 expected TEST: cfg6: port: ngroups reporting [FAIL] Number of groups was null, now is null, but 5 expected [...] Fix by skipping the test if iproute2 is too old. Fixes: 3446dcd7df05 ("selftests: forwarding: bridge_mdb_max: Add a new selftest") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/6b04b2ba-2372-6f6b-3ac8-b7cba1cfae83@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-5-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_mdb_max.sh | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh index ae255b662ba3..fa762b716288 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -1328,6 +1328,11 @@ test_8021qvs() switch_destroy } +if ! bridge link help 2>&1 | grep -q "mcast_max_groups"; then + echo "SKIP: iproute2 too old, missing bridge \"mcast_max_groups\" support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From 38f7c44d6e760a8513557e27340d61b820c91b8f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:51 +0300 Subject: selftests: forwarding: Set default IPv6 traceroute utility The test uses the 'TROUTE6' environment variable to encode the name of the IPv6 traceroute utility. By default (without a configuration file), this variable is not set, resulting in failures: # ./ip6_forward_instats_vrf.sh TEST: ping6 [ OK ] TEST: Ip6InTooBigErrors [ OK ] TEST: Ip6InHdrErrors [FAIL] TEST: Ip6InAddrErrors [ OK ] TEST: Ip6InDiscards [ OK ] Fix by setting a default utility name and skip the test if the utility is not present. Fixes: 0857d6f8c759 ("ipv6: When forwarding count rx stats on the orig netdev") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-6-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh | 2 ++ tools/testing/selftests/net/forwarding/lib.sh | 1 + 2 files changed, 3 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 9f5b3e2e5e95..49fa94b53a1c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -14,6 +14,8 @@ ALL_TESTS=" NUM_NETIFS=4 source lib.sh +require_command $TROUTE6 + h1_create() { simple_if_init $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 975fc5168c63..40a8c1541b7f 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${REQUIRE_MZ:=yes} REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no} STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} +TROUTE6=${TROUTE6:=traceroute6} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then -- cgit v1.2.3 From 66e131861ab7bf754b50813216f5c6885cd32d63 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:52 +0300 Subject: selftests: forwarding: Add a helper to skip test when using veth pairs A handful of tests require physical loopbacks to be used instead of veth pairs. Add a helper that these tests will invoke in order to be skipped when executed with veth pairs. Fixes: 64916b57c0b1 ("selftests: forwarding: Add speed and auto-negotiation test") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-7-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/lib.sh | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 40a8c1541b7f..f69015bf2dea 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -164,6 +164,17 @@ check_port_mab_support() fi } +skip_on_veth() +{ + local kind=$(ip -j -d link show dev ${NETIFS[p1]} | + jq -r '.[].linkinfo.info_kind') + + if [[ $kind == veth ]]; then + echo "SKIP: Test cannot be run with veth pairs" + exit $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip -- cgit v1.2.3 From 60a36e21915c31c0375d9427be9406aa8ce2ec34 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:53 +0300 Subject: selftests: forwarding: ethtool: Skip when using veth pairs Auto-negotiation cannot be tested with veth pairs, resulting in failures: # ./ethtool.sh TEST: force of same speed autoneg off [FAIL] error in configuration. swp1 speed Not autoneg off [...] Fix by skipping the test when used with veth pairs. Fixes: 64916b57c0b1 ("selftests: forwarding: Add speed and auto-negotiation test") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-8-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/ethtool.sh | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index dbb9fcf759e0..aa2eafb7b243 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -286,6 +286,8 @@ different_speeds_autoneg_on() ethtool -s $h1 autoneg on } +skip_on_veth + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From b3d9305e60d121dac20a77b6847c4cf14a4c0001 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:54 +0300 Subject: selftests: forwarding: ethtool_extended_state: Skip when using veth pairs Ethtool extended state cannot be tested with veth pairs, resulting in failures: # ./ethtool_extended_state.sh TEST: Autoneg, No partner detected [FAIL] Expected "Autoneg", got "Link detected: no" [...] Fix by skipping the test when used with veth pairs. Fixes: 7d10bcce98cd ("selftests: forwarding: Add tests for ethtool extended state") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-9-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/ethtool_extended_state.sh | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh index 072faa77f53b..17f89c3b7c02 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -108,6 +108,8 @@ no_cable() ip link set dev $swp3 down } +skip_on_veth + setup_prepare tests_run -- cgit v1.2.3 From 9a711cde07c245a163d95eee5b42ed1871e73236 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:55 +0300 Subject: selftests: forwarding: hw_stats_l3_gre: Skip when using veth pairs Layer 3 hardware stats cannot be used when the underlying interfaces are veth pairs, resulting in failures: # ./hw_stats_l3_gre.sh TEST: ping gre flat [ OK ] TEST: Test rx packets: [FAIL] Traffic not reflected in the counter: 0 -> 0 TEST: Test tx packets: [FAIL] Traffic not reflected in the counter: 0 -> 0 Fix by skipping the test when used with veth pairs. Fixes: 813f97a26860 ("selftests: forwarding: Add a tunnel-based test for L3 HW stats") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-10-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh index eb9ec4a68f84..7594bbb49029 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh @@ -99,6 +99,8 @@ test_stats_rx() test_stats g2a rx } +skip_on_veth + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From 23fb886a1ced6f885ddd541cc86d45c415ce705c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:56 +0300 Subject: selftests: forwarding: ethtool_mm: Skip when MAC Merge is not supported MAC Merge cannot be tested with veth pairs, resulting in failures: # ./ethtool_mm.sh [...] TEST: Manual configuration with verification: swp1 to swp2 [FAIL] Verification did not succeed Fix by skipping the test when the interfaces do not support MAC Merge. Fixes: e6991384ace5 ("selftests: forwarding: add a test for MAC Merge layer") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-11-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/ethtool_mm.sh | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/ethtool_mm.sh b/tools/testing/selftests/net/forwarding/ethtool_mm.sh index c580ad623848..39e736f30322 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_mm.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_mm.sh @@ -258,11 +258,6 @@ h2_destroy() setup_prepare() { - check_ethtool_mm_support - check_tc_fp_support - require_command lldptool - bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" - h1=${NETIFS[p1]} h2=${NETIFS[p2]} @@ -278,6 +273,19 @@ cleanup() h1_destroy } +check_ethtool_mm_support +check_tc_fp_support +require_command lldptool +bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" + +for netif in ${NETIFS[@]}; do + ethtool --show-mm $netif 2>&1 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: $netif does not support MAC Merge" + exit $ksft_skip + fi +done + trap cleanup EXIT setup_prepare -- cgit v1.2.3 From 5e8670610b93158ffacc3241f835454ff26a3469 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:57 +0300 Subject: selftests: forwarding: tc_actions: Use ncat instead of nc The test relies on 'nc' being the netcat version from the nmap project. While this seems to be the case on Fedora, it is not the case on Ubuntu, resulting in failures such as [1]. Fix by explicitly using the 'ncat' utility from the nmap project and the skip the test in case it is not installed. [1] # timeout set to 0 # selftests: net/forwarding: tc_actions.sh # TEST: gact drop and ok (skip_hw) [ OK ] # TEST: mirred egress flower redirect (skip_hw) [ OK ] # TEST: mirred egress flower mirror (skip_hw) [ OK ] # TEST: mirred egress matchall mirror (skip_hw) [ OK ] # TEST: mirred_egress_to_ingress (skip_hw) [ OK ] # nc: invalid option -- '-' # usage: nc [-46CDdFhklNnrStUuvZz] [-I length] [-i interval] [-M ttl] # [-m minttl] [-O length] [-P proxy_username] [-p source_port] # [-q seconds] [-s sourceaddr] [-T keyword] [-V rtable] [-W recvlimit] # [-w timeout] [-X proxy_protocol] [-x proxy_address[:port]] # [destination] [port] # nc: invalid option -- '-' # usage: nc [-46CDdFhklNnrStUuvZz] [-I length] [-i interval] [-M ttl] # [-m minttl] [-O length] [-P proxy_username] [-p source_port] # [-q seconds] [-s sourceaddr] [-T keyword] [-V rtable] [-W recvlimit] # [-w timeout] [-X proxy_protocol] [-x proxy_address[:port]] # [destination] [port] # TEST: mirred_egress_to_ingress_tcp (skip_hw) [FAIL] # server output check failed # INFO: Could not test offloaded functionality not ok 80 selftests: net/forwarding: tc_actions.sh # exit=1 Fixes: ca22da2fbd69 ("act_mirred: use the backlog for nested calls to mirred ingress") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-12-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/tc_actions.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index a96cff8e7219..b0f5e55d2d0b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -9,6 +9,8 @@ NUM_NETIFS=4 source tc_common.sh source lib.sh +require_command ncat + tcflags="skip_hw" h1_create() @@ -220,9 +222,9 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" -- cgit v1.2.3 From 9ee37e53e7687654b487fc94e82569377272a7a8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:58 +0300 Subject: selftests: forwarding: tc_flower: Relax success criterion The test checks that filters that match on source or destination MAC were only hit once. A host can send more than one packet with a given source or destination MAC, resulting in failures. Fix by relaxing the success criterion and instead check that the filters were not hit zero times. Using tc_check_at_least_x_packets() is also an option, but it is not available in older kernels. Fixes: 07e5c75184a1 ("selftests: forwarding: Introduce tc flower matching tests") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-13-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/tc_flower.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 683711f41aa9..b1daad19b01e 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -52,8 +52,8 @@ match_dst_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower @@ -78,8 +78,8 @@ match_src_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower -- cgit v1.2.3 From 11604178fdc3404d46518e5332f1fe865d30c4a1 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:59 +0300 Subject: selftests: forwarding: tc_tunnel_key: Make filters more specific The test installs filters that match on various IP fragments (e.g., no fragment, first fragment) and expects a certain amount of packets to hit each filter. This is problematic as the filters are not specific enough and can match IP packets (e.g., IGMP) generated by the stack, resulting in failures [1]. Fix by making the filters more specific and match on more fields in the IP header: Source IP, destination IP and protocol. [1] # timeout set to 0 # selftests: net/forwarding: tc_tunnel_key.sh # TEST: tunnel_key nofrag (skip_hw) [FAIL] # packet smaller than MTU was not tunneled # INFO: Could not test offloaded functionality not ok 89 selftests: net/forwarding: tc_tunnel_key.sh # exit=1 Fixes: 533a89b1940f ("selftests: forwarding: add tunnel_key "nofrag" test case") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Acked-by: Davide Caratti Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-14-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/tc_tunnel_key.sh | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh index 5ac184d51809..5a5dd9034819 100755 --- a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh +++ b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh @@ -104,11 +104,14 @@ tunnel_key_nofrag_test() local i tc filter add dev $swp1 ingress protocol ip pref 100 handle 100 \ - flower ip_flags nofrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofrag action drop tc filter add dev $swp1 ingress protocol ip pref 101 handle 101 \ - flower ip_flags firstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags firstfrag action drop tc filter add dev $swp1 ingress protocol ip pref 102 handle 102 \ - flower ip_flags nofirstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofirstfrag action drop # test 'nofrag' set tc filter add dev h1-et egress protocol all pref 1 handle 1 matchall $tcflags \ -- cgit v1.2.3 From 21a72166abb9c9d13fe24a07cef0a0b9f1e331b0 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:15:00 +0300 Subject: selftests: forwarding: tc_flower_l2_miss: Fix failing test with old libnet As explained in commit 8bcfb4ae4d97 ("selftests: forwarding: Fix failing tests with old libnet"), old versions of libnet (used by mausezahn) do not use the "SO_BINDTODEVICE" socket option. For IP unicast packets, this can be solved by prefixing mausezahn invocations with "ip vrf exec". However, IP multicast packets do not perform routing and simply egress the bound device, which does not exist in this case. Fix by specifying the source and destination MAC of the packet which will cause mausezahn to use a packet socket instead of an IP socket. Fixes: 8c33266ae26a ("selftests: forwarding: Add layer 2 miss test cases") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-15-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index e22c2d28b6eb..20a7cb7222b8 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -127,6 +127,7 @@ test_l2_miss_multicast_common() local proto=$1; shift local sip=$1; shift local dip=$1; shift + local dmac=$1; shift local mode=$1; shift local name=$1; shift @@ -142,7 +143,7 @@ test_l2_miss_multicast_common() action pass # Before adding MDB entry. - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was not hit before adding MDB entry" @@ -153,7 +154,7 @@ test_l2_miss_multicast_common() # Adding MDB entry. bridge mdb replace dev br1 port $swp2 grp $dip permanent - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was hit after adding MDB entry" @@ -164,7 +165,7 @@ test_l2_miss_multicast_common() # Deleting MDB entry. bridge mdb del dev br1 port $swp2 grp $dip - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 2 check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" @@ -183,10 +184,11 @@ test_l2_miss_multicast_ipv4() local proto="ipv4" local sip=192.0.2.1 local dip=239.1.1.1 + local dmac=01:00:5e:01:01:01 local mode="-4" local name="IPv4" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast_ipv6() @@ -194,10 +196,11 @@ test_l2_miss_multicast_ipv6() local proto="ipv6" local sip=2001:db8:1::1 local dip=ff0e::1 + local dmac=33:33:00:00:00:01 local mode="-6" local name="IPv6" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast() -- cgit v1.2.3 From e98e195d90cc93b1bf2ad762c7c274a40dab7173 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:15:01 +0300 Subject: selftests: forwarding: bridge_mdb: Fix failing test with old libnet As explained in commit 8bcfb4ae4d97 ("selftests: forwarding: Fix failing tests with old libnet"), old versions of libnet (used by mausezahn) do not use the "SO_BINDTODEVICE" socket option. For IP unicast packets, this can be solved by prefixing mausezahn invocations with "ip vrf exec". However, IP multicast packets do not perform routing and simply egress the bound device, which does not exist in this case. Fix by specifying the source and destination MAC of the packet which will cause mausezahn to use a packet socket instead of an IP socket. Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-16-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/forwarding/bridge_mdb.sh | 46 +++++++++++----------- 1 file changed, 24 insertions(+), 22 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 6f830b5f03c9..4853b8e4f8d3 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -850,6 +850,7 @@ cfg_test() __fwd_test_host_ip() { local grp=$1; shift + local dmac=$1; shift local src=$1; shift local mode=$1; shift local name @@ -872,27 +873,27 @@ __fwd_test_host_ip() # Packet should only be flooded to multicast router ports when there is # no matching MDB entry. The bridge is not configured as a multicast # router port. - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after flood" # Install a regular port group entry and expect the packet to not be # locally received. bridge mdb add dev br0 port $swp2 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after installing a regular entry" # Add a host entry and expect the packet to be locally received. bridge mdb add dev br0 port br0 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet not locally received after adding a host entry" # Remove the host entry and expect the packet to not be locally # received. bridge mdb del dev br0 port br0 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet locally received after removing a host entry" @@ -905,8 +906,8 @@ __fwd_test_host_ip() fwd_test_host_ip() { - __fwd_test_host_ip "239.1.1.1" "192.0.2.1" "-4" - __fwd_test_host_ip "ff0e::1" "2001:db8:1::1" "-6" + __fwd_test_host_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "-4" + __fwd_test_host_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "-6" } fwd_test_host_l2() @@ -966,6 +967,7 @@ fwd_test_host() __fwd_test_port_ip() { local grp=$1; shift + local dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mode=$1; shift @@ -999,43 +1001,43 @@ __fwd_test_port_ip() vlan_ethtype $eth_type vlan_id 10 dst_ip $grp \ src_ip $invalid_src action drop - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 0 check_err $? "Packet from valid source received on H2 before adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 before adding entry" bridge mdb add dev br0 port $swp2 grp $grp vid 10 \ filter_mode $filter_mode source_list $src_list - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 1 check_err $? "Packet from valid source not received on H2 after adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 after adding entry" bridge mdb replace dev br0 port $swp2 grp $grp vid 10 \ filter_mode exclude - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source not received on H2 after allowing all sources" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source not received on H2 after allowing all sources" bridge mdb del dev br0 port $swp2 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source received on H2 after deleting entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source received on H2 after deleting entry" @@ -1047,11 +1049,11 @@ __fwd_test_port_ip() fwd_test_port_ip() { - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "exclude" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "exclude" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "exclude" - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "include" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "include" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "include" } @@ -1127,7 +1129,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -c 1 -a own -b 01:00:5e:01:01:01 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 @@ -1140,7 +1142,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -a own -b 01:00:5e:01:01:01 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ @@ -1167,7 +1169,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ @@ -1181,7 +1183,7 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ -- cgit v1.2.3 From cb034948ac292da82cc0e6bc1340f81be36e117d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:15:02 +0300 Subject: selftests: forwarding: bridge_mdb_max: Fix failing test with old libnet As explained in commit 8bcfb4ae4d97 ("selftests: forwarding: Fix failing tests with old libnet"), old versions of libnet (used by mausezahn) do not use the "SO_BINDTODEVICE" socket option. For IP unicast packets, this can be solved by prefixing mausezahn invocations with "ip vrf exec". However, IP multicast packets do not perform routing and simply egress the bound device, which does not exist in this case. Fix by specifying the source and destination MAC of the packet which will cause mausezahn to use a packet socket instead of an IP socket. Fixes: 3446dcd7df05 ("selftests: forwarding: bridge_mdb_max: Add a new selftest") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-17-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_mdb_max.sh | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh index fa762b716288..3da9d93ab36f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -252,7 +252,8 @@ ctl4_entries_add() local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + local dmac=01:00:5e:01:01:$(printf "%02x" $grp) + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B $GRP \ -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q sleep 1 @@ -272,7 +273,8 @@ ctl4_entries_del() local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + local dmac=01:00:5e:00:00:02 + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B 224.0.0.2 \ -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP @@ -289,8 +291,10 @@ ctl6_entries_add() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv2_is_in_get $SIP $GRP $IPs) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) @@ -310,8 +314,10 @@ ctl6_entries_del() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv1_done_get $SIP $GRP) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP } -- cgit v1.2.3 From 8b5ff37097775cdbd447442603957066dd2e4d02 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:15:03 +0300 Subject: selftests: forwarding: bridge_mdb: Make test more robust Some test cases check that the group timer is (or isn't) 0. Instead of grepping for "0.00" grep for " 0.00" as the former can also match "260.00" which is the default group membership interval. Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-18-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/bridge_mdb.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 4853b8e4f8d3..d0c6c499d5da 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -617,7 +617,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not added as \"permanent\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "\"permanent\" entry has a pending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -626,7 +626,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not added as \"temp\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "\"temp\" entry has an unpending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -659,7 +659,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not marked as \"permanent\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "Entry has a pending group timer after replace" bridge mdb replace dev br0 port $swp1 $grp_key vid 10 temp @@ -667,7 +667,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not marked as \"temp\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "Entry has an unpending group timer after replace" bridge mdb del dev br0 port $swp1 $grp_key vid 10 -- cgit v1.2.3 From 90f0074cd9f9a24b7b6c4d5afffa676aee48c0e9 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 4 Aug 2023 03:37:39 -0400 Subject: selftests/bpf: fix a CI failure caused by vsock sockmap test BPF CI has reported the following failure: Error: #200/79 sockmap_listen/sockmap VSOCK test_vsock_redir Error: #200/79 sockmap_listen/sockmap VSOCK test_vsock_redir ./test_progs:vsock_unix_redir_connectible:1506: egress: write: Transport endpoint is not connected vsock_unix_redir_connectible:FAIL:1506 ./test_progs:vsock_unix_redir_connectible:1506: ingress: write: Transport endpoint is not connected vsock_unix_redir_connectible:FAIL:1506 ./test_progs:vsock_unix_redir_connectible:1506: egress: write: Transport endpoint is not connected vsock_unix_redir_connectible:FAIL:1506 ./test_progs:vsock_unix_redir_connectible:1514: ingress: recv() err, errno=11 vsock_unix_redir_connectible:FAIL:1514 ./test_progs:vsock_unix_redir_connectible:1518: ingress: vsock socket map failed, a != b vsock_unix_redir_connectible:FAIL:1518 ./test_progs:vsock_unix_redir_connectible:1525: ingress: want pass count 1, have 0 It’s because the recv(... MSG_DONTWAIT) syscall in the test case is called before the queued work sk_psock_backlog() in the kernel finishes executing. So the data to be read is still queued in psock->ingress_skb and cannot be read by the user program. Therefore, the non-blocking recv() reads nothing and reports an EAGAIN error. So replace recv(... MSG_DONTWAIT) with xrecv_nonblock(), which calls select() to wait for data to be readable or timeout before calls recv(). Fixes: d61bd8c1fd02 ("selftests/bpf: add a test case for vsock sockmap") Signed-off-by: Xu Kuohai Link: https://lore.kernel.org/r/20230804073740.194770-4-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau --- tools/testing/selftests/bpf/prog_tests/sockmap_listen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index b4f6f3a50ae5..ba35bcc66e7e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1432,7 +1432,7 @@ static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd, if (n < 1) goto out; - n = recv(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), MSG_DONTWAIT); + n = xrecv_nonblock(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), 0); if (n < 0) FAIL("%s: recv() err, errno=%d", log_prefix, errno); if (n == 0) -- cgit v1.2.3 From a4b7193d8efdfde1ea89fe34e921ad031f79f993 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 4 Aug 2023 03:37:40 -0400 Subject: selftests/bpf: Add sockmap test for redirecting partial skb data Add a test case to check whether sockmap redirection works correctly when data length returned by stream_parser is less than skb->len. In addition, this test checks whether strp_done is called correctly. The reason is that we returns skb->len - 1 from the stream_parser, so the last byte in the skb will be held by strp->skb_head. Therefore, if strp_done is not called to free strp->skb_head, we'll get a memleak warning. Signed-off-by: Xu Kuohai Link: https://lore.kernel.org/r/20230804073740.194770-5-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau --- .../selftests/bpf/prog_tests/sockmap_listen.c | 72 ++++++++++++++++++++++ .../selftests/bpf/progs/test_sockmap_listen.c | 14 +++++ 2 files changed, 86 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index ba35bcc66e7e..5674a9d0cacf 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -869,6 +869,77 @@ static void test_msg_redir_to_listening(struct test_sockmap_listen *skel, xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT); } +static void redir_partial(int family, int sotype, int sock_map, int parser_map) +{ + int s, c0, c1, p0, p1; + int err, n, key, value; + char buf[] = "abc"; + + key = 0; + value = sizeof(buf) - 1; + err = xbpf_map_update_elem(parser_map, &key, &value, 0); + if (err) + return; + + s = socket_loopback(family, sotype | SOCK_NONBLOCK); + if (s < 0) + goto clean_parser_map; + + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); + if (err) + goto close_srv; + + err = add_to_sockmap(sock_map, p0, p1); + if (err) + goto close; + + n = xsend(c1, buf, sizeof(buf), 0); + if (n < sizeof(buf)) + FAIL("incomplete write"); + + n = xrecv_nonblock(c0, buf, sizeof(buf), 0); + if (n != sizeof(buf) - 1) + FAIL("expect %zu, received %d", sizeof(buf) - 1, n); + +close: + xclose(c0); + xclose(p0); + xclose(c1); + xclose(p1); +close_srv: + xclose(s); + +clean_parser_map: + key = 0; + value = 0; + xbpf_map_update_elem(parser_map, &key, &value, 0); +} + +static void test_skb_redir_partial(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_stream_verdict); + int parser = bpf_program__fd(skel->progs.prog_stream_parser); + int parser_map = bpf_map__fd(skel->maps.parser_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (err) + return; + + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) + goto detach; + + redir_partial(family, sotype, sock_map, parser_map); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT); +detach: + xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER); +} + static void test_reuseport_select_listening(int family, int sotype, int sock_map, int verd_map, int reuseport_prog) @@ -1243,6 +1314,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, } tests[] = { TEST(test_skb_redir_to_connected), TEST(test_skb_redir_to_listening), + TEST(test_skb_redir_partial), TEST(test_msg_redir_to_connected), TEST(test_msg_redir_to_listening), }; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index 325c9f193432..464d35bd57c7 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -28,12 +28,26 @@ struct { __type(value, unsigned int); } verdict_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} parser_map SEC(".maps"); + bool test_sockmap = false; /* toggled by user-space */ bool test_ingress = false; /* toggled by user-space */ SEC("sk_skb/stream_parser") int prog_stream_parser(struct __sk_buff *skb) { + int *value; + __u32 key = 0; + + value = bpf_map_lookup_elem(&parser_map, &key); + if (value && *value) + return *value; + return skb->len; } -- cgit v1.2.3